Papers by Keyword: Case-Based Reasoning (CBR)

Abstract: The paper applied method of case-based reasoning to environmental emergency aid decision-making, and provided a decision-making method based on experience of historical cases to emergency decision-makers. Firstly, a universal method for describing and organizing environmental emergency cases based on three-tier architecture was proposed based on feature analysis of environmental emergency cases. Then a kind of two-layer structure similarity algorithm was designed based on attribute features of environmental emergency cases, which can effectively avoid the defect of traditional Nearest-Neighbor Algorithm. Finally, a CBR prototype system of emergency aid decision-making model was developed and an example of environmental mass incident case was used to testify the practicability of the model. The case example show that the emergency aid decision-making model for environmental emergency based on CBR is applicable in real work.

Abstract: In the view of the complex influence factor, simplified research method and structural or partial structural application model a drilling parameter selection optimization method based on case-based reasoning is provided in this paper. The goal of the research is to build up a drilling parameter selection optimization method which has great applicability. Based on the field drilling data and parameters a case base is built up. Afterward data discovery is used to deal with the case selection problem and select case from case base. Combining with field situation, drilling parameters selection is optimized and drilling speed could be predicted.

Abstract: The paper combines project cost estimating field features,enhance the ability of managing tacit knowledge and increase the organizing level and applying benefit of case.The technical thought and system working process of case-based reasoning ( CBR ), are introduced and analyzed in detail firstly in this paper, and discuss the introduction of CBR in the engineering field knowledge management on this basis. Meanwhile,integrate specific engineering practice case--XX Roads Comprehensive Renovation Project, do further research on the engineering cost estimation system of knowledge management applications based on case technology, and achieve knowledge reuse and innovation, as well as the shared values of knowledge resources.

Abstract: As the activated sludge sewage treatment process has strong non-linearity, uncertainty, time-varying and other complex characteristics, it is difficult to establish water quality soft-sensing model of sewage treatment process. This paper studies the present situation of detection technology of sewage quality COD, and summarizes the problems of the existing water quality soft-sensing model. Adopting the technology of mechanism modeling and RBF, establishes water quality soft-sensing model to adapt changes in a wide range of conditions, and has high precision structure.

Abstract: in the field of artificial intelligence, Case Based Reasoning (CBR) is an arising reasoning technique, in which choosing reasoning index has been the hot topic and difficulty. In order to get optimal feature subset in the process of index selection, this paper combined gray correlation analysis with genetic algorithm (GA) to optimize the feature selection process, taking the gray correlation analysis result as the initial population for GA heuristic search, which can on one hand get better feature combination, on the other hand, effectively reduce the evolution of GA, finally improving GAs execution efficiency. Based on this, an optimized GA-CBR case reasoning model is put forward, which has been proved by empirical results to have an improved CBR forecasting accuracy.

Abstract: Focusing on the problem which power plant flue gas oxygen content is hard to predict efficiently, an intelligent hybrid prediction method is proposed. First, the RBF neural network and principal component analysis method are utilized to reduce the dimension of the input variables. Second, the case-based reasoning method is carried on to predict the flue gas oxygen content based on the above analysis results. Then, in order to reflect the cumulative effect of the flue gas oxygen content with time, the GM (1, 1) grey prediction method is used to predict the current flue gas oxygen content value. Finally, the final flue gas oxygen content is obtained by the variance-covariance method of weight combination forecasting. Simulations and industrial results show that the proposed intelligent hybrid prediction model has high accuracy and robustness, and can solve the problem of predicting the flue gas oxygen content effectively.

Abstract: According to the characteristics of complex mechanical product, we put forward case matching algorithm in case-based reasoning(CBR) ,which uses grey correlation theory,combines with the variation coefficient method and Euclidean distance.And case retrieval and matching model was established.An example of CNC machine tool design was provided to validate and prove its efficiency and feasibility

Abstract: A synthetic fault diagnosis expert system for turbine generator sets based on rule based reasoning and cases based reasoning is built in this paper. The structure of synthetic fault diagnosis expert system is discussed. The rule base and case base for the fault diagnosis of expert system is established based on the domain expert knowledge and relevant fault cases of turbine generator sets. Both the inference flow and case retrieval strategy of diagnosis system are discussed in detail. Finally the expert system is verified by a given application example.

Abstract: In order to help engineers to better learn from accidents of reinforced concrete structures, accident identification and processing method, this article introduced the ideas of CBR to the accident case retrieval methods of reinforced concrete structures. At the same time, the fuzzy retrieval and knowledge index model of reinforced concrete structure accidents are presented. According to the approximate extent of construction conditions, the approximation of construction are determined, and similar cases with the current engineering cases then retrieved through the case of reinforced concrete structures, which the designer or construction workers can learn from.

Abstract: This paper was based on construction cost indexes of Xiamen, 11 feature attributes were extracted, including engineering purposes, engineering categories, and 3 predictors including square metre cost. Frame-based representation was used to represent cases. Access was used to build engineering case library. Visual Basic language was adopted to develop object-oriented design. Combined with knowledge guidance strategy and the nearest neighbor algorithm, hybrid retrieval strategy was adopted in basic retrieval and advanced retrieval. When built on case-based reasoning, engineering evaluation model provids a fast and effective method for determining the investment target of project planning and feasibility studies.