Rule-based Production Research Articles

Rule-Based Natural Language Processing in Volcanic Ash Data Searching System

Indonesia is a country with a unique geography. The confluence of three tectonic plates located in the country results in frequent natural disasters, from earthquakes to volcanic activity. BMKG is a monitoring agency tasked with providing information related to these natural disasters. However, one type of natural disaster data, the SIGMET data (Significant Meteorological Information) used to provide information on volcanic ash, has a complicated format that is difficult for ordinary people to understand. Therefore, this research seeks to make finding information related to volcanic ash and volcanic eruptions in Indonesia easier in terms of access and comprehension. In this research, an application design will be carried out that can search SIGMET data by implementing natural language processing with a production rule base. The research results have an accuracy rate of 84% using 25 test sample sentences that combine sentences and words contained in the important words section.

Intelligent Decision-Making Approach for Contingency Return Trajectory Based on Production Rule Base and Deep Learning

Intelligent Decision-Making Approach for Contingency Return Trajectory Based on Production Rule Base and Deep Learning

Development of an Expert System for Determining the Status of a Trained Intelligent System Based on the Algorithm of Fuzzy Output Mamdani

Currently, e-learning systems are widely used in the higher education system, leading among which are intelligent learning systems (IOS). A distinctive feature of using such systems is their ability to adapt the educational process to the individual characteristics of students. The article describes the development of an intellectual system that implements the selection of appropriate theoretical material for each student based on an analysis of his status ("expert," "professional," "master," "novice," "trainee"). The status of the trainee is a fuzzy characteristic, reflecting the degree of possession of the course material and consisting of two components: the level of assimilation of the discipline and the formation of the student's personal qualities. As a tool for determining status, it is proposed to use a fuzzy expert system, the core of which is the production rule base. When forming the database of fuzzy products, a description of each linguistic variable specified on the basis of the values of the student's reference model was used. This model includes dominant indicators for each quality, characterizing possible student statuses. During operation of the software, the results of evaluation of trainees "qualities are read from the database and compared with the rules of the expert system. The Mamdani method was used as the fuzzy inference algorithm. As a result, the student is offered a theoretical material of the discipline adapted to his current status. In the course of working with the system, students will be able to study the material of the discipline, building their own learning trajectory. The introduction of the developed IOS, which implements adaptive individual learning paths for each student, will significantly increase the efficiency and quality of training of specialists [1].

METHOD OF IDENTIFICATION OF OBJECT STATES ACCORDING TO THE RESULTS OF FUZZY MEASUREMENTS OF CONTROLLED PARAMETERS

The subject of consideration is the task of identifying the states of an object based on the results of fuzzy measurements of a set of controlled parameters. The fuzziness of the initial data of the task further complicates it due to the resulting inequality of the controlled parameters. The aim of the study is to develop a method of identifying the states of a fuzzy object using a fuzzy mechanism of logical output taking into account possible differences in the level of information content of its controlled parameters. The method of obtaining the desired result is based on the modification of the known mathematical apparatus for building an expert system of artificial intelligence by solving two subtasks. The first is the development of a method for assessing the informativity of controlled parameters. The second is the development of a method for constructing a mechanism for logical inference of the relative state of an object based on the results of measuring controlled parameters, which provides identification. In the first problem, a method is proposed for estimating the informativity of parameters, free from the known disadvantages of the traditional Kulbak informativity measure. In implementing the method, it is assumed that the range of possible values for each parameter is divided into subbands in accordance with possible states of the object. For each of these states, the function of belonging to the fuzzy values of the corresponding parameter is defined. At the same time, the correct problem of estimating the informativity of a parameter is solved for cases when this parameter is measured accurately or determined fuzzily by its belonging function. The fundamental difference between the proposed logical output mechanism and the traditional one is the refusal to use the production rule base, which ensures the practical independence of the computational procedure from the dimension of the task. To solve the main problem of identifying states, a non-productive approach is proposed, the computational complexity of which practically does not depend on the dimension of the problem (the product of the number of possible states Results.per the number of controlled parameters). The logic output mechanism generates a probability distribution of the system states. In this case, a set of functions of belonging of each parameter to the range of its possible values for each of the states of the object is used, as well as a set of functions of belonging to fuzzy measurement results of each parameter. Conclusions. Thus, a method of identifying the state of fuzzy objects with a fuzzy non-productive output mechanism is proposed, the complexity of which does not depend on the dimension of the task.

ВЕРИФИКАЦИЯ РАЗРАБАТЫВАЕМОЙ ИНФОРМАЦИОННОЙ ИНТЕЛЛЕКТУАЛЬНОЙ СИСТЕМЫ ОРГАНИЗАЦИИ И УПРАВЛЕНИЯ МОРСКИМИ ГРУЗОПЕРЕВОЗКАМИ В АРКТИЧЕСКИХ УСЛОВИЯХ

The paper highlights the issue of rapidly growing demand for sea cargo transportation in in the Arctic zone due to the development of the Russia Far East (the Northern Sea Route). The analysis of existing software and information resources in the field of sea cargo transportation has confirmed the need to create a transport and logistics system capable to optimize logistics operations in the Arctic zone of Russia and the subarctic zone of the Russian Far East. A visual version of fuzzy inference, the Mamdani fuzzy logic type, created using Matlab math package and GUIDE interactive tool is presented. The Mamdani fuzzy inference model and the fuzzy production rule base have been implemented using Fuzzy Logic Toolbox in Matlab math package. The necessity to customize the Mamdani fuzzy inference model based on the field data from navigators' reports has been explained. The analysis of ice-class vessels navigators' reports has been carried out, on the basis of which a training sample from the field data has been generated. Checking the adequacy of the Mamdani models based on data obtained using the database of navigators' reports has confirmed the possibility to use these models in any arctic and subarctic region of Russia. A multiple regression analysis has been conducted, as a result of which a predictive model has been built. The analysis of the predictive model has shown that the results of the Mamdani model are more accurate compared to the results of the multiple regression analysis. The customized Mamdani model is the main component of an intelligent system for calculating the efficiency of the organization of sea cargo transportation in the arctic conditions.

Synchronisation for smart factory - towards IoT-enabled mechanisms

ABSTRACTTraditionally, production scheduling is optimised using objective functions based on punctuality criteria such as earliness and tardiness. However, synchronisation in complicated manufacturing process is always neglected. Due to the lack of synchronisation, severe problems happen frequently such as long holding time and unreasonable setups. Motivated by the practical challenges, the authors are among the first to present the IoT-enabled real-time synchronisation approaches for an automobile standard part factory with the following objectives. First, the synchronisation paradigm is proposed in terms of two dimensions, namely the Horizontal Synchronisation (HSync) for the consistency of batch production progresses within one customer order, and the Vertical Synchronisation (VSync) for the coordination between adjacent processing stages. Second, the IoT-enabled synchronisation mechanisms using rule-based heuristics and real-time production data is presented. Third, an advanced planning and scheduling (APS) system framework is developed to automatically implement the synchronisation mechanisms. Finally, the effectiveness of the synchronisation mechanisms is verified through a case study.

Knowledge-Based Instrumentation and Control for Competitive Industry-Inspired Robotic Domains

Autonomy is an increasing trend in manufacturing industries. Several industry-inspired robotic competitions have been established in recent years to provide testbeds of comprehensible size. In this paper, we describe a knowledge-based instrumentation and control framework used in several of these competitions. It is implemented using a rule-based production system and creates the task goals for autonomous mobile robots. It controls the environment’s agency using sensor data from processing stations and instructs proper reactions. The monitoring and collection of various data allows for an effective instrumentation of the competitions for evaluation purposes. The goal is to achieve automated runs with no or as little human intervention as possible which would allow for more and longer lasting runs. It provides a general framework adaptable to suit many scenarios and is an interesting test case for knowledge-based systems in an industry-inspired setting.

Campaign management design based on segmentation by rank clusters

When building campaign management systems, two main aspects are important from an algorithmic point of view. First, many customers need to be classified with respect to their (bank) product portfolios, which means ranking the potential products for advertisement such as direct mailings, e-mails, website or mobile app advertisement. Second, campaigns for different customer segments need to be planned in advance to balance the costs and the success of marketing activities. For these tasks, we propose a process, starting with rule-based classification, including an evolutionary algorithm combined with a nearest-neighbor technique to obtain understandable, optimized rules. The classification results lead to product rankings for each customer. We cluster the rankings with p-means, using a modified Canberra distance, so that we obtain customer segments. Then, we design a new index for measuring the assignments of campaigns with products to the clusters. With this campaign clustering index (CACLUX), we gain the potential to plan the campaign design for customer segments in advance, comparing poor assignments with good ones. Overall, we present a line of action that generates on the basis of rule-based customer classification and product rankings quantified assignments of campaigns to clusters.

Rule-based runtime verification revisited

Runtime verification (RV) consists in part of checking execution traces against user-provided formalized specifications. Throughout the last decade many new systems have emerged, most of which support specification notations based on state machines, regular expressions, temporal logic, or grammars. The field of artificial intelligence (AI) has for an even longer period of time studied rule-based production systems, which at a closer look appear to be relevant for RV, although seemingly focused on slightly different application domains, such as, for example, business processes and expert systems. The core algorithm in many of these systems is the Rete algorithm. We have implemented a rule-based system, named LogFire, for runtime verification, founded on the Rete algorithm, as an internal DSL in the Scala programming language (in essence a library). Using Scala's support for defining DSLs allows to write rules elegantly as part of Scala programs. This combination appears attractive from a practical point of view. Our contribution is part conceptual in arguing that such rule-based frameworks originating from AI are suited for RV. Our contribution is technical by implementing an internal rule DSL in Scala; by illustrating how specification patterns can easily be encoded that generate rules, and by adapting and optimizing the Rete algorithm for RV purposes. An experimental evaluation is performed comparing to six other trace analysis systems. LogFire is currently being used to process telemetry from the Mars Curiosity rover at NASA's Jet Propulsion Laboratory.

From Local Roots to Global Screens: Shane Meadows’ Positioning in the Ecology of Contemporary British Film

This article provides a case study of the ecology of British independent film, as illustrated through the continuing career of Shane Meadows. I focus on the intersection between the practices of economic independence and creative independence, ameliorated by low-budget, local films that exploit festival showcasing and critical buzz to achieve international exhibition in a range of markets. While Meadows’ earlier films exemplify the reliance on television funding that has characterised British and continental European cinema since the 1980s, and the emerging significance of regional and Lottery-based funding in the 1990s, they also correspond to the local/international model of much low-budget European realist art cinema, best identified with the Dogme 95 films or those of the Dardenne brothers. Yet since Once Upon a Time in the Midlands (2002), Meadows has deviated from the established trajectory of recognised British auteurs, Mike Leigh and Ken Loach, instead utilising co-production funding to reduce his budgets to ensure maintaining artistic control. Akin to post-Dogme rule-based production manifestoes such as ‘Industrial Film DK’, Meadows has developed and revisited his own rules: film what you know – focusing on a particular local community, localised identities, and restricted locations – in addition to improvisational approaches to acting. Consequently Meadows has achieved recognition as a local but global film-maker.

Rule-based forecasting and production control system design utilizing a feedback control architecture

Forecasting and production control systems typically rely on operational rules that have been accumulated and refined from enterprise experts. Designing a rule-based system is a challenging task. In this article, a new rule-based system design methodology for forecasting and production control is proposed. The methodology first represents the rule-based system as a finite state automaton (a Moore machine) and then formulates an optimal control problem in a feedback control architecture. The solution to the optimal control problem provides action rules for forecasting and production that minimize cost over a given time horizon. The proposed methodology provides a systematic tool for rule-based system design that gives robust and realistic solutions.

Performance-oriented integrated control of production scheduling

Rule-based production scheduling is analyzed from the perspective of closed-loop control. An integrated feedback control methodology is proposed to enhance the performance of rule-based scheduling. The integrated control system consists of a state feedback control module, a performance-based feedback module, and a supervisory control module. Performance criteria are analyzed and classified into job-related and resource-related criteria. The key factors of performance are identified and used as state variables in the feedback control. The performance-based feedback control compensates for the errors that are caused by the scheduling rules. The supervisory control is designed to enhance the overall performance by adjusting the feedforward gains according to scheduling objectives. Simulation results show that the integrated control scheme can significantly improve the overall performance of the scheduling system.

Prioritization of congenital cardiac surgical patients using fuzzy reasoning – a solution to the problem of the waiting list?

Surgical waiting lists are of high importance in countries, where the national health system is unable to deliver surgical services at a rate that would allow patients to avoid unnecessary periods of waiting. Prioritization of these lists, however, is frequently arbitrary and inconsistent. The objective of our research was to analyze the medical decision-making process when prioritizing patients with congenital cardiac malformations for cardiac surgical procedures, identifying an appropriate representation of knowledge, and transferring this knowledge onto the design and implementation of an expert system ("PrioHeart"). The medical decision-making process was stratified into three stages. The first was to analyze the details of the procedure and patient to define important impact factors on clinical priority, such as the risk of adverse events. The second step was to evaluate these impact factors to define an appropriate "timing category" within which a procedure should be performed. The third, and final, step was to re-evaluate the characteristics of individual patients to differentiate between those in the same timing category. We implemented this decision-making process using a rule-based production system with support for fuzzy sets, using the FuzzyCLIPS inference engine and expert system shell as a suitable development environment for the knowledge base. The "PrioHeart" expert system was developed to give paediatric cardiologists a tool to allow and facilitate the prioritization of patients on the cardiosurgical waiting list. Evaluation of "PrioHeart" on limited sets of patients documented appropriate results of prioritization, with a significant correlation between the prioritization made using "PrioHeart" and those results obtained by the individual consultant specialist. We conclude that our study has demonstrated the feasibility of using an expert system approach with a fuzzy, rule-based production system to implement the prioritization of cardiac surgical patients. The approach may potentially be transferable to other medical subspecialities.

Reactive processing in ADOME-II: an extensible approach

A new approach for supporting reactive capability is described in the context of an advanced object-oriented database system called ADOME-II. Besides having a rich set of pre-defined composite event expressions and a well-defined execution model, ADOME-II supports an extensible approach to reactive processing so as to be able to gracefully accommodate dynamic applications’ requirements. In this approach, production rules combined with methods are used as a unifying mechanism to process rules, to enable incremental detection of composite events, and to allow new composite event expressions to be introduced into the system declaratively. This allows the definition of new production rules each time an extension of the model takes place. Methods of supporting new composite event expressions are described, and comparisons with other relevant approaches are also conducted. A prototype of ADOME-II has been constructed, which has as its implementation base an ordinary (passive) OODBMS and a production rule base system.

Designing reusable rule-based architectures with design patterns

Abstract Rule-based systems or production systems still have great importance in the construction of knowledge systems. In these systems, the domain expertise to solve a problem is encoded in the form of ‘if–then’ rules, enabling a modular description of the knowledge, thus facilitating its maintenance and updating. Although they have been extensively described in the Artificial Intelligence literature, their design process is at times repeated because of the lack of common software architecture and the restrictions offered by some off-the-shelf libraries and systems. This paper proposes a reusable architecture for rule-based systems described through design patterns. The aim of these patterns is to constitute a design catalog that can be used by designers to understand and create new rule-based systems, thus promoting reuse in these systems. Additionally, the use of the described patterns in the design of an intelligent tutoring system architecture is exemplified.

A rule-based master production scheduling system for an electro-mechanical manufacturing company

It is a hard process to modify master production schedule in a firm having various types of products and final assembly groups. Therefore, the system should automatically make the needed and proper modifications when they are input. Besides, it is of great importance to the firm to remove the errors of demand forecasting so as not to reject customer orders. In this study, a rule-based system for an electromechanical manufacturing company, which is able to rearrange the master production schedule, is presented. This system will provide considerableeasinessofusein themaster production scheduling activities.

Genetic production systems for intelligent problem solving

The paper discusses an evolutionary knowledge approach to intelligent problem solving. A rule-based production system is used to model the problem and the means by which the problem space should be searched. Search heuristics are modelled as production rules. These rules are redundant as there may be more than one view on the best method for building solutions. Some rules may have complex reasoning for their actions, others have none. Deciding which rule is most appropriate is solved by a genetic algorithm and ultimately only the ‘fitter’ rules will survive. The approach eliminates the necessity of designing problem specific search or variation operators, leaving the genetic algorithm to process patterns independent of the problem at hand. Learning methods and how they aid evolution is also discussed: they are Lamarckian learning and the Baldwin effect. The approach is tested on a scheduling problem.

Encoding of Production Rules in a Connectionist Network

The task of implementing a simple rule-based production system in a connectionist architecture is discussed. To implement a connectionist-based production system, it is essential to be capable of representing explicit rules by means of simple neuronlike computing units. The architecture described here uses a local representation based upon the instance oriented symbolic/connectionist expert system SC net. The problems of variable binding and variable value instantiation are solved in the context of this system. The network is built such that only one value is bound to a variable during each rule firing cycle. Issues regarding serialization and working memory consistency are also solved. An example implementation, the Farmer's Dilemma planning problem, is given to illustrate the potential of this approach. The article shows how many different rule bases may be mapped onto a connectionist architecture for parallel execution.

Formal semantics for rule-based systems

The existence of a formal description of any language is a prerequisite to any rigorous methods of proof, validation, or verification. This article develops a formal semantics in the denotational style for rule-based production systems. Primarily, a formal description of a generalized, hypothetical language for rule-based expert systems is developed as a base. Building on this base, it is possible to specify in detail the variations that distinguish individual real-world systems in a usable way.

Dynamic control of flexible manufacturing systems

Flexible manufacturing systems (FMSs) are a relatively new technological and organisational approach to helping companies respond to real-time marketing conditions for their production. Under a proposal of the National Bureau of Standards the FMSs are subdivided into virtual manufacturing cells in a dynamic manner, on the basis of group technology. A method of dynamic optimisation for the design of manufacturing processes, capacity balancing and checking, and also production scheduling or rescheduling in virtual manufacturing cells is described. It can be used during real-time production control in FMSs. Bellman's method of dynamic programming is used for the optimisation of manufacturing process design and execution. The model of manufacturing processes optimisation has been built in accordance with assumptions of Bellman's method. This model consists of a synthesised network of alternative manufacturing processes, a description of its components and an appropriate formula of criterion function. It can be considered as a “production rule base” of an expert system.