As a branch of artificial intelligence (AI), expert systems are well-known for interpreting and deducing solutions to problems based on the rules contained within a knowledge base. Over the past decade, the application of expert systems in the industrial sector has matured significantly, permeating both upstream and downstream segments of the supply chain. Unlike traditional methods in industry, the approach using expert systems leverages the knowledge within domain experts, simulating the decision-making process of experts through rules and inference engines, rather than solely relying on the intuition of manual operators or engineers. In this study, the recent progress in the industrial application of expert systems were reviewed, including (1) the fundamental concepts of expert systems (e.g. the components of expert systems, expert systems based on different reasoning mechanisms, and the developmental history of expert systems) were briefly introduced; (2) the advantages and limitations of expert systems were discussed; (3) a series of detailed examinations for the expert system application in areas such as risk assessment, decision analysis, industrial classification, and fault diagnosis were elucidated in this study; (4) The challenges currently faced by expert systems and their future development prospects were discussed. This study not only reviewed the application of expert systems in the industrial field but also revealed how these systems drive automated decision support, reduce dependence on manual experience, and enhance operational efficiency and cost-effectiveness. Furthermore, the study highlighted future development directions. Overall, the research emphasized the importance of effectively integrating expert systems in industrial automation and intelligent manufacturing, providing valuable insights for practitioners and researchers.

Deep learning-based defect detection methods have gained widespread application in industrial quality inspection. However, limitations such as insufficient sample sizes, low data utilization, and issues with accuracy and speed persist. This paper proposes a semi-supervised semantic segmentation framework that addresses these challenges through perturbation invariance at both the image and feature space. The framework employs diverse perturbation cross-pseudo-supervision to reduce dependency on extensive labeled datasets. Our lightweight method incorporates edge pixel-level semantic information and shallow feature fusion to enhance real-time performance and improve the accuracy of defect edge detection and small target segmentation in industrial inspection. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art (SOTA) semi-supervised semantic segmentation methods across various industrial scenarios. Specifically, our method achieves a mean Intersection over Union (mIoU) 3.11% higher than the SOTA method on our dataset and 4.39% higher on the public KolektorSDD dataset. Additionally, our semantic segmentation network matches the speed of the fastest network, U-net, while achieving a mIoU 2.99% higher than DeepLabv3Plus.

The eggshell is the major source of protection for the inside of poultry eggs from microbial contamination. Timely detection of cracked eggs is the key to improving the edible rate of fresh eggs, hatching rate of breeding eggs and the quality of egg products. Different from traditional detection based on acoustics and vision, this paper proposes a nondestructive method of detection for eggshell cracks based on the egg electrical characteristics model, which combines static and dynamic electrical characteristics and designs a multi-layer flexible electrode that can closely fit the eggshell surface and a rotating mechanism that takes into account different sizes of eggs. The current signals of intact eggs and cracked eggs were collected under 1500 V of DC voltage, and their time domain features (TFs), frequency domain features (FFs) and wavelet features (WFs) were extracted. Machine learning algorithms such as support vector machine (SVM), linear discriminant analysis (LDA), decision tree (DT) and random forest (RF) were used for classification. The relationship between various features and classification algorithms was studied, and the effectiveness of the proposed method was verified. Finally, the method is proven to be universal and generalizable through an experiment on duck eggshell microcrack detection. The experimental results show that the proposed method can realize the detection of eggshell microcracks of less than 3 μm well, and the random forest model combining the three features mentioned above is proven to be the best, with a detection accuracy of cracked eggs and intact eggs over 99%. This nondestructive method can be employed online for egg microcrack inspection in industrial applications.

The detection of poultry egg microcracks based on electrical characteristic models is a new and effective method. However, due to the disorder, mutation, nonlinear, time discontinuity, and other factors of the current data, detection algorithms such as support-vector machines (SVM) and random forest (RF) under traditional statistical characteristics cannot identify subtle defects. The detection system voltage is set to 1500 V in the existing method, and higher voltages may cause damage to the hatched eggs; therefore, how to reduce the voltage is also a focus of research. In this paper, to address the problem of the low signal-to-noise ratio of microcracks in current signals, a wavelet scattering transform capable of extracting translation-invariant and small deformation-stable features is proposed to extract multi-scale high-frequency feature vectors. In view of the time series and low feature scale of current signals, various convolutional networks, such as a one-dimensional convolutional neural network (1DCNN), long short-term memory (LSTM), bi-directional long short-term memory (Bi-LSTM), and gated recurrent unit (GRU) are adopted. The detection algorithm of the wavelet scattering convolutional network is implemented for electrical sensing signals. The experimental results show that compared with previous works, the accuracy, precision, recall, F1-score, and Matthews correlation coefficient of the proposed wavelet scattering convolutional network on microcrack datasets smaller than 3 $\mathsf{\mu }$m at a voltage of 1000 V are 99.4393%, 99.2523%, 99.6226%, 99.4357%, and 98.8819%, respectively, with an average increase of 2.0561%. In addition, the promotability and validity of the proposed detection algorithm were verified on a class-imbalanced dataset and a duck egg dataset. Based on the good results of the above experiments, further experiments were conducted with different voltages. The new feature extraction and detection method reduces the sensing voltage from 1500 V to 500 V, which allows for achieving higher detection accuracy with a lower signal-to-noise ratio, significantly reducing the risk of high voltage damage to hatching eggs and meeting the requirements for crack detection.

The segmentation and localization of Agaricus bisporus is a precondition for its automatic harvesting. A. bisporus growth clusters can present challenges for precise localization and segmentation because of adhesion and overlapping. A low-cost image stitching system is presented in this research, utilizing a quick stitching method with disparity correction to produce high-precision panoramic dual-modal fusion images. An enhanced technique called Real-Time Models for Object Detection and Instance Segmentation (RTMDet-Ins) is suggested. This approach utilizes SimAM Attention Module’s (SimAM) global attention mechanism and the lightweight feature fusion module Space-to-depth Progressive Asymmetric Feature Pyramid Network (SPD-PAFPN) to improve the detection capabilities for hidden A. bisporus. It efficiently deals with challenges related to intricate segmentation and inaccurate localization in complex obstacles and adhesion scenarios. The technology has been verified by 96 data sets collected on a self-designed fully automatic harvesting robot platform. Statistical analysis shows that the worldwide stitching error is below 2 mm in the area of 1200 mm × 400 mm. The segmentation method demonstrates an overall precision of 98.64%. The planar mean positioning error is merely 0.31%. The method promoted in this research demonstrates improved segmentation and localization accuracy in a challenging harvesting setting, enabling efficient autonomous harvesting of A. bisporus.

Real-time quality monitoring through molten pool images is a critical focus in researching high-quality, intelligent automated welding. However, challenges such as the dynamic nature of the molten pool, changes in camera perspective, and variations in pool shape make defect detection using single-frame images difficult. We propose a multi-scale fusion method for defect monitoring based on molten pool videos to address these issues. This method analyzes the temporal changes in light spots on the molten pool surface, transferring features between frames to capture dynamic behavior. Our approach employs multi-scale feature fusion using row and column convolutions along with a gated fusion module to accommodate variations in pool size and position, enabling the detection of light spot changes of different sizes and directions from coarse to fine. Additionally, incorporating mixed attention with row and column features enables the model to capture the characteristics of the molten pool more efficiently. Our method achieves an accuracy of 97.416% on a molten pool video dataset, with a processing time of 16 ms per sample. Experimental results on the UCF101-24 and JHMDB datasets also demonstrate the method’s generalization capability.