Search

Deep Neural Network (DNN) in recent era offers new opportunities to manage the production systems with increasing complexity. In this paper, DNN is trained with discrete event simulation and a process based association to make the job shop an autonomous one. This intelligent system operates well in complex environment with constrained time limits while making optimal decisions. The DNN is henceforth combined with constrained time limits for the process of production control. The system is implemented typically in semiconductor manufacturing industries on complex job shops of a wafer fab case. The DNN is trained in such a way that it operates in complex environment with timing constraints that ships the job in accurate way without flaws in operation. The DNN rewards the selection with reduced time constraint, which tends to operates with most critical batch list. The study therefore shows that the DNN manages well the timing constraints than the standard benchmark technique.

The industrial IoT (IIoT) accommodates a huge number of heterogeneous devices to bring vast services under a distributed computing scenarios. Most productive services in IIoT are closely related to production control and require distributed network support with low delay. However, the resource reservation based on gross traffic prediction ignores the importance of productive services and treats them as ordinary services, so it is difficult to provide stable low delay support for large amounts of productive service requests. For many productions, unexpected communication delays are unacceptable, and the delay may lead to serious production accidents causing great losses, especially when the productive service is securityrelated. In this paper, we propose a brain-like productive service provisioning scheme with federated learning (BrainIoT) for IIoT. The BrainIoT scheme is composed of three algorithms including industrial knowledge graph-based relation mining, federated learning-based service prediction, and globally optimized resource reservation. BrainIoT combines production information into network optimization and utilizes the inter-factory and intrafactory relations to enhance the accuracy of service prediction. The globally optimized resource reservation algorithm suitably reserves resources for predicted services considering various resources. The numerical results show that the BrainIoT scheme utilizes inter-factory relation and intra-factory relation to make an accurate service prediction, which achieves 96% accuracy, and improves the quality of service.

Production control, inventory and distribution is an important factor in trading activities. These three factors are discussed in a system called Supply Chain Management (SCM). Procurement of goods from a company or trading business related to suppliers. In some cases, there are several supplier that can be assessed by considering certain factors. In certain cases, the data from several factors that are considered are uncertainty, so the fuzzy approach can be used. The MINMAX Multi Choice Goal Programming model can be used to solve fuzzy supplier selection problems with linear membership function. It can be applied to selecting supplier of Brastagi Oranges. There are four suppliers, namely Jaya, Mako, Baros. Gina. There are three factor to consider, cost, quality and delivery. The decision maker select the best supplier for ordering 17000 kg Brastagi oranges. The results, the best supplier is Gina with an order quantity of 10000 kg and Mako with a total order of 7000 kg

In Prozessen mit hoher Varianz, kurzen Lieferzeiten sowie veränderlichen Produkten ermöglicht eine simulationsbasierte Planung sowie eine adaptive Anpassung der Produktionspläne eine zielgerichtete Kapazitätsauslastung der Produktion. Die Simulation der Ofenbelegung, die Implementierung einer automatisierten Maschinenansteuerung und die dadurch resultierende Steigerung der Energieeffizienz werden am Beispiel einer variantenreichen Backwarenproduktion gezeigt.

The article is devoted to the synthesis of a SMART-system for a complex industrial object control based on metaheuristic optimization algorithms and modern industrial equipment from Honeywell Company. There has been developed software for collecting industrial data, automated tuning of typical controllers of a MIMO industrial object based on such intelligent optimization algorithms as ant colony algorithm, grey wolf optimization, dragonfly algorithm and cuckoo search algorithm. These algorithms are used to minimize the developed new modified quality criteria of a MIMO industrial object. The results are integrated into the Honeywell Experion PKS distributed control system for technological process control in the oil and gas industry using a distillation column for purifying gas from impurities as an example. On the basis of the decoupling procedure, the problem of compensating for the influence of the MIMO system interconnections is solved. The paper substantiates the effectiveness of the implementation of the developed SMART-system for solving the problems of optimal complex technological production control in the oil and gas industry on the example of the real production process of the TengizChevroil enterprise.

Shortening product development cycles and fully customisable products pose major challenges for production systems. These not only have to cope with an increased product diversity but also enable h...

The study discusses how the process information reserves can be used for improving production flexibility on the basis of production component variation control. Building upon the assumption that the data in question describe the functions of the production components as those experience perturbations, we submit that it may be possible to predict the productivity and economic efficiency for new, previously unused control options. We elaborate on the production components that ensure production flexibility, approaching them as a highly autonomous holon. We determine the conditions that make it possible to analyze the holon control options in isolation from controlling all other components. We also suggest a solution to the problem of predicting the employees’ impact on production. Our suggestion is based on limiting the types of impact accessible to a human operator. The study looks at the reasons behind the uncertainty of production control simulation modeling results, which stem from the peculiarities of the data collected. We propose a criterion for assessing the impact of uncertainty on the productivity indicators’ variation. This study offers a systemic overview of the aspects of a production simulation aimed at assessing the impact of uncertainty on productivity predictions. As an example, we review how uncertainty affects the variation of coke consumption and productivity of a blast furnace, which is ensured by selecting a suitable option for iron ore sinter quality control.

Manufacturing in the age of Industry 4.0 can be characterised by a high product variety and complex material flows. The increasing individualisation of products requires adaptive production plannin...

Digital twin (DT), machine learning, and industrial Internet of things (IIoT) provide great potential for the transformation of the container terminal from automation to intelligence. The production control in the loading and unloading process of automated container terminals (ACTs) involves complex situations, which puts forward high requirements for efficiency and safety. To realize the real-time optimization and security of the ACT, a framework integrating DT with the AdaBoost algorithm is proposed in this study. The framework is mainly composed of physical space, a data service platform, and virtual space, in which the twin space and service system constitute virtual space. In the proposed framework, a multidimensional and multiscale DT model in twin space is first built through a 3D MAX and U3D technology. Second, we introduce a random forest and XGBoost to compare with AdaBoost to select the best algorithm to train and optimize the DT mechanism model. Third, the experimental results show that the AdaBoost algorithm is better than others by comparing the performance indexes of model accuracy, root mean square error, interpretable variance, and fitting error. In addition, we implement empirical experiments by different scales to further evaluate the proposed framework. The experimental results show that the mode of the DT-based terminal operation has higher loading and unloading efficiency than that of the conventional terminal operation, increasing by 23.34% and 31.46% in small-scale and large-scale problems, respectively. Moreover, the visualization service provided by the DT system can monitor the status of automation equipment in real time to ensure the safety of operation.

Introduction. Social and hygienic monitoring results are currently used to assess drinking water quality in centralized cold water supply systems and calculate the number of people provided with high-quality drinking water. Additionally, they use the results of investigations against resource-supplying organizations. There is not enough information to analyze and obtain reliable data. It is necessary to develop a comprehensive solution. The complex should include combining the goals of many fragmented digital solutions that regulate collecting and analyzing large amounts of data. Materials and methods. Research materials and methods include production control programs and the results of a study of the quality of drinking water in centralized water supply systems. The object of the study is the localities of 15 subjects of the Russian Federation. Methods of system and content analysis were used for the examination. Results. As part of the production control, resource-supplying management of gathering information on the water quality of centralized cold water supply systems. The requirements for the management of state data are set out in the documents of the Analytical Center under the Government of the Russian Federation. The fragmentation of the collected data does not allow us to meet the requirements for the quality of information. To assess the water quality of centralized cold water supply systems, information about water supply sources, water pipes, control points in the distribution network, and research results can be supplemented with information from the automated information system “Housing and Utilities Reform”. The entire set of information should be transmitted to the formation system “Interactive map of drinking water quality control in the Russian Federation”. Conclusion. To obtain a set of reliable information, it is necessary to include the results of production control in the drinking water quality monitoring system, provide the standardization of formats for the presentation of laboratory research results, create a single software product and introduce changes in regulatory documents that oblige resource-supplying organizations to send the results of industrial water quality control in electronic form. Contribution: Myasnikov I.O. — statistical processing, writing text, editing; Novikova Yu.A. — concept and design of the study, editing; Kopytenkova O.I. — collection and processing of material; Evseeva M.N. — collection and processing of material; Yeremin G.B. — collection of literature data. All co-authors — approval of the final version of the article, responsibility for the integrity of all parts of the article. Conflict of interest. The authors declare no conflict of interest. Acknowledgment. The study had no sponsorship.

We propose a new integrated queueing-inventory and reliability model. First, we obtained time-dependent performance measures by using the Laplace transform method. Then, we derived stationary perfo...

The current work examines the performance of Minimum Quantity Lubrication when turning of EN-GJL-250 cast iron compared to dry and wet cooling methods. The Taguchi design L36 has been chosen for the planification of experimentation. Then, ANOVA has been established after data acquisition in order to define the effect of cutting conditions such as the used inserts, cutting depth, feed rate and cutting speed on the studied factors. Furthermore, the surface roughness has been deeply studied using 3D roughness topography to evaluate the MQL effect. Finally, the approach ANN-MOALO was found to be helpful for future industrial applications for predicting part quality and power consumption with accurate results and optimizing cutting parameters that helps to achieve the best production control.

This work is a supplement to earlier literature reviews of research on the production control scheme known as CONWIP. In this paper, we chronicle the origins of CONWIP and address many of the issue...

Manufacturing systems with perishable products appears in several industrial branches such as food production, chemical and radioactive material manufacturing, and pharmaceutical industry. Product perishability often results in the disposal of the fraction of products that do not meet the final specifications, after being kept too long within serviceable inventory. The disposal of perishables raises several environmental issues and its minimization together with reduction of other costs related to perishable inventories are most often studied within inventory management framework. The production control problem for the systems with perishable products, especially in case of failure-prone manufacturing facilities, is an important and challenging topic that was only sparsely addressed in the scientific literature. The main difficulty consists in resolving the trade-off between having an inventory level sufficient to fill the demand in case of machine failure, and potential deterioration of products kept too long within inventory. The paper proposes an approach to resolve this trade-off. First, a mathematical model describing the stochastic behavior of such systems is developed. Next, an analytical study of the system is performed, and finally, an optimal production policy that takes the product perishability into account is determined. This policy is shown to be a hedging point-type policy; thus the well-known result about the optimality of hedging point policy (in nonperishable case) is generalized to the class of perishable products with fixed shelf-life. It is shown that under conventional conditions (limited production capacity, Markovian failure/repair processes, constant demand rate), the optimal hedging level does not exceed the cumulative demand along the product shelf-life, and that leads to no disposal of products, known as a zero-waste policy. Numerical simulations allowed to perform the sensitivity analysis and a comparative study of the costs incurred in the systems with and without perishability.

We study production planning in a multi‐product setting, in which demand for each product depends on multiple financial assets (such as commodities, market indices, etc). In addition to the production quantity decision at the beginning of the planning horizon, there is also a real‐time hedging decision throughout the horizon; and we optimize both decisions jointly. With a mean–variance problem formulation, we first derive the optimal hedging strategy, given the production quantities. This leads to an explicit objective function with which bounds on optimal production quantities are identified. Thus, optimization of the production policies can be readily solved numerically as a static minimization problem. This way, we are able to give a complete characterization of the mean–variance efficient frontier, and quantify the contribution of the hedging strategy by the variance reduction it achieves. Furthermore, the model and results are extended to allow dynamic production control that tracks the demand rates.

Steady-state analysis on production systems, especially serial lines with rigid production mode, have been carried out in a large amount of research literature. With the development of the advanced manufacturing technologies, as well as the national strategies, for example, Made in China 2025, real-time performance evaluation, prediction, production management, and efficient control of systems with flexible production mode are gradually becoming important issues. Under the assumption of assembly systems with small batch-based production tasks, we develop a mathematical model for the real-time performance analysis of such systems with the geometric machine reliability model, which is applicable in many manufacturing environments. The formulas for real-time performance analysis are derived first using the Markovian approach for three-machine assembly systems. Then, based on the idea of decomposition and aggregation, an algorithm with high accuracy and efficiency for system real-time performance approximation is proposed. Finally, the decomposition and aggregation-based real-time analysis approach is extended to the generalized assembly systems. Note to Practitioners —As the concept of manufacturing intelligence being proposed and promoted, system flexibility appears frequently in production in recent years. A flexible production refers to the implementation of small batch-based production with multitype of products on the same production line, by quick setup or machine adjustments. The steady-state analysis method that is traditionally used might be not applicable in this case since most of the production process is in transient state. An approximation-based analytical method, for real-time performance evaluation of assembly systems with small batch-based production tasks and with machines having the geometric reliability model, is proposed. The algorithm developed in this article can be utilized by production managers and engineers, with which the real-time performance of the systems can be predicted with high accuracy. It can also provide assistance for decision-making on activities of production control.

Control of production operations is one of the most cost-effective methods to improve energy efficiency in production lines. Although many research efforts have been devoted to utilizing production control to boost production energy efficiency, it is not clear how production dynamics change in reaction to the energy saving operations, which is important to capture energy saving opportunities. In this paper, an optimal energy saving control method based on N-policy is introduced to reduce the system energy consumption while only slightly decreasing productivity. A Markov chain model is established to interpret the dynamics of serial production lines with N-policy. The analytical formulas of production rate and energy consumption are derived. Then, an energy-efficient control model is formulated to balance the productivity and energy consumption. For two-machine production lines, the monotonicity property of the model is proved, and the analytical N-policy is derived. For longer production lines, an adaptive genetic algorithm is utilized to solve the energy-efficient control model. Case studies validate the effectiveness of the proposed optimal energy saving control method.

Controlling production and release of material into a manufacturing system effectively can lower work-in-progress inventory and cycle time while ensuring the desired throughput. With the extensive data collected from manufacturing systems, developing an effective real-time control policy helps achieving this goal. Validating new control methods using the real manufacturing systems may not be possible before implementation. Similarly, using simulation models can result in overlooking critical aspects of the performance of a new control method. In order to overcome these shortcomings, using a lab-scale physical model of a given manufacturing system can be beneficial. We discuss the construction and the usage of a lab-scale physical model to investigate the implementation of a data-driven production control policy in a production/inventory system. As a data-driven production control policy, the marking-dependent threshold policy is used. This policy leverages the partial information gathered from the demand and production processes by using joint simulation and optimization to determine the optimal thresholds. We illustrate the construction of the lab-scale model by using LEGO Technic parts and controlling the model with the marking-dependent policy with the data collected from the system. By collecting data directly from the lab-scale production/inventory system, we show how and why the analytical modeling of the system can be erroneous in predicting the dynamics of the system and how it can be improved. These errors affect optimization of the system using these models adversely. In comparison, the data-driven method presented in this study is considerably less prone to be affected by the differences between the physical system and its analytical representation. These experiments show that using a lab-scale manufacturing system environment is very useful to investigate different data-driven control policies before their implementation and the marking-dependent threshold policy is an effective data-driven policy to optimize material flow in manufacturing systems.

In recent years, with the increase in computing power, the sharp drop in costs, and the successful use of data management technology, a large amount of data has been rapidly spread and stored in various fields of the company. How can we passively find active data and form active knowledge from these big data information, know how to use equipment to quickly and accurately obtain high-quality information, use the obtained information to guide users in decision-making, and provide more economic and social benefits? This paper focuses on the study of the classifier model based on BP neural network, and the combination of BP neural network model and other optimization algorithms, including genetic algorithm (GA), particle swarm algorithm (PSO), Adaboost algorithm, GA, and PSO have global search performance. It is mostly used to optimize the weight threshold of the network and the number of hidden layer nodes. The Adaboost algorithm builds an enhanced classifier based on the idea of integration. At present, data mining technology has moved from the laboratory research stage to the commercialization stage. The use of widely owned knowledge and information as analysis tools can be used in many fields: such as financial analysis, engineering design, scientific research, management, and production control. At the end of this paper, the improved Adaboost_BP classifier is used, and the result proves that the efficiency of hotel management has increased by at least 75%.

For an assembly manufacturing system, its capacity planning problem and production control problem are usually considered separately. However, production capacity cannot exert its maximum productivity without employing optimal production control; and optimal production control may not satisfy the demand without sufficient production capacity. Therefore, it is important to jointly optimize capacity planning and production control. First, the mathematical formulation of integrated production control and capacity planning problem for an assembly manufacturing system with multiple upstream production lines and one downstream assembly line is proposed in this paper. Second, we develop a method to obtain the marginal probability distribution of the inventory level in the assembly system, which can be employed to calculate the average production cost under an approximate optimal production control policy. Since optimal control policy is subject to production capacity (i.e., machine number), we employ the integer programming method to optimize the machine number (i.e., production capacity), which consequently influences the control policy. Numerical experiments are conducted to verify the correctness of the method of calculating steady-state probability distribution, and the effectiveness of the algorithm of integrated optimization of production control and production capacity.

The lean manufacturing concept is a systematic minimization of waste and non-value activities in production processes introduced by the Toyota production system. In this research, lean manufacturing is implemented in a cement production line. Value Stream Mapping (VSM) is applied to give a clear picture of the value chain in cement production processes and to highlight the non-value-added in the shop floor. To begin, the existing VSM is constructed based on the information and data gathered during visiting and observing the manufacturing process in the firm. As a result, the excess inventory between workstations was identified as a major waste generation, hence, the proposed VSM conducts further improvement and makes action plans to alleviate the unwanted activities. Then, the takt time to ensure smooth material flow and to avoid any occurring delay or bottleneck in the production line was figured out. The supermarket pull-based production control is suggested to be adopted in the future map. Two pull production strategies are selected in this case. The first is applying the Kanban system to control the level of inventory between workstations. The other is the CONWIP approach to control the amount of work in process to the entire production line. The outcome of the proposed models indicates a decrease of the none-value time from 23 days in the current state to about 4 and 2 days in Kanban and CONWIP systems respectively, so the CONWIP was suggested as most efficient. Some suggestions for further research are also mentioned.

Dentre as muitas atribuições de um engenheiro eletricista, o controle de sistemas é uma tarefa primordial para o sucesso de um negócio. Esse gerenciamento é fundamental para garantir o controle da produção, reduzir custos, evitar prejuízos e visar lucros. No entanto, gerenciar sistemas de controle é um desafio que pode consumir muito tempo do gestor, inviabilizando outras ações de extrema importância para a produtividade e o crescimento da empresa. Para facilitar esse trabalho, o mercado tem desenvolvido e aperfeiçoado programas que possibilitam esse controle de forma mais simples e funcional. Nessa perspectiva, esse trabalho tem como objetivo utilizar fundamentos de sistemas de controle para ajustar a velocidade desejada de uma esteira transportadora industrial. Para isso, também foram inseridos controladores com ações independentes no sistema: do tipo proporcional (P), proporcional-integral (PI), proporcional-derivativo (PD) e proporcional-integral-derivativo (PID), apresentando os resultados obtidos a partir do desempenho do sistema para cada um dos casos, com suas respectivas discussões e conclusões.

Manufacturing servitization has become a major trend in industry that is implemented by so called integrated production and service systems (IPSSs) to offer not only products but also their associated services. In this study, we explore the capacity allocation policy for an IPSS that consists of a manufacturing facility and a service center. The IPSS serves two classes of customers, each demanding a specific product produced at the manufacturing facility and, subsequently, the associated service offered by the service center. We formulate this problem of resource allocation as a Markov decision process. Our analysis suggests that it is optimal to serve the customer with the larger cost saving rate and slower service rate, where the cost saving rate equals service rate times the sum of holding cost and waiting cost. Then we explore production control policies coupled with optimal service ones. We demonstrate that, with light service traffic, the system under the optimal production policy becomes similar to a make‐to‐stock system. Such a system can effectively hedge the system uncertainty. Therefore, the optimal production policy for the IPSS is also a hedging point policy. Under this policy, switching and idling curves split the state space into three regions: one without any production, the two others for production of two type products, respectively. We also discuss the optimal control policies of the two extensions of the IPSS (one with multiple types of product and customers, and the other with a single product and two classes of customers) and find that the characters of the optimal production and service policy still hold. Finally, we develop three heuristic integrated scheduling policies. Numerical experiments show that one is very effective.

The fast development of the so-called shared economy as well as collaborative networked organization increases the call for responsive and strongly interconnected production and delivery systems. The closer connection of information systems and control systems has to be achieved, as “Industry 4.0” developed by leading industries in Europe, USA and Asia requires to set new IT models in order to support agile collaborative business processes and production control processes. Whereas the service-based organizations and technologies, such as Service-Oriented Architecture, Web 2.0, Cloud and Everything as a Service technologies as well as Business models, have been successfully deployed to support agile systems relying on service selection, composition and orchestration, only few works have addressed cloud-based control systems. Despite the flexibility provided by the Internet of Thing, the integration of Cyber-Physical systems (CPS) in production control system is limited due to their lack of interoperability. To overcome this limit and provide a smooth integration of CPS systems in collaborative production process control, we propose a service-based control model integrating sensors, controllers and actuators. To support the Industry 4.0 digital transformation, including collaborative production process design and management, our Control as a Service model relies on control ontology. Our control ontology gathers IoT devices (sensors and actuators $$\ldots $$ ) and services, including their functional and non-functional properties description. Then, a Control as a Service architecture is designed to facilitate the development of cloud control system via two steps: service pre-selection/pre-composition, event-driven and context-aware service orchestration. The measurement of three core components, data manager, event manager and context manager, shows the feasibility of application of our Control as a Service model/architecture in a supply chain temperature control use case.

Production control in the manufacturing industry involves complex circumstances and high demand for timeliness. Unlike traditional production control methods, the approach that integrates machine l...

In a re-entrant job shop (RJS), an entity can visit the same resource type multiple times; this is called re-entrancy, which occurs frequently in actual industries. Re-entrancy causes an NP-hard pr...

Manufacturing can be defined as applying physical and/or chemical processes to modify the structure, properties, and appearance of a given starting material to produce parts or products. Manufacturing often entails combining multiple elements for the creation of assembled products. This study aimed to establish a general understanding of development production planning and control and typical products such as just in time and lean production. Method of this study through literature review. This study described activities related to production planning and production control, the difference between lean production and traditional production (push system), and the structure of lean production as known as Toyota system manufacturing.

Serial transfer lines with parallel machines in each stage are now a fairly common manufacturing system. However, its analysis and predictive-reactive control during transients remains mostly unexplored. This manufacturing system consists of a series of stages where in each stage a finite number of machines work concurrently. A two multi-state stage transfer line is studied in this paper. To describe the probability of one part being completed from the several machines in a stage, an equivalent multi-state, perfectly reliable machine is proposed. This multi-state model enables variance in the processing time between job completions to be captured stochastically. Based on historic data or engineering experience, an equivalent multi-state machine is simulated from the cumulative distribution function of the aggregated behavior of the parallel machines. In this paper, a serial production line with two equivalent, multi-state machines is used to analyze transient performance. Analytical closed-form expressions are derived to evaluate system transient behaviors. This system is also used with a controller to implement practical production control. Using model predictive control, system control parameter values provide decision support for managers to control short-term production. The proposed methodology can be applied to improve resource efficiency in other operation management problems.

ISO 13565-3 provides an evaluation method for plateau structure surfaces used as sliding surfaces in machine tools and automobile engines. The evaluation method for plateau structure surfaces of ISO 13565-3 has problems, such as the processing procedure has an ambiguous basis, and the calculation method is not specified. The existing evaluation method that solves these problems requires the implementation of a difficult algorithm. In subsequent evaluation methods, these problems were resolved, and the implementation of complicated calculation algorithms became unnecessary. However, these methods use algorithms that do not conform to the evaluation method of ISO 13565-3. This lack of adherence to the ISO standard may hinder their application in the industrial world. Therefore, in this study, a new method that conforms to the evaluation method of ISO 13565-3 with a more concise algorithm was developed. We concluded that this proposed method can contribute to the formation of plateau surfaces and production control in the industrial world.

Performance analysis of flexible manufacturing systems has received substantial research attention. Most of the studies focus on steady-state behavior. The transient performance, which is critical for system operation, control, and improvement, is less investigated. No analytical method is available to evaluate the transients in flexible lines with unreliable machines, finite buffers, and setup times. In this article, an analytical model is introduced to study the transient performance of multiproduct serial lines with Bernoulli reliability machines and nonnegligible setups during changeovers. To reduce the state-space dimension, an approximation method is introduced to evaluate the performance in two-machine lines, where the sequence of multiple part types in the inventory is approximated by the ratio of product mix. Such an approximation method leads to high precision of production rate estimation. Then, for longer lines, the analysis approach in two-machine lines is used as a building block in an iterative aggregation procedure. Numerical experiments show that the iteration procedure is convergent and results in an acceptable accuracy in performance evaluation. In addition, system properties, such as monotonicity and reversibility, are investigated. Note to Practitioners —Manufacturing systems become more and more flexible, where multiple types of products are made on the same production lines. Although significant efforts have been devoted to studying flexible manufacturing systems (FMSs), most of the research contribute to the steady-state analysis. However, the transient performance is of critical importance for control and improvement of flexible systems, particularly, when the system’s setup times cannot be ignored. Therefore, in this article, an analytical method using approximation and aggregation procedures is introduced to evaluate the performance of flexible serial lines with Bernoulli machines and setups. Applying such a method, a long serial line is first decomposed into overlapped two-machine lines and then an iteration procedure is used backward and forward to estimate the line performance. Moreover, even in two-machine lines, the part sequence is approximated by the distribution of part types to reduce computation intensity. Using such a method, the system performance of long multiproduct Bernoulli lines with setups can be evaluated efficiently with an acceptable accuracy, which provides production engineers and managers an effective tool to study the transient performance of FMSs, and design real-time production control and improvement strategies.

The advancing digitalisation of production processes increases data availability and enables real-time information sharing between value-adding partners. However, despite the technological feasibility, information relevant for production control to initiate target-oriented countermeasures against disturbances are rarely shared with value-adding partners. To create incentives for companies to exchange information for short-term production control, the respective values of information must be determined. This publication presents a method for quantifying the value of information for production control in cross-company value-adding networks on a monetary basis. The input for the required performance measurement system is derived from a simulation model of the production system. Applying the approach to a simulative scenario validates the method’s functionality and the potential of information sharing to reduce disturbance cost.

Reverse engineering is needed to acquire knowledge of design that is lost, obsolete or withheld. Techniques have evolved from manual measurements, to utilizing the possibilities that lie within 3D scanning technologies. This paper surveys literature to map the possibilities and challenges connected to methodologies and technologies using 3D scanning for reverse engineering and production control. A case study on reverse engineering using a handheld 3D laser scanner is conducted to compare with the findings in literature. In the case study, a 3D printed component with complex internal features is 3D scanned and the point cloud is optimized before two different surface modelling techniques are tested. The dimensional errors of the output CAD design are mapped before the process and results are compared with the findings in literature. The findings of this paper show that using 3D scanning technologies for RE and PC is possible but significant challenges exists in developing accurate surface reconstruction algorithms that deals with point cloud imperfections like i.e., noise and holes. Using 3D scanning for RE purposes is found to be most suitable for components with complex geometry like free-form surfaces that are hard to measure manually.

As intelligent Data Acquisition and Analysis in Manufacturing nears its apex, a new era of Digital Twins is dawning. Foresighted Digital Twins enable short- to medium-term system behavior predictions to infer optimal production operation strategies. Creating up-to-the-minute Digital Twins requires both the availability of real-time data and its incorporation and serve as a stepping-stone into developing unprecedented forms of production control. Consequently, we regard a new concept of Digital Twins that includes foresight, thereby enabling situational selection of production control agents. One critical element for adequate system predictions is human behavior as it is neither rule-based nor deterministic, which we therefore model applying Reinforcement Learning. Owing to these ever-changing circumstances, rigid operation strategies crucially restrain reactions, as opposed to circumstantial control strategies that hence can outperform traditional approaches. Building on enhanced foresights we show the superiority of this approach and present strategies for improved situational agent selection.

This paper analyzes an optimal dynamic production control problem of a remanufacturing system in stochastic environment. The system consists of one inventory for serviceable items and one virtual inventory for the items used by customers which will be either remanufactured to be serviceable items or discarded. Demands will be lost if there is no serviceable items available. At any decision epoch, the decision maker has to decide whether to produce items or not by raw materials, so as to minimize the long run average cost. The optimization problem is constructed as a Markov decision process (MDP). We show that the optimal policy has a multi-threshold structure (switching curve) and it is monotonic in system parameters. Furthermore, based on the structure of the optimal policy, we construct a performance evaluation model for computing efficiently the optimal thresholds. The expression of the average cost is given by a quasi-birth-death (QBD) process. Finally, we provide some numerical results to show the effectiveness of our approach and the impact of different parameters on the optimal policy and average cost.

Since the reliability of production plans drops largely within several days after plan creation, production control faces huge challenges, when trying to foresee the work in progress (WIP) level at bottleneck machines and trying to react appropriately. Whereas several researchers applied artificial intelligence to predict lead times or transition times to improve the planning reliability, only small efforts have been taken on time series prediction in the field of production control, especially on the topic WIP prediction. In this paper univarate times series approaches are used for predicting the work in progress for a bottleneck machine for one and more step ahead. Long short-term memory recurrent neural networks, LSMT models show higher accuracy than classical methods. For more step ahead forecasting four different approaches are investigated. Systematical model tuning and comparison of various error measures are presented for a real industrial use case from the steal manufacturing industry.

Designing meat processing systems can be a complex process since this type of cyber-physical production system has two distinguishing properties: divergent product routings due to the cutting up of meat (known as co-production), and variability in the outcome of production processes (known as random yield). In this paper, we present a model-based design framework for meat processing systems, which can be used for performance prediction and system validation of a designed system. We show how an agent-based production control layer can be integrated into a model-based design architecture for meat processing systems. Finally, this framework describes how to route products through a system with co-production and random yield.

Multi-stage assembly systems where the demand for components depends on the market-driven demand for end products, are commonly encountered in practice. Production Planning and Control (PPC) systems for this production context include Kanban, Materials Requirement Planning (MRP), Optimised Production Technology (OPT), and Demand Driven MRP (DDMRP). All four of these PPC systems are widely applied in practice and literature abounds on each of these systems. Yet, studies comparing these systems are scarce and remain largely inconclusive. In response, this study uses simulation to assess the performance of all four PPC systems under different levels of bottleneck severity and due date tightness. Results show that MRP performs the worst, which can be explained by the enforcement of production start dates. Meanwhile, Kanban and DDMRP perform the best if there is no bottleneck. If there is a bottleneck then DDMRP and OPT perform the best, with DDMRP realising lower inventory levels. If there is a severe bottleneck, then the performance results for DDMRP and OPT converge. This identification of contingency factors not only resolves some of the inconsistencies in the literature but also has important implications for the applicability of these four PPC systems in practice.

Fierce global competition drives automated manufacturing systems (AMSs) to be increasingly complex, which poses significant challenges on performance analysis and production control. The multistage production via serial stations will lead to the propagation of failures in AMSs, which will affect system performance by triggering complex competitions among multiple failure modes. Although machine performance and product quality have been considered, very little has been done to investigate the effect of imperfect quality inspection on competing failures. Focusing on a time balance serial AMS, this article presents a new competing failure model to investigate the complex interactions among machine failures, product quality, and inspection process, which enables the characterizations of time-delayed propagation of failure, accumulation of degradation, and dynamics of states in serial AMSs. In order to further analyze the impact of competing behaviors on system performance, we have also developed decision diagram models and algorithms, which are evaluated and validated on serial AMSs with imperfect inspection, revealing the characteristic of multistate interactions. Experimental results show that the proposed methods have strong potentials for performance modeling and analysis of serial AMSs and also demonstrate general applicability for manufacturing decision making.

Production Planning and Production Control systems are some of the keys that determine the development of modern production systems. The article presents the importance of a flexibility factor in the process of manufacturing, planning, and control systems development during the 20th century. Finally, actual problems and trends in the production system design and control over the design were perceived in addition to possible feasible directions of the development of manufacturing systems, probably in the 21st century were specified. Production planning and production control are usually painstaking to be one of the most noteworthy issues in the planning and operation of a manufacturing structure. A better planning system has a significant bang on cost reduction, increased productivity, customer satisfaction, and overall spirited improvement for a product. Also, the current customer demand for prominent diversity products has put into an increase in product complications that further lay emphasis on necessitates for superior planning. Proficient planning leads to the amplification in capability exploitation competence and, therefore, thereby reducing the operational time required to intact jobs and accordingly escalating the profitability of an organization in the current spirited environment. There are different systems of manufacturing, planning, and control for a job-shop together with flow-shop in which the jobs are to be a progression through a series of machines for an optimizing number of required performance measures

In this paper, the problem of adaptive finite time formation control is investigated for double integrator multi-agent systems with uncertainties. Firstly, considering the multi-agent systems with uncertain dynamic reference and external bounded disturbance, a distributed adaptive estimator control algorithm is designed to realize formation tracking control in finite-time. It is important that the collision avoidance and maintaining connectivity of the multi-agent systems are realized by constructing an effective potential function based on distance constraints. On the other hand, the problem of formation production control for the double integrator systems is discussed with desired formation shape in finite-time. Achieving four control objectives is the main contributions in all the phases, including the estimation of uncertainties, collision avoidance, connectivity maintenance, and finite-time convergence. Finally, an application example of the formation production control is presented to verify accuracy of the proposed theoretical method.

The drive to improve performance and efficiency of internal combustion engines has greatly expanded the degrees of freedom of engine systems. As efficiency objectives exceed the capability of traditional combustion strategies, advanced combustion modes are more attractive for production. These advanced combustion strategies typically add sensors, actuators, and degrees of freedom to the combustion process itself. Spark-assisted compression ignition is an efficient production-viable advanced combustion mode characterized by a spark-ignited flame propagation that triggers autoignition in the remaining unburned gas. This research focuses on autoignition modeling for spark-assisted compression ignition combustion phasing control. This work comprehensively evaluates several autoignition model structures and identifies the real-time production control implications of each. The candidate models include four ignition delay correlations, an ignition delay lookup, three polynomial regressions, and an artificial neural network. All are computationally feasible using production controllers, but the artificial neural network model represents autoignition phasing significantly better than the other options evaluated. The polynomial regressions were similar in error and exceeded the accuracy of ignition delay models. The low performance of the induction time integral–based models stems primarily from the exclusion of low-temperature heat release. The regression models are also exercised on an experimental engine dataset to identify the impact of engine phenomenon such as charge stratification on the performance of each model structure. The trends in the model performance as well as the magnitude of the error were similar when evaluated on both spark-assisted compression ignition simulation data and homogeneous charge compression ignition experimental data.

An adaptive production control structure for failure-prone manufacturing systems under inventory and demand uncertainty is proposed. It contains estimation and forecasting modules incorporated into a control loop. The customer demand is unknown and its rate is composed of ramp-type, seasonal and random components. Information available to decision maker consists of imprecise inventory records, and the Kalman filter technique is used for estimating the inventory level and demand rate online from noisy inventory measurements. Estimates obtained are shown to converge to the actual values in stochastic sense. They are subsequently used for demand component forecasting, once the estimation errors become sufficiently small. A forecasting algorithm allows estimating ramp-type and seasonal demand components, together with their potential errors. Obtained estimates are incorporated into production control procedures, recently developed for manufacturing systems under variable and uncertain demand. Optimality conditions in the form of Hamilton-Jacobi-Bellman equations are obtained. A constructive numerical method for computing sub-optimal production policies is proposed and validated through numerical simulations.

In automotive paint shops, changes of colors between consecutive production orders cause costs for cleaning the painting robots. It is a significant task to re-sequence orders and group orders with identical color as a color batch to minimize the color changeover costs. In this paper, a Color-batching Resequencing Problem (CRP) with mix bank buffer systems is considered. We propose a Color-Histogram (CH) model to describe the CRP as a Markov decision process and a Deep Q-Network (DQN) algorithm to solve the CRP integrated with the virtual car resequencing technique. The CH model significantly reduces the number of possible actions of the DQN agent, so that the DQN algorithm can be applied to the CRP at a practical scale. A DQN agent is trained in a deep reinforcement learning environment to minimize the costs of color changeovers for the CRP. Two experiments with different assumptions on the order attribute distributions and cost metrics were conducted and evaluated. Experimental results show that the proposed approach outperformed conventional algorithms under both conditions. The proposed agent can run in real time on a regular personal computer with a GPU. Hence, the proposed approach can be readily applied in the production control of automotive paint shops to resolve order-resequencing problems.

Production planning and control (PPC) systems that employ aspects from both make-to-order (MTO) and make-to-stock (MTS) production control are known as hybrid MTS/MTO systems. While both MTO and MT...