Ming Rao

Adaptive fading Kalman filter with an application

Abstract A new adaptive state estimation algorithm, namely adaptive fading Kalman filter (AFKF), is proposed to solve the divergence problem of Kalman filter. A criterion function is constructed to measure the optimality of Kalman filter. The forgetting factor in AFKF is adaptively adjusted by minimizing the defined criterion function using measured outputs. The algorithm remains convergent and tends to be optimal in the presence of model errors. It has been successfully applied to the headbox of a paper-making machine for state estimation.

An on-line wastewater quality predication system based on a time-delay neural network

Abstract The biological treatment process in a wastewater treatment system is a very complex process. The efficiency of the treatment is usually measured by laboratory tests, which typically take five days. In this paper, a time-delay neural network (TDNN) modeling method is proposed for predicting the treatment results. As the first step, a sensitivity analysis performed on a multi-layer perceptron (MLP) network model is used to reduce the input dimensions of the model. Then a TDNN model is further used to improve the performance of the original MLP network model. Subsequently, an on-line prediction and model-updating strategy is proposed and implemented. Simulations using industrial process data show that the prediction accuracy can be improved by the on-line model updating.

Dynamic case-based reasoning for process operation support systems

Abstract Modern process industry is faced with ever-increasing requirements for better quality, higher production profits, safer operation, and stringent environment regulation. New technologies are required to reduce the operators cognitive load and achieve more consistent operations. Operation support systems, which help operators in obtaining effective and timely decisions, have attracted much attention. The research described here intended to develop an efficient reasoning method for operation support systems. It is pointed out that case-based reasoning (CBR), which is based on the concept that human memory is episodic in nature, is consistent with operators problem solving. Despite their successful application to the solution of many problems, case-based reasoning methods are mostly static. Process operation support systems require a CBR method that can represent system dynamics and fault-propagation phenomena. To solve this problem, a new approach, namely dynamic case-based reasoning (DCBR), is developed. DCBR introduces a number of new mechanisms including time-tagged indexes, dynamic and composite features, and multiple indexing paths. As a result, it provides flexible case adaptation, timely and accurate problem solving, and an ability to incorporate other computational and reasoning methods.

Intelligent systems for conceptual design of mechanical products

Development of industrial techniques is closely related to the application of computers in engineering design, integrated computer-aided design (ICAD) technology has evolved as a new generation of design techniques. It also paved the way for implementing computer-integrated manufacturing (CIM). However, the key issue to accomplish the objective is conceptual design automation (Wang et al., 1990).

Soft sensors for quality prediction in batch chemical pulping processes

The characteristics, functions and configuration of a soft sensor are discussed. An intelligent soft sensor (ISS) for batch digester quality control is presented. The sensor can support a batch sulphite pulping process operation and assist operators to perform better operation by providing the estimated kappa number and the cooking time, as well as interpretation of the process operation variables. It can also be used to facilitate online supervisory control, to detect unexpected events and faults during pulping process operation.<<ETX>>

An Intelligent design environment for conceptual process design

Abstract Conceptual process design is a multiagent, distributed problem-solving activity that can be significantly enhanced with the aid of several individual intelligent ssytems. It is quite difficult to develop such intelligent systems on the basis of existing expert-system shells because of the complexity of conceptual process design. In this paper, the characteristics and requirements of conceptual process design are first analyzed, and then an intelligent design environment (Meta-COOP) for conceptual process design is presented. Meta-COOP is based on object-oriented programming (OOP) techniques and coded in C ++ . This environment provides such distinct features as the integration of various knowledge-representation and inference methods, and deals with multimedia information. An intelligent system for the conceptual design of heat exchanger networks (IDIS-CDHEN) provides an application of this intelligent design environment, and a demonstration of its methodology.

Intelligent system for safe process startup

Abstract An intelligent system has been developed to assist the process startup in a section of a refinery. The system was developed in conjunction with an industrial partner. This intelligent system codifies the knowledge from industrial process operators who have many years of experience. The project aims at investigating automation of the process startup operation by using an integrated distributed intelligent system concept, as well as capturing important expertise and knowledge from experienced operators. Testing and utilizing the intelligent system within the plant indicates that the system can provide operational advice at the level of human experts. Another element in its success is the automation of “look-up” functions in the written manual. Hypertext is used to provide rapid and efficient access to the manual. The hypertext system is integrated with the knowledge base to provide an intelligent selection of appropriate manual sections. An important result of this research is the development of a new conceptual process model, which represents the chemical and mechanical states of the unit for startup. The model is characterized by the mechanical states, modified by the operators, to manipulate the chemical states. Then, the chemical states are driven towards the goal states: the normal operation of the unit. This methodology provides a new approach to improving the industrial manufacturing environment using AI technology.

Fault-tolerant control of paper machine headboxes

Abstract This paper presents a model-based fault detection and fault-tolerant control technique for the pressurized headbox of a paper machine. A bank of Kalman filters is constructed corresponding to all the possible sensor failure modes. The possibility that each failure mode hypothesis is true is calculated using measurement innovation processes. The sensor failures are detected and located based on the calculated possibilities of the hypotheses. The controller and state estimator are automatically reorganized subsequent to the occurrence of failures to ensure the stability and good performance of the closed-loop system. The issues of system hardware redundancy and computational burden as well as implemental complexity are taken into account in the system design. Simulation results have shown satisfactory performance of the headbox control system after applying the presented technique.

New progress on integrated environment for intelligent manufacturing automation

A methodology is proposed for advanced automation in manufacturing. Building on top of the current CAD/CAM techniques and expert system methods, integrated intelligent systems can realize decision-making automation based on a knowledge processing technique to meet the challenge of the upcoming knowledge-intensive industry. The parallel hierarchical structure of integrated intelligent software systems is developed, and an architecture of the integrated intelligent unit for controlling and managing large-scale intelligent systems is investigated. In an integrated intelligent system, the different expert systems and numerical computation routines are coordinated by a metasystem. These expert systems and numerical routines are written in different languages or programming tools, and used separately. In this way, it is possible to easily add new programs and reduce the scope of rule search to enhance efficiency.<<ETX>>

Intelligennt systems approach to conceptual design

In mechanical system design, the Integrated Computer Aided Design (ICAD) technology has evolved into a new generation of design techniques. It also paves the way for implementing Computer Integrated Manufacturing (CIM) systems. However, the key issue to accomplish the objective in ICAD is the conceptual design automation. Conceptual design is a creative activity and an important decision making during overall product design to reduce energy consumption, to increase raw materials utilization, to obtain more profits, to reduce environmental effects of effluents, and to ensure flexibility, operability, controllability, and safety of manufacturing processes. Therefore, the quality of conceptual design determines the final quality of products and profit of plants. In this article, we first introduce the fundamentals and characteristics of conceptual design. Then, a general problem‐solving strategy and methodology to implement conceptual design automation are proposed. an Integrated Distributed Intelligent Design Environment (IDIDE) for developing conceptual design expert systems is presented. Fundamental principles, system organization, and implementation techniques are discussed. Finally, an application case for wheel loader design is studied.