Multi-agent reinforcement learning for online scheduling in smart factories

Rapid advances in sensing and communication technologies connect isolated manufacturing units, which generates large amounts of data. The new trend of mass customization brings a higher level of disturbances and uncertainties to production planning. Traditional manufacturing systems analyze data and schedule orders in a centralized architecture, which is inefficient and unreliable for the overdependence on central controllers and limited communication channels. Internet of things (IoT) and cloud technologies make it possible to build a distributed manufacturing architecture such as the multi-agent system (MAS). Recently, artificial intelligence (AI) methods are used to solve scheduling problems in the manufacturing setting. However, it is difficult for scheduling algorithms to process high-dimensional data in a distributed system with heterogeneous manufacturing units. Therefore, this paper presents new cyber-physical integration in smart factories for online scheduling of low-volume-high-mix orders. First, manufacturing units are interconnected with each other through the cyber-physical system (CPS) by IoT technologies. Attributes of machining operations are stored and transmitted by radio frequency identification (RFID) tags. Second, we propose an AI scheduler with novel neural networks for each unit (e.g., warehouse, machine) to schedule dynamic operations with real-time sensor data. Each AI scheduler can collaborate with other schedulers by learning from their scheduling experiences. Third, we design new reward functions to improve the decision-making abilities of multiple AI schedulers based on reinforcement learning (RL). The proposed methodology is evaluated and validated in a smart factory by real-world case studies. Experimental results show that the new architecture for smart factories not only improves the learning and scheduling efficiency of multiple AI schedulers but also effectively deals with unexpected events such as rush orders and machine failures.     

A flexible data schema and system architecture for the virtualization of manufacturing machines (VMM)

Future factories will feature strong integration of physical machines and cyber-enabled software, working seamlessly to improve manufacturing production efficiency. In these digitally enabled and network connected factories, each physical machine on the shop floor can have its ‘virtual twin’ available in cyberspace. This ‘virtual twin’ is populated with data streaming in from the physical machines to represent a near real-time as-is state of the machine in cyberspace. This results in the virtualization of a machine resource to external factory manufacturing systems. This paper describes how streaming data can be stored in a scalable and flexible document schema based database such as MongoDB, a data store that makes up the virtual twin system. We present an architecture, which allows third-party integration of software apps to interface with the virtual manufacturing machines. We evaluate our database schema against query statements and provide examples of how third-party apps can interface with manufacturing machines using the VMM middleware. Finally, we discuss an operating system architecture for VMMs across the manufacturing cyberspace, which necessitates command and control of various virtualized manufacturing machines, opening new possibilities in cyber-physical systems in manufacturing.     

Multi-agent framework based on smart sensors/actuators for machine tools control and monitoring

Throughout the history, the evolutions of the requirements for manufacturing equipments have depended on the changes in the customers’ demands. Among the present trends in the requirements for new manufacturing equipments, there are more flexible and more reactive machines. In order to satisfy those requirements, this paper proposes a control and monitoring framework for machine tools based on smart sensor, on smart actuator and on agent concepts. The proposed control and monitoring framework achieves machine monitoring, process monitoring and adapting functions that are not usually provided by machine tool control systems. The proposed control and monitoring framework has been evaluated by the means of a simulated operative part of a machine tool. The communication between the agents is achieved thanks to an Ethernet network and CORBA protocol. The experiments (with and without cooperation between agents for accommodating) give encouraging results for implementing the proposed control framework to operational machines. Also, the cooperation between the agents of control and monitoring framework contributes to the improvement of reactivity by adapting cutting parameters to the machine and process states and to increase productivity.     

Non-centralised control strategies for energy-efficient and flexible manufacturing systems

The manufacturing industry is transforming towards smart, energy-efficient, and flexible manufacturing systems. In this regard, this work deals with the design of non-centralised control architectures to improve the energy efficiency of such systems and to promote their flexibility. Based on both the configuration of manufacturing systems and their coupling dynamics, these systems are divided into sub-systems, from which smaller control problems can be stated. Thus, control/management strategies can also be modularised to confer more flexibility to manufacturing systems. Then, by using suitable distributed optimisation techniques, and properly defining the consensus stages among the local controllers, the outputs from such controllers are optimally coordinated to minimise the total energy consumption of the whole system. The proposed control strategies are tested in simulation for a typical process line of automotive parts manufacturing industry, in which the main processing units are machine tools. Based on the obtained results, manufacturing systems and their control strategies could be suitably modularised using non-centralised control schemes, from which a closed-loop performance similar to its centralised counterpart can be achieved.     

基于大数据的智能电网状态远程监测方法

智能电网作为一种智能化电力传输载体,在电力供应环节发挥了重要作用,因此保证其正常运行具有重要的现实意义。当前智能电网状态远程监测多与智能算法相结合,通过智能算法完成状态评估,常见的智能算法有神经网络、决策树以及支持向量机等,但这三种算法应用下,空间复杂度与时间复杂度较大。针对上述问题,提出一种基于大数据的自适应免疫粒子群算法智能电网状态远程监测方法。方法首先利用量测工具对智能电网状态信息量进行采集,然后对采集到的信息量进行处理,包括数据清洗、数据去噪、数据消减、数据标准化,最后利用自适应免疫粒子群算法实现智能电网健康状况评估。结果表明:与神经网络、决策树以及支持向量机三种算法相比,自适应免疫粒子群算法运行下,产生的空间复杂度与时间复杂度最小,分别为247.7 byte和154 s。     

Smart driver assistance system using raspberry pi and sensor networks

With the evolution of science and technology, monitoring human reactions and activities have become really easy and smooth. These new technologies have the potential to revolutionize the domain of safety and security in different realms of the society. Surveillance being the key factor of security measures has been elevated to a whole new level with the advancement in signal processing techniques. This paper basically focuses on the implementation of a smart surveillance system using signal processing and embedded tools which is applied in automobiles to ultimately develop the holistic driver assistance system. Earlier methods were based on physiological and analog data, but the present day scenario demands a smarter and digitalized working system so as to employ integrity and compatibility with other smart sub-systems like mobile phones and tablets. Transportation as we all know is one of the key sectors in the society. But the safety and security measures which people implement for their homes is not being employed for their vehicles. Apart from the vehicular anti-theft burglar systems, driver monitoring systems are also crucial to the lives of the driver and the passengers. Hence, this paper consists of three inter-linked modules which are the driver fatigue detection, alcohol content detection and vehicular crash detection along with control to monitor the driver's physiological state that can affect the vehicular control. A variety of input extraction hardware tools and software algorithms have been utilized in a collaborative way to implement this process.     

Interfacing CAD and CAM—A study in hole design

Computer Aided Design (CAD) and Computer Aided Manufacturing (CAM) are modern tools for both the designer and manufacturing engineer. These two tools, however, are not usually integrated into one system. In this study, an effort has been made to connect design and manufacturing by interfacing them into a unified software system. Through this demonstrative CAD/CAM package, the designer interacts with a graphics terminal to enter hole design details; these, in turn, are sent to a generative automatic process planning routing which defines appropriate process plans. In addition, a cost estimate is given which provides the designer with a measure of the economic effectiveness of his design. In the future, it will be possible to interface such systems with part programming routines to obtain explicit machine control information. Such a system represents a significant step toward making totally automated manufacturing a reality.     

OntoProg: An ontology-based model for implementing Prognostics Health Management in mechanical machines

Trends in Prognostics Health Management (PHM) have been introduced into mechanical items of manufacturing systems to predict Remaining Useful Life (RUL). PHM as an estimate of the RUL allows Condition-based Maintenance (CBM) before a functional failure occurs, avoiding corrective maintenance that generates unnecessary costs on production lines. An important factor for the implementation of PHM is the correct data collection for monitoring a machine’s health, in order to evaluate its reliability. Data collection, besides providing information about the state of degradation of the machine, also assists in the analysis of failures for intelligent interventions. Thus, the present work proposes the construction of an ontological model for future applications such as expert system in the support in the correct decision-making, besides assisting in the implementation of the PHM in several manufacturing scenarios, to be used in the future by web semantics tools focused on intelligent manufacturing, standardizing its concepts, terms, and the form of collection and processing of data. The methodological approach Design Science Research (DSR) is used to guide the development of this study. The model construction is achieved using the ontology development 101 procedure. The main result is the creation of the ontological model called OntoProg, which presents: a generic ontology addressing by international standards, capable of being used in several types of mechanical machines, of different types of manufacturing, the possibility of storing the knowledge contained in events of real activities that allow through consultations in SPARQL for decision-making which enable timely interventions of maintenance in the equipment of a real industry. The limitation of the work is that said model can be implemented only by specialists who have knowledge in ontology.     

Application of genetic algorithm to computer-aided process planning in distributed manufacturing environments

In a distributed manufacturing environment, factories possessing various machines and tools at different geographical locations are often combined to achieve the highest production efficiency. When jobs requiring several operations are received, feasible process plans are produced by those factories available. These process plans may vary due to different resource constraints. Therefore, obtaining an optimal or near-optimal process plan becomes important. This paper presents a genetic algorithm (GA), which, according to prescribed criteria such as minimizing processing time, could swiftly search for the optimal process plan for a single manufacturing system as well as distributed manufacturing systems. By applying the GA, the computer-aided process planning (CAPP) system can generate optimal or near-optimal process plans based on the criterion chosen. Case studies are included to demonstrate the feasibility and robustness of the approach. The main contribution of this work lies with the application of GA to CAPP in both a single and distributed manufacturing system. It is shown from the case study that the approach is comparative or better than the conventional single-factory CAPP.     

基于NI WSN的智能家居监控系统设计

随着物联网和计算机技术的不断发展,智能化、网络化、信息化是现代家居系统的必然发展趋势;将NI无线传感器网络(WSN)技术引入到智能家居监控系统的设计中,基于NI WSN系列产品进行了无线智能家居系统的总体框架、硬件型号和软件流程设计;系统的传感器节点分别采集盗情、烟雾、温湿度等参数,以无线形式通过网关将数据传输至上位机PC,在PC端利用Labview软件实现了智能家居防盗系统、火灾报警系统、环境舒适度等参数的实时在线监控,取得了良好的人机交互界面,并具有远程终端监控功能;该智能家居监控系统具备低功耗、实时性好、易扩展及可现实远程监控等优点,在智能家居领域具有广阔的市场前景和推广应用价值。     

Forward

A number of architectures can be used to integrate different components of a manufacturing enterprise such as machine tools, robots, and guided vehicles. The choice of architecture has a significant impact on system complexity, which in turn determines properties such as scalability, flexibility, fault-tolerance and modifiability. There is a need to develop metrics that quantify the complexity of a system that can serve as a means for comparing alternative architecture at the design stage. In this paper, we propose metrics used in software engineering to characterize the complexity of manufacturing systems. These metrics have been applied for measuring the complexity of two software systems: material delivery system and distributed scheduling.     

Optimizing smart manufacturing systems by extending the smart products paradigm to the beginning of life

The research objective of this work is to enhance the perception of, sensing in, and control of smart manufacturing systems (SMS) by leveraging active sensor systems within smart products during the manufacturing phase. Smart manufacturing utilizes rich process data, usually collected by the SMS (e.g., machine tools), to enable accurate tracking and monitoring of individual products throughout the process chain. However, until now, the to-be-manufactured product itself has not contributed to the sensing and compilation of product and process data. More specifically, data measured from the product’s structure during its own fabrication. In this paper, we discuss and evaluate the opportunity to actively use the capabilities of smart products within a SMS in terms of technical and economic feasibility. This opportunity emerged only recently with the advancements in smart products engineering. In this research, we developed a smart product prototype and evaluated it on a SMS testbed (CPlab) with eight distinct, fully-connected manufacturing processes. The results of the conducted experiments show the possibility to uniquely identify two distinct ‘fingerprints’ of manufacturing processes solely based on data provided by sensors within the smart product itself. The sensor data was collected directly from the smart product before manufacture was completed, yet after the intended sensor functionality during the product’s use phase was activated. The capability to automatically, accurately, and reliably identify process signatures and even inform the optimization of manufacturing parameters creates new opportunities for improvements in quality, scheduling, and seamless transparency across the whole value chain.     

Design and implementation of the secure compiler and virtual machine for developing secure IoT services

Recent years have seen the development of computing environments for IoT (Internet of Things) services, which exchange large amounts of information using various heterogeneous devices that are always connected to networks. Since the data communication and services occur on a variety of devices, which not only include traditional computing environments and mobile devices such as smartphones, but also household appliances, embedded devices, and sensor nodes, the security requirements are becoming increasingly important at this point in time. Already, in the case of mobile applications, security has emerged as a new issue, as the dissemination and use of mobile applications have been rapidly expanding. This software, including IoT services and mobile applications, is continuously exposed to malicious attacks by hackers, because it exchanges data in the open Internet environment. The security weaknesses of this software are the direct cause of software breaches causing serious economic loss. In recent years, the awareness that developing secure software is intrinsically the most effective way to eliminate the software vulnerability, rather than strengthening the security system of the external environment, has increased. Therefore, methodology based on the use of secure coding rules and checking tools is attracting attention to prevent software breaches in the coding stage to eliminate the above vulnerabilities. This paper proposes a compiler and a virtual machine with secure software concepts for developing secure and trustworthy services for IoT environments. By using a compiler and virtual machine, we approach the problem in two stages: a prevention stage, in which the secure compiler removes the security weaknesses from the source code during the application development phase, and a monitoring stage, in which the secure virtual machine monitors abnormal behavior such as buffer overflow attacks or untrusted input data handling while applications are running.     

STEP-NC based high-level machining simulations integrated with CAD/CAPP/CAM

With the development of manufacturing,numerical control(NC) machining simulation has become a modern tool to obtain safe and reliable machining operations.Although some research and commercial software about NC machining simulations is available,most of them is oriented for G&M code.It is a low-level data model for computer numerical control(CNC),which has inherent drawbacks such as incomplete data and lack of accuracy.These limitations hinder the development of a real simulation system.Whereas,standard for the exchange of product data-compliant numerical control(STEP-NC) is a new and high-level data model for CNC.It provides rich information for CNC machine tools,which creates the condition for an informative and real simulation.Therefore,this paper proposes STEP-NC based high-level NC machining simulations solution integrated with computer-aided design/computeraided process planning/computer-aided manufacturing(CAD/CAPP/CAM).It turned out that the research provides a better informed simulation environment and promotes the development of modern manufacturing.     

Design and implementation of a smart card based healthcare information system

Smart cards are used in information technologies as portable integrated devices with data storage and data processing capabilities. As in other fields, smart card use in health systems became popular due to their increased capacity and performance. Their efficient use with easy and fast data access facilities leads to implementation particularly widespread in security systems. In this paper, a smart card based healthcare information system is developed. The system uses smart card for personal identification and transfer of health data and provides data communication via a distributed protocol which is particularly developed for this study. Two smart card software modules are implemented that run on patient and healthcare professional smart cards, respectively. In addition to personal information, general health information about the patient is also loaded to patient smart card. Health care providers use their own smart cards to be authenticated on the system and to access data on patient cards. Encryption keys and digital signature keys stored on smart cards of the system are used for secure and authenticated data communication between clients and database servers over distributed object protocol. System is developed on Java platform by using object oriented architecture and design patterns.     

基于物联网的升降机远程监控平台

本设计是对现有升降机监控系统的信息化升级改造,实现升降机工作状态的数据采集与记录,并在本地显示器和远程监控平台上动态呈现和实时处理.整个系统分下位机数据采集和上位机软件监控两部分,下位机采集现场升降机PLC、变频器等工作参数,通过H7710(GPRS模块)发送到服务器的指定端口,数据接收采用Apache MINA框架,数据存储到oracle数据库.上位机监控软件采用B/S模式,用户根据所授予的权限能够实现对所属公司设备远程管理、信息查询、报警处理等操作.实际应用证明,该监控系统性能稳定,设计方法合理,可以广泛应用于升降机监控领域.     

基于数据融合智能检测的家居安全报警系统的设计

文章介绍了多传感器数据融合技术、智能检测系统的特点及智能家居安全报警系统软件的设计方法。文章采用PC机不同键盘信号来代替各传感器实时采集家庭的水、煤气、电、火情、偷盗、健康、抢劫、空气质量等报警信号。从键盘上直接输入信号，通过PC板卡型处理器，并进行数据融合后，做出正确的判断，从而根据不同的信号发出不同的报警响声。这种家用智能安全报警软件除可用于家庭外，也可用于大型室外设施场所。     

基于供应链的制造执行系统

针对以离散型加工装配企业为核心的供应链中各企业间信息共享的实际需求,开发了一种基于供应链的制造执行系统．它涵盖订货计划和制造执行两项主体功能．主机厂通过三层数据架构体系将订货计划或调整计划下达给外协厂,外协厂依据计划进行生产,并通过RFID技术将订单执行情况及时反馈给主机厂,为主机厂的下一步决策提供数据支持．     

Increasing productivity at Saturn

To remain competitive, manufacturing enterprises must increase and simultaneously reduce costs. This requires daily and long term examination and analysis of a plant's functions and operations. Using this data, an enterprise can identify production flow bottlenecks and analyze capacity and other factors, which in turn helps identify improvement opportunities. While such information is critical, it is often a challenge to obtain in a complex manufacturing environment. The automotive industry provides some prime examples of complex manufacturing environments. At Saturn Corp., we turned to academic research-work involving model integrated computing (MIC)-as a framework to organize the diverse types of data our information system must deal with. Using MIC and working with the Vanderbilt University researchers, Saturn built the Saturn Site Production Flow system. This system provides real time information-culled from 80000 data points-to Saturn personnel across the plant. Using SSPF provided information helped Saturn improve throughput at its plant by 10 percent. Through models, we can readily explain a complex data structure in a virtual view of a manufacturing plant floor. Diverse services are required for applications such as process monitoring and control, process simulation, statistical analysis packages, and other data manipulation tools. MIC integrates these tools into a common problem solving environment