Diagnostic Expert System Research Articles

A framework for an on-line diagnostic expert system with intelligent sensor validation

This paper outlines a framework for performing two different but inter-related functions in diagnosis, i. e. sensor validation and reasoning under uncertainty. Sensor validation plays a vital role in the ability of the overall system to correctly determine the state of a plant monitored by imperfect sensors (Sopocy, 1990). Two subsystems, Algorithmic (ASV) and Heuristic (HSV) Sensor Validation, separate activities according to the degree of plant knowledge required and represent Sensor Validation Expert System when combined. Uncertain information in sensory values is represented through probability assignments on three discrete states, High, Normal, and Low, and additional sensor confidence measures in ASV. HSV exploits deeper knowledge about parameter interaction within the plant to cull sensor faults from the data stream. Finally the modified probability distributions and validated data are used as input to the reasoning scheme which is the run-time version of the influence diagram. The influence diagram represents the backbone of reasoning under uncertainty in Influence Diagram Knowledge Base.

BEST-based expert diagnostic system for the aluminum industry

An expert system designed for diagnosis locates or identifies malfunctions within a biological, electronic, industrial or any other system. We claim BEST (Blackboard-based Expert System Toolkit) to be a very adequate environment for diagnostic tasks, since it provides natural means for simulating a human expert diagnostician's behavior. The diagnostic function deals with the generation and evaluation hypotheses. Using gathered data (symptoms) and a “forward-chaining” control strategy, the diagnostician generates a hypothesis (possible diagnosis) and then, using “ackward chaining”, acquires more data (measurements, laboratory data, etc.) and proves or rejects the hypothesis. Apart from a combined control strategy, BEST offers model-based reasoning and hypothetical reasoning, i.e. parallel exploration of different hypothetical diagnoses, which is a rather difficult task for a human diagnostician. An illustrative example of the BEST-based expert diagnostic system for a bauxite-ore mill unit in aluminum industry is described in the paper.

Adaptive uncertainty management for a class of diagnostic expert systems

AbstractThis paper gives a theoretical foundation and implementation details of data and control structures in a diagnostic expert system with adaptive uncertainty management. The considered problem covers a class of expert systems and the application domain in which the operating personnel actively monitor and control the outcome of an industrial manufacturing process. Based on subjective ranking of the latent fault in the final output product, the operator queries the expert system for a recommended corrective action. Subsequent successful or unsuccessful corrective actions consistently modify confidence measures of all corrective recommendations from the same fault set, according to the embedded analytical model. The described approach is based on the relational data representation and procedural control structures, as opposed to a more traditional declarative, production-based system.

A formal language description and inference strategy for analog circuit design

This article deals with a new intelligent analog circuit design system. Unlike previous design methods, this approach introduces a formal circuit representation for both the numerical and heuristic knowledge of the design system. The predicate logic circuit representation is proposed as a new formal analog circuit description language. The language's syntax and semantics provide a precise symbolic description of analog circuit functionality at higher levels of hierarchy and network component connectivities, together with CMOS transistor sizes as the lowest level of hierarchy. It is shown how sentence conversion rules of language grammer can be used to derive transistor level circuits from input performance specifications. Language sentences have the form of clauses. In addition to clause representation, a frame representation to reflect VLSI design hierarchy is also introduced. An original bidirectional inference mechanism with elements of hypothesis has been introduced to infer designs from the knowledge in clause and frame representations. The unique feature of this circuit knowledge representation is its ability to automate the analog CMOS circuit design process. The design methodology is described in detail. The proposed iterative closed loop design system adopts an expert system approach to provide topological synthesis, uses a SPICE circuit simulator to evaluate the circuit performance, and uses a new diagnostic expert system to provide advice on how to improve the design. The implementation of the methodology and associated experimental results for simple CMOS operational amplifier designs are also presented.

Rule-based versus probabilistic approaches to the diagnosis of faults in wastewater treatment processes

The need for computer-based diagnostic tools in wastewater management is outlined. Rule-based and probabilistic approaches to the development of diagnostic expert systems are critically reviewed, and it is demonstrated that the rule-based approach has serious limitations which make it unsuitable for diagnostic tasks under conditions of uncertainty. It is shown that Bayesian belief networks (BBNs), a probabilistic approach, has none of these limitations and is well-suited to diagnosis under uncertainty. The theory and application of BBNs are outlined and illustrated by a simple example based on a wastewater treatment plant. A brief case study is presented of the development of a full-scale BBN for the diagnosis of faults in a wastewater treatment plant. It is concluded that BBNs are far superior to rule-based systems in their ability to diagnose faults in complex systems like wastewater treatment processes, whose behaviour is inherently uncertain.

Computer expert system for the histopathologic diagnosis of salivary gland neoplasms

The design, development, and testing of a prototype interactive histopathologic expert system capable of diagnosing 15 types of primary salivary gland neoplasms is described. The system incorporates a multiple subprogram modular design and makes use of multiple reasoning methods including: data-driven and goal-directed rule-based reasoning, linear pattern recognition, and Bayesian classification. Its user interface incorporates both a "hypertext" context-sensitive information assistance facility and the video display of stored and digitized photomicrographic images. The system can report a differential diagnosis of its findings with assessment of its confidence in its diagnosis. The system's performance was evaluated in a series of tests. The results of a weighted kappa analysis of the system's diagnoses versus those of four oral pathologists for 20 salivary gland neoplasms indicated no statistical difference in diagnostic performance between the system and the human experts and each of the experts in relationship to the others (Wilcoxon rank sums test). A modified version of Turing's test of artificial intelligence demonstrated no statistically significant difference in the system's diagnoses versus the diagnosis of four human expert pathologists (Fisher's exact test). The knowledge and experience gained in the development and testing of the expert system described in this study have demonstrated the validity of histopathologic diagnostic expert systems in a selected area of oral pathology.

An Automated Diagnostic Expert System for Diesel Engines

Fault diagnosis of diesel engines can be a tedious time-consuming process, resulting in extended downtime, thus reducing productivity and increasing operational cost. This problem can be accentuated when experienced expert maintenance personnel are in short supply and also when the rate of development of new-generation engines using leading edge technology does not permit maintenance personnel to keep up with this change. An automated diagnostic system based on artificial intelligence criteria using mechanical signature analyses (MSA) of signals acquired from engine mounted sensors can overcome this problem by providing expert and consistent diagnostic advice. This paper describes the development and implementation of an automated diagnostic expert system for diesel engines. The system uses vibration signals together with oil pressure and temperature, crankcase pressures, exhaust gas temperature and pressure, exhaust emissions, manifold noise levels, inlet manifold pressure, fuel delivery pressure, and instantaneous engine speed to monitor and diagnose engine faults. State-of-the-art techniques used for signal processing to generate data required for effective diagnosis from raw signals acquired form the engine mounted sensors are described. Complexities of signal processing for diesel engines are discussed and solutions of a practical nature suggested. Signal analysis techniques relating to fault condition evaluation are also described.

Performance evaluation of a large diagnostic expert system using a heuristic test case generator

Validating the performance of a knowledge-based system is a critical step in its commercialization process. Without exception, buyers of systems intended for serious purposes require a certain level of guarantees about system performance. This is particularly true for diagnostic systems. Yet, many problems exist in the validation process, especially as it applies to large knowledge-based systems. One of the biggest challenges facing the developer when validating the system's performance is knowing how much testing is sufficient to show that the system is valid. Exhaustive testing of the system is almost always impractical due to the many possible test cases that can be generated, many of which are not useful. It would thus be highly desirable to have a means of defining a representative set of test cases that, if executed correctly by the system, would provide a high confidence in the system's validity. This paper describes the experiences of the development team in validating the performance of a large commercial diagnostic knowledge-based system. The description covers the procedure employed to carry out this task, as well as the heuristic technique used for generating the representative set of test cases.

96/03117 - A diagnostic expert system for heat pumps

96/03117 - A diagnostic expert system for heat pumps

An expert diagnostic system based on neural networks and image analysis techniques in the field of automated cytogenetics

In this study, we introduce an expert system for intelligent chromosome recognition and classification based on artificial neural networks (ANN) and features obtained by automated image analysis techniques. A microscope equipped with a CCTV camera, integrated with an IBM-PC compatible computer environment including a frame grabber, is used for image data acquisition. Features of the chromosomes are obtained directly from the digital chromosome images. Two new algorithms for automated object detection and object skeletonizing constitute the basis of the feature extraction phase which constructs the components of the input vector to the ANN part of the system. This first version of our intelligent diagnostic system uses a trained unsupervised neural network structure and an original rule-based classification algorithm to find a karyotyped form of randomly distributed chromosomes over a complete metaphase. We investigate the effects of network parameters on the classification performance and discuss the adaptability and flexibility of the neural system in order to reach a structure giving an output including information about both structural and numerical abnormalities. Moreover, the classification performances of neural and rule-based system are compared for each class of chromosome.

A diagnostic expert system for heat pumps

A computer model has been developed and validated using extensive data for air-air, water-water, and water-air heat pumps with enhanced surface-tubing heat exchangers. Good agreement between numerical and experimental results was observed. Based on numerical data obtained from the computer model, diagnostic rules were established using the NEXPERT system to identify system malfunctions. Simulations in different tests permit verification of system accuracy.

High-Resolution Random Mesh Algorithms for Creating a Probabilistic 3D Surface Atlas of the Human Brain

Striking variations exist, across individuals, in the internal and external geometry of the brain. Such normal variations in the size, orientation, topology, and geometric complexity of cortical and subcortical structures have complicated the problem of quantifying deviations from normal anatomy and of developing standardized neuroanatomical atlases. This paper describes the design, implementation, and results of a technique for creating a three-dimensional (3D) probabilistic surface atlas of the human brain. We have developed, implemented, and tested a new 3D statistical method for assessing structural variations in a database of anatomic images. The algorithm enables the internal surface anatomy of new subjects to be analyzed at an extremely local level. The goal was to quantify subtle and distributed patterns of deviation from normal anatomy by automatically generating detailed probability maps of the anatomy of new subjects. Connected systems of parametric meshes were used to model the internal course of the following structures in both hemispheres: the parieto-occipital sulcus, the anterior and posterior rami of the calcarine sulcus, the cingulate and marginal sulci, and the supracallosal sulcus. These sulci penetrate sufficiently deeply into the brain to introduce an obvious topological decomposition of its volume architecture. A family of surface maps was constructed, encoding statistical properties of local anatomical variation within individual sulci. A probability space of random transformations, based on the theory of Gaussian random fields, was developed to reflect the observed variability in stereotaxic space of the connected system of anatomic surfaces. A complete system of probability density functions was computed, yielding confidence limits on surface variation. The ultimate goal of brain mapping is to provide a framework for integrating functional and anatomical data across many subjects and modalities. This task requires precise quantitative knowledge of the variations in geometry and location of intracerebral structures and critical functional interfaces. The surface mapping and probabilistic techniques presented here provide a basis for the generation of anatomical templates and expert diagnostic systems which retain quantitative information on intersubject variations in brain architecture.

Medical expert system "Doctor"

To build a medical diagnostic expert system (ES), we considered the general decision-making procedure in medicine based on the operation of certain knowledge. This knowledge is taken from various fields of medicine and can formally be presented in the form of a database, knowledge base and decision-making rules.

Case-Based Reasoning in diagnostic expert systems

Case-Based Reasoning in diagnostic expert systems

Technology and tank maintenance: An AI-based diagnostic system for the Abrams tank

The U.S. Army holds title to one of the most envied weapon systems developed—the Abrams main battle tank (MBT). Militarily, this weapon represents the epitome of lethality and survivability on today's modern battlefield. To combat difficulties associated with maintaining this sophisticated weapon, the U.S. Army Research Laboratory (ARL) and the U.S. Army Ordnance Center and School (OC&S) combined technologies from artificial intelligence with Army tank maintenance doctrine to develop an expert diagnostic system to assist Abrams' mechanics. The system, known as turbine engine diagnostics (TED), targets the mechanic's ability to effectively and efficiently diagnose and repair the Abram's engine and transmission. The OC&S estimates that TED will save over $8 million annually by enhancing the Abrams mechanic's troubleshooting capabilities. Limited fielding of TED began in July 1994 to 60 National Guard units in 30 states. Active units of the U.S. Army will receive TED in fiscal year 1996. This paper examines the relevant background, development issues, system overview, test results, and future efforts surrounding the TED project.

The development of a real-time emergency advisory system for batch reactors

Each year a number of runaway incidents occur in batch/semi-batch chemical reactors. This number may be reduced by applying various strategies. One approach is the use of a diagnostic expert system. This can act as an advisor to plant operators following the initial indications of process deviations. It may also provide the possibility of partial control to return the plant to normal, desirable operation and/or to aid automatic shutdown. The feasibility of using an expert system shell “COGSYS”, which has real time capabilities, together with a knowledge base derived from case histories, hazop and fault-tree analysis, provides such a diagnostic tool and has been used to investigate the manufacture of Phenol-Formaldehyde resin.

Evaluating Four Diagnostic Methods with Acute Abdominal Pain Cases

Contemporary work in medical decision support is characterized by a multitude of methods. To investigate their relative strengths and weaknesses, we built four diagnostic expert systems based on different methods (Bayes, case-based classification, heuristic classification) for analysis of the same set of 1254 cases of acute abdominal pain previously documented in a prospective multicenter study. The results of the comparative evaluation indicate that differences in overall performance are relatively small (statistically not significant). The performance depends more on the quality of the knowledge base and the case data than on the inference methods of the expert systems. Methods relying exclusively on empirical knowledge (Bayes, case-based classification) tend to have slightly higher overall performance scores due to a diagnostic bias toward ordinary and common diseases. By contrast, methods operating with expert knowledge (e.g., heuristic classification) perform slightly worse overall, but are more sensitive toward uncommon (serious) diseases.

Diagnostic expert systems for defects in forged parts

This paper describes the development of a diagnostic expert system that identifies the cause of various manufacturing defects in hot forging and suggests remedies. The patterns of defect generation are various and due to many possible causes. They depend on part designs, tool designs and process conditions. Pertinent factors include part shape, the state of lubrication, location of the performed workpiece on the die and formability of the materials. This paper utilizs the theory of conditional probability to construct a diagnostic expert system that can adapt and learn its diagnostic mechanism through field data. A demonstration program, FORDIA, runs in HyperCard. FORDIA takes the part defect symptoms, uses conditional probability theory to identify possible causes and suggests remedies.

Expert and knowledge-based systems in failure analysis

All areas of industry are affected by premature failure of components which must be investigated so as to avoid future repetition. However, the complexity of the interrelations between design stress and environment often makes this a daunting task, except for the engineer with considerable knowledge or experience in failure analysis. Modern developments in information technology should allow this task to be made easier by storing and subsequently accruing this “experience” by using expert and knowledge-based systems. The application of these systems to the task of failure analysis, and design against failure, is reviewed, particular emphasis being placed on the reasoning methodologies used and the knowledge domains for which these methodologies are appropriate. Case-based reasoning techniques are considered to be the most suitable for generic failure analysis due to the complexity of knowledge required. It is concluded that future trends in diagnostic expert systems will be based on the holistic hybrid rule-case-based reasoning approach combined with a number of stand-alone engineering failure analysis calculating software tools, and a multimedia-type knowledge-based system for different failure modes.

The Impact of Explanation Facilities on User Acceptance of Expert Systems Advice

Providing explanations for recommended actions is deemed one of the most important capabilities of expert systems (ES). There is little empirical evidence, however, that explanation facilities indeed influence user confidence in, and acceptance of, ES-based decisions and recommendations. This paper investigates the impact of ES explanations on changes in user beliefs toward ES-generated conclusions. Grounded on a theoretical model of argument, three alternative types of ES explanations A trace, justification, and strategy A were provided in a simulated diagnostic expert system performing auditing tasks. Twenty practicing auditors evaluated the outputs of the system in a laboratory setting. The results indicate that explanation facilities can make ES-generated advice more acceptable to users and that justification is the most effective type of explanation to bring about changes in user attitudes toward the system. These findings are expected to be generalizable to application domains that exhibit similar characteristics to those of auditing: domains in which decision making tends to be judgmental and yet highly consequential, and the correctness or validity of such decisions cannot be readily verified.