Esko Juuso

Integration of intelligent systems in development of smart adaptive systems

Different combinations of fuzzy logic and neural networks provide various ingredients for smart adaptive applications. Both expertise and data can be integrated in the development of intelligent systems. Evolutionary computation is also widely used in tuning of these systems. For small, specialised systems there is a large number of feasible solutions, but developing truly adaptive, and still understandable, systems for highly complex systems require more compact approaches in the basic level. Linguistic equation (LE) approach originating from fuzzy logic is an efficient technique for these problems. Insight to the process operation is maintained since all the modules can be assessed by expert knowledge and membership definitions relate measurements to appropriate operating areas. The LE approach increases the performance by combining various specialised models in a case-based approach: models can be generated automatically from data. The LE approach is also successfully extended to dynamic simulation and used in intelligent controller design. The integration of intelligent systems is based on understanding the different tasks of smart adaptive systems: modelling, intelligent analysers, detection of operating conditions, control and intelligent actuators. The system integration leads to a hybrid system: fuzzy set systems move gradually to higher levels, neural networks and evolutionary computing are used for tuning, and the whole system reinforced with efficient statistical analysis, signal processing and mechanistic modelling and simulation.

Fuzzy Control in Process Industry: The Linguistic Equation Approach

The process industries face considerable control challenges, especially in the consistent production of high quality products, more efficient use of energy and raw materials, and stable operation on different conditions. The processes are nonlinear, complex, multivariable and highly interactive. Usually, the important quality variables can be estimated only from other measured variables. Constraints, e.g. physical limitations of actuators must be taken into account. Significant interactions between process variables cause interactions between the controllers. Various time-delays depend strongly on operating conditions and can dramatically limit the performance and even destabilize the closed loop system. Uncertainty is an unavoidable part of the process control in real world applications.

Intelligent control of a rotary kiln fired with producer gas generated from biomass

Abstract During the past decade, the academic world has been extremely active in developing new algorithms and theories in the field of artificial intelligence (AI) and intelligent systems. In most cases, however, emphasis has been placed more on theoretical frameworks and mathematical bases than on what the individual AI techniques could offer and on how different techniques could be applied to solve real industrial-scale problems. The reputation of intelligent systems has consequently suffered from an inability to transfer new and sophisticated techniques to industrial applications with identifiable benefits. As a result, although a wide range of intelligent control techniques has been available already for many years, most of the applications in the process industry are based on more conventional techniques. Recently, as awareness of intelligent systems has grown, industrial problems and implementations have fortunately received increasing attention. In this paper, an intelligent supervisory-level system implemented at one of the major Finnish pulp mills to control a lime kiln fired with producer gas generated from biomass is presented. First, the major results of a field study are summarised, with special attention paid to burnt lime quality aspects. Next, a novel linguistic equations approach, which provides flexible methods for both modelling and control, is briefly described. The overall structure and main functions of the developed control system are then described with the main emphasis on the control of temperature and lime quality. Finally, the results obtained during the extended testing period of the system are presented and discussed.

Real-time optical monitoring of the wastewater treatment process

One activated sludge process line was optically monitored in situ by a novel image analysis equipment. The results of the image analysis were studied to find out dependencies to the process variables of the wastewater treatment plant (WWTP) and to the quality of the treated wastewater. The quality parameter of the treated wastewater, suspended solids, was modelled using the image analysis results. The model can be used for evaluating the performance of the WWTP and for the better control for stable effluent quality. It was shown that the results of the online optical monitoring reveal useful information from the process and can be used in forecasting the quality of biologically treated wastewater. The optical monitoring method together with process measurements has an important role in keeping the process in stable operating conditions and avoiding environmental risks.

Tuning of large-scale linguistic equation (LE) models with genetic algorithms

Evolutionary computing is widely used to tune intelligent systems which incorporate expert knowledge with data. The linguistic equation (LE) approach is an efficient technique for developing truly adaptive, yet understandable, systems for highly complex applications. Process insight is maintained, while data-driven tuning relates the measurements to the operating areas. Genetic algorithms are well suited for LE models based on nonlinear scaling and linear interactions. New parameter definitions have been developed for the scaling functions to handle efficiently the parameter constraints of the monotonously increasing second order polynomials. While identification approaches are used to define the model structures of the dynamic models. Cascade models, effective delays and working point models are also represented with LE models, i.e. the whole system is configured with a set of parameters. Results show that the efficiency of the systems improves considerably after the implementation of simultaneous tuning of all parameters.

Adaptive Expert Systems for Metallurgical Processes

Abstract Expert systems are developed for the multilayer simulation system in order to improve the application facilities. The combined system contains procedures for developing simplified fuzzy models on the basis of deterministic simulation experiments. Since these models, together with rule-based linguistic models, are embedded in the expert systems, there are a total of five levels of simulation. The linguistic models developed from the fuzzy models are used together with qualitative relations to define suitable meaning for each linguistic variable. The knowledge base of the expert system is represented by linguistic relations which can be changed into matrix equations. The reasoning is based on these matrix equations or on the aggregated sets of linguistic relations which are obtained by solving the equations. Only forward chaining is needed in approximate reasoning because all the variables can be handled in the same way. The system is adaptive since the meaning of the linguistic values depends on the working point of the process.

Intelligent Trend Indices in Detecting Changes of Operating Conditions

Temporal reasoning is a very valuable tool to diagnose and control slow processes. Identified trends are also used in data compression and fault diagnosis. Although humans are very good at visually detecting such patterns, for control system software it is a difficult problem including trend extraction and similarity analysis. In this paper, an intelligent trend index is developed from scaled measurements. The scaling is based on monotonously increasing, nonlinear functions, which are generated with generalised norms and moments. The monotonous increase is ensured with constraint handling. Triangular episodes are classified with the trend index and the derivative of it. Severity of the situations is evaluated by a deviation index which takes into account the scaled values of the measurements.

Recursive Tuning of Intelligent Controllers of Solar Collector Fields in Changing Operating Conditions

Abstract Solar power plants should be designed to collect all the available thermal energy in a usable form within a desired temperature range. In cloudy conditions, the collector field is maintained in a standby mode ready for full-scale operation when the intensity of the sunlight rises again. Control is achieved by means of varying the flow of oil pumped through the pipes during the plant operation. The multilevel control system consists of a nonlinear linguistic equation (LE) controller with predefined adaptation models, some smart features for avoiding difficult operating conditions, and a cascade controller for obtaining smooth operation. The whole system can be tuned recursively with specialised dynamic LE models developed with generalised norms and moments. The parameters of the dynamic models and the controllers are closely connected. Harmful operating conditions are avoided. Fast start-up and efficient energy collection in variable operating condition extend considerably the operating time of the collector field.

Intelligent performance measures for condition‐based maintenance

Purpose – The purpose of this paper is to develop a comprehensive approach to efficiently integrate maintenance and operation by combining process and condition monitoring data with performance measures.Design/methodology/approach – Intelligent stress, condition and health indicators have been developed for control and condition monitoring by combining generalised moments and norms with efficient nonlinear scaling. The data analysis resulting nonlinear scaling functions can also be used to handle performance measures used for management. The generalised norms provide limits for an advanced statistical process control.Findings – The data‐driven analysis methodology demonstrates that management‐oriented indicators can be presented in the same scale as intelligent condition and stress indices. Control, condition monitoring, maintenance and performance monitoring are represented as interactive feedback loops.Practical implications – Performance analysis can be based on real‐time information by using various s...

Knowledge-based linguistic equations for defect detection through functional testing of printed circuit boards

Increasing globalization of the economy is imposing tough challenges to manufacturing companies. The ability to produce highly customized products, in order to satisfy market niches, requires the introduction of new features in automation systems. Flexible manufacturing processes must be able to handle unforeseen events, but their complexity makes the supervision and maintenance task difficult to perform by human operators. This paper describes how linguistic equations (LE), an intelligent method derived from Fuzzy Algorithms, has been used in a decision-helping tool for electronic manufacturing. In our case the company involved in the project is mainly producing control cards for the automotive industry. In their business, nearly 70% of the cost of a product is material cost. Detecting defects and repairing the printed circuit boards is therefore a necessity. With an ever increasing complexity of the products, defects are very likely to occur, no matter how much attention is put into their prevention. Therefore, the system described in this paper comes into use only during the final testing of the product and is purely oriented towards the detection and localization of defects. Final control is based on functional testing. Using linguistic equations and expert knowledge, the system is able to analyze that data and successfully detect and trace a defect in a small area of the printed circuit board. If sufficient amount of data is provided, self-tuning and self-learning methods can be used. Diagnosis effectiveness can therefore be improved from detection of a functional area towards component level analysis.