Adaptive Process Control and Optimization in Intelligent Manufacturing Systems

The basic requirement of production is to produce as many products as possible, at the lowest cost, with the highest possible quality. These requirements can be met with the new "Intelligent Production" paradigm. In particular, this paradigm involves the use of intelligent manufacturing systems and the introduction of intelligent production management. In this article, we'll look at intelligent manufacturing systems. The intelligent manufacturing system itself is a flexible manufacturing system that can flexibly respond to changes in production requirements as well as changes in its surroundings and interact with its surroundings. As a result of these flexible responses, there is less space, reduced production and investment costs, and increased productivity.

Pandemics like COVID-19 have created a spreading and ever-higher healthy threat to the humans in the manufacturing system which incurs severe disruptions and complex issues to industrial networks. The intelligent manufacturing (IM) systems are promising to create a safe working environment by using the automated manufacturing assets which are monitored by the networked sensors and controlled by the intelligent decision-making algorithms. The relief of the production disruption by IM technologies facilitates the reconnection of the good and service flows in the network, which mitigates the severity of industrial chain disruption. In this study, we create a novel intelligent manufacturing framework for the production recovery under the pandemic and build an assessment model to evaluate the impacts of the IM technologies on industrial networks. Considering the constraints of the IM resources, we formulate an optimization model to schedule the allocation of IM resources according to the mutual market demands and the severity of the pandemic.

Over recent decades, the demand for smarter and more intelligent manufacturing systems has increased in order to meet the growing requirements of customers. Manufacturing systems are termed as smart manufacturing systems (SMSs); these systems are capable of fully integrated autonomous operation. Specifically, the concept of autonomous systems and functions has been adopted for next generation manufacturing systems (NGMSs). Among these NGMSs, the fractal manufacturing system (FrMS) exhibits several characteristics that are similar to those of SMSs. Therefore, in this paper, a smart, self-reconfigurable manufacturing system (SSrMS) based on the FrMS is proposed. The proposed SSrMS architecture was designed for realizing self-reconfiguration functions based on the FrMS concept. SSrMS exhibits a fractal structure, which enables the distribution of control features; this also constitutes the fundamental basis of autonomous operation and reconfiguration between each fractal. SSrMS architecture includes the use of big data, digital facilities, and simulations. Furthermore, we introduce three reconfiguration methods to conduct system reconfiguration, which are a goal decision model, a negotiation model, and a sustainability assessment method. The goal decision model was developed to determine a goal of each fractal to achieve the system’s goal. In other words, each fractal can decide a goal to achieve the system’s goal, such as maximizing productivity or profit, or minimizing cost, and others. The negotiation model was adopted to perform partial process optimization by reassigning tasks and resources between the fractals, based on the goal of coping with the changes in the system’s condition. The sustainability assessment method was designed to simultaneously evaluate sustainability with respect to the system’s goals. The proposed architecture of SSrMS with goal decision model, negotiation model, and sustainability assessment method has the features of self-optimization, self-organization, and self-reconfiguration in order to achieve fully autonomous operations for the manufacturing system. The proposed architecture including three methods are expected to provide a fundamental study of the autonomous operations. The main findings of in this study is the development of a new architecture for fully autonomous operations of the smart manufacturing system with reconfiguration methods of goal-oriented manufacturing processes.

Agent and Multi-Agent system is one of the main research directions in distributed artificial intelligence. It has been considered that the Agent technology is an important method to build the model of distributed industrial system, the most natural way to design and implement the distributed Intelligent Manufacturing environment, and one of the significant technologies to construct the manufacturing system of next generation. The manufacturing system based on Agent is the specific application of the theory and method of multi-Agent system in manufacturing domain. On the basis of briefly summarizing the technology of Agent and Multi-Agent system, the architecture of Intelligent Manufacturing System based on Multi-Agent is put forward, among which, agent represents the basic processing entity. The scheduling optimization algorithm of Intelligent Manufacturing is provided, which is feasible proved by the result of stimulation experiment. Compared with the traditional artificial scheduling, it has distinct advantages. Finally, the model of communication and negotiation between Agents in the Intelligent Manufacturing System is studied, which utilizes the features of Agent such as autonomy, social interaction, response capability, preliminary capability, etc so that Intelligent Manufacturing System could make distributed decisions. The cooperation of system is completed by communication and negotiation. During the process of interaction, Agent is endowed with a role to meet the demand of flexibility of building models in the complicated process of Intelligent Manufacturing, as well as to construct an extended frame for reusable components.

In order to realize the automation, intelligence and optimization of the manufacturing process, the application and challenges of AI-driven intelligent manufacturing systems in production line automation have been proposed in order to improve the productivity, reduce the cost and enhance the product quality. The design and optimization of intelligent manufacturing system based on AI technology is a complex and important task, which needs to combine the key technologies of data acquisition and analysis, intelligent perception and recognition, task scheduling and optimization, automation and collaboration and intelligent optimization and decision support to realize the intelligence and optimization of manufacturing process. Application results show that: the application of artificial intelligence technology, but also according to the production changes and inventory, flexible deployment of raw materials and supplies, arrange the pace of production, a manufacturing automated production line through the implementation of artificial intelligence technology, to achieve the improvement of production efficiency, hourly output increased by 20 pieces, equipment utilization increased by 6%. Conclusion: Intelligent manufacturing system can reduce energy costs, improve resource utilization efficiency, improve production efficiency and reliability.

Present trends and issues in Japanese manufacturing and management

The manufacturing field is an area where the application of simulation is an essential tool for validating methods and architectures before applying them on the factory floor and the warehouse control. Multiagent system technology has demonstrated its utility in manufacturing system modelling and implementation. Agenthood features such as proactivity, reactivity, sociability and trust may also be useful for associating them with the specific simulation needs of the new manufacturing and warehouse management requirements. In this article, we present an agent-supported simulation tool for an intelligent manufacturing system and its influence with the management of the warehouse applied to a metal-mechanic manufacturing enterprise. The main goal is to provide a flexible simulation tool that can be adapted to solve the new manufacturing requirements and optimise and validate methods of management of material in warehouses that appear in real environments. Thus, the benefits of the multiagent theory application for the simulation of intelligent manufacturing and warehouse management system allows the experts of manufacturing domains to optimise the resource usage, control of inventory, providers and to have enough data to make decisions that influence the production level are presented.

The present work aims to promote the modernization of the real economy and facilitate the manufacturing industry to construct an intelligent manufacturing system. Analysis and evaluation are performed on the intelligent manufacturing system (IMS) of enterprises under the Internet of Things (IoT). First, the connotation and characteristics of machine learning (ML) in the era of IoT are explained, followed by the introduction to neural networks. Second, the optimization process of the neural network is described. Since it has no memory, the traditional deep neural network (DNN) needs to be improved. Then, the Generative Adversarial Network (GAN) is utilized to expand the sample data. Moreover, the confusion matrix is used in the indicator evaluation. The backpropagation neural network (BPNN) is optimized by the genetic algorithm (GA) to improve the network configuration and model performance. In addition, the connotation and development status of IMS are analysed, and the feasibility of applying deep learning to the evaluation of IMS is discussed. Finally, the evaluation model of IMS is designed and built via a neural network, which is ultimately verified in the simulation experiment. The experimental results indicate that the BPNN‐GA algorithm has advantages in predicting fitting accuracy, taking up less memory, and shortening training time; it can achieve generalization and accuracy in the forefront of optimal Pareto value, and the fitting accuracy attains 95.3%. The horizontal evaluation of IMS proves the effectiveness and feasibility of the evaluation model. This shows that the BPNN‐GA algorithm has an excellent evaluation effect on IMS. And the IMS evaluation model is applied to assess the IMS of sample enterprises. The evaluation results demonstrate that there are problems in the current manufacturing industry. For example, the transactions are challenging to be completed smoothly, information technology is updated slowly, and IMS is dependent on collecting resources.

The concept of an intelligent manufacturing system is proposed and described based on a comparison of manufacturing and biological organism systems. To promptly eliminate uncertain disturbances produced during the intelligent manufacturing system’s operation, an immune monitoring model for an intelligent manufacturing system is proposed that is analogous to a biological immune system mechanism. The implementation of immune recognition, assessment, learning, memory, and control regulation in response to abnormal disturbance factors is investigated. The system’s immune evaluation model based on the gray correlation analysis method is carefully analyzed. A neural network-based immune response method is used to deal with the disturbance. Finally, the paper shows how the effectiveness of the proposed method was verified experimentally through a simulation.

This paper deals with scheduling and planning in an intelligent manufacturing system. We have proposed self-organizing manufacturing systems which are composed of a number of autonomous modules. Each module decides output through the interaction with other modules. In this paper, we focus on a self-organizing conveyer system and apply an evolutionary computation method to path planning problems on its flexible transportation. There are two approaches to solve the path planning problems. One is global preplanning under the known work space. This global preplanning can obtain the optimal path, but cannot treat dynamic work space. The other is local decision making under the dynamic work space. Therefore, we must take into account the global optimization and local adaptability to reduce manufacturing cost. Consequently, we divide the path planning problem into some subproblems. The subproblems are locally solved by a genetic algorithm. Furthermore, we discuss the effectiveness of the proposed method through computer simulation.

RoBlock is the first phase of an internally financed project at the Institute aimed at building a system in which two industrial robots suspended from a gantry, as shown below, cooperate to perform a task specified by an external user, in this case, assembling an unstructured collection of coloured wooden blocks into a specified 3-dimensional pattern. The blocks are indentified and localised using computer vision and grasped with a suction cup mechanism. Future phases of the project will involve other processes such as grasping and lifting, as well as other types of robot such as autonomous vehicles or variable geometry trusses. Innovative features of the control software system include: ○ The use of an advanced trajectory planning system which ensures collision avoidance based on a generalisation of the method of artificial potential fields [1], ○ The use of a generic model-based controller which learns the values of parameters, including static and kinetic friction, of a detailed mechanical model of itself by comparing actual with planned movements [2], ○ The use of fast, flexible, and robust pattern recognition and 3D-interpretation strategies, ○ Integration of trajectory planning and control with the sensor systems in a distributed Java application running on a network of PC's attached to the individual physical components. In designing this first stage, the aim was to build in the minimum complexity necessary to make the system non-trivially autonomous and to minimize the technological risks. The aims of this project, which is planned to be operational during 2000, are as follows: ○ To provide a platform for carrying out experimental research in multi-agent systems and autonomous manufacturing systems, ○ To test the interdisciplinary cooperation architecture of the Maersk Institute, in which researchers in the fields of applied mathematics (modelling the physical world), software engineering (modelling the system) and sensor/actuator technology (relating the virtual and real worlds) could collaborate with systems integrators to construct intelligent, autonomous systems ○ To provide a showpiece demonstrator in the entrance hall of the Institute's new building. 1. CONSUMER-DRIVEN MANUFACTURING Intelligent Manufacturing Systems (IMS) address the needs of today's rapidly changing, consumer-driven market, where the demands of customers are moving towards more variants of models, and thus shorter production runs [3], which, based on research at Daimler-Chrysler, argues that conventional manufacturing control systems are not suited to handle this task, because such systems are either too difficult or too expensive to modify. This inflexibility is due to both product-specific control software and statically configured manufacturing equipment. This severely limits the generality and reusability of manufacturing systems even though they may be composed of highly flexible, reusable components such as industrial robots and machine tools. Until recently, such systems have been economic because they are optimal with respect to setup cost and project implementation-run cycles. This minimisation of the initial work load is achieved at the cost of much higher subsequent costs of modifying the system. This makes the idea of flexible, automatic production very attractive to forward-looking manufacturing companies.

Intelligent manufacturing plays a significant role in Industry 4.0. Dynamic shop scheduling is a key problem and hot research topic in the intelligent manufacturing systems, which is NP-hard. However, traditional shop scheduling mode, dynamic event prediction approach, scheduling model and scheduling algorithm, cannot cope with increasingly complicated problems under kinds of scales production disruptions in the real-world production. To deal with these problems, this paper proposes a new joint data-model driven dynamic scheduling architecture for intelligent workshop. The architecture includes four new and key characteristics in the aspects of scheduling mode, dynamic event prediction, scheduling model and algorithm. More specifically, the new scheduling mode introduces data analytics methods to quickly and accurately deal with the dynamic events encountered in the production process. The new prediction model improves the deep learning method, and further applies it predict the dynamic events accurately to provide reliable input to the dynamic scheduling. The new scheduling model proposes a new hybrid rescheduling and inverse scheduling model, which can cope with almost scales of abnormal production problems. The new scheduling algorithm hybridizes dynamic programming and intelligent optimization algorithm, which can overcome the disadvantages of the two methods based on the analysis of solution space. The dynamic programming is employed to provide high-quality initial solutions for the intelligent optimization algorithm by reducing the computation time greatly. To sum up, the presented architecture is a new attempt to understand the problem domain knowledge and broaden the solving idea, which can also provide new theories and technologies to manufacturing system optimization and promote the applications of the theoretical results.

Robotics and autonomous vehicles (AVs) represent the vanguard of intelligent systems in manufacturing, logistics, and transportation. These domains are increasingly driven by advances in data science big data pipelines, real‐time analytics, and machine learning and by emerging quantum neural networks (QNNs) that promise exponential feature spaces and novel optimization capabilities. This article presents a comprehensive framework for integrating classical AI, data science methodologies, and QNN architecture in robotics and AVs. We review the state of the art in sensing, perception, control, and decision‐making; detail hybrid classical–quantum pipeline designs; and expound technical methods for QNN‐enhanced perception and planning. Three industry case studies illustrate how these convergent technologies accelerate throughput, increase safety, and enable new service models. We assess economic, workforce, and innovation impacts under a future‐growth lens, and discuss cybersecurity, ethical, and regulatory considerations. A prioritized research roadmap outlines near‐term hybrid pilots and long‐term fault‐tolerant quantum ambitions. By combining theoretical depth, technical rigor, and practical applications, this article equips researchers and practitioners to harness robotics, AVs, data science, and QNNs for sustainable industry transformation.

Fostering Robust Human-Robot Collaboration through AI Task Planning

Traditional manufacturing systems implement paradigms to insert more flexibility and reconfigurability in their control structure. However, these concepts deliver flexibility from reconfiguring components to meet new demand at a higher granularity level. In these systems are specified control mechanisms with predictably utilizing resource functionality. The context of Industry 4.0 reveals environments of uncertainty and greater complexity, requiring proposals for emerging paradigms, such as Evolvable Assembly Systems (EAS), that treat modular components. On the other hand, Component I4.0 (I4.0C) standardizes resources in the virtual environment, especially when it comes to the coalition of functionalities, as they are created, organized throughout the life cycle of I4.0C. This work presents an architecture proposal to deal with these systems and mechanisms for self-organization of functionalities in manufacturing systems in the I4.0 context.