Adaptive terminal synergetic-backstepping technique based machine learning regression algorithm for MPPT control of PV systems under real climatic conditions

This paper deals with a comparative evaluation of nonlinear controllers based on the linear regression technique, which is a machine learning algorithm for maximum power point tracking. In the past decade, most photovoltaic systems have been equipped with classical algorithms such as perturb and observe, hill climbing, and incremental conductance. The simplicity of these techniques and their ease of implementation were seen as the main reasons for their utilization in photovoltaic systems. However, researchers' attention has recently been attracted by artificial intelligence-based techniques such as linear regression, which offer better performance within the bounds of the nonlinearity of photovoltaic system characteristics. An adaptive terminal synergetic backstepping controller is developed in this paper for a single-ended primary inductance converter. This control scheme is based on the combination of a non-singular terminal synergetic technique with an integral backstepping technique and equally a neural network for the approximation of unmeasured or inaccessible variables that guarantees the finite-time convergence. The proposed controller was further verified under virtual and real environmental conditions, and the numerical results obtained from Matlab/Simulink software under various test conditions, including load variations, show that the adaptive terminal synergetic backstepping controller gives satisfactory performance compared to the adaptive integral backstepping controller used in the same climatic conditions.

Fault diagnosis in an expert system for health services management in the tropics

An integrated large-scale expert system called Health-2000, for the management of health services in regions where tropical diseases are endemic, has been designed. This system combines knowledge and databases, the contents of which are operated upon by an inference engine, to produce usable information. The system allows a host of applications, ranging from medical diagnosis to fault detection and preventive maintenance of biomedical equipment. The theoretical background and approach used in the development of the fault diagnosis and equipment maintenance sub-system of Health-2000 is presented. Model-based knowledge acquisition, and an extension of the Failure Modes, Effects and Criticality Analysis are two methodologies applied to build its knowledge bases. The inference engine which supports backward and forward chaining, operates on numerical and non-numerical facts, and uses fuzzy logic to handle vague and uncertain knowledge. Fault isolation proceeds in a top-down fashion, from equipment sub-system, to modules and components.

Health-2000: an integrated large-scale expert system for the hospital of the future

Decision making and management are problems which plague health systems in developing countries, particularly in Sub-Saharan Africa where there is significant waste of resources. The need goes beyond national health management information systems, to tools required in daily micro-management of various components of the health system. This paper describes an integrated expert system, Health-2000, an information-oriented tool for acquiring, processing and disseminating medical knowledge, data and decisions in the hospital of the future. It integrates six essential features of the medical care environment: personnel management, patient management, medical diagnosis, laboratory management, propharmacy, and equipment management. Disease conditions covered are the major tropical diseases. An intelligent tutoring feature completes the package. Emphasis is placed on the graphical user interface to facilitate interactions between the user and the system, which is developed for PCs using Pascal, C, Clipper and Prolog.