Expert System Software Research Articles

Application of an integrated CAD/CAE/CAM system for die casting dies

According to the concept of concurrent engineering (CE), a CAD/CAE/CAM integrated system for die casting dies is established and applied in the primary stage. The platform of the Pro/ENGINEER CAD/CAM software, the MAGMASOFT simulation software and a primary expert system for the design of the die casting process are available to establish this integrated system. A primary expert system package including a series of empirical calculation equations and data for the design of technological scheme and dies of die casting has been developed by the authors. This integrated system has been applied successfully in the design and manufacture of die casting dies for aluminum and magnesium die castings, such as the water pump of the Santana sedan. The use of this integrated system can shorten the cycle of die design and manufacture, and result in the production of high quality die castings in a shorter time. The lead-time of die castings is shortened greatly.

Linking the Witness Simulation Software to an Expert System to Represent a Decision�Making Process

Expert systems, and artificial intelligence more generally, can provide a useful means for representing decision-making processes. By linking expert systems software to simulation software an effective means of including these decision-making processes in a simulation model can be achieved. This paper demonstrates how a commercial-off-the-shelf simulation package (Witness) can be linked to an expert systems package (XpertRule) through a Visual Basic interface. The methodology adopted could be used for models, and possibly software, other than those presented here.

ICONE11-36233 ISI Program in ETRR-2 Welded Parts in Form of Logic Flow Charts

A complete in-service inspection (ISI) program for nuclear research reactors requires several steps that have to be performed in sequence. These steps were described in many logic flow charts (LFC's). These logic flow charts might be separately used as a guide for future work in case of developing expert system software for research reactors. These charts included a general LFC describing the steps required to complete the ISI program. Details of this general LFC describing the steps required to complete the ISI program. Details of this general LFC are given in many modules. The next step of the LFC is to define the class of the component to be inspected. For each component class there are related modules that should be followed (examination requirements modules, examination methods modules, and flaw acceptance/rejection modules). If the component is accepted according to the requirements found in American Society of Mechanical Engineers (ASME) CODE section XI, the record and report requirement modules will be used to complete the ISI program. In the present work the inspection requirements for welded parts in the Second Egyptian Testing Research Reactor (ETRR-2) are considered. ETRR-2 is a pool- type reactor with an open water surface and variable core arrangement. Its core power is 22 MW_<th>, cooled and moderated by light water and with beryllium reflectors. It contains platetype fuel elements (MTR type, 19.7% enriched uranium) with aluminum clad. This reactor consists of 57 systems and around 200 subsystems, these systems contain many mechanical components such as; tanks, piper, valves, pumps, heat exchangers, cooling tower, air compressors and suppors.

Robotic system approach for complete denture manufacturing

A robotic system for complete denture manufacturing, which can realize automatic implanting of artificial teeth, is described. The tooth arrangement algorithm is presented, including the equations of jaw-arch curve and teeth-arch curve, setup of a single tooth coordinate system and calculation of tooth position in teeth-arch curve. An expert system software is developed that integrates high-level dentist experiences and dexterous technician skills. Three-dimensional (3-D) display of tooth arrangement, human-computer interactive adjustment of tooth position and orientation in teeth-arch curve are achieved. Robot path planning and control data creation are realized by this software also. Finally, an experiment of complete denture manufacturing is made for a patient, a pair of complete dentures is obtained, and the results are analyzed. This robotic system is expected to change the manner of complete denture manufacturing wholly, and significantly improve product quality and manufacturing efficiency.

Application of a new expert system for the structure elucidation of natural products from their 1D and 2D NMR data.

Described herein are applications of the latest version of the StrucEluc expert software system, enhanced to use 2D NMR data, to the structure elucidation of 60 recently isolated natural products. In this study, selected molecules containing between 15 and 65 skeletal atoms and having molecular masses ranging from 200 to 900 amu have been investigated. The correct structure was determined unambiguously for 58 of these molecules. The structures for 75% of the data sets were determined in less than one minute, while 90% of the analyses required no more than 30 minutes. The strategy of structure elucidation by this expert system is described, and several examples are discussed. These illustrate that StrucEluc is a powerful and versatile analytical tool for the structure elucidation of natural products.

Quantitative prediction of biodegradability, metabolite distribution and toxicity of stable metabolites

An evaluation of the capability of organic chemicals to mineralize is an important factor to consider when assessing their fate in the environment. Microbial degradation can convert a toxic chemical into an innocuous one, and vice versa , or alter the toxicity of a chemical. Moreover, primary biodegradation can convert chemicals into stable products that can be difficult to mineralize. In this paper, we present some new results obtained on the basis of a recently developed probabilistic approach to modeling biodegradation based on microbial transformation pathways. The metabolic transformations and their hierarchy were calibrated by making use of the ready biodegradability data from the MITI-I test and expert knowledge for the most probable transformation pathways. A model was developed and integrated into an expert software system named CATABOL that is able to predict the probability of biodegradation of organic chemicals directly from their structure. CATABOL simulates the effects of microbial enzyme systems, generates the most plausible transformation pathways, and quantitatively predicts the persistence and toxicity of the biodegradation products. A subset of 300 organic chemicals were selected from Canada's Domestic Substances List and subjected to CATABOL to compare predicted properties of the parent chemicals with their respective first stable metabolite. The results show that most of the stable metabolites have a lower acute toxicity to fish and a lower bioaccumulation potential compared to the parent chemicals. In contrast, the metabolites appear to be generally more estrogenic than the parent chemicals.

REF Select: expert system software for selecting restriction endonucleases for restriction endonuclease fingerprinting.

REF Select, expert system software, has been developed to assist in the selection of optimal restriction endonucleases for restriction endonuclease fingerprinting (REF), a method for rapid and sensitive mutation screening of long DNA segments (1-2 kb). The REF method typically involves six separate digestions with up to two restriction endnonucleases used in each digestion. If done manually, performing a comprehensive review of the large number of possible sets of restriction endonucleases that could be used (over 10(19) in the example presented here) and making an optimal choice is not feasible. Furthermore, the typical nonoptimal manual selection takes approximately 8 h by someone experienced with REF. REF Select enables a comprehensive review of the possible sets and a consistent, objective and fast selection of an optimal set by using a two-step strategy: the selection of sets that meet specific constraints, which is followed by a ranking of those sets by an optimality score. Based on our experience with REF, we chose default selection and ranking parameters to help the user get started quickly. These parameters form a knowledge base that can be customized and then saved by the user. In conclusion, REF Select facilitates the general application of REF by serving as an expert system for the selection of optimal restriction endonucleases. We demonstrated REF Select using an example segment from the human p53 gene.

Linking process simulation and process integration

Process design should consider alternative flowsheet topologies and alternative equipment sizes. For instance, the process design of a distillation sequence should consider different sequences (direct, indirect, others), different overhead compositions, recycle flowrates, reflux ratios, etc. Each design will have its own energy consumption. Moreover, each design will have its own potential for integration with the rest of the process. To keep track of all alternatives, the process design engineer usually relies on simulation. Different process topologies and equipment sizes are simulated, costed and compared. The wider the scope of the system is the more difficult it becomes for the engineer to keep track of all solutions and the search becomes “ad hoc”. In this situation, process integration helps. Process integration methods often guarantee, or nearly guarantee, optimal structures for a significant part of the system. In other words, process integration plays an important part in process design. However, there have been barriers to overcome in the introduction of process integration to the process design environment. Perhaps the most important such barrier has been the problem of “data extraction”. The task of “data extraction” presented a barrier because it required expert understanding of process integration techniques, particularly Pinch Technology. Inexpertly extracted data often led in practice to situations where optimum solutions were missed. Moreover, the task of “data extraction” was time consuming, even for the expert. In 1997, Linnhoff March launched software to perform the skilled task of “data extraction”, automatically. This novel and unique software is based on an expert system which acts as an intelligent interface between process simulation and process integration. In 1998, Linnhoff March complemented this with more-direct links with the main commercial process simulators. The overall package analyses any simulated process at the press of a button, automatically, to identify the potential for improvement. There are many benefits. Design time is saved. The impact of process changes on overall cost is quickly analysed for any number of options. The power to do this is made accessible to a larger number of less-experienced users. All in all, process designs will be designed close to optimum, by less experienced users, in less time. In this paper, we outline the essential principles for extracting process integration data from process simulations, as implemented in Linnhoff March's expert system software. Practical examples from industrial projects demonstrate these principles to produce rapid and reliable results to reduce process energy levels and capital investment.

Expert System for Utilization Review of Alcohol and Drug Abuse Cases

ABSTRACT Expert system software was developed to assist in determining the appropriate treatment for substance abuse patients. The software applies criteria, called the Mental Health Review Criteria (MHRC(©)), which are widely used by utilization review professionals who make treatment decisions in managed health care plans. The expert system also collects a database of patient information, including the paths that led to all treatment decisions. The expert system was evaluated by comparing its decisions with those of managed care nurse reviewers and with those of a panel of physicians who helped to develop the MHRC. A set of 70 cases were assessed by the expert system, the nurse reviewers, and the physician panel. The possible decision outcomes were approval of providers' requests for inpatient detoxification or referral for further consideration. The expert system and the nurse reviewers each agreed with the physician panel in about 85 percent of the cases. Both the expert system and the nurse reviewers were more likely to agree with the physician panel in the cases that they approved for inpatient treatment than in the cases that they referred for further consideration.

New tools: Expert systems for uncertainty budgets

An important part of quality assurance in any analytical laboratory is the production of comprehensive results integrating uncertainty measurements. Many testing laboratories face the problem that the expenditure required to evaluate small uncertainties (high precision and high accuracy) is often uneconomic. In most cases an uncertainty of high reliability has to be calculated from only a few data (one calibration, few replications, etc.). This problem can be solved by an expert system. To achieve this the analytical procedure has to be structured into a dialouge and divided into parts. The uncertainty has to be calculated for each part of the procedure. Addition of the individual uncertainties results in the combined and expanded uncertainty. During the dialouge the system should advise the analyst how to get an efficient and effective calculation of uncertainty. All calculations, mathematical and statistical procedures have to be surveyable but running the system should not be too time consuming for economic reasons. Within the scope of the EURECA-project initiated by the Eidgenossische Materialprufungs- und Forschungsanstalt (EMPA), St. Gallen, Switzerland, expert system software is being developed in cooperation with other research institutes and manufacturers of analytical instruments. Using this software it will be possible to calculate the uncertainty for analytical procedures such as titration, atomic emission spectrometry (ICP-OES), atomic absorption spectrometry (AAS) and gas- and liquid chromatography (GC, HPLC).

Automatic classification of transiently evoked otoacoustic emissions using an artificial neural network.

The increasing use of transiently evoked otoacoustic emissions (TEOAE) in large neonatal hearing screening programmes makes a standardized method of response classification desirable. Until now methods have been either subjective or based on arbitrary response characteristics. This study takes an expert system approach to standardize the subjective judgements of an experienced scorer. The method that is developed comprises three stages. First, it transforms TEOAEs from waveforms in the time domain into a simplified parameter set. Second, the parameter set is classified by an artificial neural network that has been taught on a large database TEOAE waveforms and corresponding expert scores. Third, additional fuzzy logic rules automatically detect probable artefacts in the waveforms and synchronized spontaneous emission components. In this way, the knowledge of the experienced scorer is encapsulated in the expert system software and thereafter can be accessed by non-experts. Teaching and evaluation of the neural network was based on TEOAEs from a database totalling 2190 neonatal hearing screening tests. The database was divided into learning and test groups with 820 and 1370 waveforms respectively. From each recorded waveform a set of 12 parameters was calculated, representing signal static and dynamic properties. The artifical network was taught with parameter sets of only the learning groups. Reproduction of the human scorer classification by the neural net in the learning group showed a sensitivity for detecting screen fails of 99.3% (299 from 301 failed results on subjective scoring) and a specificity for detecting screen passes of 81.1% (421 of 519 pass results). To quantify the post hoc performance of the net (generalization), the test group was then presented to the network input. Sensitivity was 99.4% (474 from 477) and specificity was 87.3% (780 from 893). To check the efficiency of the classification method, a second learning group was selected out of the previous test group, and the previous learning group was used as the test group. Repeating learning and test procedures yielded 99.3% sensitivity and 80.7% specificity for reproduction, and 99.4% sensitivity and 86.7% specificity for generalization. In all respects, performance was better than for a previously optimized method based simply on cross-correlation between replicate non-linear waveforms. It is concluded that classification methods based on neural networks show promise for application to large neonatal screening programmes utilizing TEOAEs.

Metal and ceramic powders for injection moulding: P.Minuth et al. (H.C.Starck GmbH, AG, Germany.)

A high temperature batch furnace has been constructed for real-time analysis of sample weight, compact temperature profile and evolved gas composition using various gas analysis methods. The furnace has digital mass flow controllers for atmosphere composition control. A separate precision dilatometer is used to provide dimensional change data. These analytical capabilities are controlled by a microprocessor coupled to a control computer which records the output from the various sensors. The long range goal is to develop an expert systems software to fully govern the thermal and atmosphere cycle in a closed-loop feedback mode. This will allow optimization of the sintering pathway for any material, processing objectives, and component geometry. In addition, the equipment will be used to investigate the debinding cycle of powder injection moulded (PIM) parts. By varying the heating rate, time at temperature, and atmosphere during the debinding cycle, the debinding mechanisms and rate controlling parameters can be identified. The goal of these experiments is to significantly lower the debinding time while maintaining compact integrity. A model for optimized processing is being developed in parallel with these experiments.

Computerized relational model for powder technology: powder and process selection

Part of a complete expert-system software design for powder technology is presented. This part of the system deals with powder selection according to predetermined, recommended or required material properties, and specific powder characteristics. Then the optimum powder production, i.e processing, method is determined, which satisfies the requirements of the specified powder. For this purpose a detailed database relational model is developed, and the system's software modules are described. A relational model is formulated and a structured query language (SQL) is used in the detailed software design presented.

Integrating Serials into the Triangle Research Libraries Network Document Delivery System

No library can acquire everything its patrons will need, so providing access to other collections has become essential. This article describes the Triangle Research Libraries Network Document Delivery System (TRLN DDS), which automates the process of placing requests, and as much of the request management and supply process as possible. The system uses expert system software to locate potential suppliers of requested items. Requests for serials pose significant challenges for an expert system, due to incomplete citations, incomplete holdings information in online catalogs, copyright, availability of electronic serials, alternatives for electronic delivery, and several Other factors.

Changing the infection control paradigm from off-line to real time: the experience at Millard Fillmore Health System.

In 1993, several departments at Millard Fillmore Health System joined efforts to initiate a new approach to infection control. The main emphasis of this program is to move infection control to a real-time mode to manage patient outcomes daily. The principal objective was to decrease the number of nosocomial infections by 10%, with a particular emphasis on surgical-site infections. Besides real-time surveillance, we are critically evaluating several aspects of the management of nosocomial infections. High-level computer support has been the frame-work upon which this program was built. We have microcomputers that are linked directly to microbiology, pharmacy, billing, and admissions, downloading data several times daily. An expert software system merges all of the data, and from this we can target patients for real-time interventions. The computer system allows all inpatients to be screened for either infection control or antibiotic management interventions on a daily basis, with minimal time being spent on data collection and maximal efforts devoted to interventions at the bedside. Additionally, the infection management program will assist in maintaining the extraordinarily low expenditures on antimicrobial agents. During 1993, the Millard Fillmore Health System spent $924,884 on antibiotics, an amount approximately 50% that of comparably sized hospitals.

The Development of a Skinnerian Based Expert System for Use in a Computer Managed Instructional Feedback System

This article describes efforts to include an expert system software package, based on the theories of B. F. Skinner, into a computer managed instructional system. The purpose of the system is to provide meaningful feedback to students concerning their achievement status on a weekly basis. The process for the development of the system is discussed as well as results in light of the collection and analysis of both quantitative and qualitative data. Conclusions are drawn that suggest that behaviorist techniques can be incorporated into instructional software at a level higher than the traditional task specific feedback.

Construction delay analysis techniques

Construction projects continue to suffer delays. Things go wrong and the project's completion date gets pushed back, with someone to be blamed for it. In practice, attempts are made to identify the causes of delays and schedules are modified to incorporate revised duration and new project time. The analysis itself is usually complex and can be aided by a computerized approach. This paper discusses different delay analysis techniques that are currently used by practitioners in the construction industry. It also discusses a proposed new delay analysis technique called the Isolated Delay Type (IDT). These techniques were tested against a case example and their strengths and weaknesses highlighted. The new technique can be used as a standalone module for delay analysis or could be incorporated within a computer system for construction delay analysis and claims preparation called Computerized Delay Claims Analysis (CDCA) that integrates different software including an expert system and management software such as scheduling and a database or spreadsheet.

Expert Systems for the Evaluation of Data Quality for Establishing the Recommended Dietary Allowances

In view of the important role that nutrient intake assessments play in establishing the Recommended Dietary Allowances (RDAs), the quality of food composition data must be assured for accuracy and representativeness. Assurance of data quality requires the definition of critical parameters in the data generation process and the evaluation of specific data for foods and components according to these parameters. An expert systems approach for evaluating the quality of analytical data has been developed by scientists at the Beltsville Human Nutrition Research Center to determine the quality of food composition data for five parameters: sampling plan, sample handling, number of samples, analytical method and analytical quality control. A rating scale for each parameter was developed with 0 representing poor or inadequately documented data and 3 representing optimal data. Specific criteria for each parameter and rating have been developed and incorporated into expert systems software to facilitate the objective assignment of ratings for each data source by the reviewer. After all ratings for a specific food-nutrient combination are assigned, the system calculates a composite score called the “confidence code” which indicates to the user the relative level of confidence in the data. By identifying and rating the important steps in the data generation process, one can begin to partition the possible sources of error or variability in the process. Limitation of the data set relative to specific purposes (e.g., setting the RDAs) can be identified. The evaluation process can provide the basis for focussed research to improve the most critical areas of the data generation process. A similar process could be established to evaluate the quality of analytical data for clinical measurements used to establish the RDAs.

Development of an Expert System for Daily Drought Monitoring

A daily drought-monitoring system was developed using the Clips Expert System software package. The monitoring system consists of four components: (1) the knowledge base, which contains rules in the form of IF-THEN type for the decision of assigning a daily drought severity; (2) the working memory which contains facts of historic drought characteristics including truncation levels, mean durations, and mean conditional probabilities estimated at gauging stations; (3) the inference engine, which makes inferences to decide what rules are satisfied by current facts for assigning drought-severity levels; and (4) the user interface, which provides the mechanism for communication between the user and the system. A six-month period of the historic drought that started at the beginning of May 1988 in the central Ohio region was used to test the developed system. The developed system was found to detect daily drought occurrences effectively.

Analyzing knowledge-based systems with multiviewpoint clustering analysis

Knowledge-based systems have wide commercial applicability. However, a credible validation methodology for knowledge-based systems is currently lacking. Better knowledge acquisition techniques as well as better management, understanding, and enhancement of the knowledge base is critical to the success of any verification or validation activities. Our research addresses the feasibility of partitioning rule-based systems into a number of meaningful units to enhance the comprehensibility, maintainability, and reliability of expert systems software. Preliminary results have shown that no single structuring principle or abstraction hierarchy is sufficient to understand complex knowledge bases. We therefore propose the multiviewpoint clustering analysis (MVP-CA) 'methodology to provide multiple views of the same expert system. MVP-CA provides an ability to discover significant structures within the rule base by providing a mechanism to structure both hierarchically (from detail to abstract) and orthogonally (from different perspectives). Here we describe our approach to understanding large knowledge bases via MVP-CA. We demonstrate the need for MVP-CA by use of a couple of small classic rule bases, as well as a deployed knowledge-based system that navigates the space shuttle's reentry. We also discuss the impact of this approach on verification and validation of knowledge-based systems. MVP-CA provides an essential first step toward building an integrated environment for verification and validation of knowledge-based applications. It allows one to build reliable knowledge-based systems by suitably abstracting, structuring, and otherwise clustering the knowledge in a manner that facilitates its understanding, manipulation, testing, and utilization.