Traditional engine fault diagnosis methods usually need to extract the features manually before classifying them by the pattern recognition method, which makes it difficult to solve the end-to-end fault diagnosis problem. In recent years, deep learning has been applied in different fields, bringing considerable convenience to technological change, and its application in the automotive field also has many applications, such as image recognition, language processing, and assisted driving. In this paper, a one-dimensional convolutional neural network (1D-CNN) in deep learning is used to process vibration signals to achieve fault diagnosis and classification. By collecting the vibration signal data of different engine working conditions, the collected data are organized into several sets of data in a working cycle, which are divided into a training sample set and a test sample set. Then, a one-dimensional convolutional neural network model is built in Python to allow the feature filter (convolution kernel) to learn the data from the training set and these convolution checks process the input data of the test set. Convolution and pooling extract features to output to a new space, which is characterized by learning features directly from the original vibration signals and completing fault diagnosis. The experimental results show that the pattern recognition method based on a one-dimensional convolutional neural network can be effectively applied to engine fault diagnosis and has higher diagnostic accuracy than traditional methods.

Seeking a straightforward and efficient method to predict expressway traffic noise, this study selected three expressway segments in Guangdong Province, China and conducted noise monitoring at ten different sites along these expressways. Data analysis revealed that the mean sound levels and standard deviations were significantly positively and negatively correlated with traffic volume, respectively, and the frequency distribution of sound levels closely resembled a normal distribution. A probability prediction model for expressway traffic noise, based on a normal distribution, has been constructed utilizing these characteristics. The mean and standard deviation of the model were determined using a linear regression method, and the relationship between the mean, standard deviation, and various noise evaluation indices was derived from the characteristics of the normal distribution. The proposed model enables the direct prediction of the statistical frequency distribution of sound levels and various noise evaluation indices. Despite using only two five-minute segments of monitoring data for training, the model’s average prediction error for L_eq, L₁₀, L₅₀, and L₉₀ was only 1.06, 1.07, 1.04, and 1.32 dB(A). With increased sample data for modeling, the model’s predictive accuracy notably improved. This study provides a highly effective predictive tool for assessing traffic noise for residents near expressways.

With the widespread application of UAV (UAV) in various fields, more and more attention has been paid to the operation status monitoring and fault diagnosis of UAV. During the use of UAV, the motors, blades, connectors and other components may inevitably experience wear, fatigue, and breakage, which are difficult to directly monitor through sensors. Therefore, a fault identification method based on one-dimensional convolutional neural network (1D-CNN) is proposed to provide ideas for the research on the mechanical fault diagnosis of UAV. A Bluetooth wireless acceleration-attitude sensor is used to collect the acceleration, angular velocity and angle of the free flying UAV in X, Y, and Z directions. With these characteristic parameters as sample data, fault identification can be implemented using deep learning model. Besides, to deal with over-fitting, a data reconstruction method of partition sampling is proposed. By comparing different input parameters and optimization functions, we found that when using multi-parameter + RMSProp optimization, the recognition accuracy reaches 98%. In addition, a comparative analysis is carried out using shallow neural network PNN and SVM methods, and the results show that the proposed 1D-CNN model outperforms both shallow neural networks and traditional machine learning methods.

Unmanned aerial vehicles are increasingly used across various applications, but their vulnerability to faults under complex operating conditions poses significant risks to safety and mission success. Fault diagnosis in UAVs is essential for ensuring reliable and safe operations. This paper proposes a novel framework for UAV fault diagnosis, integrating a Multi-Scale Residual Network (MSR) with an Ordered Quadruplet Loss (OQL). The MSR leverages multi-scale feature extraction to capture intricate fault patterns, while the OQL addresses the challenge of modeling fault severity progression within fault categories, thus improving fault classification and severity ordering. The framework is designed to handle both known and unknown fault states, using deep metric learning to structure the embedding space based on fault similarities. Through a series of experiments, including rotor faults simulated on a DJI Phantom 4 Pro+ V2.0 quadrotor, we demonstrate that the proposed model achieves high classification accuracy (100%) and robust fault severity ordering (99.6%). Additionally, it shows excellent generalization capability, performing well even with partially unseen fault states. This work enhances the diagnostic performance and practical applicability of UAV fault detection, offering a significant step forward in ensuring UAV safety and reliability in real-world conditions.

The vibration modulation of the localized faults of sun gears is complicated because of the structure and motion features of planetary gearboxes. It is challenging to completely determine the vibration modulation mechanism. To address this issue, the influences of fluctuations in speed on the factors that affect vibration like the transfer path function, time-varying projection function, and meshing force were studied. Improved vibration amplitude and frequency modulation models were then established by combining the factors affecting vibration considering the speed fluctuations caused by the localized faults of sun gears. Regarding the features of vibration modulation of localized faults of sun gears, we concluded that both fault feature frequency and carrier rotational frequency modulate the harmonics of the meshing frequency, which form two groups of modulation sidebands. In addition, the harmonics of the fault feature frequency over the whole frequency range are modulated by the rotational frequency of the carrier, which is more dominant in the resonance domain. The experimental results of localized faults of sun gears strongly agree with those deduced using the proposed models. This research contributes an effective frequency indicator that can be used to confirm the condition of planetary gearboxes.