Search Results (38)

Gear defect detection directly affects the operational reliability of critical equipment in fields such as automotive and aerospace. Gear defect detection technology based on machine vision, leveraging the advantages of non-contact measurement, high efficiency, and cost-effectiveness, has become a key support for quality control in intelligent manufacturing. However, it still faces challenges including difficulties in semantic alignment of multimodal data, the imbalance between real-time detection requirements and computational resources, and poor model generalization in few-shot scenarios. This paper takes the paradigm evolution of gear defect detection technology as the main line, systematically reviews its development from traditional image processing to deep learning, and focuses on the innovative application of intelligent algorithms. A research framework of “technical bottleneck-breakthrough path-application verification” is constructed: for the problem of multimodal fusion, the cross-modal feature alignment mechanism based on Transformer network is deeply analyzed, clarifying its technical path of realizing joint embedding of visual and vibration signals by establishing global correlation mapping; for resource constraints, the performance of lightweight models such as MobileNet and ShuffleNet is quantitatively compared, verifying that these models reduce Parameters by 40–60% while maintaining the mean Average Precision essentially unchanged; for small-sample scenarios, few-shot generation models based on contrastive learning are systematically organized, confirming that their accuracy in the 10-shot scenario can reach 90% of that of fully supervised models, thus enhancing generalization ability. Future research can focus on the collaboration between few-shot generation and physical simulation, edge-cloud dynamic scheduling, defect evolution modeling driven by multiphysics fields, and standardization of explainable artificial intelligence. It aims to construct a gear detection system with autonomous perception capabilities, promoting the development of industrial quality inspection toward high-precision, high-robustness, and low-cost intelligence. Full article

Automotive manufacturing quality control faces persistent challenges such as limited defect samples, cross-domain variability, and the demand for interpretable decision-making. This work presents an explainable few-shot anomaly detection framework that integrates EfficientNet-based feature extraction, adaptive prototype learning, and component-specific attention mechanisms to address these requirements. The system is designed for rapid adaptation to novel defect types while maintaining interpretability through a multi-modal explainable AI module that combines visual, quantitative, and textual outputs. Evaluation on automotive datasets demonstrates promising performance on evaluated automotive components, achieving 99.4% accuracy for engine wiring inspection and 98.8% for gear inspection, with improvements of 5.2–7.6% over state-of-the-art baselines, including traditional unsupervised methods (PaDiM, PatchCore), advanced approaches (FastFlow, CFA, DRAEM), and few-shot supervised methods (ProtoNet, MatchingNet, RelationNet, FEAT), and with only 0.63% cross-domain degradation between wiring and gear inspection tasks. The architecture operates under real-time industrial constraints, with an average inference time of 18.2 ms, throughput of 60 components per minute, and memory usage below 2 GB on RTX 3080 hardware. Ablation studies confirm the importance of prototype learning (−4.52%), component analyzers (−2.79%), and attention mechanisms (−2.21%), with K = 5 few-shot configuration providing the best trade-off between accuracy and adaptability. Beyond performance, the framework produces interpretable defect localization, root-cause analysis, and severity-based recommendations designed for manufacturing integration with execution systems via standardized industrial protocols. These results demonstrate a practical and scalable approach for intelligent quality control, enabling robust, interpretable, and adaptive inspection within the evaluated automotive components. Full article

This study introduces a machine vision system (MVS) developed for the inspection and removal of defective gears to enhance the efficiency of mass production processes. The system employs a rotary table that transports gears through the inspection stage at a controlled speed. Various defects, including missing teeth, surface irregularities, and dimensional deviations, are reliably identified through this method. Faulty gears are automatically separated from the production line using a pneumatic actuator. Experimental evaluations confirm the system’s high accuracy and consistency, with a defect detection standard deviation of less than 1%. This level of deviation corresponds to a defect detection accuracy exceeding 98%, with both precision and recall consistently surpassing 96%. By reducing manual intervention and accelerating quality control procedures, the proposed system contributes to improved production efficiency and product quality, offering a practical and effective solution for manufacturing environments. Full article

Localized defects are common in gear transmission systems and can sometimes cause serious production problems or even catastrophic accidents. To reveal the failure mechanisms and study the localized defects in gear transmission systems, a 24-degree-of-freedom (DOF) dynamic coupling model is proposed considering shafts, bearings, and gears. The dynamic characteristics of the established model when defects appear on the raceways of bearings and surfaces of gears are analyzed. It can be found in the results that the response of the established model produces periodic shocks when localized defects appear on bearings or gears through numerical analysis. Sidebands generated by fault frequencies can be detected from the frequency spectrum. Especially, bearing-localized defects on the inner race and gear surface are similar in modulation form envelope analysis, and the increase in rotating frequency leads to difficulties in distinguishing defects on bearings and gears. The established coupling dynamic model was validated through experimentation and offers a theoretical basis for the fault diagnosis of gear transmission systems. Full article

Variable frequency drives (VFDs) are widely used in industry as an efficient means to control the rotational speed of AC motors by varying the supply frequency to the motor. VFD signatures can be detected in vibration signals in the form of sidebands (modulations) induced on tonal components (carrier frequencies). These sidebands are spaced at twice the “pseudo line” VFD frequency, as the magnetic forces in the motor have two peaks per current cycle. VFD-related signatures are generally less susceptible to interference from other mechanical sources, making them particularly useful for deriving speed variation information and obtaining a “pseudo” tachometer from the motor’s synchronous speed. This tachometer can then be employed to accurately estimate the speed profile and to facilitate order tracking in mechanical systems for vibration analysis purposes. This paper presents a signal processing technique designed to extract a pseudo tachometer from the VFD signature found in a vibration signal. The algorithm was tested on publicly available vibration data from a test rig featuring a two-stage gearbox with seeded bearing faults operating under variable-speed conditions with no load, i.e., with minimal slip between the induction motor’s synchronous and actual speed. The results clearly demonstrate the feasibility of using VFD signatures both to extract an accurate speed profile (root mean square error, RMSE of less than 2.5%) and to effectively perform order tracking, leading to the identification of bearing faults. This approach offers an accurate and reliable tool for the analysis of vibration in mechanical systems driven by AC motors with VFDs. However, it is important to note that some inaccuracies may occur at higher motor slip levels under heavy or variable loads due to the mismatch between the synchronous and actual speeds. Slip-induced variations can further distort tracked order frequencies, compromising the accuracy of vibration analysis for gear mesh and bearing defects. These issues will need to be addressed in future research. Full article

This paper studies the relevance of CWT (continuous wavelet transform) processing of vibration signals for improving the performance of CNN-based models that detect certain types of helical gearbox faults. Gear tooth damages, such as incipient and localized pitting and localized wear on helical pinion tooth flanks, combined with improper lubrication, are the faults under observation. Vibrations at the housing level for three rotating velocities of the AC motor and three load levels (for each velocity) are acquired with a triaxial accelerometer. Through CWT, the vibration signal is decomposed into 2D time-frequency grayscale images, with a filter bank of ten voices per octave in the frequency band of interest. Three 2D-CNN-based models trained on the CWT-based representation of the vibration signals measured on individual accelerometer axes (X, Y, and Z) are proposed to detect the four health states (one normal and three faulty) of the helical gearbox, regardless of the selected load level or speed on the test rig. These models achieve an accuracy higher than 99%. By fusing the CWT-based representations of the signals on individual axes for use as input to a 2D-CNN, the best-performing model for the proposed defect detection task is generated, reaching an accuracy of 99.91%. Full article

The use of artificial intelligence-based techniques to solve engineering problems is increasing. One of the most challenging tasks facing industry is the timely diagnosis of failures in electromechanical systems, as they are an essential part of production systems. In this sense, the earlier the detection, the higher the economic loss reduction. For this reason, this work proposes the development of a new methodology based on infrared thermography and an artificial intelligence-based classifier for the detection of multiple faults in an electromechanical system. The proposal combines the intensity profile of the grey-scale image, the use of Fast Fourier Transform and an artificial neural network to perform the detection of twelve states for the state of an electromechanical system: healthy, bearing defect, broken rotor bar, misalignment and gear wear on the gearbox. From the experimental setup, 50 thermographic images were obtained for each state. The method was implemented and tested under different conditions to verify its reliability. The results show that the precision, accuracy, recall and F1-score are higher than 99%. Thus, it can be concluded that it is possible to detect multiple conditions in an electromechanical system using the intensity profile and an artificial neural network, achieving good accuracy and reliability. Full article

In marine electric propulsion systems (MEPS) driven by variable-frequency drives, motor current signals often exhibit complex modulation components, ambiguous spectra, and severe noise interference, rendering it challenging to extract fault-related modulation components. To address this issue, we propose a zero-crossing tacholess order tracking method based on motor current signals. This method utilizes zero-crossing estimation of the instantaneous frequency to perform angular resampling of stator current signals and demodulates the envelope spectrum to extract fault characteristic spectra, enabling the diagnosis of mechanical faults in MEPS. Given the synchronization of the synchronous motor speed with the inverter fundamental frequency, this method estimates instantaneous frequencies in the time domain without requiring integration or time–frequency representation, which is simple and computationally efficient. Data validation on a small-scale marine electric propulsion test platform demonstrates that the proposed method exhibits good robustness under variable-speed conditions and effectively detects imbalance faults caused by propeller breakages and gear faults resulting from bevel gear tooth defects. Therefore, the proposed method can be applied to diagnose faults in downstream mechanical equipment driven by motors. Full article

The integrative potential of LPBF-printed parts for various innovative applications depends upon the robustness and infallibility of the part quality. Eliminating or sufficiently reducing factors contributing to the formation of defects is an integral step to achieving satisfiable part quality. Significant research efforts have been conducted to understand and quantify the triggers and origins of LPBF defects by investigating the material properties and process parameters for LPBF-printed geometries using various sensing technologies and techniques. Frequently, combinations of sensing techniques are applied to deepen the understanding of the investigated phenomena. The main objectives of this review are to cover the roles of selective sensing technologies by (1) providing a summary of LPBF metal print defects and their corresponding causes, (2) informing readers of the vast number and types of technologies and methodologies available to detect defects in LPBF-printed parts, and (3) equipping readers with publications geared towards defect detection using combinations of sensing technologies. Due to the large pool of developed sensing technology in the last few years for LPBF-printed parts that may be designed for targeting a specific defect in metal alloys, the article herein focuses on sensing technology that is common and applicable to most common defects and has been utilized in characterization for an extended period with proven efficiency and applicability to LPBF metal parts defect detection. Full article

The current paper presents helical gearbox defect detection models built from raw vibration signals measured using a triaxial accelerometer. Gear faults, such as localized pitting, localized wear on helical pinion tooth flanks, and low lubricant level, are under observation for three rotating velocities of the actuator and three load levels at the speed reducer output. The emphasis is on the strong connection between the gear faults and the fundamental meshing frequency GMF, its harmonics, and the sidebands found in the vibration spectrum as an effect of the amplitude modulation (AM) and phase modulation (PM). Several sets of features representing powers on selected frequency bands or/and associated peak amplitudes from the vibration spectrum, and also, for comparison, time-domain and frequency-domain statistical feature sets, are proposed as predictors in the defect detection task. The best performing detection model, with a testing accuracy of 99.73%, is based on SVM (Support Vector Machine) with a cubic kernel, and the features used are the band powers associated with six GMF harmonics and two sideband pairs for all three accelerometer axes, regardless of the rotation velocities and the load levels. Full article

The occurrence of an axlebox bearing ring raceway defect is an inevitable and commonly observed phenomenon in railway wheels. It not only leads to surface damage but also poses the potential threat of further damage and degradation, thereby increasing the risks associated with running safety and maintenance costs. Hence, it becomes imperative to detect raceway defects at an early stage to mitigate safety hazards and reduce maintenance efforts. In this study, the focus lies in investigating the effectiveness of vibration-based detection techniques for identifying raceway defects in high-speed train axlebox bearing systems. To achieve this, a dynamic model that accurately represents the coupling dynamics between the vehicle and the track is developed. This model incorporates various dynamic factors, such as traction transmission, gear transmission, and track geometry irregularities. By using the comprehensive dynamic model, the dynamic responses of the axlebox can be accurately calculated. The proposed methodology primarily revolves around analysing the vertical vibrations of the axlebox caused by raceway defects in both the time and frequency domains. Additionally, an envelope analysis using a developed band-pass filter is also employed. The results obtained from this study clearly demonstrate the successful detection of raceway defects in a more realistic vehicle model, thereby providing an efficient approach for the detection of axlebox bearing raceway defects. Consequently, this research contributes significantly to the field of high-speed train systems and paves the way for enhanced safety and maintenance practices. Full article

Data-based equipment fault detection and diagnosis is an important research area in the smart factory era, which began with the Fourth Industrial Revolution. Steel manufacturing is a typical processing industry, and efficient equipment operation can improve product quality and cost. Steel production systems require precise control of the equipment, which is a complex process. A gearbox transmits power between shafts and is an essential piece of mechanical equipment. A gearbox malfunction can cause serious problems not only in production, quality, and delivery but in safety. Many researchers are developing methods for monitoring gearbox condition and for diagnosing failures in order to resolve problems. In most data-driven methods, the analysis data set is derived from a distribution of identical data with failure mode labels. Industrial sites, however, often collect data without information on the failure type or failure status due to varying operating conditions and periodic repair. Therefore, the data sets not only include frequent false alarms, but they cannot explain the causes of the alarms. In this paper, a framework called the Reduced Lagrange Method (R-LM) periodically assigns pseudolabels to vibration signals collected without labels and creates an input data set. In order to monitor the status of equipment and to diagnose failures, the input data set is fed into a supervised learning classifier. To verify the proposed method, we build a test rig using motors and gearboxes that are used on production sites in order to artificially simulate defects in the gears and to operate them to collect vibration data. Data features are extracted from the frequency domain and time domain, and pseudolabeling is applied. There were fewer false alarms when applying R-LM, and it was possible to explain which features were responsible for equipment status changes, which improved field applicability. It was possible to detect changes in equipment conditions before a catastrophic failure, thus providing meaningful alarm and warning information, as well as further promising research topics. Full article

In industrial production, the quality, reliability, and precision of parts determine the overall quality and performance of various mechanical equipment. However, existing part defect detection methods have shortcomings in terms of feature extraction and fusion, leading to issues of missed detection. To address this challenge, this manuscript proposes a defect detection algorithm for parts (CRD-YOLO) based on the improved YOLOv5. Our first aim is to increase the regional features of small targets and improve detection accuracy. In this manuscript, we design the channel- aware aggregation (CAA) module, utilizing a multi-branch convolutional segmentation structure and incorporating an attention mechanism and ConvNeXt V2 Block as bottleneck layers for feature processing. Secondly, the re-parameterization asymptotic module (RAFPN) is used to replace the original model neck structure in order to improve the interaction between shallow-detail features and deeper semantic features, and to avoid the large semantic gaps between non-neighboring layers. Then, the DO-DConv module is encapsulated within the BN layer and the LeakyReLU activation function to become the DBL module, which further processes the feature output from the backbone network and fuses neck features more comprehensively. Finally, experiments with the self-made dataset show that the model proposed in this paper improves the accuracy of detecting various types of defect. In particular, it increased the accuracy of detecting bearing scuffing defects with significant dimensional variations, with an improvement of 6%, and gear missing teeth defects with large shape differences, with an 8.3% enhancement. Additionally, the mean average precision (mAP) reached 96.7%, an increase of 5.5% and 6.4% compared to YOLOv5s and YOLOv8s, respectively. Full article

This paper proposes a new approach to defect detection system design focused on exact damaged areas demonstrated through visual data containing gear wheel images. The main advantage of the system is the capability to detect a wide range of patterns of defects occurring in datasets. The methodology is built on three processes that combine different approaches from unsupervised and supervised methods. The first step is a search for anomalies, which is performed by defining the correct areas on the controlled object by using the autoencoder approach. As a result, the differences between the original and autoencoder-generated images are obtained. These are divided into clusters using the clustering method (DBSCAN). Based on the clusters, the regions of interest are subsequently defined and classified using the pre-trained Xception network classifier. The main result is a system capable of focusing on exact defect areas using the sequence of unsupervised learning (autoencoder)–unsupervised learning (clustering)–supervised learning (classification) methods (U2S-CNN). The outcome with tested samples was 177 detected regions and 205 occurring damaged areas. There were 108 regions detected correctly, and 69 regions were labeled incorrectly. This paper describes a proof of concept for defect detection by highlighting exact defect areas. It can be thus an alternative to using detectors such as YOLO methods, reconstructors, autoencoders, transformers, etc. Full article

Steel plays an indispensable role in our daily lives, permeating various products ranging from essential commodities and recreational gears to information technology devices and general household items. The meticulous evaluation of steel defects holds paramount importance to ensure the secure and dependable operation of the end products. Photoacoustic imaging (PAI) emerges as a promising modality for structural inspection in the realm of health monitoring applications. This study incorporates PAI experimentation to generate an image dataset and employs machine learning techniques to estimate the length and width of surface cracks. Furthermore, the research delves into the feasibility assessment of employing PAI to investigate internal cracks within a steel sample through a numerical simulation-based study. The study’s findings underscore the efficacy of the PAI in achieving precise surface crack detection, with an acceptable root mean square error (RMSE) of 0.63 ± 0.03. The simulation results undergo statistical analysis techniques, including the analysis of variance (ANOVA) test, to discern disparities between pristine samples and those featuring internal cracks at different locations. The results discern statistically significant distinctions in the simulated acoustic responses for samples with internal cracks of varying sizes at identical/different locations (p < 0.001). These results validate the capability of the proposed technique to differentiate between internal crack sizes and positions, establishing it as a viable method for internal crack detection in steel. Full article