Repository logo
 
Loading...
Profile Picture
Person

Amaral, Tito Gerardo Batoreo

Search Results

Now showing 1 - 4 of 4
  • Fault Detection in PV Tracking Systems Using an Image Processing Algorithm Based on PCA
    Publication . Amaral, Tito G.; Pires, Vitor Fernão; Pires, A. J.
    Photovoltaic power plants nowadays play an important role in the context of energy generation based on renewable sources. With the purpose of obtaining maximum efficiency, the PV modules of these power plants are installed in trackers. However, the mobile structure of the trackers is subject to faults, which can compromise the desired perpendicular position between the PV modules and the brightest point in the sky. So, the diagnosis of a fault in the trackers is fundamental to ensure the maximum energy production. Approaches based on sensors and statistical methods have been researched but they are expensive and time consuming. To overcome these problems, a new method is proposed for the fault diagnosis in the trackers of the PV systems based on a machine learning approach. In this type of approach the developed method can be classified into two major categories: supervised and unsupervised. In accordance with this, to implement the desired fault diagnosis, an unsupervised method based on a new image processing algorithm to determine the PV slopes is proposed. The fault detection is obtained comparing the slopes of several modules. This algorithm is based on a new image processing approach in which principal component analysis (PCA) is used. Instead of using the PCA to reduce the data dimension, as is usual, it is proposed to use it to determine the slope of an object. The use of the proposed approach presents several benefits, namely, avoiding the use of a wide range of data and specific sensors, fast detection and reliability even with incomplete images due to reflections and other problems. Based on this algorithm, a deviation index is also proposed that will be used to discriminate the panel(s) under fault. Several test cases are used to test and validate the proposed approach. From the obtained results, it is possible to verify that the PCA can successfully be adapted and used in image processing algorithms to determine the slope of the PV modules and so effectively detect a fault in the tracker, even when there are incomplete parts of an object in the image.
  • A Fault Diagnosis Scheme Based on the Normalized Indexes of the Images eccentricity for a Multilevel Converter of a Switched Reluctance Motor Drive
    Publication . Amaral, Tito G.; Pires, Vitor; Foito, Daniel José Medronho; Cordeiro, Armando; Rocha, José Inácio Pinto Rosado; Pires, A. J.; Martins, J. F.
    This paper addresses the fault detection and diagnosis of a fault in the switches of the Switched Reluctance Machine (SRM) power electronic converter. Due to the advantages of using multilevel converters with these machines, a fault detection and diagnosis algorithm is proposed for this converter. The topology under consideration is the asymmetric Neutral Point Clamped (ANPC), and the algorithm was developed to detect open and short circuit faults. The proposed algorithm is based on an approach that discriminates eccentricity of the images formed by the converter voltages. This discrimination is realized through the development of normalized indexes based on the entropy theory. Besides the different fault type the algorithm is also able to detect the transistor under fault. The possibility to implement the proposed approach will be verified through simulation tests.
  • Fault-Tolerant SRM Drive with a Diagnosis Method Based on the Entropy Feature Approach
    Publication . Pires, Vitor Fernão; Amaral, Tito G.; Cordeiro, Armando; Foito, Daniel José Medronho; Pires, A. J.; Martins, João F.
    The power electronic converter design is essential for the operation of the switched reluctance motor (SRM). Thus, a fault-tolerant power converter is fundamental to ensure high reliability and extend the drive operation. To achieve fault tolerance, fault detection and diagnosis methods are critical in order to identify, as soon as possible, the failure mode of the drive. To provide such capability, it is proposed in this paper a new fault-tolerant power converter scheme combined with a fault detection method regarding the most common power semiconductors failures in SRM drives. The fast and reliable proposed diagnosis method is based on the entropy theory. Based on this theory, normalized indexes (diagnostic variables) are created, which are independent from the load and speed of the motor. Through this method, it is possible to identify the faulty leg, as well as the type of power semiconductor fault. To test and evaluate the proposed solution several laboratory experiments were carried out using a 2 kW four-phase 8 / 6 SRM.
  • Fault detection and diagnosis technique for a SRM drive based on a multilevel converter using a machine learning approach
    Publication . Amaral, Tito G.; Pires, Vítor; Foito, Daniel José Medronho; Pires, A. J.; Martins, J. F.
    SRM drives based on multilevel converters is now a solution well accepted due to their interesting features like extended voltage range and capability to fault tolerance. However, one aspect that is fundamental to ensure fault tolerance or preventive maintenance is the fault detection and diagnosis of failures in power semiconductors. In this way, in this paper it is presented a new diagnostic method for the failure of those semiconductors in asymmetric neutral point clamped converters. The proposed method will be based on the development of specific patterns that are associated to each semiconductor and fault type. The procedures presented here are based on the image identification of the currents patterns in the multilevel converter that allow the identification of distinct fault type. The pattern recognition system uses visual-based efficient invariants features for continuous monitoring of multilevel converter The proposed method will be verified through several tests in which were used a simulation tool and an experimental prototype.