The application of expert systems to process control

In the new stage for intelligent manufacturing of traditional Chinese medicine(TCM) from pilot demonstration to in-depth application and comprehensive promotion, how to raise the degree of intelligence for the process quality control system has become the bottleneck of the development of TCM production process control technology. This article has sorted out 226 TCM intelligent manufacturing projects that have been approved by the national and provincial governments since the implementation of the "Made in China 2025" plan and 145 related pharmaceutical enterprises. Then, the patents applied by these pharmaceutical enterprises were thoroughly retrieved, and 135 patents in terms of intelligent quality control technology in the production process were found. The technical details about intelligent quality control at both the unit levels such as cultivation, processing of crude herbs, preparation pretreatment, pharmaceutical preparations, and the production workshop level were reviewed from three aspects, i.e., intelligent quality sensing, intelligent process cognition, and intelligent process control. The results showed that intelligent quality control technologies have been preliminarily applied to the whole process of TCM production. The intelligence control of the extraction and concentration processes and the intelligent sensing of critical quality attributes are currently the focus of pharmaceutical enterprises. However, there is a lack of process cognitive patent technology for the TCM manufacturing process, which fails to meet the requirements of closed-loop integration of intelligent sensing and intelligent control technologies. It is suggested that in the future, with the help of artificial intelligence and machine learning methods, the process cognitive bottleneck of TCM production can be overcome, and the holistic quality formation mechanisms of TCM products can be elucidated. Moreover, key technologies for system integration and intelligent equipment are expected to be innovated and accelerated to enhance the quality uniformity and manufacturing reliability of TCM.

An alternative technique for developing intelligent process monitoring and control systems is expert systems (ESs). ESs use logic rules to carry out heuristic reasoning. Knowledge used to reach a conclusion is transparent because ESs have explanation capabilities. In this respect, ESs are superior to neural networks because the knowledge embedded in neural networks is opaque. It has long been recognised that a critical issue in developing knowledge based ESs is the bottleneck of knowledge acquisition. Traditionally knowledge acquisition has been dependent on consulting domain experts. A disadvantage of this approach is that experts are usually better in collecting and archiving cases than in expressing the experience and cases explicitly into production rules. There are more difficulties in compiling knowledge about process operations due to the large number of interacting variables.

With ever increased needs for an improved product quality, production efficiency, and cost in today's globalized world market, advanced process control should not only realize the accuracy of each control loops, but also has the ability to achieve an optimization control of global production indices that are closely related to the improved product quality, enhanced production efficiency and reduced consumption. As a result, the optimal control for the global production indices has attracted an increased attention of various process industries. The optimal control of the global production indices requires an optimal combination of the production indices, technical indices and the operation of each control loops. In this paper, a hybrid intelligent control strategy is proposed for process industries. This new strategy consists of three control layers, namely the intelligent optimization of the global production indices, the intelligent optimal control of the technical indices and the intelligent process control. The intelligent optimization of the global production indices is composed of the setting model of the technical indices, the predictor of the global production indices, the feedback and prediction analysis adjustment models. The intelligent optimal control of the technique indices consists of the setpoints model of control loops, the prediction of technical indices, the feedback and feedfoword regulators. The intelligent process control is then composed of normal decoupled PID controllers, decoupled nonlinear PID controllers with a neural network feedforword compersator for un-modeled dynamics and a switching mechanism.

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

In the construction and development of modern society, the traditional artificial production line operation mode, has been unable to meet the needs of enterprise development, research scholars in the study of the Internet of things as the core of the intelligent production line process control system. The whole system design not only references a lot of advanced technology theory, but also has remote control and automatic assembly and other unique functions. On the basis of understanding the theory of Internet of Things technology, this paper mainly discusses the components of intelligent production line process control system, combined with practical cases to study the system application effect. The final results show that the internal functions of the system are in line with the current production and transportation needs of enterprises, and can solve the problems existing in the traditional production line process control.

Artificial intelligence and cognitive science must look at the world of industrial-process control to find the technological reifications of the concept of mind.

Recent literature has focused on the reduction of laboratory errors and the potential impact on patient management. This study assessed the intelligent, automated preanalytical process-control abilities in newer generation analyzers as compared with older analyzers and the impact on error reduction. Three generations of immuno-chemistry analyzers were challenged with pooled human serum samples for a 3-week period. One of the three analyzers had an intelligent process of fluidics checks, including bubble detection. Bubbles can cause erroneous results due to incomplete sample aspiration. This variable was chosen because it is the most easily controlled sample defect that can be introduced. Traditionally, lab technicians have had to visually inspect each sample for the presence of bubbles. This is time consuming and introduces the possibility of human error. Instruments with bubble detection may be able to eliminate the human factor and reduce errors associated with the presence of bubbles. Specific samples were vortexed daily to introduce a visible quantity of bubbles, then immediately placed in the daily run. Errors were defined as a reported result greater than three standard deviations below the mean and associated with incomplete sample aspiration of the analyte of the individual analyzer Three standard deviations represented the target limits of proficiency testing. The results of the assays were examined for accuracy and precision. Efficiency, measured as process throughput, was also measured to associate a cost factor and potential impact of the error detection on the overall process. The analyzer performance stratified according to their level of internal process control The older analyzers without bubble detection reported 23 erred results. The newest analyzer with bubble detection reported one specimen incorrectly. The precision and accuracy of the nonvortexed specimens were excellent and acceptable for all three analyzers. No errors were found in the nonvortexed specimens. There were no significant differences in overall process time for any of the analyzers when tests were arranged in an optimal configuration. The analyzer with advanced fluidic intelligence demostrated the greatest ability to appropriately deal with an incomplete aspiration by not processing and reporting a result for the sample. This study suggests that preanalytical process-control capabilities could reduce errors. By association, it implies that similar intelligent process controls could favorably impact the error rate and, in the case of this instrument, do it without negatively impacting process throughput. Other improvements may be realized as a result of having an intelligent error-detection process including further reduction in misreported results, fewer repeats, less operator intervention, and less reagent waste.

As we all know, big data and intelligent computing have been widely used in information science, life science, computer science and intelligent control, intelligent robots, vehicle networking, space technology, marine development and other fields, especially in the future life science and medical field. This paper is based on a new digital optimal decision-making idea of intelligent signal processing and control. On the basis of extending non-digital signal processing and information prediction to signal processing and information prediction in the digital generalized information measurement space, and making full use of optimization algorithms such as digital filtering and frequency spectrum analysis, this article discusses in depth the intelligent optimal control of a class of non-stationary random processes in artificial intelligence, biomedicine, radio communication, automatic control and other scientific and technological fields. It provides a new theory, a new approach and an effective and reliable new method for the mathematical modeling and optimal control of such processes, and has broad application prospects and value.

Abstract: The First Symposium on The Theory and Application of Expert Systems in Emergency Management, held at the Department of Commerce, Washington, D.C. (April 24 and 25, 1985) was funded by the Federal Emergency Management Agency and organized by the National Bureau of Standards' Operations Research Division. The purpose of the symposium was to bring together researchers in expert systems, artificial intelligence, and emergency operations in a forum to review the concepts of expert systems and the problems of emergency management, with the objective of determining how expert systems can be used to augment the experience of local, State and Federal emergency managers faced with the difficult tasks of determining the best response to an emergency situation. Speakers addressed the following areas: The theory and uncertainty aspects of expert systems, artificial intelligence's future role in emergency management, technology for building and using expert systems, emergency management decisions and information needs and uses, applications of expert systems in the management of chemical spills and shipboard and coal mine fires, and the role and use of simulation in emergency management expert systems.

Expert System Approach of Industrial Process Adaptive Control

The application of a supervisory knowledge-based system (KBS) to provide robust multivariable control of a chemical reaction process with reduced conservatism is examined. The supervisory KBS is capable of monitoring the process to detect process and control system faults or deteriorating control system performance due to changes in the process behavior or operating conditions. If a fault or change in performance is detected, the KBS formulates and implements the necessary corrective action. Control loop tuning is emphasized. The underlying mechanisms are discussed and validation results, using a rigorous simulation of the chemical reactor process, are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

8 - Real-time fault-tolerant control systems

Automatic detonator code recognition via deep neural network

The increasing of wafer size from 200mm to 300mm and downscaling of IC design rule has imposed increasingly tighter overlay tolerances, which becomes very challenging at the 100 nm lithographic node. Such tight tolerances will require very high performance in alignment and overlay measurement. In this paper, we present a concept of total process control of alignment and overlay, which we had used to get deeper understanding of our metal process with W-CMP and aluminum sputter. Traditionally, a lot of works are focusing on alignment process control and overlay process control separately. However, based on what we had observed, the final overlay performance is largely affected by the difference between alignment system (alignment mark, alignment sensor and process) and overlay system (overlay mark, overlay sensor and process). Deeper understanding of this difference between alignment and overlay system do help us to get better overlay process control o and process/tool matching.

The authors review and categorize the research in applications of artificial intelligence (AI) and expert systems (ES) in new product development (NPD) activities. A brief overview of NPD process and AI is presented. This is followed by a literature survey in regard to AI and ES applications in NPD, which revealed twenty four articles (twenty two applications) in the 1990–1997 period. The applications are categorized into five areas: expert decision support systems for NPD project evaluation, knowledge-based systems (KBS) for product and process design, KBS for QFD, AI support for conceptual design and AI support for group decision making in concurrent engineering. Brief review of each application is provided. The articles are also grouped by NPD stages and seven NPD core elements (competencies and abilities). Further research areas are pointed out.