This paper develops an incipient fault detection and isolation method using the Wasserstein distance, which measures the difference between the probability distributions of normal and faulty data sets from the aspect of optimal transport. For fault detection, a moving window based approach is introduced, resulting in two monitoring statistics that are constructed based on the Wasserstein distance. From analysis of the limiting distribution under multivariate Gaussian case, it is proved that the difference measured by the Wasserstein distance is more sensitive than conventional quadratic statistics like Hotelling’s $T^2$ and Squared Prediction Error (SPE). For non-Gaussian distributed data, a project robust Wasserstein distance (PRW) model is proposed and the Riemannian block coordinate descent (RBCD) algorithm is applied to estimate the Wasserstein distance, which is fast when the number of sampled data is large. In addition, a fault isolation method is further proposed once the incipiently developing fault is detected. Application studies to a simulation example, a continuous stirred tank reactor (CSTR) process and a real-time boiler water wall over-temperature process demonstrate the effectiveness of the proposed method.

Composite laminates have complex failure modes. In order to investigate the evolution of failure in the composite laminates, this paper performed an experimental study on four laminates with different layups using acoustic emission (AE) technique. Two different kinds of defects are imposed on the laminates, including a hole and a crack in the center. Tensile and bending tests are performed on the defective laminates and real‐time AE signals are collected. By analyzing the spectrograms of the obtained AE signals and integrating with the dispersion curves, the evolution of failure modes for different laminates can be observed. The tests show that the defects cause multiple failure modes, which change gradually during the experiments. It is also revealed that laminates with different layups have different failure modes. More specifically, the stacking order of different plies has a greater impact on the occurrence of delamination and fiber fracture than matrix crack. The tentative research shows that there is great potential for improving the performance of the composite laminates by careful selection of ply layups.

Industrial computed tomography (CT) is widely used in the measurement field owing to its advantages such as non-contact and high precision. To obtain accurate size parameters, fitting parameters can be obtained rapidly by processing volume data in the form of point clouds. However, due to factors such as artifacts in the CT reconstruction process, many abnormal interference points exist in the point clouds obtained after segmentation. The classic least squares algorithm is easily affected by these points, resulting in significant deviation of the solution of linear equations from the normal value and poor robustness, while the random sample consensus (RANSAC) approach has insufficient fitting accuracy within a limited timeframe and the number of iterations. To address these shortcomings, we propose a spherical point cloud fitting algorithm based on projection filtering and K-Means clustering (PK-RANSAC), which strategically integrates and enhances these two methods to achieve excellent accuracy and robustness. The proposed method first uses RANSAC for rough parameter estimation, then corrects the deviation of the spherical center coordinates through two-dimensional projection, and finally obtains the spherical center point set by sampling and performing K-Means clustering. The largest cluster is weighted to obtain accurate fitting parameters. We conducted a comparative experiment using a three-dimensional ball-plate standard. The sphere center fitting deviation of PK-RANSAC was 1.91 μm, which is significantly better than RANSAC’s value of 25.41 μm. The experimental results demonstrate that PK-RANSAC has higher accuracy and stronger robustness for fitting geometric parameters.

Efficient monitoring of the blast furnace system is crucial for maintaining high production efficiency and ensuring product quality. This article introduces a hybrid cluster variational autoencoder model for monitoring the blast furnace ironmaking process which exhibits multimode behaviors. In contrast to traditional approaches, this method utilizes neural networks to learn data features and effectively handles the diverse feature types observed in different production modes. Through the utilization of a clustering process within the hidden layer of the variational autoencoder, the proposed technique facilitates efficient fault detection in the context of multimodal blast furnace data. Based on the variational autoencoder model, this study further establishes a unified monitoring index and defines a method for computing the control limits. The application of the model to real blast furnace data reveals its proficiency in accurately identifying faults across diverse modes; compared with the probabilistic principal component analysis based on the local nearest neighbor standardization method and the recursive probabilistic principal component analysis, the model shows a reduction in false positives by up to 10.3% and a substantial reduction of 19.2% in the missed detection rate. This method achieves a remarkable false detection rate of only 0.2% and 0 instances of missed detection.