Grading evaluation method for thermal power plant equipment state

Abstract

The invention relates to the technical field of thermal power generation, aims at solving the technical problem that in the prior art, thermal power plant evaluation quantitative indexes are too absolute, so that evaluation values are too one-sided and inaccurate, and particularly relates to a thermal power plant equipment state grading evaluation method which comprises the following steps: S1, obtaining measurement data of a thermal power plant including a steam turbine and a coal mill, pre-processing the measurement data to obtain pre-processed data, wherein the pre-processed data comprises a pre-processed image and primary processing data; s2, edge detection is carried out on the preprocessed image to obtain the diameter Dz of a pixel point, multi-level evaluation, level values and level matrixes are carried out on the single body and all equipment of the thermal power plant, so that the evaluation method has the effect of evaluating important factors which are difficult to quantify accurately, the evaluation accuracy is improved, and the evaluation efficiency is improved. Therefore, the evaluation result has certain authority, and the safety and stability of the thermal power plant are improved through early warning of the evaluation result.

Description

Technical Field

[0001] The invention relates to the technical field of thermal power generation, and in particular to a grading evaluation method for equipment status of a thermal power plant. Background Art

[0002] Thermal power plants generally refer to coal-fired power plants, which are factories that use combustibles as fuel to produce electricity. When the fuel is burned, it heats water to generate steam, converting the chemical energy of the fuel into thermal energy. The steam pressure drives the turbine to rotate, converting the thermal energy into mechanical energy. The turbine then drives the generator to rotate, converting the mechanical energy into electrical energy. The operation of the thermal power plant directly affects the quality of power generation. An objective evaluation of the equipment status is a prerequisite for improving the fault diagnosis system architecture and realizing the status monitoring and maintenance of thermal power plants. In the existing technology for comprehensive evaluation of thermal power plants, various factors of complex systems are generally divided into several evaluation levels, and weight calculations are performed on the evaluation levels to obtain the rating of the thermal power plant. However, although this method can quantify various factors of thermal power plants, it is easy for the evaluation value to be too absolute during the quantification process, so that many important factors that are difficult to accurately quantify are ignored, resulting in the evaluation results being too one-sided and inaccurate. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a hierarchical evaluation method for the equipment status of a thermal power plant, which solves the technical problem that the quantitative indicators of the prior art for evaluating a thermal power plant are too absolute, resulting in the evaluation values ​​being too one-sided and inaccurate, thereby achieving the purpose of both multi-level rating of thermal power plants and improving the accuracy of the evaluation values.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for grading evaluation of equipment status in a thermal power plant, the method comprising the following steps:

[0005] S1. Obtain measurement data of a thermal power plant including a steam turbine and a coal mill, and preprocess the measurement data to obtain preprocessed data, wherein the preprocessed data includes a preprocessed image and preliminary processed data;

[0006] S2. Perform edge detection on the preprocessed image to obtain the diameter D of the pixel point z , and according to the diameter D of the pixel point z Calculate the humidity value W of the turbine steam;

[0007] S3. Calculate the correction factor M of the steam flow of the steam turbine, and calculate the internal power P of the steam turbine based on the correction factor M. z ;

[0008] S4. Calculate the coal powder mass flow rate L of the coal mill mf , and according to the coal powder mass flow rate L mfConstruct the outlet temperature model of the coal mill and obtain the outlet temperature Wd g ;

[0009] S5, according to the humidity value W and internal power P z Calculate the individual grade evaluation value PZ of the steam turbine ql ;

[0010] S6, according to the outlet temperature Wd g Calculate the individual grade evaluation value PZ of the coal mill mm ;

[0011] S7, according to the individual grade evaluation value PZ of steam turbine and coal mill ql and PZ mm Calculate the comprehensive evaluation value Zh of thermal power plants h ;

[0012] S8, according to the comprehensive evaluation value Zh h Evaluate or issue early warning on the operation of thermal power plants.

[0013] Preferably, in step S1, the specific implementation steps are as follows:

[0014] S11. Obtain various parameters of various equipment in the thermal power plant and generate measurement data;

[0015] S12, preprocessing the steam image in the measurement data by a mean filtering method to obtain a preprocessed image;

[0016] S13, preprocessing the measurement data except the steam image by a data cleaning method to obtain preliminary processing data, and merging the preprocessed image and the preliminary processing data into preprocessed data;

[0017] The preliminary processing data include the actual steam specific volume ZV, feed water mass flow L md , Superheat and desuperheating water mass flow rate L mg 、Unknown leaked steam mass flow rate L ml , isentropic heat recovery extraction steam mass flow rate L mh , the mass flow rate of steam leakage from the high-pressure cylinder shaft seal under isentropic state L mz , reheating water mass flow rate L mzr , the mass flow rate of steam extraction from the jth stage of the steam turbine L mj , Mass flow rate of heating extraction steam L me , wheel speed N lv and intake pressure p jq , the raw coal quality Zl of the coal mill y , coal powder quality Zl mf , Imported primary air mass flow rate L mar , grinding wheel speed n v And coal powder fineness R f .

[0018] Preferably, in step S2, the specific implementation steps are as follows:

[0019] S21, establish a two-dimensional coordinate system with any pixel point in the preprocessed image as the origin, the horizontal direction as the X-axis, and the vertical direction as the Y-axis, and obtain an image Tu(x, y);

[0020] S22. Determine the edge function B(x, y) according to the image Tu(x, y). The calculation formula is:

[0021]

[0022] Wherein, B(x, y) represents the edge function of the image Tu(x, y), and σ represents the standard deviation of the edge function B(x, y);

[0023] S23, calculate the first-order directional derivative B of the edge function B(x, y) f , the calculation formula is:

[0024]

[0025] in, represents the partial derivative of the marginal function B(x, y) with respect to the variable x, represents the gradient vector of the edge function B(x, y), represents the direction vector of the edge function B(x, y), cosθ and sinθ represent The cosine and sine of the angle θ with the abscissa;

[0026] S24, image Tu (x, y) and the first-order directional derivative B f Do convolution and calculate the direction parameter F. The calculation formula is:

[0027]

[0028] Where, F represents the direction parameter;

[0029] S25. Set the direction parameter F equal to zero and calculate the edge parameter tanθ. The calculation formula is:

[0030]

[0031] Among them, tanθ represents the edge parameter;

[0032] S26. Calculate the direction parameter F equal to zero based on the edge parameter tanθ The calculation formula is:

[0033]

[0034] in, Represents the direction vector when the direction parameter f is equal to zero;

[0035] S27, through the non-maximum suppression method, under the condition that the direction parameter F is equal to zero The gradient image is processed by double threshold value to obtain the edge image;

[0036] S28. Obtain the coordinates of two edge pixel points of the same droplet in the edge image at random, and calculate the distance D between the coordinates of the two edge pixel points. c , the expression is:

[0037]

[0038] Among them, D c Represents the distance between the coordinates of the cth edge pixel, (dx a ,y a )、(x b ,y b ) represent the coordinates of two edge pixels of the droplet in the edge image respectively;

[0039] S29, the obtained multiple distances D c Sort from large to small, and divide the distance D c The maximum value is taken as the droplet diameter D z , the expression is:

[0040] D z =max(D c )

[0041] Among them, D z represents the diameter of the droplet;

[0042] S210, according to the diameter D of the droplets in the steam z Calculate volume concentration Tn e , the calculation formula is:

[0043]

[0044] Among them, Tn e Indicates volume concentration, Ns(D z ) represents the size distribution function of the liquid droplets in the steam, f and g represent the maximum and minimum diameters of the liquid droplets in the steam, Indicates diameter D z The average value, σ D Indicates diameter D z The standard deviation of

[0045] S211, according to volume concentration Tn eCalculate the humidity value W of the steam turbine using the following formula:

[0046]

[0047] Where W represents the humidity value of the steam turbine, ρ e represents the saturated water density, ρ s Represents the saturated vapor density.

[0048] Preferably, in step S3, the specific implementation steps are as follows:

[0049] S31. Calculate the correction factor M based on the actual steam specific volume ZV. The calculation formula is:

[0050]

[0051] Wherein, M represents the correction factor, ZV represents the actual steam specific volume, and ZV' represents the steam specific volume under isentropic expansion;

[0052] S32, according to the water mass flow L md , Superheat and desuperheating water mass flow rate L mg and unknown leakage steam mass flow rate L ml Calculate the working medium mass flow rate L of the main steam in the isentropic state of the steam turbine mm , the expression is:

[0053] L mm =L md +L mg -L ml

[0054] Among them, L mm It represents the working medium mass flow rate of main steam under the isentropic state of the steam turbine;

[0055] S33, according to the working fluid mass flow L mm Calculate the high pressure cylinder exhaust steam mass flow rate L mt , the calculation formula is:

[0056] L mt =L mm -∑L mh -L mz

[0057] Among them, L mt Indicates the exhaust mass flow rate of high pressure cylinder, L mh is the isentropic heat recovery extraction steam mass flow rate, L mz It indicates the mass flow rate of steam leakage from the high-pressure cylinder shaft seal under isentropic state;

[0058] S34, according to the high pressure cylinder exhaust steam mass flow L mt Calculate the reheat steam mass flow rate L mrh, the calculation formula is:

[0059] L mrh =L mt +L mzr

[0060] Among them, L mrh Represents the reheat steam mass flow rate, L mzr Represents the mass flow rate of reheat desuperheating water;

[0061] S35, according to the working medium mass flow rate L of the main steam mm Calculate the low pressure cylinder exhaust steam mass flow rate L mc , the calculation formula is:

[0062] L mc =L mm +L mzr -∑L mj -L mz -L me

[0063] Among them, L mc Indicates the exhaust mass flow rate of the low-pressure cylinder, L mj represents the mass flow rate of steam extraction at the jth stage of the steam turbine, L me Indicates the mass flow rate of heating extraction steam;

[0064] S36. Calculate the internal power P of the steam turbine z , the calculation formula is:

[0065] P l =L mm ×b m +L mrh ×b rh -L mt ×b t -L mc ×b c -L me ×b e -∑L mj ×b j

[0066]

[0067] Among them, P l Indicates the uncorrected power value, P z represents the internal power of the steam turbine, b m , b rh , b t , b c , b e and b jThey respectively represent the specific enthalpy of the mass flow rate of main steam, reheat steam, high-pressure cylinder exhaust steam, low-pressure cylinder exhaust steam, heating extraction steam and turbine j-th stage extraction steam.

[0068] Preferably, in step S4, the specific implementation steps are as follows:

[0069] S41, according to the raw coal quality Zl y And coal powder quality Zl mf , calculate the total internal coal mass Zl of the coal mill zn , the calculation formula is:

[0070] Zl zn =Zl y +Zl mf

[0071] Among them, Zl zn It indicates the total coal mass stored in the coal mill;

[0072] S42, based on the total stored coal mass Zl zn and the inlet primary air mass flow rate L mar Calculate the inlet and outlet pressure difference ΔP a , the calculation formula is:

[0073]

[0074] Where ΔP a represents the inlet and outlet pressure difference, k1 and k2 represent the model parameters respectively;

[0075] S43, according to the inlet and outlet pressure difference ΔP a , Raw coal quality Zl y And coal powder quality Zl mf Calculate the raw coal mass flow rate L ym and coal powder mass flow rate L mf , the calculation formula is:

[0076] L ym =k3ΔP a Zl y

[0077] Ln mf =k4ΔP a Zl mf

[0078] Among them, L ym Indicates the raw coal mass flow rate, L mf represents the mass flow rate of pulverized coal, k3 and k4 represent the model parameters respectively;

[0079] S44, according to the raw coal mass flow L ym Calculate the moisture evaporation of raw coal Zf m , the calculation formula is:

[0080]

[0081] Among them, Zf m Indicates the amount of water evaporated from the raw coal, w in Indicates the coal mill operating temperature, Sf a Indicates the moisture content of raw coal;

[0082] S45, according to the raw coal quality Zl y And coal powder quality Zl mf Calculate the coal grinding current I mm , the calculation formula is:

[0083] I mm =k7Zl y +k8Zl mf +k9

[0084] Among them, I mm Indicates coal grinding current;

[0085] S46, according to the water evaporation Zf m , coal grinding current I mm , Raw coal mass flow rate L ym , coal powder mass flow rate L mf and the inlet primary air mass flow rate L mar Modeling the Outlet Temperature The expression is:

[0086]

[0087] in, The differential model representing the outlet temperature, k5, k6, k7, k8, k9, k 10 , k 11 , k 12 , k 13 and k 14 represents the heat coefficient;

[0088] S47, according to the outlet temperature model Get the outlet temperature Wd g .

[0089] Preferably, in step S5, the specific implementation steps are as follows:

[0090] S51, according to the humidity value W and internal power P of the steam turbine at multiple times z , wheel speed N lv and intake pressure p jq Form multiple groups of evaluation matrices and obtain the time t sj The evaluation matrix Pj under ql , the expression is:

[0091]

[0092] Among them, Pj ql Indicates time t sj Evaluation matrix for lower steam turbine;

[0093] S52, setting the level division set T based on the historical data of the thermal power plant dj , the expression is:

[0094]

[0095] Among them, T dj represents the hierarchical partition set, T a , T b , T c and T d Respectively represent humidity value W, internal power P z , wheel speed N lv and intake pressure p jq Row vector of rank values, T ai , T bi , T ci and T di Respectively represent the i-th level classification value;

[0096] S53, according to the evaluation matrix Pj ql and the level partition set T dj Calculate the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq The level value of Dj ql , the calculation formula is:

[0097]

[0098]

[0099] Among them, DJ qlw ,Dj qlPz ,Dj qlN and DJ qlPq Respectively represent the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq The grade value, Pj qlw , Pj qlPz , Pj qlN and Pj qlPq Respectively represent the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jqEvaluation matrix value of ;

[0100] S54, the grade values ​​Dj of the multiple evaluation matrices of the steam turbine ql Composition level matrix Jz dj , the expression is:

[0101]

[0102] Among them, Jz dj Denotes the rank matrix, Dj qlw ,Dj qlPz ,Dj qlN and DJ qlPq Respectively represent humidity value W, internal power P z , wheel speed N lv and intake pressure p jq The level value of

[0103] S55, based on the turbine humidity value W, internal power P z , wheel speed N lv and intake pressure p jq Obtain different weight values ​​through the hierarchical analysis method to form the weight matrix QJ sgj , and calculate the rank matrix Jz dj The evaluation matrix Pj jz , the expression is:

[0104]

[0105] Among them, Pj jz represents the evaluation matrix, QJ sgj represents the jth weight value;

[0106] S56, according to the evaluation matrix Pj jz Calculate individual rating value PZ h , the calculation formula is:

[0107] PZ h = median(Pj jzl )

[0108] Among them, PZ h represents the individual grade evaluation value, Pj jzl Represents the lth evaluation matrix value.

[0109] Preferably, in step S6, the specific implementation method is:

[0110] S61, according to the outlet temperature Wd of the coal mill at multiple times g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R fForm multiple groups of evaluation matrices and obtain the time t rt The evaluation matrix Pj under mj , the expression is:

[0111]

[0112] Among them, Pj mj Indicates time t rt Evaluation matrix for lower steam turbine;

[0113] S62. Setting a classification set S based on historical data of thermal power plants md , the expression is:

[0114]

[0115] Among them, S md represents the level partition set, S a , S b , S c and S d Respectively represent the outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Row vector of rank values, S ai , S bi , S ci and S di Respectively represent the i-th level classification value;

[0116] S63, according to the evaluation matrix Pj mj and the level partition set S md Calculate the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Level value DM mm , the calculation formula is:

[0117]

[0118]

[0119] Among them, DM mmWd DM mmZL DM mmnv and DM mmRf Respectively represent the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f The grade value, Pj mjWd 、PjmjZL 、Pj mjnv and Pj mjRf Respectively represent the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Evaluation matrix value of ;

[0120] S64, the grade values ​​DM of the multiple evaluation matrices of the coal mill mm Composition level vector MJ dj , the expression is:

[0121]

[0122] Among them, MJ dj represents the rank vector;

[0123] S65, based on the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Obtain different weight values ​​through the hierarchical analysis method to form the weight matrix QZ mge , and calculate the rank vector MJ dj The evaluation matrix Pj mm , the expression is:

[0124]

[0125] Among them, Pj mm represents the evaluation matrix, QZ mge represents the e-th weight value;

[0126] S66, according to the evaluation matrix Pj mm Calculate the individual grade evaluation value GT I , the calculation formula is:

[0127] GT I = median(Pj mmk )

[0128] Among them, GT I represents the individual grade evaluation value, Pj mmk Represents the kth evaluation matrix value.

[0129] Preferably, in step S7, the specific implementation steps are as follows:

[0130] S71, according to the evaluation matrix Pj of the steam turbine jz and weight matrix Qj sgj , and the evaluation matrix Pj of the coal mill mmand the weight matrix QZ mge , the maximum eigenvalues ​​λq of the steam turbine and coal mill are obtained by the sum-product method max and λm max ;

[0131] S72, according to the maximum eigenvalue λq max and λm max Calculate the test numerator Cq for the steam turbine and coal mill separately jy and Cm jy , the calculation formula is:

[0132]

[0133] Among them, Cq jy represents the test numerator of the steam turbine, Cm jy represents the test numerator of the coal mill, and m represents the weight matrix Qj sgj The order of p represents the weight matrix QZ mge The order of

[0134] S73, according to the test molecule Cq jy and Cm jy Calculate the consistency test coefficient C of the steam turbine and coal mill respectively qR and C mR , the calculation formula is:

[0135]

[0136]

[0137] Among them, C qR and C mR Respectively represent the consistency test coefficients of steam turbine and coal mill, C L is the consistency test constant;

[0138] S74, according to the consistency test coefficient C qR and C mR Obtain consistency test results;

[0139] If C qR <0.1 and C mR <0.1, then both the steam turbine and coal mill meet the consistency test results;

[0140] If C qR ≥0.1, the turbine does not meet the requirements, and the evaluation matrix Pj is obtained again after adjusting the turbine. jz and the weight matrix QJ sgj , and returns to step S71;

[0141] If C mR≥0.1, the coal mill does not meet the requirements, and the evaluation matrix Pj is obtained again after adjusting the coal mill. mm and the weight matrix QZ mge , and returns to step S71;

[0142] S75. Obtain the evaluation scores R of H experts on the operating parameters of the thermal power plant pb , where R pb Represents the bth evaluation score, according to the evaluation score R pb Calculate the expert weight value Zj d , the calculation formula is:

[0143]

[0144] Among them, Zj d represents the expert weight value, H represents the evaluation score R pb the number of

[0145] S76, according to the expert weight value Zj d Calculate the comprehensive evaluation value Zh h , the calculation formula is:

[0146] Zh jz =Zj d ×Pj jz

[0147] Zh mz =Zj d ×Pj mm

[0148]

[0149]

[0150] Among them, Zh h Indicates the comprehensive evaluation value, Zh jz and Zh mz denote the transition matrices of the steam turbine and coal mill, respectively, denote the element of the fth transition matrix of the steam turbine, Zh mzr represents the element of the rth transition matrix of the coal mill, F and R represent the number of elements in the transition matrices of the steam turbine and coal mill respectively, E and Y represent the number of equipment in the steam turbine and coal mill respectively, and U and V represent the number of equipment categories in the thermal power plant respectively.

[0151] Preferably, in step S8, the specific implementation steps are as follows:

[0152] S81. Comprehensive evaluation values ​​Zh at different times in the historical data of the thermal power plant h Calculate the average The calculation formula is as follows:

[0153]

[0154] in, Indicates the comprehensive evaluation value Zh h The average value of B represents the comprehensive evaluation value Zh h the number of

[0155] S82, based on the average Calculate the maintenance threshold K, the calculation formula is:

[0156]

[0157] Among them, K represents the maintenance threshold;

[0158] S83, according to the maintenance threshold K and the comprehensive evaluation value Zh h Evaluate the operation of thermal power plants;

[0159] If Zh h >K, the thermal power plant operates well and sends the evaluation results to the thermal power plant monitoring center;

[0160] If Zh h ≤K, the thermal power plant is operating poorly and an early warning is sent to the thermal power plant monitoring center.

[0161] By means of the above technical solution, the present invention provides a method for grading evaluation of the equipment status of a thermal power plant, which has at least the following beneficial effects:

[0162] 1. The present invention establishes a two-dimensional coordinate system based on the pixel points of the processed image, and then determines the edge of the pixel and determines the accurate droplet diameter based on the pixel edge, and then calculates the steam humidity. This method can not only improve the accuracy of droplet recognition and obtain accurate droplet images, but also make the results of humidity calculation more accurate, thereby increasing the accuracy of the evaluation method.

[0163] 2. The present invention calculates and analyzes the power inside the steam turbine under different extraction flow conditions based on the heat balance characteristics inside the steam turbine, and comprehensively considers the mass flow rate of the steam turbine under various conditions during operation, thereby increasing the accuracy of the calculation of the internal power of the steam turbine. This method takes many aspects into consideration and is conducive to the evaluation of the evaluation method of thermal power plants.

[0164] 3. The present invention establishes a mathematical model of the outlet temperature of the coal mill according to the internal flow conditions of the coal mill through a method of establishing a mathematical model, thereby being able to accurately obtain the outlet temperature of the coal mill during the change process, thereby improving the efficiency of obtaining the outlet temperature. In addition, the dynamic mathematical model encompasses the changes in multiple parameters, thereby increasing the accuracy of obtaining the outlet temperature.

[0165] 4. The present invention performs multi-level evaluation on single units and all equipment in thermal power plants, and through level values ​​and level matrices, enables the evaluation method to evaluate important factors that are difficult to accurately quantify, thereby improving the accuracy of the thermal power plant evaluation method and avoiding the one-sided results caused by overly absolute evaluation of thermal power plants. By adding expert evaluation and multi-level evaluation, the evaluation results have a certain degree of authority. At the same time, through early warning of the evaluation results, the staff can be reminded in time to maintain and repair the thermal power plant equipment, thereby improving the safety and stability of the thermal power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0166] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0167] Figure 1 It is a flow chart of a method for grading evaluation of equipment status in a thermal power plant according to the present invention;

[0168] Figure 2 Schematic diagram of the distance between two edge pixels of the same droplet in the edge image of the present invention. DETAILED DESCRIPTION

[0169] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0170] Due to the technical problem that the existing technology is too absolute in the quantitative indicators of thermal power plant evaluation, the evaluation value is too one-sided and inaccurate. Please refer to Figure 1 - Figure 2 This embodiment provides a method for grading the equipment status of a thermal power plant, which can not only perform multi-level rating on the thermal power plant, but also improve the accuracy of the evaluation value. The method includes the following steps:

[0171] S1. Obtain measurement data of a thermal power plant including a steam turbine and a coal mill, and preprocess the measurement data to obtain preprocessed data, the preprocessed data including a preprocessed image and preliminary processed data; after obtaining the measurement data, the data needs to be preprocessed to improve the accuracy of subsequent evaluation. In step S1, the specific implementation steps are as follows:

[0172] S11. Acquire various parameters of various equipment in a thermal power plant and generate measurement data; the equipment in a thermal power plant is roughly divided into a coal transportation system, a boiler system, a steam turbine system and a power generation system. In the coal transportation system, the coal mill plays a major role, in the boiler system, the boiler is the main equipment, in the steam turbine system, the steam turbine is the main equipment, and in the power generation system, the generator plays a major role. Therefore, when collecting data, the four types of equipment, namely, the coal mill, boiler, steam turbine and generator, are mainly collected. If necessary, other equipment can also be collected for evaluation. Since it is relatively easy to collect parameters of boilers and generators, in the present invention, data collection and parameter analysis are mainly performed on coal mills and steam turbines.

[0173] S12. Preprocess the steam image in the measurement data by the mean filtering method to obtain a preprocessed image; the mean filtering method is a commonly used method for filtering image data. In this step, only the mean filtering method is needed to obtain the desired result without additional steps. The mean filtering method is a commonly used image preprocessing method and will not be described in detail here.

[0174] S13. Preprocess the measurement data except the steam image by data cleaning method to obtain preliminary processing data, and merge the preprocessed image and the preliminary processing data into preprocessed data; data cleaning is a commonly used data processing method, generally deleting redundant or abnormal data. In this step, the desired result can be obtained only through data cleaning, without additional steps, and data cleaning is a common data processing method, which will not be elaborated here.

[0175] The preliminary processing data include the actual steam specific volume ZV, feed water mass flow L md , Superheat and desuperheating water mass flow rate L mg 、Unknown leaked steam mass flow rate L ml , isentropic heat recovery extraction steam mass flow rate L mh , the mass flow rate of steam leakage from the high-pressure cylinder shaft seal under isentropic state L mz , reheating water mass flow rate L mzr , the mass flow rate of steam extraction from the jth stage of the steam turbine L mj , Mass flow rate of heating extraction steam L me , wheel speed N lv and intake pressure p jq , the raw coal quality Zl of the coal mill y , coal powder quality Zl mf , Imported primary air mass flow rate L mar , grinding wheel speed n v And coal powder fineness R fWhen acquiring and collecting data on boilers and generators, the evaporation volume, steam pressure, feed water temperature and boiler efficiency of the boiler can also be obtained, and the rated power, rated voltage and working efficiency of the generator can be obtained. The parameters of the boiler and generator can also be used to evaluate the thermal power plant. At the same time, the parameters of the coal mill, steam turbine, boiler and generator can also be used together to evaluate the thermal power plant. In the present invention, taking the coal mill and steam turbine as an example, through preprocessing of the data, the data can be made more accurate, so that the subsequent evaluation results can be more accurate and more referenceable.

[0176] S2. Perform edge detection on the preprocessed image to obtain the diameter D of the pixel point z , and according to the diameter D of the pixel point z Calculate the humidity value W of the steam turbine; in the droplet diameter in the acquired image, since the droplets are very small, the size of the diameter is prone to errors in measurement. In step S2, the specific implementation steps are as follows:

[0177] S21, establish a two-dimensional coordinate system with any pixel point in the preprocessed image as the origin, the horizontal direction as the X-axis, and the vertical direction as the Y-axis, and obtain an image Tu(x, y);

[0178] S22. Determine the edge function B(x, y) according to the image Tu(x, y). The calculation formula is:

[0179]

[0180] Wherein, B(x, y) represents the edge function of the image Tu(x, y), σ represents the standard deviation of the edge function B(x, y); the edge function is a preliminary edge curve formed by edge pixels in the image;

[0181] S23, calculate the first-order directional derivative B of the edge function B(x, y) f , the calculation formula is:

[0182]

[0183] in, represents the partial derivative of the marginal function B(x, y) with respect to the variable x, represents the gradient vector of the edge function B(x, y), represents the direction vector of the edge function B(x, y), cosθ and sinθ represent Cosine and sine of the angle θ with the abscissa; first-order directional derivative B f is the first-order derivative of the edge function B(x, y), which is convenient for obtaining the direction vector and the gradient vector

[0184] S24, image Tu (x, y) and the first-order directional derivative B f Do convolution and calculate the direction parameter F. The calculation formula is:

[0185]

[0186] Where, F represents the direction parameter;

[0187] S25. Set the direction parameter F equal to zero and calculate the edge parameter tanθ. The calculation formula is:

[0188]

[0189] Among them, tanθ represents the edge parameter;

[0190] S26. Calculate the direction parameter F equal to zero based on the edge parameter tanθ The calculation formula is:

[0191]

[0192] in, Represents the direction vector when the direction parameter F is equal to zero;

[0193] S27, through the non-maximum suppression method, under the condition that the direction parameter F is equal to zero The gradient image is processed by double thresholding to obtain the edge image; the non-maximum suppression method is an algorithm widely used in computer vision tasks, which is mainly used to remove overlapping detection frames and retain the best detection results. In this step, only the non-maximum suppression method is needed to obtain the gradient image without additional steps. The non-maximum suppression method is a commonly used image processing method and will not be described in detail here. The gradient image is processed by double thresholding to quickly obtain a clear edge image. In the double thresholding processing, the pixels of the image are divided into three parts: pixels below the first threshold, pixels between the two thresholds, and pixels above the second threshold. This processing method can quickly and efficiently obtain the edge image of the droplet image, which is convenient for obtaining the diameter of the droplet. The double thresholding processing is a common image edge processing method and will not be described in detail here.

[0194] S28. Obtain the coordinates of two edge pixel points of the same droplet in the edge image at random, and calculate the distance D between the coordinates of the two edge pixel points. c , the expression is:

[0195]

[0196] Among them, D c Represents the distance between the coordinates of the cth edge pixel, (x a ,y a)、(x b ,y b ) represent the coordinates of two edge pixels of the droplet in the edge image respectively;

[0197] S29, the obtained multiple distances D c Sort from large to small, and divide the distance D c The maximum value is taken as the droplet diameter D z , the expression is:

[0198] D z =max(D c )

[0199] Among them, D z Indicates the diameter of the droplet; see Figure 2 As shown, among the coordinates of two points, only the coordinates of the diameter are the farthest, so at multiple distances D c The farthest distance must be the diameter distance.

[0200] S210, according to the diameter D of the droplets in the steam z Calculate volume concentration Tn e , the calculation formula is:

[0201]

[0202]

[0203] Among them, Tn e Indicates volume concentration, Ns(D z ) represents the size distribution function of the liquid droplets in the steam, f and g represent the maximum and minimum diameters of the liquid droplets in the steam, Indicates diameter D z The average value, σ D Indicates diameter D z The standard deviation of

[0204] S211, according to volume concentration Tn e Calculate the humidity value W of the steam turbine using the following formula:

[0205]

[0206] Where W represents the humidity value of the steam turbine, ρ e represents the saturated water density, ρ sIt represents the saturated vapor density. By acquiring the droplet diameter, a more accurate droplet diameter can be obtained, so that the calculation of the humidity value can be more accurate. A two-dimensional coordinate system is established according to the pixel points of the processed image, and then the edge of the pixel is determined. The accurate droplet diameter is determined according to the pixel edge, and then the steam humidity is calculated. This method can not only improve the accuracy of recognition and obtain an accurate droplet image, but also make the result of humidity calculation more accurate, thereby increasing the accuracy of the evaluation method.

[0207] S3. Calculate the correction factor M of the steam flow of the steam turbine, and calculate the internal power P of the steam turbine based on the correction factor M. z In the process of obtaining the internal power of the steam turbine, there are many factors that affect the internal power, so that the internal power of the steam turbine is difficult to obtain and has a large error. In step S3, the specific implementation steps are as follows:

[0208] S31. Calculate the correction factor M based on the actual steam specific volume ZV. The calculation formula is:

[0209]

[0210] Wherein, M represents the correction coefficient, ZV represents the actual steam specific volume, and ZV' represents the steam specific volume under isentropic expansion; the actual steam specific volume refers to the volume occupied by unit mass of steam under specific conditions, and the steam specific volume under isentropic expansion refers to the change of the specific volume of steam, that is, the ratio of volume to mass, during the isentropic expansion process. Isentropic expansion refers to the expansion process of gas under adiabatic conditions with constant entropy.

[0211] S32, according to the water mass flow L md , Superheat and desuperheating water mass flow rate L mg and unknown leakage steam mass flow rate L ml Calculate the working medium mass flow rate L of the main steam in the isentropic state of the steam turbine mm , the expression is:

[0212] L mm =L md +L mg -L ml

[0213] Among them, L mm It indicates the working medium mass flow rate of main steam under the isentropic state of steam turbine; mass flow rate refers to the mass of fluid passing through the effective cross-section of closed pipe or open tank per unit time; feed water mass flow rate is the mass flow rate of water in feed water; superheated desuperheated water mass flow rate is the mass flow rate of superheated desuperheated water.

[0214] S33, according to the working fluid mass flow L mm Calculate the high pressure cylinder exhaust steam mass flow rate Lmt , the calculation formula is:

[0215] L mt =L mm -∑L mh -L mz

[0216] Among them, L mt Indicates the exhaust mass flow rate of high pressure cylinder, L mh is the isentropic heat recovery extraction steam mass flow rate, L mz It indicates the mass flow rate of steam leakage from the high-pressure cylinder shaft seal under isentropic state;

[0217] S34, according to the high pressure cylinder exhaust steam mass flow L mt Calculate the reheat steam mass flow rate L mrh , the calculation formula is:

[0218] L mrh =L mt +L mzr

[0219] Among them, L mrh Represents the reheat steam mass flow rate, L mzr Represents the mass flow rate of reheat desuperheating water;

[0220] S35, according to the working medium mass flow rate L of the main steam mm Calculate the low pressure cylinder exhaust steam mass flow rate L mc , the calculation formula is:

[0221] L mc =L mm +L mzr -∑L mj -L mz -L me

[0222] Among them, L mc Indicates the exhaust mass flow rate of the low-pressure cylinder, L mj represents the mass flow rate of steam extraction at the jth stage of the steam turbine, L me Indicates the mass flow rate of heating extraction steam;

[0223] S36. Calculate the internal power P of the steam turbine z , the calculation formula is:

[0224] P l =L mm ×b m +L mrh ×b rh -L mt ×b t -L mc ×b c -Lme ×b e -∑L mj ×b j

[0225]

[0226] Among them, P l Indicates the uncorrected power value, P z represents the internal power of the steam turbine, b m , b rh , b t , b c , b e and b j They respectively represent the specific enthalpy of the mass flow of main steam, reheated steam, high-pressure cylinder exhaust, low-pressure cylinder exhaust, heating extraction steam and turbine j-th stage extraction. The specific enthalpy of mass flow refers to the enthalpy value of unit mass of fluid. Specific enthalpy is an important parameter to describe the energy state of fluid. It represents the energy possessed by unit mass of fluid, including internal energy and flow energy. The specific enthalpy value in the present invention can be obtained by acquiring parameters through sensors and brought into the calculation formula of specific enthalpy. According to the thermal balance characteristics inside the turbine, the power inside the turbine under different extraction flow conditions is calculated and analyzed, and the mass flow of the turbine under various conditions during operation is comprehensively considered to increase the accuracy of the calculation of the internal power of the turbine. This method takes many aspects into consideration, which is beneficial to the evaluation of the evaluation method of thermal power plants.

[0227] S4. Calculate the coal powder mass flow rate L of the coal mill mf , and according to the coal powder mass flow rate L mf Construct the outlet temperature model of the coal mill and obtain the outlet temperature Wd g In the operation of the coal mill, the outlet temperature needs to be used to evaluate the evaluation value of the coal mill and the thermal power plant. In step S4, the specific implementation steps are as follows:

[0228] S41, according to the raw coal quality Zl y And coal powder quality Zl mf , calculate the total internal coal mass Zl of the coal mill zn , the calculation formula is:

[0229] Zl zn =Zl y +Zl mf

[0230] Among them, Zl zn It indicates the total coal mass stored in the coal mill;

[0231] S42, based on the total stored coal mass Zl zn and the inlet primary air mass flow rate L mar Calculate the inlet and outlet pressure difference ΔP a, the calculation formula is:

[0232]

[0233] Where ΔP a represents the inlet and outlet pressure difference, k1 and k2 represent the model parameters respectively; the model parameters are obtained through the thermodynamic experimental results and the least square method.

[0234] S43, according to the inlet and outlet pressure difference ΔP a , Raw coal quality Zl y And coal powder quality ZL mf Calculate the raw coal mass flow rate L ym and coal powder mass flow rate L mf , the calculation formula is:

[0235] L ym =k3ΔP a Zl y

[0236] Ln mf =k4ΔP a Zl mf

[0237] Among them, L ym Indicates the raw coal mass flow rate, L mf represents the mass flow rate of pulverized coal, k3 and k4 represent model parameters respectively; the model parameters are obtained through thermodynamic experimental results and the least square method.

[0238] S44, according to the raw coal mass flow L ym Calculate the moisture evaporation of raw coal Zf m , the calculation formula is:

[0239]

[0240] Among them, Zf m Indicates the amount of water evaporated from the raw coal, w in Indicates the coal mill operating temperature, Sf a Indicates the moisture content of raw coal; coal mill operating temperature w in The moisture content of raw coal Sf can be measured by temperature sensor a It can be obtained by testing the moisture content of the raw coal before using it.

[0241] S45, according to the raw coal quality Zl y And coal powder quality Zl mf Calculate the coal grinding current I mm , the calculation formula is:

[0242] I mm =k7Zly +k8Zl mf +k9

[0243] Among them, I mm Indicates coal grinding current;

[0244] S46, according to the water evaporation Zf m , coal grinding current I mm , Raw coal mass flow rate L ym , coal powder mass flow rate L mf and the inlet primary air mass flow rate L mar Modeling the Outlet Temperature The expression is:

[0245]

[0246] in, The differential model representing the outlet temperature, k5, k6, k7, k8, k9, k 10 , k 11 , k 12 , k 13 and k 14 Represents heat coefficient; the heat coefficient is obtained by maximum likelihood estimation method, which is a commonly used parameter estimation method in statistics. It estimates unknown parameters by finding parameter values ​​that can make the observed data appear with the highest probability. This step only needs maximum likelihood estimation method to get the desired result, and maximum likelihood estimation method is a commonly used parameter acquisition method, which will not be elaborated here.

[0247] S47, according to the outlet temperature model Get the outlet temperature Wd g Through the method of establishing mathematical models, a mathematical model of the outlet temperature of the coal mill is established according to the internal flow conditions of the coal mill, so that the outlet temperature of the coal mill can be accurately obtained during the change process, which improves the efficiency of obtaining the outlet temperature. The dynamic mathematical model includes the changes of multiple parameters, which increases the accuracy of obtaining the outlet temperature.

[0248] S5, according to the humidity value W and internal power P z Calculate the individual grade evaluation value PZ of the steam turbine ql The evaluation value obtained by the existing weight algorithm is too absolute, and the accuracy of the obtained evaluation value is not high. In step S5, the specific implementation steps are as follows:

[0249] S51, according to the humidity value W and internal power P of the steam turbine at multiple times z , wheel speed N lv and intake pressure p jq Form multiple groups of evaluation matrices and obtain the time t sjThe evaluation matrix Pj under ql , the expression is:

[0250]

[0251] Among them, Pj ql Indicates time t sj The evaluation matrix of the steam turbine is obtained; the humidity value W and the internal power P at multiple times are obtained z , wheel speed N lv and intake pressure p jq Can make the evaluation results more reliable and accurate.

[0252] S52, setting the level division set T based on the historical data of the thermal power plant dj , the expression is:

[0253]

[0254] Among them, T dj represents the hierarchical partition set, T a , T b , T c and T d Respectively represent humidity value W, internal power P z , wheel speed N lv and intake pressure p jq Row vector of rank values, T ai , T bi , T ci and T di They represent the i-th grade classification value respectively; for the evaluation, each parameter has a different evaluation grade, so that different parameters can get more accurate evaluation results, and the parameter unit name in each row is different.

[0255] S53, according to the evaluation matrix Pj ql and the level partition set T dj Calculate the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq The level value of Dj ql , the calculation formula is:

[0256]

[0257] Among them, DJ qlw ,Dj qlPz ,Dj qlN and DJ qlPq Respectively represent the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jqThe grade value, Pj qlw , Pj qlPz , Pj qlN and Pj qlPq Respectively represent the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq Evaluation matrix value; grade value Dj ql It is a fuzzy evaluation calculation method, which transforms the evaluation parameters into a matrix through the membership function. This method can take the factors that are easy to ignore and difficult to quantify into consideration in the evaluation.

[0258] S54, the grade values ​​Dj of the multiple evaluation matrices of the steam turbine ql Composition level matrix Jz dj , the expression is:

[0259]

[0260] Among them, Jz dj Denotes the rank matrix, Dj qlw ,Dj qlPz ,Dj qlN and DJ qlPq Respectively represent humidity value W, internal power P z , wheel speed N lv and intake pressure p jq The grade value is the fuzzy judgment matrix obtained through the membership function.

[0261] S55, based on the turbine humidity value W, internal power P z , wheel speed N lv and intake pressure p jq Obtain different weight values ​​through the hierarchical analysis method to form a weight matrix Qj sgj , and calculate the rank matrix Jz dj The evaluation matrix Pj jz , the expression is:

[0262]

[0263] Among them, Pj jz represents the evaluation matrix, QJ sgj Represents the jth weight value; the weight matrix is ​​obtained by the hierarchical analysis method and combined with the level matrix Jz as the judgment matrix dj Perform calculations.

[0264] S56, according to the evaluation matrix Pj jz Calculate individual rating value PZ h , the calculation formula is:

[0265] PZ h = median(Pj jzl )

[0266] Among them, PZ h represents the individual grade evaluation value, Pj jzl It represents the value of the lth evaluation matrix. By conducting multi-level evaluation on the single equipment of the thermal power plant, and through the grade value and grade matrix, the evaluation method can evaluate the important but difficult to accurately quantify factors, thereby improving the accuracy of the thermal power plant evaluation method and avoiding the one-sided results caused by the overly absolute evaluation of the thermal power plant.

[0267] S6, according to the outlet temperature Wd g Calculate the individual grade evaluation value PZ of the coal mill mm After calculating the evaluation of the steam turbine, the coal mill is calculated. In step S6, the specific implementation method is:

[0268] S61, according to the outlet temperature Wd of the coal mill at multiple times g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Form multiple groups of evaluation matrices and obtain the time t rt The evaluation matrix Pj under mj , the expression is:

[0269]

[0270] Among them, Pj mj Indicates time t rt Evaluation matrix for lower steam turbine;

[0271] S62. Setting a classification set S based on historical data of thermal power plants md , the expression is:

[0272]

[0273] Among them, S md represents the level partition set, S a , S b , S c and S d Respectively represent the outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Row vector of rank values, S ai , S bi , S ci and S diRespectively represent the i-th level classification value;

[0274] S63, according to the evaluation matrix Pj mj and the level partition set S md Calculate the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Level value DM mm , the calculation formula is:

[0275]

[0276]

[0277] Among them, DM m m W d.DM mmZL DM mmnv and DM mmRf Respectively represent the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f The grade value, Pj mjWd , Pj mjZL , Pj mjnv and Pj mjRf Respectively represent the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Evaluation matrix value of ;

[0278] S64, the grade values ​​DM of the multiple evaluation matrices of the coal mill mm Composition level vector MJ dj , the expression is:

[0279]

[0280] Among them, MJ dj represents the level vector;

[0281] S65, based on the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Obtain different weight values ​​through the hierarchical analysis method to form the weight matrix QZ mge , and calculate the rank vector MJ dj The evaluation matrix Pj mm , the expression is:

[0282]

[0283] Among them, Pj mm represents the evaluation matrix, QZ mge represents the e-th weight value;

[0284] S66, according to the evaluation matrix Pj mm Calculate the individual grade evaluation value GT I , the calculation formula is:

[0285] GT I = median(Pj mmk )

[0286] Among them, GT I represents the individual grade evaluation value, Pj mmk Represents the kth evaluation matrix value. If all four values ​​are different, the average of the two numbers in the middle is used to determine the individual grade evaluation value GT I By conducting multi-level evaluation on the individual units and all equipment of thermal power plants, and through the use of grade values ​​and grade matrices, the evaluation method can evaluate important factors that are difficult to accurately quantify, thereby improving the accuracy of the thermal power plant evaluation method and avoiding the one-sided results caused by overly absolute evaluation of thermal power plants.

[0287] S7, according to the individual grade evaluation value PZ of steam turbine and coal mill ql and PZ mm Calculate the comprehensive evaluation value Zh of thermal power plants h After obtaining the single-unit evaluation, it is also necessary to evaluate the entire thermal power plant. In step S7, the specific implementation steps are as follows:

[0288] S71, according to the evaluation matrix Pj of the steam turbine jz and the weight matrix QJ sgj , and the evaluation matrix Ph of the coal mill mm and the weight matrix QZ mge , the maximum eigenvalues ​​λq of the steam turbine and coal mill are obtained by the sum-product method max and λm max ;

[0289] S72, according to the maximum eigenvalue λq max and λm max Calculate the test numerator Cq for the steam turbine and coal mill separately jy and Cm jy , the calculation formula is:

[0290]

[0291] Among them, Cq jy represents the test numerator of the steam turbine, Cm jy represents the test numerator of the coal mill, and m represents the weight matrix QJ sgj The order of p represents the weight matrix QZ mge The order of

[0292] S73, according to the test molecule Cq jy and Cm jy Calculate the consistency test coefficient C of the steam turbine and coal mill respectively qR and C mR , the calculation formula is:

[0293]

[0294] Among them, C qR and C mR Respectively represent the consistency test coefficients of steam turbine and coal mill, C L is the consistency test constant; the consistency test is used to test the consistency between multiple evaluators or multiple evaluation results, and to evaluate whether the results obtained by different methods, different observers or different time points are consistent, so as to make the evaluation results more referenceable and make the evaluation more accurate.

[0295] S74, according to the consistency test coefficient C qR and C mR Obtain consistency test results;

[0296] If C qR <0.1 and C mR <0.1, then both the steam turbine and coal mill meet the consistency test results;

[0297] If C qR ≥0.1, the turbine does not meet the requirements, and the evaluation matrix Pj is obtained again after adjusting the turbine. jz and the weight matrix QJ sgj , and returns to step S71;

[0298] If C mR ≥0.1, the coal mill does not meet the requirements, and the evaluation matrix Pj is obtained again after adjusting the coal mill. mm and the weight matrix QZ mge , and returns to step S71;

[0299] S75. Obtain the evaluation scores R of H experts on the operating parameters of the thermal power plant pb , where R pb Represents the bth evaluation score, according to the evaluation score R pb Calculate the expert weight value Zj d , the calculation formula is:

[0300]

[0301] Among them, Zj d represents the expert weight value, H represents the evaluation score R pb the number of

[0302] S76, according to the expert weight value Zj d Calculate the comprehensive evaluation value Zh h , the calculation formula is:

[0303] Zh jz =Zj d ×Pj jz

[0304] Zh mz =Zj d ×Pj mm

[0305]

[0306] Among them, Zh h Indicates the comprehensive evaluation value, Zh jz and Zh mz denote the transition matrices of the steam turbine and coal mill, respectively, denote the element of the fth transition matrix of the steam turbine, Zh mzr represents the element of the rth transition matrix of the coal mill, F and R represent the number of elements of the transition matrix of the steam turbine and the coal mill respectively, E and Y represent the number of equipment in the steam turbine and the coal mill respectively, U and V represent the number of equipment categories in the thermal power plant respectively. The present invention only provides the evaluation of the two types of equipment, the coal mill and the steam turbine, and the overall evaluation method of the two types of equipment. In the actual evaluation, the coal mill, the coal feeder, the belt conveyor and the pulverized dust fan in the coal transportation system of the thermal power plant can be evaluated one by one, the main burner, the drum water level gauge, the air preheater, the economizer and the superheater of the boiler system of the thermal power plant can be evaluated one by one, and the steam turbine, the circulating water pump, the condenser and the steam turbine system of the thermal power plant can be evaluated one by one. The steam boiler and high and low pressure heaters are evaluated one by one, the generator, main exciter and main transformer of the thermal power plant power generation system are evaluated one by one, and then all the evaluations are evaluated as a whole to obtain the final evaluation result. In the present invention, the coal mill and steam turbine are taken as examples to illustrate the method. By performing multi-level evaluation on the single unit and all equipment of the thermal power plant, and through the grade value and grade matrix, the evaluation method can evaluate the important but difficult to accurately quantify factors, thereby improving the accuracy of the thermal power plant evaluation method, avoiding the one-sided results caused by the thermal power plant evaluation being too absolute, and by adding expert evaluation and multi-level evaluation, the evaluation result has a certain degree of authority.

[0307] S8, according to the comprehensive evaluation value Zh hEvaluate or warn the operation of the thermal power plant. In step S8, the specific implementation steps are as follows:

[0308] S81. Comprehensive evaluation values ​​Zh at different times in the historical data of the thermal power plant h Calculate the average The calculation formula is as follows:

[0309]

[0310] in, Indicates the comprehensive evaluation value Zh h The average value of B represents the comprehensive evaluation value Zh h the number of

[0311] S82, based on the average Calculate the maintenance threshold K, the calculation formula is:

[0312]

[0313] Among them, K represents the maintenance threshold;

[0314] S83, according to the maintenance threshold K and the comprehensive evaluation value Zh h Evaluate the operation of thermal power plants;

[0315] If Zh h >K, the thermal power plant operates well and sends the evaluation results to the thermal power plant monitoring center;

[0316] If Zh h ≤K, the thermal power plant is operating poorly, and an early warning is sent to the thermal power plant monitoring center. By conducting multi-level evaluations on the thermal power plant units and all equipment, and through the grade values ​​and grade matrices, the evaluation method can evaluate the important but difficult to accurately quantify factors, thereby improving the accuracy of the thermal power plant evaluation method and avoiding the one-sided results caused by the thermal power plant evaluation being too absolute. By adding expert evaluation and multi-level evaluation, the evaluation results have a certain degree of authority. At the same time, through early warnings on the evaluation results, the staff can be reminded in time to maintain and repair the thermal power plant equipment, thereby improving the safety and stability of the thermal power plant.

[0317] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0318] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for grading and evaluating the equipment status of a thermal power plant, characterized in that: The method comprises the following steps: S1. Obtain measurement data of a thermal power plant including a steam turbine and a coal mill, and preprocess the measurement data to obtain preprocessed data, wherein the preprocessed data includes a preprocessed image and preliminary processed data; S2. Perform edge detection on the preprocessed image to obtain the diameter D of the pixel point z , and according to the diameter D of the pixel point z Calculate the humidity value W of the turbine steam; S3. Calculate the correction factor M of the steam flow of the steam turbine, and calculate the internal power P of the steam turbine based on the correction factor M. z ; S4. Calculate the coal powder mass flow rate L of the coal mill mf , and according to the coal powder mass flow rate L mf Construct the outlet temperature model of the coal mill and obtain the outlet temperature Wd g ; S5, according to the humidity value W and internal power P z Calculate the individual grade evaluation value PZ of the steam turbine ql ; S6, according to the outlet temperature Wd g Calculate the individual grade evaluation value PZ of the coal mill mm ; S7, according to the individual grade evaluation value PZ of steam turbine and coal mill ql and PZ mm Calculate the comprehensive evaluation value Zh of thermal power plants h ; S8, according to the comprehensive evaluation value Zh h Evaluate or issue early warning on the operation of thermal power plants.

2. The grading evaluation method according to claim 1, characterized in that: In step S1, the specific implementation steps are as follows: S11. Obtain various parameters of various equipment in the thermal power plant and generate measurement data; S12, preprocessing the steam image in the measurement data by a mean filtering method to obtain a preprocessed image; S13, preprocessing the measurement data except the steam image by a data cleaning method to obtain preliminary processing data, and merging the preprocessed image and the preliminary processing data into preprocessed data; The preliminary processing data include the actual steam specific volume ZV, feed water mass flow L md , Superheat and desuperheating water mass flow rate L mg 、Unknown leaked steam mass flow rate L ml , isentropic heat recovery extraction steam mass flow rate L mh , the mass flow rate of steam leakage from the high-pressure cylinder shaft seal under isentropic state L mz , reheating water mass flow rate L mzr , the mass flow rate of steam extraction from the jth stage of the steam turbine L mj , Mass flow rate of heating extraction steam L me , wheel speed N lv and intake pressure p jq , the raw coal quality Zl of the coal mill y , coal powder quality Zl mf , Imported primary air mass flow rate L mar , grinding wheel speed n v And coal powder fineness R f .

3. The grading evaluation method according to claim 1, characterized in that: In step S2, the specific implementation steps are as follows: S21, establish a two-dimensional coordinate system with any pixel point in the preprocessed image as the origin, the horizontal direction as the X-axis, and the vertical direction as the Y-axis, and obtain an image Tu(x, y); S22. Determine the edge function B(x, y) according to the image Tu(x, y). The calculation formula is: Wherein, B(x, y) represents the edge function of the image Tu(x, y), and σ represents the standard deviation of the edge function B(x, y); S23, calculate the first-order directional derivative B of the edge function B(x, y) f , the calculation formula is: in, represents the partial derivative of the marginal function B(x, y) with respect to the variable x, represents the gradient vector of the edge function B(x, y), represents the direction vector of the edge function B(x, y), cosθ and sinθ represent The cosine and sine of the angle θ with the abscissa; S24, image Tu (x, y) and the first-order directional derivative B f Do convolution and calculate the direction parameter F. The calculation formula is: Where, F represents the direction parameter; S25. Set the direction parameter F equal to zero and calculate the edge parameter tanθ. The calculation formula is: Among them, tanθ represents the edge parameter; S26. Calculate the direction parameter F equal to zero based on the edge parameter tanθ The calculation formula is: in, Represents the direction vector when the direction parameter F is equal to zero; S27, through the non-maximum suppression method, under the condition that the direction parameter F is equal to zero The gradient image is processed by double threshold value to obtain the edge image; S28. Obtain the coordinates of two edge pixel points of the same droplet in the edge image at random, and calculate the distance D between the coordinates of the two edge pixel points. c , the expression is: Among them, D c Represents the distance between the coordinates of the cth edge pixel, (x a ,y a )、(x b ,y b ) represent the coordinates of two edge pixels of the droplet in the edge image respectively; S29, the obtained multiple distances D c Sort from large to small, and divide the distance D c The maximum value is taken as the droplet diameter D z , the expression is: D z =max(D c ) Among them, D z represents the diameter of the droplet; S210, according to the diameter D of the droplets in the steam z Calculate volume concentration Tn e , the calculation formula is: Among them, Tn e Indicates volume concentration, Ns(D z ) represents the size distribution function of the liquid droplets in the steam, f and g represent the maximum and minimum diameters of the liquid droplets in the steam, Indicates diameter D z The average value, σ D Indicates diameter D z The standard deviation of S211, according to volume concentration Tn e Calculate the humidity value W of the steam turbine using the following formula: Where W represents the humidity value of the steam turbine, ρ e represents the saturated water density, ρ s Represents the saturated vapor density.

4. The grading evaluation method according to claim 2, characterized in that: In step S3, the specific implementation steps are as follows: S31. Calculate the correction factor M based on the actual steam specific volume ZV. The calculation formula is: Wherein, M represents the correction factor, ZV represents the actual steam specific volume, and ZV' represents the steam specific volume under isentropic expansion; S32, according to the water mass flow L md , Superheat and desuperheating water mass flow rate L mg and unknown leakage steam mass flow rate L ml Calculate the working medium mass flow rate L of the main steam in the isentropic state of the steam turbine mm , the expression is: L mm =L md +L mg -L ml Among them, L mm It represents the working medium mass flow rate of main steam under the isentropic state of the steam turbine; S33, according to the working fluid mass flow L mm Calculate the high pressure cylinder exhaust steam mass flow rate L mt , the calculation formula is: L mt =L mm -ΣL mh -L mz Among them, L mt Indicates the exhaust mass flow rate of high pressure cylinder, L mh is the isentropic heat recovery extraction steam mass flow rate, L mz It indicates the mass flow rate of steam leakage from the high-pressure cylinder shaft seal under isentropic state; S34, according to the high pressure cylinder exhaust steam mass flow L mt Calculate the reheat steam mass flow rate L mrh , the calculation formula is: L mrh =L mt +L mzr Among them, L mrh Represents the reheat steam mass flow rate, L mzr Represents the mass flow rate of reheat desuperheating water; S35, according to the working medium mass flow rate L of the main steam mm Calculate the low pressure cylinder exhaust steam mass flow rate L mc , the calculation formula is: L mc =L mm +L mzr -∑L mj -L mz -L me Among them, L mc Indicates the exhaust mass flow rate of the low-pressure cylinder, L mj represents the mass flow rate of steam extraction at the jth stage of the steam turbine, L me Indicates the mass flow rate of heating extraction steam; S36. Calculate the internal power P of the steam turbine z , the calculation formula is: P l =L mm ×b m +L mrh ×b rh -L mt ×b t -L mc ×b c -L me ×b e -ΣL mj ×b j Among them, P l Indicates the uncorrected power value, P z represents the internal power of the steam turbine, b m 、b rh 、b t 、b c 、b e and b j They respectively represent the specific enthalpy of the mass flow rate of main steam, reheat steam, high-pressure cylinder exhaust steam, low-pressure cylinder exhaust steam, heating extraction steam and turbine j-th stage extraction steam.

5. The grading evaluation method according to claim 2, characterized in that: In step S4, the specific implementation steps are as follows: S41, according to the raw coal quality Zl y And coal powder quality Zl mf , calculate the total internal coal mass Zl of the coal mill zn , the calculation formula is: PLN zn =PLN y +PLN mf Among them, Zl zn It indicates the total coal mass stored in the coal mill; S42, based on the total stored coal mass Zl zn and the inlet primary air mass flow rate L mar Calculate the inlet and outlet pressure difference ΔP a , the calculation formula is: Among them, ΔP a represents the inlet and outlet pressure difference, k1 and k2 represent the model parameters respectively; S43, according to the inlet and outlet pressure difference ΔP a , Raw coal quality Zl y And coal powder quality Zl mf Calculate the raw coal mass flow rate L ym and coal powder mass flow rate L mf , the calculation formula is: L ym =k3ΔP a Zl y L mf =k4ΔP a Zl mf Among them, L ym Indicates the raw coal mass flow rate, L mf represents the mass flow rate of pulverized coal, k3 and k4 represent the model parameters respectively; S44, according to the raw coal mass flow L ym Calculate the moisture evaporation of raw coal Zf m , the calculation formula is: Among them, Zf m Indicates the amount of water evaporated from the raw coal, w in Indicates the coal mill operating temperature, Sf a Indicates the moisture content of raw coal; S45, according to the raw coal quality Zl y And coal powder quality Zl mf Calculate the coal grinding current I mm , the calculation formula is: I mm =k7Zl y +k8Zl mf +k9 Among them, I mm Indicates coal grinding current; S46, according to the water evaporation Zf m , coal grinding current I mm , Raw coal mass flow rate L ym , coal powder mass flow rate L mf and the inlet primary air mass flow rate L mar Modeling the Outlet Temperature The expression is: in, The differential model representing the outlet temperature, k5, k6, k7, k8, k9, k 10 , k 11 , k 12 , k 13 and k 14 represents the heat coefficient; S47, according to the outlet temperature model Get the outlet temperature Wd g .

6. The grading evaluation method according to claim 2, characterized in that: In step S5, the specific implementation steps are as follows: S51, according to the humidity value W and internal power P of the steam turbine at multiple times z , wheel speed N lv and intake pressure p jq Form multiple groups of evaluation matrices and obtain the time t sj The evaluation matrix Pj under ql , the expression is: Among them, Pj ql Indicates time t sj Evaluation matrix for lower steam turbine; S52, setting the level division set T based on the historical data of the thermal power plant dj , the expression is: Among them, T dj represents the level partition set, P a , T b , T c and T d Respectively represent humidity value W, internal power P z , wheel speed N lv and intake pressure p jq Row vector of rank values, T ai , T bi , T ci and T di Respectively represent the i-th level classification value; S53, according to the evaluation matrix Pj ql and the level partition set T dj Calculate the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq The level value of Dj ql , the calculation formula is: Among them, DJ qlw ,Dj qlPz ,Dj qlN and DJ qlPq Respectively represent the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq The grade value, Pj qlw , Pj qlPz , Pj qlN and Pj qlPq Respectively represent the turbine humidity value W and internal power P z , wheel speed N lv and intake pressure p jq Evaluation matrix value of ; S54, the grade values ​​Dj of the multiple evaluation matrices of the steam turbine ql Composition level matrix Jz dj , the expression is: Among them, Jz dj Denotes the rank matrix, Dj qlw ,Dj qlPz ,Dj qlN and DJ qlPq Respectively represent humidity value W, internal power P z , wheel speed N lv and intake pressure p jq The level value of S55, based on the turbine humidity value W, internal power P z , wheel speed N lv and intake pressure p jq Obtain different weight values ​​through the hierarchical analysis method to form the weight matrix QJ sgj , and calculate the rank matrix Jz dj The evaluation matrix Pj jz , the expression is: Among them, Pj jz represents the evaluation matrix, QJ sgj represents the jth weight value; S56, according to the evaluation matrix Pj jz Calculate individual rating value PZ h , the calculation formula is: PZ h =median(Pj jzl ) Among them, PZ h represents the individual grade evaluation value, Pj jzl Represents the lth evaluation matrix value.

7. The grading evaluation method according to claim 2, characterized in that: In step S6, the specific implementation method is: S61, according to the outlet temperature Wd of the coal mill at multiple times g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Form multiple groups of evaluation matrices and obtain the time t rt The evaluation matrix Pj under mj , the expression is: Among them, Pj mj Indicates time t rt Evaluation matrix for lower steam turbine; S62. Setting a classification set S based on historical data of thermal power plants md , the expression is: Among them, S md represents the level partition set, S a , S b , S c and S d Respectively represent the outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Row vector of rank values, S ai , S bi , S ci and S di Respectively represent the i-th level classification value; S63, according to the evaluation matrix Pj mj and the level partition set S md Calculate the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Level value DM mm , the calculation formula is: Among them, DM mmWd DM mmZl DM mmnv and DM mmRf Respectively represent the coal mill outlet temperature Wd g , Raw coal quality ZL y , grinding wheel speed n v And coal powder fineness R f The grade value, Pj mjWd 、Pj mjZL 、Pj mjnv and Pj mjRf Respectively represent the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Evaluation matrix value of ; S64, the grade values ​​DM of the multiple evaluation matrices of the coal mill mm Composition level vector MJ dj , the expression is: Among them, MJ dj represents the level vector; S65, based on the coal mill outlet temperature Wd g , Raw coal quality Zl y , grinding wheel speed n v And coal powder fineness R f Obtain different weight values ​​through the hierarchical analysis method to form the weight matrix QZ mge , and calculate the rank vector MJ dj The evaluation matrix Pj mm , the expression is: Among them, Pj mm represents the evaluation matrix, Qz mge represents the e-th weight value, e = [1, 2, 3, 4]; S66, according to the evaluation matrix Pj mm Calculate the individual grade evaluation value GT I , the calculation formula is: GT I =median(Pj mmk ) Among them, GT I represents the individual grade evaluation value, Pj mmk Represents the kth evaluation matrix value.

8. The grading evaluation method according to claim 7, characterized in that: In step S7, the specific implementation steps are as follows: S71, according to the evaluation matrix Pj of the steam turbine jz and the weight matrix QJ sgj , and the evaluation matrix Pj of the coal mill mm and the weight matrix QZ mge , the maximum eigenvalues ​​λq of the steam turbine and coal mill are obtained by the sum-product method max and λm max ; S72, according to the maximum eigenvalue λq max and λm max Calculate the test numerator Cq for the steam turbine and coal mill separately jy and Cm jy , the calculation formula is: Among them, Cq jy represents the test numerator of the steam turbine, Cm jy represents the test numerator of the coal mill, and m represents the weight matrix QJ sgj The order of p represents the weight matrix QZ mge The order of S73, according to the test molecule Cq jy and Cm jy Calculate the consistency test coefficient C of the steam turbine and coal mill respectively qR and C mR , the calculation formula is: Among them, C qR and C mR Respectively represent the consistency test coefficients of steam turbine and coal mill, C L is the consistency test constant; S74, according to the consistency test coefficient C qR and C mR Obtain consistency test results; If C qR <0.1 and C mR <0.1, then both the steam turbine and coal mill meet the consistency test results; If C qR ≥0.1, the turbine does not meet the requirements, and the evaluation matrix Pj is obtained again after adjusting the turbine. jz and the weight matrix QJ sgj , and returns to step S71; If C mR ≥0.1, the coal mill does not meet the requirements, and the evaluation matrix Pj is obtained again after adjusting the coal mill. mm and the weight matrix QZ mge , and returns to step S71; S75. Obtain the evaluation scores R of H experts on the operating parameters of the thermal power plant pb , where R pb Represents the bth evaluation score, according to the evaluation score R pb Calculate the expert weight value Zj d , the calculation formula is: Among them, Zj d represents the expert weight value, H represents the evaluation score R pb the number of S76, according to the expert weight value Zj d Calculate the comprehensive evaluation value Zh h , the calculation formula is: Zh jz =Zj d ×Pj jz Zh mz =Zj d ×Pj mm Among them, Zh h Indicates the comprehensive evaluation value, Zh jz and Zh mz Denote the transition matrices of the steam turbine and coal mill respectively, Zh jzf represents the element of the fth transition matrix of the steam turbine, Zh mzr represents the element of the rth transition matrix of the coal mill, F and R represent the number of elements of the transition matrices of the steam turbine and the coal mill respectively, E and Y represent the number of equipment in the steam turbine and the coal mill respectively, and U and V represent the number of equipment categories in the thermal power plant respectively.

9. The grading evaluation method according to claim 1, characterized in that: In step S8, the specific implementation steps are as follows: S81. Comprehensive evaluation values ​​Zh at different times in the historical data of the thermal power plant h Calculate the average The calculation formula is as follows: in, Indicates the comprehensive evaluation value Zh h The average value of B represents the comprehensive evaluation value Zh h the number of S82, based on the average Calculate the maintenance threshold K, the calculation formula is: Among them, K represents the maintenance threshold; S83, according to the maintenance threshold K and the comprehensive evaluation value Zh h Evaluate the operation of thermal power plants; If Zh h >K, the thermal power plant operates well and sends the evaluation results to the monitoring center of the thermal power plant; If Zh h ≤K, the thermal power plant is operating poorly and an early warning is sent to the monitoring center of the thermal power plant.

Images