Effluent ammonia nitrogen soft measurement method based on dual-correlation pruning strategy neural network

The invention discloses an effluent ammonia nitrogen soft measurement method based on a dual-correlation pruning strategy neural network, and the method comprises the steps: firstly extracting input features through employing a high-dimensional mutual information method, and reducing the input redundancy and calculation complexity; then, a self-construction strategy composed of a growth scheme and a pruning scheme is provided, and dynamic optimization is carried out on the fuzzy neural network model to obtain a neural network SCFNN-DCP based on a dual-correlation pruning strategy. In the growth stage of the fuzzy rule, the fuzzy rule is generated by using the system error judgment criterion and the accommodation boundary criterion, and the generalization ability of the network is enhanced. In the pruning stage of the fuzzy rule, the fuzzy rule is removed from the rule base by adopting a double-correlation criterion so as to reduce the complexity of the network. Meanwhile, a dynamic adjustment scheme is adopte