Search

Tool condition monitoring (TCM) is a necessary action in a high-speed milling (HSM) process. As a worn milling tool might irreversibly damage a workpiece, there is a vital demand for a TCM system to evaluate the tool wear progress, or equivalently the resultant surface roughness, nonintrusively. To build up a condition monitoring system for HSM processes, sensor signals are to be utilized to form a reference model that reflects the performance of the system. Therefore, a desired reference model has to apply more efficient feature extraction and artificial intelligence techniques to be more repeatable and generalizable. This paper illustrates the performance of clustering techniques on high-speed end milling experimental data. Studied clustering methods are applied to the wavelet features of force and vibration signals to illustrate the repeatability of their results. It is shown that clustering methods can coarsely capture the status of the process and can be applied for fault diagnosis and TCM purposes. It is also discussed how the application of clustering methods may improve the performance of existing reference models toward the more efficient utilization of available experimental data and to develop easily generalizable reference models. Finally, a possible application of clustering results is discussed comparing with state-of-the-art papers.

The process of high speed milling is regarded as one of the most sophisticated and complicated manufacturing operations. In the past four decades, many investigations have been conducted on this process, aiming to better understand its nature and improve the surface quality of the products as well as extending tool life. To achieve these goals, it is necessary to form a general descriptive reference model of the milling process using experimental data, thermomechanical analysis, statistical or artificial intelligence (AI) models. Moreover, increasing demands for more efficient milling processes, qualified surface finishing, and modeling techniques have propelled the development of more effective modeling methods and approaches. In this paper, an extensive literature survey of the state-of-the-art modeling techniques of milling processes will be carried out, more specifically of recent advances and applications of AI-based modeling techniques. The comparative study of the available methods as well as the suitability of each method for corresponding types of experiments will be presented. In addition, the weaknesses of each method as well as open research challenges will be presented. Therefore, a comprehensive comparison of recent developments in the field will be a guideline for choosing the most suitable modeling technique for this process regarding its goals, conditions, and specifications.

In this paper, the viability of using Fuzzy-Rule-Based Regression Modeling (FRM) algorithm for tool performance and degradation detection is investigated. The FRM is developed based on a multi-layered fuzzy-rule-based hybrid system with Multiple Regression Models (MRM) embedded into a fuzzy logic inference engine that employs Self Organizing Maps (SOM) for clustering. The FRM converts a complex nonlinear problem to a simplified linear format in order to further increase the accuracy in prediction and rate of convergence. The efficacy of the proposed FRM is tested through a case study — namely to predict the remaining useful life of a ball nose milling cutter during a dry machining process of hardened tool steel with a hardness of 52–54 HRc. A comparative study is further made between four predictive models using the same set of experimental data. It is shown that the FRM is superior as compared with conventional MRM, Back Propagation Neural Networks (BPNN) and Radial Basis Function Networks (RBFN) in terms of prediction accuracy and learning speed.

The elective introduction of the computer integrated manufacturing (CIM) concept requires a coordinated effort to use and control the knowledge, information, data and material within an organization. This article describes a framework of an intelligent computer integrated manufacturing information and data exchange system, CIMIDES together with some of the research case studies undertaken jointly with industry. CIMIDES controls the flow of information and coordinates the activities of ten interrelated mini expert systems (MES) together with their data processing elements using the artificial intelligence, Al and blackboard paradigm. This paradigm is applicable to many complex tasks where several bodies of expertise must interact in harmony to resolve a complex problem of greater magnitude than any one of these MESs can effectively handle. The MESs communicate through a shared global database called the blackboard, rather than by communicating directly with one another. Using such methodology, the...

This article describes an intelligent knowledge-based object-oriented process planning (IKOOPP) system for the manufacture of progressive die plates. A die assembly is designed using a variety of standardised components based on a computer-aided design (CAD) system. A feature recognition module extracts all the pertinent geometrical properties and functional attributes of each machining feature from the CAD representation models. These properties and attributes are converted into an object-oriented representation. Knowledge of the functions of the machining feature allows process planning information to be automatically deduced. Specialised tool engineering knowledge are formulated as production rules or procedures to establish the required set of cutting tools, together with the machining allowances and sequence of operations.

Embryonic stem cells, ESC are the foundation for all the tissue and organ, in the body. They are unique and have the ability to differentiate into any type of cell in the human body. Large number of experiments is usually required in order to establish how stem cells can be effectively grown outside the body before they can be effectively used in regenerative medicine to cure life-style related diseases. These can range from the determination of the optimum growth factors to the cell differentiation mechanism. Such experiments if they were to be truly exhaustive are not only costly in terms of the scientist's effort but require large sterilised incubation space, particularly if they were to be carried out manually using Petri dishes based on 10 reagents - requiring a combination of 10! In order to comprehensively explore all the possible combination of the reagent and growth factors required, high throughput automated dispensing and high density micro-wells are critically required. The viability of the cells for large scale experiments depends on many factors. The main aim of the research describe in this paper is to establish the key factors to ensure cell viability. This include the determination of most effective number of wells per plate; its ideal size, diameter and depth; amount of fluid to contain; effective number of cells in a colony; level of humidity; salinity and evaporation rates of the medium. It is through these research findings, that a micro- fiuidic level sensing and dispensing system for cell cultivation is developed as a base for high throughput experiments [1].

In the mould making process, inevitable human error can arise with the authentication, verification, measurement, recording, programming and arrangement of electrodes prior to the electro-discharge machining (EDM) process. The focus of research is to develop effective methodologies that can proactively eliminate preventable errors. Cost-effective multi-sensor fusion techniques for the identification of electrodes; verification of the sequence and the precedence between the finishing, roughing and texturing tools used were developed and implemented in one of the largest mould-maker in Asia. This implementation in turn has further improved the performance of the EDM process, particularly in the manufacturing of large, fast turn around, high value engineered moulds. In addition, a verification and diagnostics engine to verify the identity and sequence of the electrodes placed on the automatic tool change (ATC) prior to the actual spark erosion process was developed. With the implementation of the prototype, Fu Yu Corp Ltd has reported that it is now possible for two operators to manage five EDM machines concurrently (instead of 3 machines), representing a direct benefit gain of 66%.

In the mould making process, inevitable human error can arise with the authentication, verification, measurement, recording, programming and arrangement of electrodes prior to the electro-discharge machining (EDM) process. Cost-effective multi-sensor fusion techniques for the identification of electrodes; verification of the sequence and the precedence between the finishing, roughing and texturing tools used are proposed in this paper. The focus of research is to develop effective methodologies that can effectively eliminate the preventive errors. This in turn will further improve the performance of the EDM process, particularly for high value engineered moulds. Multi-sensor fusion techniques for the extracting and correlating the data from three sensors, namely - barcode scanner, radio frequency identification (RFID) reader and proximity sensor are used. In addition, a verification and diagnostics engine to verify the identity and sequence of the electrodes placed on the automatic tool change (ATC) prior to the actual spark erosion process is developed. With the implementation of the prototype, Fu Yu Corp Ltd has reported that it is now possible for two operators to manage five EDM machines concurrently (instead of 3 machines), representing a direct benefit gain of 66%.

Diner-Waiter pattern has been proposed to improve the real-time performance and resource usage in distributed control. This paper further proposes an approach to enhance and implement the Diner-Waiter pattern in an agent framework with QoS being the time delay measured from the request is raised until the service is fulfilled. The time critical services are modelled and the evaluation criterion is given. An algorithm is proposed to dynamically change the preference list and routing rule for better Qos service providers. As the result, requests are routed to appropriate service providers in less time, and the interruption to the service providers (event processors) is reduced.

Embryonic stem cells, ESC are the foundation for all the tissue and organ, in the body. They are unique and have the ability to differentiate into any type of cell in the human body. Large number of experiments is usually required in order to establish how stem cells can be effectively grown outside the body before they can be effectively used in regenerative medicine to cure life-style related diseases. These can range from the determination of the optimum growth factors to the cell differentiation mechanism. Such experiments if they were to be truly exhaustive are not only costly in terms of the scientist's effort but require large sterilised incubation space, particularly if they were to be carried out manually using Petri dishes based on 10 reagents - requiring a combination of 10! In order to comprehensively explore all the possible combination of the reagent and growth factors required, high throughput automated dispensing and high density micro-wells are critically required. The viability of the cells for large scale experiments depends on many factors. The main aim of the research describe in this paper is to establish the key factors to ensure cell viability. This include the determination of most effective number of wells per plate; its ideal size, diameter and depth; amount of fluid to contain; effective number of cells in a colony; level of humidity; salinity and evaporation rates of the medium. It is through these research findings, that a micro-fluidic level sensing and dispensing system for cell cultivation is developed as a base for high throughput experiments.

Faced with stiff competition, regional mould makers are compelled to seek for cost effective methods to increase their performance in the production of large, error free and fully engineered moulds all within a very short lead-time - 4 weeks. One of the major challenges in mould making is associated with the pre-EDM (electro-discharge machining) activities. The EDM process itself is a highly accurate but slow process that uses a large variety of precisely machined electrodes for eroding thin walls and sharp pockets on both the cores and cavities. Most of the preventable errors arise during the setup of the electrodes, measurement of offset values, insertion of offset values into the EDM programme, validation of electrode sequence and exchange of work in progress status. This paper described an innovative, cost effective and easily adaptable shop-floor solution to eliminate all these potential errors together with the manual effort required. Five units of the Makino EDNC 65 EDM machine and the EROWA 2D pre-setter were tested on the prototype. With the implementation on 5 machines, Fu Yu Corp has reported that it is now possible for two operators to manage five EDM concurrently (instead of 3), representing a performance gain of 66%.

In order to remain highly competitive, mould makers are compelled to shorten lead-time to produce mistake free complex mould for high value quick-turnaround products. One of the critical processes in mould making is the electro-discharge machining (EDM) process, which uses a large variety of precisely machined electrodes for making thin walls and sharp pockets. Potential sources of errors, particularly from manual processes such as setup and presetting of electrodes, programme preparation, electrode sequence validation and management of a large amount of electrodes with relevant offset data, make it extremely difficult to meet the delivery lead-time. This paper describes an innovative low cost, easily adaptable shop-floor solution to eliminate manual intervention and potential errors. It can be easily integrated with existing brands and models of EDM machines and tool pre-setters. It eliminates all manual entry of critical data, provides a method to combine programme and to merge offset values for the available electrodes, and validates both the electrode sequence and the precedence relationships between the finishing and roughing tools. The system architecture, criteria for sensor selection, placement and data synchronization, together with sequence verification are also described. With the help of such a system, it is possible for operators to manage several EDM machines concurrently together with an avalanche of orders, electrodes and offset values without any stress.

A prototype twin-arm robot workcell has been developed for modular fixture assembly. Model-based robot programming plans collision free robot path, and generates an off-line program. A six-component force/torque sensor detects local frames in the real world. Automatic framing compensates the discrepancy between the ideal world in the CAD model and the real world. By means of active force control, automatic error recovery can be incorporated to enhance the reliability of robot operation. >

Component design and tool engineering functions are two sequentially related activities. Many additional benefits may arise if these activities can be effectively integrated together within a central environment. The principal aim of the research described in this paper is to develop a component design and tool engineering Intelligent Knowledge Based System (IKBS), called Holdex to demonstrate such a concept. It is an implementation designed to deduce the planning, design, tooling, procurement and scheduling information at the component design stage. It also assists the component designers in the operation of a Computer Aided Design (Cad) system and leads them towards the rationalisation of resources by encouraging standardisation of designs. A major benefit to arise from the provision of such assistance is to facilitate the tasks of executing the production engineering functions. The range of functions performed by Holdex includes the specification of a set of cutting tools; planning a set of pre-machining requirements; recommendation of the appropriate machine tool and manning level; and the automated design of fixtures. Towards this end, this research aims to provide a foundation for enabling industry to manufacture with the least amount of manual interpretation.