Computers in Industry最新文献

Large numbers of maintenance Work Request Notification (WRN) records are created by industry as part of standard business work flows. These digital records hold invaluable insights crucial to best practice in asset management. Of particular interest are the cause–effect relations in the long text WRN field. In this research we develop a two-stage deep learning pipeline to extract cause-and-effect triples and construct a causal graph database. A novel sentence-level noise removal method in the first stage filters out information extraneous to causal semantics. The second stage leverages a joint entity-and-relation extraction model to extract causal relations. To train the noise removal and causality extraction models we produced an annotated dataset of 1027 WRN records. The results for causality extraction as measured by F1-score are 83% and 92% for the identification of Cause and Effect entities respectively, and 78% for a correct causal relation between these entities. The pipeline is applied to a real-word, industrial plant dataset of 98,000 WRN records to produce a graph database. This work provides a framework for technical personnel to query the causes of equipment failures enabling answers to questions such as “what are the most common, costly, and recent causes of failures at my facility?”.

Ultrasound welding technology is widely applied in the field of industrial manufacturing. In complex working conditions, various factors such as welding parameters, equipment conditions and operational techniques contribute to the formation of diverse and unpredictable line defects during the welding process. These defects exhibit characteristics such as varied shapes, random positions, and diverse types. Consequently, traditional defect surface detection methods face challenges in achieving efficient and accurate non-destructive testing. To achieve real-time detection of ultrasound welding defects efficiently, we have developed a lightweight network called the Lightweight Attention Detection Network (LAD-Net) based on an attention mechanism. Firstly, this work proposes a Deformable Convolution Feature Extraction Module (DCFE-Module) aimed at addressing the challenge of extracting features from welding defects characterized by variable shapes, random positions, and complex defect types. Additionally, to prevent the loss of critical defect features and enhance the network's capability for feature extraction and integration, this study designs a Lightweight Step Attention Mechanism Module (LSAM-Module) based on the proposed Step Attention Mechanism Convolution (SAM-Conv). Finally, by integrating the Efficient Multi-scale Attention (EMA) module and the Explicit Visual Center (EVC) module into the network, we address the issue of imbalance between global and local information processing, and promote the integration of key defect features. Qualitative and quantitative experimental results conducted on both ultrasound welding defect data and the publicly available NEU-DET dataset demonstrate that the proposed LAD-Net method achieves high performance. On our custom dataset, the F1 score and [email protected] reached 0.954 and 94.2%, respectively. Furthermore, the method exhibits superior detection performance on the public dataset.

Organizations use business process management systems to automate processes that they use to perform tasks or interact with customers. However, several variants of the same business process may exist due to, e.g., mergers, customer-tailored services, diverse market segments, or distinct legislation across borders. As a result, reliable support for process variability has been identified as a necessity. In this article, we introduce the concept of declarative process families to support process variability and present a procedure to formally verify whether a business process model is part of a specified process family. The procedure allows to identify potential parts in the process that violate the process family. By introducing the concept of process families, we allow organizations to deviate from their prescribed processes using normal process model notation and automatically verify if such a deviation is allowed. To demonstrate the applicability of the approach, a simple example process is used that describes several variants of a car rental process which is required to adhere to several process families. Moreover, to support the proposed procedure, we present a tool that allows business processes, specified as Petri nets, to be verified against their declarative process families using the NuSMV2 model checker.

Employee attrition and absenteeism are major problems that affect many industries and organizations, resulting in diminished productivity, elevated costs, and losses. These phenomena can be attributed to multiple factors that are difficult to anticipate for human resources or management. Therefore, this paper proposes a content-based methodology for the analysis and classification of employee attrition and absenteeism that can be used for talent analysis and management, a task that is traditionally carried out ex-post. The developed methodology, called E(3A)CSPM, is based on SPM (sequential pattern mining). In the methodology, four public datasets with diversified employee data are adopted, which are initially transformed into a suitable format. Then, SPM algorithms are applied to the transformed datasets to reveal recurring patterns and rules of features. The discovered patterns and rules not only offer information regarding features that have a key role in employee attrition and absenteeism but also their values. These frequent patterns of features are thereafter used to classify/predict employee attrition and absenteeism. Eight classifiers and multiple evaluation metrics are used in experiments. The performance of E(3A)CSPM is contrasted with state-of-the-art approaches for employee attrition and absenteeism and the obtained findings reveal that E(3A)CSPM surpasses these approaches.

This study presents a framework for the real-time detection of surface cracking in large-sized stamped metal parts. The framework aims to address the challenges of low detection efficiency and high error rates associated with manual cracking detection. Within this framework, a novel network, SNF-YOLOv8, is proposed to efficiently detect cracking while ensuring that the detection speed matches the production speed. The network incorporates a convolutional spatial-to-depth module to enhance the detection of small-sized cracking and mitigate surface interference during inspections. Furthermore, a visual self-attention mechanism is introduced to improve feature extraction. A combination of standard convolutional and depth-wise separable convolutional layers in the neck network enhances speed without compromising accuracy. Experimental validation conducted using a dataset from actual production lines, in collaboration with a multi-national corporation, demonstrates that SNF-YOLOv8 achieves an average precision of 85.2% at a detection speed of 164 frames per second. The framework achieves an accuracy rate of 98.8% in detecting large-sized cracking and 96.4% in detecting small-sized cracking, meeting the requirements for high-precision and real-time detection applications.

To make manufacturing technology productive, manufacturers rely on a production planning and control (PPC) framework that plans ahead and monitors ongoing transformation processes. The design of an appropriate framework has far-reaching implications for the manufacturing organization as a whole. Yet, to date, there has been no unified guidance on key PPC design issues. This is strongly needed, as it has been argued that novel information processing technologies – as part of Industry 4.0 – result in PPC frameworks with decentral structures. This conflicts with traditional works arguing for hierarchical or central structures. Therefore, we review the PPC design literature to create a comprehensive overview and summarize design proposals. Based on our review, we come to the intermediate conclusion that PPC frameworks continue to have a hierarchical structure, although decision-making is shifted more to decentral levels compared to traditional hierarchies. Our analysis suggests that the effect of a decentralization shift has potentially strong and poorly understood implications, both from a decision-making and organizational perspective.

In the manufacturing industry, unstructured documents such as design guidelines, regulatory documents, and failure cases are essential for product development. However, due to the large volume and frequent revisions of these documents, designers often find it difficult to keep up to date with the latest content. This study presents a method for analyzing the characteristics of unstructured design guidelines and automatically constructing a knowledgebase of design requirements from them. A knowledgebase is structured data that a computer can understand, and that can be used to assist designers in the design process. The knowledgebase is constructed using the sections of the document, including design variables and design requirements. The construction process involves pre-processing the documents, extracting information using natural language processing models, and generating a knowledgebase using predefined rules. A requirements knowledgebase was experimentally constructed from a standard document on the general requirements for the design of pressure vessels (American Society of Mechanical Engineers Section VIII Division 1) using the proposed method. In the experiment, the accuracy of information extraction was 86.3 %, and the generation process took 3 min and 50 s. Thus, the proposed method eliminates the need for specialized training of deep learning models and can be applied to various design guideline documents with simple modifications to the design vocabulary and rules. The knowledgebase has applications in design validation, and is expected to enhance the efficiency of the product development process and contribute to reducing the overall development timeline.

As a crucial component supporting aero-engine functionality, effective fault diagnosis of bearings is essential to ensure the engine's reliability and sustained airworthiness. However, practical limitations prevail due to the scarcity of aero-engine bearing fault data, hampering the implementation of intelligent diagnosis techniques. This paper presents a specialized method for aero-engine bearing fault diagnosis under conditions of limited sample availability. Initially, the proposed method employs the refined composite multiscale phase entropy (RCMPhE) to extract entropy features capable of characterizing the transient signal dynamics of aero-engine bearings. Based on the signal amplitude information, the composite multiscale decomposition sequence is formulated, followed by the creation of scatter diagrams for each sub-sequence. These diagrams are partitioned into segments, enabling individualized probability distribution computation within each sector, culminating in refined entropy value operations. Thus, the RCMPhE addresses issues prevalent in existing entropy theories such as deviation and instability. Subsequently, the bonobo optimization support vector machine is introduced to establish a mapping correlation between entropy domain features and fault types, enhancing its fault identification capabilities in aero-engine bearings. Experimental validation conducted on drivetrain system bearing data, actual aero-engine bearing data, and actual aerospace bearing data demonstrate remarkable fault diagnosis accuracy rates of 99.83 %, 100 %, and 100 %, respectively, with merely 5 training samples per state. Additionally, when compared to the existing eight fault diagnosis methods, the proposed method demonstrates an enhanced recognition accuracy by up to 28.97 %. This substantiates its effectiveness and potential in addressing small sample limitations in aero-engine bearing fault diagnosis.

The Knowledge-Based Digital Twin System is a digital twin system developed on the foundation of a knowledge graph, aimed at serving the complex manufacturing process. This system embraces a knowledge-driven modeling approach, aspiring to construct a digital twin model for the manufacturing process, thereby enabling precise description, management, prediction, and optimization of the process. The core of this system lies in the comprehensive knowledge graph that encapsulates all pertinent information about the manufacturing process, facilitating dynamic modeling and iteration through knowledge matching and inference within the knowledge, geometry, and decision model. This approach not only ensures consistency across models but also addresses the challenge of coupling multi-source heterogeneous information, creating a holistic and precise information model. As the manufacturing process deepens and knowledge accumulates, the model's understanding of the process progressively enhances, promoting self-evolution and continuous optimization. The developed knowledge-decision-geometry model acts as the ontological layer within the digital twin framework, laying a foundational conceptual framework for the digital twin of the manufacturing process. Validated on an aero-engine blade production line in a factory, the results demonstrate that the knowledge model, as the core driver, enables continuous self-updating of the geometric model for an accurate depiction of the entire manufacturing process, while the decision model provides deep insights for decision-makers based on knowledge. The system not only effectively controls, predicts, and optimizes the manufacturing process but also continually evolves as the process advances. This research offers a new perspective on the realization of the digital twin for the manufacturing process, providing solid theoretical support with a knowledge-driven approach.

Anomaly detection with high accuracy, recall, and low error rate is critical for the safe and uninterrupted operation of cyber-physical systems. However, detecting anomalies in multimodal time series with different modalities obtained from cyber-physical systems is challenging. Although deep learning methods show very good results in anomaly detection, they fail to detect anomalies according to the requirements of cyber-physical systems. In the use of graph-based methods, data loss occurs during the conversion of time series into graphs. The fixed window size used to transform time series into graphs causes a loss of spatio-temporal correlations. In this study, we propose an Event Aware Graph Attention Network (EA-GAT), which can detect anomalies by event-based cyber-physical system analysis. EA-GAT detects and tracks the sensors in cyber-physical systems and the correlations between them. The system analyzes and models the relationship between the components during the marked periods as a graph. Anomalies in the system are found through the created graph models. Experiments show that the EA-GAT technique is more effective than other deep learning methods on SWaT, WADI, MSL datasets used in various studies. The event-based dynamic approach is significantly superior to the fixed-size sliding window technique, which uses the same learning structure. In addition, anomaly analysis is used to identify the attack target and the affected components. At the same time, with the slip subsequence module, the data is divided into subgroups and processed simultaneously.