Expert systems in anesthesiology.

The traditional fault diagnosis expert system is dependent on knowledge acquisition of the experts. Knowledge acquisition is recognized as the problem of expert system. In addition, there are also some limitations of adaptive capacity, learning ability and real-time. And artificial neural network with good fault-tolerance and associative memory function, as well as very strong self-adaptive, self-learning ability, just can make up for the limitations of traditional expert system. This paper will construct a new expert system with the artificial neural network into and fault tree. Besides fault tree and neural network, this article mainly introduces the system model of fault diagnosis of the fire control computer and sensor subsystem, the method and process of fault diagnosis. In this expert system, we use the object-oriented production rule to represent the knowledge, which solves the bottleneck problem of the diagnostic knowledge acquisition effectively. The inferential process begins with the abnormal event and finally finds all of the possible faults and the faulty component. For some possible faulty components, which have large number of fault samples, the neural network model can be used to diagnose. The training network of fault samples employs the BP neural network. Finally, simulation training results show that the fault diagnosis expert system based on the combination of fault tree and neural network is rational and effective in fault diagnosis of the fire control system, realizes perfectly the combination of new knowledge and old one, and can grasp the state of systems dynamically.

For a complicated system based on high technology, once a part breaks down, the entire system can not work normally. Moreover, due to the complexity of its structure and fault causes, the fault diagnosis of the system is also complex and indeterminate, a single test equipment can hardly finish a difficult diagnose task, and fault diagnosis expert system can resolve these problems effectively. The traditional diagnose expert systems have many problems such as the bottleneck of knowledge acquisition, the fragility of knowledge, the pool ability of self-study, the inefficient reasoning, and the monotonicity of reasoning, so there are certain limitations. But the artifical neural networks technology is a new system, it is an mathematical model that applies the structure like the joint of synapses in hypothalamic neurons, which has the strong ability to study, and can learn from samples, obtain knowledge, store it in the network in the form of weight and threshold, and it is easy to implement the parallel processing, has the character of association memory, own the better robust. it ability of adaptive self-study is manifested mainly in adjusting the weight of network according to the change of enviroment by learning algorithms, so as to adapt to the environmental change. But the neural network can not explain its own reasoning. Therefore we will apply the neural network to the expert knowledge system, which can make them learn each other's good points mutually for common progress, constructing the new neural network expert system. The system is applied to the power fault diagnosis, achieving good results.

With the use of fuzzy logic techniques, neural computing can be integrated in symbolic reasoning to solve complex real world problems. In fact, artificial neural networks, expert systems, and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A model of Fuzzy Connectionist Expert System is introduced, in which an artificial neural network is designed to construct the knowledge base of an expert system from, training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the synaptic connections in an AND-OR structure: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through min-max fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feedforward network is described and first illustrated in a biomedical application (medical diagnosis assistance from inflammatory-syndromes/proteins profiles). Then, it is shown how this methodology can be utilized for handwritten pattern recognition (characters play the role of diagnoses): in a fuzzy neuron describing a number for example, the linguistic weights represent fuzzy sets on cross-detecting lines and the numerical weights reflect the importance (or weakness) of connections between cross-detecting lines and characters.

It is an urgent task to implement a lot of expert systems to capture the valuable expertise of experienced doctors of traditional Chinese medicine. In order to meet the needs, a software tool is developed. It features a unified diagnosis model, a specially designed knowledge representation language and an efficient but effective inference engine. To implement an expert system, it is only necessary to input the expert’s knowledge expressed in knowledge representation language without the design of any additional software. The time and effort required for implementing an expert system are thus greatly saved. The software is very compact and can run on microcomputers e.g. IBM-PC/XT. Two traditional Chinese medical expert systems have been successfully implemented with the tool.

Bare-bones languages serve small systems with ease: Cushmann, R HEDN Vol 25 No 16 (5 September 1980) pp 171–177

Due to the complex structure and massive volume of large equipment in petrochemical enterprises, it was very difficult to carry out inspection and maintenance work. The traditional expert system used a single knowledge base and reasoning machine, so the processing efficiency and prediction accuracy were low. In this paper, the dimensionality reduction which is used to process a large amount of physical information collected by the sensors, remove redundant components and extract main characteristic parameters. Meanwhile, combined with the powerful pattern recognition and judgment ability of fuzzy neural network, the forward reasoning mechanism and error back propagation keeping continuous training correction until meeting the accuracy requirements, the expert system gave the equipment fault prediction conclusion. Finally, taking main fan oil station circulating oil pump and motor of heavy oil catalytic cracking unit and nine stages of bearing damage as monitoring objects, the fault predictions was implemented by the following steps: data collection, feature extraction, dimension reduction of big data and expert system with the fusion of fuzzy neural network, and it is proved that the expert system with fuzzy neural network based on dimension reduction can greatly improve the convergence speed.

This work focuses on the construction of an expert system shell for airborne equipment design. Traditional expert systems are constructed using a single monolithic software program for a specific application. Since the airborne equipment design is critical & complex, it demands the use of expert system technology. Since present aircrafts take in different equipments for different purposes, it is not feasible to think in terms of independently developed monolithic expert system program for each equipment. To overcome these problems, we have designed and developed a complex competent system i.e., a generic component based expert system for airborne equipment design. The main advantage of the component-based approach is that, the knowledge base is not hard coded and these components can be coupled with any domain-specific knowledge bases. The expert system with its expertise knowledge is made to guide the designer by providing design guidelines & testing procedures for the desired equipment. The expert system also audits the design and provides guidelines to modify & to improve the design.

The expert neural network system the author has developed for use in DNA sequence analysis combines a traditional symbolic expert system with an artificial neural network. The resulting hybrid system can accurately model underlying domain knowledge to improve accuracy, generalization performance, and information-processing speed.

Development of a data acquisition sub-system using DAQ-Middleware

Several applications need to stock and interrogate fuzzy data in a flexible manner. Unfortunately, these two requirements are not supported by the database management systems which currently dominate the databases servers market. Several works have tried to cure these insufficiencies; we speak henceforth of fuzzy databases and flexible querying of these databases. The design problem of such databases did not receive the interest that it deserves. The fuzzy data types are numerous and varied what puts the designer of a fuzzy database in front of a complex problem of choice. In this paper, we propose an approach based on an expert system which helps the designer to choose the appropriate data types for the columns susceptible to stock fuzzy data or interrogated by flexible queries. This solution suits the migration toward a fuzzy database as well as a fuzzy database under design. Although this solution is based on the fuzzy model GEFRED (GEneralised model for Fuzzy RElational Database), it can be applied to other fuzzy models. This expert system can be integrated into the classic design environments like Rational Rose, Power AMC, etc.

This paper investigates a fault diagnosis expert system base on artificial neural network (ANN-FD-ES) for mixed-signal circuits. We built this system by given a faulty circuit. Based on the transient response testing (TRT) on the mixed-signal circuits, both analog and digital signal characteristics are unified. The system includes knowledge base, reasoning machine, explanatory, and interface. The diagnostic portion of the system is based on neural-calculation approach, which is used to establish the knowledge base composed of the weigh values and threshold values. With this approach, conclusions are developed directly from the outputs of the net, rather than the domain knowledge in traditional expert system. Compared with the traditional expert system, this system is good at processing data. The experimental results show that the system not only improves the shortcoming of the traditional expert system such as the deficiency on knowledge acquisition and self-learning capability, but also achieves a satisfied fault diagnosis efficiency.

Neural networks and fuzzy logic in power electronics

The giant panda is an obligate bamboo grazer. Therefore, the availability and abundance of understorey bamboo determines the quantity and quality of panda habitat. However, there is little or no information about the spatial distribution or abundance of bamboo underneath the forest canopy, due to the limitations of traditional remote sensing classification techniques. In this paper, a new method combines an artificial neural network and a GIS expert system in order to map understorey bamboo in the Qinling Mountains of south‐western China. Results from leaf‐off ASTER imagery, using a neural network and an expert system, were evaluated for their suitability to quantify understorey bamboo. Three density classes of understorey bamboo were mapped, first using a neural network (overall accuracy 64.7%, Kappa 0.45) and then using an expert system (overall accuracy 62.1%, Kappa 0.43). However, when using the results of the neural network classification as input into the expert system, a significantly improved mapping accuracy was achieved with an overall accuracy of 73.8% and Kappa of 0.60 (average z‐value = 3.35, p = 0.001). Our study suggests that combining a neural network with an expert system makes it possible to successfully map the cover of understorey species such as bamboo in complex forested landscapes (e.g. coniferous‐dominated and dense canopy forests), and with higher accuracy than when using either a neural network or an expert system.

The secondary system of the intelligent substation has a complex logic structure and a variety of failure modes, making it difficult and time-consuming to locate the fault. Aiming at the shortcomings of traditional fault location methods, a fault tree-based positioning method is proposed. Fault tree analysis method can effectively react to fault alarms and the causal relationship between fault locations that cause them. The fault tree analysis method is applied to the expert system, which solves the problems of low efficiency, lack of knowledge and inaccurate reasoning results of the traditional rule-based expert system, and the logical relationship between knowledge is not reflected. Aiming at the difficulty of obtaining the probability of the event at the bottom of the fault tree, the fuzzy number method is proposed to improve the traditional fault tree method, and the triangular fuzzy number is used to express the fuzzy probability of the bottom events, thereby improving the efficiency of the fault maintenance and positioning of the maintenance personnel.

Iterative learning belief rule-base inference methodology using evidential reasoning for delayed coking unit