Functional and diagnostic structure of the equipment of a wind power station

This article describes functional and diagnostic structure of the equipment of a Wind Power Station. Considering particular operational conditions of a technical object, that is a set of Wind Power Station equipment, this is a significant issue. A structural model of Wind Power Station  equipment is developed. Based on that, a functional – diagnostic model of Wind Power Station  equipment is elaborated. That model is a basis for determining primary elements of the object structure, as well as for interpreting a set of diagnostic signals and their reference signals.


INTRODUCTION
Expert systems are programs that can help or replace human experts in a specific field. Such systems can provide pieces of advice, recommendations or diagnoses relating to problems appearing in a specific field [1, 2, 7-13, 16, 28]. Computer programs developed in that way are of great importance and use for fields that are poorly formalized (without having mathematical backgrounds, which could be created algorithms for) e.g. diagnostics, medicine, etc [4,6,[22][23][26][27]. Expert systems are characterized not only by their capability to solve non-algorithmically defined problems but also have other advantages e.g. collected expert knowledge can be easily transmitted and available if experts are not present at time (due to their sick health or retirement) and coded knowledge can be easily delivered (it is easier to copy a computer program than teach another human) and a response can be acquired fast, and there are no human symptoms like fatigue nor stress [8][9][10][11][12][13].
A problem of creating effective knowledge bases for expert systems to be used in a diagnostic process of safe usage of Wind Power Plant's equipment is considerably complex. One may say that this problem is of interdisciplinary character since it relates to e.g. IT (expert systems, knowledge bases), math (gathering and analyzing knowledge sets), diagnostic (creating models for technical models and organizing signals' measurements), reliability -operational (examining technical conditions of objects), artificial intelligence (processing and transferring human expertise into artificial knowledge using a computer programming languages) [2,7,[10][11][12][13].
The article covers issues such as: − making models for technical objects, including functional-diagnostic models, − examining technical objects, including evaluation of technical condition, and creation of diagnostic signal sets, − measuring diagnostic signals, including analysis of measurement results and creation of reference diagnostic signal sets, − expert knowledge relating to gathering, analyzing, and concluding in an expert system, − math problems, including creation of knowledge sets, analysis, and conclusions (making decisions). The above-mentioned issues are not presented in literature clearly and comprehensively. Hence the diversity of the subject matter of publications used in the article. The authors of this article presented their approach to the development (solution) of such a complex problem. Such a full approach to the problem of presenting the issue of building an expert knowledge base for the purposes of diagnosing the state of safe use of wind farm equipment is an innovative solution [1,7,17,20,[24][25].
This work presents the issues of building a diagnostic knowledge base for wind farm equipment. The development of a diagnostic knowledge base is the basis for building a set of facts and rules for the future expert knowledge base being built.

FUNCTIONAL AND DIAGNOSTIC STRUCTURE OF THE EQUIPMENT OF A WIND POWER STATION
The basis of the technical diagnostics of technical devices and items {O(ei,j)} is the performance of a diagnostic test of the item examined. The diagnostic test of the item consists in a number of technical and technological activities as well as mental activities. The effect of these activities is the structure of the technical item in the form of its functional and diagnostic diagram based on which the set of the diagnostic signals {Xi,j} is determined. The functional units of the item (units) in the functional and diagnostic diagram presented in Fig. 1 are "addressed": numbered in the following manner: (Ei) is the i-th number of the functional unit in the item [3][4][5][6].
The elements of the unit are "addressed" in the form (ei,j), where j-th means the number of the element in the i-th unit. It is accepted that the j-th element or the basic module distinguished in the diagram of the structure of the item is such an element (module) of the item which is indivisible in its structure, and which develops its output signal. This signal is further known as the measuring signal or the diagnostic signal. When the element develops more than one output signal, it is only one generalized signal that needs to be determined which expresses best the functional (diagnostic, reliability etc.) properties of a given j-th element [3][4][5][6].
It is assumed that the j-th basic element or basic module highlighted in the structure of the object structure is the element-module of the object that is not divisible in its structure, and which produces its output signal. The signal generated is referred to as the measuring signal or diagnostic signal. If an element generates more than one output signal, then only one generalized signal should be determined, which most closely reflects the functional (diagnostic, reliability, etc.) properties of the given jth element.
As a result of functional and diagnostic analysis, a set of measuring and reference diagnostic signals {X(ei, j)} was identified in the wind farm model, which are identified at the outputs of j-functional elements. The designated set of reference and measuring diagnostic signals {Xw(ei, j)} of a wind power plant is presented in Table 2. By analyzing values of measurement signals, a set of reference diagnostic signals {Xw(ei,j)} of wind turbine generators is designated and shown in Table 2. Fig. 2. Screen of (DIAG 2) programme -diagram of the functional and diagnostic structure of the wind power system, where: E1 -generator drive system, E2 -synchronous generator system, E3 -generator's magnet system, E4 -power regulator system, E5electric power converter system, E6 -voltage and current coordinate converter system, E7 -MV transformer assembly Fig. 3. Screen of consolidated diagnostic information in (DIAG 2) software, where: E1 -generator drive system, E2synchronous generator system, E3 -generator's magnet system, E4 -power regulator system, E5 -electric power converter system, E6 -voltage and current coordinate converter system, E7 -MV transformer assembly

CONCLUSIONS
The expert system described above that supports diagnosing wind farm devices works out an assessment of the working condition of its individual elements based on input data and a knowledge base created. Obtaining a diagnosis and the realization of the inference process takes place in an intuitive manner through the subsequent occurrence of panels that form the so-called diagnosing path. Owing to the use of a graphical interface, there is a quick access to the working condition of all the elements of the wind farm within the framework of a consolidated (general) assessment. In a detailed assessment, each element of the farm presents the working conditions of all the sub-assemblies (blocks) and the reasons of the occurrence of an alarm or failure signal. The database that is based on real measurements (the real values of diagnostic signals) and an extended knowledge base allow one to obtain a reliable diagnosis of the functioning condition of the wind farm devices. Owing to this, the expert system described can be successfully used as a part of an intelligent supervision and safety system in the operation of the wind farm.