Method and system for analyzing abnormality of coal as fired

Abstract

The invention discloses an as-fired coal anomaly analysis method and system, and the method comprises the steps: obtaining basic information of as-fired coal, determining a coal sample mixing proportion of the as-fired coal according to the basic information, and generating a to-be-detected coal sample mixing sequence based on the coal sample mixing proportion; extracting to-be-inspected parameters of the to-be-inspected coal sample mixed sequence according to a preset anomaly judgment principle, and performing judgment to obtain abnormal parameters of the current to-be-inspected coal sample mixed sequence; determining an anomaly type of the current to-be-detected coal sample mixed sequence according to all the anomaly parameters, and performing anomaly degree evaluation based on the anomaly type and the corresponding anomaly parameters to obtain an anomaly degree evaluation value; according to the method, all the abnormal parameters of the abnormal type are subjected to correlation prediction, the correction coefficient is generated according to the correlation prediction result, the abnormal degree evaluation value is corrected, the abnormal grade of the current to-be-detected coal sample mixed sequence is set according to the corrected abnormal degree evaluation value, and the accuracy of abnormality analysis of the coal sample mixed sequence of the coal as fired is improved.

Description

Technical Field

[0001] The present application relates to the technical field of coal entering a furnace, and in particular to a method and system for analyzing abnormality of coal entering a furnace. Background Art

[0002] The coal quality test of thermal power plants is conducted twice, namely, the test before entering the plant and the test before entering the furnace, to verify the accuracy of the coal test data. When the samples of the coal entering the plant and the coal entering the furnace are prepared and sent for inspection, the sample bags should be mixed with each other to form a mixed sequence of coal samples before sending them for inspection to prevent the test personnel from calculating the batch of the tested samples based on the inspection time. Therefore, improving the accuracy of abnormality analysis of the mixed sequence of coal samples entering the furnace is a technical problem that needs to be solved urgently. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a method and system for analyzing the abnormality of coal entering the furnace. According to the preset abnormality judgment principle, the parameters to be tested are extracted and judged for the mixed sequence of coal samples to be tested, the abnormal parameters are obtained, and the corresponding abnormality type is determined. The degree of abnormality is evaluated according to the abnormality type and abnormal parameters, and a corrected abnormality degree evaluation value is obtained according to the associated prediction result, thereby improving the accuracy of the abnormality analysis of the mixed sequence of coal samples entering the furnace.

[0004] In some embodiments of the present application, a method for analyzing abnormality of incoming coal is provided, comprising: Obtain basic information of coal entering the furnace, determine the mixing ratio of coal samples entering the furnace according to the basic information, and generate a mixing sequence of coal samples to be tested based on the mixing ratio of coal samples; Extract and judge the parameters to be tested of the mixed sequence of coal samples to be tested according to the preset abnormality judgment principle, and obtain the abnormal parameters of the current mixed sequence of coal samples to be tested; Determine the abnormal type of the current mixed sequence of coal samples to be tested according to all abnormal parameters, evaluate the abnormality level based on the abnormal type and the corresponding abnormal parameters, and obtain an abnormality level evaluation value; All abnormal parameters of the abnormal type are predicted in association, and a correction coefficient is generated according to the result of the association prediction to correct the abnormality degree evaluation value. The abnormality level of the current mixed sequence of coal samples to be tested is set according to the corrected abnormality degree evaluation value.

[0005] In some embodiments of the present application, determining the mixing ratio of coal samples fed into the furnace according to basic information includes: Obtaining basic information of the coal entering the furnace, the basic information including the credibility of the supplier of the coal entering the furnace and the importance of the corresponding coal type; Generate an initial evaluation value of the incoming coal according to the supplier's credibility, set a coal sample compensation coefficient according to the importance of the corresponding coal type of the incoming coal, and correct the initial evaluation value according to the coal sample compensation coefficient to obtain a coal sample evaluation value; According to the relationship between the coal sample evaluation value and the preset coal sample evaluation value interval, a corresponding preset coal sample mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; Presetting a first preset coal sample evaluation value interval, a second preset coal sample evaluation value interval, a third preset coal sample evaluation value interval and a fourth preset coal sample evaluation value interval; When the coal sample evaluation value is within the first preset coal sample evaluation value interval, the first preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is within the second preset coal sample evaluation value interval, the second preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is within the third preset coal sample evaluation value interval, the third preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is in the fourth preset coal sample evaluation value interval, the fourth preset mixing ratio is selected as the coal sample mixing ratio of the coal currently entering the furnace.

[0006] In some embodiments of the present application, the preset abnormality judgment principle includes: Several preset abnormality types are set, including: a first preset abnormality type, a second preset abnormality type, and a third preset abnormality type; Each preset abnormality type is pre-set with a number of abnormality evaluation indicators, and each abnormality evaluation indicator is pre-set with a number of normal parameter intervals; Each normal parameter interval is associated with a number of abnormal difference values, and each abnormal difference value is configured with a corresponding preset abnormal degree coefficient.

[0007] In some embodiments of the present application, the abnormal parameters of the mixed sequence of the coal sample to be tested are obtained, including: The algorithm matching factor of each normal parameter interval is obtained based on the setting process of the normal parameter interval of all abnormal evaluation indicators; A learning algorithm matching each normal parameter interval is obtained by screening in an algorithm database based on an algorithm matching factor, and a parameter to be tested corresponding to each normal parameter interval in a mixed sequence of coal samples to be tested is generated based on the learning algorithm; Compare the parameter to be tested with the corresponding normal parameter interval. If the parameter to be tested is within the corresponding normal parameter interval, set the current parameter to be tested as a normal parameter. If the parameter to be tested is not within the corresponding normal parameter range, the current parameter to be tested is set as an abnormal parameter.

[0008] In some embodiments of the present application, the abnormal type of the current mixed sequence of coal samples to be tested is determined according to all abnormal parameters, including: Obtain the number of abnormal parameters of all abnormal evaluation indicators of each preset abnormal type, and generate a ratio value according to the number of abnormal parameters of all abnormal evaluation indicators of the same preset abnormal type and the number of all parameters to be tested; If the proportion ratio of the preset abnormal type is greater than the preset ratio threshold, the abnormal type of the mixed sequence of coal samples to be tested is set to the corresponding preset abnormal type.

[0009] In some embodiments of the present application, the abnormality level is evaluated based on the abnormality type and the corresponding abnormality parameter, including: When the abnormal type of the mixed sequence of coal samples to be tested is a preset abnormal type: If the abnormality type is the first preset abnormality type, a first time reference line is established, and a plurality of first inspection time nodes are evenly configured according to the first inspection number, and abnormal parameters of all abnormality evaluation indicators of the first preset abnormality type are obtained according to the first inspection time nodes, and mapped to the first time reference line; Calculate the difference value between the abnormal parameter and the corresponding normal parameter interval at each first inspection time node on the first time reference line, perform average processing on the difference values ​​of the same abnormal parameter at all first inspection time nodes, and obtain the first characteristic difference value of each abnormal parameter; Compare the first characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the first characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a first fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at consecutive first inspection time nodes, and set a first compensation coefficient of the current abnormal parameter according to the first fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the first characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the first preset abnormality type, the first compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; If the abnormality type is the second preset abnormality type, a second time reference line is established, and a plurality of second inspection time nodes are evenly configured according to the second inspection number, and abnormal parameters of all abnormality evaluation indicators of the second preset abnormality type are obtained according to the second inspection time nodes, and mapped to the second time reference line; Calculate the difference value between the abnormal parameter and the corresponding normal parameter interval at each second inspection time node on the second time reference line, perform mean processing on the difference values ​​of the same abnormal parameter at all second inspection time nodes, and obtain a second characteristic difference value of each abnormal parameter; Compare the second characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the second characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a second fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at the second consecutive inspection time node, and set the second compensation coefficient of the current abnormal parameter according to the second fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the second characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the second preset abnormality type, the second compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; If the abnormality type is the third preset abnormality type, a third time reference line is established, and a plurality of third inspection time nodes are evenly configured according to the third inspection number, and abnormal parameters of all abnormality evaluation indicators of the third preset abnormality type are obtained according to the third inspection time nodes, and mapped to the third time reference line; Calculate the difference between the abnormal parameter and the corresponding normal parameter interval at each third inspection time node on the third time reference line, perform average processing on the difference values ​​of the same abnormal parameter at all third inspection time nodes, and obtain a third characteristic difference value of each abnormal parameter; Compare the third characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the third characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a third fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at the third consecutive inspection time node, and set a third compensation coefficient of the current abnormal parameter according to the third fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the third characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the third preset abnormality type, the third compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; When the abnormality type of the mixed sequence of coal samples to be tested is multiple preset abnormality types: The abnormality degree evaluation value of each preset abnormality type is obtained respectively in the analysis order, and the abnormality degree evaluation value of the mixed sequence of coal samples to be tested is generated according to the abnormality degree evaluation values ​​of multiple preset abnormality types and the weight coefficients of the corresponding preset abnormality types.

[0010] In some embodiments of the present application, obtaining an abnormality evaluation value includes: When the abnormal type of the mixed sequence of coal samples to be tested is a preset abnormal type, the calculation formula of the abnormal degree evaluation value is: ; Among them, Y is the abnormality evaluation value, is the weight coefficient of the first abnormal evaluation index of the current abnormal type, is the abnormality degree coefficient of the characteristic difference value of the ith abnormal parameter of the first abnormal evaluation index, is the compensation coefficient of the ith abnormal parameter of the first abnormal evaluation index, i=0, 1, 2, ...n1, is the weight coefficient of the jth abnormal evaluation index of the current abnormal type, is the abnormality degree coefficient of the characteristic difference value of the sth abnormal parameter of the jth abnormal evaluation index, is the compensation coefficient of the sth abnormal parameter of the jth abnormal evaluation index, s=0, 1, 2, ...nj, j=1, 2, ...m, is the abnormality degree coefficient of the characteristic difference value of the xth abnormal parameter of the mth abnormal evaluation index, is the compensation coefficient of the xth abnormal parameter of the mth abnormal evaluation index, x=0, 1, 2, ...nm, is the weight coefficient of the mth abnormal evaluation index of the current abnormal type, and m is the total number of abnormal evaluation indicators of the current abnormal type; When the abnormality type of the mixed sequence of coal samples to be tested is a plurality of preset abnormality types, the calculation formula of the abnormality degree evaluation value is: ;in, is the abnormality evaluation value of the zth preset abnormality type, is the weight coefficient of the zth preset abnormal type, g is the number of abnormal types in the mixed sequence of coal samples to be tested, g=2 or 3, z=1,…,g.

[0011] In some embodiments of the present application, association prediction is performed on all abnormal parameters of the abnormal type, and a correction coefficient is generated according to the association prediction result and the abnormality evaluation value is corrected, including: All abnormal parameters of the abnormal type of the mixed sequence of coal samples to be inspected are correlated and predicted to obtain the impact factors associated with all abnormal parameters, and the impact factors are divided into economic impact factors, efficiency impact factors and safety impact factors according to their types; According to the abnormal degree coefficients of all abnormal parameters, the economic impact degree, efficiency impact degree and safety impact degree corresponding to the associated economic impact factor, efficiency impact factor and safety impact factor are set; Generate correction factors based on economic impact, efficiency impact, and safety impact; The abnormality evaluation value is corrected according to the correction coefficient, and the corrected abnormality evaluation value is: ; Among them, c1 is the degree of economic impact, v1 is the weight coefficient of the economic impact, c2 is the degree of efficiency impact, v2 is the weight coefficient of the efficiency impact, c3 is the degree of safety impact, and v3 is the weight coefficient of the safety impact.

[0012] In some embodiments of the present application, the abnormality level of the current mixed sequence of coal samples to be tested is set according to the corrected abnormality level evaluation value, including: Presetting a first preset abnormality level evaluation value threshold and a second preset abnormality level evaluation value threshold; When the corrected abnormality evaluation value is less than the first preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset first-level abnormality level, and a first-level processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library; When the corrected abnormality evaluation value is between the first preset abnormality evaluation value threshold and the second preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset secondary abnormality level, and a secondary processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library; When the corrected abnormality evaluation value is greater than the second preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset third-level abnormality level, and a three-level processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library.

[0013] In some embodiments of the present application, a system for analyzing abnormality of incoming coal is also included: An acquisition module is used to acquire basic information of the coal entering the furnace, determine the mixing ratio of the coal samples entering the furnace according to the basic information, and generate a mixing sequence of the coal samples to be tested based on the mixing ratio of the coal samples; A judgment module is used to extract and judge the parameters to be tested of the mixed sequence of coal samples to be tested according to a preset abnormality judgment principle, and obtain the abnormal parameters of the current mixed sequence of coal samples to be tested; An evaluation module is used to determine the abnormal type of the current mixed sequence of coal samples to be tested according to all abnormal parameters, and to evaluate the degree of abnormality based on the abnormal type and the corresponding abnormal parameters to obtain an abnormality evaluation value; The correction module is used to perform correlation prediction on all abnormal parameters of the abnormal type, generate a correction coefficient based on the correlation prediction result and correct the abnormal degree evaluation value, and set the abnormal level of the current mixed sequence of coal samples to be tested based on the corrected abnormal degree evaluation value.

[0014] Compared with the prior art, the method and system for analyzing abnormality of incoming coal in the embodiment of the present application have the following beneficial effects: According to the preset abnormality judgment principle, the parameters to be tested are extracted and judged for the mixed sequence of coal samples to be tested, the abnormal parameters are obtained, and the corresponding abnormality type is determined. The abnormality degree is evaluated according to the abnormality type and abnormal parameters, and the corrected abnormality degree evaluation value is obtained according to the associated prediction result, which improves the accuracy of abnormality analysis of the mixed sequence of coal samples entering the furnace. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a method for analyzing abnormality of incoming coal in a preferred embodiment of the present application; Figure 2 It is a schematic diagram of a system for analyzing abnormality of incoming coal in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0016] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0017] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0020] like Figure 1 As shown, a method for analyzing abnormality of incoming coal in a preferred embodiment of the present application includes: Step S101: acquiring basic information of incoming coal, determining the mixing ratio of coal samples of the incoming coal according to the basic information, and generating a mixed sequence of coal samples to be tested based on the mixing ratio of coal samples; Step S102: extracting and judging the parameters to be tested of the mixed sequence of the coal samples to be tested according to the preset abnormality judgment principle, and obtaining the abnormal parameters of the current mixed sequence of the coal samples to be tested; Step S103: determining the abnormality type of the current mixed sequence of coal samples to be tested according to all abnormal parameters, and evaluating the degree of abnormality based on the abnormality type and the corresponding abnormal parameters to obtain an abnormality degree evaluation value; Step S104: perform association prediction on all abnormal parameters of the abnormal type, generate a correction coefficient based on the association prediction result and correct the abnormality level evaluation value, and set the abnormality level of the current mixed sequence of coal samples to be tested based on the corrected abnormality level evaluation value.

[0021] In this embodiment, the mixed sequence of coal samples to be tested refers to the coal samples entering the furnace and the coal samples entering the factory constructed according to the coal sample mixing ratio and time sequence. By evaluating the degree of abnormality of the mixed sequence of coal samples to be tested, the abnormality evaluation value is obtained, and the abnormality level is determined, so as to indirectly determine the abnormality of the coal entering the furnace, judge whether there is fraud, and improve the accuracy of the abnormality analysis of the coal entering the furnace.

[0022] In some embodiments of the present application, determining the mixing ratio of coal samples fed into the furnace according to basic information includes: Obtaining basic information of the coal entering the furnace, the basic information including the credibility of the supplier of the coal entering the furnace and the importance of the corresponding coal type; Generate an initial evaluation value of the incoming coal according to the supplier's credibility, set a coal sample compensation coefficient according to the importance of the corresponding coal type of the incoming coal, and correct the initial evaluation value according to the coal sample compensation coefficient to obtain a coal sample evaluation value; According to the relationship between the coal sample evaluation value and the preset coal sample evaluation value interval, a corresponding preset coal sample mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; Presetting a first preset coal sample evaluation value interval, a second preset coal sample evaluation value interval, a third preset coal sample evaluation value interval and a fourth preset coal sample evaluation value interval; When the coal sample evaluation value is within the first preset coal sample evaluation value interval, the first preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is within the second preset coal sample evaluation value interval, the second preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is within the third preset coal sample evaluation value interval, the third preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is in the fourth preset coal sample evaluation value interval, the fourth preset mixing ratio is selected as the coal sample mixing ratio of the coal currently entering the furnace.

[0023] In this embodiment, the coal sample evaluation value = credibility * coal sample compensation coefficient, credibility refers to whether the supplier's historical coal supply meets the standard. When the importance of the coal type is greater, the coal sample compensation coefficient is smaller, and when the importance of the coal type is smaller, the coal sample compensation coefficient is larger. The value range of the coal sample compensation coefficient is (0.75, 1.25). When the credibility is greater, the coal sample evaluation value is larger, and when the credibility is smaller, the coal sample evaluation value is smaller. The coal sample mixing ratio refers to the mixing ratio of the coal entering the factory and the coal entering the furnace. When the coal sample mixing ratio is larger, it means that the number of coal entering the furnace in the mixed sequence of coal samples to be inspected is smaller.

[0024] In this embodiment, when the coal sample evaluation value is smaller, it means that the credibility of the current supplier of coal entering the furnace is lower, that is, the number of inspections of the coal entering the furnace should be increased, that is, a smaller coal sample mixing ratio should be selected. When the coal sample evaluation value is larger, the number of inspections of the coal entering the furnace can be reduced, that is, a larger coal sample mixing ratio can be selected.

[0025] In this embodiment, the first preset coal sample evaluation value interval is less than the second preset coal sample evaluation value interval is less than the third preset coal sample evaluation value interval is less than the fourth preset coal sample evaluation value interval, and the first preset mixing ratio is less than the second preset mixing ratio is less than the third preset mixing ratio is less than the fourth preset mixing ratio.

[0026] In this embodiment, by setting the coal sample mixing ratio according to the basic information of the coal entering the furnace, the probability of abnormal coal entering the furnace due to supplier problems is reduced, and the accuracy of abnormal analysis of the coal entering the furnace is improved, laying the foundation for the subsequent determination of the abnormality evaluation value of the coal entering the furnace.

[0027] In some embodiments of the present application, the preset abnormality judgment principle includes: Several preset abnormality types are set, including: a first preset abnormality type, a second preset abnormality type, and a third preset abnormality type; Each preset abnormality type is pre-set with a number of abnormality evaluation indicators, and each abnormality evaluation indicator is pre-set with a number of normal parameter intervals; Each normal parameter interval is associated with a number of abnormal difference values, and each abnormal difference value is configured with a corresponding preset abnormal degree coefficient.

[0028] In this embodiment, the first preset abnormality type refers to the lack of randomness in the mixed sequence of coal samples to be tested, the second preset abnormality type refers to the abnormal mixing ratio in the mixed sequence of coal samples to be tested, that is, the proportion of elements in the coal samples entering the furnace increases or decreases, and the third preset abnormality type refers to the degree of deviation between the test data of all coal samples entering the furnace in the mixed sequence of coal samples to be tested and the original data of the test form is greater than the preset deviation degree threshold.

[0029] In this embodiment, the abnormality evaluation index is set according to the evaluation basis for judging the corresponding preset abnormality type. When the preset abnormality type does not have randomness, the corresponding abnormality evaluation index includes the number of sequence runs, the probability of element occurrence, the sample autocorrelation coefficient, etc.

[0030] In this embodiment, the abnormal difference value is the difference between the historical parameters extracted from the mixed sequence of historical abnormal inspection coal samples and the normal parameter interval, and the preset abnormal degree coefficient is set according to the historical impact degree of the abnormal difference value.

[0031] In some embodiments of the present application, the abnormal parameters of the mixed sequence of the coal sample to be tested are obtained, including: The algorithm matching factor of each normal parameter interval is obtained based on the setting process of the normal parameter interval of all abnormal evaluation indicators; A learning algorithm matching each normal parameter interval is obtained by screening in an algorithm database based on an algorithm matching factor, and a parameter to be tested corresponding to each normal parameter interval in a mixed sequence of coal samples to be tested is generated based on the learning algorithm; Compare the parameter to be tested with the corresponding normal parameter interval. If the parameter to be tested is within the corresponding normal parameter interval, set the current parameter to be tested as a normal parameter. If the parameter to be tested is not within the corresponding normal parameter range, the current parameter to be tested is set as an abnormal parameter.

[0032] In this embodiment, the algorithm matching factor refers to the algorithm used in the analysis or calculation of each normal parameter interval. The algorithm database includes the learning algorithm used for abnormal evaluation of the mixed sequence of all test coal samples. The parameters to be tested are extracted according to the learning algorithm to improve the extraction accuracy of the parameters to be tested, thereby laying a data foundation for subsequent analysis of the degree of abnormality.

[0033] In some embodiments of the present application, the abnormal type of the current mixed sequence of coal samples to be tested is determined according to all abnormal parameters, including: Obtain the number of abnormal parameters of all abnormal evaluation indicators of each preset abnormal type, and generate a ratio value according to the number of abnormal parameters of all abnormal evaluation indicators of the same preset abnormal type and the number of all parameters to be tested; If the proportion ratio of the preset abnormal type is greater than the preset ratio threshold, the abnormal type of the mixed sequence of coal samples to be tested is set to the corresponding preset abnormal type.

[0034] In some embodiments of the present application, the abnormality level is evaluated based on the abnormality type and the corresponding abnormality parameter, including: When the abnormal type of the mixed sequence of coal samples to be tested is a preset abnormal type: If the abnormality type is the first preset abnormality type, a first time reference line is established, and a plurality of first inspection time nodes are evenly configured according to the first inspection number, and abnormal parameters of all abnormality evaluation indicators of the first preset abnormality type are obtained according to the first inspection time nodes, and mapped to the first time reference line; Calculate the difference value between the abnormal parameter and the corresponding normal parameter interval at each first inspection time node on the first time reference line, perform average processing on the difference values ​​of the same abnormal parameter at all first inspection time nodes, and obtain the first characteristic difference value of each abnormal parameter; Compare the first characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the first characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a first fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at consecutive first inspection time nodes, and set a first compensation coefficient of the current abnormal parameter according to the first fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the first characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the first preset abnormality type, the first compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; If the abnormality type is the second preset abnormality type, a second time reference line is established, and a plurality of second inspection time nodes are evenly configured according to the second inspection number, and abnormal parameters of all abnormality evaluation indicators of the second preset abnormality type are obtained according to the second inspection time nodes, and mapped to the second time reference line; Calculate the difference value between the abnormal parameter and the corresponding normal parameter interval at each second inspection time node on the second time reference line, perform mean processing on the difference values ​​of the same abnormal parameter at all second inspection time nodes, and obtain a second characteristic difference value of each abnormal parameter; Compare the second characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the second characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a second fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at the second consecutive inspection time node, and set the second compensation coefficient of the current abnormal parameter according to the second fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the second characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the second preset abnormality type, the second compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; If the abnormality type is the third preset abnormality type, a third time reference line is established, and a plurality of third inspection time nodes are evenly configured according to the third inspection number, and abnormal parameters of all abnormality evaluation indicators of the third preset abnormality type are obtained according to the third inspection time nodes, and mapped to the third time reference line; Calculate the difference between the abnormal parameter and the corresponding normal parameter interval at each third inspection time node on the third time reference line, perform average processing on the difference values ​​of the same abnormal parameter at all third inspection time nodes, and obtain a third characteristic difference value of each abnormal parameter; Compare the third characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the third characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a third fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at the third consecutive inspection time node, and set a third compensation coefficient of the current abnormal parameter according to the third fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the third characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the third preset abnormality type, the third compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; When the abnormality type of the mixed sequence of coal samples to be tested is multiple preset abnormality types: The abnormality degree evaluation value of each preset abnormality type is obtained respectively in the analysis order, and the abnormality degree evaluation value of the mixed sequence of coal samples to be tested is generated according to the abnormality degree evaluation values ​​of multiple preset abnormality types and the weight coefficients of the corresponding preset abnormality types.

[0035] In this embodiment, the abnormality type of the mixed sequence of coal samples to be tested can be one or more preset abnormality types. If there are multiple preset abnormality types, the analysis order is set, and the analysis order is the third preset abnormality type > the second preset abnormality type > the first preset abnormality type.

[0036] In this embodiment, the change trend includes an upward trend and a downward trend. When the change trend is in an upward trend, it means that multiple difference values ​​of the current abnormal parameters are getting larger and larger. When the change trend is in a downward trend, it means that multiple difference values ​​of the current abnormal parameters are getting smaller and smaller. When the change trend is in an upward trend and the fluctuation value is larger, the corresponding fluctuation evaluation value is larger, and the corresponding compensation coefficient is set larger, that is, the subsequent calculated abnormality evaluation value will become larger. When the change trend is in a downward trend and the fluctuation value is smaller, the corresponding fluctuation evaluation value is smaller, and the corresponding compensation coefficient is set smaller, that is, the subsequent calculated abnormality evaluation value will become smaller.

[0037] In this embodiment, by setting a corresponding time reference line and an inspection time node for each preset abnormality type, an analysis benchmark between different preset abnormality types is established, and the corresponding abnormality degree coefficient and compensation coefficient are determined by the abnormality and fluctuation of each abnormal parameter in the inspection time node of the time reference line, thereby improving the accuracy of the subsequent calculation of the abnormality degree evaluation value of the mixed sequence of coal samples to be inspected, that is, improving the accuracy of the abnormality analysis results of the current coal entering the furnace.

[0038] In some embodiments of the present application, obtaining an abnormality evaluation value includes: When the abnormal type of the mixed sequence of coal samples to be tested is a preset abnormal type, the calculation formula of the abnormal degree evaluation value is: ; Among them, Y is the abnormality evaluation value, is the weight coefficient of the first abnormal evaluation index of the current abnormal type, is the abnormality degree coefficient of the characteristic difference value of the ith abnormal parameter of the first abnormal evaluation index, is the compensation coefficient of the ith abnormal parameter of the first abnormal evaluation index, i=0, 1, 2, ...n1, is the weight coefficient of the jth abnormal evaluation index of the current abnormal type, is the abnormality degree coefficient of the characteristic difference value of the sth abnormal parameter of the jth abnormal evaluation index, is the compensation coefficient of the sth abnormal parameter of the jth abnormal evaluation index, s=0, 1, 2, ...nj, j=1, 2, ...m, is the abnormality degree coefficient of the characteristic difference value of the xth abnormal parameter of the mth abnormal evaluation index, is the compensation coefficient of the xth abnormal parameter of the mth abnormal evaluation index, x=0, 1, 2, ...nm, is the weight coefficient of the mth abnormal evaluation index of the current abnormal type, and m is the total number of abnormal evaluation indicators of the current abnormal type; When the abnormality type of the mixed sequence of coal samples to be tested is a plurality of preset abnormality types, the calculation formula of the abnormality degree evaluation value is: ;in, is the abnormality evaluation value of the zth preset abnormality type, is the weight coefficient of the zth preset abnormal type, g is the number of abnormal types in the mixed sequence of coal samples to be tested, g=2 or 3, z=1,…,g.

[0039] In this embodiment, the characteristic difference values ​​include a first characteristic difference value, a second characteristic difference value and a third characteristic difference value, and the compensation coefficients include a first compensation coefficient, a second compensation coefficient and a third compensation coefficient. The above compensation coefficients and characteristic difference values ​​are determined according to the preset abnormality type, and the value range of the first compensation coefficient, the second compensation coefficient and the third compensation coefficient is (0.8, 1.2).

[0040] In some embodiments of the present application, association prediction is performed on all abnormal parameters of the abnormal type, and a correction coefficient is generated according to the association prediction result and the abnormality evaluation value is corrected, including: All abnormal parameters of the abnormal type of the mixed sequence of coal samples to be inspected are correlated and predicted to obtain the impact factors associated with all abnormal parameters, and the impact factors are divided into economic impact factors, efficiency impact factors and safety impact factors according to their types; According to the abnormal degree coefficients of all abnormal parameters, the economic impact degree, efficiency impact degree and safety impact degree corresponding to the associated economic impact factor, efficiency impact factor and safety impact factor are set; Generate correction factors based on economic impact, efficiency impact, and safety impact; The abnormality evaluation value is corrected according to the correction coefficient, and the corrected abnormality evaluation value is: ; Among them, c1 is the degree of economic impact, v1 is the weight coefficient of the economic impact, c2 is the degree of efficiency impact, v2 is the weight coefficient of the efficiency impact, c3 is the degree of safety impact, and v3 is the weight coefficient of the safety impact.

[0041] In this embodiment, the influencing factor is an influencing factor set according to the historical impact of the current abnormal parameter. The influencing factor associated with the corresponding abnormal parameter is determined according to the damage in the historical impact. The efficiency influencing factor refers to the factor affecting the operating efficiency of the boiler. The economic influencing factor refers to the factor affecting the fuel cost, maintenance cost, economic benefit, etc. The safety influencing factor refers to the factor affecting the normal operation of the boiler.

[0042] In this embodiment, the correction factor is , and the correction coefficient range is (1, 1.25).

[0043] In this embodiment, by performing correlation prediction on all abnormal parameters and generating correction coefficients to correct the abnormality evaluation values, the accuracy of the abnormality evaluation values ​​of the mixed sequence of coal samples to be tested is improved, that is, the accuracy of abnormality analysis of the corresponding coal entering the furnace is improved.

[0044] In some embodiments of the present application, the abnormality level of the current mixed sequence of coal samples to be tested is set according to the corrected abnormality level evaluation value, including: Presetting a first preset abnormality level evaluation value threshold and a second preset abnormality level evaluation value threshold; When the corrected abnormality evaluation value is less than the first preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset first-level abnormality level, and a first-level processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library; When the corrected abnormality evaluation value is between the first preset abnormality evaluation value threshold and the second preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset secondary abnormality level, and a secondary processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library; When the corrected abnormality evaluation value is greater than the second preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset third-level abnormality level, and a three-level processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library.

[0045] In this embodiment, the preset processing strategy library is constructed based on the historical processing strategies of the historical abnormality inspection coal sample mixed sequences. According to the coal type entering the furnace, the coal sample mixing ratio and the corrected abnormality degree evaluation value, the historical abnormality inspection coal sample mixed sequence with the greatest similarity is screened out in the preset processing strategy library and the corresponding historical processing strategy is set as the corresponding primary / secondary / tertiary processing strategy.

[0046] In this embodiment, by accurately calculating the abnormality evaluation value of the mixed sequence of coal samples to be inspected and determining the corresponding abnormality level, a corresponding processing strategy is set for the mixed training of the coal samples to be inspected, so as to realize the abnormality analysis, judgment and processing of the coal entering the furnace, reduce the associated abnormal impact caused by the fraudulent behavior of the coal entering the furnace, and improve the inspection efficiency of the coal entering the furnace.

[0047] In some embodiments of the present application, Figure 2 As shown, it also includes a system for analyzing abnormality of incoming coal: An acquisition module is used to acquire basic information of the coal entering the furnace, determine the mixing ratio of the coal samples entering the furnace according to the basic information, and generate a mixing sequence of the coal samples to be tested based on the mixing ratio of the coal samples; A judgment module is used to extract and judge the parameters to be tested of the mixed sequence of coal samples to be tested according to a preset abnormality judgment principle, and obtain the abnormal parameters of the current mixed sequence of coal samples to be tested; An evaluation module is used to determine the abnormal type of the current mixed sequence of coal samples to be tested according to all abnormal parameters, and to evaluate the degree of abnormality based on the abnormal type and the corresponding abnormal parameters to obtain an abnormality evaluation value; The correction module is used to perform correlation prediction on all abnormal parameters of the abnormal type, generate a correction coefficient based on the correlation prediction result and correct the abnormal degree evaluation value, and set the abnormal level of the current mixed sequence of coal samples to be tested based on the corrected abnormal degree evaluation value.

[0048] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for analyzing abnormality of coal entering a furnace, characterized in that: include: Obtain basic information of coal entering the furnace, determine the mixing ratio of coal samples entering the furnace according to the basic information, and generate a mixing sequence of coal samples to be tested based on the mixing ratio of coal samples; Extract and judge the parameters to be tested of the mixed sequence of coal samples to be tested according to the preset abnormality judgment principle, and obtain the abnormal parameters of the current mixed sequence of coal samples to be tested; Determine the abnormal type of the current mixed sequence of coal samples to be tested according to all abnormal parameters, evaluate the abnormality level based on the abnormal type and the corresponding abnormal parameters, and obtain an abnormality level evaluation value; All abnormal parameters of the abnormal type are predicted in association, and a correction coefficient is generated according to the result of the association prediction to correct the abnormality degree evaluation value. The abnormality level of the current mixed sequence of coal samples to be tested is set according to the corrected abnormality degree evaluation value.

2. The method for analyzing abnormality of incoming coal according to claim 1, characterized in that: The mixing ratio of coal samples fed into the furnace is determined based on basic information, including: Obtaining basic information of the coal entering the furnace, the basic information including the credibility of the supplier of the coal entering the furnace and the importance of the corresponding coal type; Generate an initial evaluation value of the incoming coal according to the supplier's credibility, set a coal sample compensation coefficient according to the importance of the corresponding coal type of the incoming coal, and correct the initial evaluation value according to the coal sample compensation coefficient to obtain a coal sample evaluation value; According to the relationship between the coal sample evaluation value and the preset coal sample evaluation value interval, a corresponding preset coal sample mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; Presetting a first preset coal sample evaluation value interval, a second preset coal sample evaluation value interval, a third preset coal sample evaluation value interval and a fourth preset coal sample evaluation value interval; When the coal sample evaluation value is within the first preset coal sample evaluation value interval, the first preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is within the second preset coal sample evaluation value interval, the second preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is within the third preset coal sample evaluation value interval, the third preset mixing ratio is selected as the coal sample mixing ratio of the current coal entering the furnace; When the coal sample evaluation value is in the fourth preset coal sample evaluation value interval, the fourth preset mixing ratio is selected as the coal sample mixing ratio of the coal currently entering the furnace.

3. The method for analyzing abnormality of incoming coal according to claim 2, characterized in that: The preset abnormality judgment principle includes: Several preset abnormality types are set, including: a first preset abnormality type, a second preset abnormality type, and a third preset abnormality type; Each preset abnormality type is pre-set with a number of abnormality evaluation indicators, and each abnormality evaluation indicator is pre-set with a number of normal parameter intervals; Each normal parameter interval is associated with a number of abnormal difference values, and each abnormal difference value is configured with a corresponding preset abnormal degree coefficient.

4. The method for analyzing abnormality of incoming coal according to claim 3, characterized in that: Obtain the abnormal parameters of the mixed sequence of the coal sample to be tested, including: The algorithm matching factor of each normal parameter interval is obtained based on the setting process of the normal parameter interval of all abnormal evaluation indicators; A learning algorithm matching each normal parameter interval is obtained by screening in an algorithm database based on an algorithm matching factor, and a parameter to be tested corresponding to each normal parameter interval in a mixed sequence of coal samples to be tested is generated based on the learning algorithm; Compare the parameter to be tested with the corresponding normal parameter interval. If the parameter to be tested is within the corresponding normal parameter interval, set the current parameter to be tested as a normal parameter. If the parameter to be tested is not within the corresponding normal parameter range, the current parameter to be tested is set as an abnormal parameter.

5. The method for analyzing abnormality of incoming coal according to claim 4, characterized in that: Determine the abnormal type of the current mixed sequence of coal samples to be tested based on all abnormal parameters, including: Obtain the number of abnormal parameters of all abnormal evaluation indicators of each preset abnormal type, and generate a ratio value according to the number of abnormal parameters of all abnormal evaluation indicators of the same preset abnormal type and the number of all parameters to be tested; If the proportion ratio of the preset abnormal type is greater than the preset ratio threshold, the abnormal type of the mixed sequence of coal samples to be tested is set to the corresponding preset abnormal type.

6. The method for analyzing abnormality of incoming coal according to claim 5, characterized in that: The abnormality level is evaluated based on the abnormality type and the corresponding abnormality parameters, including: When the abnormal type of the mixed sequence of coal samples to be tested is a preset abnormal type: If the abnormality type is the first preset abnormality type, a first time reference line is established, and a plurality of first inspection time nodes are evenly configured according to the first inspection number, and abnormal parameters of all abnormality evaluation indicators of the first preset abnormality type are obtained according to the first inspection time nodes, and mapped to the first time reference line; Calculate the difference value between the abnormal parameter and the corresponding normal parameter interval at each first inspection time node on the first time reference line, perform average processing on the difference values ​​of the same abnormal parameter at all first inspection time nodes, and obtain the first characteristic difference value of each abnormal parameter; Compare the first characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the first characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a first fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at consecutive first inspection time nodes, and set a first compensation coefficient of the current abnormal parameter according to the first fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the first characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the first preset abnormality type, the first compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; If the abnormality type is the second preset abnormality type, a second time reference line is established, and a plurality of second inspection time nodes are evenly configured according to the second inspection number, and abnormal parameters of all abnormality evaluation indicators of the second preset abnormality type are obtained according to the second inspection time nodes, and mapped to the second time reference line; Calculate the difference value between the abnormal parameter and the corresponding normal parameter interval at each second inspection time node on the second time reference line, perform mean processing on the difference values ​​of the same abnormal parameter at all second inspection time nodes, and obtain a second characteristic difference value of each abnormal parameter; Compare the second characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the second characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a second fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at the second consecutive inspection time node, and set the second compensation coefficient of the current abnormal parameter according to the second fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the second characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the second preset abnormality type, the second compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; If the abnormality type is the third preset abnormality type, a third time reference line is established, and a plurality of third inspection time nodes are evenly configured according to the third inspection number, and abnormal parameters of all abnormality evaluation indicators of the third preset abnormality type are obtained according to the third inspection time nodes, and mapped to the third time reference line; Calculate the difference between the abnormal parameter and the corresponding normal parameter interval at each third inspection time node on the third time reference line, perform mean processing on the difference values ​​of the same abnormal parameter at all third inspection time nodes, and obtain the three-feature difference values ​​of each abnormal parameter; Compare the third characteristic difference value with the abnormal difference value associated with the normal parameter interval corresponding to the current abnormal parameter, set the preset abnormality degree coefficient corresponding to the abnormal difference value with the greatest similarity to the third characteristic difference value as the abnormality degree coefficient of the current abnormal parameter, generate a third fluctuation evaluation value according to the change trend and fluctuation value of multiple difference values ​​of the current abnormal parameter at the third consecutive inspection time node, and set a third compensation coefficient of the current abnormal parameter according to the third fluctuation evaluation value; Generate an abnormality degree evaluation value of the mixed sequence of coal samples to be tested according to the abnormality degree coefficient of the third characteristic difference value of the abnormal parameter corresponding to different abnormality evaluation indicators of the third preset abnormality type, the third compensation coefficient and the weight coefficient of the corresponding abnormality evaluation indicator; When the abnormality type of the mixed sequence of coal samples to be tested is multiple preset abnormality types: An analysis order of multiple preset abnormality types is set, and an abnormality degree evaluation value of each preset abnormality type is obtained according to the analysis order. An abnormality degree evaluation value of a mixed sequence of coal samples to be tested is generated according to the abnormality degree evaluation values ​​of multiple preset abnormality types and the weight coefficients of the corresponding preset abnormality types.

7. The method for analyzing abnormality of incoming coal according to claim 6, characterized in that: Obtain an abnormality evaluation value, including: When the abnormal type of the mixed sequence of coal samples to be tested is a preset abnormal type, the calculation formula of the abnormal degree evaluation value is: ； Among them, Y is the abnormality evaluation value, is the weight coefficient of the first abnormal evaluation index of the current abnormal type, is the abnormality degree coefficient of the characteristic difference value of the ith abnormal parameter of the first abnormal evaluation index, is the compensation coefficient of the ith abnormal parameter of the first abnormal evaluation index, i=0, 1, 2, ...n1, is the weight coefficient of the jth abnormal evaluation index of the current abnormal type, is the abnormality degree coefficient of the characteristic difference value of the sth abnormal parameter of the jth abnormal evaluation index, is the compensation coefficient of the sth abnormal parameter of the jth abnormal evaluation index, s=0, 1, 2, ...nj, j=1, 2, ...m, is the abnormality degree coefficient of the characteristic difference value of the xth abnormal parameter of the mth abnormal evaluation index, is the compensation coefficient of the xth abnormal parameter of the mth abnormal evaluation index, x=0, 1, 2, ...nm, is the weight coefficient of the mth abnormal evaluation index of the current abnormal type, and m is the total number of abnormal evaluation indicators of the current abnormal type; When the abnormality type of the mixed sequence of coal samples to be tested is a plurality of preset abnormality types, the calculation formula of the abnormality degree evaluation value is: ;in, is the abnormality evaluation value of the zth preset abnormality type, is the weight coefficient of the zth preset abnormal type, g is the number of abnormal types in the mixed sequence of coal samples to be tested, g=2 or 3, z=1,…,g.

8. The method for analyzing abnormality of incoming coal according to claim 7, characterized in that: Perform correlation prediction on all abnormal parameters of the abnormal type, generate correction coefficients based on the correlation prediction results and correct the abnormality evaluation value, including: All abnormal parameters of the abnormal type of the mixed sequence of coal samples to be inspected are correlated and predicted to obtain the impact factors associated with all abnormal parameters, and the impact factors are divided into economic impact factors, efficiency impact factors and safety impact factors according to their types; According to the abnormal degree coefficients of all abnormal parameters, the economic impact degree, efficiency impact degree and safety impact degree corresponding to the associated economic impact factor, efficiency impact factor and safety impact factor are set; Generate correction factors based on economic impact, efficiency impact, and safety impact; The abnormality evaluation value is corrected according to the correction coefficient, and the corrected abnormality evaluation value is: ; Among them, c1 is the degree of economic impact, v1 is the weight coefficient of the economic impact, c2 is the degree of efficiency impact, v2 is the weight coefficient of the efficiency impact, c3 is the degree of safety impact, and v3 is the weight coefficient of the safety impact.

9. The method for analyzing abnormality of incoming coal according to claim 8, characterized in that: The abnormality level of the current mixed sequence of coal samples to be tested is set according to the corrected abnormality evaluation value, including: Presetting a first preset abnormality level evaluation value threshold and a second preset abnormality level evaluation value threshold; When the corrected abnormality evaluation value is less than the first preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset first-level abnormality level, and a first-level processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library; When the corrected abnormality evaluation value is between the first preset abnormality evaluation value threshold and the second preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset secondary abnormality level, and a secondary processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library; When the corrected abnormality evaluation value is greater than the second preset abnormality evaluation value threshold, the abnormality level of the current mixed sequence of coal samples to be tested is set to the preset third-level abnormality level, and a three-level processing strategy for the current mixed sequence of coal samples to be tested is generated based on the preset processing strategy library.

10. A system for analyzing abnormality of coal entering a furnace, characterized in that: include: An acquisition module is used to acquire basic information of the coal entering the furnace, determine the mixing ratio of the coal samples entering the furnace according to the basic information, and generate a mixing sequence of the coal samples to be tested based on the mixing ratio of the coal samples; A judgment module is used to extract and judge the parameters to be tested of the mixed sequence of coal samples to be tested according to a preset abnormality judgment principle, and obtain the abnormal parameters of the current mixed sequence of coal samples to be tested; An evaluation module is used to determine the abnormal type of the current mixed sequence of coal samples to be tested according to all abnormal parameters, and to evaluate the degree of abnormality based on the abnormal type and the corresponding abnormal parameters to obtain an abnormality evaluation value; The correction module is used to perform correlation prediction on all abnormal parameters of the abnormal type, generate a correction coefficient based on the correlation prediction result and correct the abnormal degree evaluation value, and set the abnormal level of the current mixed sequence of coal samples to be tested based on the corrected abnormal degree evaluation value.

Images