Production Rule System Research Articles

Procedure for describing traffic situation scene development

PurposeThis study aims to comprehensively address the challenge of delineating traffic scenarios in video footage captured by an embedded camera within an autonomous vehicle.Design/methodology/approachThis methodology involves systematically elucidating the traffic context by leveraging data from the object recognition subsystem embedded in vehicular road infrastructure. A knowledge base containing production rules and logical inference mechanism was developed. These components enable real-time procedures for describing traffic situations.FindingsThe production rule system focuses on semantically modeling entities that are categorized as traffic lights and road signs. The effectiveness of the methodology was tested experimentally using diverse image datasets representing various meteorological conditions. A thorough analysis of the results was conducted, which opens avenues for future research.Originality/valueOriginality lies in the potential integration of the developed methodology into an autonomous vehicle’s control system, working alongside other procedures that analyze the current situation. These applications extend to driver assistance systems, harmonized with augmented reality technology, and enhance human decision-making processes.

Multidimensional Multi-Connected Fuzzy Interval-Logic Controller

The key features and the principle of operation of a multidimensional fuzzy interval-logic controller with interconnected adjustable parameters developed by the authors are considered. The scheme of interpretation of continuous physical quantities by an equivalent set of terms and the basic version of the block diagram of the regulator are presented. The main elements of the logical output block are described, including the block of production rules, which includes a predefined database of values of control actions on control objects in the form of ordinal numbers of terms of output continuous quantities. The advantages and features of setting up the mutual connections between the input and output continuous values of the regulator are considered, which is expressed in determining the functional dependencies between them. The set of parameters possessed by the terms of input continuous quantities in relation to specific output continuous quantities of the regulator is described. The methods of defuzzification of the values of output continuous quantities within the boundaries of their terms are shown. The possibility of combining input and output continuous quantities into groups when setting up mutual connections between them is described. The mechanism of determining groups of interrelated continuous quantities is illustrated, the total number of which is determined by forming a matrix of relationships, according to the author’s scheme. The algorithm of sequential processing of the contents of the cells of the matrix of relationships, consisting of three steps, is considered. Expressions are given for calculating the basic parameters of a multidimensional fuzzy interval-logic controller with interrelated adjustable parameters. The results of a computational experiment to reduce the system of production rules of the regulator in determining the relationships between input and output continuous quantities are presented.

Fuzzy rule-based classification of complex biogas energy projects

The work is devoted to the problems analyzing the effectiveness of projects in the field of biogas energy. The purpose of the work is to build an intellectual toolkit for classifying innovative bioenergy projects. To form a variety of classification characteristics, it is proposed to use the Ishikawa cause-and-effect diagram, which makes it possible to systematize the factors influencing the features of the project. The specifics of biogas technologies, associated with the possibility of generating not only electrical but thermal energy, as well as waste disposal and the production of organic fertilizers, are taken into account by introducing an additional group of factors reflecting the need for these types of products. Expert technologies for assessing factors led to the use of the methodology of fuzzy analysis. The constructed classification procedure is based on a system of fuzzy production rules that reflect the cause-and-effect relationships of the subject area.The developed tools make it possible to reduce the labor intensity of comparative analysis of the effectiveness of the implementation of innovative bioenergy projects by identifying the class of compared projects.

Study of ACS of rotor rotation frequency and gas temperature with accurate regulators in the control loop of a gas turbine engine

This article discusses the automatic control system for parameters (rotor speed and gas temperature) of a gas turbine engine based on clear logic controllers. It is proposed to use clear logical controllers, consisting of a comparing device, a fuzzifier, an inference block with a system of production rules and with given membership functions of clear terms of variables, and a defuzzifier. Precise logical controllers, using the membership functions of precise terms, in the control loops of the object’s influence stably maintain the overshoot time.

Fuzzy linguistic forecasting of the results of the implementation of regional socio-economic projects

The article is devoted to the problem of improving the intellectual digital support for managing the implementation of regional socio-economic projects, which are an effective mechanism for the development of regions. Given the high level of uncertainty in the description of the subject area, it is proposed to use expert technologies to assess the degree of achievement of the intermediate and target indicators of the project. L. Zadeh's linguistic modeling apparatus was used as the basis for intellectual tools for representing and processing expert judgments. A linguistic indicative-temporal-territorial model of the project has been built in the form of a set of linguistic variables and a system of fuzzy production rules linking these variables. At the same time, temporal and territorial linguistic variables reflect the time and place of measurement of project indicators, the incomplete correspondence of which determines the degree of reliability of the measured values of indicators. The use of the constructed system of indicative-temporal-territorial fuzzy production rules makes it possible to link the intermediate values of the indicators with the target values of the project indicators and thereby predict the possible outcomes of its implementation. For this, a fuzzy logic inference procedure based on the use of the Mamdani algorithm has been developed. Preliminary results of using a research prototype of an intelligent expert system for analyzing the intermediate results of the project stages and predicting its results may indicate the effectiveness of the proposed approach.

The task of technological adjustment of an axial-rotor type grain combine

One of the promising approaches to improve the efficiency and effectiveness of the harvesting process of grain crops using a combine method is the use of an intelligent information system in the form of a decision support system. The expansion of the use of high-performance rotary-type combines in production conditions puts the task of optimal technological adjustment of the working bodies and the entire combine as a whole into the category of topical ones. When performing harvesting work with an axial-rotary threshing and separating device (ARTSD), as a result of continuously changing external harvesting factors, deviations in the values of work quality indicators from acceptable values are possible. For their timely elimination, it is important to know the relationships between the groups of signs: “environmental factors - parameters of the working bodies - indicators of the quality of work.” The lack of knowledge leads to non-optimal decisions on the choice of specific values of the controlled parameters and, as a result, to the loss of grain and other resources. To select the optimal strategy for managing the technological process of harvesting using a rotary harvester, we propose a new approach based on the use of an intelligent information system (expert system), which corresponds to the concept of intellectualization of a new type of machine. The article presents the results of research into the process of technological adjustment of a rotary harvester, as well as an analysis of the empirical knowledge of experts with extensive production experience in operating combines of this type. The concepts of parameters, causes and methods for eliminating violations of the technological process are introduced. As a result of expert analysis, decision trees were formed for the first time, on the basis of which the rules of the knowledge base are formulated. To create a knowledge base, it is proposed to use a production model of knowledge. An example of constructing a decision tree when searching for the cause of the appearance of one of the external signs of a violation of the quality of the work of a rotary harvester is given. A fragment of the system of production rules for solving the problem of adjusting the values of control parameters is presented.

Models and Methods of Information Support in the Management of the Maintenance and Repair of Equipment Based on Artificial Intelligence Technologies

Intelligent Information Support for Decision Making in Maintenance and Equipment Repair Management is discussed in this article. The authors propose a solution approach that includes Bayes method, knowledge engineering technologies and fuzzy logic to formalization of revealed and expert knowledge (production rules system) for diagnostics, (fuzzy production system) for classify equipment and components, forecasting and optimization methods for planning the components procurement. Practical realization is performed using analytical MATLAB platform and EXSYS Corvid and software developed in USATU. The proposed approach by authors of this article can be implemented as the local application for information system, or as part of the creation of the digital twin of the production system. The results of experimental studies have shown a significant gain in time in decision-making in the diagnostic task, as well as in the level of timely replacement of components by 12 percent due to the introduction of demand coefficients in planning purchases.

Intellectual assessment of staff sufficiency for innovative development of the sustainable regional agro-industrial complex

The paper is devoted to the problems of assessment of staff sufficiency for regional economy agroindustrial sector’s innovative development. The proposed approach is based on the application of models and methods of expert assessment and digital intelligent technologies. The share of employees who are ready (professionally) to use innovations from the total number of employees was chosen as the main evaluation characteristic. At the same time, the indicators of staff sufficiency of subsystems and the sustainable regional agro-industrial complex as a whole are formed on the basis of statistical data provided by enterprises, expert judgments and knowledge about the subject area represented by a system of fuzzy production rules. The developed hierarchy of indicators reflects the structure of the regional agro-industrial complex (subcomplexes, reproduction and functional components, categories of enterprises). The transition to indicators of a higher tier of the hierarchy is realized based on the indicators of the previous tier, using weighted summation and/or fuzzy logical inference, which allows taking into account not only the relative importance of individual subsystems (components), but also the high level of uncertainty characteristic of the agro-industrial economy. At the same time, evaluation indicators of various tiers of the hierarchy can be used to make managerial decisions. Preliminary results of the application of the developed hierarchy of evaluation indicators of staffing of the sustainable regional agro-industrial complex and the proposed procedure for determining the values of these indicators may indicate the effectiveness of the proposed approach.

Synthesis of a fuzzy regulator for a vibration protective platform

The problem solution of a fuzzy logic controller (FLC) synthesis for a combined vibration isolation system with an electromagnetic motor is considered. An analysis of the passive system characteristics is carried out and its key disadvantages, the presence of a pronounced resonance peak and the ineffectiveness of vibration isolation in the low-frequency range, are identified on the basis of a mathematical model of a vibration-protective platform on elastic suspensions. The structure of the FLC is proposed, a system of production rules is drawn up, a parametric synthesis of the FLC is carried out by finding the optimal centers location of the accessory functions terms for input and output quantities. Using mathematical modeling in the MATLAB Simulink software package, the advantages of a synthesized combined system over a passive installation are demonstrated. Keywords vibration, active vibration protection, fuzzy control, mathematical model, optimal control, electromagnetic system, mathematical modeling

Sup_Ont

A domain-independent conceptual model that aims to be highly reusable across specific domain applications is provided by upper-level ontologies which usually describe abstract concepts. In this paper, the authors proposed Sup_Ont, a fundamental upper ontology. In this ontology, the structure of the universe shows the concept of reality that is defined to have an existence which is known as truth. The devised super ontology and hence the domain ontologies can be reused across applications because of the generalized representation scheme used that is an EHCPR. An extended hierarchical censored production rules (EHCPRs) system is a knowledge representation system for reasoning with real-life problems and a step towards a generalized representation system. An EHCPR is a unit of knowledge resulting in a knowledge base that shows modularity and hierarchy. Extended hierarchical censored production rules (EHCPRs) have been used to represent the knowledge in intelligent systems.

DEVELOPMENT OF A MATHEMATICAL MODEL AND SOFTWARE COMPLEX FOR OPTIMIZING EFFECTIVE EMPLOYMENT MANAGEMENT OF UNIVERSITY GRADUATES

The paper proposes a model for managing the distribution of university graduates from the point of view of meeting the demand of the population for educational services and providing the regional economy with specialists with higher education, formalizing the task of employing a university graduate in a specialty, defining the nature of the functional dependence of the university's throughput on the student's professional self-determination, using real data to obtain a system of production rules, which makes it possible to formulate recommendations for adjusting the professional self-determination of prospective employment of future graduates.

The available methods of computer modeling of biofilms and their development trends

The object of this research is the available means of computer modeling of bacterial communities-biofilms. Such communities include the majority (95-99%) of bacteria and are ubiquitous. Biofilms are much more resistant than single bacteria to antibiotics and other antibacterial means due to weak permeability of intercellular environment and moderation of metabolism of some specimen of the community. Examination of influence techniques on biofilms is an important problem of biology; its solution requires various computer modeling tools that allow achieving significant scientific results. The subject of this research is the mathematical models used in modern techniques of biofilm modeling, and as well as the software for their implementation. The conclusion is made that the available methods of biofilm modeling are capable of successful reproduction of multiple behavioral aspects of these bacteria communities, including growth, destruction, and self-regulation; however, certain relevant problems are yet to be resolved. This is associated with the fact that the development of modern software for two-dimensional and three-dimensional agent modeling of biofilms – BSim, iDynoMiCS, CellModeller, require competent programmers for describing the interactions between simulated objects. Most promising direction in further development of this software implies a more active usage of tools for describing behavior and interaction of agents applied in the sphere of artificial intelligence, for example, fin-state automaton or production rules systems, with mandatory preservation of biological content of the models.

Comprehensive analysis of rule formalisms to represent clinical guidelines: Selection criteria and case study on antibiotic clinical guidelines.

The over-use of antibiotics in clinical domains is causing an alarming increase in bacterial resistance, thus endangering their effectiveness as regards the treatment of highly recurring severe infectious diseases. Whilst Clinical Guidelines (CGs) focus on the correct prescription of antibiotics in a narrative form, Clinical Decision Support Systems (CDSS) operationalize the knowledge contained in CGs in the form of rules at the point of care. Despite the efforts made to computerize CGs, there is still a gap between CGs and the myriad of rule technologies (based on different logic formalisms) that are available to implement CDSSs in real clinical settings. To helpCDSS designers to determine the most suitable rule-based technology (medical-oriented rules, production rules and semantic web rules) with which to model knowledge from CGs for the prescription of antibiotics. We propose a framework of criteria for this purpose that is extensible to more generic CGs. Our proposal is based on the identification of core technical requirements extracted from both literature and the analysis of CGs for antibiotics, establishing three dimensions for analysis: language expressivity, interoperability and industrial aspects. We present a case study regarding the John Hopkins Hospital (JHH) Antibiotic Guidelines for Urinary Tract Infection (UTI), a highly recurring hospital acquired infection. We have adopted our framework of criteria in order to analyse and implement these CGs using various rule technologies: HL7 Arden Syntax, general-purpose Production Rules System (Drools), HL7 standard Rule Interchange Format (RIF), Semantic Web Rule Language (SWRL) and SParql Inference Notation (SPIN) rule extensions (implementing our own ontology for UTI). We have identified the main criteria required to attain a maintainable and cost-affordable computable knowledge representation for CGs. We have represented the JHH UTI CGs knowledge in a total of 12 Arden Syntax MLMs, 81 Drools rules and 154 ontology classes, properties and individuals. Our experiments confirm the relevance of the proposed set of criteria and show the level of compliance of the different rule technologies with the JHH UTI CGs knowledge representation. The proposed framework of criteria may help clinical institutions to select the most suitable rule technology for the representation of CGs in general, and for the antibiotic prescription domain in particular, depicting the main aspects that lead to Computer Interpretable Guidelines (CIGs), such as Logic expressivity (Open/Closed World Assumption, Negation-As-Failure), Temporal Reasoning and Interoperability with existing HIS and clinical workflow. Future work will focus on providing clinicians with suggestions regarding new potential steps for CGs, considering process mining approaches and CGs Process Workflows, the use of HL7 FHIR for HIS interoperability and the representation of Knowledge-as- a-Service (KaaS).

Разработка системы иерархических продукционных правил для диагностирования электротехнического оборудования

The process of electrical equipment diagnosing at the operational stage is a multifactor process, complicated for mathematical description and modeling, since the factors affecting the operation and technical condition of equipment can be represented not only by quantitative variables, but also by linguistic variables. In order to improve the operating performance and the level of equipment fault tolerance, it is necessary to develop diagnostic methods and models using modern information technologies that take into account the main factors that affect the technical condition of the equipment. In this paper, we solve the problem of developing a system of hierarchical production rules for electrical equipment diagnosing including measuring and expert information. The novelty is that the rules are tied to developed heterogeneous cognitive models that cover all the laws of obtaining, transmitting, processing heterogeneous data and ranking rules taking into account the path length in the models between the “condition” and “conclusion” vertices, reflecting the generalized knowledge of the duty staff. This makes it possible to reduce the knowledge base capacity containing production rules, to make the search process more efficient and to take scientifically based diagnostic decisions regarding equipment health.

Fuzzy output system on the basis of the modified fuzzy Petri nets

The development of information technologies requires improvement of simulation methods and mathematical apparatus. The mathematical apparatus of Petri nets is used for simulation of parallel asynchronous systems and has a broad scope. The modified fuzzy Petri nets expand the modeling capabilities of Petri nets by combining the properties of different extensions. Modified extension can serve for construction of models with a complex structure and logic of operation with the use of fuzzy logic apparatus for control on the basis of the system of production rules.

The development of a decision support information-modeling system for safety in the chemical industry

The analysis of the urgency of developing a decision and support information-modeling system for safety in the chemical industry is carried out. The article also covers the main elements of this information-modeling system. Key normative documents backing up the knowledge base of such an information-modeling system are listed below. The algorithm of the safety decision supporting information-modeling system is proposed. A database model of the safety decision supporting information-modeling system is elaborated below. A production rule system is set forth to manage issuing recommendations on the robust decision support information-modeling system in the chemical industry based on a methodological document. An implementation plan is laid out for the robust decision support information-modeling system in chemical industry. It is a ready-made software package based on two-level (client–server) architecture of information systems. This article also contains recommendations based on a test case of a tank equipment total destruction. Results of the computational experiments’ simulation in the TOXI+Risk software corresponding to the test selected values are available.

Artificial neural network technologies as a tool to histological preparation analysis

Food fraud has become one of the great internal and external threats nowadays. For effective and objective detection of adulterated products, real-time control systems are used.Microstructural analysis is one of these methods. It allows rapid quality and composition assessment of food’s raw materials and the finished products. Human skills and expertise/involvement in interpreting the resultsof microstructural analysis is still absolutely necessary, despite the possibility this is subjective. Modern hardware/software systems for histological analysis with neural network technologies will exclude the subjectivity of that result interpretation. For convolutional neural network operating, the “learning with the teacher” model is used. With this training method, a set of data is prepared, whichacts as a series of observations, and for which the values of the input and output variables are indicated, such as: histological analysis data > conclusion about the sample composition > adulteration definition. The network learns to establish connections between them. This paper presents the classification parameters for vegetable food component identification as a part of meat raw materials and finished products. A unified database structure has been developedfor structuring and summarizing the main microstructural characteristics of histological sections for various types of meat raw materials. The production-rule systems of “If… then …else” are given, and vegetable protein components were chosen as an example. Based on these rules, training of convolutional neural network occurs.

An Operational Semantics for the Cognitive Architecture ACT-R and Its Translation to Constraint Handling Rules

Computational psychology has the aim to explain human cognition by computational models of cognitive processes. The cognitive architecture Adaptive Control of Thought--Rational (ACT-R) is popular to develop such models. Although ACT-R has a well-defined psychological theory and has been used to explain many cognitive processes, there are two problems that make it hard to reason formally about its cognitive models: First, ACT-R lacks a computational formalization of its underlying production rule system, and, second, there are many different implementations and extensions of ACT-R with many technical artifacts complicating formal reasoning even more. This article describes a formal operational semantics—the very abstract semantics —that abstracts from as many technical details as possible, keeping it open to extensions and different implementations of the ACT-R theory. In a second step, this semantics is refined to define some of its abstract features that are found in many implementations of ACT-R—called the abstract semantics . It concentrates on the procedural core of ACT-R and is suitable for analysis of the general transition system, since it still abstracts from details like timing, the sub-symbolic layer of ACT-R or conflict resolution. Furthermore, a translation of ACT-R models to the declarative programming language Constraint Handling Rules (CHR) is defined. This makes the abstract semantics an executable specification of ACT-R. CHR has been used successfully to embed other rule-based formalisms like graph transformation systems or functional programming. There are many theoretical results and practical tools that support formal reasoning about and analysis of CHR programs. The translation of ACT-R models to CHR is proven sound and complete w.r.t. the abstract operational semantics of ACT-R. This paves the way to analysis of ACT-R models through CHR analysis results and tools. Therefore, to the best of our knowledge, our abstract semantics is the first abstract formulation of ACT-R suitable for both analysis and execution.

Statement of the problem optimal control the hardness of the steel produced based on the model of Takagi-Sugeno-Kang

В данном исследовании обсуждается проблема математического моделирования сложных технологических систем в условиях неопределенности для получения наиболее оптимальных параметров при управлении производственным процессом в прикладной области – металлургии. В предлагаемом подходе рассмотрена одна из важнейших задач управления технологическим процессом выплавки стали: обеспечение заданной твердости (прокаливаемости) стали, распределенной по глубине выплавляемого изделия. Для минимизации неизбежных ошибок, связанных с экспертным выбором химического состава, повышения эффективности управления и качества выплавляемой стали, предложено применение системы нечетких продукционных правил Токаги-Суджено-Канга (модель ТСК), на основе моделирования зависимости «состав-твердость». Применение данной модели также позволит оптимизировать выбор химического состава стали в условиях стохастичности параметров регрессионных моделей. Кроме того, при исследовании процесса производства стали возникает необходимость решение обратной задачи – определение химического состава выплавляемой стали по заданному значению твердости. Предложенная модель ТСК на основе нечетких продукционных правил для прогнозирования и управления выплавкой стали представлена в матричной форме, поэтому одним из возможных путей решения задачи управления является решение соответствующего матричного уравнения. При этом на основе экспериментальных данных выявлено существенное смещение оценок значений химических элементов. В связи с этим управление необходимо строить на основе оптимизационного подхода. Предложенная постановка оптимизационной задачи позволит разработать алгоритм решения задачи оптимального управления твердостью на основе модели ТСК, отличающийся возможностью автоматически определять необходимый химический состав стали по заданному распределению ее твердости. Кроме того, разработанная модель ТСК с применением задачи оптимального управления позволит исключить ошибки при определении модели расчета, а также определять твердость стали для химического состава не соответствующего в полной мере определенной совокупности допустимых интервалов изменения массовых долей химических элементов. This study discusses the problem of mathematical modeling of complex technological systems under uncertainty to obtain the most optimal parameters in the management of the production process in the applied field – metallurgy. In the offered approach one of the most important tasks of management of technological process of steel smelting is considered: maintenance of the set hardness (calcification) of the steel distributed on depth of the smelted product. To minimize the inevitable errors associated with the expert choice of chemical composition, improve the management efficiency and the quality of the produced steel, it is proposed to apply the system of fuzzy production rules Takagi-Sugeno-Kanga (model TSK), based on the modeling of the dependence "composition-hardness". Application of this model will also allow to optimize the choice of the chemical composition of the steel in the conditions of stochasticity of the parameters of the regression models. In addition, in the study of the steel production process there is a need to solve the inverse problem – the determination of the chemical composition of the steel produced at a given hardness value. The proposed model of TSK based on fuzzy production rules for steel smelting prediction and control is presented in matrix form, so one of the possible ways to solve the control problem is to solve the corresponding matrix equation. At the same time, on the basis of experimental data, a significant shift in the estimates of the values of chemical elements was revealed. Therefore, governance must be based on an optimization approach. The proposed formulation of the optimization problem will develop an algorithm for solving the problem of optimal hardness control on the basis of the TSK model, characterized by the ability to automatically determine the required chemical composition of steel by a given distribution of its hardness. In addition, the developed model TSK using the optimal control problem will eliminate errors in determining the calculation model, as well as to determine the hardness of steel for the chemical composition does not fully correspond to a certain set of allowable intervals of changing the mass fractions of chemical elements.

A hybrid model based on modular neural networks and fuzzy systems for classification of blood pressure and hypertension risk diagnosis

In this paper, a hybrid model using modular neural networks and fuzzy logic was designed to provide the hypertension risk diagnosis of a person. This model considers age, risk factors and behavior of the blood pressure in a period of 24 h, using as a basis the Framingham Heart Study.Records of blood pressure are collected with the ambulatory blood pressure monitoring (ABPM), a device which takes readings for a period of time of 24 h. A modular neural network was designed, with three modules, of which the first and second modules correspond to the systolic and diastolic pressures and the last one to the heart rate. Each module is trained with the data obtained by the ABPM of different patients, this in order that the neural network learns the different behaviors that the blood pressure may have. Also, different architectures and learning methods are considered to obtain the best possible architecture. In addition, two fuzzy inference systems (FISs) for classification purpose are proposed, the first one for the heart rate level and the second one for the night profile of the patient. These were tested with different types of membership functions and then selecting the FIS that obtained the best results. Furthermore, a third FIS as a blood pressure classifier is also used.The different proposed methodologies were tested, in the case of the modular neural network to find the architecture that produces better results and in the fuzzy inference systems to find which membership functions were the ideal ones for the case study, in this way obtaining overall good results. For the case of the modular neural network, the learning accuracy in the first module is 98%, in the second module is 97.62% and the third module is 97.83% respectively. For the night profile, the fuzzy system is compared to a traditional system of production rules, and it is noted that the first one gives all correct outputs and the second one just gives 53% of the outputs, this is due to the uncertainty handling that fuzzy systems can provide, which the traditional system cannot because its rules are very strict.Hybrid intelligent systems for the solution of this kind of complex problems have excellent performance, due to the good learning in each module of the neural network and the classification uncertainty that is well managed by the fuzzy systems, obtaining with this a hybrid combination for achieving good results.