The global value creation networks have experienced increased volatility and dynamic behavior in recent years, resulting in an acceleration of a trend already evident in the shortening of product and technology cycles. In addition, the manufacturing industry is demonstrating a trend of allowing customers to make specific adjustments to their products at the time of ordering. Not only do these changes require a high level of flexibility and adaptability from the cyber-physical systems, but also from the employees and the supervisory production planning. As a result, the development of control and monitoring mechanisms becomes more complex. It is also necessary to adjust the production process dynamically if there are unforeseen events (disrupted supply chains, machine breakdowns, or absences of staff) in order to make the most effective and efficient use of the available production resources. In recent years, reinforcement learning (RL) research has gained increasing popularity in strategic planning as a result of its ability to handle uncertainty in dynamic environments in real time. RL has been extended to include multiple agents cooperating on complex tasks as a solution to complex problems. Despite its potential, the real-world application of multi-agent reinforcement learning (MARL) to manufacturing problems, such as flexible job-shop scheduling, has been less frequently approached. The main reason for this is most of the applications in this field are frequently subject to specific requirements as well as confidentiality obligations. Due to this, it is difficult for the research community to obtain access to them, which presents substantial challenges for the implementation of these tools. ...

No description available.

No description available.

<p>  </p> <p>Smart manufacturing is a broad concept of manufacturing technology that employs the computer aided systems, digital information technology, artificially intelligent algorithms, etc., to realize high-level automation of the production. The rise of the smart manufacturing concept, which has also been treated as the fourth industrial revolution, has been increasingly advocated by the policy makers and investigated by the worldwide researchers. Though machining is one of the key processes in the manufacturing industry, there are only a few researches focusing on automatically scheduling and improving the machining process. The design of the machining parameters and tool path planning still requires engineers with significant knowledge and experience in manufacturing fields to juggle between product quality, machine tool maintenance, and production cost. This design process also requires high level of human intelligence to consider the type of material, machine tool setups, workpiece geometry, and cutting tool property to provide an optimal manufacturing process. The overall machining related processes cannot satisfy the requirement of the ultimate goal of the smart manufacturing – to fully automate the machining process without human’s involvements.</p> <p><br></p> <p>In order to solve this problem, we aim to employ advanced machine learning technologies to enable the machine tool to automatically build up the cutting physics and generate the optimized toolpath. The final optimized result can be conducted automatically and shows a near human level optimization design ability. The generated toolpath beats the result from other commercial software. The overall framework can be fully automated when the machine learning technology is mature. </p>

In this thesis report, interactive algorithms aid in the analysis of fluid flows are presented. Special functions and algorithms to average, smooth, and calculate the similarity between digitized curves were developed. The developed routines process the images in the spatial domain, thereby eliminating the need to calculate discrete Fourier and inverse Fourier transforms. The algorithms are effective, efficient, and fast. As an integral part of the algorithms, special data buffer routines for the effective data manipulation of curves, as well as cursor routines, were developed. An arbitrary set of frames consisting of curves, or an arbitrary set of curves, can be averaged or smoothed. Curves can be smoothed with a modified, variable, convolution filter. A special function makes it possible to express the similarity of two curves in a numerical value. This technique can be used to study time effects in fluid flows. Noise reduction can be obtained by averaging and smoothing a set of curves. / Thesis / Master of Science in Manufacturing Engineering (MSMANFE)

No / Reconfigurable manufacturing systems (RMSs) are designed based on the current and future requirements of the market and the manufacturing system (MS). The first stage of designing an RMS at the tactical level is the evaluation of economic and manufacturing/operational feasibility. Because of risk and uncertainty in an RMS environment, this major task must be performed precisely before investment in the detailed design. The present paper highlights the importance of manufacturing capacity and functionality for the feasibility of an RMS design during reconfiguration processes. Due to uncertain demands of product families, the RMS key-design factors, i.e. capacity value, functionality degree and reconfiguration time, are characterized by the identified fuzzy sets. Consequently, an integrated structure of the analytical hierarchical process and fuzzy set theory is presented. The proposed model provides additional insights into a feasibility study of an RMS design by considering both technical and economical aspects. The fuzzy analytical hierarchical process model is examined in an industrial case study by means of Expert Choice software. Finally, the fuzzy multicriteria model is sensitively analysed within the fuzzy domains of those attributes, which are considered to be critical for the case study.

The present dynamic manufacturing environment has been characterized by a greater variety of products, shorter life-cycles of products and rapid introduction of new technologies, etc. Recently, a new manufacturing paradigm, i.e. Reconfigurable Manufacturing Systems (RMS), has emerged to address such challenging issues. RMSs are able to adapt themselves to new business conditions timely and economically with a modular design of hardware/software system. Although a lot of research has been conducted in areas related to RMS, very few studies on system-level control for RMS have been reported in literature. However, the rigidity of current manufacturing systems is mainly from their monolithic design of control systems. Some new developments in Information Technology (IT) bring new opportunities to overcome the inflexibility that shadowed control systems for years. Component-based software development gains its popularity in 1990's. However, some well-known drawbacks, such as complexity and poor real-time features counteract its advantages in developing reconfigurable control system. New emerging Extensible Markup Language (XML) and Web Services, which are based on non-proprietary format, can eliminate the interoperability problems that traditional software technologies are incompetent to accomplish. Another new development in IT that affects the manufacturing sector is the advent of agent technology. The characteristics of agent-based systems include autonomous, cooperative, extendible nature that can be advantageous in different shop floor activities. This dissertation presents an innovative control architecture, entitled Component-based Intelligent Control Architecture (CICA), designed for system-level control of RMS. Software components and open-standard integration technologies together are able to provide a reconfigurable software structure, whereas agent-based paradigm can add the reconfigurability into the control logic of CICA. Since an agent-based system cannot guarantee the best global performance, agents in the reference architecture are used to be exception handlers. Some widely neglected problems associated with agent-based system such as communication load and local interest conflicts are also studied. The experimental results reveal the advantage of new agent-based decision making system over the existing methodologies. The proposed control system provides the reconfigurability that lacks in current manufacturing control systems. The CICA control architecture is promising to bring the flexibility in manufacturing systems based on experimental tests performed. / Ph. D.

A Flexible Manufacturing System (FMS) is an integrated system consisting of several automated work centers interconnected by an automated material handling system. An integrated scheduling methodology is required to schedule all FMS sub-systems. The overall objective of this research was to develop a scheduling methodology to integrate job sequencing and Automatic Guided Vehicle System dispatching within a FMS environment. To develop the new scheduling methodology, the currently used AGVS controller decision set was examined and expanded. The expanded decision set gives the AGVS controller more options to choose from when scheduling the AGVS. The developed integrated scheduling methodology contains four steps. The first step determines which job is to be processed next by each work center based on job sequencing heuristics. The second step determines which work center is to be serviced next by the AGVS based on the estimated time till the work center is forced to stop production. The third step determines which specific job is to be serviced next by the AGVS by combining the work centers' processing orders and the work center servicing priorities. The fourth step decides which AGV is to transport the job requiring immediate service. Based on the preliminary study of a fictitious FMS, the new scheduling methodology showed a statistically significant increase in total job throughput, and a significant decrease in average flow time. Work center utilization also increased. A slight increase in unloaded AGV travel time was found, but was outweighed by the other benefits. / Master of Science

There are a large number of Group Technology (GT) based cell formation techniques in the literature, but their applications rare. It is hypothesized that the reason behind the lack of applications of these techniques in practice, is "fear of the unknown”. There have been a very limited number of attempts to determine the performance of any of the cell formation techniques. This thesis attempts to demonstrate a method to determine the performance of cell formation techniques by measuring the physical performance of the manufacturing cell. The methodology involves a manual evaluative approach to determine the cell performance from the data given for the system. The methodology presents selection of important Performance Measures (PMs), data requirement for the measurement of PMs and cell formation technique analysis. The performance measures to determine the performance of these techniques were selected according to their importance to the productivity of the manufacturing cell and their significance among GT principles. The cell formation techniques selected to demonstrate the method are Rank Order Clustering algorithm (ROC) and Production Flow Analysis (PFA). Using ROC and PFA, part families and machines groups were formed creating cell layouts. From the given data, performance measure values were calculated for a functional layout as well as ROC and PFA layouts. Performance of ROC and PFA layouts were compared to each other and to the functional layout. Results from the example show that performance improvement can be achieved by the two cell formation techniques in all the performance measures category except in flexibility. Performance of ROC and PFA are the same in the categories of setup time, machine utilization. and flexibility. The reason being, similar machine groupings and part families were achieved by both techniques for this example. Material handling performance and flexibility are dependent largely on machine grouping, whereas setup time is dependent on part families. Machine utilization and work-in-process are dependent on machine groups as well as part families. It appears PFA would have better performance in cases of complex problems having large number of machines and parts due to its comprehensiveness and ability to group machines according to the parts’ processing similarities. The advantage of ROC is mainly in its ease of application and rather elegant way of handling bottleneck machines and exceptional parts. Due to the lack of flexibility in GT layouts, system design and operation planning should be done carefully. / Master of Science

Presently there is a trend in manufacturing system design from stand-alone, automatic operations to Computer Integrated Manufacturing (CIM). The success of the integration depends largely on the performance of system control software. This document presents research in the design and implementation of a shop control system, for a CIM facility, using a new method called the three-layer integrated approach. Two basic techniques used in this research are expert systems and object-oriented programming. The CIM system at VPI is an automated manufacturing and assembly system. In designing the control system for this CIM facility, the design of products, production facilities, and overall system must be taken into account. In order to manage this complex system, a control system called the “shop controller” has been developed using C++, an object-oriented programming language. In addition, three real-time simulators for the cell controllers have been developed for testing and debugging the production rules of the expert system. The basic approach taken for the shop control system has several advantages: applied intelligence, program efficiency, reusability of code, and ease of maintenance. Moreover, this approach has a new feature—modularity, which is the result of combining expert systems and object-oriented programming. / Master of Science