A knowledge-based simulation environment for hierarchical flexiblemanufacturing

This article presents an approach to embedding expert systems within an object oriented simulation environment. The basic idea is to create classes of expert system models that can be interfaced with other model classes. An expert system shell is developed within a knowledge-based design and simulation environment which combines artificial intelligence and systems modeling concepts. In the given framework, interruptible and distributed expert systems can be defined as components of simulations models. This facilitates simulation modeling of knowledge-based controls for flexible manufacturing and many other autonomous intelligent systems. Moreover, the structure of a system can be specified using a recursive system entity structure (SES) and unfolded to generate a family of hierarchical structures using an extension of SES pruning called recursive pruning. This recursive generation of hierarchical structures is especially appropriate for design of multilevel flexible factories. The article illustrates the utility of the proposed framework within the flexible manufacturing context     

A distributed time-driven simulation method for enabling real-time manufacturing shop floor control

This paper proposes a distributed simulation approach for scheduling discrete-events in manufacturing shop floors. The proposed approach employs a time-driven method to simulate occurrence of discrete-events using distributed entities that replicate physical entities in the manufacturing shop floor. In specific, the proposed approach iteratively controls the timing of discrete-events occurrence using a control theoretic model. In this approach, changing the speed of the simulation clock, termed time-scaling factor, can accelerate or decelerate the simulation speed resulting in simpler synchronizations of discrete-events and faster simulation than standard distributed discrete-event simulations according to the capability of the communication networks. Computational experiments are conducted to test the performance of the proposed system with different values of the time-scaling factor, and the relationship between the system performance and the time-scaling factor is investigated through analysis of the system model. Results obtained from the computational experiments show significant successes in speeding up discrete-event simulations in such a way that the proposed approach can be used for the control of manufacturing shop floors, providing real-time decision supports.     

A knowledge intensive multi-agent framework for cooperative/collaborative design modeling and decision support of assemblies

Multi-agent modeling has emerged as a promising discipline for dealing with decision making process in distributed information system applications. One of such applications is the modeling of distributed design or manufacturing processes which can link up various designs or manufacturing processes to form a virtual consortium on a global basis. This paper proposes a novel knowledge intensive multi-agent cooperative/collaborative framework for concurrent intelligent design and assembly planning, which integrates product design, design for assembly, assembly planning, assembly system design, and assembly simulation subjected to econo-technical evaluations. An AI protocol based method is proposed to facilitate the integration of intelligent agents for assembly design, planning, evaluation and simulation process. A unified class of knowledge intensive Petri nets is defined using the O-O knowledge-based Petri net approach and used as an AI protocol for handling both the integration and the negotiation problems among multi-agents. The detailed cooperative/collaborative mechanism and algorithms are given based on the knowledge objects cooperation formalisms. As such, the assembly-oriented design system can easily be implemented under the multi-agent-based knowledge-intensive Petri net framework with concurrent integration of multiple cooperative knowledge sources and software. Thus, product design and assembly planning can be carried out simultaneously and intelligently in an entirely computer-aided concurrent design and assembly planning system.     

A lab-scale manufacturing system environment to investigate data-driven production control approaches

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.     

A framework for intelligent design of manufacturing cells

One of the major thrusts of agile/lean/responsive manufacturing strategies of the twentyfirst century is to introduce advanced information technology into manufacturing. This paper presents a framework for robust manufacturing system design with the integration of simulation, neural networks and knowledge-based expert system tools. An operation/ cost-driven cell design methodology was applied to concurrently consider cell physical design and the complexity of cell control functions. Simulation was exercised to estimate performance measures based on input parameters and given cell configurations. A rulebased expert system was employed to store the acquired expert knowledge regarding the relation between cell control complexities, cost of cell controls, performance measures and cell configuration. Neural networks were applied to predict the cell design configuration and corresponding complexities of cell control functions. Training of neural networks was performed with both forward and backward methods by using the same pair of data sets. Hence, trained neural networks will be able to predict either input or output parameters. This innovative new design methodology was illustrated via a successful implementation exercise resulting in actually acquiring an automated cell at industrial settings. The experience learned from this exercise indicates that the proposed design methodology works well as an effective decision support system for cell designers and the management in determining appropriate cell configuration and cell control functions at the design stage.     

大型高空台进排气控制半物理仿真系统设计

为构建大型复杂高空模拟试车台进排气控制半物理仿真系统,提出了仿真模型和实物部件相结合的系统设计方法。依据系统结构组成及工作机理统筹规划系统仿真模型和实物部件,利用理论建模、系统辨识方法建立仿真模型,并基于PLC完成系统设计和软件开发,最终将仿真模型和实物部件高效统一形成半物理仿真试验台。通过仿真平台实现了系统一体化虚拟仿真,结果表明系统运行可靠稳定,能够准确模拟真实发动机试车过程。     

Automatic generation of IDEF0 models

This paper looks into a new area for knowledge-based system application, that of manufacturing modelling. Manual generation of IDEF0 models of manufacturing systems is time-consuming and inconsistent. However, the process can be automated to improve timeliness and consistency. In this paper, a knowledge-based manufacturing modelling system for the automatic generation of IDEF0 models is proposed. The system will not only greatly reduce the IDEF0 modelling time but will also eliminate the inconsistency problem of conventional IDEF0 modelling systems. The paper explains the knowledge-based approach and identifies the kinds of domain knowledge that are required for the construction of the knowledge-based manufacturing modelling system.     

Smart shop floor scheduling using knowledge based simulation

In this paper, the need for knowledge-based simulation technique in shop floor scheduling are addressed. A prototype integrated system in Feed Mill manufacturing utilizing an integrated approach of Artificial Intelligence (AI) and simulation is discussed. The system is designed to support the production planner in scheduling and controlling the shop floor on real-time and on-line basis. System overview with the emphasis on knowledge-based simulation module is described.     

基于数字孪生的智能车间系统仿真加速测试方法

为解决当前制造系统软件可靠性仿真测试时间长、测试环境难以搭建等问题,提出采用数字孪生技术与智能车间系统仿真加速测试相结合的方法;建立智能车间高保真数字孪生模型替代现实生产车间系统用于制造系统软件的可靠性仿真测试,首先要构建包含产品、设备资源、工艺流程等系统级仿真模型;同时,为仿真车间生产事件流程,在模型中,还需结合生产实际情况,设置设备间通信协议、通信数据以及生产线事件及队列顺序,真实模拟系统运行环境;通过构建步进电机产线数字孪生模型,仿真加工装配流程,运行智能车间系统软件,采用仿真时钟推进机制开展加速测试,验证了该方法的有效性和实用性,对开展工业系统软件高保真快速测试评估具有一定的借鉴意义。     

Frame-based architectures for manufacturing planning and control

Effective manufacturing planning and control (MPC) necessitates coordination and integration of various aspects of demand, production and logistics management. A holistic approach is therefore the key to success in this field. A frame-based architecture should be ideally suited to constructing knowledge-based systems for MPC, as frames can represent entities in the planning process, rules can express interrelationships between these entities, and the planning strategy is paralleled by the inference procedure. Four applications are described in detail by means of four frame-based paradigms: design of an operations regime; project planning of a new product launch; configuration of a process cell; and an analysis of the operation of an integrated manufacturing system. These architectures, and others presented in a previous article, are categorized as examples of generic tasks, a methodology proposed by Chandrasekaran¹² which defines underlying structures in terms of system goals, input/output characteristics, knowledge representation and inference strategy. The generic task approach appears to be useful in determining an appropriate architecture for a given MPC task, and also for designing and implementing the resultant knowledge-based system.     

基于虚拟化技术的卫星控制系统软件构件库运行监控与可信验证技术

动态系统建模工具可以按照设定的仿真步长对控制器的行为动态模拟,也可以在仿真环境下模拟控制器所在的系统架构和动态数据交互,因此传统的卫星控制系统方案设计时一般采用在同一模型建模体系进行,并进行相应的控制算法设计。但是由于动态系统建模工具其自身的时钟步长和数据流处理逻辑,不能完全模拟目标机的内部ALU逻辑和真实外围设备工作行为,可能与真实物理环境要求的系统有一定的出入,造成对承载卫星控制器功能的目标机CPU处理系统存在一定程度的失真,影响仿真效果。提出了一种基于虚拟化技术的卫星控制系统软件构件库可信验证技术,使用虚拟化技术实现对真实物理目标机功能的完全模拟,运用软件非干涉运行监控技术,获取可信的开发证据和应用证据,利用协同仿真组件和卫星控制系统方案设计的控制算法模型对各个软件构件进行动态同步仿真验证。     

Design patterns for real-time distributed control system benchmarking

In this paper, we describe the design and development of a simulation–agent interface for real-time distributed control system benchmarking. This work is motivated by the need to test the feasibility of extending agent-based systems to the physical device level in manufacturing and other industrial automation systems. Our work focuses on the development of hybrid physical/simulation environment that can be used to perform tests at both the physical device level, as well as the planning and scheduling level of control. As part of this work, we have extended the proxy design pattern for this application. This paper focuses on the resulting software design pattern for distributed control system benchmarking and provides examples of its use in our hybrid physical/simulation environment.     

基于混杂系统理论的制造系统仿真

根据制造系统连续事件与离散事件并存的特点,提出一种制造系统半实物仿真方法,设计连续事件和离散事件并存时仿真系统的时间推进机制。在Arena环境中实现对离散事件系统的建模,在Labview环境中实现特定连续变量事件的半实物仿真。设计并实现离散事件系统与连续事件的接口连接。仿真实验结果表明,该系统能较好地反映出整个制造系统的混杂特性,为混杂制造系统的仿真提供一种新的思路。     

A knowledge-based decision support system for the management of parts and tools in FMS

Flexible manufacturing systems (FMS) are very complex systems with large part, tool, and information flows. The aim of this work is to develop a knowledge-based decision support system (KBDSS) for short-term scheduling in FMS strongly influenced by the tool management concept to provide a significant operational control tool for a wide range of machining cells, where a high level of flexibility is demanded, with benefits of more efficient cell utilization, greater tool flow control, and a dependable way of rapidly adjusting short-term production requirements. Development of a knowledge-based system to support the decision making process is justified by the inability of decision makers to diagnose efficiently many of the malfunctions that arise at machine, cell, and entire system levels during manufacturing. In this context, this paper proposes three knowledge-based models to ease the decision making process: an expert production scheduling system, a knowledge-based tool management decision support systems, and a tool management fault diagnosis system. The entire system has been created in a hierarchical manner and comprises more than 400 rules. The expert system (ES) was implemented in a commercial expert system shell, Knowledge Engineering System (KES) Production System (PS).     

A virtual prototyping system for rapid product development

This paper describes a virtual prototyping (VP) system that integrates virtual reality with rapid prototyping (RP) to create virtual or digital prototypes to facilitate product development. The proposed VP system incorporates two new simulation methodologies, namely the dexel-based and the layer-based fabrication approaches, to simulate the powder-based and the laminated sheet-based RP processes, respectively. The dexel-based approach deposits arrays of solid strips to form a layer, while the layer-based approach directly forms a complete layer by extruding the slice contours. The layer is subsequently stacked up to fabricate a virtual prototype. The simulation approaches resemble the physical fabrication processes of most RP systems, and are therefore capable of accurately representing the geometrical characteristics of prototypes. In addition to numerical quantification of the simulation results, the system also provides stereoscopic visualisation of the product design and its prototype for detailed analyses. Indeed, the original product design may be superimposed on its virtual prototype, so that areas with dimensional errors beyond design limits may be clearly highlighted to facilitate point-to-point analysis of the surface texture and the dimensional accuracy of the prototype. Hence, the key control parameters of an RP process, such as part orientation, layer thickness and hatch space, may be effectively tuned up for optimal fabrication of physical prototypes in subsequent product development. Furthermore, the virtual prototypes can be transmitted via the Internet to customers to facilitate global manufacturing. As a result, both the lead-time and the product development costs can be significantly reduced.     

航天器主动热控制系统辐射散热的半物理仿真

该文提出在主动式热控制系统的地面动态实验中用半物理仿真的方法模拟在轨热辐射环境和辐射散热器。文中给出了半物理仿真系统的设计方案,用伪组件代替辐射散热器连接在真实回路中,用虚拟组件在计算机中模拟真实的在轨热辐射环境和辐射散热器的运行,并通过测控系统控制伪组件的运行状态。文中给出了虚拟组件和伪组件的设计与实现。实验结果表明这种方案能够准确地模拟出热辐射环境对热控制系统运行的影响。     

Mathematical programming representation of pull controlled single-product serial manufacturing systems

Pull policies may perform quite differently depending on the particular manufacturing system they must control. Hence, it is clear the necessity of having efficient performance evaluation models to select the best control policy in a specific context. This paper proposes a mathematical programming representation of the main pull control policies applied to single-product serial manufacturing systems. The proposed models simulate the pull controlled system in the sense that, if instantiated with the same parameter values as in a simulation model, their solution gives the same event sequence of the simulation. The proposed mathematical representation is also used for a formal comparison of the considered pull control policies. The new models presented in this paper can represent a base to build new efficient optimization algorithms for the design of pull controlled production systems.     

Simulation and knowledge based objects

A knowledge-based simulation model was developed by using a hypertext-like semi-object-oriented environment (SuperCard^TM). This environment enabled the building of a tightly coupled knowledge representation scheme and simulation algorithm. Our knowledge-based simulation model combines three different paradigms: production rules, an inference engine, and knowledge-based objects. The production rule paradigm is used as the basis for describing and coding the processes to be simulated. The knowledge-based objects are built as the active objects of the simulation. A knowledge-based object has a number of rules that support its behavior and an agenda that defines its goals. A knowledge-based object then proceeds in the simulation process (via the inference engine) until its goals are achieved. Since an inference engine with a knowledge base is built into the simulation process, such a system has the ability to reason about the behavior of the model. In addition, the knowledge-based simulation model has a friendly user interface. This enables changing the parameters of the simulation model without doing any programming. The inference engine in the knowledge-based simulation combines backward chaining, decision lattices, and links so as to produce an overall pattern of inference that is as efficient as possible.     

A digital twin to train deep reinforcement learning agent for smart manufacturing plants: Environment,interfaces and intelligence

Filling the gaps between virtual and physical systems will open new doors in Smart Manufacturing. This work proposes a data-driven approach to utilize digital transformation methods to automate smart manufacturing systems. This is fundamentally enabled by using a digital twin to represent manufacturing cells, simulate system behaviors, predict process faults, and adaptively control manipulated variables. First, the manufacturing cell is accommodated to environments such as computer-aided applications, industrial Product Lifecycle Management solutions, and control platforms for automation systems. Second, a network of interfaces between the environments is designed and implemented to enable communication between the digital world and physical manufacturing plant, so that near-synchronous controls can be achieved. Third, capabilities of some members in the family of Deep Reinforcement Learning (DRL) are discussed with manufacturing features within the context of Smart Manufacturing. Trained results for Deep Q Learning algorithms are finally presented in this work as a case study to incorporate DRL-based artificial intelligence to the industrial control process. As a result, developed control methodology, named Digital Engine, is expected to acquire process knowledges, schedule manufacturing tasks, identify optimal actions, and demonstrate control robustness. The authors show that integrating a smart agent into the industrial platforms further expands the usage of the system-level digital twin, where intelligent control algorithms are trained and verified upfront before deployed to the physical world for implementation. Moreover, DRL approach to automated manufacturing control problems under facile optimization environments will be a novel combination between data science and manufacturing industries.