The authors discuss high-voltage power conversion. Conventional series connection and three-level voltage source inverter techniques are reviewed and compared. A novel versatile multilevel commutation cell is introduced: it is shown that this topology is safer and more simple to control, and delivers purer output waveforms. The authors show how this technique can be applied to either choppers or voltage-source inverters and generalized to any number of switches.<<ETX>>

Multi-level conversion : high voltage choppers and voltage-source inverters

A comprehensive review on convolutional neural network in machine fault diagnosis

Provided is an electric power converter. A First and second series circuits of switching devices and a series circuit of capacitors are connected in parallel. Between the connection point in the first series circuit of switching devices and the connection point in the series circuit of capacitors, a first bidirectional switch is connected and, between the connection point in the second series circuit of switching devices and the connection point in the series circuit of capacitors, a second bidirectional switch is connected. The connection point in the first series circuit of switching devices is connected through a reactor to an input-output common connection line connected to one end of an AC power supply and the other end of the AC power supply is connected to the connection point in the series circuit of capacitors.

Electric power converter

A smart factory is a highly digitized and connected production facility that relies on smart manufacturing. Additionally, artificial intelligence is the core technology of smart factories. The use of machine learning and deep learning algorithms has produced fruitful results in many fields like image processing, speech recognition, fault detection, object detection, or medical sciences. With the increment in the use of smart machinery, the faults in the machinery equipment are expected to increase. Machinery fault detection and diagnosis through various deep learning algorithms has increased day by day. Many types of research have been done and published using both open-source and closed-source datasets, implementing the deep learning algorithms. Out of many publicly available datasets, Case Western Reserve University (CWRU) bearing dataset has been widely used to detect and diagnose machinery bearing fault and is accepted as a standard reference for validating the models. This paper summarizes the recent works which use the CWRU bearing dataset in machinery fault detection and diagnosis employing deep learning algorithms. We have reviewed the published works and presented the working algorithm, result, and other necessary details in this paper. This paper, we believe, can be of good help for future researchers to start their work on machinery fault detection and diagnosis using the CWRU dataset.

/pdf/bearing-fault-detection-and-diagnosis-using-case-western-1af0gxj849.pdf

Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review

Recently, deep-learning-based fault diagnosis methods have been widely studied for rolling bearings. However, these neural networks are lack of interpretability for fault diagnosis tasks. That is, how to understand and learn discriminant fault features from complex monitoring signals remains a great challenge. Considering this challenge, this article explores the use of the attention mechanism in fault diagnosis networks and designs attention module by fully considering characteristics of rolling bearing faults to enhance fault-related features and to ignore irrelevant features. Powered by the proposed attention mechanism, a multiattention one-dimensional convolutional neural network (MA1DCNN) is further proposed to diagnose wheelset bearing faults. The MA1DCNN can adaptively recalibrate features of each layer and can enhance the feature learning of fault impulses. Experimental results on the wheelset bearing dataset show that the proposed multiattention mechanism can significantly improve the discriminant feature representation, thus the MA1DCNN outperforms eight state-of-the-arts networks.

Understanding and Learning Discriminant Features based on Multiattention 1DCNN for Wheelset Bearing Fault Diagnosis

Multilevel inverters (MLIs) have gained increasing interest for advanced energy-conversion systems due to their features of high-quality produced waveforms, modularity, transformerless operation, voltage, and current scalability, and fault-tolerant operation. However, these merits usually come with the cost of a high number of components. Over the past few years, proposing new MLIs with a lower component count has been one of the most active topics in power electronics. The first aim of this article is to update and summarize the recently developed multilevel topologies with a reduced component count, based on their advantages, disadvantages, construction, and specific applications. Within the framework, both single-phase and three-phase topologies with symmetrical and asymmetrical operations are taken into consideration via a detailed comparison in terms of the used component count and type. The second objective is to propose a comparative method with novel factors to take component ratings into account. The effectiveness of the proposed method is verified by a comparative study.

Voltage Source Multilevel Inverters With Reduced Device Count: Topological Review and Novel Comparative Factors

Temperature rise of the form-wound multi-conductor stator winding of a 1250-kW cage induction motor was analyzed. Eddy currents in the winding significantly affect the temperature rise. The eddy current was modeled using time-discretized finite-element analysis (FEA). The resistive losses in each of the bars obtained from the FEA are used as input for thermal modeling. The distance from the air gap to the topmost bar in the stator has a significant effect on the eddy-current loss as well as temperature rise in the winding. An acceptable distance for winding design was recommended. By using magnetic slot wedges the eddy-current losses can be reduced.

Eddy-Current Loss and Temperature Rise in the Form-Wound Stator Winding of an Inverter-Fed Cage Induction Motor

Bearings are one of the most critical elements in rotating machinery systems. Bearing faults are the main reason for failures in electrical motors and generators. Therefore, early bearing fault detection is very important to prevent critical system failures in the industry. In this paper, the support vector machine algorithm is used for early detection and classification of bearing faults. Both time and frequency domain features are used for training the support vector machine learning algorithm. The trained classier can be employed for real-time bearing fault detection and classification. By using the proposed method, the bearing faults can be detected at early stages, and the machine operators have time to take preventive action before a large-scale failure. The usefulness of the algorithm is validated by using a run-to-failure experimental test data.

Early detection and classification of bearing faults using support vector machine algorithm

Detection and isolation of single and mixed faults in a gearbox are very important to enhance the system reliability, lifetime, and service availability. This paper proposes a hybrid learning algorithm, consisting of multilayer perceptron (MLP)- and convolutional neural network (CNN)-based classifiers, for diagnosis of gearbox mixed faults. Domain knowledge features are required to train the MLP classifier, while the CNN classifier can learn features itself, allowing to reduce the required knowledge features for the counterpart. Vibration data from an experimental setup with gearbox mixed faults is used to validate the effectiveness of the algorithms and compare them with conventional methods. The comparative study shows that accuracies and robustness of the individual MLP and CNN algorithms are better than those of the compared methods and can be significantly improved using data fusion at the feature level. Furthermore, the robustness of the algorithm is secured under noises by combining the results of individual classifiers.

Multiple Classifiers and Data Fusion for Robust Diagnosis of Gearbox Mixed Faults

A triple-cage circuit of a deep-bar induction motor is numerically identified in the time domain. The parameters are estimated either in the transient state or in the steady state by using a curve-fitting technique. The data used for estimation were obtained from finite-element analysis and measurements using a 37 kW induction motor. The accurate parameters allow the circuit model to well represent the operating motor or predict the performance of the motor. The goodness and limitations of the method are also discussed.

Huynh Van Khang

Papers

Voltage Source Multilevel Inverters With Reduced Device Count: Topological Review and Novel Comparative Factors

Eddy-Current Loss and Temperature Rise in the Form-Wound Stator Winding of an Inverter-Fed Cage Induction Motor

Early detection and classification of bearing faults using support vector machine algorithm

Multiple Classifiers and Data Fusion for Robust Diagnosis of Gearbox Mixed Faults

Parameter estimation for a deep-bar induction motor