Concept With the continuous development of database technology and the extensive application of database management systems, the amount of data stored in the database has increased dramatically. However, in the face of these massive data, there are few tools that can be analyzed and processed at present. The limitations of the tools currently used make it impossible for people to dig out the many important information hidden behind large amounts of data, and these information can support people's decision-making well. In order to solve these problems in practice, in order to meet people's needs, KDD technology in the database has gradually developed. KDD is also known as Data Mining (DM). Actually, there are differences between the two, but it is generally not necessary. Use differently.
Data mining itself is an integrated body of multiple technologies, including mature database management systems, data warehouses, statistics, and machine learning technologies. Data mining can be applied in many areas and process control, such as medicine, finance, intelligence, law, defense, logic, education, but also in anomaly detection and diagnosis. In many areas of scientific research and engineering practice, there are often situations that require rapid diagnosis and decision-making. For a complex large system such as a power system, this situation often occurs, such as power system failure.
Data mining is suitable for such hidden rules of discovery and is used for rapid diagnosis and decision making.
People usually define data mining as follows: Data mining is a method of exploring a large number of enterprise data according to established business goals, revealing the hidden laws and further modeling it.
A well-known definition of KDD is that KDD is a credible, novel, effective, and understandable mode processing process from a large amount of data. This process is an advanced process.
There are several points in this definition that need to be explained. "Data" refers to a collection of facts F. It is used to describe information concerning aspects of things. Generally speaking, these data are all accurate. "Pattern" refers to the characteristics of the data in the set F obtained by describing it in a certain language L. "Processing process" refers to a multi-step process in KDD, including data preprocessing, pattern extraction, knowledge evaluation, and process optimization. The pattern of "trusted" discovery from the current data through KDD must have a certain degree of accuracy, otherwise KDD will have no effect.
This should be the case for the system. If the pattern obtained through the KDD only reveals the general law, it is considered useless. The “potential role†means that the extracted model should be meaningful. If the extracted model is novel, it has no practical meaning and is considered useless.
Application Technology China Power Bookmark3 helps people better understand the information contained in the database. 2 The process of knowledge discovery process in the database The model of knowledge discovery process is multi-stage. Under normal circumstances, KDD processing can be divided into several phases: (1) Analysis, understanding and definition of domain problems. Data miners collaborate with domain experts to conduct in-depth analysis of the issues to determine possible solutions and ways to evaluate learning outcomes. (2) Collection, extraction and cleanup of relevant data. Collect relevant data according to the definition of the problem. In the data extraction process, database query functions can be used to speed up data extraction.
At the same time to understand the meaning of the field in the database and its relationship with other fields, and then check the validity of the extracted data and clean up the data with the error. (3) Data Engineering. The reprocessing of data is mainly the removal of redundant attributes, the selection of representative data from a large amount of data to reduce the amount of learning, and the conversion of the representation of data to suit learning algorithms. (4) Select and run data mining algorithms. Select the appropriate data mining algorithm based on the problem to be solved and the data, and decide how to use the algorithm on these data. Then, according to the selected knowledge discovery algorithm, the processed data is extracted, ie, data mining. (5) Evaluation of the result model. The assessment of mining results depends on the problems that need to be solved, and domain experts evaluate the novelty and effectiveness of the discovery model. (6) Expression and use of results. The results model is expressed in a form that people can understand, and these mining results are applied in practical work to provide support for decision-making.
This model emphasizes the participation of data mining personnel and domain experts in the overall process of KDD. Domain experts are very clear about the issues that need to be solved in the field. Domain experts explain to data mining personnel at the stage of problem analysis, understanding and definition. Data mining personnel introduce data mining technology and types of problems to domain experts. . After mutual understanding, the two parties reached consensus on the issues to be resolved, including the definition of problems and the data processing methods. After data mining personnel get accurate problem definition and analysis, they begin to collect the data that needs to be used and reprocess it to make the data more suitable for later mining algorithms. According to the need to solve the problem, select the appropriate mining algorithm. The extracted knowledge needs to be interpreted by domain experts to evaluate the knowledge and the entire process.
It can be seen that the above-mentioned model is mainly based on the needs of practical applications. It mainly emphasizes the participation of domain experts, and guides the various stages of KDD by domain expertise, and evaluates the discovered knowledge. This model is also the most commonly used one in practical engineering. At the same time, data mining is just one of many stages in KDD, and it is the most important one because it can find hidden patterns. However, both are often referred to as data mining indiscriminately.
3 Architecture of a typical data mining system The architecture of a typical data mining system is mainly composed of the following components: Typical architecture of a data mining system Database, data warehouse, or other information storage means one or more databases, data warehouses, and extended forms. Or other kinds of information warehouse. (2) The database or data warehouse server is responsible for obtaining relevant data, which is based on user data mining requirements. (3) Knowledge base refers to the knowledge in a certain field, which is used to guide data search or evaluate the result model that the user cares about. (4) Data mining engines usually consist of functional modules for specific tasks, such as description, joint analysis, classification, evolution, and dissimilation analysis. (5) The model evaluation module usually uses benefit measures to interact with the data mining module so that the search for data develops in the direction of the user's concern. For more effective data mining, the model benefit evaluation should be combined as closely as possible with the excavation process to limit the search to only the patterns of interest. (6) The user interface is mainly responsible for the interaction between the user and the data mining system, providing information to help the user to focus on the search direction of data mining.
4 Application 4.1 Current data utilization in power systems In power systems, except for certain special applications, the main sources of various data include real-time data, archive data, and analog data. At the same time, each data source also contains many different kinds of data, all of which constitute an extremely large information storage system. However, at present, in the actual operation and planning management of power systems, the amount of information people obtain through these data is only a part of the amount of information contained in these massive data, such as the results of load flow calculations, state estimation, etc. The more important information that is hidden behind these data is the description of the overall characteristics of these data and the prediction of their development trends. Such information cannot be obtained by conventional methods, but this information has important value in the process of decision-making. That is to say, a large amount of useful data has not been fully developed and utilized. This situation is bound to create a situation in which, although the application technology is adequate, the information available from it is relatively lacking, that is, many valuable data are Information extraction is in a "dead" state, and a large amount of available resources are wasted. This is all due to the lack of technology for deep analysis of data.
4.2 Data Mining Application Based on Power System Since the data utilization in the current power system is not sufficient, the information obtained from it is relatively lacking and monotonous. Therefore, a deep data analysis technology suitable for power system applications is needed to change this situation. The gradual maturity of data mining technology (ie, knowledge discovery in the database) has brought this opportunity. Applying data mining techniques to these data in a manner suitable for power systems will facilitate the use of these potentially important information.
In the power system, there are several types of data that can be applied to data mining technologies: (1) the range characteristics (including time and space) and statistical characteristics of the power system, which often contain several thousand state variables; (2) mixed existence Discrete information (such as network topology changes or protection actions, etc.) and continuous information (such as some continuously changing state variables) (3) the mastery and processing of certain uncertainties (such as noise and incomplete information, etc.) ).
When using classical power system analysis methods to process these data, usually only a few general application results are obtained for conventional targets. However, the use of data mining technology can solve the problem that some traditional methods cannot solve or solve with certain difficulties. For some specific conventional problems, using this technology sometimes has higher efficiency or better results.
The following are some applications of data mining technology in the power system: (1) Classification of the power system operating status. The power system is divided into the normal state, alert state, emergency state, test state, or recovery state. This classification of the power system into various states is important. Because once the state of the power system is determined, a suitable instruction for the state is sent to the operator to complete the operation. Data mining algorithms help this sort of processing.
Description of the operating status of the power system. That is, a machine learning algorithm is used to learn a rule that describes a certain power system operating state that is satisfied by the data in the database. For example, the emergency state of the power system is described by the voltage drop on the busbars and other characteristics. Data mining helps to find better description rules. (3) Using the numerical method to analyze the relationship between power system faults.
This type of data mining uses a form of numerical rules. By learning a function, you can use the given data to predict the value of the new input. Data mining can discover certain relationships that occur when different accidents occur, thus providing a reliable description of power system failures. (4) Stability analysis and safety evaluation of the power system. This kind of knowledge discovery often exists in the form of a decision tree or a dependency table. For example, a decision tree can be used to classify a power system into a stable state and an unstable state, and to use other machine learning techniques to evaluate the safety of a power system.
Of course, this also requires a reasonable description of certain rules. (5) Detection and prediction of changes and dissimilation in power system operation. Using data mining, many important potential changes can be discovered from a large amount of historical data previously stored, and then the system knowledge of the power system domain can be used for further use. This type of data mining is very meaningful for power system load forecasting, electricity pricing strategies in the electricity market, and so on. (6) Construct an expert system using the induction rules from accident case analysis. The data mining can be used to analyze the power system fault report database and form a certain induction rule. The rule can be applied to the diagnosis expert system for different types of faults. This method of using induction to form an expert system is relatively easy.
4.3 Major advantages Compared with the power system analysis methods for classical theory, data mining can show higher superiority in three main areas: higher predictability, computational efficiency, and uncertainty for potential problems and laws. Detection and management. (1) Higher predictability of potential problems and laws. In the current engineering practice, engineers often have to solve some new problems after they do not meet the desired results in the system, that is, there is a general lack of high predictability for potential problems and laws. However, "the description of the overall characteristics of the data and the prediction of its development trend" is exactly the characteristics of data mining, and the use of data mining can overcome these difficulties. (2) Higher computational efficiency. Using data mining to extract comprehensive information, rather than numerical results, they can bring higher speed for real-time decision making. In addition, for the requirements of input information, data mining may only require meaningful or available input parameters without a complete description of the model, ie, redundant information is masked. These characteristics will inevitably bring about an increase in efficiency. (3) Management of uncertainties. Some events that occur in the power system are always unpredictable, such as relay protection misoperation, operator misoperation, incorrect description of a load model, and so on. Data mining is simulated by relaxing the assumptions of the dynamic model, and then using the corresponding domain knowledge to effectively manage it.
In short, the structure of the power system is quite complex, and the various problems faced are huge and complex. Some of them cannot establish accurate mathematical models, or they cannot be described simply by mathematical models, while others cannot establish mathematical models. For these problems, the application of data mining technology can reflect superiority and is a powerful tool to solve such problems.
4.4 Key points and difficulties (1) The guiding role of background knowledge. The background knowledge or theory related to a certain research field of the power system must be used to correctly guide the data mining process, so that the mining algorithm can be closely integrated with the field. (2) Excavating different kinds of knowledge. Different types of information required for different application directions in the power system are also different, and data mining should be able to cover a wider range of applications.
The interactive nature of the mining process. The data mining should be guided through the use of background knowledge in a certain field of the power system in an interactive manner. This helps the user to focus on the search for the interest model and improve the efficiency.
Application technology mines the results for ease of understanding and availability. The discovered knowledge should be expressed in a way that can be easily understood and used by others. That is, the potential laws discovered must be understandable, and it can have practical value. (5) Deal with abnormal and incomplete data. Massive information in the power system will inevitably contain noise, abnormal or incomplete data. This information may confuse the analysis process and reduce the accuracy of the discovered patterns. In fact, data mining can effectively manage these information by relaxing the assumptions of the dynamic model, and the key is the implementation. (6) Evaluation of data mining results model. For the results of mining, the domain knowledge of the power system is needed to evaluate it, because the result must be applied in a specific field to make sense.
5 Conclusion Data mining is a new data analysis method. So far, some commercial data mining products and research prototypes have been applied. However, the application of data mining combined with the characteristics of the power system to this field has only just begun. With the further development of the power industry, the direction of data analysis will be further expanded in various applications of the power system. Conventional methods have been stretched, and data mining has been introduced into power system analysis in a timely manner. It will surely play an active role in solving existing problems. effect. Researchers who are working to solve problems related to power systems should understand data mining and can use different technologies to obtain comprehensive and practical solutions.
PVA sponge polishing wheel adopts special synthetic resin to enhance its wear resistance
And the grinding force, by the existence of special air hole, can quickly eliminate the dust, no packing and hair
Heat phenomenon, avoid heat burn workpiece, suitable for long time grinding work. The binder is soft and slow
Impact, no deep blemishes on the grinding surface.
Use of PVA grinding wheel :1. It is easy to heat up when using general sand flower and sand cloth
Used for grinding stainless steel, aluminum, copper, iron, wood, gemstone, marble, glass, graphite
Products, urea products and leather, etc. PVA sponge grinding wheel is the most suitable. In addition, it can be eliminated
Burr, dirt, rust, etc.
2. Using PVA sponge grinding wheel, you can get beautiful grinding surface and saving after a short time of work
Omitted number of projects. For example, all kinds of metal grinding, copper mixing cylinder (centerless polishing), watchcase,
Grinding of watchband, gemstone and marble before plating or polishing.
Mounted Point,Polishing Mounted Point,Grinding Mounted Points,Mounted Point Grinding Wheel
Henan Jinlun Superhard Material Co., Ltd , https://www.jinlunsuperhard.com