In this paper, a new fault monitoring method based on adaptive partitioning non-negative matrix factorization (APNMF) is presented for non-Gaussian processes. Non-negative matrix factorization (NMF) is a new dimension reduction technique, which can effectively deal with Gaussian and non-Gaussian data. However, the NMF model of traditional fault monitoring method is time-invariant and cannot provide fault warning for the slowly changing industrial process. Therefore, this paper proposes an adaptive partition NMF algorithm with non-fixed sub-block NMF models. First, the process variables under different operating conditions of the system are divided into several sub-variable spaces adaptively by the complete linkage algorithm. Then, the global variables space and each sub-variable space are modeled by the NMF method. Finally, the kernel density estimation (KDE) method is adapted to calculate the control limits of the defined statistical metrics. The proposed method makes full use of intra-block local information and inter-block global information, which improves diagnostic performance. The experimental results of a numerical process and the Tennessee Eastman (TE) benchmark process show that the proposed method improves the accuracy of fault monitoring compared with the existing algorithms.

The boiler is an essential energy conversion facility in a thermal power plant. One small malfunction or abnormal event will bring huge economic loss and casualties. Accurate and timely detection of abnormal events in boilers is crucial for the safe and economical operation of complex thermal power plants. Data-driven fault diagnosis methods based on statistical process monitoring technology have prevailed in thermal power plants, whereas the false alarm rates of those methods are relatively high. To work around this, this paper proposes a novel fault detection and identification method for furnace negative pressure system based on canonical variable analysis (CVA) and eXtreme Gradient Boosting improved by genetic algorithms (GA-XGBoost). First, CVA is used to reduce the data redundancy and construct the canonical residuals to measure the prediction ability of the state variables. Then, the fault detection model based on GA-XGBoost is schemed using the constructed canonical residual variables. Specially, GA is introduced to determine the optimal hyperparameters of XGBoost and speed up the convergence. Next, this paper presents a novel fault identification method based on the reconstructed contribution statistics, considering the contribution of state space, residual space and canonical residual space. Besides, the proposed statistics renders different weights to the state vectors, the residual vectors and the canonical residual vectors to improve the sensitivity of faulty variables. Finally, the real industrial data from a boiler furnace negative pressure system of a certain thermal power plant is used to demonstrate the ability of the proposed method. The result demonstrates that this method is accurate and efficient to detect and identify the faults of a true boiler.

The operational integrity and rotational accuracy of bearings are critical in maintaining the reliability of precision devices within IoT systems. In order to improve the efficiency and accuracy of bearing fault diagnosis, a portable advanced bearing fault diagnosis model for IoT applications is proposed. It leverages a novel long short-term memory (LSTM) neural network architecture augmented with memristor technology for enhanced computational efficiency. In this work, a hardware neural network capable of running LSTM is designed, enabling low-power, fast and parallel computation. The circuit comprises three modules: 1) the weight calculation module; 2) the activation function module; and 3) the output module. The weights of the neural network are optimized and adjusted using the double-population jackal optimization algorithm. This algorithm performs convex lens imaging on the jackal population, applies reverse learning, and divides them into elite and ordinary jackals based on fitness values. It integrates the whale algorithm and cosine algorithm to strengthening the optimization ability of the jackal algorithm. Finally, the model is validated using the dataset from Paderborn University (PU). The results indicate that the accuracy of the model exceeds 96% for all four fault types. The findings underscore the potential of this model in powering the next generation of portable diagnostic tools for consumer electronics within the IoT framework.