• Energy Research

Large rotating machinery, such as centrifugal gas compressors and pumps, have been widely applied and acted as crucial components in the oil and gas industries. Breakdowns or deteriorated performance of these rotating machines can bring significant economic loss to the companies. In order to conduct effective maintenance and avoid unplanned downtime, a system-wide health indicator is proposed in this paper. The health indicator not only uses a dynamic risk profile, but also considers financial loss and the fault probability based on condition monitoring data. This methodology is carried out by four steps: fault detection, probability of fault calculation, consequence of fault calculation and dynamic risk assessment. In our methodology, the fault probability is calculated by robust Mahalanobis distance, presenting as a system-wide feature from a sparse autoencoder fault detection model enabled early fault detection. The value of the health indicator is presented in financial loss, which assists in effective operational decision-making in a process system. To evaluate the performance of the proposed indicator, two case studies were carried out—one case tested on multivariate industrial data obtained from a pump, and another one tested on an industrial data set from a compressor. Results prove that the integrated health indicator can detect the faults at their incipient stages, indicate the degradation of the system with dynamically updated process risk at each sampling instant, and suggest an appropriate shutdown time before the system suffers severe damage. In addition, this methodology can be adapted to other machines’ health assessments, such as those of turbines and motors. The presented method of processing the industrial data set can benefit relevant readers.

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.

This paper deals with open switch Fault Detection and Diagnosis (FDD) in three-level Neutral Point Clamped (NPC) inverter for electrical drives. The approach is based on the already available phase current time series measurements for different operating conditions (motor speed, load, and environment noise). Both fault detection and classification are studied and the efficiency performances of the proposed selected features are shown. For the fault detection, we focus on the first four statistical moments and the extracted features and then the Cumulative Sum (CUSUM) algorithm as the feature analysis technique to improve the performances. For the classification study, we propose to couple the knowledge on the faulty system brought by the statistical moments and the Kullback-Leibler divergence particularly suitable for the detection of incipient changes. The Principal Component Analysis (PCA) is then used to perform the classification. A 2D framework is obtained, which allows the faults to be classified efficiently within the considered operating conditions for all the selected fault durations.

This article describes the findings of a study which examined the influence of fouling on the behaviour of a cascade and by making use of these results the performance implications for gas turbine engines of exposure to airborne foulants. A suction-type compressor cascade tunnel with a plenum chamber was employed for investigating fouling blade effects. The tests showed that such a testing arrangement allows the extraction of pressure and corrected velocity distribution data downstream of the blades that is comparable with what can be obtained from blow-type cascade tunnels. This study presents experimental results for smooth clean cascade blades and for uniformly fouled blades. For all the cases considered, mid-span-corrected velocity distributions and pressure losses taken one chord downstream of the blades were investigated in order to identify the effects of fouling on the blades. The result of fouling on exit flow angle was investigated as well. In the present study, cascade clean and fouled cases were used to predict real engine performance. Results are obtained in terms of stage polytropic efficiency, thermal efficiency, useful power, and compressor efficiency deterioration. Roughening the cascade blades uniformly with particles of 254 μ m size, the compressor efficiency dropped by 7.7 percentage points.

The Rotating Biological Contactor (RBC) is used for both municipal and industrial wastewater treatment; however, the RBC has been plagued with mechanical deficiencies since its conception. The unpredicted loss of mechanical integrity results in loss of operation and the discharge, into the environment, of effluent that does not meet consent standards as set by governmental bodies. The consequence of the latter on aquatic life cannot be understated. Whilst maintaining an effluent standard is of vital importance this has to be balanced against the capital costs of RBC units. In addition to detailing reasons for defects associated with RBC’s this paper presents a novel design approach for shaftless RBC’s. This novel design takes cognisance of the mechanisms and reasons for mechanical failure, thereby reducing occurrence of loss operation of RBC units and ensuring that the effluent continually meets discharge standards. The added significance of the design is a 50% reduction in costs.

Granulators play a key role in many pharmaceutical processes because they are involved in the production of tablets and capsule dosage forms. Considering the characteristics of the production processes in which a granulator is involved, proper maintenance of the latter is relevant for plant safety. During the operational phase, there is a high risk of explosion, pollution, and contamination. The nature of this process also requires an in-depth examination of the time-dependence of the process variables. This study proposes the application of canonical variate analysis (CVA) to perform fault detection in a granulation process that operates under time-varying conditions. Beyond this, a different approach to the management of process non-linearities is proposed. The novelty of the study is in the application of CVA in this kind of process, because it is possible to state that the actual literature on the theme shows some limitations of CVA in such processes. The aim was to increase the applicability of CVA in variable contexts, with simple management of non-linearities. The results, considering process data from a pharmaceutical granulator, showed that the proposed approach could detect faults and manage non-linearities, exhibiting future scenarios for more performing and automatic monitoring techniques of time-varying processes.

Abstract This paper presents an experimental investigation using Acoustic Emission (AE) technology to monitor sand transport characteristics and identify the sand minimum transport condition (MTC) in two-phase flow. The sand concentration investigated ranged from 300 lb/1000 bbl to 700 lb/1000 bbl and superficial liquid velocity (VSL) had a range of between 0.1 ms−1 and 1.2 ms−1. The experimental findings clearly showed a correlation between MTC and AE energy levels.