A Hybrid LSTM-DNN Model with Fuzzy Inference for Adaptive Dispatcher Control of Industrial Information-Control Systems

Abstract

Abstract Erroneous and noisy measurements significantly distort the assessment of the stability of technological lines in industrial information and control systems. This paper proposes an algorithm for operational dispatch control of technological complexes based on the assessment of noise immunity using a hybrid LSTM-DNN model and a fuzzy set apparatus. The hybrid model predicts time dependencies and failure probabilities, while the fuzzy inference system combines objective sensor data and subjective expert assessments into a single reliability indicator. The center of gravity method’s use of trapezoidal membership functions and defuzzification ensures a smooth mapping between linguistic and numerical variables. The study then carries out an analysis of the conditional monotonic behavior of the interference immunity coefficient with respect to system performance under the adopted modeling assumptions. Modelling has shown that, compared to probabilistic methods, the proposed neuro-fuzzy approach can improve the adaptability and stability of a system under non-stationary disturbances. The model developed here can potentially be integrated into industrial dispatch control systems, subject to further validation.