Fault Diagnosis Method For Hydrometallurgical Leaching Process Based On Dynamic Causality Diagram

With the development of economy,the demand for rare metals such as gold is increasling year by year.As the main metallurgy technology,hydrometallurgy is widely used because of its unique advantages in dealing with low grade complex ores.But along with the scale of production process of hydrometallurgy continues to expand,the production process complexity and the risk are increasing.Continuous production and long time running of the equipment will lead to an increase in the probability of a system failure.Once a failure occurs,it may cause great losses.Therefore,it is of great significance to diagnose faults in hydrometallurgy process.Data based fault diagnosis methods are often unsatisfactory due to the coexistence of qualitative information and quantitative information in the process of hydrometallurgy.Definite information and uncertain information exist at the same time in the process of hydrometallurgy.The fault diagnosis technology based on expert knowledge,represented by Dynamic Causality Diagram(DCD),has drawn extensive attention of experts and scholars.Because it can make up for the shortcomings of fault diagnosis method which completely relying on process data.This paper is based on the background of hydrometallurgical leaching process.By setting up the DCD of leaching process and calculating the conditional probability of each possible cause of failure,the deep process failure reason of hydrometallurgy can be obtained,so as to realize the diagnosis of common failures in leaching process.First of all,the paper analyzed the process mechanism and common faults of the hydrometallurgical leaching process,established the DCD of the fault diagnosis of leaching process through mechanism knowledge and DCD structure learning algorithm.Then,the parameters of the model were obtained according to the parameter learning algorithm of DCD.And the common faults of the leaching process were simulated and analyzed by DCD reasoning method.The simulation results verified the effectiveness of the DCD fault diagnosis method.In order to improve the accuracy of fault diagnosis of DCD,an improved interval DCD reasoning method was proposed.By using the interval number to represent the uncertain information in the process,the interval number is substituted into the DCD reasoning calculation process.And the reasoning result was weighted by defining the credibility of the interval to obtain a more accurate diagnosis result and reduce the diagnostic error.Finally,the simulation verified the superiority of the improved fault diagnosis method based on interval number DCD.