Knowledge-based Expert System Research Articles

Verifying Welding Processes Selection for a Case Study Using an Analytic Hierarchical Process

This paper aims to develop a framework for differentiating the selection of welding processes using specialized knowledge-based expert systems, which are particularly useful in dealing with issues that require complex decision-making. A program was created and programmed using the process information maps (PRIMAs) matrix in Visual Basic Access for selecting welding processes in a study. The program is in two stages. In the first stage, it excludes non-candidate operations according to several criteria, the most important of which is the type of metal and its thickness. The second stage is arranging operations using multi-criteria methods for decision-making through research to resolve complicated problems involving multiple factors. The hierarchical analysis process (AHP) was used. It is considered one of the most frequently used multi-criteria decision-making methods. The selection of analytic hierarchical process. AHP criteria depend on experience and knowledge rather than specific data for selecting alternatives and determining weights. The methodology is straightforward, easy to comprehend, and applicable to various domains needing intricate decision-making. The program results are compared with those of a previously published case to choose the best welding processes for a study case, which is a home radiator, and results matching the candidate processes were discovered.

Модель процесса формирования каталога сценариев для анализа и оценки функциональной безопасности автоматизированных систем вождения автомобилей

In the development of highly automated and unmanned vehicles, the auto industry is faced with a new set of problems associated with the need to standardize elements of automated driving systems and determine the rules for their testing and certification. Due to the acceleration of scientific and technological progress and the development of new technologies, previously used standards began to become obsolete as the practice of their application accumulated, and sometimes even before the approval of a particular technical regulation. In these conditions, a promising technical and legal solution may be the use of fuzzy logic in tools for aggregation and management of expert knowledge in the processes of certification and testing of highly automated vehicles and elements of their automated control systems. Fuzzy decision-making models use typical fuzzy situations that form catalogs of scenarios for testing vehicles and their systems. In this way, an expert system knowledge base can be formed in which knowledge engineers apply a set of test scenario or experiment parameters for testing and simulation. Determining the parameters of a new scenario, their similarity with previously formalized scenarios and the decision to include a particular scenario in the scenario catalog remains with the experts. The approaches used at the present stage to the formalization of expert knowledge are not acceptable for creating knowledge bases controlled by big data management systems or artificial neural networks, which are in the near future in the development of expert systems. The article proposes a method by which a knowledge engineer administering an expert system can automate the creation of a catalog of “fuzzy” test scenarios and simulation modeling of systems, by automatically searching for the maximum value of the states of these systems belonging to maps and catalogs of scenarios, with a probability specified by the expert, with using machine learning methods.

Additive manufacturing service bureau selection: A Bayesian network integrated framework

Additive manufacturing service bureaus (AMSBs) are crucial for enabling manufacturing organizations to leverage the benefits of additive manufacturing (AM) technology, such as on-demand manufacturing, production speed, etc., all while eliminating the expense of maintaining inventories. Consequently, many organizations favor AMSBs for expertise, cost efficiency, and access to diverse equipment, materials, and post-processing, reducing the necessity for substantial in-house investments. While researchers have explored evolving business models and the types of AM services offered by AMSBs to some extent, there is a noticeable research gap in selecting the most compatible AMSB for specific customer requirements, which this research would like to address. Initially, this research identifies various types of services offered by AMSBs, classifying them into eight groups: generative, evaluative, explorative, facilitative, constructive, decisive, selective, and assistive. Then, a knowledge-based expert system is introduced to select a suitable type of AM service. Further, 101 AMSB selection criteria are identified and grouped into criteria and sub-criteria by incorporating insights from literature and experts. Then, 26 pertinent criteria were shortlisted through Delphi. Neutrosophic best-worst method is then utilized to quantify criteria weights. Finally, a Bayesian network is used to calculate the selection probability of each AMSB, identifying the AMSB with the highest probability as the most compatible. The robustness of this framework is validated through sensitivity analysis. The practical effectiveness of the framework was demonstrated through a case study involving Ferro Oil-Tech India Private Limited. The analysis of the results provided valuable managerial insights and suggested ways to enhance the business competitiveness of the organization.

Knowledge-based expert system to drive an informationally interoperable manufacturing system: An experimental application in the Aerospace Industry

The industrial revolutions have challenged organisations to rethink their product design and manufacturing processes, making them faster and more connected to market demands and changes. Digital technologies have emerged with solutions to virtual represent physical objects, processes, systems, or assets to simulate and analyse the impact of manufacturing changes before actual implementation. However, the challenge is to deal with thousands of heterogeneous information sets which must be shared simultaneously by different groups within and across institutional boundaries. Each manufacturing industry has its format and model to represent the product in the development, manufacturing process, material features, etc. In this context, this paper explores a knowledge-based expert system to support the information exchange and inconsistency detection across the manufacturing process, specifically in an experimental application in the Aerospace Industry. The proposed framework was based on knowledge formalisation and semantic rules through ontologies, semantic reconciliation strategies and connectivity interfaces to manage information and knowledge and identify inconsistencies across the manufacturing system. It was mainly evaluated across the product and manufacturing design of sheet metal forming aluminium thin wall parts for the aerospace industry. Results demonstrate the capability of the approach to enhance data accuracy, coherence, and efficiency throughout the manufacturing of complex products. However, the solution presents challenges such as interdisciplinary collaboration in product design, specific information requirements for manufacturing planning, and the impact of production planning on manufacturing capacities.

A knowledge-based expert system for campus helpdesk request processing

A knowledge-based expert system for campus helpdesk request processing

Degumming and bleaching process troubleshooting in a palm oil refining process using fuzzy expert system with thematic analysis

AbstractDegumming and bleaching are critical steps in the palm oil refining process, as they are the precursors to the qualities of refined, bleached, and deodorized palm oil. In practice, plant operators often face oil rejections in these processes and solve the problem by trial and error. Hence, a fuzzy expert system is developed to troubleshoot the degumming and bleaching process, for identifying failures and suggesting actions. However, developing the knowledge base and inference engine in the fuzzy expert system for troubleshooting the degumming and bleaching process is challenging because the data in the actual palm oil refining process are poorly documented and must be obtained from various sources, including field observation, document analysis, and interviews, and need to be analyzed using thematic analysis. The results from the thematic analysis were represented as input and output variables of the fuzzy expert system. The developed fuzzy expert system is tested and validated against different data sets and industrial data to identify faults and suggest necessary actions. To evaluate the robustness of the troubleshooting system, the membership functions of the fuzzy expert system are adjusted based on the distributed control system (DCS). The results show that the troubleshooting system can effectively diagnose potential faults and provide necessary actions and can serve as a useful guidance for failures in the degumming and bleaching process.

INTEGRATED ARTIFICIAL INTELLIGENCE TECHNIQUES APPLICATION FOR WASTEWATER pH CONTROL

The control of the pH neutralization process has a decisive role in many industrial branches, as: wastewater treatment, biotechnology, pharmaceutical industry, chemical processing, etc. However, the pH neutralization process is a difficult one to control, due to time-varying process parameters, its high non-linearity and to the sudden variation of the pH around the equivalence point. The paper presents a device and an integrated application that uses artificial intelligence (IA) developed for dosage of the necessary reactants in wastewater pH control. The AI techniques were integrated into the application by developing an expert system (ES). For this purpose, were used the necessary if-then rules (rules that make up the inference engine (IE) of the ES) related to the flowrates of the reactants necessary for wastewater pH neutralization. The ES knowledge base (KB) was built based on the recorded pH values. The hardware component (the device) was created using the Arduino equipment.

An Expert Knowledge-Based System to Evaluate the Efficiency of Dry Construction Methods

The issues that the construction sector currently faces with regard to productivity and efficiency are well acknowledged. In the construction industry, there is plenty of space for efficiency to improve, with an increasing number of new tools and methods coming out. One of the solutions to increase efficiency is the application of modern methods of construction. The modern methods of construction, especially dry construction techniques, are developing so that there is a larger volume of high-quality production with a shorter time for procurement. Not only in the construction of skeletons but also in the finishing works, it is a huge advantage if there are implemented techniques that eliminate traditional wet construction works and thus shorten the construction time. On the other hand, however, the question of efficiency in relation to their costs is raised. Based on theoretical and empirical research, the aim of this study is to demonstrate the potential of modern dry construction systems and solutions for finishing works, especially in relation to the construction time and construction cost. For this purpose, an expert knowledge system, named the complex COMBINATOR, was developed. Through a set of simulations with the help of the COMBINATOR, the effects of different combinations of dry construction systems and techniques (DCSTs) and traditional wet construction systems and techniques (WCSTs) on the time and cost of finishing construction works were measured. Based on the results of simulations carried out through the complex COMBINATOR with an inference engine that enabled these simulations, the potential of dry construction techniques for the implementation of finishing works in the construction of residential buildings was demonstrated. Without simulating the effects of the individual technological models for finishing construction works in relation to two of the most important parameters of construction projects, namely time and cost, it would not be possible to obtain the resulting parameters for different combinations of DCSTs and WCSTs from the study presented. Therein lies the huge importance of the presented knowledge system for deciding on the benefits of DCSTs.

Material selection using knowledge-based expert system for racing bicycle forks

Materials today provide enormous prospects for innovation. However, progress is only possible if a mechanism for making a sensible choice from the materials exists. When choosing a material for a component, one should start with the full menu of materials as an option. When selecting a material for an engineering component, there is usually more than one option. However, the final choice will be a balance between the materials based on the benefits and drawbacks they provide. This paper focuses on material selection for racing bicycle forks utilizing knowledge-based expert systems based on design requirements. Knowledge-based expert systems are computer methods replicating human problem-solving through artificial intelligence to arrive at the best decisive action. A database of 67 materials with its own set of attributes was created. The material index and shape factor were evaluated for all the materials in the database based on the critical selection factors of mass and section shape. Material selection is determined by considering the material index, shape factor, and coupling various design requirements by framing simple IF-THEN rules using the python interface and Jupyter Notebook. According to this method, the final suitable materials for selecting racing bicycle forks are Aluminium alloys and Carbon Fiber Reinforced Plastics (CFRP). As the application demands lower weight by compromising on the cost, Carbon Fiber Reinforced Plastic (CFRP) is the most preferred choice for material selection of racing bicycle forks.

Evolutionary trends in the use of artificial intelligence in support of architectural design

The paper analyses the evolutionary tendencies in the use of artificial intelligence in building design, highlighting: a) the ground lost by knowledge-based expert systems and the diffusion of systems combined with heuristic and stochastic approaches; b) the spread of evolutionary algorithms in the field of optimisation; c) a climax of the influence of probabilistic approaches around 2010; d) the progressive dominance of deep learning since 2012. It is likely that the next step requires hybridisation of deep learning and symbolic artificial intelligence, and it is expected that the contribution of design domain experts in terms of knowledge formalisation will be a fundamental driver of it.

A new framework integrating reinforcement learning, a rule-based expert system, and decision tree analysis to improve building energy flexibility

This study presents a new framework that integrates machine learning and a domain knowledge-based expert system to improve building energy flexibility. In this framework, a rule-based expert system was used to maximize the self-consumption of solar photovoltaics (PV) power, while a reinforcement learning (RL) agent was constructed to efficiently optimize the grid power import for battery charging and facilitate decision-making for battery discharging in response to the time of use electricity prices. Meanwhile, a Classification and Regression Tree (CART) model was developed to quantitatively analyze the relationships between building energy flexibility and external variables of interest to enhance the explainability of the framework. This work integrates the advantages of safety and simpleness of the domain knowledge-based expert system and the exploration and optimization capability of RL into building energy management. The performance of the proposed framework was evaluated using the four-year data collected from a real net zero energy office building. The system cost reduction ratio, self-consumption ratio, and self-sufficiency ratio were used as the energy flexibility indicators. The results showed that the integration of the RL and the rule-based expert system was able to reduce the electricity cost and grid power consumption by 7.0% and 10.6% respectively, and increase the self-consumption of PV power by 9.2% as compared with the use of the rule-based expert system only. The CART analysis also showed that external conditions can significantly influence the level of building energy flexibility. For instance, the average daily cost reduction ratio was 0.89 out of 1.0 when the daily maximum solar irradiance was above 717.5 W/m2, while it decreased to 0.28 when the daily mean solar irradiance was below 62.4 W/m2. This strategy can be used to facilitate building demand-side management and improve the design and control of building energy systems for enhanced demand flexibility.

A Hybrid Multi-Criteria Decision-Making Framework for Ship-Equipment Suitability Evaluation Using Improved ISM, AHP, and Fuzzy TOPSIS Methods

The inherent complexity of large ships makes it challenging to evaluate ship designs systematically and scientifically. Knowledge-based expert systems can be reasonable solutions. However, this problem needs more rationality and better operability, especially in complicated ship-equipment suitability evaluation problems with numerous indicators and complex structures. This paper presents a hybrid multi-criteria decision-making (MCDM) framework to extend the ship-equipment suitability evaluation to group decision-making settings, where individual consistency and group consensus are thoroughly investigated to improve rationality and operability. As a result, an improved Interpretive Structural Modeling (ISM) method is developed to construct the evaluation index systems. Furthermore, based on an applicability analysis of the selected MCDM methods, an improved Analytical Hierarchy Process (AHP) method is proposed to distribute the index weights, and an applicable Fuzzy Technique for Order Preference by Similarity to Ideal Solution (Fuzzy TOPSIS) method is utilized to evaluate and select appropriate ship designs. Finally, a ship-equipment environmental suitability evaluation case is examined. The results indicate that the proposed framework improves the rationality and operability of the decision-making process and provides practical support to decision-makers for the systematic and scientific evaluation of ship designs. Therefore, it can also be applied to other ship design evaluation and selection problems.

On Selecting, Ranking, and Quantifying Features for Building a Liver CT Diagnosis Aiding Computational Intelligence Method

The liver is one of the most common locations for incidental findings during abdominal CT scans. There are multiple types of disease that can arise within the liver and many of them are nodular. The ultimate goal of our research is to develop an expert knowledge-based system using fuzzy signatures, to support decisions during diagnosis of the most frequent of these nodular lesions. Since the literature contains limited information about the graphical properties of CT images that must be taken into consideration and their relationship to one another, in this paper we focused on selecting and ranking the input parameters using expert knowledge and determining their importance. Six visual attributes of lesions (size, shape, density, homogeneity contour, and other features) were selected based on textbooks of radiology and expert opinion. The importance of these attributes was ranked by radiologist experts using questionnaires and a pairwise comparison technique. The most important feature was found to be the density of the lesion on the various CT phases, and the least important was the size, the order of the other attributes was other features, contour, homogeneity, and shape, with a Kendall concordance coefficient of 0.612. Weights for the attributes, to be used in the future fuzzy signatures, were also determined. As a last step, several statistical parameter-based quantities were generated to represent the above abstract attributes and evaluated by comparing them to expert opinions.

Forecasting development trends in the information technology industry using fuzzy logic

The IT industry occupies a significant place in the economy of the world. Trends in its development directly affect changes in various sectors of the economy. This paper considers the dynamics of IT industry under conditions of increased entropy of the functioning environment caused by crises, military conflicts, non-standard events. The mathematical basis of the study is an apparatus of fuzzy logic. The proposed technique for analyzing and forecasting the state and dynamics of the IT sector makes it possible to take into account the influences of a set of factors of different nature and direction of action, which contributes to obtaining a reasonable assessment under conditions of inaccurate information. The software platform for implementing the methodology is the authentically designed fuzzy expert system (ES) FuzzyKIDE. The conceptual foundations of the platform structure have been defined. A modification of the fuzzy inference mechanism has been proposed, which, unlike existing samples, makes it possible to eliminate saving intermediate results and reduces the load on the database. The composition and structure of the knowledge base (KB) for ES have been proposed. Fuzzy rules are based on predetermined relationships between key factors of influence. The technology of ES operation is represented using simulated scenarios with obtaining predictive results. The analysis of the final data of expert consultations proves the ES operability, providing for the possibility of KB significant expansion in the process of industrial operation. The use of ES is aimed at forming a holistic view of possible directions of IT sector development. Maintaining the actual state of ES KB is a condition for early warning of the emergent negative/crisis phenomena. The FuzzyKIDE expert consulting system is proposed as a tool to support management decision-making based on the analysis and forecasting of the state and dynamics of IT sector under conditions of high uncertainty

Development of a Knowledge-Based Expert System for Diagnosing Post-Harvest Diseases of Apple

Post-harvest diseases are one of the main causes of economical losses in the apple fruit production sector. Therefore, this paper presents an application of a knowledge-based expert system to diagnose post-harvest diseases of apple. Specifically, we detail the process of domain knowledge elicitation for constructing a Bayesian network reasoning system. We describe the developed expert system, dubbed BN-DSSApple, and the diagnostic mechanism given the evidence provided by the user, as well as a likelihood evidence method, learned from the estimated consensus of users’ and expert’s interactions, to effectively transfer the performance of the model to different cohorts of users. Finally, we detail a novel technique for explaining the provided diagnosis, thus increasing the trust in the system. We evaluate BN-DSSApple with three different types of user studies, involving real diseased apples, where the ground truth of the target instances was established by microbiological and DNA analysis. The experiments demonstrate the performance differences in the knowledge-based reasoning mechanism due to heterogeneous users interacting with the system under various conditions and the capability of the likelihood-based method to improve the diagnostic performance in different environments.

Improving the fuzzy expert system for diagnosing depressive disorders

This paper presents an improving knowledge base and inference engine of a medical expert system for diagnosing depressive disorders. This medical expert system calls PORUL.DEP. PORUL.DEP’s knowledge base includes more than 850 positive rules. PORUL.DEP has been tested on more than 260 medical records of depressed patients. PORUL.DEP gives a correct diagnosis of more than 95% with light depressive disorder and without depressive disorder, but the remaining depressive disorders are not accurate. Average percent of more than 24 %. A new expert system, called STRESSDIAG, was developed on combining positive rules (for confirmation of conclusion) and negative rules (for exclusion of conclusion) for diagnosing depressive disorders. STRESSDIAG’s knowledge base consists of more than 850 positive rules of PORUL.DEP and more than 120 negative rules. Abelian group operation of Mycin is used to improve the inference engine based on fuzzy relations. STRESSDIAG gives the correct diagnosis of more than 76% with 4 depressive disorders types and without depressive disorders. Average percent of more than 82 %, up nearly 60% compared to PORUL.DEP.

Application of Low Back Pain Myogenic Therapy Based on Multimedia

Low back pain restricts activity and causes work absenteeism. Cases of low back pain are common worldwide. This paper presents the design of multimedia-based low back pain myogenic therapy aids. Data collection involves observation and interviews with medical rehabilitation specialists and physiotherapists. The collected data is represented using a production ruler in the form of if - then. Rule-based reasoning can be used as an expert system knowledge base in cases of myogenic low back pain. Forward chaining can be used as an inference engine for similar cases because the reasoning starts from the facts section before reaching the hypothesis. Design of this assistive device model is expected to provide information regarding the choice of therapy for low back pain myogenic by patients, independently at home or with the help of close family. Application design is multimedia-based to make it easier for users to look at examples visually. The expert system application is well accepted by users. Ten physiotherapists and one doctor consider the application performance good because it attains an acceptable value of 0.80 or 80%. The physiotherapists suggest that this assistive device model will likely increase the intensity of therapy because it can be carried out by the patient's family independently.

Expert system and entropy‐ordered weighted average method in cold supply chain risk evaluation

AbstractIf not well identified and controlled, risks in systematically engineered cold supply chains can lead directly to food safety incidents. In current approaches to cold supply chain risk evaluation, there is a lack of systematic classification and quantitative analysis of the influences of risk factors in the chain. To accurately evaluate unknown risks that can exert a fluctuating influence and result in great losses, this study builds a knowledge base of expert systems based on expertise and extensive experience and modifies the expert weights in conjunction with entropy weights to reduce subjective error. An ordered weighted average (OWA) operator is used to evaluate risk in a cold supply chain effectively. First, in combination with a case study of a typical fresh food e‐commerce enterprise, a typical fresh food e‐commerce enterprise, this paper identifies the risks in a food refrigeration supply chain. Second, relying on an expert group with professional knowledge and rich experience, an expert system knowledge base is constructed, risks are assigned, and the expert weight is modified in combination with the entropy weight method. Finally, based on the OWA operator, the modified risk assignment is effectively evaluated, and the risk value is obtained and sorted. Specific risk control measures are put forward according to the results of the calculation. The results show that an evaluation method combining an expert system knowledge base and the entropy‐OWA method can effectively depict and process the evaluation information needed for risk rankings and solve the problems of supply chain risks more rapidly and effectively.

Intelligent fault diagnosis expert system for multi-parameter monitor based on fault tree

Aiming at the dilemma of expensive and difficult maintenance, lack of technical data and insufficient maintenance force for modern medical equipment, an intelligent fault diagnosis expert system of multi-parameter monitor based on fault tree was proposed in this study. Firstly, the fault tree of multi-parameter monitor was established and analyzed qualitatively and quantitatively, then based on the analysis results of fault tree, the expert system knowledge base and inference engine were constructed and the overall framework of the system was determined, finally the intelligent fault diagnosis expert system for multi-parameter monitor was developed by using the page hypertext preprocessor (PHP) language, with an accuracy rate of 80% in fault diagnosis. The results showed that technology fusion on the basis of fault tree and expert system can effectively realize intelligent fault diagnosis of multi-parameter monitors and provide troubleshooting suggestions, which can not only provide experience accumulation for fault diagnosis of multi-parameter monitors, but also provide a new idea and technical support for fault diagnosis of medical equipment.

On Z-Intuitionistic Fuzzy Fractional Valuations for Medical Diagnosis: An Intuitionistic Fuzzy Knowledge-Based Expert System

In an uncertain situation, data may present in continuous form or discrete form. We have various techniques to deal with continuous data in a realistic situation. However, when data are in discrete form, the existing techniques are inadequate to deal with these situations, and these techniques cannot provide the proper modulation for adequate analysis of the system. In order to provide the proper acceleration to discrete data, we need an appropriate modulation technique that can help us to handle unconditional boundedness on the technique and will operate like the techniques used for continuous data with fractional variables. In this work, we developed an intuitionistic fuzzy fractional knowledge-based expert system using unconditional and qualified fuzzy propositions based on the Z-intuitionistic fuzzy fractional valuation probability density function. In this proposed method, the discrete fractional variables will be converted into intuitionistic fuzzy fractional numbers and then be used in our algorithm. The proposed Z-intuitionistic fuzzy fractional valuation knowledge-based system can easily be applied in the medical field for the diagnosis of diseases in a vague environment due to the ordered-pair characteristics of the Z-intuitionistic fuzzy fractional valuation. In this study, we collected data of dengue patients, which included seven clinical findings: Temperature, sugar, Pulse Rate (PR), age, cough, and Blood Pressure (BP). A numerical example was also carried out to elaborate on the present technique. In addition, a comparative study is discussed in this work. We also provide the managerial implications of the data, with the limitations of the proposed technique presented at the end of this work.