Recently, to ensure the reliability and safety of modern large-scale industrial processes, data-driven methods have been receiving considerably increasing attention, particularly for the purpose of process monitoring. However, great challenges are also met under different real operating conditions by using the basic data-driven methods. In this paper, widely applied data-driven methodologies suggested in the literature for process monitoring and fault diagnosis are surveyed from the application point of view. The major task of this paper is to sketch a basic data-driven design framework with necessary modifications under various industrial operating conditions, aiming to offer a reference for industrial process monitoring on large-scale industrial processes.

A Review on Basic Data-Driven Approaches for Industrial Process Monitoring

斜向妥当化(Cross-Validation)の必要と方法

Interior permanent-magnet synchronous motors (IPMSMs) become attractive candidates in modern hybrid electric vehicles and industrial applications. Usually, to obtain good control performance, the electric drives of this kind of motor require one position, one dc link, and at least two current sensors. Failure of any of these sensors might lead to degraded system performance or even instability. As such, sensor fault resilient control becomes a very important issue in modern drive systems. This paper proposes a novel sensor fault detection and isolation algorithm based on an extended Kalman filter. It is robust to system random noise and efficient in real-time implementation. Moreover, the proposed algorithm is compact and can detect and isolate all the sensor faults for IPMSM drives. Thorough theoretical analysis is provided, and the effectiveness of the proposed approach is proven by extensive experimental results.

A Sensor Fault Detection and Isolation Method in Interior Permanent-Magnet Synchronous Motor Drives Based on an Extended Kalman Filter

High-speed trains have become one of the most important and advanced branches of intelligent transportation, of which the reliability and safety are still not mature enough for keeping up with other aspects. The first objective of this paper is to present a comprehensive review on the fault detection and diagnosis (FDD) techniques for high-speed trains. The second purpose of this work is, motivated by the pros and cons of the FDD methods for high-speed trains, to provide researchers and practitioners with informative guidance. Then, the application of FDD for high-speed trains is presented using data-driven methods which are receiving increasing attention in transportation fields over the past ten years. Finally, the challenges and promising issues are speculated for the future investigation.

A Review of Fault Detection and Diagnosis for the Traction System in High-Speed Trains

A sensor fault detection and isolation unit is considered for induction-motor drives based on an adaptive observer with rotor-resistance estimation. Generally, closed-loop induction-motor drives with voltage-source inverters use a speed or position, a dc-link voltage, and two or three phase-current sensors. In the proposed fault-detection and isolation unit, the estimated phase currents and rotor resistance are sent to a decision-making unit, which identifies the faulty sensor type based on a deterministic rule base. In the case of a current-sensor failure, it also detects the phase with erroneous sensor output. It is shown that, unlike the other proposed model-based fault-tolerant systems, using a bank of observers is not necessary, and only one current observer with rotor-resistance estimation is sufficient for isolation of all sensors' faults. The accuracy of the proposed approach is analytically proved. Furthermore, extensive simulation and experimental tests verify the effectiveness of the proposed method at different operating conditions.

Detection and Isolation of Speed-, DC-Link Voltage-, and Current-Sensor Faults Based on an Adaptive Observer in Induction-Motor Drives

An adaptive observer with online estimation of rotor and stator resistances is considered for induction motors, while only one phase current is measured. Generally, an induction motor drive controller needs at least two phase-current sensors. Nevertheless, failure of one current sensor results in degradation of motor drive performance and reliability, and also state and parameter estimation errors. Furthermore, any controller or observer in induction motor drives should be robust to rotor and stator resistance variations. The proposed observer is capable of concurrent estimation of stator currents and rotor fluxes with online tuning of rotor and stator resistances, while rotor speed and only one phase current are available. Stability and convergence of the observer are analytically verified based on the partial stability theory. The observer equations and adaptation laws can be easily implemented, which makes it attractive for industrial development of fault tolerant drives. A complex programmable logic device is implemented for the experimental setup that controls an intelligent power module including insulated gate bipolar transistors. Extensive simulation and experimental tests verify the asymptotic convergence of the proposed observer.

An Adaptive Observer With Online Rotor and Stator Resistance Estimation for Induction Motors With One Phase Current Sensor

An adaptive observer is proposed for concurrent estimation of rotor fluxes, unknown dc-link voltage, and rotor resistance of induction motor with voltage source inverters. For the reported flux observers and parameter estimators, the implied assumption had been that the input voltages were measured by sensors, or presumed to be known, for example while plug-in converters were utilized. However, this assumption may not be valid due to bus voltage variations, such as for battery powered servo drives, or propulsion system in hybrid electric vehicles. A drift in input voltage measurement results in state and parameter estimation errors. The proposed observer is capable of concurrent flux and dc-link voltage observation with online tuning of rotor resistance, while the phase currents and rotor speed are measured. No terminal voltage measurement is needed for this adaptive observer. The stability of the proposed observer is proved based on a Lyapunov function. Besides, it is shown that injection of a diagnosis signal is necessary to force the estimated parameters converge to the right values regardless of their initial conditions. A complex programmable logic device is implemented for the experimental setup, which controls an intelligent power module including insulated gate bipolar transistors. Extensive simulation and experimental tests verify the asymptotic convergence of the proposed observer.

An Adaptive Flux Observer With Online Estimation of DC-Link Voltage and Rotor Resistance For VSI-Based Induction Motors

This paper presents a novel smart street lighting (SmSL) system in which energy consumption by a group of street lighting poles is minimized based on Brute-Force search algorithm. While outdoor lighting imposes considerable cost, maintenance, safety, and environmental issues; utilization of advanced street lighting system with energy saving, autonomous fault detection, and monitoring capabilities benefits all the players involved including municipalities and distribution companies. The proposed SmSL has a hierarchical platform. The segment or intermediate controller determines the scheduling, switching, and dimming level of each pole based on the proposed optimization subroutine and transmits the controller set points to the local pole controller through power line communications. Optimization of street lighting electrical energy is achieved by minimizing a cost function, considering operational constraints, ambient luminance, and local traffic flow. The local controller acts as an actuator and applies the received commands. The controller inherently responses to lamp fault. Moreover, pole electrical parameters and status of the lamp and its capacitor is transmitted to the intermediate controller. The supervisory controller, which is installed on a server in distribution center monitors the whole system and sends appropriate commands such as minimum required luminance in the area to the segment controller based on WiMAX wireless communications. The whole system is developed and implemented in a pilot street. The experimental results show considerable energy saving with the proposed SmSL and reduced maintenance costs.

A Hierarchical Smart Street Lighting System With Brute-Force Energy Optimization

Acute myelogenous leukemia (AML) is a subtype of acute leukemia, which is characterized by the accumulation of myeloid blasts in the bone marrow. Careful microscopic examination of stained blood smear or bone marrow aspirate is still the most significant diagnostic methodology for initial AML screening and considered as the first step toward diagnosis. It is time-consuming and due to the elusive nature of the signs and symptoms of AML; wrong diagnosis may occur by pathologists. Therefore, the need for automation of leukemia detection has arisen. In this paper, an automatic technique for identification and detection of AML and its prevalent subtypes, i.e., M2-M5 is presented. At first, microscopic images are acquired from blood smears of patients with AML and normal cases. After applying image preprocessing, color segmentation strategy is applied for segmenting white blood cells from other blood components and then discriminative features, i.e., irregularity, nucleus-cytoplasm ratio, Hausdorff dimension, shape, color, and texture features are extracted from the entire nucleus in the whole images containing multiple nuclei. Images are classified to cancerous and noncancerous images by binary support vector machine (SVM) classifier with 10-fold cross validation technique. Classifier performance is evaluated by three parameters, i.e., sensitivity, specificity, and accuracy. Cancerous images are also classified into their prevalent subtypes by multi-SVM classifier. The results show that the proposed algorithm has achieved an acceptable performance for diagnosis of AML and its common subtypes. Therefore, it can be used as an assistant diagnostic tool for pathologists.

Tooraj Abbasian Najafabadi

Papers

Detection and Isolation of Speed-, DC-Link Voltage-, and Current-Sensor Faults Based on an Adaptive Observer in Induction-Motor Drives

An Adaptive Observer With Online Rotor and Stator Resistance Estimation for Induction Motors With One Phase Current Sensor

An Adaptive Flux Observer With Online Estimation of DC-Link Voltage and Rotor Resistance For VSI-Based Induction Motors

A Hierarchical Smart Street Lighting System With Brute-Force Energy Optimization

Automatic Recognition of Acute Myelogenous Leukemia in Blood Microscopic Images Using K-means Clustering and Support Vector Machine.