Process Knowledge Base Research Articles

A comparative study of LLMs and NLP approaches for supporting business process analysis

ABSTRACT This paper compares two approaches to support Business Process Analysis (BPA) for the construction of a Business Process Knowledge Base (BPKB). The methodology is based on the BPA Canvas metamodel, which starts from the preliminary output of the business analysis (an interview). We focus on the extraction of key elements from the text to build the BPKBcore. We experiment with approaches based on Natural Language Processing (NLP) and Large Language Models (LLMs), using a running example to compare the outcomes with manual annotations. The experiment shows that the LLM-based approach yields better performance, especially with enriched prompts.

A data-driven method combining knowledge graph with deep learning for constructing machining process knowledge base

A data-driven method combining knowledge graph with deep learning for constructing machining process knowledge base

Neural Network Approach to Cutting Tools Selection

Cutting tools selection is a key issue in today's research of computer aided process planning (CAPP). Traditionally, this task is carried out by process planners and knowledge base systems. Recently, process planners have started using newer artificial intelligent techniques, such as neural networks, fuzzy logic, intelligent agents, etc. to model cutting tools. In this study, the problem of cutting tools selection for milling and drilling operations is investigated. A neural network model is proposed to select the needed cutting tools and their geometry based feature type and machining operation. Feature type, feature condition, dimension ratio, feature taper and machining operation are presented to the network for each feature as input parameters. The network selects the required cutting tool. The advantage and effectiveness of the proposed model are verified through a several types of machining features

Design of a digital twin system for micro-lens array embossing manufacturing

Micro-lens arrays, due to their unique structure and outstanding optical performance, have been widely applied in advanced domains such as display technology, optical imaging, and laser processing. Among the manufacturing techniques, embossing molding is considered an efficient and precise method for fabricating micro-lens arrays. However, given the intricate structural characteristics of these arrays, precise control over the process becomes paramount. This study introduces a digital twin system for micro-lens array embossing manufacturing, grounded on a process knowledge base. The system relies on the rich process knowledge within the backend database combined with real-time sensor data, providing a powerful drive for the digital twin, thereby ensuring the precision and stability of the embossing manufacturing process. Additionally, the digital twin technology not only offers real-time monitoring and feedback for the production process of the micro-lens arrays but also aids researchers in optimizing process parameters, further enhancing product quality and consistency.

Foundations, the status quo, and future trends of the business model innovation process knowledge base

Foundations, the status quo, and future trends of the business model innovation process knowledge base

A method for constructing a machining knowledge graph using an improved transformer

Process knowledge base is a core component in the intelligent process, which determines the intelligent degree of product manufacturing and directly affects the production efficiency of products. However, traditional process knowledge base is often constructed manually, which is difficult and time-consuming. In addition, in the field of machining, there is a large amount of unstructured invisible process knowledge, which is not effectively organized and managed. To make use of this knowledge and provide knowledge support for downstream production and maintenance, a process knowledge base construction framework is proposed by using Knowledge Graph (KG) technology. Firstly, the ontology rules of process knowledge are designed from the perspective of the processing method of process characteristics according to the particularity of knowledge in the machining field. The process KG schema layer is then constructed. Secondly, a neural network BERT–Improved TRANSFORMER–CRF (BITC) model is proposed for the machining knowledge extraction task, and the data layer is constructed. Then, entity linking and knowledge fusion are performed by using the word vector cosine similarity algorithm and stored in Neo4j. The process KG is then constructed. Finally, the effectiveness of the proposed method is verified by using an aero-engine casing of an enterprise as an example. Under the same dataset, the BITC model scored higher than several other classical models. The Precision, Recall, and F1-score were 85.27%, 86.40%, and 85.83 %, respectively.

Template-based knowledge reuse method for generating high-speed railway virtual construction scenes

ABSTRACT Virtual construction has become an important approach to the high-quality development of high-speed railways, but existing methods have problems such as low efficiency in generating virtual construction scenes and the inability to reuse construction knowledge. To support the rapid visual representation of multiple types of construction processes and construction methods, a template-based knowledge reuse method is proposed. The method includes using a component-based modeling mode to build body structure models of a high-speed railway project and generate a 3D scene; decomposing the construction process and building a construction process knowledge base; establishing joint linkage models of construction machinery and forming a construction method knowledge template; and fusing multiple types of information according to a time sequence to visualize the construction process. Based on the template-based knowledge reuse method, a prototype system was developed, and virtual construction experiments were carried out. The results show that this method achieves the reuse of construction knowledge at different levels including construction machinery level, construction method level, and work site level. Compared with animation software for virtual construction, this method improves the production efficiency by 87%. Moreover, this method can provide a multilevel knowledge reuse scheme for diversified virtual construction.

The impact of entrepreneurship education on tourism students’ entrepreneurial intention in South Africa

ABSTRACT This paper explores the impact of entrepreneurship education on tourism students’ entrepreneurial intention, and insights of the desirability and feasibility of starting a tourism-related business upon graduation. A structured questionnaire survey was used to collect data from 154 randomly selected tourism students in a comprehensive University in South Africa. Data analyses included descriptive, bivariate, and multivariate analyses to address research objectives. The results indicate that entrepreneurship education influences tourism students’ entrepreneurial intentions, including students’ perceptions of the desirability and feasibility of starting tourism-related businesses. The findings further suggest that some respondent profile variables have influences on how tourism students perceive entrepreneurship education and entrepreneurial behaviour. The study recommends that the university that is studied implement a variety of reform programmes aimed at increasing employability or self-employment among university tourism graduates. Among them is the addition of a new entrepreneurship track to the undergraduate curriculum. Students, as from their first year of study should be invited to apply for the entrepreneurship education track, which includes business training as well as individualised coaching sessions with industry mentors. This will aid in the formation of professional networks, increased entrepreneurship process knowledge base, and self-efficacy among tourism students who want to become tourism entrepreneurs.

Scheme Design of Structured Process Data Management System Base on Android

The traditional paper process regulation form wastes a lot of resources and has low circulation efficiency, which is difficult to promote the digital transformation of enterprises. Based on Teamcenter platform, Process knowledge base and bill of processes can be built. Extract and summarize structured process information through Teamcenter and output process regulation form. On this basis, this paper develops an Android Application of process data management, which transmits the electronic process regulation form to the Android Application of process data management through JSON format in the internal LAN of the enterprise, to guide the operation and production. Verified by enterprise users, the process management collaboration platform improves the enterprise business flow, process preparation efficiency and process knowledge reuse rate, reduces many processes data redundancy, and lays a foundation for the digital transformation of enterprise process data management.

A knowledge-based method for tool path planning of large-sized parts

Proper tool paths ensure the high-efficiency and high-quality machining of workpiece. The current tool path planning method is inadequate to meet the complex process requirements for the complex workpiece of abundant local features. Due to the lack of ability of independent process decision-making, the planning effect is still heavily dependent on human experience and the planning is time-consuming and laborious, which is not conducive to shortening development cycle of new products. Therefore, a novel knowledge-based method for tool path planning is proposed in this paper. The proposed method can automatically plan the tool path that meets the requirements of the machining process by the adaptive process decision-making according to the perceived features of complex workpiece. The knowledge extraction method based on the syntactic dependency analysis is used to extract named entities in the process document. And the correctly classified entities are filled in the nodes of knowledge model represented by the form of frame to finish the establishment of process knowledge base. Then, with the help of feature extraction module based on the hybrid clustering method, the semantic segmentation of the point cloud of the workpiece is completed, and the Feature Matrix (FM) is formed. This matrix is used to provide feature information required for process decision, including Feature Vector (FV) and Structure Description Matrix (SDM). Finally, the tool path is generated in the Path Generator. At last, an automatic path planning system is developed for the painting process of automotive exterior. The planned paths are tested for 20 types of bumpers, where the chromatic aberration ΔE of each product is less than 1.4; both the average thickness of each paint and the requirement of production rate are satisfactory. These test results verify the effectiveness of the proposed tool path planning method.

An automatic method for constructing machining process knowledge base from knowledge graph

• A framework for automatically constructing a knowledge base is developed. • The extraction effect of this framework is better than other frameworks. • A evaluation algorithm is proposed to judge the optimal expression of knowledge. • Semantic and attribute weighting factors among knowledge entities are considered. The process knowledge base is the key module in intelligent process design, it determines the intelligence degree of the design system and affects the quality of product design. However, traditional process knowledge base construction is non-automated, time consuming and requires much manual work, which is not sufficient to meet the demands of the modern manufacturing mode. Moreover, the knowledge base often adopts a single knowledge representation, and this may lead to ambiguity in the meaning of some knowledge, which will affect the quality of the process knowledge base. To overcome the above problems, an automatic construction framework for the process knowledge base in the field of machining based on knowledge graph (KG) is introduced. First, the knowledge is classified and annotated based on the function-behavior-states (FBS) design method. Second, a knowledge extraction framework based on BERT-BiLSTM-CRF is established to perform the automatic knowledge extraction of process text. Third, a knowledge representation method based on fuzzy comprehensive evaluation is established, forming three types of knowledge representation with the KG as the main, production rules and two-dimensional data linked list as a supplement. In addition, to overcome the redundancy in the knowledge fusion stage, a hybrid algorithm based on an improved edit distance and attribute weighting is built. Finally, a prototype system is developed, and quality analysis is carried out. Compared with the F values of BiLSTM-CRF and CNN-BiLSTM-CRF, that of the proposed extraction method in the machining domain is increased by 7.35% and 3.87%, respectively.

A twin data and knowledge-driven intelligent process planning framework of aviation parts

ABSTRACT As the core link of intelligent manufacturing, the process planning of aviation parts still faces the challenges such as relying on manual experiences for process decision-making and lack of linkage between process design and manufacturing for process optimisation. Process knowledge could support scientific decision-making on process issues, while twin data, namely high-fidelity simulation data and feedback information of manufacturing site, could further verify the process plans and optimise process parameters, so as to continuously improve the quality of process plans. Consequently, this paper proposes a general framework for twin data and knowledge-driven intelligent process planning (TDKIPP) of aviation parts, and analyses four standard procedures that support the above-mentioned reference framework, namely mechanism-data fusion process digital twin model, dynamic process knowledge base, process decision-making and evaluation, machining quality prediction and process feedback optimisation. A thus constructed test bed of TDKIPP and its four application examples about the process planning of a micro turbojet engine integral impeller demonstrate the feasibility and effectiveness of the proposed approach.

Foundation, Status Quo, and Future Trends of the Business Model Innovation Process Knowledge Base

Foundation, Status Quo, and Future Trends of the Business Model Innovation Process Knowledge Base

Predicate model of process knowledge about observed objects in multichannel intelligent monitoring systems

A model of process knowledge about observed objects in multichannel intelligent monitoring systems, a method of intellectual analysis of processes and a decision-making method based on precedents are proposed. The main features and structural elements of the model of process knowledge are given. It is shown that advantage of this model is related to the configuration and hierarchical representation of the process for detecting and recognizing moving objects based on the intelligent analysis of signals and algebra of finite predicates. It is shown how this approach can be used to automate the process of detecting and recognizing objects that can be both in motion mode and in rest mode. As a result of the experiments, real radar signals are converted into symbolic images based on the algebra of finite predicates, and process knowledge about moving, stationary and inactive objects in monitoring systems of air and ground transport is formalized. It is also proposed to use this approach as a tool for building a model of process knowledge of multi-frame signal processing in intelligent monitoring systems for stealth and inactive objects. From the received signals about air and ground objects, a map or data matrix is formed. Then, as a result of accumulation, a new spatial signal image or virtual image is formed, that is, a new symbolic model of signal marks for moving and stationary objects is formed. Thus, the database turns into a process knowledge base, as a result of analysis of which the required solution is obtained.

The research on construction and application of machining process knowledge base

In order to realize the application of knowledge in machining process design, from the perspective of knowledge in the application of computer aided process planning(CAPP), a hierarchical structure of knowledge classification is established according to the characteristics of mechanical engineering field. The expression of machining process knowledge is structured by means of production rules and the object-oriented methods. Three kinds of knowledge base models are constructed according to the representation of machining process knowledge. In this paper, the definition and classification of machining process knowledge, knowledge model, and the application flow of the process design based on the knowledge base are given, and the main steps of the design decision of the machine tool are carried out as an application by using the knowledge base.

The Collaborative System Workflow Management of Industrial Design Based on Hierarchical Colored Petri-Net

Industrial design is a requisite and incontrovertible front-end design for Industrie 4.0 to realize personalization, agility, intelligence, and standardization, so it has very important practical significance to achieve industrial design collaborative workflow flexible management. This paper proposed a hierarchical colored Petri net (HCPN) for modeling the industrial design collaborative system workflow, which aims to provide a valid workflow model for the process management of the industrial design collaborative system. First, it is built the top-level workflow CPN model from product planning, markets research, product design, and product evaluation to prototype production, then the model is extended layer by layer to build the subnet model by the model refinement method. In the model, the activity of the workflow and the activity execution results are represented by the transitions ( $T$ ) and places ( $S$ ), respectively. The running state of the whole workflow is represented by the distribution of the token in the places. The token’ color sets expresses the real-time discrete state. By use of the function of token coloring places ( $S$ ) and the token’ color sets of HCPN, this paper extracts the common characteristics of process knowledge, including markets research results, design ideas, conceptual sketches, design schemes, human resources, and tacit creative knowledge, then uses the what, when, where, who, and how method to build knowledge information units for specific design event. Thus, realizes the industrial design process knowledge base construction and knowledge acquisition, which provides the necessary information and knowledge resources for the design reuse, flexibility management, and intelligent manufacturing of subsequent products.

Design and development of a CNC machining process knowledge base using cloud technology

Nowadays, computer numerical control (CNC) machine tool undertakes more processing tasks than other common machine tools because of its highly automated machining ability and high performance. However, due to the lack of intelligence in machining process planning, machining procedure of products mostly depends on process planners rather than CNC machine tools. To make product quality less dependable on process planner’s ability and improve the efficiency of process planning in order to fulfill changeable market, this paper presents an approach to design and develop CNC machining process knowledge base using cloud technology. The general standard STEP-NC is mapped to web ontology language (OWL) to describe machining process-related knowledge in a readable and comprehensible way. This mapping relation also makes knowledge suitable for storage in HBase. Through this ontology model, descriptive and logical knowledge can be collected. Hadoop platform is used in this approach to provide the NoSQL database HBase for large-scale knowledge storage and MapReduce programming model for large-scale knowledge processing. Taking advantage of MapReduce, knowledge query engine and reasoning engine can be developed. Users can submit task and resource descriptive files to the cloud through CNC controller and get machining process solutions from knowledge base. Evaluation mechanism is also adopted to filter low-quality knoweldge.

Development of a Knowledge Management System for the Automobile Industry Based on CAPP

Process planning is the key sector for automobile industry enterprises to shorten product development cycle. By studying the expression method of process information and standardized description method of process knowledge based on MBD, the process knowledge base is established with the uniform representation model as the core, on this basis, the knowledge embedding method oriented to process planning task, modeling method of process planning wizard and process planning navigation technology is studied, the maintenance and application platform of the process knowledge for the automobile industry is established, and integrated with the existing CAPP system, to realize the whole-process management of processes knowledge, so as to provide the support for the optimization and improvement of the manufacturing process.

Agent-based manufacturing service discovery method for cloud manufacturing

The development of new generation information technology has brought opportunities for industrial production model innovation. Especially, the cloud computing, Internet of Things, and big data technology are widespread applied in industrial fields. Based on this tendency, a service-oriented networked manufacturing model called cloud manufacturing (CM) was proposed in 2010. In order to realize this manufacturing model, one of the key technologies is how to achieve the discovery of manufacturing service which has not found a suitable solution. In this paper, a manufacturing service discovery framework based on agent is provided. The architecture consists of two parts: one is that manufacturing task agent and manufacturing service agent based on the expansion of the object model, and the other one is task and service matching process knowledge base. Furthermore, a structural matching method is proposed to implement the static parameters matching of task agent and service agent, and a multi-agent system bid mechanism is built to accomplish the dynamic parameters matching of the two agents. A simulation environment based on JADE has been properly developed. The simulation shows that the discovery method can effectively achieve the manufacturing service discovery in CM environment, which provides technical support for the cloud manufacturing service platform development.

Towards a method for business process and informal business rules compliance

SUMMARYBusiness process reengineering (BPR) is a common practice for a continuous improvement of the organization and the operations of an enterprise. An important technique of BPR is based on business rules (BRs). The latter are, in general, represented using natural language and, therefore, carry a certain degree of imprecision and ambiguity; therefore, our first objective is to start from informal BR and disambiguate them by using a question answering method based on a decision table. The introduction of BRs impacts on existing business processes (BPs), requiring often a reengineering intervention. In this paper, we present an approach to BPR based on the systematic use of ontologies and semantic annotations and focused on dependency constraints, a particular kind of BRs. To this end, we propose the synergic use of Business Process Abstract Language, a BP modeling framework to represent BP schemas, and Object Process Actor modeling Language, an ontological framework to capture the semantics of a business scenario. Both the frameworks are grounded in logic, and therefore, it is possible to apply effective reasoning methods to make inferences over a Business Process Knowledge Base stemming from the union of the two above components. Then we propose a query engine allowing for the detection of BPs that are not compliant with the BRs and, more precisely, the specific BP segment where to intervene. The proposed platform has been conceived not to substitute existing BPM tools but to integrate them providing advanced services to support rule‐based BPR activities. Copyright © 2011 John Wiley & Sons, Ltd.