Search

Lane changing behavior (LCB) prediction is a crucial functionality of advanced driver-assistance systems and autonomous vehicles. Predicting whether or not the driver of a considered ego vehicle is likely to change lanes in the near future plays an important role in improving road safety and traffic efficiency. Understanding the underlying intentions behind the driver's behavior is an important factor for the effectiveness of assistance and monitoring systems. Machine learning (ML) algorithms have been broadly used to predict this behavior by analyzing datasets of traffic and driving data related to the considered ego vehicle. However, this technology has not yet been widely adopted in commercial products. Further improvements in these algorithms are necessary to enhance their robustness and reliability. In some domains, receiver operating characteristic and precision-recall curves are commonly used to evaluate ML algorithms, not considering the effects of process parameters in the evaluation, while it might be necessary to access the performance of these algorithms with respect to such parameters. This paper proposes the use of deep autoencoders to extract multi-level features from datasets, which can then be used to train an ensemble of classifiers. This allows for taking advantage of high feature-extraction capabilities of deep learning models and improving the final result using ensemble learning techniques. The concept of probability of detection is used in combination with the networks employed here to evaluate which classifiers can detect the correct LCB better in a statistical sense. Applications on data acquired from a driving simulator show that the proposed method can be adopted to improve the reliability of the classifiers, and ensemble ANNs perform best in predicting the upcoming human behavior in this dynamical context earlier than 3 s before the event itself. [ABSTRACT FROM AUTHOR]

Vessel motion simulation as well as model-based accurate trajectory prediction of vessels require accurate models with respect to related dynamic properties. The ability to predict vessel's trajectory behaviors will become relevant in the case of future autonomous navigation of vessels to predict the behavior of others. The definition of models or parameters can be realized via first principles or by using experimental modeling methods leading to a time invariant or variant model. Existing hydrodynamical modeling approaches are based on mathematical approaches, which use parameters like mass, hydrodynamic forces, wind velocity, depth under the keel, loading parameters, etc. So, determining a dynamic vessel's model is a complex task, since the model is vessel-specific. For collision avoidance of autonomous or assisted vessels, the trajectory prediction of encountering other vessels is especially required. It is not possible to use complex hydrodynamical models of encountering vessels online due to missing required information/measurements. Even existing deep learning approaches provide better predictions, but are still insufficient for collision avoidance in the case of strong dynamical changes, since the considered input sequences are long. Due to long input sequences, the model does not adapt to strong dynamical changes. In this work, a simple parameter-based approach is developed to predict the intended behavior using the last seconds of the measured position variables. The idea is to globally identify the model parameters of the vessel, which remains constant for the situation, and additionally two parameters for local adaptation, which adapt at every updated input sequence. Typically parameters like rudder angle, wind velocities, and water current affect the behavior of vessels. The introduced approach works with a sliding window approach for which, after identification of the global system, local values are identified based on the last 80 measurements of the vessels. A trajectory prediction (assuming no additional rudder-based maneuvering) is realized for the prediction horizon of 180 s. To confirm the robustness of the new approach, real AIS/GPS-based measurements from a German research inland vessel for different scenarios and sailing conditions including 'loaded' and 'empty' sailing cases are used. Furthermore, additional results are shown for position data information of different sample rates. [ABSTRACT FROM AUTHOR]

Vision-based object detection plays a crucial role for the complete functionality of many engineering systems. Typically, detectors or classifiers are used to detect objects or to distinguish different targets. This contribution presents a new evaluation of CNN classifiers in image detection using a modified Probability of Detection reliability measure. The proposed method allows the evaluation of further image parameters affecting the classification results. The proposed evaluation method is implemented on images and comparisons made on parameters with the best detection capability. A typical certification standard ( 90 / 95 ) denoting a 90% probability of detection at 95% reliability level is adapted and successfully applied. Using the 90 / 95 standard, comparisons are made between different image parameters. A noise analysis procedure is introduced, permitting the trade-off between the detection rate, false alarms, and process parameters. The advantage of the novel approach is experimentally evaluated for vision-based classification results of CNN considering different image parameters. With this new POD evaluation, classifiers will become a trustworthy part of vision systems. [ABSTRACT FROM AUTHOR]

Due to increasing fuel prices, the world is moving towards the use of hybrid electric vehicles (HEVs) because they are environmentally friendly, require less maintenance, and are a green technology. The energy management system (EMS) plays an important role in HEVs for the efficient storage of energy and control of the power flow mechanism. This paper deals with the design, modeling, and result-oriented approach for the development of EMS for HEVs using a fuzzy logic controller (FLC). Batteries and supercapacitors (SCs) are used as primary and secondary energy storage systems (ESSs), respectively. EMS consists of the ultra-power transfer algorithm (UPTA) and FLC techniques, which are used to control the power flow. The UPTA technique is used to charge the battery with the help of a single-ended primary inductor converter (SEPIC) during regenerative braking mode. The proposed research examines and compares the performance of FLC with a proportional integral (PI) controller by using MATLAB (Simulink) software. Three scenarios are built to confirm the efficiency of the proposed design. The simulation results show that the proposed design with FLC has a better response as its rise time (2.6 m) and settling time (1.47 µs) are superior to the PI controller. [ABSTRACT FROM AUTHOR]

Featured Application: A simplified graphical method is proposed to represent the generic connections among the mechanical units of the hybrid systems with the continuously variable units. An example with wider ratio coverage and higher torque capacity is provided. To increase the energy efficiency of road vehicles, an ideal transmission system should have a wide ratio coverage, a high torque capacity, and a high mechanical efficiency. Continuously variable units (CVUs) have been successfully implemented due to the smooth ratio variation, sufficient torque capacity, and ratio coverage. Hence, it will be beneficial to develop a hybrid powertrain comprising a CVU. In this paper, a design method called the "basic path diagram" (BPD) is proposed. It provides a simplified schematic of the system and represents the generic connections among the mechanical components. The system configurations synthesized by the BPD can be sorted according to three characteristics: Direction of power flows through the CVU, coupling pattern of the power inputs, and number of transmission paths parallel to the CVU. The first characteristic determines the number of times the CVU ratio coverage can be exploited, the second characteristic determines whether the torque of the power inputs can be independently controlled, and the third characteristic can help reduce the torque loading of the CVU. With the aid of a BPD, one of the possible system configurations is provided as an example. The result shows that the system can exploit twice the ratio coverage of the CVU and reduce the torque and power transmitted by the CVU in combination with planetary gearsets. [ABSTRACT FROM AUTHOR]

The converter is an important component in wind turbine power drive-train systems, and usually, it has a higher failure rate. Therefore, detecting the potential faults for prediction of its failure has become indispensable for condition-based maintenance and operation of wind turbines. This paper presents an approach to wind turbine converter fault detection using convolutional neural network models which are developed by using wind turbine Supervisory Control and Data Acquisition (SCADA) system data. The approach starts with the selection of fault indicator variables, and then the fault indicator variables data are extracted from a wind turbine SCADA system. Using the data, radar charts are generated, and the convolutional neural network models are applied to feature extraction from the radar charts and characteristic analysis of the feature for fault detection. Based on the analysis of the Octave Convolution (OctConv) network structure, an improved AOctConv (Attention Octave Convolution) structure is proposed in this paper, and it is applied to the ResNet50 backbone network (named as AOC–ResNet50). It is found that the algorithm based on AOC–ResNet50 overcomes the issues of information asymmetry caused by the asymmetry of the sampling method and the damage to the original features in the high and low frequency domains by the OctConv structure. Finally, the AOC–ResNet50 network is employed for fault detection of the wind turbine converter using 10 min SCADA system data. It is verified that the fault detection accuracy using the AOC–ResNet50 network is up to 98.0%, which is higher than the fault detection accuracy using the ResNet50 and Oct–ResNet50 networks. Therefore, the effectiveness of the AOC–ResNet50 network model in wind turbine converter fault detection is identified. The novelty of this paper lies in a novel AOC–ResNet50 network proposed and its effectiveness in wind turbine fault detection. This was verified through a comparative study on wind turbine power converter fault detection with other competitive convolutional neural network models for deep learning. [ABSTRACT FROM AUTHOR]

Featured Application: This work uses AFRBF-SMC to achieve the vehicle stability control after the estimation of the sideslip angle by ADUKF. This study is targeted at the key state parameters of vehicle stability controllers, the controlled vehicle model, and the nonlinearity and uncertainty of external disturbance. An adaptive double-layer unscented Kalman filter (ADUKF) is used to compute the sideslip angle, and a vehicle stability control algorithm adaptive fuzzy radial basis function neural network sliding mode control (AFRBF-SMC) is proposed. Since the sideslip angle cannot be directly determined, a 7-degrees-of-freedom (DOF) nonlinear vehicle dynamic model is established and combined with ADUKF to estimate the sideslip angle. After that, a vehicle stability sliding mode controller is designed and used to trace the ideal values of the vehicle stability parameters. To handle the severe system vibration due to the large robustness coefficient in the sliding mode controller, we use a fuzzy radial basis function neural network (FRBFNN) algorithm to approximate the uncertain disturbance of the system. Then the adaptive rate of the system is solved using the Lyapunov algorithm, and the systemic stability and convergence of this algorithm are validated. Finally, the controlling algorithm is verified through joint simulation on MATLAB/Simulink-Carsim. ADUKF can estimate the sideslip angle with high precision. The AFRBF-SMC vehicle stability controller performs well with high precision and low vibration and can ensure the driving stability of vehicles. [ABSTRACT FROM AUTHOR]

The future of electric vehicles relies nearly entirely on the design, monitoring, and control of the vehicle battery and its associated systems. Along with an initial optimal design of the cell/pack-level structure, the runtime performance of the battery needs to be continuously monitored and optimized for a safe and reliable operation and prolonged life. Improved charging techniques need to be developed to protect and preserve the battery. The scope of this Special Issue is to address all the above issues by promoting innovative design concepts, modeling and state estimation techniques, charging/discharging management, and hybridization with other storage components. [ABSTRACT FROM AUTHOR]

In light of increasing alerts about limited energy sources and environment degradation, it has become essential to search for alternatives to thermal engine-based vehicles which are a major source of air pollution and fossil fuel depletion. Hybrid electric vehicles (HEVs), encompassing multiple energy sources, are a short-term solution that meets the performance requirements and contributes to fuel saving and emission reduction aims. Power management methods such as regulating efficient energy flow to the vehicle propulsion, are core technologies of HEVs. Intelligent power management methods, capable of acquiring optimal power handling, accommodating system inaccuracies, and suiting real-time applications can significantly improve the powertrain efficiency at different operating conditions. Rule-based methods are simply structured and easily implementable in real-time; however, a limited optimality in power handling decisions can be achieved. Optimization-based methods are more capable of achieving this optimality at the price of augmented computational load. In the last few years, these optimization-based methods have been under development to suit real-time application using more predictive, recognitive, and artificial intelligence tools. This paper presents a review-based discussion about these new trends in real-time optimal power management methods. More focus is given to the adaptation tools used to boost methods optimality in real-time. The contribution of this work can be identified in two points: First, to provide researchers and scholars with an overview of different power management methods. Second, to point out the state-of-the-art trends in real-time optimal methods and to highlight promising approaches for future development. [ABSTRACT FROM AUTHOR]

Reliability and availability of technically complex and safety-critical systems are of increasing importance. Besides the degree of wear, the quality of mechanical systems is significant for the system reliability. The focus of this contribution is the development and application of readily applicable and easily interpretable algorithms for industrial data obtained from technical systems during operation. The methods are within the focus of the production-oriented automation programs (Industrial Internet, Automation 4.0, China 2025). In this contribution as example a hydraulically driven machine in which parts slide over each other is chosen as sliding wear example. Monitoring is applied to distinguish normal and abnormal operation as well as to define end of useful lifetime. In this contribution four different methods will be introduced and experimentally compared without the availability of objective information about the wear state. The approaches differ with respect to the used measurements and data preparation. As measurements Acoustic Emission and the hydraulic pressure of the driving machine are used. For processing the accumulation of damage related values, a machine learning algorithm, and a sensitivity matrix are used. For comparison the experimental validation is based on identical data sets. Different operational states of the system denoted as actual system state are defined and classified. The comparison shows that the four introduced methods provide similar classification results although the underlying measurements are based on different physical principles. The newly introduced approaches allow online evaluation of the actual system state and can serve within improved maintenance strategies. [ABSTRACT FROM AUTHOR]

The field of hybrid vehicles has undergone intensive research and development, primarily due to the increasing concern of depleting resources and increasing pollution. In order to investigate further options to optimize the performance of hybrid vehicles with regards to different criteria, such as fuel economy, battery aging, etc., a detailed state-of-the-art review is presented in this contribution. Different power management and optimization techniques are discussed focusing on rule-based power management and multi-objective optimization techniques. The extent of rule-based power management and optimization in solving battery aging issues is investigated along with an implementation in real-time driving scenarios where no pre-defined drive cycle is followed. The goal of this paper is to illustrate the significance and applications of rule-based power management optimization based on previous contributions. [ABSTRACT FROM AUTHOR]

The reliability of complex or safety critical systems is of increasing importance in several application fields. In many cases, decisions evaluating situations or conditions are made. To ensure the high accuracy of these decisions, the assignments from different classifiers can be fused to one final decision to improve the decision performance in terms of given measures like accuracy or false alarm rate. Recent research results show that fusion methods not always outperform individual classifiers trained and optimized for a specific situation. Nevertheless fusion helps to ensure reliability and redundancy by combining the advantages of individual classifiers, even if some classifiers are not performing well for specific situations. Especially in unexpected (untrained) situations, fusion of more than one classifier allows to get a suitable decision, because of different behavior of classifiers in this case. Nevertheless, there are several examples, where fusion not always improves the overall accuracy of a decision. In this contribution fusion options are discussed to overcome the problem to overcome the aforementioned problem and to define influencing factors on overall fusion accuracy. As a results requirements for good or guaranteed or possibly increased fusion performance and also suggestions denoting those options not leading to any kind of improvement are given. For illustrating the effects a practical example based on three characteristics of fusion methods (type of classifier output, use of these outputs and necessity of training) and four data properties (number of classes, number of samples, entropy of classes and entropy of attributes) are considered and analyzed with 15 different benchmark data sets, which are classified with eight classification methods. The classification results are fused using seven fusion methods. From the discussion of the results it can be concluded, which fusion method performs best/worst for all data sets as well as which fusion method characteristic or data property has more or less positive/negative influence on the fusion performance in comparison to the best base classifier.Using this information, suitable fusion methods can be selected or data sets can be adapted to improve the reliability of decisions made in complex or safety critical systems. [ABSTRACT FROM AUTHOR]

Germination paper (GP) is used as a growth substrate in plant development studies. Current studies bear two limitations: (1) The actual GP water content and variations in GP water content are neglected. (2) Existing irrigation methods either maintain the GP water content at fully sufficient or at a constant deficit. Variation of the intensity of water deficit over time for plants grown on GP is not directly achievable using these methods. In this contribution, a new measurement and control approach was presented. As a first step, a more precise measurement of water content was realized by employing the discharging process of capacitors to determine the electrical resistance of GP, which is related to the water content. A Kalman filter using an evapotranspiration model in combination with experimental data was used to refine the measurements, serving as the input for a model predictive controller (MPC). The MPC was used to improve the dynamics of the irrigation amount to more precisely achieve the required water content for regulated water uptake in plant studies. This is important in studies involving deficit irrigation. The novel method described was capable of increasing the accuracy of GP water content control. As a first step, the measurement system achieved an improved accuracy of 0.22 g/g. The application of a MPC for water content control based on the improved measurement results in an overall control accuracy was 0.09 g/g. This method offers a new approach, allowing the use of GP for studies with varying water content. This addressed the limitations of existing plant growth studies and allowed the prospection of dependencies between dynamic water deficit and plant development using GP as a growth substrate for research studies. [ABSTRACT FROM AUTHOR]

In this study, different standard frequency analysis (FA) methods are applied to measured leaf temperature data of maize plants (developmental stages EC13–15). These FA methods are used to identify specific behaviors, regularities, and sudden changes in frequencies/amplitudes of data, e.g., in control engineering. The thorough application of different FA methods in plant studies is novel. The aim of this paper is to analyze features of the measured data and to explore the explanatory power of different methods for the detection of plant dynamic behavioral changes. The basic assumption is an expected relation between plant water stress and resulting changes in leaf temperature oscillations caused by stress-induced changes in stomatal behavior. Therefore, an irrigation experiment (laboratory; controlled environmental conditions) was implemented to compare leaf temperature behavior of stressed and unstressed plants. Leaf temperature time series are processed and the results are compared as functions of time showing the behavioral changes in terms of the different methods applied. The analysis of results is explained; conclusions, which can be made based on different methods, are given. The study confirms the applicability of FA methods and provides new insights into leaf temperature behavioral patterns. Results are discussed regarding the hypothesized incipience of leaf temperature oscillations due to water stress. [ABSTRACT FROM AUTHOR]

Recently, research on data-driven bearing fault diagnosis methods has attracted increasing attention due to the availability of massive condition monitoring data. However, most existing methods still have difficulties in learning representative features from the raw data. In addition, they assume that the feature distribution of training data in source domain is the same as that of testing data in target domain, which is invalid in many real-world bearing fault diagnosis problems. Since deep learning has the automatic feature extraction ability and ensemble learning can improve the accuracy and generalization performance of classifiers, this paper proposes a novel bearing fault diagnosis method based on deep convolutional neural network (CNN) and random forest (RF) ensemble learning. Firstly, time domain vibration signals are converted into two dimensional (2D) gray-scale images containing abundant fault information by continuous wavelet transform (CWT). Secondly, a CNN model based on LeNet-5 is built to automatically extract multi-level features that are sensitive to the detection of faults from the images. Finally, the multi-level features containing both local and global information are utilized to diagnose bearing faults by the ensemble of multiple RF classifiers. In particular, low-level features containing local characteristics and accurate details in the hidden layers are combined to improve the diagnostic performance. The effectiveness of the proposed method is validated by two sets of bearing data collected from reliance electric motor and rolling mill, respectively. The experimental results indicate that the proposed method achieves high accuracy in bearing fault diagnosis under complex operational conditions and is superior to traditional methods and standard deep learning methods. [ABSTRACT FROM AUTHOR]

In recent years, the rapidly-increasing demand for energy generation from renewable resources has been noticeable. Additional requirements are consequently set on Wind Turbine (WT) systems, primarily reflected in WT size and power rating increases. With the size increase of WT, structural loads/fatigue stress on the wind turbine become larger, simultaneously leading to its accelerated aging and the shortening of its lifetime. The primary goal of this contribution is to establish an approach for structural load reduction while retaining or slightly sacrificing the power production requirements. The approach/control strategy includes knowledge about current fatigue damage and/or damage increments and consists of multi-input multi-output controllers with variable control parameters. By the appropriate selection of the designed Multi-Input Multi-Output (MIMO) controllers, the mitigation of structural loads in accordance with a predefined range of accumulated fatigue damage or damage increments, exactly to the extent required to provide a predefined service lifetime, is obtained. The validation of the aforementioned control strategy is based on the simulation results and the WT model developed by National Renewable Energy Laboratory (NREL). The obtained results prove the efficiency of the proposed control strategy with respect to the reduction of rotor blade bending moments, simultaneously exhibiting no significant impact on the resulting power generation. [ABSTRACT FROM AUTHOR]

Today, the demand for continuous monitoring of valuable or safety critical equipment is increasing in many industrial applications due to safety and economical requirements. Therefore, reliable in-situ measurement techniques are required for instance in Structural Health Monitoring (SHM) as well as process monitoring and control. Here, current challenges are related to the processing of sensor data with a high data rate and low latency. In particular, measurement and analyses of Acoustic Emission (AE) are widely used for passive, in-situ inspection. Advantages of AE are related to its sensitivity to different micro-mechanical mechanisms on the material level. However, online processing of AE waveforms is computationally demanding. The related equipment is typically bulky, expensive, and not well suited for permanent installation. The contribution of this paper is the development of a Field Programmable Gate Array (FPGA)-based measurement system using ZedBoard devlopment kit with Zynq-7000 system on chip for embedded implementation of suitable online processing algorithms. This platform comprises a dual-core Advanced Reduced Instruction Set Computer Machine (ARM) architecture running a Linux operating system and FPGA fabric. A FPGA-based hardware implementation of the discrete wavelet transform is realized to accelerate processing the AE measurements. Key features of the system are low cost, small form factor, and low energy consumption, which makes it suitable to serve as field-deployed measurement and control device. For verification of the functionality, a novel automatically realized adjustment of the working distance during pulsed laser ablation in liquids is established as an example. A sample rate of 5 MHz is achieved at 16 bit resolution. [ABSTRACT FROM AUTHOR]