A method, device and equipment for evaluating the health state of a coal mill and a storage medium

Abstract

The application relates to a coal mill health state evaluation method, device, equipment and storage medium, the method comprising the following steps: establishing a coal mill initial dynamic model; determining parameters of the coal mill initial dynamic model according to historical operation data of the coal mill based on a preset method, obtaining a coal mill target dynamic model; inputting a coal mill operation data sequence into the coal mill target dynamic model, determining a coal mill health index initial value according to an output result; and optimizing the coal mill health index initial value according to main measuring point operation data of the coal mill to obtain a health index final value. The application provides a coal mill health state evaluation method, device, equipment and storage medium, the coal mill operation data sequence is input into the coal mill target dynamic model, the health index final value of the coal mill is further determined according to the output result, the operation state of the coal mill is calculated in real time, the health of the coal mill can be monitored throughout the process, and early faults of the coal mill can be found in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mill monitoring, and in particular to a coal mill health state evaluation method, device, equipment and storage medium. BACKGROUND

[0002] As the core equipment of the coal pulverizing system of a coal-fired power plant, the running health state of the coal mill is closely related to the safe and stable operation of the power plant. Although the raw coal delivered from the coal yard has been screened and cleaned, it may still contain impurities such as iron blocks, wood blocks and stone blocks. Moreover, due to the poor working environment on site, the equipment is in a high-load running state for a long time, so that various faults of the coal mill are inevitable, thereby affecting its running health state.

[0003] At present, the real-time monitoring of the coal mill in power plants in China is mostly to install sensors at key positions, such as inlet primary air temperature sensors, outlet temperature sensors, inlet air pressure monitoring sensors, etc., and then set monitoring upper and lower limits for important measuring points. For example, for the outlet temperature sensor of a certain type of medium-speed coal mill, the parameter value limit is set to not less than 65℃ and not higher than 90℃, and an audible and visual signal will be issued on site to warn when the measured value exceeds the limit value.

[0004] In the prior art, the monitoring method of installing sensors at key positions is simple in logic and single in method, and there are numerous measuring points on the coal mill, with dozens of measuring points displayed on the interface of the monitoring system, and the correlation between the measuring points is not clearly explained, so that the on-site operating personnel cannot accurately know the working state of the coal mill through the measuring point data displayed on the interface, especially when the equipment is in the early stage of failure, it is more difficult to judge by the measured value alone. SUMMARY

[0005] Therefore, it is necessary to provide a coal mill health state evaluation method, device, equipment and storage medium to solve the problem that the measuring points measurable by the monitoring method of installing sensors at key positions in the prior art are limited and it is difficult to accurately determine the fault in the early stage of the equipment failure.

[0006] To achieve the above technical purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a coal mill health state evaluation method, comprising:

[0008] establishing an initial dynamic model of the coal mill;

[0009] determining parameters of the initial dynamic model of the coal mill according to historical running data of the coal mill based on a preset method to obtain a target dynamic model of the coal mill;

[0010] The coal mill operation data sequence is input into the coal mill target dynamic model, and the initial value of the coal mill health index is determined according to the output result;

[0011] The initial value of the coal mill health index is optimized according to the operation data of the main measuring point of the coal mill to obtain the final value of the health index.

[0012] In some possible implementations, the coal mill operation data sequence is input into the coal mill target dynamic model, and the initial value of the coal mill health index is determined according to the model output result, including:

[0013] The actual operation data of the coal mill is collected in real time in a preset time sequence to obtain the coal mill operation data sequence;

[0014] The coal mill operation data sequence is input into the coal mill target dynamic model to obtain the model output result and calculate the coal mill parameter deviation matrix;

[0015] The initial value of the coal mill health index is determined according to the historical operation data of the coal mill and the coal mill parameter deviation matrix.

[0016] In some possible implementations, the coal mill operation data sequence is input into the coal mill target dynamic model to obtain the output result and calculate the coal mill parameter deviation matrix, including:

[0017] The coal mill operation data sequence is input into the coal mill target dynamic model to obtain the coal mill parameter calculation value;

[0018] The coal mill parameter calculation value is subtracted from the actual value to obtain the coal mill parameter deviation matrix.

[0019] In some possible implementations, the initial value of the coal mill health index is determined according to the historical operation data of the coal mill and the coal mill parameter deviation matrix, including:

[0020] The coal mill parameter total deviation value is obtained by weighted calculation according to the preset weight and the coal mill parameter deviation matrix;

[0021] The conversion relationship between the coal mill parameter total deviation value and the health index is determined by analyzing the coal mill model and the historical operation data of the coal mill;

[0022] The initial value of the coal mill health index is determined according to the conversion relationship and the coal mill parameter total deviation value.

[0023] In some possible implementations, the initial value of the coal mill health index is optimized according to the operation data of the main measuring point of the coal mill to obtain the final value of the health index, including:

[0024] The main measuring point parameters are divided into a plurality of evaluation intervals according to the operation data of the main measuring point of the coal mill, and the health index optimization rules are established based on the evaluation intervals;

[0025] The health index final value is obtained by optimizing the health index initial value according to the health index optimization rule and the model output result.

[0026] In some possible implementation manners, the main measuring point parameter is divided into a plurality of evaluation intervals according to the main measuring point operation data of the coal mill, and the health index optimization rule is established based on the evaluation intervals, including:

[0027] The safety interval is set according to the main measuring point parameter of the coal mill in normal operation exceeding the preset range;

[0028] The early warning interval and the dangerous interval are respectively set based on the safety interval; different deduction strategies are set when the model output result is in different evaluation intervals.

[0029] In some possible implementation manners, the parameters of the initial dynamic model of the coal mill are determined according to the historical operation data of the coal mill based on a preset method, and the target dynamic model of the coal mill is obtained, including:

[0030] The optimal value range of the dynamic model parameter of the coal mill is determined by first-stage parameter optimization according to the historical operation data of the coal mill;

[0031] The numerical value of the dynamic model parameter of the coal mill is determined by second-stage parameter optimization on the optimal value range of the dynamic model parameter of the coal mill, and the target dynamic model of the coal mill is obtained.

[0032] In a second aspect, the present application further provides an evaluation device for the health state of a coal mill, including:

[0033] An initial model establishing module is configured to establish an initial dynamic model of the coal mill;

[0034] A target model determining module is configured to determine the parameters of the initial dynamic model of the coal mill according to the historical operation data of the coal mill based on a preset method, and obtain a target dynamic model of the coal mill;

[0035] An initial value determining module is configured to input the operation data sequence of the coal mill into the target dynamic model of the coal mill, and determine the health index initial value of the coal mill according to the output result;

[0036] A final value determining module is configured to optimize the health index initial value of the coal mill according to the main measuring point operation data of the coal mill, and obtain the health index final value.

[0037] In a third aspect, the present application further provides an electronic device including a memory and a processor, wherein,

[0038] The memory is configured to store a program;

[0039] The processor is coupled with the memory and is configured to execute the program stored in the memory to implement the steps in the evaluation method for the health state of the coal mill in any of the above implementation manners.

[0040] In a fourth aspect, the present application further provides a computer readable storage medium for storing computer readable programs or instructions, which, when executed by a processor, can realize the steps in the coal mill health state evaluation method in any of the above implementation manners.

[0041] The beneficial effects of the above embodiment are that the present application relates to a coal mill health state evaluation method, device, equipment and storage medium, the method comprising: establishing a coal mill initial dynamic model; determining parameters of the coal mill initial dynamic model according to historical operation data of the coal mill based on a preset method to obtain a coal mill target dynamic model; inputting a coal mill operation data sequence into the coal mill target dynamic model to determine a coal mill health index initial value according to an output result; and optimizing the coal mill health index initial value according to main measurement point operation data of the coal mill to obtain a health index final value. The coal mill health state evaluation method, device, equipment and storage medium provided by the present application can perform real-time calculation on the operation state of the coal mill by inputting a coal mill operation data sequence into the coal mill target dynamic model, determine a coal mill health index initial value according to an output result, and then optimize the coal mill health index initial value according to main measurement point operation data of the coal mill to obtain a health index final value. The change of the coal mill health index final value can be determined to monitor the health of the coal mill throughout the process and understand the health state change of the coal mill, so that early faults of the coal mill can be found in time. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A flowchart of an embodiment of the coal mill health state evaluation method provided by the present application;

[0043] Figure 2 A flowchart of an embodiment of step S103 in the method; Figure 1

[0044] A flowchart of an embodiment of step S203 in the method; Figure 3 Figure 2 A flowchart of an embodiment of step S203 in the method;

[0045] Figure 4 A calculation result diagram of an embodiment of the coal mill health index provided by the present application;

[0046] Figure 5 A structural diagram of an embodiment of the coal mill health state evaluation device provided by the present application;

[0047] Figure 6 A structural diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0048] ​Preferred embodiments of the present application are described in detail below with reference to the attached drawing figures, wherein the application is shown as currently contemplated by the inventor. The application is described and explained with additional specificity and detail through the use of the accompanying drawings in which:

[0049] In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly specifically limited otherwise.

[0050] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. As will be apparent to one of ordinary skill in the art, embodiments described herein can be combined with other embodiments.

[0051] The application provides a coal mill health state evaluation method, device, equipment and storage medium, which are described below respectively.

[0052] Please refer to Figure 1 , Figure 1 The flowchart of an embodiment of the coal mill health state evaluation method provided by the application, a specific embodiment of the application, discloses a coal mill health state evaluation method, comprising:

[0053] S101, establishing a coal mill initial dynamic model;

[0054] S102, determining parameters of the coal mill initial dynamic model according to historical operation data of the coal mill based on a preset method, to obtain a coal mill target dynamic model;

[0055] S103, inputting a sequence of operation data of the coal mill into the coal mill target dynamic model, and determining a coal mill health index initial value according to an output result;

[0056] S104, optimizing the coal mill health index initial value according to operation data of a main measuring point of the coal mill to obtain a health index final value.

[0057] In the above embodiment, the coal mill of a coal-fired power plant is taken as an example for description, and the function of the coal mill of the coal-fired power plant is to grind the raw coal delivered by the coal feeder into qualified coal powder, and then blow the coal powder into the boiler through the primary air system for combustion. The output of the process mainly includes drying output, grinding output and ventilation output, and the main output parameters of the process include outlet temperature, coal mill current and primary air pressure difference, etc.

[0058] The model built by the application is based on the following assumptions:

[0059] 1) Only raw coal and coal powder exist in the coal mill;

[0060] 2) The separation process of coal particles is not considered;

[0061] 3) The internal flow variation of the mill is ignored;

[0062] 4) The heat transfer between the mill and the external environment is ignored.

[0063] Based on the above conditions, the dynamic model of the mill considering the synergistic effect of the three outputs is established. The input parameters of the model are the coal feed rate, the inlet primary air flow, the inlet primary air temperature and the grinding pressure difference, and the output parameters are the outlet temperature, the mill current and the primary air pressure difference.

[0064]

[0065]

[0066] W pf = K3AP pa M pf ; (3)

[0067] W gp = O grind - O reac ; (4)

[0068]

[0069] I = K6M pf + K7M c + K8W gp + K9; (6)

[0070]

[0071]

[0072]

[0073] The parameters of the model are explained as follows:

[0074] W c Coal feed rate (kg / s);

[0075] W air Inlet primary air flow (kg / s);

[0076] W gp Grinding pressure difference (mpa);

[0077] T in Inlet primary air temperature (℃);

[0078] O grind Grinding oil pressure (mpa);

[0079] O reac Reaction force oil pressure (MPa);

[0080] M c Raw coal mass in mill (kg);

[0081] M pf Coal powder mass in mill (kg);

[0082] θ cm Raw coal moisture (%);

[0083] γ res Coal powder moisture (%);

[0084] W pf Outlet coal powder flow (kg / s);

[0085] Evaporation amount of coal moisture (kg / s);

[0086] ΔP pa Primary air pressure difference (mbar);

[0087] I Coal mill current (A);

[0088] T out Outlet temperature (℃);

[0089] K i Parameters to be identified; i = 1, 2, …, 19.

[0090] Equations (1) and (2) are mass balance equations of coal, (K1+K2Wgp) represents the efficiency of raw coal conversion into coal powder. Equation (3) represents the mass of coal powder carried by primary air. Equation (4) represents the calculation method of mill pressure difference. Equation (7) defines the moisture balance in the coal mill, and equation (8) represents the moisture evaporated in the milling process. Equations (5), (6) and (9) respectively define the three output parameters of the model. Ki (i = 1, 2, …, 19) are the parameters to be identified.

[0091] The preset method in the embodiment is a genetic algorithm. Since the model contains many parameters to be identified and the optimization range is wide, in order to improve the convergence speed of the parameter identification process and improve the accuracy of the result, the application designs a two-stage parameter optimization method based on a genetic algorithm.

[0092] Compared with the prior art, the embodiment provides an evaluation method for the health state of a coal mill, which comprises the following steps: establishing an initial dynamic model of the coal mill; determining dynamic model parameters of the coal mill according to historical operation data of the coal mill based on a preset method, to obtain a target dynamic model of the coal mill; inputting a sequence of operation data of the coal mill into the target dynamic model of the coal mill, and determining an initial value of a health index of the coal mill according to an output result; and optimizing the initial value of the health index of the coal mill according to operation data of a main measuring point of the coal mill to obtain a final value of the health index. The evaluation method for the health state of the coal mill, the device, the equipment and the storage medium provided by the embodiment can perform real-time calculation on the operation state of the coal mill by inputting the sequence of operation data of the coal mill into the target dynamic model of the coal mill, determine the initial value of the health index of the coal mill according to the output result, and then optimize the initial value of the health index of the coal mill according to the operation data of the main measuring point of the coal mill to obtain the final value of the health index. The change of the final value of the health index of the coal mill can be determined, the health of the coal mill can be monitored throughout the process, the change of the health state of the coal mill can be understood, and early faults of the coal mill can be found in time.

[0093] Please refer to Figure 2 , Figure 2 for Figure 1 an embodiment of step S103, in some embodiments of the present application, the sequence of operation data of the coal mill is input into the target dynamic model of the coal mill, the initial value of the health index of the coal mill is determined according to the output result of the model, and the method comprises the following steps:

[0094] S201, real-time collection of actual operation data of the coal mill at a preset time sequence to obtain a sequence of operation data of the coal mill;

[0095] S202, inputting the sequence of operation data of the coal mill into the target dynamic model of the coal mill to obtain a model output result and calculate a parameter deviation matrix of the coal mill;

[0096] S203, determining an initial value of a health index of the coal mill according to historical operation data of the coal mill and the parameter deviation matrix of the coal mill.

[0097] In the above embodiment, the actual operation data of the coal mill is collected in real time at a preset time sequence, that is, the real-time data of the coal mill is collected for 60 s continuously and with an interval of 3 s. The actual operation data of the coal mill is collected in real time, and the change process of the health state of the coal mill in the whole operation process can be understood through these data.

[0098] It should be noted that the real-time data of the coal mill can be collected by a sensor or by other collection methods. Data collection is a prior art, and the present application does not need to be described in detail. As long as the data collection can be completed according to the collection requirements.

[0099] The mill operation data sequence is input into the mill target dynamic model, the three parameters of outlet temperature, mill current and primary air pressure difference are calculated by the mill target dynamic model, the calculated parameters are subtracted from the parameter values at the corresponding time, and a mill parameter deviation matrix is obtained, which records the real-time parameter conditions of the main measuring points of the mill.

[0100] The conversion relationship is set according to the multiple parameter conditions of the mill in normal operation and various faults determined according to the historical operation data of the mill, and the mill health index initial value is determined by the conversion relationship and the mill parameter deviation matrix.

[0101] In some embodiments of the present application, the mill operation data sequence is input into the mill target dynamic model, the output result is obtained and the mill parameter deviation matrix is calculated, including:

[0102] The mill operation data sequence is input into the mill target dynamic model, and the mill parameter calculation value is obtained;

[0103] The mill parameter calculation value is subtracted from the actual value to obtain the mill parameter deviation matrix.

[0104] In the above embodiment, the mill parameter calculation value is subtracted from the actual value to obtain the mill parameter deviation matrix, the mill parameter deviation matrix reflects the deviation between the predicted parameter condition of the mill target dynamic model and the actual condition, and reflects the deviation between the predicted parameter of the mill target dynamic model and the parameter in normal operation of the mill. The health condition of the mill is finally determined by the mill parameter deviation matrix.

[0105] Please refer to Figure 3 , Figure 3 for Figure 2 an embodiment of step S203, in some embodiments of the present application, the mill health index initial value is determined according to the mill historical operation data and the mill parameter deviation matrix, including:

[0106] S301, according to the preset weight and the mill parameter deviation matrix, the mill parameter total deviation value is calculated by weighting calculation;

[0107] S302, the mill type and the mill historical operation data are analyzed to determine the conversion relationship between the mill parameter total deviation value and the health index;

[0108] S303, the mill health index initial value is determined according to the conversion relationship and the mill parameter total deviation value.

[0109] In the above embodiment, the real-time deviation of the three parameter output values is respectively assigned a weight, and the total deviation value is obtained by weighted summation, and the calculation formula is as follows:

[0110]

[0111] wherein D is the total deviation value, I cal (i) and is the model output of the i-th group of data calculated by the model, T out (i), I(i) and ΔP pa (i) is the true value of the i-th group of data, N represents the total number of data, and ω represents the calculation weight.

[0112] It should be noted that the preset weight can be set according to actual conditions, and the weight can be different for different coal mills, and the present application does not make further limitation.

[0113] At the same time, according to the analysis of the historical running characteristics and deviation data of this type of coal mill, the conversion relationship between the coal mill deviation and the health index is designed. It can be understood that the health values of the parameters of different types of coal mills are different.

[0114] As a preferred embodiment of the present application, according to the running characteristics of different equipment, for example, according to the distribution of the deviation value calculated according to the historical running data of a certain equipment, the total deviation value is converted into a scalar value of 0 to 50, and then 100 is subtracted from the converted scalar value to obtain the health index initial value. It can be understood that the calculation rule of the health index initial value can also be adjusted according to the specific situation, and the present application does not make further limitation.

[0115] In some embodiments of the present application, the health index final value is obtained by optimizing the health index initial value of the coal mill according to the running data of the main measuring point of the coal mill, including:

[0116] According to the running data of the main measuring point of the coal mill, the main measuring point parameters are divided into a plurality of evaluation intervals, and the health index optimization rule is established based on the evaluation intervals;

[0117] According to the health index optimization rule and the model output result, the health index initial value of the coal mill is optimized to obtain the health index final value.

[0118] In the above embodiment, in order to improve the sensitivity of the coal mill health state index to known obvious faults, the threshold limit of the outlet temperature, the coal mill current and the primary air pressure difference is set as part of the health state index calculation, that is, the main measuring point parameter, which can better reflect the running health condition of the coal mill. A plurality of evaluation intervals are divided by the normal value of the main measuring point parameter, and the health index optimization rule is established according to the evaluation intervals.

[0119] As a preferred embodiment, the output results of 20 coal mill target dynamic models are averaged, the initial value of the coal mill health index is optimized through the average value and the health index optimization rule, the final value of the coal mill health index is determined, and the accuracy of the health condition assessment of the coal mill is improved.

[0120] In some embodiments of the present application, the main measuring point parameters are divided into several evaluation intervals according to the main measuring point operation data of the coal mill, and the health index optimization rule is established based on the evaluation intervals, including:

[0121] The safety interval is set according to the main measuring point parameters of the coal mill when it is running normally beyond the preset range;

[0122] The warning interval and the danger interval are set based on the safety interval; different deduction strategies are set when the model output results are in different evaluation intervals.

[0123] In the above embodiment, the outlet temperature of the coal mill is taken as an example for illustration, the preset range is 95%, the operation site alarm limit is that the outlet temperature value is lower than 65 DEG C or higher than 90 DEG C, and through analysis of the real-time operation data of the coal mill in the past year, it can be known that when the coal mill is running normally, 95% of the data are greater than 78.90 DEG C, and 95% of the data are lower than 88.32 DEG C, therefore, the measuring point limit value operation value interval is divided into [78.9, 88.4], [70, 90], [65, 90], which are safety interval, warning interval and danger interval respectively.

[0124] When the average value of the outlet temperature output by the coal mill target dynamic model is located in the interval [78.9, 88.4], the initial value of the health index is deducted by 0; when the average value is not located in [78.9, 88.4] but in [70, 90], the initial value of the health index is deducted by 0.5; when the average value is not located in [70, 90] but in [65, 90], the initial value of the health index is deducted by 1; if the average value is lower than 65 DEG C or higher than 90 DEG C, the initial value of the health index is deducted by 1.5, and the rest of the main measuring points are appropriately deducted in the same way, but the total deduction score is not higher than 5.

[0125] The final value of the coal mill health index is determined through the above optimization method, and the accuracy of the health condition assessment of the coal mill is improved.

[0126] The above coal mill health assessment method is experimentally tested in the present application. The test method includes inputting the historical operation data of the coal mill before and after maintenance, inputting the historical data of the coal mill before and after known failure, and inputting the randomly sampled annual operation data of the coal mill for verification.

[0127] Please refer to Figure 4 , Figure 4A schematic diagram of a calculation result of an embodiment of the coal mill health index provided by the application, Figure 4 The health index calculated according to the actual operation data of the coal mill in a certain period of time shows that the calculated health index gradually decreases from about 85 to 79, indicating that the running health degree of the coal mill is decreasing.

[0128] A large amount of data test proves that the health index of the coal mill before maintenance is obviously lower than the health index after maintenance; the health index before and after the fault occurs is gradually reduced from more than 85 to less than 70; and after analyzing the annual data, it is found that when the running state of the coal mill is stable and the values of each measuring point are in a normal state, the health index of the coal mill is almost higher than 85, and when the coal mill appears a fault, the health index is lower than 70.

[0129] In some embodiments of the application, based on a preset method, parameters of an initial dynamic model of the coal mill are determined according to historical operation data of the coal mill, and a target dynamic model of the coal mill is obtained, including:

[0130] The optimal value range of the dynamic model parameters of the coal mill is determined by first-stage parameter optimization according to the historical operation data of the coal mill;

[0131] The numerical value of the dynamic model parameters of the coal mill is determined by second-stage parameter optimization on the optimal value range of the dynamic model parameters of the coal mill, and a target dynamic model of the coal mill is obtained.

[0132] In the above embodiments, the purpose of the first stage is to find the approximate range of the optimal value of each parameter, so the mutation rate of the individual and the updating range of the parameter are larger. The identification result of the previous stage is taken as the reference range for the initialization of the individual in the population in the second stage, and the purpose of this stage is to find the model parameters meeting the requirements, and the mutation rate of the individual and the updating range of the parameter value are smaller, and the crossover rate is higher.

[0133] It should be noted that the genetic algorithm optimization belongs to the prior art, and related materials in the prior art have been introduced in detail, and the application will not be described in detail.

[0134] The actual operation data of the coal mill in a coal-fired power plant after maintenance and replacement of worn parts are selected as the parameter identification data set, the sampling period of the data set is 3s, and there are 10800 groups of data. In addition, the data of a certain period of time are selected as the model test data set, and the sampling period is also 3s, and there are 28800 groups of data. The fitness function calculation formula of the parameter optimization process is as follows:

[0135]

[0136] Wherein, f is the individual fitness function value, I Max And is the maximum value of the corresponding parameter in the data set, I Min and is the minimum value. I cal (i) and is the model output of the i-th group of data calculated by the model, T out (i), I(i) and ΔP pa (i) is the true value of the i-th group of data, N represents the total number of data, and ω represents the calculation weight.

[0137] Since the coal mill current value has the characteristics of large instantaneous fluctuation, it is difficult to accurately calculate the single time value thereof, but the calculation result of the model built in the present application is basically located at the center position of the fluctuation, and can better reflect the change trend. Table 1 is the parameter value finally identified in the present research.

[0138] Table 1 parameter identification result

[0139]

[0140] In order to better implement the coal mill health condition evaluation method in the embodiment of the present application, on the basis of the coal mill health condition evaluation method, please refer to Figure 5 , Figure 5 Fig. 1 is a structural schematic diagram of an embodiment of the coal mill health condition evaluation device provided by the present application, and the embodiment of the present application provides a coal mill health condition evaluation device 500, which comprises:

[0141] An initial model establishing module 510 is configured to establish an initial dynamic model of the coal mill.

[0142] A target model determining module 520 is configured to determine parameters of the initial dynamic model of the coal mill based on a preset method according to historical operation data of the coal mill, so as to obtain a target dynamic model of the coal mill.

[0143] An initial value determining module 530 is configured to input a sequence of operation data of the coal mill into the target dynamic model of the coal mill, and determine an initial value of a health index of the coal mill according to an output result.

[0144] A final value determining module 540 is configured to optimize the initial value of the health index of the coal mill according to operation data of a main measuring point of the coal mill, so as to obtain a final value of the health index.

[0145] It should be noted that the device 500 provided by the above embodiment can implement the technical solutions described in the above method embodiments, and the principles of the specific implementation of the above modules or units can be referred to the corresponding contents in the above method embodiments, which will not be described here.

[0146] Please refer to Figure 6 , Figure 6A structural schematic diagram of an electronic device is provided for the embodiments of the present application. Based on the above-mentioned coal mill health condition assessment method, the present application also correspondingly provides a coal mill health condition assessment device. The coal mill health condition assessment device can be a mobile terminal, a desktop computer, a notebook computer, a palm computer, a server, and other computing devices. The coal mill health condition assessment device comprises a processor 610, a memory 620, and a display 630. Figure 6 Only part of the components of the electronic device are shown, but it should be understood that all the shown components are not required to implement, and more or less components can be alternatively implemented.

[0147] The memory 620 can be an internal storage unit of the coal mill health condition assessment device in some embodiments, such as a hard disk or a memory of the coal mill health condition assessment device. The memory 620 can also be an external storage device of the coal mill health condition assessment device in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Further, the memory 620 can include both the internal storage unit and the external storage device of the coal mill health condition assessment device. The memory 620 is used to store application software and various data installed on the coal mill health condition assessment device, such as program codes installed on the coal mill health condition assessment device. The memory 620 can also be used to temporarily store data that has been output or will be output. In an embodiment, the memory 620 stores a coal mill health condition assessment program 640, which can be executed by the processor 610 to implement the coal mill health condition assessment method of the embodiments of the present application.

[0148] The processor 610 can be a central processing unit (CPU), a microprocessor, or other data processing chip in some embodiments, which is used to run program codes or process data stored in the memory 620, such as to execute the coal mill health condition assessment method.

[0149] The display 630 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, and the like in some embodiments. The display 630 is used to display information of the coal mill health condition assessment device and to display a visualized user interface. The components 610-630 of the coal mill health condition assessment device communicate with each other through a system bus.

[0150] In an embodiment, the steps in the above-described method of evaluating the health condition of the coal mill are implemented when the processor 610 executes the evaluation program 640 of the health condition of the coal mill in the memory 620.

[0151] The embodiment also provides a computer-readable storage medium having stored thereon an evaluation program of the health condition of the coal mill, which, when executed by a processor, implements the following steps:

[0152] establishing an initial dynamic model of the coal mill;

[0153] determining parameters of the initial dynamic model of the coal mill according to historical operation data of the coal mill based on a preset method, to obtain a target dynamic model of the coal mill;

[0154] inputting a sequence of operation data of the coal mill into the target dynamic model of the coal mill, and determining an initial value of the health index of the coal mill according to an output result;

[0155] optimizing the initial value of the health index of the coal mill according to operation data of a main measuring point of the coal mill to obtain a final value of the health index.

[0156] In summary, the embodiment provides a method, device, equipment and storage medium for evaluating the health condition of a coal mill, which includes: establishing an initial dynamic model of the coal mill; determining parameters of the initial dynamic model of the coal mill according to historical operation data of the coal mill based on a preset method, to obtain a target dynamic model of the coal mill; inputting a sequence of operation data of the coal mill into the target dynamic model of the coal mill, and determining an initial value of the health index of the coal mill according to an output result; and optimizing the initial value of the health index of the coal mill according to operation data of a main measuring point of the coal mill to obtain a final value of the health index. The method, device, equipment and storage medium for evaluating the health condition of the coal mill can calculate the running state of the coal mill in real time by inputting a sequence of operation data of the coal mill into the target dynamic model of the coal mill, determine an initial value of the health index of the coal mill according to an output result, and then optimize the initial value of the health index of the coal mill according to operation data of a main measuring point of the coal mill to obtain a final value of the health index. The change in the final value of the health index of the coal mill can be determined, and the health condition of the coal mill can be monitored throughout the process to understand the change in the health condition of the coal mill, so that early faults of the coal mill can be found in time.

[0157] The above describes only the preferred embodiments of the present application, but the protection scope of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed by the present application can be easily thought of by those skilled in the art, which should be covered within the protection scope of the present application.

Claims

1. A method of assessing the health of a coal mill, characterised by, The application relates to a coal mill health index determination method and device. The initial dynamic model of the coal mill is established, and the model input parameters are coal supply, inlet primary air flow, inlet primary air temperature and grinding pressure difference, and the output parameters are outlet temperature, coal mill current and primary air pressure difference. ；(1) ；（2） ； (3) ； (4) ；(5) ； (6) ；(7) ；(8) (9) The parameters of the model are explained as follows: W c for the coal quantity (kg / s); W air for the inlet primary air flow (kg / s); W gp is the mill differential pressure (MPa); T in For inlet primary air temperature (°C); O grind To mill oil pressure (MPa); O reac Reaction force oil pressure (MPa) M c M is the mass of the raw coal (kg); M pf M is the mass of the coal powder (kg); θ cm is the moisture content of the raw coal (%) ; gamma res is the moisture content of the coal fines (%) W pf Qout is the outlet coal flow rate (kg / s); M is the coal moisture evaporation amount (kg / s); ΔP pa is the pressure difference (mbar) for primary air; I is the current of the coal mill (A); T out for the outlet temperature (°C); K i for the parameters to be identified; i = 1, 2,... 19; Equations (1) and (2) are mass balance equations of the coal, (K1+K2Wgp) represents the conversion efficiency of the raw coal into the coal powder; equation (3) represents the mass of the coal powder carried by the primary air; equation (4) represents the calculation method of the grinding pressure difference; equation (7) defines the water balance in the coal mill, equation (8) represents the water evaporation in the coal making process; equations (5), (6) and (9) respectively define the three output parameters of the model; and Ki (i=1, 2, …, 19) is the parameter to be identified. The parameters of the initial dynamic model of the coal mill are determined according to the historical operation data of the coal mill based on a preset method, and a target dynamic model of the coal mill is obtained. The operation data sequence of the coal mill is input into the target dynamic model of the coal mill, and the initial value of the health index of the coal mill is determined according to the output result. The initial value of the health index of the coal mill is optimized according to the operation data of the main measuring point of the coal mill to obtain the final value of the health index, including: the main measuring point parameters are divided into a plurality of evaluation intervals according to the operation data of the main measuring point of the coal mill, and a health index optimization rule is established based on the evaluation intervals; and the initial value of the health index of the coal mill is optimized to obtain the final value of the health index according to the health index optimization rule and the model output result.

2. The method of assessing the health of a coal mill as claimed in claim 1, wherein, The operation data sequence of the coal mill is input into the target dynamic model of the coal mill, and the initial value of the health index of the coal mill is determined according to the output result. The actual operation data of the coal mill is collected in real time in a preset time sequence to obtain the operation data sequence of the coal mill; The operation data sequence of the coal mill is input into the target dynamic model of the coal mill to obtain the model output result and calculate the parameter deviation matrix of the coal mill; The initial value of the health index of the coal mill is determined according to the historical operation data of the coal mill and the parameter deviation matrix of the coal mill.

3. The method of assessing the health of a coal mill as claimed in claim 2, wherein, The operation data sequence of the coal mill is input into the target dynamic model of the coal mill to obtain the model output result and calculate the parameter deviation matrix of the coal mill; The operation data sequence of the coal mill is input into the target dynamic model of the coal mill to obtain the model output result and calculate the parameter deviation matrix of the coal mill; The initial value of the health index of the coal mill is determined according to the historical operation data of the coal mill and the parameter deviation matrix of the coal mill.

4. The method of assessing the health of a coal mill as claimed in claim 3 wherein, The total deviation value of the parameters of the coal mill is obtained by weighted calculation according to a preset weight and the parameter deviation matrix of the coal mill; The conversion relationship between the total deviation value of the parameters of the coal mill and the health index is determined by analyzing the model of the coal mill and the historical operation data of the coal mill; The initial value of the health index of the coal mill is determined according to the conversion relationship and the total deviation value of the parameters of the coal mill. The main measuring point parameters are divided into a plurality of evaluation intervals according to the operation data of the main measuring point of the coal mill, and a health index optimization rule is established based on the evaluation intervals; and the initial value of the health index of the coal mill is optimized to obtain the final value of the health index according to the health index optimization rule and the model output result.

5. The method of assessing the health of a coal mill as claimed in claim 1, wherein, ​ According to the main measuring point parameter of the coal mill normal operation exceeding the preset range, a safety interval is set; Based on the safety interval, a pre-warning interval and a dangerous interval are set respectively; when the model output result is in different evaluation intervals, different deduction strategies are set.

6. The method of assessing the health of a coal mill as claimed in claim 1, wherein, According to the preset method, the parameters of the initial dynamic model of the coal mill are determined according to the historical operation data of the coal mill, and a target dynamic model of the coal mill is obtained, including: According to the historical operation data of the coal mill, a first-stage parameter optimization is performed to determine the optimal value range of the dynamic model parameters of the coal mill; The optimal value range of the dynamic model parameters of the coal mill is subjected to a second-stage parameter optimization to determine the numerical value of the dynamic model parameters of the coal mill, and a target dynamic model of the coal mill is obtained.

7. An apparatus for evaluating a health state of a coal mill, for executing the method for evaluating the health state of the coal mill according to any one of claims 1 to 6, characterized by, It includes: An initial model establishing module is configured to establish an initial dynamic model of the coal mill; A target model determining module is configured to determine the parameters of the initial dynamic model of the coal mill according to the historical operation data of the coal mill based on a preset method, and obtain a target dynamic model of the coal mill; An initial value determining module is configured to input the operation data sequence of the coal mill into the target dynamic model of the coal mill, and determine an initial value of the health index of the coal mill according to the output result; A final value determining module is configured to optimize the initial value of the health index of the coal mill according to the operation data of the main measuring point of the coal mill to obtain a final value of the health index.

8. An electronic device, comprising: It includes a memory and a processor, wherein, The memory is configured to store a program; The processor is coupled with the memory and is configured to execute the program stored in the memory to implement the steps in the coal mill health state evaluation method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer readable program or instruction is stored, and when the program or instruction is executed by a processor, the steps in the coal mill health state evaluation method of any one of claims 1 to 6 can be implemented.

Images