Papers by Keyword: Case-Based Reasoning (CBR)

Abstract: The efficiency of design has significant impact on the overall lead time for the new product of heavy industry machinery. Case-based reasoning (CBR) can be used to heavy industry machinery design for improving the effectiveness of design. However, CBR is short of flexibility to cope with the semantic retrieval, which is the main cause of the decline in the efficiency and accuracy. Confronted with the problem, the approach has been developed based on the combining ontology and retrieval in case-based reasoning for heavy industry machinery design. Through incorporating ontology with CBR, the paper provides a flexible and comprehensive operation. An example case study of rotary drilling rig demonstrates the potential which the proposed method is more effective to retrieve cases on the semantic level.

Abstract: This study aims to assist the semiconductor assembly and testing industry in finding the best way of talent training. Firstly, the analysis of competency designs the training path according to engineers' different realms, introduces Case-Based Reasoning (CBR) combined with courses of the analysis of competency. Then, after the interview of professional engineers regarding their experiences, we analyze the courses' main factors, the degree of demand of instituting the courses, and finally set up the knowledge database of talent training. The results will inspire the training path for automation equipment and process and act as reference for the human resources department, reducing discrepancies between the tech and management department for required skills to equipment and manufacturing processing and enhancing the productive output.

Abstract: It is always being a bottleneck to adaptive cases in CBR, how to solve this problem has vexed researchers for a long time. In this paper, Formula for fusing similar cases is used at first, then artificial immune algorithm (AIA) is applied for optimizing the solution. In the end of the paper, in order to compare the superiority of AIA with genetic algorithm (GA) in the process of case adaptation, the model based on AIA is simulated by MATLAB, and the simulation proves that AIA is more suitable for adapting case.

Abstract: In order to provide more efficient knowledge services in the CNC turret design process, a rapid design method of a case-based reasoning is proposed. Firstly, according to different types of demand in case retrieval, the similarity measurement models for crisp and fuzzy attribute type demands are constructed respectively. Secondly, in the weights assignment, this paper utilized the deviation information of similarity values to calculate objective weights, and then combined the objective weights and subjective weights to form synthesis weights. Finally, the similarity measurement and weights coefficient assignment methods were applied in a CNC turret design CBR system, and using the calculation function of MATLAB. It was demonstrated that this method could improve the accuracy of case retrieval.

Abstract: In order to improve the control accuracy of the coiling temperature of strip in the laminar cooling process when working condition is varying, an intelligent setting method of the cooling water volume is researched in this paper. The strip coiling temperature mechanism model is built firstly. Secondly, the key model parameters are identified with case-based reasoning (CBR) technology to improve the model accuracy. Lastly, the cooling water volume setting method based the model is proposed where disturbance input method is applied. The simulation result showed that the proposed method can improve the strip coiling temperature accuracy when the operation condition is changing. The strip coiling temperature accuracy can be improved due to the CBR technology which can adjust the key model parameters according to the varying operation condition. So, the setting values based the improved model are adjusted with the changing working condition, with self-adaptive ability.

Abstract: Aiming at the problems of no strong real-time performance and poor scalability using traditional filtering recommendation technology, and a novel case recommended based on fuzzy clustering is proposed in this paper. Using case-based reasoning technology to personalized recommendation system, and the old case is clustered using fuzzy clustering algorithm, and a classification model is built, and the target case-the case base is converted to the target case-case class to reduce the most case retrieval space of the target cases the nearest neighbors. The experimental results indicate that this method can effectively improve the real-time performance, and it is used in E-commerce recommendation systems, and the degree of recommendation results universe of discourse is improved.

Abstract: This paper applies case-based reasoning approach in university-industry problem-solving to solve problems emerged in knowledge flow when companies cooperate with universities. Solve the problems or conflicts in this domain are very important for companies, because these will decide whether companies could get competitive advantages or not. Capturing and preserving past experiences and knowledge of individuals in company by CBR will form corporate memory which facilitates the cooperation. Case structure and case features are presented in this paper.

Abstract: Since the widespread application of NC machine, fault diagnosis and repair of NC machine has been the subject of attention. Now both at home and abroad has a number of new concepts and methods to the field. The application of CBR technology in NC machine fault diagnosis analysis system is a very good exploration and research. Application of CBR technology is based on similarity of NC machine failure, using the method of case-based reasoning to identify the reference case, diagnosis method with reference to the case to find a reasonable solution. The CBR technology is applied to diagnose faults of CNC system, the accumulation of collection is convenient for the experts' experience, the fault diagnosis analysis system is more practical.

Abstract: Experience and knowledge play a very important role in design; however, experts experience and knowledge are difficult to impart effectively and precisely to novices. Artificial intelligence (AI) approaches have been successfully applied to many fields. Among the numerous AI approaches, Case-Based Reasoning (CBR) is an approach that mainly focuses on the reuse of knowledge and experience. However, little work is done on applications of CBR to improve assembly part design. Similarity measures and the weight of different features are crucial in determining the accuracy of retrieving cases from the case base. This research presents a Case-Based Reasoning (CBR) system, CBR-DFA, consisting of a complete CBR cycle to retrieve and evaluate an assembly part design. Experience and knowledge in the form of suggestions include qualitative and quantitative information offered to novices by retrieving and adapting a similar case. Early experimental results indicate that the similar part design is effectively retrieved by these similarity measures.

Abstract: The key technology of personalized recommendation based on CBR involves the representation and the organization of case, construction and maintenance of multiple cases library, judging of the similarity of case and methods of retrieval, and the combination of personalized recommendation technology. The four interrelated aspects are the important links to design the personalized recommendation system. This paper studies the key technology of the personalized recommendation system based on CBR.