The detection and classification of power quality (PQ) disturbances have become a pressing concern due to the increasing number of disturbing loads connected to the power line and the susceptibility of certain loads to the presence of these disturbances; moreover, they can appear simultaneously since, in any real power system, there are multiple sources of different disturbances. In this paper, a new dual neural-network-based methodology to detect and classify single and combined PQ disturbances is proposed, consisting, on the one hand, of an adaptive linear network for harmonic and interharmonic estimation that allows computing the root-mean-square voltage and total harmonic distortion indices. With these indices, it is possible to detect and classify sags, swells, outages, and harmonics-interharmonics. On the other hand, a feedforward neural network for pattern recognition using the horizontal and vertical histograms of a specific voltage waveform can classify spikes, notching, flicker, and oscillatory transients. The combination of the aforementioned neural networks allows the detection and classification of all the aforementioned disturbances even when they appear simultaneously. An experiment under real operating conditions is carried out in order to test the proposed methodology.

Induction motors are critical components for most industries. Induction motor failures may yield an unexpected interruption at the industry plant. Several conventional vibration and current analysis techniques exist by which certain faults in rotating machinery can be identified; however, they generally deal with a single fault only. Instead, in real induction machines, the case of multiple faults is common. When multiple faults exist, vibration and current are excited by several fault-related frequencies combined with each other, linearly or nonlinearly. Different techniques have been proposed for the diagnosis of rotating machinery in literature, where most of them are focused on detecting single faults and few works deal with the diagnosis and identification of multiple combined faults. The contribution of this paper is the development of a condition-monitoring strategy that can make accurate and reliable assessments of the presence of specific fault conditions in induction motors with single or multiple combined faults present. The proposed method combines a finite impulse response filter bank with high-resolution spectral analysis based on multiple signal classification for an accurate identification of the frequency-related fault. Results show the methodology potentiality as a deterministic detection technique that is suited for detecting multiple features where the fault-related frequencies are very close to those analytically reported in literature.

Overall system performance on a production line is one of the major concerns in modern industry where induction motors are present and their condition monitoring is mandatory. Periodic offline monitoring of the motor condition is usually performed in the industry, consuming production time and increasing cost. Broken rotor bars are among the most common failures in induction motors. Reported research projects give a broken-rotor-bar-detection methodology based on personal-computer implementation that is performed offline and requires an expert technician interpretation which is not a cost-effective solution. The novelty of this paper is the development of an automatic online diagnosis algorithm for broken-rotor-bar detection, optimized for single low-cost field-programmable gate-array (FPGA) implementation, which guarantees the development of economical self-operated equipment. The proposed algorithm requires less computation load than the previously reported algorithms, and it is mainly based on the discrete-wavelet-transform application to the start-up current transient; a further single mean-square computation determines a weighting function that, according to its value, clearly points the motor condition as either healthy or damaged. In order to validate the proposed algorithm, several tests were performed, and an FPGA implementation was developed to show the algorithm feasibility for automatic online diagnosis.