Gas storage facilities have long faced bottlenecks in the core control systems of high-power compressors, where operational safety, efficiency, and automation under complex conditions remain key challenges. Traditional single-sensor monitoring offers limited perception and low data utilization, falling short of ensuring reliable operation and intelligent decision-making. With AI engineering advancing toward multi modal and heterogeneous industrial applications, research has increasingly focused on multi-sensor fusion and intelligent diagnostics. Although multi-sensor networks provide complementary information and enhanced perception, issues like data heterogeneity, class imbalance, and cross-domain distribution differences continue to constrain diagnostic performance. To address these issues, a Dual-branch Heterogeneous Synergistic Network (DHSNet) is proposed to achieve cross-modal fusion of vibration signals and infrared thermal imaging signals. The framework incorporates a cross domain adaptation strategy to enhance domain-invariant feature learning and a dynamic focal loss function to adaptively adjust class weights based on real-time output indicators, mitigating the impact of sample imbalance. Experimental results demonstrate that the proposed method achieves an average diagnostic accuracy of 93.27% in cross-load transfer tasks, outperforming other methods used in imbalanced scenarios by over 4%. Besides, the proposed method maintains robust diagnostic performance exceeding 90% accuracy across most load transfer scenarios, even under moderately imbalanced data conditions. Feature contribution analysis further validates the effectiveness of multi modal synergy, and revealing the complementary mechanism of multi-source data. This study enhances Prognostics and Health Management (PHM) systems' engineering applicability and perception capabilities in multi-sensor industrial environments, providing reliable multi-modal diagnostics to advance intelligent maintenance.

This paper investigates the compound control problem of aero-engine networked systems with multiple uncertainties and saturation constraints. To address these challenges, a novel sliding mode controller (SMC) with extended state observer (ESO) is first designed to implement anti-disturbance control, which can alleviate the chattering phenomenon without sacrificing robustness by two parallel ways: adaptive switching term and disturbance compensation. Then, the predictive control strategy is introduced to further optimize the reaching phase, and two disturbance-compensation-based predictive SMC schemes are proposed to coordinate diverse control requirements in the presence and absence of system constraints. When there are no saturation limits, the optimization problem is formulated as a convex one, and its analytic solution is derived explicitly. Furthermore, both state and control limits are considered in the system synthesis, and a standard prediction problem with multiple constraints is established. For high-frequency sampling needs, the Laguerre function is designed to reconstruct the input variables of the prediction sequence, which can effectively reduce the calculation complexity without compromising the dynamic performance. The experiment simulations show that the proposed compound schemes have strong robustness to multiple uncertainties and saturation constraints, and achieve promising control performance in both transient and steady-state phases.Note to Practitioners—As the heart of aircraft, aero-engine system is developing towards networked and intelligent. Subsequently, some new challenges are exposed to be addressed, such as communication delays, saturation constraints, electromagnetic disturbances, etc., which make the existing linear schemes fail to guarantee diverse requirements. Although SMC owns good robustness against multiple uncertainties, most relevant results still face some challenges, such as high switching gain, known disturbance boundary assumption, and sufficient control period. To address these difficulties, we propose two disturbance-compensation-based predictive SMC schemes to coordinate diverse control requirements with and without system constraints. The proposed schemes do not rely on excessive computing resources and are applicable to high-frequency sampling systems. The results of this paper can also provide guidance for the design of robust compound strategies for other networked systems with multiple uncertainties.

In industrial scenarios, mechanical faults are episodic and uncertain. Thus the monitoring data collected is usually extremely imbalanced, resulting in intelligent diagnostic models that suffer from majority-class dominance, minority-class overfitting, and poor generalization performance. Therefore, a knowledge distillation-guided cost-sensitive ensemble learning framework is proposed. It effectively combines ensemble learning and cost-sensitive learning to fully extract the multiscale features, effectively leverage the critical multi-depth features, and emphasize classifying the most confusing classes. Specifically, multiple-scale feature extraction and multi-order fusion are first employed to fully utilize the fault information. Afterward, the complementary diagnostic knowledge at different depths of the network is embedded into a novel ensemble learning process for better integration decisions. Then an improved knowledge distillation method achieves the mutual transfer and sublimation of excellent diagnostic knowledge while focusing on the most confusing fault classes to achieve the effective representation of various types of faults. Finally, a cost-sensitive strategy is applied to further increase attention to minority classes. The experimental results for various complex data imbalance scenarios, including extreme imbalance, step imbalance, continuous imbalance, interclass imbalance, and intra-class imbalance, all indicate that the proposed method can achieve state-of-the-art performance and provide a promising solution for the practical industrial application of intelligent diagnostic methods.

The high energy, transient, and nanosecond pulse of laser shock peening (LSP) renders real-time monitoring of material surface integrity challenging. Along these lines, this article proposes a novel method for real-time evaluation of the surface quality in the LSP process based on the multiple acoustic emission (AE) technique and hybrid attention-based convolutional neural networks (HACNN). First, a new quality index, surface hardness integrity (SHI) is constructed to fully characterize both the hardening rate and the impact depth of the material surface, while a good linear relationship is demonstrated between SHI and AE. Then, a feature extraction method, called wavelet packet energy cepstrum (WPEC), is proposed that requires minor signal processing expertise while being able to adaptively match the modal distribution of the broadband AE signals. Next, WPEC is fed into HACNN, where HA consists of channel attention and multiscale spatial attention (MSA). MSA combines the information flow at the global time, local time, and local frequency. Moreover, numerous comparisons were conducted with several traditional cepstrum and advanced attention mechanisms. The effectiveness of the proposed method is carefully verified by the LSP experiments for 7075 Al alloy achieving the highest average accuracy of 99.33% for the identification of four types of SHI. In addition, the sensitivity of HA in high-frequency event onset and offset is demonstrated by visualizing the gradient weights.

Strict industry demands necessitate better penetration classification in gas tungsten arc welding of aluminum alloys. An innovative classification method, namely time-frequency spectrogram based convolutional neural network (TF-CNN), has been developed in this article. The logarithmic time-frequency spectrograms are used to interpret the raw arc sound data in the time-frequency domain and served as the input of an optimized convolutional neural network (CNN) model for welding quality classification. The leaky rectified linear unit activation function and root mean square prop optimizer are utilized to improve the property of CNN. Effective arc sound features are extracted automatically by the CNN model. The proposed method is experimentally verified to recognize four penetration states with an average accuracy of 98.2%, which significantly outperforms the four typical comparison models. The generation mechanism and characteristics of arc sound are discussed as the adaptive feature extraction of TF-CNN. These studies expand the application scope of CNN to intelligent welding and achieve notable effects.

Online monitoring and diagnosis of welding quality is essential for intelligent welding manufacturing. The recognition performance of penetration for aluminum alloy in gas tungsten arc welding (GTAW) still needs to be improved to meet the strict industry demands. This paper proposed a novel recognition method, time-frequency image based convolution neural network (TF-CNN), for GTAW penetration recognition. Time-frequency images were calculated from arc sound signals using short time Fourier transform and applied to analyze the non-stationarity of arc sound. The logarithm of time-frequency image was taken to construct the appropriate input matrix of CNN, which was optimized to improve its recognition performance, including the activation function, learning rate and architecture of network. The experimental results show that the proposed TF-CNN achieved an excellent recognition performance with 98.2% recognition accuracy and 0.21 accuracy variance for GTAW seam penetration recognition and outperformed the traditional methods. This paper provides some guidance for the application of CNN to other monitoring signals of intelligent manufacturing.

Aluminum alloy is the main structure material in aerospace industry. Online defect detection for aluminum alloy in pulsed gas tungsten arc welding (GTAW) is still challenging, especially for increasing application of robotics. This paper presents an intelligent methodology for real-time evaluation of weld penetration defects based on arc audible sound sensing for aluminum alloy in robotic-pulsed GTAW. The generation mechanism of arc sound was investigated using correlation analysis, high-speed camera observing and frequency spectrum analysis before denoising of arc sound. Two feature selection approaches based on Fisher distance and principal component analysis (PCA) were developed to select the frequency components related to seam defects, and then, their performance were qualitatively and quantitatively analyzed. Finally, a new classification model integrating support vector machine with grid search optimization and cross-validation (SVM-GSCV) was established to identify underpenetration, normal penetration, and burning through. The proposed methodologies were verified to be effective with high accuracy and robustness. This paper can provide some guidance for condition monitoring of additive manufacturing (AM) or process industry.