Smart-Sensor for the Automatic Detection of Electromechanical Faults in Induction Motors Based on the Transient Stray Flux Analysis

Abstract

Induction motors are essential and widely used components in many industrial processes. Although these machines are very robust, they are prone to fail. Nowadays, it is a paramount task to obtain a reliable and accurate diagnosis of the electric motor health, so that a subsequent reduction of the required time and repairing costs can be achieved. The most common approaches to accomplish this task are based on the analysis of currents, which has some well-known drawbacks that may lead to false diagnosis. With the new developments in the technology of the sensors and signal processing field, the possibility of combining the information obtained from the analysis of different magnitudes should be explored, in order to achieve more reliable diagnostic conclusions, before the fault can develop into an irreversible damage. This paper proposes a smart-sensor that explores the weighted analysis of the axial, radial, and combination of both stray fluxes captured by a low-cost, easy setup, non-invasive, and compact triaxial stray flux sensor during the start-up transient through the short time Fourier transform (STFT) and characterizes specific patterns appearing on them using statistical parameters that feed a feature reduction linear discriminant analysis (LDA) and then a feed-forward neural network (FFNN) for classification purposes, opening the possibility of offering an on-site automatic fault diagnosis scheme. The obtained results show that the proposed smart-sensor is efficient for monitoring and diagnosing early induction motor electromechanical faults. This is validated with a laboratory induction motor test bench for individual and combined broken rotor bars and misalignment faults.

Winding Tensor Approach for the Analytical Computation of the Inductance Matrix in Eccentric Induction Machines

“…End turns, end rings, and slot leakage inductances, included in the L σ matrix, need to be pre-calculated, as usual in the technical literature, where explicit expressions for these inductances can be found in [44][45][46]. This work deals only with the analytical computation of L m in (2). Linear behavior of the iron material will be assumed, as in [47].…”

“…Induction machine (IM) maintenance, integrated in condition-based maintenance (CBM) systems [1][2][3][4][5], is a field of growing industrial interest, due to its widespread use in production lines, electrical vehicles, wind generators, etc. The failure of an IM can cause huge losses, due to unexpected breakdowns of machines and supply systems.…”

Utilization of Two Sensors in Offline Diagnosis of Squirrel-Cage Rotors of Asynchronous Motors

“…These methods are useful during operation when disassembly of the electric motor is not required. Fault measurements can be performed at a safe distance from the machine [21]. Widely used techniques are, e.g., single-phase test with reduced machine supply, MSCA (Motor Signature Current Analysis), or diagnostics from the stray field in radial or axial direction [21,22].…”

Convolutional Neural Network and Motor Current Signature Analysis during the Transient State for Detection of Broken Rotor Bars in Induction Motors

“…Even though IM is a robust and reliable machine, it is susceptible to suffer diverse types of faults during its service life because of different thermal, electrical, and mechanical stresses produced during its operation [ 2 , 3 ]. Among the faults that can occur in IMs, e.g., broken rotor bars (a cracked bar), damaged bearings, unbalances, mixed eccentricities, and winding faults, among others, the broken rotor bar (BRB) (a fault produced by excessive temperature, dynamic forces, and high currents generated into the rotor cage) has become one of the most studied faults, since it allows the IM to operate with apparent normality; however, if the fault is not detected and corrected at stages of low severity, it can lead to the shutdown of processes and cause time and economical losses, as well as, in certain cases, putting at risk the operator and other machines connected to the same production line since it alters the consumed current and produces new frequency components [ 3 , 4 ]. To schedule maintenance times and avoid economic and human catastrophes, the development and application of diagnostic methods that offer more efficient and reliable results in terms of complexity and accuracy are still tasks of paramount importance, mainly considering BRB conditions at low severity, e.g., partially-broken rotor bars.…”

“…In this regard, the fast Fourier transform [ 17 , 18 ], statistical methods [ 19 , 20 ], Welch method [ 21 ], regressive-based models [ 22 ], fractality-based method [ 23 ], entropy-based methods [ 24 , 25 ], multiple signal classification method [ 26 ], wavelet transform [ 27 , 28 , 29 ], empirical mode decomposition [ 30 , 31 ], and principal component analysis [ 32 ], among other indices or methods, have been explored to extract patterns about the IM condition. In a similar venue, different pattern recognition algorithms have already been presented to diagnose the IM condition automatically, e.g., artificial neural networks [ 4 ], fuzzy logic systems [ 23 ], k-means [ 33 ], support vector machines [ 34 ], and decision trees [ 35 ], among others. Notwithstanding the obtaining of promising results in the above-mentioned works, those techniques or algorithms present diverse issues that can compromise their performance in real-life situations, for instance: (1) a fine-tuning (a procedure performed typically by trial-and-error) of diverse parameters such as decomposition level, wavelet mother, model order, among others, for properly analyzing the in-test signals is required [ 36 ]; (2) noisy signals with nonstationary properties as the ones measured in the IMs degrades somehow their performance [ 37 ]; and (3) the adroit integration of feature (or set of features) and classifier is achieved by trial and error, where in all the cases the researcher proposes, tests, and selects the features to be used, which, on the one hand, increases the complexity and, on the other hand, might not lead to the best results [ 15 ].…”