Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
2,056
result(s) for
"Lin, Shih-Lin"
Sort by:
Research on tire crack detection using image deep learning method
Driving can understand the importance of tire tread depth and air pressure, but most people are unaware of the safety risks of tire oxidation. Drivers must maintain vehicle tire quality to ensure performance, efficiency, and safety. In this study, a deep learning tire defect detection method was designed. This paper improves the traditional ShuffleNet and proposes an improved ShuffleNet method for tire image detection. The research results are compared with the five methods of GoogLeNet, traditional ShuffleNet, VGGNet, ResNet and improved ShuffleNet through tire database verification. The experiment found that the detection rate of tire debris defects was 94.7%. Tire defects can be effectively detected, which proves the robustness and effectiveness of the improved ShuffleNet, enabling drivers and tire manufacturers to save labor costs and greatly reduce tire defect detection time.
Journal Article
Intelligent Fault Diagnosis and Forecast of Time-Varying Bearing Based on Deep Learning VMD-DenseNet
Rolling bearings are important in rotating machinery and equipment. This research proposes variational mode decomposition (VMD)-DenseNet to diagnose faults in bearings. The research feature involves analyzing the Hilbert spectrum through VMD whereby the vibration signal is converted into an image. Healthy and various faults show different characteristics on the image, thus there is no need to select features. Coupled with the lightweight network, DenseNet, for image classification and prediction. DenseNet is used to build a model of motor fault diagnosis; its structure is simple, and the calculation speed is fast. The method of using DenseNet for image feature learning can perform feature extraction on each image block of the image, providing full play to the advantages of deep learning to obtain accurate results. This research method is verified by the data of the time-varying bearing experimental device at the University of Ottawa. Through the four links of signal acquisition, feature extraction, fault identification, and prediction, a mechanical intelligent fault diagnosis system has established the state of bearing. The experimental results show that the method can accurately identify four common motor faults, with a VMD-DenseNet prediction accuracy rate of 92%. It provides a more effective method for bearing fault diagnosis and has a wide range of application prospects in fault diagnosis engineering. In the future, online and timely diagnosis can be achieved for intelligent fault diagnosis.
Journal Article
Application Combining VMD and ResNet101 in Intelligent Diagnosis of Motor Faults
Motor failure is one of the biggest problems in the safe and reliable operation of large mechanical equipment such as wind power equipment, electric vehicles, and computer numerical control machines. Fault diagnosis is a method to ensure the safe operation of motor equipment. This research proposes an automatic fault diagnosis system combined with variational mode decomposition (VMD) and residual neural network 101 (ResNet101). This method unifies the pre-analysis, feature extraction, and health status recognition of motor fault signals under one framework to realize end-to-end intelligent fault diagnosis. Research data are used to compare the performance of the three models through a data set released by the Federal University of Rio de Janeiro (UFRJ). VMD is a non-recursive adaptive signal decomposition method that is suitable for processing the vibration signals of motor equipment under variable working conditions. Applied to bearing fault diagnosis, high-dimensional fault features are extracted. Deep learning shows an absolute advantage in the field of fault diagnosis with its powerful feature extraction capabilities. ResNet101 is used to build a model of motor fault diagnosis. The method of using ResNet101 for image feature learning can extract features for each image block of the image and give full play to the advantages of deep learning to obtain accurate results. Through the three links of signal acquisition, feature extraction, and fault identification and prediction, a mechanical intelligent fault diagnosis system is established to identify the healthy or faulty state of a motor. The experimental results show that this method can accurately identify six common motor faults, and the prediction accuracy rate is 94%. Thus, this work provides a more effective method for motor fault diagnosis that has a wide range of application prospects in fault diagnosis engineering.
Journal Article
Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults
In recent years, artificial intelligence technology has been widely used in fault prediction and health management (PHM). The machine learning algorithm is widely used in the condition monitoring of rotating machines, and normal and fault data can be obtained through the data acquisition and monitoring system. After analyzing the data and establishing a model, the system can automatically learn the features from the input data to predict the failure of the maintenance and diagnosis equipment, which is important for motor maintenance. This research proposes a medium Gaussian support vector machine (SVM) method for the application of machine learning and constructs a feature space by extracting the characteristics of the vibration signal collected on the spot based on experience. Different methods were used to cluster and classify features to classify motor health. The influence of different Gaussian kernel functions, such as fine, medium, and coarse, on the performance of the SVM algorithm was analyzed. The experimental data verify the performance of various models through the data set released by the Case Western Reserve University Motor Bearing Data Center. As the motor often has noise interference in the actual application environment, a simulated Gaussian white noise was added to the original vibration data in order to verify the performance of the research method in a noisy environment. The results summarize the classification results of related motor data sets derived recently from the use of motor fault detection and diagnosis using different machine learning algorithms. The results show that the medium Gaussian SVM method improves the reliability and accuracy of motor bearing fault estimation, detection, and identification under variable crack-size and load conditions. This paper also provides a detailed discussion of the predictive analytical capabilities of machine learning algorithms, which can be used as a reference for the future motor predictive maintenance analysis of electric vehicles.
Journal Article
Advancements in noise reduction for wheel speed sensing using enhanced LSTM models
This research presents an Enhanced Long Short-Term Memory (LSTM) deep learning model for robust noise reduction in automotive wheel speed sensors. While wheel speed sensors are pivotal to vehicle stability, high-intensity or non-stationary noise often degrades their performance. Traditional filtering methods, including adaptive approaches and basic digital signal processing, frequently underperform under complex conditions. The proposed model addresses these limitations by incorporating an attention mechanism that selectively emphasizes transient high-noise frames, preserving essential rotational information. Comprehensive experiments, supported by Variational Mode Decomposition (VMD) and the Hilbert-Huang Transform (HHT), demonstrate that the Enhanced LSTM surpasses conventional techniques and baseline LSTM architectures in suppressing interference. T results yield significantly improved metrics across varying noise intensities, confirming both efficacy and stability. Although factors such as computational cost and the need for extensive labeled data remain, the Enhanced LSTM shows strong potential for real-time applications in wheel speed sensing. This work offers valuable insights into advanced noise mitigation and serves as a foundation for future deep learning research in complex automotive signal processing tasks.
Journal Article
Energy regeneration: A study on dynamic capacitance adjustment technology in piezoelectric shock absorbers for electric vehicles under varied road conditions
This study investigates the performance of dynamic capacitance regulation technology in electric vehicle piezoelectric shock absorbers for energy recovery under varying road conditions. By simulating a quarter-vehicle suspension system, this paper comprehensively analyzes the energy recovery efficiency of piezoelectric shock absorbers on gravel, speed bumps, and bumpy road conditions, comparing the performance differences between traditional fixed capacitance and dynamic capacitance. The results demonstrate that dynamic capacitance regulation technology can automatically adjust the capacitance value in response to instantaneous voltage changes, thereby enhancing energy recovery efficiency under various road conditions. This technology not only improves the energy conversion efficiency of piezoelectric shock absorbers but also strengthens the system’s adaptability to different vibration frequencies and amplitudes. Further simulation evidence confirms that piezoelectric shock absorbers, under dynamic capacitance regulation, achieve better energy recovery performance across diverse road conditions, offering new insights into improving the energy efficiency and sustainability of electric vehicles. The novelty of this research lies in the first application of dynamic capacitance regulation technology to the energy recovery system of electric vehicle piezoelectric shock absorbers, providing a new theoretical foundation and technical reference for optimizing electric vehicle energy recovery systems.
Journal Article
The Application of Machine Learning ICA-VMD in an Intelligent Diagnosis System in a Low SNR Environment
This paper proposes a new method called independent component analysis–variational mode decomposition (ICA-VMD), which combines ICA and VMD. The purpose is to study the application of ICA-VMD in low signal-to-noise ratio (SNR) signal processing and data analysis. ICA is a very important method in the field of machine learning. It is an unsupervised learning algorithm that can dig out the independent factors hidden in the observation signal. The VMD method estimates each signal component by solving the frequency domain variational optimization problem, and it is very suitable for mechanical fault diagnosis. The advantage of ICA-VMD is that it requires two sensory cues to distinguish the original source from the unwanted noise. In the three cases studied here, the original source was first contaminated by white Gaussian noise. The three cases in this study are under different SNR conditions. The SNR in the first case is –6.46 dB, the SNR in the second case is –21.3728, and the SNR in the third case is –46.8177. The simulation results show that the ICA-VMD method can effectively recover the original source from the contaminated data. It is hoped that, in the future, there will be new discoveries and advances in science and technology to solve the noise interference problem through this method.
Journal Article
AI-Based Tire Pressure Detection Using an Enhanced Deep Learning Architecture
Tires are integral to vehicular systems, directly influencing both safety and overall performance. Traditional tire pressure inspection methods—such as manual or gauge-based approaches—are often time-consuming, prone to inconsistency, and lack the flexibility needed to meet diverse operational demands. In this research, we introduce an AI-driven tire pressure detection system that leverages an enhanced GoogLeNet architecture incorporating a novel Softplus-LReLU activation function. By combining the smooth, non-saturating characteristics of Softplus with a linear adjustment term, this activation function improves computational efficiency and helps stabilize network gradients, thereby mitigating issues such as gradient vanishing and neuron death. Our enhanced GoogLeNet algorithm was validated on a dedicated tire pressure image database comprising three categories-low pressure, normal pressure, and undetected. Experimental results revealed a classification accuracy of 98.518% within 11 min and 56 s of total processing time, substantially surpassing the original GoogLeNet’s 95.1852% and ResNet18’s 92.7778%. This performance gain is attributed to superior feature extraction within the Inception modules and the robust integration of our novel activation function, leading to improved detection reliability and faster inference. Beyond accuracy and speed, the proposed system offers significant benefits for real-time monitoring and vehicle safety by providing timely and precise tire pressure assessments. The automation facilitated by our AI-based method addresses the limitations of manual inspection, delivering consistent, high-quality results that can be easily scaled or customized for various vehicular platforms. Overall, this work establishes a solid foundation for advanced tire pressure monitoring systems and opens avenues for further exploration in AI-assisted vehicle maintenance, contributing to safer and more efficient automotive operations.
Journal Article
Advanced Multi-Channel Echo Separation Techniques for High-Interference Automotive Radars
This paper proposes an integrated multi-stage framework to enhance frequency modulated continuous wave (FMCW) automotive radar performance under high noise and interference. The four-stage pipeline is applied consecutively: (i) an improved independent component analysis (ICA) blindly separates the two-channel echoes, isolating target and interference components; (ii) a recursive least-squares (RLS) filter compensates amplitude- and phase-mismatches, restoring signal fidelity; (iii) variational mode decomposition (VMD) followed by the Hilbert-Huang Transform (HHT) extracts noise-free intrinsic mode functions (IMFs) and sharpens their time-frequency signatures; and (iv) HHT-based beat-frequency estimation reconstructs a clean echo and delivers accurate range information. Finally, key IMFs are reconstructed into a clean signal, and a beat-frequency estimation via HHT confirms accurate distance results, closely aligning with theoretical predictions. On synthetic data with an input signal-to-noise ratio (SNR) of 12.7 dB, the pipeline delivers a 7.6 dB SNR gain, yields a mean-squared error of 0.25 m2, and achieves a range root-mean-square error (Range-RMSE) of 0.50 m. Empirical evaluations demonstrate that this enhanced ICA and VMD/HHT scheme effectively restores the fundamental echo signature, providing a robust approach for advanced driver assistance systems (ADAS).
Journal Article