RESUMO

This paper presents a novel method for load torque estimation in three-phase induction motors using air gap flux measurement and the conversion of this type of time-domain signal into grayscale images for further processing as inputs for an inception-type convolutional neural network. The magnetic flux was measured employing a Hall effect sensor installed inside the machine, near the stator slots, and above the stator windings. In this case, the sensor was able to measure a resultant magnetic flux density, having both rotor and stator magnetic flux contributions. The present methodology does not require motor parameters for torque prediction. The proposed approach successfully estimated load torque using three optimizers across almost the entire motor load operational range, spanning from 1.5% to 93.9% of the rated load. Four model configurations achieved a mean absolute percentage error (MAPE) less than or equal to 3.7%. Specifically, two models for a 40 × 50 pixel image achieved MAPE of 3.7% and 3%, one model for a 40 × 25 pixel image achieved a MAPE of 3.5%, and one model for a 50 × 80 pixel image achieved a MAPE of 3.3%. This research has been experimentally validated with a 7.5 kW squirrel cage induction machine.

RESUMO

This paper presents the design, implementation, and validation of an on-blade sensor system for remote vibration measurement for low-capacity wind turbines. The autonomous sensor system was deployed on three wind turbines, with one of them operating in harsh weather conditions in the far south of Chile. The system recorded the acceleration response of the blades in the flapwise and edgewise directions, data that could be used for extracting the dynamic characteristics of the blades, information useful for damage diagnosis and prognosis. The proposed sensor system demonstrated reliable data acquisition and transmission from wind turbines in remote locations, proving the ability to create a fully autonomous system capable of recording data for monitoring and evaluating the state of health of wind turbine blades for extended periods without human intervention. The data collected by the sensor system presented in this study can serve as a foundation for developing vibration-based strategies for real-time structural health monitoring.

RESUMO

Manufacturing systems are becoming increasingly flexible, necessitating the adoption of new technologies that allow adaptations to a turbulent and complex modern market. Consequently, modern concepts of production systems require horizontal and vertical integration, extending across value networks and within a factory or production shop. The integration of these environments enables the acquisition of a substantial amount of data containing information pertaining to production, processes, and equipment located on the shop floor. When these data and information are processed and analyzed, they have the potential to reveal valuable insights and knowledge about the manufacturing systems, offering interpretive outcomes for strategic decision making. One of the opportunities presented in this context includes the implementation of predictive maintenance (PdM). However, industrial adoption of PdM is still relatively low. In this paper, the aim is to propose a methodology for selecting the main attributes (variables) to be considered in the instrumentation setup of rotating machines driven by electric motors to decrease the associated costs and the time spent defining them. For this, the most well-known data science and machine learning algorithms are investigated to choose the one most adequate for this task. For the experiments, different testing scenarios were proposed to detect the different possible types of anomalies, such as uncoupled, overloaded, unbalanced, misaligned, and normal. The results obtained show how these algorithms can be effective in classifying the different types of anomalies and that the two models that presented the best accuracy values were k-nearest neighbor and multi-layer perceptron.

RESUMO

This work presents an innovative application of Frequency Response Analysis (FRA) in order to detect early degradation of Metal Oxide Surge Arresters (MOSAs). This technique has been widely used in power transformers, but has never been applied to MOSAs. It consists in comparisons of spectra, measured at different instants of the lifetime of the arrester. Differences between these spectra are an indicator that some electrical properties of the arrester have changed. An incremental deterioration test has been performed on arrester samples (with controlled circulation of leakage current, which increases the energy dissipation over the device), and the FRA spectra correctly identified the progression of damage. Although preliminary, the FRA results seemed promising, and it is expected that this technology could be used as another diagnostic tool for arresters.

RESUMO

Gears are reliable and robust elements that are found in any power transmission system. However, gears are prone to present incipient faults, such as wear, since they are constantly subjected to contact forces. Due to gears playing a key role in many industrial processes, it is important to develop condition monitoring strategies that ensure the proper functioning of the related power transmission system and the overall components. In this regard, the data on entropy provide relevant information that allow us to identify and quantify the effect of different wear levels in gears. Therefore, in this work, we proposed the use of seven entropy-related features to perform the identification of different wear severities in a gearbox. The novelty of this proposal lies in the use of the entropy features to carry out a high-performance characterization of the available vibration signals that are acquired from experimental tests. The novelty of this proposal lies in the fusion of three different techniques: entropy features, linear discriminant analysis, and artificial neural networks to obtain a machine learning approach for improving the detection of different wear severities in gears compared to other reported methodologies. This situation is achieved due to the high-performance characterization of the available vibration signals that are acquired from experimental tests. Additionally, the entropy features are subjected to a feature space transformation by means of linear discriminant analysis to obtain a 2D representation and, finally, the set of features extracted by linear discriminant analysis are used as inputs of a neural network-based classifier to determine the severity of wear that is present in the gears. The proposed methodology is validated and compared with a conventional statistical approach to show the improvement in the classification.

RESUMO

This paper presents a literature review on the subject of Condition-Based Maintenance of surge arresters. Both a bibliometric analysis and traditional comprehensive research are presented. The bibliometric analysis is useful for obtaining insights about the literature. It quantitatively highlights relationships between journals, authors and keywords (related to the monitoring methods) and reveals future trends for research based on the timeline of the keywords. The traditional comprehensive literature review is also presented. It summarizes the methods, their advantages and disadvantages and also points to some known measurement issues of the methods. Both online (leakage current, harmonic components, temperature, partial discharges, power loss and the counting of discharges) and offline (reference voltage, residual voltage, insulation resistance, polarization/depolarization, return voltage, microscopy, spectrometry, X-ray, RUS and the recent application of FRA) methods have been qualitatively analyzed.

RESUMO

Condition monitoring of synchronous generators through non-invasive methods is widely requested by maintenance teams for not interfering the machine operation. Among the techniques used, external magnetic field monitoring is a recent strategy with great potential for detecting incipient faults. In this context, this paper proposes the application of a simple strategy with low computational cost to process data of external magnetic field time derivative signals for the purposes of condition monitoring and fault detection in synchronous machines. The information of interest is extracted from changes in the magnetic signature of the synchronous generator, obtained from frequency spectra of monitored signals using induction magnetic field sensors. The process forms a set of time series that reflects constructive and operational characteristics of the machine. The Shewhart control chart method is applied for anomaly detection in these time series, allowing the detection of changes in the machine magnetic signature. This method is employed in an algorithm for continuous condition monitoring of synchronous generators, presenting as output a global change indicator for the multivariable problem associated with magnetic signature monitoring. Correlation matrices are used to improve the algorithm response, filtering series with similar variation patterns associated with detected events. The proposed method is validated through tests on an experimental bench that allows the controlled imposition of faults in a synchronous generator. The proposed global change indicator allows the automatic detection of stator and rotor faults with the machine synchronized with the commercial power grid. The proposed methodology is also applied on data obtained from an equipment installed in a 305 MVA synchronous generator of a hydroelectric power plant where the evolution of an incipient fault, i.e., a mechanical vibration fault, has been detected.

Assuntos

RESUMO

The monitoring of machine conditions is very important from the viewpoints of productivity, economic benefits, and maintenance. Several techniques have been proposed in which sensors are the key to providing relevant information to verify the system. Recently, the smart sensor concept is common, in which the sensors are integrated with a data processing unit executing dedicated algorithms used to generate meaningful information about the system in situ. Additionally, infrared thermography has gained relevance in monitoring processes, since the new infrared cameras have more resolution, smaller dimensions, reliability, functionality, and lower costs. These units were firstly used as secondary elements in the condition monitoring of machines, but thanks to modern techniques for data processing, the infrared sensors can be used to give a first, or even a direct, diagnosis in a nonintrusive way in industrial applications. Therefore, in this manuscript, the structure and development of an infrared-thermography-based smart sensor for diagnosing faults in the elements associated with induction motors, such as rolling bearings and the gearbox, is described. The smart sensor structure includes five main parts: an infrared primary sensor, a preprocessing module, an image processing module, classification of faults, and a user interface. The infrared primary sensor considers a low-cost micro thermal camera for acquiring the thermal images. The processing modules and the classification module implement the data processing algorithms into digital development boards, enabling smart system characteristics. Finally, the interface module allows the final users to require the smart sensor to perform processing actions and data visualization, with the additional feature that the diagnosis report can be provided by the system. The smart sensor is validated in a real experimental test bench, demonstrating its capabilities in different case studies.

Assuntos

RESUMO

Induction motors play a key role in the industrial sector. Thus, the correct diagnosis and classification of faults on these machines are important, even in the initial stages of evolution. Such analysis allows for increased productivity, avoids unexpected process interruptions, and prevents damage to machines. Usually, fault diagnosis is carried out by analyzing the characteristic effects caused by the faults. Thus, it is necessary to know and understand the behavior during the operation of the faulty machine. In general, monitoring these characteristics is complex, as it is necessary to acquire signals from the same motor with and without failures for comparison purposes. Whether in an industrial environment or in laboratories, the experimental characterization of failures can become unfeasible for several reasons. Thus, computer simulation of faulty motors digital twins can be an important alternative for failure analysis, especially in large motors. From this perspective, this paper presents and discusses several limitations found in the technical literature that can be minimized with the implementation of digital twins. In addition, a 3D finite element model of an induction motor with broken rotor bars is demonstrated, and motor current signature analysis is used to verify the fault effects. Results are analyzed in the time and frequency domain. Additionally, an artificial neural network of the multilayer perceptron type is used to classify the failure of broken bars in the 3D model rotor.

Assuntos

RESUMO

The computer numerical control (CNC) machine has recently taken a fundamental role in the manufacturing industry, which is essential for the economic development of many countries. Current high quality production standards, along with the requirement for maximum economic benefits, demand the use of tool condition monitoring (TCM) systems able to monitor and diagnose cutting tool wear. Current TCM methodologies mainly rely on vibration signals, cutting force signals, and acoustic emission (AE) signals, which have the common drawback of requiring the installation of sensors near the working area, a factor that limits their application in practical terms. Moreover, as machining processes require the optimal tuning of cutting parameters, novel methodologies must be able to perform the diagnosis under a variety of cutting parameters. This paper proposes a novel non-invasive method capable of automatically diagnosing cutting tool wear in CNC machines under the variation of cutting speed and feed rate cutting parameters. The proposal relies on the sensor information fusion of spindle-motor stray flux and current signals by means of statistical and non-statistical time-domain parameters, which are then reduced by means of a linear discriminant analysis (LDA); a feed-forward neural network is then used to automatically classify the level of wear on the cutting tool. The proposal is validated with a Fanuc Oi mate Computer Numeric Control (CNC) turning machine for three different cutting tool wear levels and different cutting speed and feed rate values.

Assuntos

RESUMO

This paper presents an approach for impedance-based sensor monitoring of dressing tool condition in grinding by using the electromechanical impedance (EMI) technique. This method was introduced in Part 1 of this work and the purpose of this paper (Part 2) is to achieve an optimal selection of the excitation frequency band based on multi-layer neural networks (MLNN) and k-nearest neighbor classifier (k-NN). The proposed approach was validated on the basis of dressing tool condition information obtained from the monitoring of experimental dressing tests with two industrial stationary single-point dressing tools. Moreover, representative damage indices for diverse damage cases, obtained from impedance signatures at different frequency bands, were taken into account for MLNN data processing. The intelligent system was able to select the most damage-sensitive features based on optimal frequency band. The best models showed a general overall error lower than 2%, thus robustly contributing to the efficient automation of grinding and dressing operations. The promising results of this study foster the EMI-based sensor monitoring approach to fault diagnosis in dressing operations and its effective implementation for industrial grinding process automation.

RESUMO

Low-cost piezoelectric lead zirconate titanate (PZT) diaphragm transducers have attracted increasing attention as effective sensing devices, based on the electromechanical impedance (EMI) principle, for applications in many engineering sectors. Due to the considerable potential of PZT diaphragm transducers in terms of excellent electromechanical coupling properties, low implementation cost and wide-band frequency response, this technique provides a new alternative approach for tool condition monitoring in grinding processes competing with the conventional and expensive indirect sensor monitoring methods. This paper aims at assessing the structural changes caused by wear in single-point dressers during their lifetime, in order to ensure the reliable monitoring of the tool condition during dressing operations. Experimental dressing tests were conducted on aluminum oxide grinding wheels, which are highly relevant for industrial grinding processes. From the results obtained, it was verified that the dresser tip diamond material and the position of the PZT diaphragm transducer mounted on the dressing tool holder have a significant effect on the sensitivity of damage detection. This paper contributes to the realization of an effective monitoring system of dressing operations capable to avoid catastrophic tool failures as the proposed sensing approach can identify different stages of the dressing tool lifetime based on representative damage indices.

RESUMO

Partial discharges (PDs) are one of the most important classes of ageing processes that occur within electrical insulation. PD detection is a standardized technique to qualify the state of the insulation in electric assets such as machines and power cables. Generally, the classical phase-resolved partial discharge (PRPD) patterns are used to perform the identification of the type of PD source when they are related to a specific degradation process and when the electrical noise level is low compared to the magnitudes of the PD signals. However, in practical applications such as measurements carried out in the field or in industrial environments, several PD sources and large noise signals are usually present simultaneously. In this study, three different inductive sensors have been used to evaluate and compare their performance in the detection and separation of multiple PD sources by applying the chromatic technique to each of the measured signals.

RESUMO

Both in industrial as in controlled environments, such as high-voltage laboratories, pulses from multiple sources, including partial discharges (PD) and electrical noise can be superimposed. These circumstances can modify and alter the results of PD measurements and, what is more, they can lead to misinterpretation. The spectral power clustering technique (SPCT) allows separating PD sources and electrical noise through the two-dimensional representation (power ratio map or PR map) of the relative spectral power in two intervals, high and low frequency, calculated for each pulse captured with broadband sensors. This method allows to clearly distinguishing each of the effects of noise and PD, making it easy discrimination of all sources. In this paper, the separation ability of the SPCT clustering technique when using a Rogowski coil for PD measurements is evaluated. Different parameters were studied in order to establish which of them could help for improving the manual selection of the separation intervals, thus enabling a better separation of clusters. The signal processing can be performed during the measurements or in a further analysis.