Hybrid intelligent parameter estimation based on grey case-based reasoning for laminar cooling process

Abstract

a b s t r a c tIn this paper, a hybrid intelligent parameter estimation algorithm is proposed for predicting the strip temperature during laminar cooling process. The algorithm combines a hybrid genetic algorithm (HGA) with grey case-based reasoning (GCBR) in order to improve the precision of the strip temperature prediction. In this context, the hybrid genetic algorithm is formed by combining the genetic algorithm with an annealing and a local multidimensional search algorithm based on deterministic inverse parabolic interpolation. Firstly, the weight vectors of retrieval features in case-based reasoning are optimised using hybrid genetic algorithm in offline mode, and then they are used in grey case-based reasoning to accurately estimate the model parameters online. The hybrid intelligent parameter estimation algorithm is validated using a set of operational data gathered from a hot-rolled strip laminar cooling process in a steel plant. Experiment results show the effectiveness of the proposed method in improving the precision of the strip temperature prediction. The proposed method can be used in real-time temperature control of hot-rolled strip and has potential for parameter estimation of different types of cooling process.

Data-Driven Soft-Sensor Modeling for Product Quality Estimation Using Case-Based Reasoning and Fuzzy-Similarity Rough Sets

“…Case-based reasoning (CBR) is a successful artificial intelligence methodology currently employed in a variety of applications such as planning and scheduling, medical sciences fault diagnoses, parameter estimation, and process control [15]- [22]. CBR is suitable to the cases where precise physical models on the concerned process are not available, and usually designed as automated problem-solvers for producing a solution to a given problem by adapting the solution to a similar, previously solved problem [17], [18].…”

“…Moreover, considering that the fact that appropriate weight weighting for the case features can enhance CBR performance and reduce its sensitivity to the similarity functions [21], a new approach for feature weighting is proposed using fuzzy-similarity rough sets [23]- [25]. Compared to the existing knowledge-guide methods and machine learning methods [20]- [22], the proposed approach does not require transcendental knowledge and other related information, and the computation complexity is only linear with respect to the number of attributes and cases.…”

A novel case adaptation method based on an improved integrated genetic algorithm for power grid wind disaster emergencies

“…This method is mainly applied to find the correlation 290 between the behavioral sequence of system features and behav-291 ioral sequence of influencing factors in complex discrete systems 292 with high degrees of randomness (Chuang, 2013;Tang, 2015). 293 Compared with other methods, grey relational analysis has more 294 advantages, such as fewer samples and a small number of calcula-295 tions (Xing, Ding, Chai, Afshar, & Wang, 2012). Moreover, this 296 method does not require data in a typical distribution, which is 297 helpful to characterize the correlation degree between objects 298 (Gu, Liang, Bichindaritz, Zuo, & Wang, 2012).…”

A hybrid soft sensor for measuring hot-rolled strip temperature in the laminar cooling process

“…This paper is built on our previous work on modeling the laminar cooling process [16,17], where a two-dimensional parameterized model, the case-based reasoning (CBR) and GA-based optimization techniques have been used. In [16], we considered the influence of changing conditions on the model parameters, but did not address how to set up the initial case base of the case-based reasoning system.…”

“…Also, the retrieval weight, an important parameter in the case-based reasoning system, was determined subjectively. In [17], a hybrid parameter identification method was proposed to deal with uncertainties caused by the strip specification.…”