Search

This paper proposes a leader–follower control method for multiple snake robot formation. Based on the simplified snake robot model, this work improves the traditional Serpenoid gait mode to a time-varying frequency form. Combined with the line-of-sight (LOS) method, a snake robot trajectory tracking controller is designed to enable the leader to track the desired trajectory at the ideal velocity. Then, the leader–follower following error system of a snake robot formation is established. In this framework, the follower can maintain a preset geometric position relationship with the leader to ensure the fast convergence of the formation location. Lyapunov's theory proves the stability of a snake robot formation error. Simulation and experimental results show that this strategy has the advantages of faster convergence speed and higher tracking accuracy than other current methods. • Based on a simplified snake robot model, a time-varying Serpenoid gait curve is proposed to control speed in real-time and solve traditional gait inefficiency. • This work presents the design of a snake robot trajectory tracker using LOS guidance and a time-varying Serpenoid gait, enabling the body can track the reference trajectory in accordance with the desired time-varying velocity. • A snake robot formation controller is designed based on the leader-follower idea so that the geometric position relationship between the robot follower and the leader can be maintained and converged to the formation position. [ABSTRACT FROM AUTHOR]

One of the most significant advantages of Model Predictive Control (MPC) is its ability to explicitly incorporate system constraints and actuator specifications. However, a major drawback is the computational cost associated with calculating the optimal control sequence at each sampling time, posing a substantial challenge for real-time implementation in high-order systems with fast dynamics. Additionally, uncertainties are inherently present in dynamic systems, requiring a robust formulation that accounts for these uncertainties. Additionally, uncertainties are inherently present in dynamic systems, requiring a robust formulation that accounts for these uncertainties. The tube-based MPC is one of the robustification formulations that can tackle these challenges. We propose a comprehensive methodology for designing a tube-based MPC framework specifically tailored for high-order Linear Parameter-Varying (LPV) systems with fast dynamics, along with its real-time implementation in embedded systems. Our innovations include the use of zonotopes for the offline computation of reachable sets, significantly reducing computational costs, and the development of new Linear Matrix Inequality (LMI) conditions that ensure the existence of nominal control and state sets. Additionally, we introduce a novel scaled-symmetric ADMM-based optimization algorithm, which diverges from conventional quadratic programming structures and integrates acceleration strategies and normalization techniques for enhanced numerical robustness and rapid convergence. The methodology is validated on a tiltrotor UAV with a suspended load, demonstrating its effectiveness in a trajectory tracking problem. Experimental results using a controller-in-the-loop (CIL) framework with a high-fidelity 3D simulator confirm its suitability for real-time control in practical scenarios. • A tube-based MPC approach for high-order LPV systems with fast dynamics. • A novel tube-based MPC designed for fast execution in embedded systems. • A zonotope-based formulation to compute the reachable sets for LPV systems • LMI conditions to obtain feedback gains, ensuring nominal control and state set existence • New LMI conditions for feedback gain computation, ensuring nominal set existence • Validation using CHIL and a 3D CAD-based simulator for a tiltrotor UAV. [ABSTRACT FROM AUTHOR]

Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Compared with traditional adaptive algorithms, the complex and changing operating environment of intelligent networks demands high real-time accuracy in data transmission, necessitating an accurate and adaptive traffic light control strategy. Machine learning (ML) techniques can predict traffic conditions based on historical data and real-time information. However, some scholars have mentioned that ML techniques are still deficient in real-time response and in coping with random traffic accidents. Traditional Reinforcement Learning (RL) requires repeated trial and error operations. Applying traditional RL techniques to the optimal control of traffic lights may lead to more serious traffic congestion in some cases. Therefore, this paper combines perceptual control with real-time adaptive control methods to provide a rule-based reasoning method for adaptive intelligent perception and precise control of traffic signals under real-time smart grid-connected hybrid vehicle conditions. IIoT (Industrial Internet of Things) devices are utilized to monitor the parking queue length, pedestrian flow, vehicle flow, and traffic flow in each lane in real time to dynamically adjust the green light duration. By adjusting the light priority according to real-time vehicle and road conditions, this method solves the problem of wasting green lights when random accidents occur in a certain lane, optimizes traffic light settings, achieves real-time precise control of lane flow, and improves the adaptability and precision of traffic lights. [ABSTRACT FROM AUTHOR]

During the batch process, the need for security control is becoming increasingly urgent with the gradual penetration of network control technology. For small time delay batch processes subject to deception attacks, an iterative learning robust security predictive tracking control approach is developed. Reviewing previous studies for iterative learning control, the issue that the repetitive character of the batch process would mask the characteristics of deception attacks was not considered. Moreover, the gains of iterative learning control law are utilized offline, which makes large deviations for the system state as the operating time increases. This will lead to "excessive-input" conditions for control inputs, which means more consumption of energy and production resources. To address these challenges, we introduce robust security invariant sets to improve the robustness of the system by constraining the system state to be in a safe range. Also, the design of the iterative learning controller incorporates deception attack data for historical batches, which is continuously improved and optimized to withstand deception attacks. Meanwhile, by calculating stability conditions online, the real-time control law gain is obtained, which could make the control inputs adjusted online based on the real-time system's dynamic characteristics, avoiding excessive inputs and improving the efficiency of energy and resource utilization. Additionally, the stability analysis proves that the system is input to state stability. Ultimately, simulation verifies the effectiveness and feasibility of the developed method. • An iterative learning robust security predictive control method is proposed for batch processes under deception attacks. • Historical spoofing attack data incorporated into iterative learning controller design. • The online control law gain improves convergence speed along the batch direction by incorporating historical input data. [ABSTRACT FROM AUTHOR]

This paper contributes to the fusion of metaheuristic fuzzy neural network (FNN) and self-tuning autonomous control for omnidirectional mobile platforms in robotic cyber-physical systems (RCPSs). A cyber grey wolf optimization (GWO)-based FNN computing is incorporated with the backstepping control scheme and dynamic modeling to achieve autonomous control for the omnidirectional Mecanum platforms with uncertainties for RCPSs, called GWOFNN. The proposed cyber GWOFNN computing method is employed to address the self-tuning autonomous control problem of RCPS omnidirectional platforms by considering modeling uncertainties and unknown frictions. Numerical simulations and real-time experiments via field-programmable gate array (FPGA) realization are provided to illustrate the efficacy, applicability and merits of the presented RCPS GWOFNN real-time self-tuning cyber control strategy. Through comparison works, the advantages of the proposed GWOFNN computing are validated to accomplish autonomous control for Mecanum mobile RCPSs in polar space. [ABSTRACT FROM AUTHOR]

Robotic arms have become increasingly popular and widely used in various industrial applications. However, conventional control methods are not capable of adequately controlling a robotic arm in tasks that require contact with a surface. To address this issue, this study proposes a Cartesian impedance control method to control a 3-DOF robotic arm in real-time during contact with a surface. The proposed controller consists of two control loops: an inner loop and an outer loop. The inner loop utilizes a motion control method in the joint space, with the parameters of the controller being calculated through system identification. The outer loop implements Cartesian impedance control in the Cartesian space using a mass-spring-damper model. The coefficients of the Cartesian impedance control were determined based on the over-damped response with real-time applications. By selecting the inner loop in the joint space and the outer loop in the Cartesian space, the control of the robotic arm is guaranteed. The proposed method was tested in real-time, and its performance was compared with the PID with gravity compensation control in the Cartesian space. The results indicated that the proposed method was able to successfully follow reference trajectories and reduce the contact force. [ABSTRACT FROM AUTHOR]

A wide range of endeavors has been made to propose various approaches to reduce Greenhouse gas emissions in the agricultural sector. The present study investigates the impacts of Surface Water Distribution Systems (SWDS) modernization in reducing groundwater overexploitation, energy consumption, and carbon emission in the agriculture sector. Four modernization alternatives, including an improved manual-based system (A1, A2), off-line, and real-time automatic control systems (A3, A4), are developed and tested on a real test case in Central Iran, which is confronted with severe water shortages. The results reveal that SWDS's operating system modernization improves 4 ~ 21% surface water distribution through the alternatives A1 ~ A4. This surface water distribution enhancement led to groundwater over-extraction reduction. Spatial analysis reveals that 0.075, 0.100, 0.281, and 0.470 of the irrigation district's cultivated area was thoroughly fulfilled by the delivered surface water and no need for groundwater extraction due to alternatives A1 ~ A4, respectively. Closure of several active tubewells up to 1,668 semi-deep and 497 deep tube-well were verified. SWDS' modernization led to 5, 7, 20, and 30% of energy consumption and consequently 1,864.90, 2,714.33, 8,427.19, and 12,674.32 tC ha-1 carbon emission reduction in alternatives A1 ~ A4, respectively. This study's results show that modernization of off-farm operating systems - responsible for surface water conveyance and distribution from a dam reservoir to farms - resulted in significant environmental benefits through improving the reliability of systems supplied by surface water and reducing the tendency of the farmers to groundwater resources. [ABSTRACT FROM AUTHOR]

The comprehensive performance and user experience of large-scale distributed video conference systems are constrained by network traffic, and conventional network services are difficult to ensure the stability and reliability of the above data transmission activities. This article combines conference video transmission and congestion control related technologies to propose a conference video traffic prediction model based on the large neural network GRU algorithm, and constructs a large-scale distributed video conference transmission congestion control mode on this basis. The simulation experiments on the real-time congestion control model of research results show that it effectively avoids system fluctuations and significantly improves the user experience, providing a feasible method for improving the comprehensive performance of large-scale distributed video conference systems. [ABSTRACT FROM AUTHOR]

IoT techniques have transformative potential across domains, particularly in precision agriculture, where they enable farmers to optimize crop production while minimizing environmental impact. This paper presents an IoT-based real-time monitoring and control system for hydroponic tomato cultivation. The system integrates various hardware components, including sensors for monitoring temperature, humidity, pH levels, and gas concentrations. Arduino microcontrollers collect and process sensor data, enabling automated control of water, nutrient supply, and ventilation. Wi-Fi and GSM modules facilitate remote monitoring and data transmission, empowering farmers to monitor and control their tomato crops remotely. The system has been successfully tested for tomato cultivation, demonstrating promising results. Although tailored for tomatoes, its design principles can be adapted for other crops. Moreover, it shows significant water and nutrient efficiency, highlighting its economic feasibility. [ABSTRACT FROM AUTHOR]

The magnetic levitation (maglev) ball system is a prototypical Single-Input-Single-Output (SISO) system, characterized by its pronounced nonlinearity, rapid response, and open-loop instability. It serves as the basis for many industrial devices. For describing the dynamics of the maglev ball system precisely in the pseudo linear model, the long short-term memory (LSTM) based auto-regressive model with exogenous input variables (LSTM-ARX) is proposed. Firstly, the LSTM network is modified by incorporating the auto-regressive structure with respect to sequence input, allowing it to deduce a locally linearized model without the need for Taylor expansion. Then, the LSTM-ARX model is transformed into a linear parameter varying (LPV) state space model, and upon this foundation, a model predictive controller (MPC) is proposed. Specifically, when deducing the MPC, the deep learning-based model is linearized by fixing its state input at the current state, so that the nonlinear, non-convex optimization problem can be converted to a finite-horizon quadratic programming problem, thereby deriving the explicit form of MPC. To further enhance the efficiency of the controller in real-time control tasks, a predictive functional controller (PFC) is proposed. It employs multiple nonlinear functions to fit the control sequence, thereby reducing the number of decision variables of the on-line optimization problem in MPC. The proposed controller was successfully applied to the real-time control of the maglev ball system. Simulation and real-time control experiments have validated the improvement in transient performance and efficiency of the LSTM-ARX model-based PFC (LSTM-ARX-PFC). • The LSTM-ARX model is proposed, it describes global nonlinearity dynamics and bears pseudo linear structure. • The explicit form of a deep learning based computational efficient MPC is proposed and its stability is proved. • A predictive functional control method is proposed to furtherly facilitate computational efficiency in real-time control. [ABSTRACT FROM AUTHOR]

IoT techniques have transformative potential across domains, particularly in precision agriculture, where they enable farmers to optimize crop production while minimizing environmental impact. This paper presents an IoT-based real-time monitoring and control system for hydroponic tomato cultivation. The system integrates various hardware components, including sensors for monitoring temperature, humidity, pH levels, and gas concentrations. Arduino microcontrollers collect and process sensor data, enabling automated control of water, nutrient supply, and ventilation. Wi-Fi and GSM modules facilitate remote monitoring and data transmission, empowering farmers to monitor and control their tomato crops remotely. The system has been successfully tested for tomato cultivation, demonstrating promising results. Although tailored for tomatoes, its design principles can be adapted for other crops. Moreover, it shows significant water and nutrient efficiency, highlighting its economic feasibility. [ABSTRACT FROM AUTHOR]

Particle Swarm Optimization (PSO) is considered as one of Maximum Power Point Tracking (MPPT) controller algorithm developed for PhotoVoltaic system (PV) to guarantee a maximum power extraction under different climatic conditions of temperature and irradiation. Classical MPPT algorithms like Perturbe and Observe (P&O), PSO, Adaptive Neuro-Fuzzy Inference System (ANFIS) are an effective method for tracking the maximum power point (MPP) for the PV systems, but the problems with these approaches that they are less stable, high oscillation around steady state and slower convergence to the MPP. Based on recent research, the purpose of this paper is to introduces a novel MPPT controller based on a modified version of heterogeneous multi swarm PSO algorithm using an adaptive factor selection strategy (FMSPSO), to overcome the previous shortcomings and compared with conventional PSO, ANFIS and classical P&O controllers. Simulation and experimental results revealed that the new FMSPSO algorithm can overcome the previous shortcomings providing the superior performance to track the MPP efficiently with a shorter convergence time and small oscillations compared to other algorithms. The experimental confirmation of the FMSPSO algorithm has been carried out using NI-myRIO-1900 card and shows that with the proposed MPPT approach efficiency can reach a value greater than 99% even in climatic variation of irradiation and temperature. • A classical MPPT controller cannot track the dynamic the MPP, has obvious oscillations, and converges slowly. • A novel MPPT controller based on a modified version of MSPSO algorithm using an adaptive factor selection strategy (FMSPSO) is proposed. • A FMSPSO based MPPT algorithm is compared with conventional PSO, classical P&O and ANFIS controllers for validation. • The proposed FMSPSO algorithm provides the superior performance by boosting the PV system tracking efficiency more than 99%. [ABSTRACT FROM AUTHOR]

Digital twins and virtual reality are pivotal technologies in the context of Industry 4.0, facilitating the design, simulation, optimization, and remote interaction with production systems. These technologies also present new prospects for developing immersive and hyper-realistic digital factories within the metaverse. This paper aims to enhance collaboration and communication in a 3D virtual world, focusing on shared reality and the metaverse's integration in digital factories. Our main contribution enables users to have full-body immersive interaction with virtual 3D assets and realistic locomotion in a 3D environment, fostering flexibility in collaboration and environment monitoring/control. To achieve this, we propose a systematic methodology for designing and implementing a digital twin-based factory with an IoT infrastructure. By replicating sensors and actuators in digital twins, real-time asset management synchronized with the physical factory is realized, empowering full-body interaction. To enable full-body interaction with virtual equipment, we employ a human motion tracking system. A proof-of-concept case study, developed using Unity3D game engine, Solace PubSub+ event streaming APIs, and Awinda Xsens wearable inertial sensors as the motion tracking system, validates our proposed methodology. The results of the case study demonstrate the successful integration of digital twins, virtual reality, and the metaverse, enabling real-time monitoring and control, full-body interaction, and immersive user experiences in the virtual environment. [ABSTRACT FROM AUTHOR]

Background: Detecting peripheral neuropathy (PNP) is crucial in preventing complications such as foot ulceration. Clinical examinations for PNP are infrequently provided to patients at high risk due to restrictions on facilities, care providers, or time. A gamified health assessment approach combining wearable sensors holds the potential to address these challenges and provide individuals with instantaneous feedback on their health status. Objective: We aimed to develop and evaluate an application that assesses PNP through video games controlled by pressure sensor–equipped insoles. Methods: In the proof-of-concept exploratory cohort study, a complete game-based framework that allowed the study participant to play 4 video games solely by modulating plantar pressure values was established in an outpatient clinic setting. Foot plantar pressures were measured by the sensor-equipped insole and transferred via Bluetooth to an Android tablet for game control in real time. Game results and sensor data were delivered to the study server for visualization and analysis. Each session lasted about 15 minutes. In total, 299 patients with diabetes mellitus and 30 with metabolic syndrome were tested using the game application. Patients' game performance was initially assessed by hypothesis-driven key capabilities that consisted of reaction time, sensation, skillfulness, balance, endurance, and muscle strength. Subsequently, specific game features were extracted from gaming data sets and compared with nerve conduction study findings, neuropathy symptoms, or disability scores. Multiple machine learning algorithms were applied to 70% (n=122) of acquired data to train predictive models for PNP, while the remaining data were held out for final model evaluation. Results: Overall, clinically evident PNP was present in 247 of 329 (75.1%) participants, with 88 (26.7%) individuals showing asymmetric nerve deficits. In a subcohort (n=37) undergoing nerve conduction study as the gold standard, sensory and motor nerve conduction velocities and nerve amplitudes in lower extremities significantly correlated with 79 game features (| R|>0.4, highest R value +0.65; P <.001; adjusted R 2=0.36). Within another subcohort (n=173) with normal cognition and matched covariates (age, sex, BMI, etc), hypothesis-driven key capabilities and specific game features were significantly correlated with the presence of PNP. Predictive models using selected game features achieved 76.1% (left) and 81.7% (right foot) accuracy for PNP detection. Multiclass models yielded an area under the receiver operating characteristic curve of 0.76 (left foot) and 0.72 (right foot) for assessing nerve damage patterns (small, large, or mixed nerve fiber damage). Conclusions: The game-based application presents a promising avenue for PNP screening and classification. Evaluation in expanded cohorts may iteratively optimize artificial intelligence model efficacy. The integration of engaging motivational elements and automated data interpretation will support acceptance as a telemedical application. [ABSTRACT FROM AUTHOR]

Copyright of Ciencia e Ingenieria Neogranadina is the property of Ciencia e Ingenieria Neogranadina and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The wire DED-LB/M AM process is fast, cost-effective and it creates high-quality, dense parts. However, its industrial adoption is limited since process stability needs complex monitoring devices and tools. This work proposes a twofold strategy to resolve this issue; A fast-running, physics-based simulation tool calculates the temperature field during the building of single walls, while, an affordable vision-based monitoring system captures the melt pool dimensions that are correlated to the temperature and reveal heat accumulation. Therefore, real-time process stability control is enabled. An infrared thermal camera is used to validate the model and calibrate the monitoring system. [ABSTRACT FROM AUTHOR]

Computer Vision (CV) provides computers with the ability to perceive, analyze, and understand the content of images and videos. The applications are numerous and range from medical diagnosis to industrial quality control and special effects. CV uses different technologies and techniques to extract relevant information from a large number of images acquired via Machine Vision (MV) components. In industry, CV and MV are combined for trustworthy inspection of high-end products, quality control, and data collection applications. In this article, first, we present the CV and MV with a focus on the convenient artificial intelligence tools that may bused, such as machine & deep learning, and also the common color recognition methods. Second, we consider two industrial applications of artificial vision, especially CV, in real-time quality control to review their scientific valorization based on the primary findings of the studies carried out. Finally, we critically analyzed their findings to identify shortcomings, make recommendations, and open up new horizons for future research. [ABSTRACT FROM AUTHOR]

The article focuses on the challenges in teaching practical distillation control in process control education and introduces a digital-twin-based approach using simulations to enhance understanding. Topics include the difficulties of abstract mathematical teaching methods, the limitations of traditional distillation courses, and the potential benefits of digital-twin-based operator training simulators in continuing education for engineers and operators.

Copyright of DYNA - Ingeniería e Industria is the property of Publicaciones Dyna SL and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Development of new approaches to adaptive traffic signal control has received significant attention; an example is the reinforcement learning (RL), where training and implementation of an RL agent can allow adaptive signal control in real time, considering the agent's past experiences. Furthermore, autonomous vehicle (AV) technology has shown promise to enhancing the traffic mobility at highways and intersections. In this paper, delayed action deep Q-learning is developed for a vehicle network with signalized intersections to control the signal phase. A model predictive control (MPC) scheme is proposed to allow AVs to adapt their speed. Several case studies that consider mixed autonomy are examined aiming at reducing network traffic and fuel consumption in the traffic network with multiple intersections. Simulation studies reveal that even with a few AVs in the network, the waiting time, fuel consumption, and the number of stop-and-go movements are significantly reduced, while the travel time is increased. [ABSTRACT FROM AUTHOR]

In recent years, the hype around Digital Twins (DTs) has been exponentially increasing in both industry and academia. DTs are a potential solution to increase automation and advance towards Smart Manufacturing. Manufacturing DTs have been implemented at different hierarchical levels, ranging from system of systems to unit level. Increasing computational capacity and data exchange rates can enable DT implementations for real-time applications. Several literature reviews on manufacturing DTs have been published. However, no previous paper focuses on manufacturing DTs at the unit level for which real-time control is most applicable. Simultaneously, the challenges to engineer DTs with real-time capabilities are enormous, both from a scientific and technological perspective. Therefore, we focus on DTs of single production units such as traditional machine tools, additive manufacturing machines and advanced robotic applications. In this systematic literature review, 96 papers about practical unit level DT applications found in the Scopus database using a combination of the keywords "Digital Twin", "Production" and "Manufacturing" are reviewed. We summarize how DTs are currently implemented and operated, and what potential benefits DTs offer at the unit process level in four categories: generic reference models, services, DT content (models and data) and DT deployment (hardware and software). Following the thematic analysis, an overall discussion, summary of key contributions and identified research gaps, and outlook into future research avenues is given. Key findings of this review can be summarized as: focus on DT components versus being holistic; need to share data and models across multiple stakeholders; lack of physical fidelity of the models; stark contrast of lab scale developments and real world testing, e.g., historical data and storage related challenges; lack of clear definition of DT in industry, and missing semantic interoperability between a wide variety of domains. [Display omitted] [ABSTRACT FROM AUTHOR]

This paper introduces a novel application of the Long Short-Term Memory (LSTM) recurrent neural network for the identification and control of complex systems. The computation-intensive task of calculating the interaction matrix, a necessity for visual control laws in these systems, makes LSTM a fitting solution. The proposed control law unfolds in two phases: an offline phase, where the LSTM is trained on a set of visual features to generate a kinematic screw vector, and an online phase, where the trained LSTM is utilized for real-time system control. To assess the efficacy of the LSTM-based approach, we undertook a case study involving a manipulator robot, the UR5. We executed a series of simulations under various conditions to illustrate the effectiveness of the proposed LSTM-based control law. The outcomes from these experiments affirm the robustness of the LSTM controller, outperforming traditional methods even when faced with rapid fluctuations in visual features, partial loss of visual information, and model uncertainties in the robot. [ABSTRACT FROM AUTHOR]

This note presents a new passivity-based controller that ensures asymptotic stability for quadrotor position without solving partial differential equations or performing a partial dynamic inversion. After a resourceful change of coordinates, a pre-feedback controller, and a backstepping stage on the yaw angle dynamic, it is possible to identify new quadrotor cyclo passive outputs. Then, a simple proportional-integral controller of these cyclo-passive outputs completes the design. The cyclo-passive outputs allow the construction of an energy-based Lyapunov function that includes five out of six quadrotor degrees of freedom and guarantees asymptotic stability of the desired equilibrium. Moreover, the constant velocity reference tracking problem is solved with a slight modification to the proposed controller. Finally, the approach is validated through simulations and real-time experimental results. • The controller simultaneously shapes the energy of five out of six quadrotor degrees of freedom. • The stability proof relies on a Lyapunov function and a detectable output. • Real-time experiments validate the controller synthesis. [ABSTRACT FROM AUTHOR]

Additive Manufacturing, a pillar of Industry 4.0, to enable automatic real-time process control, relies on in-situ measurements, some of which - currently under development - exploit surface topography. Topographic characterisation requires a large set of parameters, loosely linked to visual appearance upon which related in-situ measurements are mostly based. A supervised machine learning classifier of as-built surfaces based on topographical characterisation is proposed and applied to tool steel test pieces fabricated by electron beam powder bed fusion. The methodology is developed to provide process engineers with the visual appearance of the topographical parameters set, and enable multi-scale, information-rich quality control. • PBF components as built topography depends on internal defects and process parameters. • Topographies are quantitatively characterised by a large set of complex parameters. • In-situ controls are based on qualitative inspection. • An ML-algorithm is developed to visually classify topographies based on parameters. • The tool will allow multi-scale, information-rich automated quality control for AM. [ABSTRACT FROM AUTHOR]

Handling sentiment drifts in real time twitter data streams are a challenging task while performing sentiment classifications, because of the changes that occur in the sentiments of twitter users, with respect to time. The growing volume of tweets with sentiment drifts has led to the need for devising an adaptive approach to detect and handle this drift in real time. This work proposes an adaptive learning algorithm-based framework, Twitter Sentiment Drift Analysis-Bidirectional Encoder Representations from Transformers (TSDA-BERT), which introduces a sentiment drift measure to detect drifts and a domain impact score to adaptively retrain the classification model with domain relevant data in real time. The framework also works on static data by converting them to data streams using the Kafka tool. The experiments conducted on real time and simulated tweets of sports, health care and financial topics show that the proposed system is able to detect sentiment drifts and maintain the performance of the classification model, with accuracies of 91%, 87% and 90%, respectively. Though the results have been provided only for a few topics, as a proof of concept, this framework can be applied to detect sentiment drifts and perform sentiment classification on real time data streams of any topic. [ABSTRACT FROM AUTHOR]

In recent years, there has been an increasing demand for efficient and robust control algorithms to optimize the performance of autonomous systems. Traditional control techniques often struggle to handle the complexity and uncertainty associated with such systems. To address these challenges, hybrid neuro-fuzzy-genetic algorithms have emerged as a promising approach. This paper presents a comprehensive review of the application of hybrid neuro-fuzzy-genetic algorithms for optimal control of autonomous systems. The proposed algorithms combine the strengths of neural networks, fuzzy logic, and genetic algorithms to achieve adaptive and optimal control in real-time scenarios. The neurofuzzy component provides the ability to model and handle complex and uncertain systems, while the genetic algorithm component facilitates the optimization of control parameters. The combination of these techniques enables autonomous systems to adapt and optimize their control strategies based on changing environments and objectives. The paper discusses the underlying principles of hybrid neuro-fuzzy-genetic algorithms, their advantages, and challenges. It also provides a review of the state-of-the-art research in this field, highlighting successful applications and potential future directions. Overall, the integration of neuro-fuzzy-genetic algorithms in autonomous systems holds great promise for achieving optimal control in various domains, including robotics, aerospace, and autonomous vehicles. [ABSTRACT FROM AUTHOR]

This paper presents a PyQt6 server-based application design for controlling a quadrotor multibody system in a simulated environment using the Gazebo 3D model and ROS2 on Linux. The combination of PyQt6 with ROS2 offers an intuitive graphical interface that simplifies access to control parameters and flight modes. The system incorporates a unique Gazebo plugin that connects to a proportional-derivative (PD) controller, providing stable quadrotor flight control. Notably, this plugin facilitates precise quadrotor movements and establishes reliable communication between the server and quadrotor, distinguishing it from other plugins. Moreover, simulation results demonstrate the effectiveness of the proposed PyQt6 server-based application in real-time quadrotor control. The results exemplify the system's capability to achieve stable and precise quadrotor movement by effectively controlling motion along the three axes (x, y, and z) along with yaw. However, the primary contribution of the system presented in this paper lies in the development of a robust PyQt6 server-based application designed to control a quadrotor multibody system. Furthermore, the system exhibits inherent potential for extension to encompass the control of a physical quadrotor, thereby substantiating its viability in real-world applications. [ABSTRACT FROM AUTHOR]

Diabetes is a big problem in the world. Also, in Peru there is a high rate of type 2 diabetes mellitus; this happens due to insulin resistance, which causes damage to the muscles and liver. In addition, fat cells do not generate insulin properly because the body needs to generate more insulin, so glucose can enter the cells. Due to this problem, we sought a solution that aims to develop the design of a mobile app that monitors and control, in real-time, diabetes in patients. This will help patients to have an effective follow-up plan. The methodology used in this research is Design Thinking because it fits perfectly with the solution of social problems, which was developed successfully using five phases: empathize, define, ideate, prototype, and finally test. As a result, the design of the mobile app to monitor and control in real-time type 2 diabetes mellitus in patients in Peru was developed. In addition, we obtained the diabetes data verified by the Peruvian Ministry of Health. [ABSTRACT FROM AUTHOR]

This paper presents the state-of-the-art and latest advances in implementing multi-use practices on BESS applications to the power system grid. Representative papers on modeling and optimization methods were selected, most of them working with realistic use cases, but none reporting on real-world implementations. Some major findings from reviewing key representative papers are that current optimization methods were able to handle uncertainty related to prices and other parameters either in the look-ahead planning stage or real-time control for obtaining an optimal dispatch schedule, thus addressing previously pointed-out gaps. Further, a recommendation for future work is to implement current multi-use methods, found to be mature enough, to real-world BESS use cases for validation and gaining experimental experience. Furthermore, the multi-use performance can further be improved by joining the strong contributions from each paper's method. Current methods have shown great potential for bringing simultaneous benefits to the grid, as well as being economical for the owner. A continued exploration and inclusion of new future BESS applications in prescriptive analytics for BESS multi-use suggest robustness for future market changes. However, further assessments are needed to evaluate whether the technology is economical and green for each particular use case and also for a potential systematic upscaling of the technology as a means to facilitate the green shift. [ABSTRACT FROM AUTHOR]

This study explores the benefits and challenges of using robotic process automation (RPA) and collaborative robots (CoBot) in transport management. The combination of RPA and CoBot can streamline processes, minimize errors, and boost productivity. However, the implementation of such technology comes with challenges and costs [1].This study aims to provide valuable insights into the role of RPA and CoBot in transport management, adding to the growing body of research on the use of automation in logistics and supply chain management [2]. Our analysis indicates that RPA and CoBot can revolutionize transport management, but their implementation requires careful consideration of factors such as security and investment. The study fills a gap in the literature by providing an in-depth examination of the benefits and challenges of using RPA and CoBot in transport management, offering practical recommendations for organizations considering implementing such technology. [ABSTRACT FROM AUTHOR]

Advancement of mobile technologies has enabled economical collection, storage, processing, and sharing of traffic data. These data are made accessible to intended users through various application program interfaces (API) and can be used to recognize and mitigate congestion in real time. In this paper, quantitative (time of arrival) and qualitative (color-coded congestion levels) data were acquired from the Google traffic APIs. New parameters that reflect heterogeneous traffic conditions were defined and utilized for real-time control of traffic signals while maintaining the green-to-red time ratio. The proposed method utilizes a congestion-avoiding principle commonly used in computer networking. Adaptive congestion levels were observed on three different intersections of Delhi (India), in peak hours. It showed good variation, hence sensitive for the control algorithm to act efficiently. Also, simulation study establishes that proposed control algorithm decreases waiting time and congestion. The proposed method provides an economical alternative to expensive sensing and tracking technologies. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) are a major element of Internet of Things (IoT) networks which offer seamless sensing and wireless connectivity. Disaster management in smart cities can be considered as a safety critical application. Therefore, it becomes essential in ensuring network accessibility by improving the lifetime of IoT assisted WSN. Clustering and multihop routing are considered beneficial solutions to accomplish energy efficiency in IoT networks. This article designs an IoT enabled energy aware metaheuristic clustering with routing protocol for real time disaster management (EAMCR-RTDM). The proposed EAMCR-RTDM technique mainly intends to manage the energy utilization of nodes with the consideration of the features of the disaster region. To achieve this, EAMCR-RTDM technique primarily designs a yellow saddle goatfish based clustering (YSGF-C) technique to elect cluster heads (CHs) and organize clusters. In addition, enhanced cockroach swarm optimization (ECSO) based multihop routing (ECSO-MHR) approach was derived for optimal route selection. The YSGF-C and ECSO-MHR techniques compute fitness functions using different input variables for achieving improved energy efficiency and network lifetime. The design of YSGF-C and ECSO-MHR techniques for disaster management in IoT networks shows the novelty of the work. For examining the improved outcomes of the EAMCR-RTDM system, a wide range of simulations were performed and the extensive results are assessed in terms of different measures. The comparative outcomes highlighted the enhanced outcomes of the EAMCRRTDM algorithm over the existing approaches. [ABSTRACT FROM AUTHOR]

Industrial Control Systems (ICS) and SCADA (Supervisory Control and Data Acquisition) systems play a critical role in the management and regulation of critical infrastructure. SCADA systems brings us closer to the real-time application world. All process and equipment control capability is typically provided by a Distributed Control System (DCS) in industries such as power stations, agricultural systems, chemical and water treatment plants. Instead of control through DCS, this paper proposes a SCADA and PLC (Programmable Logic Controller) system to control the ratio control division and the assembly line division inside the chemical plant. A specific design and implementation method for development of SCADA/PLC based real time ratio control and automated assembly line system in a chemical plant is introduced. The assembly line division is further divided into sorting stage, filling stage and the auxiliary stage, which includes the capping unit, labelling unit and then the storage. In the ratio control division, we have defined the levels inside the mixer and ratio of the raw materials through human machine interface (HMI) panel. The ratio of raw materials is kept constant on the basis of flow rates of wild stream and manipulated stream. There is a flexibility in defining new levels and the ratios of the raw materials inside the mixer. But here we taken the predefined levels (low, medium, high) and ratios (3:4, 2:1, 2:5). Control valves are used for regulating the flow of the compositions. In the assembly line division, the containers are sorted on the basis of size and type of material used i.e., big sized metallic containers and small sized non-metallic containers by inductive and capacitive proximity sensors. All the processes are facilitated with laser beam type or reflective type sensors on the conveyor system. Building a highly stable and dependable PLC/SCADA system instead of Distributed Control System is required to achieve automatic management and control of chemical industry processes to reduce waste manpower and physical resources, as well as to improve worker safety. [ABSTRACT FROM AUTHOR]

Environmental adaptability and real-time control are significant to the actual application of biped robots. The current Spring-Loaded Inverted Pendulum (SLIP) walking exhibits the compliant interaction with environments. However, the movability and controllability of this model is limited owing to the lack of ankles. Moreover, complicated nonlinear optimization problems in gait generation bring difficulties to real-time control. To overcome these problems, this study proposes an online whole-stage gait planning method to enhance the bipedal walking performance. Firstly, considering the role of ankles, this study applies the proposed template model called Variable Spring-Loaded Inverted Pendulum with Finite-sized Foot (VSLIP-FF) model. Then a Finite State Machine (FSM)-based gait pattern including the corresponding bio-inspired gait strategies is established, which extends the single cyclic gait to the whole-stage gait. Secondly, to realize real-time gait planning, an online gait generator based on a neural network is applied to reduce the calculational burden. Finally, the method is applied on the simulation prototype and real robot platform for verification. Experimental results validate that the proposed method can achieve an autonomous gait with the online planning time of 0.01s, and the step length range is expanded by 37.52% compared with the traditional SLIP model. • A whole-stage gait planning pattern is presented based on the improved VSLIP-FF model. • Movability and controllability of biped robots is improved by using the proposed bio-inspired gait strategies. • High-quality online gait planning is realized based on a BP neural network-based gait generator. [ABSTRACT FROM AUTHOR]

This work designed an innovative group touring service based on the Multi-Access Edge Computing (MEC) architecture and developed the associated group touring APP called ＂DEH_Narrator＂. The DEH_Narrator APP allows users to form an Mobile Social Network (MSN) group that contains a group leader and some group members. The group leader can (i) share her/his downloaded text and multimedia contents of Point of Interest (POIs) to all of the group members and (ii) control the playout of these shared contents in the handheld devices' DEH_Narrator APPs of all group members to assist her/his oral explanation work in the group touring scenario. That is, it belongs to the other type of real time and synchronous multimedia presentation because the corresponding multimedia content needs to be displayed to other group members' handheld devices during the group leader's oral explanation of the target POI. To meet the requirement of synchronously control and real time's presenting POI's multimedia content in all of the group members' handheld devices, the proposed group touring service adopted the MEC paradigm and architecture, in which a MEC server is associated with a mobile WiFi router, to provide users better quality of service (QoS) in terms of the data transmission time and quality of experience (QoE) in terms of the response time from selecting a POI to displaying the selected POI's multimedia content to all of the group members' handheld devices. Experimental results demonstrated that the adoption of the MEC paradigm and architecture can significantly improve the performance, i.e., the response time than without adopting the MEC paradigm and architecture. [ABSTRACT FROM AUTHOR]

Real-time monitoring of metabolic rate (MET) and clothing insulation (CLO) is essential to ensure effective occupant-centric control (OCC) for thermal comfort. This study aims to develop multi-task model using semi-supervised learning to enhance occupant activities and clothes detection performance by utilizing both labeled and unlabeled data. The convolutional neural network-based model and training approach with pseudo labels to update all parameters comprehensively were proposed. The developed model is validated by conducting comparative analysis with state-of-the-art models and applying it in a real-world environment. The results demonstrate that the developed model, employing semi-supervised learning and the dual-phase training method (DPTM), achieves superior performance in activity and clothes detection outperforming previous studies with a 15.8 % higher mean Average Precision (mAP) for activity detection and a 25 % improvement for clothes detection. The findings highlight the potential of this multi-task model using semi-supervised learning to automate data collection improving the accuracy of estimating occupant thermal comfort. This approach can dynamically optimize indoor environments tailored to individual needs within the OCC framework, enhancing thermal comfort and energy efficiency through precise monitoring of occupant information. • Multi-task model for collecting metabolic rate and clothing insulation was developed. • The model performs vision-based activity and clothes detection task in real time. • Semi-supervised learning approach and novel training method was adopted. • Ablation study and comparative analysis with existing models was conducted. • The proposed model achieves superior performance compared to existing methods. [ABSTRACT FROM AUTHOR]

A specially developed vision sensor seam tracking system is installed to improve the welding quality for Robotic-Arm Arc Welding (RAAW). New software is used for welding seam monitoring to examine different features of robotic arm arc welding. The software system comprises several components: welding voltage regulation, analytical parameters, image capture or analysis using enhanced algorithms, weld experts' database, robot coordination, and trajectory operations management. Experimentation is carried out to ensure the quality and reliability of various traditional welding methods and to evaluate the effectiveness of an established seam-tracking process. The results indicate that seam tracking is accurate for most welding processes. However, it is noted that most image-learning algorithms have limited adaptability and capacity during welding. A vision sensor-based algorithm for adaptive extraction functionality is proposed to solve this issue. Conventional welding seams are divided into laser strip pictures into continuous and discontinuous weld seams. The vision system then processes the captured data to convert the pixel coordinates into real-world coordinates, often using hand-eye calibration techniques to align with the robot's coordinate system. The vision system captures data and processes it to convert pixel coordinates into real-world coordinates. The alignment process with the coordinate system of the robot is done using hand-eye calibration techniques. The Exponentially Weighted Moving Average (EWMA) control panel is used to diagnose and identify faults, keeping an eye on anomalous deviations from the extracted slurry profile while welding. To achieve a 96 % seam extraction ratio and ± 0.50 mm seam tracking errors, the system uses an Aristo six-axis robot, a custom vision sensor, and seam-tracking software. The system demonstrates accuracy in industrial welding processes, with maximum and average seam tracking errors of 0.56 mm and 0.48 mm for continuous seams and 0.36 mm and 0.30 mm for non-continuous seams. [ABSTRACT FROM AUTHOR]

Thermal comfort models that account for individual thermal sensations are crucial for optimizing environmental control while maintaining occupant comfort. However, the current approach of developing occupant-specific models is not scalable for new occupants whose data were not used for training, making it impractical for multi-occupant spaces and burdensome for management. To address this, we propose a thermal comfort model based on a subject-independent evaluation approach, capable of generalizing to new individuals not included during model training. This model accurately predicts thermal sensations without the need for occupant-specific models, allowing scalability and adaptability to new occupants. Furthermore, this study considers occupants with face masks, which is essential in environments where masks are required for their wellbeing and performance. The model was developed using Compact Convolutional Transformers which combines convolutional layers and transformer layers, allowing the model to capture both fine-grained local features and broader contextual relationships, making it effective for predicting thermal comfort from thermal images. The model was trained using the Leave-One-Subject-Out (LOSO) and Leave-One-Group-Out (LOGO) training approaches. The LOSO approach achieved high accuracies of 98.04 %, 98.93 %, and 98.88 % for dataset A (participants without face masks), dataset B (participants with face masks), and dataset C (a combination of both), respectively. The LOGO approach achieved accuracies of 99.92 %, 99.40 %, and 99.85 % for datasets A, B, and C, respectively, showing a slightly better prediction performance. The approach presented in this study offers a promising solution for designing accurate generalized models for real-time environmental control to meet the thermal comfort needs of occupants. • Generalized comfort models were developed using thermal images and transformer. • Data was collected from 19 participants under varying temperature conditions. • Models predict thermal comfort with 98–99 % accuracy, with or without face mask. • Leave-one-group-out training captures occupants' thermal responses better. [ABSTRACT FROM AUTHOR]

Key Takeaways: Desalination is a widely used process in the universal drive to create new water supplies, with systems frequently turning to reverse osmosis (RO) as an affordable treatment technology. Intelligent water models, which use advanced algorithms to analyze large amounts of diverse data, can work in tandem with membrane forensics to boost RO systems' efficiency. Membrane fouling is a prime candidate for the benefits of intelligent water technologies, which could allow for real‐time analysis and control. Machine learning could gain a foothold in water treatment as its capabilities evolve and applications are understood and accepted. [ABSTRACT FROM AUTHOR]

Garment manufacturing has embraced the integration of digital human modelling (DHM) within the context of Industry 5.0 (I5.0), where human-machine collaboration (HMC) is at the forefront of technological advancements. This chapter explores the synergy between DHM and defect detection such as stitching errors, pattern inaccuracies, fabric flaws, and alignment issues, in the context of Garment Industry 5.0. The combination of DHM and defect detection in Industry 5.0 facilitates real-time quality control, as well as improved accuracy and efficiency in garment production. This chapter discusses the opportunities and challenges associated with defect detection for DHM in the context of I5.0, with the collaboration between human expertise and artificial intelligence (AI) systems. The adoption of DHM and defect detection in I5.0 fosters a collaborative environment where humans and machines work together to enhance quality control processes, optimize production workflows, and ensure garments meet or exceed customer expectations. [ABSTRACT FROM AUTHOR]

The tune up of fractional order (FO)- P I λ D μ controllers is largely advocated in available literature which mostly requires evolutionary optimization techniques or solution of complex non-linear equations thereby leading to lack of practical solutions in terms of selecting the controller parameters. It may be quite feasible if one can consider PID control in the form of cascaded P I − P D control with which the task of attainment of the control objectives can be accomplished methodically. In extension to this, studies related to FO P I λ − P D μ controller are not too exhaustive. Generally, graphical methods are adopted to compute the controller parameters. There is still paucity of comprehensive design algorithms for these controllers to which end this work comes up with a novel and simple specification driven design methodology of the cascaded structures of FO P I λ − P D μ and [ P I ] λ − [ P D ] μ controllers following the classical control theory Keeping away from the complex and implicit design strategies they assist with an exact and unique solution to design these FO controllers in frequency domain with satisfactory dynamic performance in time domain which may not be possible with the FO- P I λ D μ controllers. Illustrative examples and experimental validations aid to substantiate the reliability of the proposed method. • A novel specification driven design methodology of two distinct cascaded structures of fractional order (FO) PI-PD controllers. • Exact and unique solution to design these FO controllers in frequency domain with satisfactory dynamic performance. • Simple and meticulous design algorithms for selecting the controller parameters applicable to any stable and unstable plants. • Delay margin compensation technique made available for time delayed plants as well to accommodate the maximum delay that can be sustained. • Exhibition and validation of simulation studies by Experimental Results of Cart-Inverted Pendulum System. [ABSTRACT FROM AUTHOR]

As a data-driven design method, model-free optimal control based on reinforcement learning provides an effective way to find optimal control strategies. The design of model-free optimal control is sensitive to system data because it relies on data rather than detailed dynamic models. A prerequisite for generating applicable data is that the system must be open-loop stable (with a stable equilibrium point), which restricts the data-based control design methods in actual control problems and leads to rare experimental studies or verification in the literature. To improve this situation and enrich its applications, we propose a pre-stabilized mechanism and apply it to the motion control of a mechanical system together with a reinforcement learning-based model-free optimal control method, which constitutes a so-called hierarchical control structure. We design two real-time control experiments on an underactuated system to verify its effectiveness. The control results show that the proposed hierarchical control is quite promising in controlling this mechanical system, even though it is open-loop unstable with unknown dynamics. • Establish a pre-stabilized mechanism to effectively collect training data. • The parameters of near-optimal hierarchical control are tuned by system data. • Find parameter q is insensitive to the training result of weight coefficients of NNs. [ABSTRACT FROM AUTHOR]

This study presents the development of a grey-box modelling approach and fuzzy logic control for real time trajectory control of an experimental four degree-of-freedom Leader–Follower​ Robot (LFR) manipulator system using a hybrid optimisation algorithm, known as Grey Wolf Optimiser (GWO) - Whale Optimisation Algorithm (WOA). The approach has advantages in achieving an accurate model of the LFR manipulator system, and together with a better trajectory tracking performance. In the first instance, the white box model is formed by modelling the dynamics of the follower manipulator using the Euler–Lagrange formulation. This white-box model is then improved upon by re-tuning the model's parameters using GWO-WOA and experimental data from the real LFR manipulator system, thus forming the grey-box model. A minimum improvement of 73.9% is achieved by the grey-box model in comparison to the white-box model. In the latter part of this investigation, the developed grey-box model is used for the design, tuning and real-time implementation of a fuzzy PD＋I controller on the experimental LFR manipulator system. A 78% improvement in the total mean squared error is realised after tuning the membership functions of the fuzzy logic controller using GWO-WOA. Experimental results show that the approach significantly improves the trajectory tracking performance of the LFR manipulator system in terms of mean squared error, steady state error and time delay. [Display omitted] • A dynamic model of a 4-DOF leader–follower robot (LFR) manipulator system using the Euler–Lagrange formulation is presented. • The development of the LFR manipulator's grey-box model using a hybrid GWO-WOA approach is proposed. • A comparative study on the Euler–Lagrange based white-box model and GWO-WOA based grey box model is carried out to ascertain the superiority of the grey-box approach. • A fuzzy PD＋I controller is presented and tuned using the hybrid GWO-WOA approach. • The accuracy and robustness of the proposed controller is evaluated in terms of mean squared error, steady-state error, and time delay. [ABSTRACT FROM AUTHOR]

Coupled multiple-tank systems are very important for a wide range of industrial applications due to their unique uses. However, the liquid level control for the coupled two-tank multi-input multi-output (MIMO) system is quite challenging because it has strong nonlinearity and coupling, and it is susceptible to multiple external disturbances. For this process, this paper proposes a novel anti-disturbance control strategy consisting on a nonlinear composite hierarchical anti-disturbance predictive control (CHADPC). First, a model-based explicit nonlinear model predictive controller (ENMPC) is designed assuming that all disturbances are measurable and its global exponential stability is proved. Then, a nonlinear disturbance observer (DO) is designed to estimate the lumped disturbances. The composite controller handling the estimated disturbances is then proposed. Finally, simulation and experimental tracking control tests under perturbations and comparisons with recently reported works have been carried out to highlight the promising performance of the proposed ENMPC and CHADPC schemes. [ABSTRACT FROM AUTHOR]

As a data-driven design method, model-free optimal control based on reinforcement learning provides an effective way to find optimal control strategies. The design of model-free optimal control is sensitive to system data because it relies on data rather than detailed dynamic models. A prerequisite for generating applicable data is that the system must be open-loop stable (with a stable equilibrium point), which restricts the data-based control design methods in actual control problems and leads to rare experimental studies or verification in the literature. To improve this situation and enrich its applications, we propose a pre-stabilized mechanism and apply it to the motion control of a mechanical system together with a reinforcement learning-based model-free optimal control method, which constitutes a so-called hierarchical control structure. We design two real-time control experiments on an underactuated system to verify its effectiveness. The control results show that the proposed hierarchical control is quite promising in controlling this mechanical system, even though it is open-loop unstable with unknown dynamics. • Establish a pre-stabilized mechanism to effectively collect training data. • The parameters of near-optimal hierarchical control are tuned by system data. • Find parameter q is insensitive to the training result of weight coefficients of NNs. [ABSTRACT FROM AUTHOR]