A knowledge-based inspection process planning system for coordinate measuring machines

The coordinate measuring machine (CMM) is one of the most effective geometry inspection facilities used in manufacturing industry. To fully utilize its capabilities in a computer-integrated manufacturing (CIM) environment, we should integrate CMM with other systems and facilities. This paper presents the development of a knowledge-based inspection planner based on the fundamental principles of AI planning to integrate computer-aided design systems and CMMs. The issues involved in CAD-directed inspection process planning are examined; the task of inspection process planning is decomposed into a number of sub-tasks. According to the task decomposition, a knowledge-based planning system was designed with several modules. Each of these modules consists of a knowledge base, a control operator, a context and a communication interface. The knowledge base is the local knowledge source for problem solving; the control operator determines when and where the knowledge is applied; the context contains the initial planning state which is essential input part information, the intermediate planning states which result from the tentative decision made by the modules, and the goal state. The module interfacing was realized by directly calling procedures defined in other modules to pass the planning tasks and decisions. Examples are included to explain the planning knowledge and strategy.     

Prospects for process selection using artificial intelligence

On problem facing modern industry is the lack of a skilled labor force to produce machined parts as has been done in the past. In the near future, this problem may become acute for a number of manufacturing tasks. One such task is process planning. Since process planning requires intelligent reasoning and considerable experiential knowledge, almost all existing computer aided process planning systems require a significant amount of supervision by an experienced human being.There is some prospect that “expert computer system” techniques from the field of Artificial Intelligence may be successfully used to automate (at least partially) several of the reasoning activities involved with process planning. This paper discusses some current prospects for automating a process planning task known as process selection. These ideas are currently being considered for use int he Automated Manufacturing Research Facility project at the U.S. National Bureau of Standards, and steps are being taken to implement them in an expert computer system.     

Optimizing task scheduling in human-robot collaboration with deep multi-agent reinforcement learning

Human-Robot Collaboration (HRC) presents an opportunity to improve the efficiency of manufacturing processes. However, the existing task planning approaches for HRC are still limited in many ways, e.g., co-robot encoding must rely on experts’ knowledge and the real-time task scheduling is applicable within small state-action spaces or simplified problem settings. In this paper, the HRC assembly working process is formatted into a novel chessboard setting, in which the selection of chess piece move is used to analogize to the decision making by both humans and robots in the HRC assembly working process. To optimize the completion time, a Markov game model is considered, which takes the task structure and the agent status as the state input and the overall completion time as the reward. Without experts’ knowledge, this game model is capable of seeking for correlated equilibrium policy among agents with convergency in making real-time decisions facing a dynamic environment. To improve the efficiency in finding an optimal policy of the task scheduling, a deep-Q-network (DQN) based multi-agent reinforcement learning (MARL) method is applied and compared with the Nash-Q learning, dynamic programming and the DQN-based single-agent reinforcement learning method. A height-adjustable desk assembly is used as a case study to demonstrate the effectiveness of the proposed algorithm with different number of tasks and agents.     

飞机故障知识的本体建模及语义检索

针对目前飞机维修保障工作中故障知识共享应用的实际困难,对飞机故障知识的表达建模以及检索应用进行了研究。依据飞机故障知识的领域特性和共享需求,采用本体作为知识表示的方法。根据本体组成元素分析了飞机故障本体的知识来源,并提出了飞机故障知识的本体工程构建方法。在本体模型的基础上,研究了飞机故障知识的语义检索模型,基于最近相邻检索策略提出了飞机故障本体的语义检索相似匹配算法及其实现流程。开发飞机故障知识管理原型系统并在某航空制造企业进行应用验证。     

基于扩展状态任务网的制造供应链计划

制造供应链计划是制造供应链管理的关键问题,它不仅需要分配生产任务和控制库存,还需要解决不同工厂(企业)间的运输配套问题.为统一描述具有复杂产品生产过程(包括装配型、分解型和多输入多输出型等)的生产任务、存储任务和不同模式(包括单种物料独立运输模式和多种物料组合运输模式)的运输任务,提出了扩展状态任务网(extended state task network,简称ESTN).扩展状态任务网用比例转化任务统一描述生产任务、存储任务和单种物料独立运输任务,用虚比例转化任务和组合移动任务共同描述多种物料组合运输任务.应用扩展状态任务网,meta启发式方法在求解制造供应链问题时更容易编码和操作.为求解基于ESTN的制造供应链计划模型,提出了具有多样性检测的参考解集更新策略与分散性解变异策略的路径重连算法.路径重连算法维护一个由高质量解(精英解)组成的参考解集,将一个向导精英解的属性逐步引入一个起始精英解而形成的中间解序列(路径),并用此中间解序列更新参考解集以获得进化.计算实例表明,该路径重连算法比标准遗传算法、标准Tabu搜索算法以及普通路径重连算法能够获得更好的解,证明了多样性检测对参考解集更新的关键作用以及分散性解变异策略在提高解的质量上的能力.     

USING REENGINEERING FOR KNOWLEDGE-BASED SYSTEMS

Reverse engineering, also called reengineering, is used to modify systems that have functioned for many years, but which can no longer accomplish their intended tasks and, therefore, need to be updated. Reverse engineering can support the modification and extension of the knowledge in an already existing system. However, this can be an intricate task for a large, complex and poorly documented knowledge-based system. The rules in the knowledge base must be gathered, analyzed and understood, but also checked for verification and validation. We introduce an approach that uses reverse engineering for the knowledge in knowledge-based systems. The knowledge is encapsulated in rules, facts and conclusions, and in the relationships between them. Reverse engineering also collects functionality and source code. The outcome of reverse engineering is a model of the knowledge base, the functionality and the source code connected to the rules. These models are presented in diagrams using a graphic representation similar to Unified Modeling Language and employing ontology. Ontology is applied on top of rules, facts and relationships. From the diagrams, test cases are generated during the reverse engineering process and adopted to verify and validate the system.     

一种利用工作流模型的分层任务网络规划领域建模方法

为了有效地获取和利用领域知识,提高规划效率,分析了工作流模型和分层任务网络(HTN)规划领域模型的相似性,提出了一种采用工作流模型进行规划领域建模,对领域知识进行获取和表达的方法.工作流模型中的行动和工作流模式,转换为HTN规划中的行动和任务分解;另外,引入了循环(Loop)工作流模式,转换为HTN规划中的递归调用,扩展了工作流模式对规划领域知识的表达能力.在典型的几个规划领域中,引入领域知识后大大提高了规划器的求解效率,从而验证了应用工作流模型进行规划领域建模的有效性.     

New methods of creating MBD process model: On the basis of machining knowledge

Traditional machining process planning, which passes manufacturing information through 2D drawing, fails to meet the requirement of current 3D manufacturing environment. Thus, model based definition technology, which uses 3D technology to upgrade the current manufacturing capacity, comes into being. This paper focuses on the creation methods of 3D machining process model. In the first place, the relation between machining knowledge and 3D modeling knowledge has been analyzed, establishing machining ontology and modeling ontology. Then, forward creation method and reversed creation method of machining-knowledge-based 3D process model are proposed. In forward creation method, to drive 3D modeling with machining knowledge, process model is created in commercial CAD platform with modeling ontology transferred from machining ontology for knowledge reasoning through the decision tree constructed from training set and test set. Reversed creation method is established by identifying and suppressing the volumetric machining features and surface machining features after building attributed adjacent graph of process model, and the machining knowledge contained in 3D process model is extracted for subsequent reuse. Finally, the validity of this method is verified with the proposed prototype system.     

Adaptability analysis of design for additive manufacturing by using fuzzy Bayesian network approach

The rapid development of Additive Manufacturing (AM) has been conspicuous and appealing towards manufacturing end-use products and components over the past decade. The continual advancement of AM has brought many advantages such as personalization and customization, reduction of material waste, cutting off the existence of special tooling during fabrication, etc. However, the AM approach has its limitations, such as a lack of knowledge of AM process activities and the progressive industrialization of AM, which makes the design process activities unstable, unpredictable, and have a limited effect. The concept of “design for AM (DFAM)” is increasing, which means we have the opportunity to concentrate almost totally on product functioning. Therefore, the entire design paradigm must be revised to accommodate new production capabilities, geometries, and parameters to avoid molding or machine tooling technology constraints. Few studies have attempted to provide systematic and quantitative knowledge of the relationship between these elements and the feasibility of the design process, making it difficult for designers to assess and control AM industrialization. For this reason, DFAM is needed to reform AM from rapid manufacturing to a mainstream manufacturing method. This paper put forward a framework based on the Fuzzy Bayesian Network (FBN) for DFAM decision-making. Twenty impact factors were encapsulated from experts’ experience and existing literature to investigate the potential adaptability of DFAM. The proposed approach uses expert knowledge and Fuzzy Set Theory (FST) presented with Triangular Fuzzy Numbers (FFN) to perceive the uncertainties. The Bayesian Network (BN) captures the causal relationships and dependencies among the impact components and analyzes the DFAM adaptability for robust probabilistic reasoning. A robot arm claw was used to show the effectiveness of our approach. The results showed that FBN could be used to guide DFAM adaptability in the manufacturing industry.     

A novel knowledge graph-based optimization approach for resource allocation in discrete manufacturing workshops

Dynamic personalized orders demand and uncertain manufacturing resource availability have become the research hotspots of intelligent resource optimization allocation. Currently, the data generated from the manufacturing industry are rapidly expanding. Such data are multi-source, heterogeneous and multi-scale. Transforming the data into knowledge to optimize the allocation between personalized orders and manufacturing resources is an effective strategy to improve the cognitive intelligent production level of enterprises. However, the manufacturing processes in resource allocation is diversity. There are many rules and constraints among the data. And the relationship among data is more complicated. There lacks a unified approach to information modeling and industrial knowledge generation from mining semantic information from massive manufacturing data. The research challenge is how to fully integrate the complex data of workshop resources and mine the implicit semantic information to form a viable knowledge-driven resource allocation optimization method. Such method can then efficiently provide the relevant engineering information needed for resource allocation. This research presented a unified knowledge graph-driven production resource allocation approach, allowing fast resource allocation decision-making for given order inserting tasks, subject to the resource machining information and the device evaluation strategy. The workshop resource knowledge graph (WRKG) model was presented to integrate the engineering semantic information in the machining workshop. A distributed knowledge representation learning algorithm was developed to mine the implicit resource information for updating the WRKG in real-time. Moreover, a three-staged resource allocation optimization method supported by the WRKG was proposed to output the device sets needed for a specific task. A case study of the manufacturing resource allocation process task in an aerospace enterprise was used to demonstrate the feasibility of the proposed approach.     

Legal modeling and automated reasoning with ON-LINE

In this paper we present a modeling approach to legal knowledge systems and its computational realization in the ON-LINE architecture. ON-LINE has modules for modeling legal sources, for storing and retrieving legal information and for reasoning with legal knowledge. The approach takes two perspectives: domain and task. In the domain perspective, a core ontology divides legal knowledge into five major categories: normative, world, responsibility, reactive and creative. For the normative knowledge, which is most typical of legal domains, we developed a new representation and inference formalisms which are an alternative to deontic logic. For the world knowledge, we argue for using a terminological knowledge representation language. The structure of the ontology is not a taxonomy, but a network of dependencies between the categories. These dependencies reflect the global structure of arguments in legal reasoning. In the task perspective, we followed a top-down approach using the CommonKADS modeling library. Design, planning and assessment were identified as typical tasks in the legal domain. For assessment, a model was specified and implemented.     

A multi-agent approach to process planning and fabrication in distributed manufacturing

In the paper a multi-agent approach to the development of a distributed manufacturing architecture is presented. An essential building block introduced here is the virtual work system (VWS) which represents a manufacturing work system in the information space. The VWS is structured as an autonomous agent and is a constituent entity of an agent network. In the network dynamic clusters of cooperating agents are solving manufacturing tasks. A machining work system and its VWS is demonstrated in a case study. Its role in the agent communication network is discussed in a process planning and fabrication domain.     

Learning process in a class of computer integrated manufacturing systems with parametric uncertainties

The paper is concerned with a class of manufacturing processes described by a relational knowledge representation containing unknown parameters. Two kinds of the manufacturing processes with different structures of material and task flow are considered. For these kinds the algorithms of learning and control for the central decision support computer system integrating the manufacturing process are presented. The learning process consists in using the results of step by step knowledge validation and updating to the determination of the current control decisions. The idea of learning described in the paper may be considered as a generalization of the known concept of the adaptive control using the results of current identification. Simple illustrative examples, results of simulations for a simple case and additional remarks concerning related problems are included.     

Decision making on the factory floor: An integrated approach to process planning and scheduling

Computers make accesible large amounts of information to the different levels of manufacturing organizations. However, this information can be of limited use if adequate decision making methodology is not applied. Very often, decisions made on the factory floor have a substantial impact on the performance of the entire manufacturing system. Process planning and scheduling are two activities that influence significantly these decisions. The common aspect of these activities is the assignment of various factory resources to the production tasks. The method presented in this paper seeks to use this commonality to integrate process planning and scheduling.     

Knowledge based manufacturing system (KBMS)

Production management, in batch type manufacturing environment, is regarded by the current research community as a very complex task. This paper claims that the complexity is a result of the system approach where management performance relies on decisions made at a too early stage in the manufacturing process. Decisions are made and stored in company databases by engineers who are neither economists nor production planner’s experts. This paper presents a new method where engineer’s task is not to make decisions but rather to prepare a knowledge-based “road map”. The road map method does introduce flexibility and dynamics in the manufacturing process and thus simplifies the decision making process in production planning. Each user will generate a routine that meets his/her needs at the time of needs by using KBMS CAPP. Thereby this method increases dramatically manufacturing efficiency.     

A cost-driven process planning method for hybrid additive–subtractive remanufacturing

Hybrid manufacturing combines additive manufacturing’s advantages of building complex geometries and subtractive manufacturing’s benefits of dimensional precision and surface quality. This technology shows great potential to support repairing and remanufacturing processes. Hybrid manufacturing is used to repair end-of-life parts or remanufacture them to new features and functionalities. However, process planning for hybrid remanufacturing is still a challenging research topic. This is because current methods require extensive human intervention for feature recognition and knowledge interpretation, and the quality of the derived process plans are hard to quantify. To fill this gap, a cost-driven process planning method for hybrid additive–subtractive remanufacturing is proposed in this paper. An automated additive–subtractive feature extraction method is developed and the process planning task is formulated into a cost-minimization optimization problem to guarantee a high-quality solution. Specifically, an implicit level-set function-based feature extraction method is proposed. Precedence constraints and cost models are also formulated to construct the hybrid process planning task as a mixed-integer programming model. Numerical examples demonstrate the efficacy of the proposed method.     

An integrated processing energy modeling and optimization of automated robotic polishing system

The automated robotic polishing system (ARPS) consisting of several robotic polishing cells (RPCs) is widely adopted in polishing industry to replace manual labor. Recently, energy-saving becomes a hotspot issue in manufacturing industry because of the increase in energy costs and requirement of environmental protection. Traditionally, robot motion planning and task scheduling are carried out separately and sequentially, which constrain the potential for energy-saving. In this paper, a task energy characteristic model is proposed as a polynomial function of the feedrate override to forecast the energy consumption of the polishing process of RPC, in which the designed parameters of the RPC and the polishing process parameters are encapsulated into the polynomial coefficients based on experimental data. Furthermore, an optimization model is proposed for an ARPS with mass tasks to minimize the energy consumption, in which the robot motion planning and the task scheduling are considered integratedly. An adaptive genetic algorithm with elite retention strategy is adopted to solve the optimization model. A case study is introduced to verify the proposed approach, which demonstrates the forecast error of task energy is less than 7%, and the proposed optimization approach can reduce the energy consumption of ARPS by more than 18% compared with the original processing scheme.     

Knowledge acquisition and integration tools aiming to support managerial planning in Greek SMEs

Most existing expert systems are defined in structured task domains. However, many real-life decision tasks are novel, unstructured and consequential. To support these tasks, expert systems are needed which provide an integrated environment capable of capturing new knowledge by updating the existing knowledge base. This paper describes the incremental development process of an expert system, from the initial gathering of data up to the development of knowledge acquisition tools and knowledge integration methodologies. The expert system developed addresses managerial planning tasks of Greek small-to-medium sized enterprises (SMEs). The manager sets values for parameters specifying environmental and company characteristics. The expert system responds with suggestions on feasible tactics, objectives and strategies. To cope with the changes of planning situations and also to improve the integrity of the knowledge base as the manager gains experience, knowledge acquisition tools have been introduced. These knowledge acquisition tools, which are manipulated directly by the manager, provide the system with additional knowledge and validate the knowledge already embedded in the knowledge base.     

Review of Intelligent Software Architectures for the Development of An Intelligent Decision Support System for Design Process Planning in Concurrent Engineering

Concurrent engineering (CE) is a strategy that attempts to process as many product development tasks in parallel and incorporate relevant life-cycle attributes as early as possible in the design phase in an effort to reduce the duration of design projects, save development costs, and provide better quality products. The CE environment is characterized by a high degree of distributed cognitive processing in the form of product development team structures. The distribution of appropriate knowledge to members of these teams and other participants in the design process for the purpose of supporting management and planning decisions is a considerably complex problem. New approaches and tools based on artificial intelligence methodologies are needed to deal with this level of complexity in coordinating knowledge resources. This paper reviews a number of potential candidates for an intelligent software architecture that can represent this type of problem as well as support the knowledge handling necessary to solve such problems. The selection of an appropriate architecture will support the development of an intelligent information system that is able to mimic human cognitive processes as the basic tool for providing decision-making support for planning and controlling a CE design process.