Fault detection in water pumps based on sound analysis using a deep learning technique

Machine fault detection is designed to automatically detect faults or damage in machines. When a machine operates, it produces vibrations and sound signals that can be analyzed to provide information about the status of the machine. This study proposed a method to detect the faults in a machine based on sound analysis using a deep learning technique. The sound signals generated by the machine were obtained and analyzed under different operating conditions. These signals were first pre-processed to eliminate noise, and then the features were extracted as mel-spectrograms so that the convolutional neural network could automatically learn the appropriate features required for classification. Experiments were conducted on three different water pumps during suction from and discharge to the water tank under normal and abnormal operating conditions. The high accuracies in fault detections in both known and unknown machines indicated that the proposed model performed very well in the detection of machine faults.

Process Safety for Sustainable Applications

Process safety techniques have been used in industry for decades to make processes and systems safer and to optimize them, and thus to improve sustainability. Their main aim is to prevent damage to people, equipment and the environment. In this overview, process safety and risk management techniques are shown that can be applied in the different life cycle phases of an application without much implementation effort. A broad and universal applicability in a wide range of business sectors is set as the main focus. In addition to the application of system improvement techniques, a number of additional considerations, such as maintenance and the consideration of abnormal operating conditions, are included in order to be able to comprehensively improve a system or application.

Master-Slave Approach for a Multi-terminal VSC-HVDC Systems Connected Offshore Wind Farm

The world is facing today the global challenge of energy transition since countries need more and more energy to grow their economy on a planet where resources are limited and poorly distributed. The integration of renewable energies and especially offshore wind energy into high voltage direct current (VSC-HVDC) transmission systems demonstrates great flexibility and reliability. In this paper, a control strategy for a multi-terminal VSC-HVDC system based on Master-Slave approach is proposed to automatically share the real power variation and stabilize the DC bus voltage in presence of abnormal operating conditions.

Convolutional Neural Network for Dust and Hotspot Classification in PV Modules

This paper proposes an innovative approach to classify the losses related to photovoltaic (PV) systems, through the use of thermographic non-destructive tests (TNDTs) supported by artificial intelligence techniques. Low electricity production in PV systems can be caused by an efficiency decrease in PV modules due to abnormal operating conditions such as failures or malfunctions. The most common performance decreases are due to the presence of dirt on the surface of the module, the impact of which depends on many parameters and conditions, and can be identified through the use of the TNDTs. The proposed approach allows one to automatically classify the thermographic images from the convolutional neural network (CNN) of the system, achieving an accuracy of 98% in tests that last a couple of minutes. This approach, compared to approaches in literature, offers numerous advantages, including speed of execution, speed of diagnosis, reduced costs, reduction in electricity production losses.

Wide Input Voltage Range Operation of the Series Resonant DC-DC Converter with Bridgeless Boost Rectifier

The series resonant DC-DC converter (SRC) can regulate the input voltage in a wide range at a fixed switching frequency. In this work, the bridgeless rectifier, which is utilized intensively in the applications of the power factor correction, has been integrated into the SRC as a voltage step-up cell at the output-side of the SRC. It is shown that the conventional overlapping pulse-width modulation (PWM) of the two metal oxide semiconductor field-effect transistors MOSFETs in this rectification cell limits the input voltage regulation range of the converter due to excessive power losses in abnormal operating conditions. The abnormal operating conditions occur when the instantaneous voltage across the resonant capacitor is larger than the secondary voltage of the isolation transformer. This happens at high values of the DC voltage gain, i.e., low input voltages and high currents, which causes the resonant current to flow in the reverse direction in the same half-cycle through a parasitic path formed by overlapping PWM of the rectifier MOSFETs. The abnormal operation results in additional conduction loss in the converter as the MOSFETs of the bridgeless boost rectifier turn on at high current at the beginning of each half of the switching period. Accordingly, the overall efficiency of the converter significantly deteriorates. This paper proposes the hybrid PWM aiming to improve the efficiency of the SRC with a bridgeless boost rectifier in a wide input voltage regulation range. The converter swaps between the overlapping and the proposed short-pulse PWM schemes to drive the MOSFETs in the bridgeless boost rectifier. The transition between the two PWM schemes is defined according to the boundary condition that relies upon the operating point of the converter power and the input voltage. The proposed hybrid PWM scheme is analyzed and compared to the overlapping PWM at different levels of the input voltage and the load power. A 300 W prototype was studied in the laboratory to show the feasibility of the proposed hybrid PWM scheme with the closed-loop control system to switch between the two PWM schemes.

Exploratory research for developing advanced pumping and compressor equipment adapted to abnormal operating conditions of oil and gas production

The observed instability of the oil and gas market makes it necessary to intensify the exploratory scientific research for the development of advanced and inexpensive pumping and compressor equipment intended for oil and gas production and treatment. The ongoing research work is being undertaken with a view to modernize well-known technical solutions and develop new scientific principles for gas compression with the use of labyrinth compressors. From the published materials, it became known that when designing labyrinth pumps, the screw auger on the pump rotor can be replaced with a set of vane wheels. This design approach should be transferred from the field of pumping technology to the field of compressor technology as well. At the initial stage of such research microlevel models of new turbocompressors have been developed to test their performance. Further, was made the transition from the low-cost physical experiments with micro-level models to a deeper study of the working process for the basic model of the compressor with the screw rotor. 3D-model development was carried out with the use of the SolidWorks 3D CAD-system. In order to undertake a calculation study, the FloEFD software package of computational fluid dynamics developed by Mentor Graphics Corporation has been used. The results of the research findings can be used for the development of energy-efficient technologies for the compression and pumping of various gases. The development of cheaper and more economical pump-compressor units will allow for the solution of urgent hydrocarbon exploration and production problems in abnormal operating conditions. Based on similar compressor units, there is a possibility to develop other sectors of science and technology as well.

Numerical and Experimental Investigation of the 4-Quadrant Behavior of Different Mixed Flow Diffuser Pumps

Besides operating a centrifugal pump under normal conditions there are additional operating conditions possible; for example, a pump operated as turbine. Another example would be a pump trip where there are several abnormal operating conditions possible when the direction of flow and/or the direction of rotation are changing. The machine behavior in every possible operation condition can be represented by the complete pump characteristics, often called the 4-quadrant (4Q) behavior of a centrifugal pump. To gather the 4Q behavior, a test rig allowing the flow direction as well as the rotation direction to be reverted is necessary, with time-consuming measurements at variable positive and negative discharge in both directions of rotation the complete pump characteristics are evaluated. In the present study, an approach to investigate the complete pump characteristics by means of computational fluid dynamics (CFD) calculations is presented. With steady-state calculations and additional transient CFD investigations in the normal operating conditions, the whole pump characteristics were calculated accurately. Two different types of mixed flow diffuser pumps were investigated—one equipped with adjustable impeller blades, the second one with comparable low specific speed. Experimental verifications have shown a remarkably good agreement. Furthermore, an exemplary numerical waterhammer analysis shows the successful application of the presented approach.