Pumps are one of the most critical machines in the petrochemical process. Condition monitoring of such parts and detecting faults at an early stage are crucial for reducing downtime in the production line and improving plant safety, efficiency and reliability. This paper develops a fault detection and isolation scheme based on an unsupervised machine learning method, sparse autoencoder (SAE), and evaluates the model on industrial multivariate data. The Mahalanobis distance (MD) is employed to calculate the statistical difference of the residual outputs between monitoring and normal states and is used as a system-wide health indicator. Furthermore, fault isolation is achieved by a reconstruction-based two-dimensional contribution map, in which the variables with larger contributions are responsible for the detected fault. To demonstrate the effectiveness of the proposed scheme, two case studies are carried out based on a multivariate data set from a pump system in an oil and petrochemical factory. The classical principal component analysis (PCA) method is compared with the proposed method and results show that SAE performs better in terms of fault detection than PCA, and can effectively isolate the abnormal variables, which can hence help effectively trace the root cause of the detected fault.

Due to the exponential expansion of the global fleet of electric vehicles (EVs) in the utility grid, the vehicle-to-grid paradigm is gaining more attention to alleviate the pressure on the grid. Therefore, an EV aggregator acts as a resilient load to enhance the power deficiency in the electrical grid. This paper proposes the vital development of a central aggregator to optimize the hierarchical bi-directional technique throughout the vehicle-to-grid (V2G) and grid-to-vehicle (G2V) technologies. This study was implemented using three different types of EVs that are assumed to penetrate the utility grid throughout the day in an organized pattern. The aggregator determines the number of EVs that would participate in the electric power trade during the day and sets the charging/discharging capacity level for each EV. In addition, the proposed model minimized the battery degradation cost while maximizing the revenue of the EV owner using the V2G technology and ensuring a sufficient grid peak load demand shaving based on the genetic algorithm (GA). Three case studies were investigated based on the parking interval time where the battery degradation cost was minimized to reach approx. 82.04%. However, the revenue of the EV owner increased when the battery degradation cost was ignored. In addition, the load demand decreased by 26.5%. The implemented methodology ensured an effective grid stabilization service by shaving the load demand to identify the average required power throughout the day. The efficiency of the proposed methodology is ensured since our output findings were in good agreement with the literature survey.

This article presents a simple, low-cost, and effective method for the early diagnosis of stator short-circuit faults. The approach relies on the combination of an induction motor mathematical model and parameter estimation algorithm. The kernel of the method is the efficient search for the characteristic parameters that indicate stator short-circuit faults. However, the non-linearity of a machine model may imply multiple local minima of an objective function implemented in the estimation algorithm. Taking this into consideration, the suitability of two industry-proven optimization algorithms (pattern search algorithm and genetic algorithm) as applied in the proposed condition monitoring method was investigated. Experimental results show that the proposed diagnosis method is capable of detecting stator short-circuit faults and estimating level and location of faults. The study also indicates that the proposed method is robust to motor parameters offset and unbalanced voltage supply. Application of the pattern search algorithm is suitable for a continuous monitoring system, where the previous result can be used as starting point of the new search. The genetic algorithm requires longer computation time and is suitable for the offline diagnostic system. It is not sensitive to the starting point, and achieving global solution is guaranteed.

Electromagnetic techniques are widely employed for corrosion detection, and their performance for inspection of corrosion is well established. However, limited work is carried out on the development and reliability of smart corrosion monitoring devices for tracking internal or buried thickness loss due to corrosion remotely. A novel smart magnetic corrosion transducer is developed for long-term monitoring of thickness loss due to corrosion at critical locations. The reliability of the transducer is enhanced by using a dissimilar active redundancy approach. The improved corrosion monitor has been tested in the ambient environment for seven months to evaluate the stability against environmental factors and degradation. The monitor is found to show great sensitivity to detect defects due to corrosion. Detection of anomalous patterns in the time series data received from the monitors is accomplished by using Pearson’s correlation coefficient. The critical component of the monitor is identified at the end of the test. Research findings reveal that, compared to the existing corrosion monitoring techniques in the industry, the detection and isolation of faulty sensor features introduced in this study can contribute to reliable monitoring of thickness loss due to corrosion in ferromagnetic structures over an extended period of time.