Research on Fault Monitoring of Chillers Unit Based on Optimized BP Neural Network
In order to improve the accuracy and real-time performance of chiller failure monitoring,a real-time online monitoring model based on optimized BP neural network is proposed by combining the particle swarm optimization algorithm and the introduction of momentum factor.The optimization method of BP neural network,chiller fault analysis and parameter selection,and online state management are mainly introduced,and the BP neural network model is constructed by Java programming language and Encog neural network library and deployed in a city's intelligent operation and maintenance platform,which effectively improves the platform's ability to monitor chiller faults.
BP neural networkchillers unitparticle swarm optimizationmomentum factoronline monitoring
NETL
NSTL
万方数据
