Papers by Keyword: Expert System

Abstract: The simulation of hydro-mechanical billet pressing of bimetallic composite is performed. Using mathematical modeling and simulation exercise, the influence of the main operational parameters, which include: draw-forming, the cone angle of the working die and the conditions of contact friction, on the strain heterogeneity, damage to the fibers (cores), and the extrusion stress, is studied. A method and an expert system were developed that allowed to carry out a computational experiment and a multi-criteria choice of rational values of the technological experiment is carried out. The results of the study are used to improve the industrial production of multi-core bimetallic wires for electrical purposes.

Abstract: The paper presents and compares the results on the reliability and remaining life assessment of a reactor (coxing box) from a petrochemical plant. The reactor shell is made of 16Mo5 (W1.5423) steel, with a thickness of 25 mm, plated with 3 mm thick X6CrAl13 (W1.4002) stainless steel. The assessment was made in two steps. For preliminary remnant life assessment, specifications of section VII of the ASME code was used followed by iRiS‑Thermo expert system. Further, experimental creep and metallographic replica analysis were performed. Results comparison of the two methods applied revealed a reduction of the preliminary estimated remaining live obtained using metallographic replica analysis. Based on the results obtained, the possibility to extend the service duration of the coxing box in the safety condition, using current process parameters, with of 20.000 hours was highlighted.

Abstract: The huge industrial data recorded by several years in copper bioleaching operations represents an opportunity for the technology improvement. A systematic approach is being developed to get insights from the field data from an industrial process and to deliver the obtained knowledge with the aim to serve as the foundation for optimal industrial decision making even in presence of inherent process variations. The development of this Decision Support System (DSS) considers a Q-PCR array, a database for data logging and storage, the application of suitable statistical and computational tools for data analyses and knowledge acquiring and finally the creation of a system of knowledge translation to transform it into action (operational suggestions). The user can accurately retrieve data and design similar matches to the historic operation to get e.g. the expected metallurgical performance of a strip based on its mineralogical parameters. In addition, the user can get computed information and recommendations that should be analyzed. We will discuss the process followed to construct the base of knowledge of the DSS.

Abstract: The objective of this research is to develop the expert software to use for planning the production process and quality control. Starting from collecting the data of knowledge, and expertise experiences, to analyze, design, tests and record in systematic ways. By using the forward chaining inference and knowledge acquisition subsystem, writing with SQL and developing by Oracle to work on Unix server and exporting through Microsoft Excel for the convenient working. Process and decision procedures show after feeding the data into the system, for estimation and sending the results to program page. According to the set up pattern, experts spend 60 minutes for a piece of work manually. After introducing this system, experts are able to reduce time consumption by 98.33 %. Previously they spend 45 minutes/120 yards to check of fabric. Time consumption is reduced 55.55%, this means the increasing production result of 3,072 yards/day and the average cost is 61,440 baht/day. The investment is paid back within 26 days. This system can be used without experts who have estimation experiences. It does not need any specialized persons. This is the way to preserve the knowledge and solve the problems which may occur at the workplace. It is the foundation for managing the value added production system to be stable and sustainable.

Abstract: The requirements of CNC machine tools for the feed servo system could generally be summarized as high precision, well stability, fast response, wide range of speed regulation, high torque at low speed and so on. The PID controller of feed servo-system based on intelligent fuzzy control was presented based on traditional PID controller. The main feature of this arithmetic was to change parameters in different degrees according to time-varying working conditions, specially this arithmetic could change its domain intelligently according to different conditions and cooperated with a stable controller in case of system crash so that adaptivity and reliability of the feed servo-system were improved, also this feature made application field of the feed servo-system wider.

Abstract: This paper proposes a novel anytime fuzzy supervisory expert system for online signal processing. We demonstrate via simulations that this system is able to follow slowly varying signals and heal the signal in case of missing input data. In the presence of contaminating noise, the supervisory system performs the automatic wavelet shrinkage procedure selection, which ensures to pick the proper algorithm that is the most efficient in the given scenario. The necessary level of wavelet decomposition is determined online by the fuzzy supervisory expert. The system applies orthogonal wavelet functions in order to reduce significantly the processing time of reconstruction. The paper also shows how the online threshold estimator selection module ensures the highest denoising efficiency by selecting the most suitable algorithm.

Abstract: An accurate and fast flowchart of surface-mounted permanent magnet brushless machine (SPMBM) design based on exact analytical method (EAM) rivaling finite element method (FEM) is formally proposed in this paper. It is recognized as a promising expert system for the preliminary electromagnetic design of SPMBM, even to replace the conventional design flowchart using equivalent magnetic circuit method (EMCM). By applying this expert system aiming at the low cogging torque and high power density, a special SPMBM named electronically commutated permanent magnet synchronous DC machine (PMSDCM) with conventional DC armature winding is put forward and verified based on both the simulation and experiment.

Abstract: According to the characteristics of the large equipment, electromagnetic interference, using neural network method is put forward a set of for large electronic equipment electromagnetic coupling and interference, the analysis of the expert system based on the large electronic equipment as analysis object, the common interference on the interference classification and coding, the BP neural network is constructed, using neural network, the inference mechanism of expert system for the optimization design, and test verification.

Abstract: This paper briefly recommends the conception and syntax construction of the expert system language – CLIPS. Aim at fault happening mode, the paper build up fault analysis model of certain self-propelled gun servo system with CLIPS, compiled knowledge base and reasoning engine, realized embedded programming of CLIPS, and illuminated the application of CLIPS in fault diagnosis of self-propelled gun servo system.

Abstract: Environmental parameter control is a common case in the technique of computer measurement and control, which has been widely applied to the practice of industrial and agricultural production. PID refers to one of the algorithms commonly used in temperature control, while the setting of PID parameters is the key to the algorithm. As one of the most successful branches in artificial intelligence technology application, expert system can simulate the thinking process of human experts by making use of the experience and expertise accumulated by experts for years, so as to resolve difficult problems that can only be settled by experts. An application scheme of expert system to PID thermostatic control is proposed by this paper for the purpose of making thermostatic control more convenient and intelligent.