Medium-speed coal mill ignition early warning method, device and system and storage medium

Abstract

The invention discloses a medium-speed coal mill ignition early warning method, device and system and a storage medium. The method, device and system are used for coal mill ignition early warning. The method comprises the steps that in the running process of the medium-speed coal mill, various preset parameters of the medium-speed coal mill are obtained; judging whether the medium-speed coal mill has an ignition risk or not according to at least one preset parameter of the medium-speed coal mill; and when the medium-speed coal mill has the ignition risk, an early warning prompt is given out. According to the scheme, whether the coal mill has the ignition risk or not is judged through the multiple preset parameters, and the accuracy and real-time performance of coal mill ignition early warning are improved.

Description

Technical Field

[0001] The present application relates to the field of safety monitoring technology, and in particular to a medium-speed coal mill fire warning method, device, system and storage medium. Background Art

[0002] Medium-speed coal mills are core equipment in a thermal power plant's pulverizing system, and their operating status directly impacts boiler combustion efficiency and unit safety. A pulverizer operating abnormality, such as a fire, can rapidly disrupt the pulverizing system's equilibrium, triggering a chain reaction that threatens unit safety. Existing technologies rely solely on a single parameter monitoring model, setting fixed thresholds to trigger alarms. This makes it difficult to fully capture fire risks under complex operating conditions. Alternatively, manual intervention and delayed response prevent real-time threshold updates, forcing some systems to require manual confirmation of alarms before action is taken.

[0003] Therefore, how to provide a medium-speed coal mill ignition method to improve the accuracy and real-time performance of coal mill ignition warning has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The present application provides a medium-speed coal mill fire warning method, device, system and storage medium to improve the accuracy and real-time performance of the coal mill fire warning.

[0005] The present application provides a medium-speed coal mill fire early warning method, comprising:

[0006] During the operation of the medium-speed coal mill, various preset parameters of the medium-speed coal mill are obtained;

[0007] determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill;

[0008] When there is a fire risk in the medium-speed coal mill, an early warning will be issued.

[0009] In one embodiment, when the preset parameters include an expected value of the grinding bowl pressure difference, the obtaining of multiple preset parameters of the medium-speed coal mill includes:

[0010] Monitor the operation of the grinding system;

[0011] When the grinding system is put into operation, the fire alarm function is activated;

[0012] When the fire alarm function is activated, the primary air volume, coal powder mass flow rate, speed and separator pressure difference of the medium-speed coal mill are obtained;

[0013] Determining an expected value of the grinding bowl differential pressure of the medium-speed coal mill according to the primary air volume, coal powder mass flow rate, rotation speed, and separator pressure difference;

[0014] The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes:

[0015] Determine the deviation between the expected value of the grinding bowl differential pressure of the medium-speed coal mill and the actual value of the grinding bowl differential pressure of the medium-speed coal mill;

[0016] When the deviation is greater than a first dynamic threshold, it is determined that the medium-speed coal mill has a fire risk and an early warning message is issued, wherein the first dynamic threshold is obtained by a moving standard deviation of the deviation.

[0017] In one embodiment, when the preset parameters include temperature difference and temperature rise rate, the steps of obtaining multiple preset parameters of the medium-speed coal mill include:

[0018] Obtaining the hot primary air volume, hot primary air temperature, cold primary air volume, cold primary air temperature and actual outlet temperature of the medium-speed coal mill;

[0019] Substituting the hot primary air volume, hot primary air temperature, cold primary air volume and cold primary air temperature of the medium-speed coal mill into an outlet temperature model to determine a theoretical outlet temperature value of the medium-speed coal mill;

[0020] Calculating a temperature difference based on an actual outlet temperature value and a theoretical outlet temperature value of the medium-speed coal mill, and calculating a temperature rise rate based on the actual outlet temperature value;

[0021] The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes:

[0022] When the temperature difference exceeds a preset threshold or the temperature rise rate exceeds a normal temperature rise rate range, it is determined that the outlet temperature of the medium-speed coal mill has abnormally increased;

[0023] When the outlet temperature of the medium-speed coal mill increases abnormally, it is determined that the medium-speed coal mill has a fire risk.

[0024] In one embodiment, when the preset parameters include powder pipe blockage, obtaining multiple preset parameters of the medium-speed coal mill includes:

[0025] Obtain the total primary air pressure of the medium-speed coal mill and the primary air flow of each powder pipe;

[0026] Determine the current working condition based on the moving average of the total primary air pressure;

[0027] The weight coefficient of each powder hose air volume to the total air volume is calculated based on the moving average of the primary air flow of each powder hose;

[0028] Determine whether the powder hose is blocked based on the current working conditions and the weight coefficient of each powder hose air volume to the total air volume;

[0029] The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes:

[0030] When the powder pipe is blocked, it is determined that the medium-speed coal mill has a fire risk.

[0031] In one embodiment, the weight coefficient of each powder hose air volume to the total air volume is calculated based on the moving average of the primary air flow of each powder hose, including:

[0032] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0033]

[0034] Among them, W i,current Indicates the weight coefficient of the i-th powder hose air volume to the total air volume; F i,MA Represents the moving average of the primary air flow rate of the i-th pipeline.

[0035] In one embodiment, when the preset parameters include safety information of the primary air system, the obtaining of multiple preset parameters of the medium-speed coal mill includes:

[0036] Obtain primary air inlet temperature, primary air temperature rise rate, valve failure, and valve jam detection results;

[0037] Determining safety information of the primary air system based on at least one of the primary air inlet temperature, the primary air temperature rise rate, valve failure, and valve jam detection results;

[0038] The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes:

[0039] When at least one of the following conditions occurs, it is determined that there is a fire risk in the medium-speed coal mill:

[0040] The primary air inlet temperature is greater than the primary air explosion temperature of the coal mill;

[0041] The primary air temperature rise rate is greater than the maximum temperature rise rate of the primary air system;

[0042] The valve failure detection result indicates that the valve has failed;

[0043] The valve sticking test result indicates that the valve is stuck.

[0044] In one embodiment, when the preset parameters include a medium-speed coal mill purge result, determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes:

[0045] acquire the last historical purging result of the medium-speed coal mill;

[0046] when the historical purging result represents a failure of the medium-speed coal mill purging, determine that the medium-speed coal mill has a fire risk.

[0047] In an embodiment, the purging result judgment process is as follows:

[0048] when the coal mill meets the purging condition, determine the steam type for purging the coal mill according to the coal type information of the residual coal powder in the coal mill;

[0049] inject the purging steam of the corresponding type into the coal mill;

[0050] detect whether the injected steam type and steam pressure are qualified;

[0051] when both the steam type and steam pressure are qualified, judge whether the steam flow meets the minimum purging steam flow requirement;

[0052] when the steam flow meets the minimum purging steam flow requirement, time the purging duration;

[0053] during the purging process, monitor the internal pressure of the coal mill, and adjust the steam pressure according to the internal pressure of the coal mill, so that the internal pressure of the coal mill rises at a specific rate;

[0054] when the timed purging duration reaches the preset duration, monitor the oxygen content in the coal mill;

[0055] when the oxygen content in the coal mill is lower than the preset content, determine that the purging is successful.

[0056] The application also provides a medium-speed coal mill fire warning device, comprising:

[0057] an acquisition module, configured to acquire a plurality of preset parameters of the medium-speed coal mill during the operation of the medium-speed coal mill;

[0058] a judgment module, configured to judge whether the medium-speed coal mill has a fire risk according to at least one preset parameter of the medium-speed coal mill;

[0059] a warning module, configured to issue a warning prompt when the medium-speed coal mill has a fire risk.

[0060] In an embodiment, when the preset parameters include a mill bowl differential pressure expectation value, the acquisition module comprises:

[0061] a monitoring submodule, configured to monitor the commissioning of the grinding system;

[0062] an activation submodule, configured to activate the fire alarm function when the grinding system has been commissioned;

[0063] The first obtaining sub-module is configured to obtain the primary air volume, the pulverized coal mass flow, the rotating speed, and the pressure difference of the separator of the medium-speed coal mill when the fire alarm function is activated.

[0064] The first determining sub-module is configured to determine the expected value of the differential pressure of the grinding bowl of the medium-speed coal mill according to the primary air volume, the pulverized coal mass flow, the rotating speed, and the pressure difference of the separator.

[0065] The judging module comprises:

[0066] The second determining sub-module is configured to determine the deviation of the expected value of the differential pressure of the grinding bowl of the medium-speed coal mill from the actual value of the differential pressure of the grinding bowl of the medium-speed coal mill.

[0067] The second determining sub-module is further configured to determine that the medium-speed coal mill has a fire risk and issue a warning information when the deviation is greater than a first dynamic threshold, wherein the first dynamic threshold is obtained by a moving standard deviation of the deviation.

[0068] In one embodiment, when the preset parameters comprise a temperature difference and a temperature rise rate, the obtaining module comprises:

[0069] The second obtaining sub-module is configured to obtain the hot primary air volume, the hot primary air temperature, the cold primary air volume, the cold primary air temperature, and the actual outlet temperature value of the medium-speed coal mill.

[0070] The third determining sub-module is configured to determine the theoretical outlet temperature value of the medium-speed coal mill according to the hot primary air volume, the hot primary air temperature, the cold primary air volume, and the cold primary air temperature of the medium-speed coal mill by substituting into an outlet temperature model.

[0071] The first calculating sub-module is configured to calculate the temperature difference according to the actual outlet temperature value and the theoretical outlet temperature value of the medium-speed coal mill, and calculate the temperature rise rate according to the actual outlet temperature value.

[0072] The judging module comprises:

[0073] The fourth determining sub-module is configured to determine that the outlet temperature of the medium-speed coal mill has an abnormal temperature rise when the temperature difference exceeds a preset threshold or the temperature rise rate exceeds a normal temperature rise rate range.

[0074] The fourth determining sub-module is further configured to determine that the medium-speed coal mill has a fire risk when the outlet temperature of the medium-speed coal mill has an abnormal temperature rise.

[0075] In one embodiment, when the preset parameters comprise a pulverized coal pipe blockage, the obtaining module comprises:

[0076] The third obtaining sub-module is configured to obtain the total primary air pressure of the medium-speed coal mill and the primary air flow of each pulverized coal pipe.

[0077] A fifth determination submodule is configured to determine a current operating condition based on a moving average of the total primary air pressure;

[0078] The second calculation submodule is used to calculate the weight coefficient of each powder hose air volume to the total air volume based on the moving average of the primary air flow of each powder hose;

[0079] The judgment submodule is used to judge whether there is a powder hose blockage based on the current working conditions and the weight coefficient of each powder hose air volume to the total air volume;

[0080] The judgment module is further configured to:

[0081] When the powder pipe is blocked, it is determined that the medium-speed coal mill has a fire risk.

[0082] In one embodiment, the second calculation submodule is further configured to:

[0083] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0084]

[0085] Among them, W i,current Indicates the weight coefficient of the i-th powder hose air volume to the total air volume; F i,MA Represents the moving average of the primary air flow rate of the i-th pipeline.

[0086] In one embodiment, when the preset parameters include safety information of the primary air system, the acquisition module includes:

[0087] The fourth acquisition submodule is used to obtain the primary air inlet temperature, primary air temperature rise rate, valve failure and valve jam detection results;

[0088] a sixth determining submodule, configured to determine safety information of the primary air system based on at least one of the primary air inlet temperature, the primary air temperature rise rate, the valve failure, and the valve jam detection results;

[0089] The judgment module is further configured to:

[0090] When at least one of the following conditions occurs, it is determined that there is a fire risk in the medium-speed coal mill:

[0091] The primary air inlet temperature is greater than the primary air explosion temperature of the coal mill;

[0092] The primary air temperature rise rate is greater than the maximum temperature rise rate of the primary air system;

[0093] The valve failure detection result indicates that the valve has failed;

[0094] The valve sticking test result indicates that the valve is stuck.

[0095] In one embodiment, when the preset parameters include the medium-speed coal mill purge result, the judgment module includes:

[0096] The fifth acquisition submodule is used to obtain the latest historical purge results of the medium-speed coal mill;

[0097] The seventh determining submodule is configured to determine that the medium-speed coal mill has a fire risk when the historical purging result indicates that the purging of the medium-speed coal mill has failed.

[0098] In one embodiment, the purge result determination process is as follows:

[0099] When the coal mill meets the purging conditions, determining the type of steam used to purge the coal mill according to the coal type information of the residual coal powder in the coal mill;

[0100] injecting the corresponding type of purge steam into the coal mill;

[0101] Check whether the type and pressure of injected steam are qualified;

[0102] When the steam type and steam pressure are qualified, determine whether the steam flow meets the minimum purge steam flow requirement;

[0103] When the steam flow rate meets the minimum purge steam flow rate requirement, the purge time is counted;

[0104] During the purging process, the internal pressure of the coal mill is monitored, and the steam pressure is adjusted according to the internal pressure of the coal mill so that the internal pressure of the coal mill increases at a specific rate;

[0105] When the timed purge time reaches the preset time, the oxygen content inside the coal mill is monitored;

[0106] When the oxygen content inside the coal mill is lower than the preset content, it is determined that the purging is successful.

[0107] The present application also provides a medium-speed coal mill fire warning system, comprising:

[0108] at least one processor; and,

[0109] a memory communicatively connected to the at least one processor; wherein,

[0110] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the medium-speed coal mill fire warning method recorded in any of the above embodiments.

[0111] The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by the processor corresponding to the medium-speed coal mill fire warning system, the medium-speed coal mill fire warning system can implement the medium-speed coal mill fire warning method recorded in any of the above embodiments.

[0112] The beneficial effects of the present application are: obtaining a variety of preset parameters of the medium-speed coal mill during its operation; judging whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill; and issuing an early warning when the medium-speed coal mill has a fire risk. Since the coal mill is judged to have a fire risk based on a variety of preset parameters, the situation where a single parameter monitoring cannot capture the fire risk under complex working conditions is avoided. In addition, automatic judgment based on preset parameters improves the real-time nature of the early warning. In addition, the present application improves the sensitivity and accuracy of anomaly recognition through multi-parameter collaborative analysis, integration of multi-dimensional data, and calculation of deviations through dynamic models.

[0113] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present application. The purposes and other advantages of the present application can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0114] The technical solution of the present application is further described in detail below through the accompanying drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0115] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings:

[0116] Figure 1 This is a flow chart of a medium-speed coal mill fire warning method in one embodiment of the present application;

[0117] Figure 2 This is a structural diagram of a fire warning device for a medium-speed coal mill in one embodiment of the present application;

[0118] Figure 3 This is a hardware structure diagram of a medium-speed coal mill fire warning system in one embodiment of the present application. DETAILED DESCRIPTION

[0119] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application.

[0120] Figure 1 FIG. 1 is a flow chart of a method for early warning of fire of a medium-speed coal mill according to an embodiment of the present application. Figure 1 As shown, the method can be implemented as the following steps S101-S103:

[0121] In step S101, during the operation of the medium-speed coal mill, various preset parameters of the medium-speed coal mill are obtained;

[0122] In step S102, it is determined whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill;

[0123] In step S103, when there is a fire risk in the medium-speed coal mill, an early warning prompt is issued.

[0124] This application achieves full-cycle accurate early warning and real-time alarm for medium-speed coal mill fires through multi-parameter dynamic threshold fusion analysis and phased fire source positioning strategy, solving the problems of early warning lag, high false alarm rate and lack of fire source positioning caused by single-parameter static monitoring in traditional methods.

[0125] During the operation of the medium-speed coal mill, a variety of preset parameters of the medium-speed coal mill are obtained. In order to provide a comprehensive fire warning for the coal mill, the warning before the fire in this application includes an early warning of abnormal fluctuations in the grinding bowl differential pressure, an abnormal early warning of the outlet temperature / temperature rise rate, an early warning of abnormal changes in the primary air temperature, an early warning of severe blockage of the burner powder pipe, and an early warning of failure of the fire steam purge; the early warning during the fire includes an alarm of violent fluctuations in the grinding bowl differential pressure and an alarm of rapid increase in the outlet temperature. Therefore, the preset parameters include the expected value of the grinding bowl pressure difference, the calculated temperature difference between the actual outlet temperature value and the theoretical outlet temperature value, the temperature rise rate of the outlet temperature, the blockage of the powder pipe, the safety information of the primary air system, the purge result of the medium-speed coal mill, etc. Then, it is determined whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill. When the medium-speed coal mill has a fire risk, an early warning prompt is issued.

[0126] Specifically, early warnings before a fire occurs include:

[0127] (1) Warning of abnormal fluctuation of grinding bowl differential pressure

[0128] When the preset parameters include the expected value of the grinding bowl pressure difference, the multiple preset parameters of the medium-speed coal mill are obtained, including: monitoring the operation status of the grinding system; activating the fire alarm function when the grinding system is in operation; when the fire alarm function is activated, obtaining the primary air volume, coal powder mass flow rate, rotation speed and separator pressure difference of the medium-speed coal mill; and determining the expected value of the grinding bowl pressure difference of the medium-speed coal mill based on the primary air volume, coal powder mass flow rate, rotation speed and separator pressure difference.

[0129] Specifically, the operation status of the medium-speed coal mill and the corresponding coal feeder is monitored. When the medium-speed coal mill starts to run and the corresponding coal feeder is in operation, it is determined that the grinding system is in operation; when the medium-speed coal mill is stopped, the corresponding coal feeder is stopped, and the corresponding mill outlet temperature is lower than 40°C, it is determined that the grinding system is not in operation. When the grinding system is in operation, the fire alarm function is activated. When the grinding system is not in operation, the fire alarm function is shielded. Since the grinding bowl differential pressure is affected by the nonlinear coupling of multiple parameters such as air volume, coal volume, and rotation speed, when the fire alarm function is activated, the primary air volume, coal powder mass flow rate, rotation speed and separator pressure difference of the medium-speed coal mill are obtained, and then the expected value of the grinding bowl differential pressure of the medium-speed coal mill is determined based on the primary air volume, coal powder mass flow rate, rotation speed and separator pressure difference. The determination process is as follows:

[0130] Since the grinding bowl differential pressure of the medium-speed coal mill is time series data and fluctuates at all times, the standard deviation is usually used to judge the fluctuation. However, a large standard deviation at a certain moment may be caused by some interference, such as an increase in the primary air pressure or an increase in the coal feed. These changes are normal and reasonable, and the resulting fluctuations are also reasonable. In order to filter out reasonable fluctuations, a calculation model for the expected value of the grinding bowl differential pressure of the medium-speed coal mill can be constructed to calculate the theoretical value of the grinding bowl differential pressure.

[0131] Therefore, according to the correlation between primary air volume, coal volume, speed and separator pressure difference, a calculation model for the expected value of grinding bowl differential pressure of medium-speed coal mill is established to calculate the dynamic theoretical value P of grinding bowl differential pressure of medium-speed coal mill. expected (t). The calculation model of the expected value of the grinding bowl differential pressure of the medium-speed coal mill is expressed as follows:

[0132] P expected (t)=f(Q1(t),M coal (t),n(t),ΔP sep (t))

[0133] Among them, P expected (t) is the dynamic theoretical value of the differential pressure of the grinding bowl of the medium-speed coal mill; f is the fitting function; Q1(t) is the primary air volume, which is the air flow entering the coal mill through the air ring, directly affecting the air flow velocity and dynamic pressure, unit: m 3 / h;M coal (t) is the coal powder mass flow rate, that is, the coal powder mass entering the pulverizer per unit time, which determines the material load's resistance to the airflow, and is measured in t / h; n(t) is the grinding bowl speed, which affects the coal powder grinding efficiency and airflow distribution, and is measured in rpm; ΔP sep (t) is the pressure difference between the inlet and outlet of the separator, which reflects the gas-solid separation effect and indirectly affects the circulating gas flow in the mill. Unit: Pa.

[0134] In order to construct a specific model, the correlation between the expected value of the grinding bowl differential pressure of the medium-speed coal mill and multiple preset parameters is obtained, wherein the multiple preset parameters include at least two of the primary air volume, coal powder mass flow rate, rotation speed, and separator pressure difference, and then a calculation model related to the multiple preset parameters is constructed based on the correlation. For example, according to the Bernoulli equation, the expected value of the grinding bowl differential pressure of the medium-speed coal mill P expected (t) is positively correlated with the square of the primary air Q1(t), and the expected value of the grinding bowl differential pressure of the medium-speed coal mill P expected (t) and other parameters (and pulverized coal mass flow rate M coal (t), grinding bowl speed n(t), separator inlet and outlet pressure difference ΔP sep (t)) is an approximately linear relationship, the calculation model related to the multiple preset parameters is constructed according to the correlation, including:

[0135] The following calculation model related to the various preset parameters is constructed based on the correlation:

[0136]

[0137] Among them, a, b, c, and d are unknown coefficients and can be adjusted by the least squares method.

[0138] After the calculation model is constructed, the calculation model is optimized so that the calculation result of the calculation model is close to the optimal value of the grinding bowl differential pressure of the medium-speed coal mill. Specifically, given a set of observation data, Need to find the polynomial regression model: The optimal parameters a, b, c, and d in the equation are such that the sum of the squared errors between the predicted value and the actual value is minimized. That is, the objective function is constructed with the goal of minimizing the sum of the squared errors between the calculation model results and the actual value of the grinding bowl differential pressure of the medium-speed coal mill:

[0139]

[0140] Among them, P actual (i) is the actual value of the grinding bowl differential pressure of the medium-speed coal mill; Q1(i) is the primary air volume; M coal (i) is the mass flow rate of pulverized coal; n(i) is the grinding bowl speed; ΔP sep (i) is the pressure difference between the inlet and outlet of the separator; a, b, c, d are unknown coefficients;

[0141] The optimal value of the undetermined coefficient in the objective function is determined by the least square method.

[0142] Therefore, a data matrix is ​​constructed based on the collected samples. Assuming the collected sample numbers are i=1, 2, ..., N, the matrix is ​​constructed:

[0143]

[0144] Where i is the sample number; P actual is the measured value of the grinding bowl differential pressure of the medium-speed coal mill; Q1 is the measured value of the primary air volume; M coal is the measured value of coal powder mass flow rate; n is the measured value of grinding bowl speed; ΔP sep It is the measured value of the pressure difference between the inlet and outlet of the separator.

[0145] For parameter vector θ = [a, b, c, d] T , then the objective function can be expressed as:

[0146] min θ ||P-Xθ|| 2

[0147] Taking the partial derivative of θ and setting it to zero, we get: X T Xθ=X T P;

[0148] Therefore, the solution is: θ=(X T X) -1 X T P.

[0149] The plurality of preset parameters are substituted into the optimized calculation model to calculate the expected value of the grinding bowl differential pressure of the medium-speed coal mill.

[0150] Then, determine whether there is a fire risk in the medium-speed coal mill, specifically, by determining the deviation between the expected value of the grinding bowl differential pressure of the medium-speed coal mill and the actual value of the grinding bowl differential pressure of the medium-speed coal mill;

[0151] When the deviation is greater than a first dynamic threshold, the medium-speed coal mill is determined to be at risk of fire and an early warning is issued. The first dynamic threshold is obtained by the moving standard deviation of the deviation. First, the moving average of the deviation is obtained. A time window N is selected, for example, one point is taken per second, for a total of 10 points, and the moving average of the deviation is calculated using the following formula:

[0152]

[0153] Where MA(t) is the moving average of the time deviation; N is the window length; ΔP(i) is the i-th deviation.

[0154] Then, the moving standard deviation of the deviation is determined according to the moving average of the deviation; specifically, within the same time window, the moving standard deviation of the deviation is calculated:

[0155]

[0156] Where MSD(t) is the moving standard deviation of the time deviation; N is the window length; ΔP(i) is the i-th deviation, and MA(t) is the moving average of the time deviation.

[0157] The first dynamic threshold is determined based on the moving standard deviation of the deviation. A fluctuation coefficient k1 is set, and the first dynamic threshold is determined to be k1MSD(t). k1 can be obtained based on historical data fitting. Similarly, a second dynamic threshold greater than the first dynamic threshold can be set. k1 and k2 are used to control the sensitivity of the judgment. At this point, a determination can be made as to whether the fluctuation is abnormal: ① If the deviation is less than the first dynamic threshold, the fluctuation is determined to be within the normal range, i.e., |ΔP(t)| ≤ k1MSD(t), indicating a normal fluctuation. ② If the deviation is between the first and second dynamic thresholds, the fluctuation is determined to be abnormal and requires further analysis, resulting in an abnormal fluctuation warning. That is, k1MSD(t) < |ΔP(t)| ≤ k2MSD(t), indicating an abnormal fluctuation requiring further analysis. ③ If the deviation is greater than the second dynamic threshold, a severe fluctuation is determined, and a severe fluctuation warning is issued. That is, |ΔP(t)| > k2MSD(t), indicating a severe fluctuation.

[0158] (2) Outlet temperature / temperature rise rate abnormal warning

[0159] When the preset parameters include the temperature difference between the actual outlet temperature value and the theoretical outlet temperature value of the medium-speed coal mill, as well as the temperature rise rate of the actual outlet temperature, the multiple preset parameters of the medium-speed coal mill are obtained, including: obtaining the hot primary air volume, hot primary air temperature, cold primary air volume, cold primary air temperature and actual outlet temperature value of the medium-speed coal mill, and substituting the hot primary air volume, hot primary air temperature, cold primary air volume and cold primary air temperature of the medium-speed coal mill into the outlet temperature model to determine the theoretical outlet temperature value of the medium-speed coal mill. The outlet temperature of the medium-speed coal mill is mainly determined by the mixing ratio of the hot primary air and the cold primary air. Taking into account the possible heat loss or other complex factors in actual operation, the correction coefficients α and β are introduced to obtain the following model, and the outlet temperature can be expressed as:

[0160]

[0161] Among them, T 出口 is the outlet temperature, Q h is the hot primary air volume, T h For hot air temperature, Q l is the cooling air volume, T l is the cold primary air temperature, α is the heat transfer efficiency, and β is the additional heat loss or gain.

[0162] Furthermore, the real-time temperature value of the outlet temperature can be determined through the above model. The introduced dual parameters α and β respectively characterize the equipment status and the unmodeled thermal effect. The model output is dynamically adjusted with the operating conditions (air volume, air temperature), avoiding the mismatch problem of the static model to the changes in the operating conditions and improving the physical interpretability of the model.

[0163] In order to obtain the specific values ​​of the correction coefficients α and β, historical data of the parameter values ​​of the coal mill preset parameters (such as the second-level operation data of the past month) are collected, and α and β are fitted using the least squares method using the historical data. The objective function in the fitting process is as follows:

[0164]

[0165] The temperature difference is calculated based on the actual outlet temperature value and the theoretical outlet temperature value of the medium-speed coal mill, and the temperature rise rate is calculated based on the actual outlet temperature value.

[0166] In the real-time monitoring process, in order to reduce the influence of sensor noise and transient interference on temperature judgment, the sliding window statistical method is used to perform dynamic smoothing calculations on the theoretical temperature value and the actual temperature value. Specifically, the moving average of the actual outlet temperature value and the moving average of the theoretical outlet temperature value of the medium-speed coal mill are calculated respectively; the absolute value of the difference between the moving average of the actual outlet temperature value and the moving average of the theoretical outlet temperature value is determined as the temperature difference. Set the sliding window length to w (for example: 60 seconds) and the sliding interval to t (for example: slide once every 10 seconds), and then calculate the following data in each window:

[0167] 1) Theoretical outlet temperature moving average:

[0168]

[0169] 2) Actual outlet temperature moving average:

[0170]

[0171] 3) The temperature difference between the theoretical outlet temperature moving average and the actual outlet temperature moving average:

[0172]

[0173] After long-term operation, equipment aging can cause model deviations (the difference between actual and theoretical temperatures) to increase, potentially rendering the original anomaly detection ineffective, leading to false alarms or missed alarms. Equipment aging (such as roller wear and liner scaling, which can all be categorized as equipment aging) occurs over a long period of time. Because the α correction primarily reflects the decline in heat transfer efficiency, which is caused by equipment aging, the deviations caused by equipment aging are primarily due to α deviations. This requires optimizing and updating the model parameters. Adjusting α can bring the theoretical value back to the actual value.

[0174] Specifically, the deviation between the actual outlet temperature of the medium-speed coal mill and the theoretical outlet temperature is calculated:

[0175]

[0176] e(t)=T 实际 (t)-T 理论 (t);

[0177] Where, e(t) is the deviation between the theoretical outlet temperature and the actual outlet temperature, T 实际 (t) is the actual outlet temperature, T 理论 (t) is the theoretical outlet temperature.

[0178] The outlet temperature model is then updated based on the deviation. The deviation serves as the input to the PID controller, and the output is used to adjust the model parameter α to keep the deviation close to zero. This ensures the model remains accurate even as the equipment ages.

[0179]

[0180] Among them, Δα(t) is the adjustment amount, K p , K i , K d are the proportional, integral, and differential coefficients respectively.

[0181] Then according to α k =α k-1 +Δα k Update the parameter α.

[0182] K in the above model p , K i , K d The integral can be adjusted by the Ziegler-Nichols critical oscillation method. Since the deviation period is very long, the integral action will be mainly used for adjustment, while the proportional and differential actions are weakened as much as possible. In this way, α can be slowly adjusted to make the deviation approach zero, thereby eliminating the influence of aging. Specifically, turn off the integral (K i =0) and differential (Kd =0), gradually increase K p Until the system output oscillates with equal amplitude. Assume that K is gradually increased p When K p = 5, the temperature oscillates with equal amplitude within the range of ±3°C (e.g. 82°C → 88°C → 82°C…), then record the critical gain K c =5 and oscillation period P c = 900 seconds, calculate the initial parameters according to the formula.

[0183] K p =0.6K c =3,K i =K p / (0.5K c )=0.007,K d =0.125K p P c =337.5.

[0184] Furthermore, in view of the slow time-varying characteristics of equipment aging, the α parameter is adjusted in real time through deviation feedback (the difference between actual temperature and theoretical temperature) to compensate for the attenuation of heat transfer efficiency caused by equipment aging and achieve long-term drift suppression.

[0185] Then, the medium-speed coal mill is judged to have a fire risk based on the temperature difference and the temperature rise rate. If the temperature difference exceeds a preset threshold or the temperature rise rate exceeds a normal temperature rise rate range, it is determined that the outlet temperature of the medium-speed coal mill has increased abnormally. If the outlet temperature of the medium-speed coal mill has increased abnormally, it is determined that the medium-speed coal mill has a fire risk.

[0186] In this application, to accurately determine whether abnormal temperature rise exists, a dual determination criteria of an abnormal temperature rise rate and an abnormal temperature difference is employed. When the temperature difference exceeds a preset threshold or the temperature rise rate exceeds the normal temperature rise rate range, it is determined that the outlet temperature of the medium-speed coal mill has increased abnormally. When the outlet temperature of the medium-speed coal mill has increased abnormally, an alarm is issued.

[0187] The temperature rise rate reflects the rate of change of the outlet temperature and is a key indicator for determining whether there is abnormal temperature rise. Specifically, the temperature rise rate is the amount of change in temperature per unit time, and the corresponding formula is as follows:

[0188] v k =T 出口,k -T 出口,k-1

[0189] Among them, v k Indicates the temperature rise rate, unit is ℃ / s; T 出口 ,k represents the outlet temperature at the current moment, unit is ℃; T出口 ,k-1 represents the outlet temperature at the previous moment, unit is ℃.

[0190] Determine whether the temperature rise rate exceeds the normal temperature rise rate range. The normal temperature rise rate range is an interval used to distinguish normal temperature rise rates from abnormal rapid temperature rises, and can be determined based on historical data. Specifically, calculate the historical mean and historical standard deviation of the temperature rise rate; determine the normal temperature rise rate range based on the historical mean and historical standard deviation of the temperature rise rate. If the current temperature rise rate v k If the temperature exceeds this range, it is determined to be abnormal temperature rise. In this application, the normal temperature rise rate range is determined according to the following formula:

[0191] v normal =[μ v -3σ v ,μ v +3σ v ];

[0192] Among them, v normal Indicates the normal temperature rise rate range, μ v is the mean of the historical temperature rise rate, σ v is the standard deviation of the historical temperature rise rate.

[0193] The above normal temperature rise rate range represents the range of 3 standard deviations extending outward from the mean.

[0194] When judging whether the temperature rise rate is abnormal, the current temperature rise rate v k or ΔT k When it exceeds the normal range, it is determined that there is abnormal temperature rise. k >(μ v +3σ v )or If the temperature rises, it is determined to be abnormal. Otherwise, the temperature rise is determined to be normal.

[0195] A dual-dimensional anomaly diagnosis logic is constructed using temperature difference and temperature rise rate. Temperature difference analysis is suitable for slowly changing conditions, while temperature rise rate analysis is suitable for sudden changes. The temperature difference criterion filters out normal operating fluctuations (such as air volume adjustment), while the temperature rise rate criterion captures rapid fire characteristics. Both criteria can trigger an alarm.

[0196] (3) Burner powder pipe blockage warning

[0197] When the preset parameters include powder pipe blockage, the multiple preset parameters of the medium-speed coal mill are obtained, including:

[0198] Obtain the total primary air pressure of the medium-speed coal mill and the primary air flow rate of each powder pipe. After obtaining the real-time parameter values, pre-process the real-time inlet total primary air pressure and primary air flow rate of each powder pipe using the moving average method to obtain more stable and reliable data. Specifically, the moving average of the total primary air pressure is calculated using the following formula:

[0199]

[0200] Among them, P MA is the moving average of the total primary air pressure; T is the number of data points for calculating the moving average; P is the actual value of the total primary air pressure.

[0201] Similarly, the moving average of the primary air flow of each powder hose is calculated using the following formula:

[0202]

[0203] Among them, F i,MA is the moving average of the primary air flow of the i-th powder hose; T is the number of data points for calculating the moving average; F i is the actual value of the primary air flow of the i-th powder hose.

[0204] The current working condition is determined based on the moving average of the total primary air pressure. Since the powder hose air volume distribution rules are significantly different under different working conditions, and different working conditions can be represented by the total primary air pressure at the inlet, the current working condition is determined based on the total primary air pressure at the inlet. Specifically, the moving average of the total primary air pressure at the inlet is matched with a pre-constructed total primary air pressure-working condition correspondence table to determine the current working condition. Among them, the total primary air pressure-working condition correspondence table can be pre-constructed based on experience, or it can be determined by cluster analysis. In one embodiment of the present application, clustering is performed using an unsupervised clustering algorithm (K means). Among them, the K means algorithm is a clustering algorithm based on distance metric, and its goal is to divide the data set into K different clusters so that the similarity of the data points within the cluster is high and the similarity of the data points between clusters is low. In this embodiment, the historical data of the total primary air pressure is obtained and a moving average process is performed; then the total primary air inlet pressure after the moving average process is clustered, for example, it is divided into three different working condition intervals (low pressure, medium pressure, high pressure). Therefore, the total primary air pressure-operating condition correspondence table can be constructed based on the clustering results. For example, when the total primary air inlet pressure P in ∈[5.0,6.0)kPa, it belongs to the low pressure working range; when P in ∈[6.0,7.5)kPa, it belongs to the medium pressure range; when P in ∈[7.5,8.5)kPa, it belongs to the high pressure operating range.

[0205] According to the moving average of the primary air flow of each powder pipe, the weight coefficient of the air flow of each powder pipe to the total air flow is calculated; the distribution weight of the primary air flow of each powder pipe is basically fixed under a certain working condition, therefore, the weight coefficient of each powder pipe is calculated by the following formula:

[0206]

[0207] Wherein, W i，current represents the weight coefficient of the i-th powder pipe; F i,MA represents the moving average of the primary air flow of the i-th pipe.

[0208] According to the working condition currently belonging to and the weight coefficient of the air flow of each powder pipe to the total air flow, it is judged whether there is a powder pipe blockage. In order to accurately analyze the blockage status of the powder pipe under the current working condition, the weight coefficient of the current powder pipe is compared with the weight coefficient under the normal state of the working condition, so as to judge whether the current weight coefficient deviates. Specifically, by means of total primary air inlet pressure clustering analysis and sub-working condition modeling, the reference parameters (including mean and standard deviation) of the primary air flow and weight coefficient of each powder pipe under different working conditions are calculated. Through this process, the current running state of the powder pipe can be accurately matched, and false alarm caused by cross-working condition can be effectively avoided. In this application, the mean and standard deviation of the total air flow under each working condition, and the mean and standard deviation of the weight of each powder pipe under each working condition are obtained in advance.

[0209] 1) The mean and standard deviation of the total air flow under each working condition:

[0210] Firstly, the historical data of the primary air flow of each powder pipe under each working condition is obtained, and the corresponding moving average is calculated Then the historical data of the total air flow of all powder pipes under the corresponding working condition can be obtained.

[0211]

[0212] Wherein, represents the total air flow of all powder pipes under working condition k; represents the moving average of the primary air flow of the i-th powder pipe.

[0213] For each working condition k, after obtaining the historical data of the total air flow of all powder pipes under each working condition, the mean and standard deviation of the historical total air flow are calculated by the following formula:

[0214]

[0215] Wherein, μ k represents the mean of the historical total air flow under working condition k; σ k represents the standard deviation of the historical total air flow under working condition k, represents the jth data value in the historical total air volume dataset; N represents the number of samples in the total air volume dataset.

[0216] 2) Mean and standard deviation of each powder hose weight under each working condition:

[0217] First, obtain the historical weight coefficient of each powder hose under each working condition:

[0218]

[0219] in, represents the historical weight coefficient of the i-th powder hose under working condition k; Indicates the historical total air volume of all powder hoses under working condition k; Represents the moving average of the primary air flow of the i-th powder hose.

[0220] Then calculate the average value and standard deviation of the weight coefficient of each powder hose under each working condition:

[0221]

[0222] in, is the average value of the historical weight coefficient of the i-th powder hose under working condition k; is the standard deviation of the historical weight coefficient of the i-th powder hose under working condition k; represents the nth historical weight coefficient of the i-th powder hose under working condition k; N is the number of samples in the data set of a single powder hose air volume.

[0223] Based on the baseline parameters under different operating conditions, the average and standard deviation of the historical weight coefficients of each powder hose corresponding to the current operating condition are obtained. A standardized score, or Zscore, is calculated for each powder hose based on the weight coefficient of each powder hose's air volume relative to the total air volume and the average and standard deviation of the historical weight coefficients of each powder hose. This score reflects how many standard deviations the current weight deviates from after standardization. The standardized score corresponding to each powder hose can then be used to determine whether a blockage exists. Specifically, for each powder hose i, the standardized score is calculated using the following formula:

[0224]

[0225] Among them, W i，current is the weight coefficient of the i-th powder tube at the current moment; is the average value of the historical weight coefficient of the i-th powder hose under working condition k; is the standard deviation of the historical weight coefficient of the i-th powder hose under working condition k.

[0226] When there is a first powder hose with a normalized score lower than a first preset value, the first powder hose is marked as a potential blocked pipe; for example, the first preset value is -3, if there is a normalized score Z of the i-th powder hose i <-3, that is, the real-time value is 3 standard deviations smaller than the average value. It is determined that the flow rate of the i-th powder hose is abnormally small, so the i-th powder hose is marked as a potential blocked pipe, and the number of potential blocked pipes N is counted. 异常低 .

[0227] 1) When the number of potentially blocked pipes N 异常低 =1, the compensation effect of the medium-speed coal mill burner powder pipe system is verified.

[0228] Specifically, the compensation effect verification is to check whether there is a significant positive deviation in other powder hoses except for the potential blocked pipeline and whether the overall air volume of the medium-speed coal mill burner powder hose system is normal: when there is a significant positive deviation in other powder hoses and the overall air volume is normal, the compensation effect verification passes; otherwise, the compensation effect verification fails.

[0229] ① When the number of potentially blocked pipes N 异常低 =1, and the compensation effect verification is passed, it is confirmed that a single pipe is blocked, and a single pipe blockage alarm is triggered.

[0230] Specifically, when there is a second powder tube with a normalized score greater than the second preset value, for example, the second preset value is 2, that is, there is a normalized score Z of the jth powder tube. j >2, indicating that the j-th powder hose has a significant positive deviation; at the same time, if the reduced air volume is approximately equal to the air volume compensated by other pipes, there is If the flow of the entire system is normal, it is confirmed that a single pipe is blocked and the single pipe blockage alarm is triggered. Of course, the reduced air volume is approximately equal to the air volume compensated by other pipes. It can also be verified by the deviation between the total air volume of all powder hoses and the average value of the historical total air volume within the preset range. That is, when This indicates that the reduced air volume has been compensated, where δ is the total air volume deviation allowed by the system, which can be predetermined based on experience.

[0231] ② When the number of potentially blocked pipes N 异常低 =1, but the compensation effect verification fails, it is confirmed that the air volume sensor is abnormal and the sensor abnormality alarm is triggered.

[0232] Specifically, when there is no second powder hose with a standardized score greater than the second preset value or the reduced air volume is not compensated (i.e., the deviation between the total air volume of all powder hoses and the average value of the historical total air volume is greater than the total air volume deviation allowed by the system), This indicates that the reduced air volume has not been compensated, and it is determined that the air volume sensor is abnormal, triggering a sensor abnormality alarm.

[0233] 2) When the number of potentially blocked pipes N 异常低 ≥2, verify the compensation effect and compensation dispersion of the powder pipe system of the medium-speed coal mill burner.

[0234] Specifically, the verification of compensation effect is consistent with the above content and will not be repeated here. The verification of compensation dispersion is to measure the standard deviation of the weight coefficient change of the potential blocked pipeline under real-time working conditions σ 补偿 The standard deviation of historical normal compensation σ 正常补偿 When the standard deviation of the weight coefficient change of the potential blocked pipeline under real-time working conditions is σ 补偿 Less than the historical normal compensation standard deviation σ 正常补偿 , the compensation dispersion verification passes; otherwise, the compensation dispersion verification fails.

[0235] The calculation process of the standard deviation of the weight coefficient change of the potential blocked pipeline under real-time working conditions is as follows:

[0236] Calculate the standard deviation σ of the weight coefficient change of the powder hoses that are not marked as potential blocked pipes 补偿 , real-time σ 补偿 It is the standard deviation of the fluctuation between the flow weight of all non-blocked pipelines and their baseline mean at the current moment. It is used to quantify the compensation dispersion of non-blocked pipelines under real-time working conditions. The specific calculation formula is as follows:

[0237]

[0238] Among them, σ 补偿 is the standard deviation of the weight coefficient change of the powder hose that is not marked as a potential blocked pipeline; w m，current is the weight coefficient of the mth powder hose that is not marked as a potential blocked pipe; is the average historical weight coefficient of the mth powder hose that is not marked as a potential blocked pipe under working condition k; M represents the number of non-blocked pipes.

[0239] The calculation process of the historical normal compensation standard deviation is as follows:

[0240] Using historical data, first calculate the historical standard deviation of all fan tube weights and their benchmark mean:

[0241]

[0242] Among them, σ 补偿 (t j ) represents t j The standard deviation of all powder tube weight coefficients at the moment; W i (t j ) represents the weight of the i-th powder tube at time j; μ i (k)It represents the historical weight mean of the N weight time series of the i-th powder hose under working condition k.

[0243] Then aggregate the historical deviation standard deviation to calculate the historical normal compensation standard deviation. Specifically, the σ 补偿 (t j ) to obtain the historical normal compensation standard deviation:

[0244]

[0245] Among them, σ 正常补偿 is the historical normal compensation standard deviation; σ 补偿 (t j ) represents the standard deviation of all powder tube weight coefficients at time j.

[0246] ① When the number of potentially blocked pipes N 异常低 ≥2, when the compensation effect verification passes but the compensation dispersion verification fails, it means that the reduced air volume of the potential blocked duct is compensated by other ducts in a centralized manner rather than evenly, triggering a centralized compensation multi-duct blockage alarm.

[0247] ② When the number of potentially blocked pipes N 异常低 ≥2, the compensation effect verification fails, but the compensation dispersion verification passes, indicating that the reduced air volume in the potential blocked duct is evenly compensated by other ducts instead of concentrated compensation, triggering the uniform compensation multi-duct blockage alarm.

[0248] ③ When the number of potentially blocked pipes N 异常低 ≥2. If both the compensation effect verification and the compensation dispersion verification fail, the total air volume normality verification is performed. The total air volume normality verification verifies whether the total air volume of all powder hoses is normal. If the total air volume is reduced during this verification, it means that the reduced air volume in the blocked pipe has not been compensated by other pipes, and the total air volume is reduced, indicating that multiple pipes are severely blocked. This triggers the multiple pipes severe blockage alarm.

[0249] The normality verification process of the total air volume is as follows: obtain the average value and standard deviation of the historical total air volume of all powder hoses corresponding to the current working condition; determine the dynamic threshold of the total air volume based on the average value and standard deviation of the historical total air volume of all powder hoses corresponding to the current working condition; when the total air volume of all powder hoses is less than the dynamic threshold of the total air volume, it is determined that the overall air volume is low and a warning message of low overall air volume is issued. For example, obtain the average value of the historical total air volume corresponding to the current working condition and standard deviation If the total air volume dynamic threshold is That is , it means the overall air volume is low.

[0250] Furthermore, when the powder pipe is blocked, it is determined that the medium-speed coal mill has a fire risk.

[0251] This application has dynamic adaptability to multiple working conditions. Through inlet pressure cluster analysis, the operating state is divided into multiple working condition intervals, and independent modeling is performed for different working conditions to eliminate misjudgments caused by working condition switching. In addition, it can accurately locate anomalies and suppress missed detections. By combining the three-level detection logic of Zscore (single variable), total air volume (multi-variable overall judgment), and compensation dispersion (system level), it covers local and global anomalies, and has strong specific multi-pipeline collaborative analysis capabilities. The moving average filter is used to suppress instantaneous noise, and it has strong anti-noise and anti-interference capabilities. The moving average method is used to dynamically update the working condition model parameters, and new congestion patterns are incrementally learned based on historical data. The congestion pattern library can automatically learn new abnormal patterns and support incremental training and dynamic expansion.

[0252] (4) Warning of abnormal changes in primary air temperature

[0253] If the primary air temperature is too high or the temperature rise rate is too fast, it may cause the volatile matter in the coal powder to be released quickly, thereby causing a local high temperature area. When the preset parameters include the safety information of the primary air system, the multiple preset parameters of the medium-speed coal mill are obtained, including:

[0254] Obtain the primary air inlet temperature, primary air temperature rise rate, valve failure, and valve jam test results. In this application, the test process is as follows:

[0255] 1) Air temperature detection

[0256] The rapid increase in the temperature of the primary air at the inlet of the medium-speed coal mill can easily cause the coal powder in the coal mill to spontaneously combust or explode. Therefore, this application determines the explosion temperature based on the source of the coal powder, and issues an alarm when it is higher than the explosion temperature. In addition, since the volatile content V is not an online value, but intermittent data regularly tested by the team members, the data cannot be automatically updated in the DCS system, and the volatile content data can only be input regularly by the operator. In order to provide continuous online data, this application installs an online instrument for the coal feeder to measure the volatile content of the coal powder, and then determines the primary air explosion temperature of the coal mill based on the volatile content of the coal powder. In this application, the volatile content and explosion temperature of a variety of coal powders are obtained in advance based on the test data, and the volatile content and explosion temperature of a variety of coal powders are fitted to obtain the functional relationship between the volatile content and the explosion temperature:

[0257] T 爆燃 =f(V);

[0258] Among them, T 爆燃 is the primary air explosion temperature; V is the volatile matter content in the coal powder.

[0259] In one embodiment, the functional relationship between the volatile matter content and the deflagration temperature is:

[0260] T 爆燃 =a·e -bV +c;

[0261] Among them, T 爆燃 is the primary air explosion temperature; V is the volatile matter content in the coal powder; parameters a, b, and c can be determined by fitting experimental data.

[0262] This model has few parameters to fit, is simple, and is suitable for rapid estimation. It exhibits strong fitting stability for small amounts of data (e.g., fewer than 10 data sets) and is less prone to overfitting. Here, a corresponds to the theoretical limit temperature in the absence of volatiles (approximately the fixed carbon ignition point); b reflects the accelerating effect of volatiles on the burning rate; and c represents the lower temperature limit (related to the ash thermal resistance).

[0263] In another embodiment, the functional relationship between the volatile matter content and the deflagration temperature is:

[0264]

[0265] Among them, T 爆燃 is the primary air explosion temperature; V is the volatile matter content in the coal powder; parameters a, b, c, d, e, f, g, and h can be determined by fitting experimental data.

[0266] The model establishes functional relationships in segments, improving the accuracy of model predictions. For low-volatility zones, it reflects nonlinear decay characteristics; for medium-volatility zones, it reflects the linear relationship between volatile release and temperature drop; and for high-volatility zones, it reflects rapid convergence characteristics.

[0267] Furthermore, through the method provided by the present application, the deflagration temperature threshold is no longer a fixed value, but a variable that changes according to the type of coal.

[0268] After determining the deflagration temperature, obtaining the primary air inlet temperature of the coal mill; comparing the primary air inlet temperature of the coal mill with the primary air deflagration temperature of the coal mill; and judging whether the primary air system is abnormal based on the comparison result.

[0269] Specifically, in this application, a corresponding temperature threshold is set according to the deflagration temperature. When the primary air inlet temperature of the coal mill is greater than the temperature threshold, the primary air system is determined to be abnormal. Furthermore, this application sets multiple temperature preset values ​​according to the deflagration temperature to issue three levels of alarms for excessive primary air temperature according to the degree of urgency:

[0270] ① When the primary air inlet temperature is greater than the first preset value and lower than the second preset value and maintains the preset time, the alarm type is determined to be a primary air temperature level 1 alarm; for example, when T 爆燃-10<T 一次风 <T 爆燃 -5, and it lasts for more than 3 seconds, the alarm message "explosion temperature is about to be reached, level 1 alarm" will be sent;

[0271] ② When the primary air inlet temperature is greater than the second preset value and lower than the deflagration temperature and maintains the preset time, the alarm type is determined to be a primary air temperature level 2 alarm; for example, when T 爆燃 -5<T 一次风 <T 爆燃 , and keep it for more than 3 seconds, send the alarm message "explosion temperature is about to reach the second level alarm";

[0272] ③When the primary air inlet temperature is greater than or equal to the deflagration temperature, that is, when T 一次风 >T 爆燃 , determine that the alarm type is a three-level wind temperature alarm, send the alarm message "explosion temperature has been reached", and start the emergency stop procedure.

[0273] 2) Temperature rise rate detection

[0274] If the primary air temperature of the pulverizer rises too quickly, there is also a risk of deflagration, so there is a limit on the temperature rise rate exceeding 5℃ / min (bituminous coal, 3℃ / min for lignite). However, this is a rough engineering setting. In fact, the temperature rise limit value for mixed coal types is variable and is still related to the volatile matter. The higher the volatile matter, the lower the temperature rate requirement, and vice versa.

[0275] To determine whether the primary air system is abnormal based on the parameter values ​​of the preset parameters, it is necessary to first determine the maximum temperature rise rate of the primary air system based on the volatile matter content of the pulverized coal. Specifically, a functional relationship between the volatile matter content of the pulverized coal and the maximum temperature rise rate is obtained by fitting experimental data in advance:

[0276] α max =f(V);

[0277] Among them, α max is the maximum temperature rise rate; V is the volatile matter content in coal powder.

[0278] In one embodiment, the functional relationship between the volatile matter content of the pulverized coal and the maximum temperature rise rate is as follows:

[0279]

[0280] Among them, α max is the maximum temperature rise rate; V is the volatile matter content in the pulverized coal; the parameters k, α0, and β can be obtained by fitting the experimental data, k is the rate attenuation coefficient, α0 is the volatile matter offset, and β is the reference rate.

[0281] After determining the maximum temperature rise rate, the primary air temperature rise rate of the coal mill is obtained, and the primary air temperature rise rate of the coal mill is compared with the maximum temperature rise rate of the primary air system. Specifically, the present application sets a temperature rise rate threshold according to the temperature rise rate. When the primary air temperature rise rate is greater than the temperature rise rate threshold, the temperature rise rate is determined to be abnormal, and the corresponding alarm type is determined based on the comparison result. In the present application, two levels of alarm are set for abnormal temperature rise rate:

[0282] When the primary air temperature rise rate is greater than the first temperature rise rate warning threshold and less than the maximum temperature rise rate, and the second preset time is maintained, the alarm type is determined to be a temperature rise rate level 1 alarm. For example, when α max >α>α max -0.2, and keep it for more than 3 seconds, the alarm message "the upper limit of temperature rise is about to be reached, level 1 alarm" will be sent.

[0283] When the primary air temperature rise rate is greater than or equal to the maximum temperature rise rate and is maintained for a second preset time, the alarm type is determined to be a temperature rise rate level 2 alarm, and the hot primary air volume is reduced; for example, when α≥α max , and keep it for more than 3 seconds, reduce the hot air volume once, and reduce the temperature rise to below the alarm value.

[0284] 3) Valve jam detection

[0285] Under normal circumstances, the valve opening command and feedback are consistent, with the deviation between the two being essentially zero. When a valve is stuck, the valve opening feedback and the opening command become mismatched. A typical situation is when the difference between the opening and the measured value fluctuates, often failing to reach zero. Another situation is when the feedback remains unchanged regardless of the command, indicating severe valve sticking.

[0286] Therefore, the preset parameters corresponding to the valve sticking are determined to be the valve opening command value and the valve opening actual value of the coal mill primary air regulating valve;

[0287] The method of judging whether the primary air system is abnormal based on the parameter value of the preset parameter is as follows: specifically, calculating the variance of the valve opening instruction value and the actual valve opening value of the primary air regulating valve; then, comparing the equation with the preset variance threshold, wherein the preset variance threshold can be determined based on data under historical normal conditions, such as the standard deviation of the valve opening instruction value and the actual valve opening value of the primary air regulating valve under historical normal working conditions. Furthermore, when the variance is greater than the preset variance threshold (for example, three standard deviations), it is determined that the primary air system is abnormal and the primary air regulating valve is stuck. It is understandable that the valve stuck here can be analyzed and determined for the valve stuck of the hot primary air regulating valve and the valve stuck of the cold primary air regulating valve respectively.

[0288] Furthermore, in the present application, a two-level alarm is performed for valve sticking. When the variance is greater than a preset variance threshold, it is determined to be a first-level sticking. When, under the premise of first-level sticking, the actual measured value of the valve opening remains unchanged for a long time within a preset time period, that is, it does not change with the change of the valve instruction, it is determined to be a second-level sticking.

[0289] For example, the data 600 seconds before the timing point (once per second) is used to calculate the variance of the difference between the opening command and the measured value. If it exceeds three standard deviations under normal operating conditions, it is beyond the normal range and can be determined as a level one jam. On the premise of meeting the level one jam, if the measured value remains unchanged for a long time (the data 600 seconds before the current point can be used for judgment), it is determined as a level two jam.

[0290] 4) Valve failure detection

[0291] Valve failure is difficult to determine. For example, if the valve connecting rod falls off, the valve core is severely worn, or the valve leaks, no matter how the actuator operates, even if the feedback is normal, the actual flow rate of the valve will not change much or even not change. This effect can be called a failure. Valve failure is more dangerous. The apparent normal state masks the possibility of an impending crisis, such as a rapid increase in temperature. Therefore, this application calculates the theoretical flow rate and temperature of the mixed primary air formed by mixing hot primary air and cold primary air, and compares the theoretical values ​​with the actual values ​​to determine whether the valve has failed.

[0292] Therefore, when the target detection is valve failure detection, the preset parameters are the valve opening of the hot primary air regulating valve and the valve opening of the cold primary air regulating valve of the coal mill determined according to the preset corresponding relationship table.

[0293] Specifically, judging whether the primary air system is abnormal based on the parameter value of the preset parameter includes: determining the flow adjustment coefficient of the hot primary air adjustment valve and the flow adjustment coefficient of the cold primary air adjustment valve based on the valve opening of the hot primary air adjustment valve and the valve opening of the cold primary air adjustment valve of the coal mill; for example, querying a pre-stored first correspondence table based on the valve opening of the hot primary air adjustment valve and the valve opening of the cold primary air adjustment valve to determine the flow adjustment coefficient of the hot primary air adjustment valve and the flow adjustment coefficient of the cold primary air adjustment valve.

[0294] Then, the theoretical value of the hot primary air flow rate and the theoretical value of the cold primary air flow rate are calculated based on the flow adjustment coefficient of the hot primary air adjustment valve and the flow adjustment coefficient of the cold primary air adjustment valve. For example, the flow adjustment coefficient of the hot primary air adjustment valve and the flow adjustment coefficient of the cold primary air adjustment valve are respectively substituted into the following primary air flow prediction model to determine the theoretical value of the hot primary air flow rate and the theoretical value of the cold primary air flow rate:

[0295]

[0296] Among them, Q h is the theoretical value of hot primary air flow; Q c is the theoretical value of cold primary air flow; C v h C is the flow coefficient of the hot primary air adjustment valve; v c P is the flow coefficient of the cold primary air adjustment valve; h is the hot primary air inlet pressure; P c is the cold primary air inlet pressure; P mix is the pressure of the mixed primary air; ρ h is the hot primary air density; ρ c is the density of cold primary air.

[0297] For ρ h and ρ c The inlet air temperature and pressure can be measured in real time and calculated using the following formula:

[0298] ρ h =P h / (RT h ),ρ c =P c / (RT c );

[0299] Among them, ρ h is the hot primary air density; ρ c is the density of cold primary air; P h is the hot primary air inlet pressure; P c is the cold primary air inlet pressure; T h is the hot primary air inlet temperature; T c is the cold primary air inlet temperature; R is the gas constant.

[0300] Furthermore, the theoretical value of the mixed primary air flow rate and the theoretical value of the mixed primary air temperature can be calculated based on the theoretical value of the hot primary air flow rate and the theoretical value of the cold primary air flow rate. For example, the theoretical value of the hot primary air flow rate and the theoretical value of the cold primary air flow rate are substituted into the following formula to determine the theoretical value of the mixed primary air flow rate and the theoretical value of the mixed primary air temperature:

[0301] Q mix =Q h +Q C ;

[0302]

[0303] Among them, Q mix is the theoretical value of mixed primary air flow; Q h is the theoretical value of hot primary air flow; Qc Qhot is the theoretical value of the hot primary air flow; T mix Tmix is the theoretical value of the mixed primary air temperature; P h Pht is the hot primary air inlet pressure; P c Pc is the cold primary air inlet pressure; T h Th is the hot primary air inlet temperature; T c Tc is the cold primary air inlet temperature; p h ph is the hot primary air density; p c pc is the cold primary air density.

[0304] The theoretical value of the mixed primary air flow is compared with the actual value of the mixed primary air flow, and the theoretical value of the mixed primary air temperature is compared with the actual value of the mixed primary air temperature. The present application considers two valves as a whole, and abnormal temperature and flow will be caused if one of the valves is out of order. After the valve fails, the mixed primary air flow is affected first, which may be larger or smaller, and then the mixed primary air temperature, which has greater inertia relative to the flow and needs a certain time to react. According to the above characteristics, the present application detects the valve failure, specifically, determines the proportion of the deviation of the theoretical value of the mixed primary air flow from the actual value of the mixed primary air flow to the theoretical value of the mixed primary air flow as a first comparison result; and determines the deviation of the theoretical value of the mixed primary air temperature from the actual value of the mixed primary air temperature as a second comparison result. The present application determines whether the primary air system is abnormal according to the comparison results, which includes:

[0305] When the first comparison result is greater than a preset proportion coefficient or the second comparison result is greater than a preset temperature deviation value, it is determined that the primary air system is abnormal. Specifically, when the first comparison result exceeds a preset proportion of the theoretical value of the mixed primary air flow, it is determined that the alarm type is a first-level failure alarm of the hot primary air adjusting valve and the cold primary air adjusting valve; when the second comparison result is greater than a first preset temperature deviation value, it is determined that the alarm type is a second-level failure alarm of the hot primary air adjusting valve and the cold primary air adjusting valve; and when the second comparison result is greater than a second preset temperature deviation value, it is determined that the alarm type is a third-level failure alarm of the hot primary air adjusting valve and the cold primary air adjusting valve.

[0306] For example, when |Q mix理论 -Q mix实际 | / Q mix理论 >10%, it is a first-level failure alarm of the hot primary air adjusting valve and the cold primary air adjusting valve; when |T mix理论 -T mix实际 |>5℃, it is a second-level failure alarm of the hot primary air adjusting valve and the cold primary air adjusting valve; when |T mix实际 -T mix理论 |>10℃, it is a third-level failure alarm of the hot primary air adjusting valve and the cold primary air adjusting valve.

[0307] In this application, it should be noted that the hot primary air adjustment valve flow coefficient C v h Flow coefficient C of cold primary air regulating valve v c Although calculated from the valve inlet and outlet parameters, they do not depend on the mixed parameters (flow and temperature). The mixed parameters are only the result of the mixing. They are only related to the inlet temperature, flow and opening. Therefore, each pair of inlet temperature, flow and opening can be mapped to an outlet mixed flow and temperature. In this way, a mapping table can be established to achieve C v h and C v c Real-time calculation.

[0308] In one embodiment of the present application, the flow adjustment coefficient of the hot primary air adjustment valve and the flow adjustment coefficient of the cold primary air adjustment valve are determined according to the valve opening of the hot primary air adjustment valve and the valve opening of the cold primary air adjustment valve of the coal mill; for example, a pre-stored first correspondence table is queried according to the valve opening of the hot primary air adjustment valve and the valve opening of the cold primary air adjustment valve to determine the flow adjustment coefficient of the hot primary air adjustment valve and the flow adjustment coefficient of the cold primary air adjustment valve, wherein the first correspondence table stores the correspondence between valve opening combinations and flow adjustment coefficient combinations.

[0309] In another embodiment of the present application, since each real-time state can obtain an inlet pressure combination (P h ,P c ), inlet temperature combination (T h ,T c ) and valve opening combination (θ h ,θ c), so that the target working condition closest to the working condition can be selected in the corresponding relationship table to determine the corresponding flow adjustment coefficient. At this time, the method for determining the flow adjustment coefficient of the hot primary air adjusting valve and the flow adjustment coefficient of the cold primary air adjusting valve according to the valve opening of the hot primary air adjusting valve and the valve opening of the cold primary air adjusting valve of the coal mill comprises: obtaining the inlet pressure combination and the inlet temperature combination of the hot primary air and the cold primary air corresponding to the valve opening combination at the current time; constructing a working condition feature vector from the valve opening combination and the inlet pressure combination and the inlet temperature combination; matching the working condition feature vector with the working condition feature vectors of each standard working condition in the second corresponding relationship table stored in advance to determine the target working condition corresponding to the working condition feature vector, wherein the second corresponding relationship table stores the corresponding relationship between the working condition feature vectors of the standard working conditions and the flow adjustment coefficient combinations; and determining the flow adjustment coefficient combination of the target working condition as the flow adjustment coefficient combination of the hot primary air adjusting valve and the cold primary air adjusting valve.

[0310] For example, the matching of the working condition feature vector with the working condition feature vectors of each standard working condition in the second corresponding relationship table stored in advance to determine the target working condition corresponding to the working condition feature vector can be: calculating the deviation of each element in the working condition feature vector from the corresponding element in the working condition feature vector of each standard working condition in the second corresponding relationship table stored in advance; determining the standard working condition with all deviations less than a preset deviation threshold as a candidate working condition; and determining the working condition with the smallest deviation in the candidate working conditions as the target working condition. For example, find the working condition with an absolute difference of no more than 5% for the above six points, and select the working condition with the smallest deviation as the target working condition.

[0311] Of course, the matching of the working condition feature vector with the working condition feature vectors of each standard working condition in the second corresponding relationship table stored in advance to determine the target working condition corresponding to the working condition feature vector can also be: calculating the similarity of the working condition feature vector with the working condition feature vectors of each standard working condition in the second corresponding relationship table stored in advance; and determining the standard working condition with the highest similarity as the target working condition.

[0312] In this embodiment, the second correspondence table is constructed in the following manner: obtaining the valve opening combination of the hot primary air regulating valve and the cold primary air regulating valve under standard working conditions and the corresponding historical parameter data, wherein the historical parameter data at least includes the inlet pressure combination of the hot primary air and the cold primary air, the inlet temperature combination of the hot primary air and the cold primary air, and the measured value of the mixed primary air pressure, the measured value of the mixed primary air flow rate, and the measured value of the mixed primary air temperature; calculating the wind density combination of the hot primary air and the cold primary air, the wind flow combination of the hot primary air and the cold primary air, the hot primary air regulating valve opening combination and the corresponding historical parameter data according to the historical data. and the differential pressure combination of the hot primary air regulating valve; calculate the flow adjustment coefficient combination of the hot primary air regulating valve and the cold primary air regulating valve according to the wind density combination of the hot primary air and the cold primary air, the wind flow combination of the hot primary air and the cold primary air, and the differential pressure combination of the hot primary air regulating valve and the cold primary air regulating valve; construct the second correspondence table according to the valve opening combination of the hot primary air regulating valve and the cold primary air regulating valve under the standard working conditions, the inlet pressure combination of the hot primary air and the cold primary air, the inlet temperature combination of the hot primary air regulating valve and the cold primary air regulating valve and the flow adjustment coefficient combination of the hot primary air regulating valve and the cold primary air regulating valve.

[0313] Specifically, the wind density combination of the hot primary air and the cold primary air is calculated by the following formula:

[0314] ρ h =P h / (RT h ),ρ c =P c / (RT c );

[0315] Among them, ρ h is the hot primary air density; ρ c is the density of cold primary air; P h is the hot primary air inlet pressure; P c is the cold primary air inlet pressure; T h is the hot primary air inlet temperature; T c is the cold primary air inlet temperature; R is the gas constant.

[0316] The combined flow rate of hot primary air and cold primary air is calculated using the following formula:

[0317]

[0318] Among them, Q h is the hot primary air flow rate; Q c Q is the cold primary air flow rate; mix is the mixed primary air flow rate; T mix is the mixed primary air temperature; ρ h is the hot primary air density; ρc is the density of cold primary air; T h is the hot primary air inlet temperature; T c It is the cold primary air inlet temperature.

[0319] The differential pressure combination of the hot primary air regulating valve and the cold primary air regulating valve is calculated by the following formula:

[0320] ΔP h =P h -P mix ,ΔP c =P c -P mix ;

[0321] Where ΔP h The differential pressure between the inlet and outlet of the hot primary air regulating valve; ΔP c P is the differential pressure between the inlet and outlet of the cold primary air regulating valve; h is the hot primary air inlet pressure; P c is the cold primary air inlet pressure; P mix is the pressure of the mixed primary air.

[0322] The flow adjustment coefficient combination of the hot primary air adjustment valve and the cold primary air adjustment valve is calculated by the following formula:

[0323]

[0324] Among them, C v h C is the flow coefficient of the hot primary air adjustment valve; v c Q is the flow coefficient of the cold primary air adjustment valve; h is the hot primary air flow rate; Q c is the cold primary air flow rate; ΔP h The differential pressure between the inlet and outlet of the hot primary air regulating valve; ΔP c P is the differential pressure between the inlet and outlet of the cold primary air regulating valve; h is the hot primary air inlet pressure; P c is the cold primary air inlet pressure; ρ h is the hot primary air density; ρ c is the density of cold primary air.

[0325] For example, if 1000 historical data are extracted, for each set of data, the opening combination (θh, θc), inlet pressure combination (Ph, Pc), inlet temperature combination (Th, Tc) and flow adjustment coefficient combination (C v h , C v c ) to construct a second correspondence table that can cover all working conditions.

[0326] Furthermore, the safety information of the primary air system is determined based on at least one of the primary air inlet temperature, the primary air temperature rise rate, the valve failure, and the valve jamming detection results. The safety information of the primary air system is determined as the safety information of the primary air system.

[0327] The method of judging whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes: determining that the medium-speed coal mill has a fire risk when at least one of the following conditions occurs: the primary air inlet temperature is greater than the primary air explosion temperature of the coal mill; the primary air temperature rise rate is greater than the maximum temperature rise rate of the primary air system; the valve failure detection result indicates that the valve has failed; the valve jam detection result indicates that the valve is jammed.

[0328] (5) Fire steam purge failure warning

[0329] When the preset parameters include a medium-speed coal mill purge result, the step of determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes:

[0330] Obtain the most recent historical purge result of the medium-speed coal mill; when the historical purge result indicates that the purge of the medium-speed coal mill has failed, determine that the medium-speed coal mill has a fire risk. Specifically, the purge result judgment process is as follows:

[0331] In this application, the grinding system needs to be shut down before purging. Since the coal mill is filled with a mixture of coal powder and air when it is running, and during normal operation, the primary air will continue to provide the coal mill with power to transport coal powder, so that the coal powder is in a flowing and suspended state. If fire steam purging is carried out at this time, a large amount of steam will enter the coal mill, which will cause the mixture of coal powder and air to be strongly disturbed, causing the coal powder to fly and fully mix with the air to form an explosive mixture. Once it encounters a fire source or high temperature, it is very easy to cause an explosion accident. Therefore, before steam purging, the hot primary air damper and the cold primary air damper of the coal mill need to be closed, and the operation of the coal mill needs to be stopped.

[0332] When the pulverizer meets the purging conditions, the type of steam used to purge the pulverizer is determined based on the coal type information of the residual pulverized coal in the pulverizer. This coal type information refers to the classification of coal into anthracite, bituminous coal, and lignite based on indicators such as dry ash-free volatile matter (DAFV). Bituminous coal can be further divided into lean coal, lean lean coal, lean coal, coking coal, fat coal, 1 / 3 coking coal, gas-fat coal, gas coal, 1 / 2 medium-caking coal, weakly caking coal, non-caking coal, and long-flame coal, among other categories of lignite and bituminous coal. Coal type information can be obtained using a volatile matter detector installed on the coal feeder. Because different types of pulverized coal have different volatile contents and ignition points, for example, lignite has a higher volatile content and a lower ignition point, making it prone to spontaneous combustion or explosion at high temperatures. Using inappropriate steam for purging can cause the pulverized coal temperature to rise, potentially leading to explosions. Therefore, it is necessary to select the appropriate steam type based on the coal type to reduce the temperature and humidity of the pulverized coal and prevent explosions. Specifically, the types of steam used for purging include supersaturated steam and saturated steam, wherein the types of steam required for different types of coal can be predetermined, for example, supersaturated steam is used for lignite and saturated steam is used for other types of coal.

[0333] Then, the corresponding type of purge steam is injected into the coal mill; the injected steam type and steam pressure are tested to determine if they meet the requirements. In this application, the steam pressure and steam temperature of the purge steam are obtained, and the steam type is determined based on the steam pressure and steam inlet temperature. The steam pressure is determined based on the steam pressure threshold and the pressure fluctuation threshold.

[0334] 1) Check whether the steam type is qualified:

[0335] According to the steam pressure, the corresponding saturation temperature table (i.e., water vapor table) is searched to determine the saturation temperature range corresponding to the current steam pressure; then, whether the current steam temperature is qualified is determined. Specifically, if the steam temperature is in the saturation temperature range, it is saturated steam; if the steam temperature is higher than the maximum value of the saturation temperature range, it is superheated steam; if the steam temperature is lower than the minimum value of the saturation temperature range, it is unsaturated steam. When the current steam is saturated steam or superheated steam, the steam type is determined to be qualified; of course, in order to ensure the purging effect, the steam temperature can also be continuously observed for one minute. If the qualified steam quality is reached within one minute and remains qualified for 30 seconds, the steam quality is determined to be qualified.

[0336] If the current steam is unsaturated steam, it will prompt that the steam type is unqualified; similarly, in order to ensure the purging effect, you can also continuously observe the steam temperature for one minute when the current steam is unsaturated steam. If it reaches saturated steam or superheated steam within one minute and maintains for 30 seconds, it is judged that the steam type is qualified, otherwise it is unqualified.

[0337] 2) Check whether the steam pressure is qualified.

[0338] Under normal circumstances, the purge pressure needs to be higher than a certain pressure value (such as 0.3Mpa). However, if there are many steam users in the steam manifold, the pressure may be lower during some periods of time. This may cause the steam to be unable to penetrate the coal powder layer and the inerting effect is insufficient. In addition, the purge steam pressure should be relatively stable during the injection process. For example, the absolute value of the pressure fluctuation should be within 0.1MPa. If the pressure drops suddenly or fluctuates frequently, it may indicate that the pipeline is blocked, the valve is leaking, or the steam source is unstable, which seriously affects the purge effect. Therefore, this application pre-sets the steam pressure threshold and the pressure fluctuation threshold. When the steam pressure is greater than the preset steam pressure threshold and the pressure fluctuation is less than or equal to the preset pressure fluctuation threshold, the steam pressure is determined to be qualified. For example, the steam pressure is greater than 0.3MP and the purge steam pressure fluctuation during the process should be ≤±0.1MPa to be qualified. Otherwise, the steam pressure is judged to be unqualified.

[0339] Because different types of coal have varying physical and chemical properties, such as hardness and viscosity, these properties can affect the accumulation and flow characteristics of the coal within the pulverizer, and thus the purging effect. For example, for viscous coal, higher-pressure steam may be required for purging to improve the purging effect. Therefore, in one embodiment of the present application, the steam pressure threshold and pressure fluctuation threshold are pre-set based on the coal type information.

[0340] If the steam type and steam pressure tests are qualified, proceed to the next step. Otherwise, if the steam type and / or steam pressure tests are unqualified, the purge is determined to have failed, the steam purge valve is closed, and a message is displayed indicating that the steam contains water or the pressure is unstable. Please take action.

[0341] When the steam type and steam pressure are qualified, determine whether the steam flow meets the minimum purge steam flow requirement. The fire steam volume of the coal mill should be determined according to the volume of the inerted coal mill to determine the required minimum steam flow, and the fire steam replaces and dilutes the oxygen in the coal mill to reduce the oxygen concentration to within the preset content (i.e., the lower limit of coal powder explosion). Specifically, the preset time for the coal mill to complete the purge and the preset content of oxygen required for the coal mill to reach the purge requirement after the purge is completed are determined based on the coal type information of the residual coal powder in the coal mill. Then, the preset time t for the coal mill to complete the purge and the preset content C1 of oxygen required for the coal mill to reach the purge requirement after the purge is completed are substituted into the following formula to determine the minimum steam volume required for the coal mill to reduce the oxygen content in the coal mill from the initial value C0 to the target value C1:

[0342]

[0343] Among them, Q steam Indicates the required fire steam mass flow rate (kg / h); V indicates the coal mill volume (m 3); Co represents initial oxygen concentration (e.g. 21%); C1 represents preset oxygen content of the pulverizer to meet the purging requirement after the purging is completed (e.g. 12% for bituminous coal, 10% for high-volatile coal and lignite); p air represents air density (1.29 kg / m 3 , standard state); η represents inerting efficiency (0.7-0.8); t represents preset time length for the pulverizer to complete purging (e.g. 10 minutes for conventional, 8 minutes for high-volatile coal and 5 minutes for lignite); M air represents air molar mass; M steam represents steam molar mass.

[0344] When the steam flow meets the minimum purging steam flow requirement, the purging time is counted. By obtaining the current real-time steam flow, if the steam flow is greater than or equal to the minimum steam purging flow, the purging requirement is met, and the steam purging timing is started; if the check steam flow is less than the minimum steam purging flow, it is determined that the purging fails, the steam purging valve is closed, and it is prompted that the steam purging flow is insufficient.

[0345] During the purging process, the internal pressure of the pulverizer is monitored, and the steam pressure is adjusted according to the internal pressure of the pulverizer, so that the internal pressure of the pulverizer rises at a specific rate. The pressure rise rate reflects the dynamic change of steam in the pulverizer. If the rise rate is too fast, it may cause excessive impact on the internal structure of the pulverizer, resulting in equipment damage; while the rise rate is too slow, it may not achieve effective purging effect. Therefore, the internal pressure of the pulverizer should be ensured to rise at a specific rate. Specifically, the specific rate can be a preset pressure rise rate range, for example, 1-3 kPa / min. The specific adjustment process is as follows: by obtaining the internal pressure of the pulverizer in real time, the internal pressure rise rate of the pulverizer is determined; by PID dynamic adjustment of the steam pressure, the internal pressure rise rate of the pulverizer is maintained within the preset pressure rise rate range. In the whole process, the PID controller continuously adjusts the steam flow or the opening degree of the pressure regulating device (such as the regulating valve) according to the deviation between the specific rate of the internal pressure rise of the pulverizer preset in advance and the actual measured pressure rise rate, combined with the PID parameters adjusted in advance according to the characteristics of the coal, so as to realize accurate control of the steam pressure rise rate.

[0346] Among them, PID control is a feedback control algorithm widely used in industrial process control. The three parameters of proportional coefficient (P), integral time (I) and differential time (D) work together to adjust the control output according to the deviation between the set value and the actual measured value. The proportional link adjusts the output proportionally according to the size of the deviation. The larger the deviation, the larger the adjustment amplitude; the integral link is used to eliminate steady-state errors and adjusts the deviation as it accumulates over time; the differential link adjusts according to the rate of change of the deviation and can respond quickly to dynamic changes in the system. In this application, different adjustment parameters are selected according to different coal types. For example, lignite, a coal with a high volatile content, has a relatively low ignition point and is prone to combustion or even explosion. During fire steam purge, it is necessary to control the steam pressure rise rate more quickly and accurately. Using a more aggressive proportional coefficient (larger P value) means that when there is a deviation, the control system will make a larger adjustment, so that the steam pressure rise rate can reach and stabilize at an appropriate value more quickly, thereby more effectively suppressing the fire risk caused by the volatile content of lignite.

[0347] At the same time, this application adds feedforward control and monitors the steam main pressure to predict possible disturbances to the steam pressure inside the coal mill. For example, if the steam main pressure suddenly increases or decreases, this may directly affect the steam pressure entering the coal mill. Through feedforward control, the system can adjust the steam flow rate or other related parameters in advance based on the changing trend of the steam main pressure before the internal pressure of the coal mill is significantly affected, thereby reducing the impact of disturbances on the rate of pressure rise inside the coal mill and ensuring that the pressure can rise according to the pre-set pressure rise rate.

[0348] When the timed purge time reaches the preset time, the oxygen content inside the coal mill is monitored.

[0349] Consistent with the above, the preset time for the coal mill to complete purging and the preset oxygen content required for the coal mill to meet the purging requirements after purging are determined based on the coal type information of the residual coal powder in the coal mill.

[0350] This application determines the preset time for the coal mill to complete the purge based on the coal type information. First, based on the predetermined coal type-purge time correspondence table, the basic purge time of each coal type is queried. For example, the basic purge time of bituminous coal is 10 minutes, the basic purge time of high-volatile coal is 8 minutes, and the basic purge time of lignite is 5 minutes. Then, the current stop state is obtained. When the current stop state is an emergency stop, the preset time for the coal mill to complete the purge is the basic purge time plus the preset time; otherwise, the preset time for the coal mill to complete the purge is determined to be the basic purge time.

[0351] When the purge duration reaches a preset value, the oxygen content within the coal mill is measured. When the oxygen content within the coal mill falls below the preset value, the purge is determined to be successful, and the steam purge valve is closed. In this application, the preset oxygen content after purging for different coal types can be determined based on a preset coal type-oxygen content mapping table. For example, the oxygen content threshold for bituminous coal is 12%, and the oxygen content threshold for high-volatile coal and lignite is 10%. When the oxygen content in the coal mill is greater than or equal to the preset content corresponding to the coal type, it is determined whether it is an emergency stop; when the current stop state is an emergency stop, when the oxygen content of the coal mill is lower than the preset content, the steam purge valve is automatically closed to determine that the purge is successful; when the current stop state is an emergency stop and the purge time reaches the maximum purge time, the steam purge valve is automatically closed, and the re-purge process is restarted after checking that the purge steam system has no faults and the coal mill has no leakage; when it is not an emergency stop, it is determined that the purge has failed, the steam purge valve is closed, and a prompt is given that "the oxygen content does not meet the safety quality assurance, and the steam purge failed."

[0352] In one embodiment of the present application, after the purging is successful, the internal pressure stability of the coal mill is monitored to determine whether there is any leakage in the system. When the purging is successful, the pressure fluctuation amplitude should be within the preset range, for example, the absolute value of the pressure fluctuation is ≤1kPa. If the pressure continues to drop, it indicates that there is a leakage interruption in the system. When the rate of decrease of the internal pressure of the coal mill is less than the first rate, it is determined that the coal mill has no leakage; when the rate of decrease of the internal pressure of the coal mill is greater than the first rate, it is determined that the coal mill has a leakage. Further, when the rate of decrease of the internal pressure of the coal mill is greater than the first rate and less than the second rate, it is determined that the coal mill has a first-level leakage, and the steam flow rate is increased and the purging time is extended. For example, when the rate of decrease is 0.5-1kPa / min, the steam flow rate is increased by 10% and the purging time is extended by 20%; when the rate of decrease of the internal pressure of the coal mill is greater than or equal to the second rate, it is determined that the coal mill has a second-level leakage, for example, when the rate of decrease is greater than 1kPa / min, it is determined that the purging has failed, the purging is immediately interrupted, the coal mill is locked and the maintenance alarm is triggered.

[0353] In one embodiment of the present application, the purging effect can also be judged based on the temperature of the coal mill shell. Since the temperature should tend to be stable after the steam is injected and eventually approach the temperature of the fire steam. In this embodiment, the coal mill shell temperature is obtained; the temperature rise rate is calculated based on the coal mill shell temperature; when the temperature rise rate is less than the preset temperature rise rate value, it indicates that the current coal mill shell temperature is tending to be stable. When the temperature rise rate is less than the preset temperature rise rate value or the purging reaches the preset time, the difference between the current coal mill shell temperature and the steam temperature is calculated; when the difference is greater than the preset temperature threshold, it means that the purging has not cleaned or processed the internal substances to the ideal state, and there are still potential safety hazards. It is determined that the purging has failed and an alarm is issued.

[0354] In summary, this coal mill fire steam purging solution is dedicated to ensuring safe, efficient, and reliable operation of the mill, offering significant safety and economic advantages. The solution encompasses multiple measures: real-time monitoring of key parameters ensures effective inerting to prevent deflagration, dynamically adjusting purge time based on coal type; real-time verification of steam quality, intelligent calculation of minimum steam flow, and monitoring of pressure fluctuations to optimize purge effectiveness; closed-loop control processes and fault self-diagnosis enhance automation and reduce human error; improved adaptability to special operating conditions such as high-volatile coal and emergency shutdowns; and protection against wet steam effects to extend equipment life and reduce maintenance costs. Key components of the solution include real-time verification of steam quality, calculation and dynamic adjustment of minimum steam flow, real-time monitoring of oxygen concentration and pressure, dynamic adjustment of purge time, and fault self-diagnosis and closed-loop control. This comprehensive technical approach ensures the precision, automation, and safety of coal mill fire steam purging. Especially for high-risk scenarios, this approach leverages multi-parameter model collaborative optimization and real-time decision-making logic to create a technical barrier to prevent deflagration.

[0355] Through the above monitoring, early warning before fire can be achieved. When a medium-speed coal mill is about to catch fire, the system will show some abnormal fluctuations or instability.

[0356] Through the above monitoring, in addition to warning before a fire and alarming when a fire occurs, the fire site can also be accurately located. Whether a fire has occurred is mainly determined by a comprehensive judgment of the grinding bowl differential pressure and the mill outlet temperature, and the stage, location and severity of the fire are judged according to various conditions of differential pressure and temperature changes. The grinding bowl differential pressure is sensitive: compared with temperature (heat transfer lag), the differential pressure change can more quickly reflect the sudden change of airflow resistance in the mill, and is a key parameter for early warning. However, it does not mean that the differential pressure change will necessarily be earlier than the outlet temperature change. This depends on multiple conditions such as the location of the fire source, and is divided into the following situations:

[0357] (1) Grinding bowl fire alarm

[0358] When the differential pressure first fluctuates violently and then the temperature rises rapidly, the fire source is concentrated in the grinding bowl area. The reason is that local coking / explosion directly affects the airflow resistance, causing the grinding bowl to fluctuate violently. After the heat diffuses to the outlet, the temperature rises rapidly. In this case, a "grinding bowl on fire" alarm is issued.

[0359] (2) Fire alarm at the mill outlet

[0360] When the outlet temperature rises first, and then the grinding bowl differential pressure fluctuates violently, this indicates that the mill outlet is on fire. The reason is that the outlet is directly burned and the temperature rises rapidly; the differential pressure fluctuation occurs later due to subsequent coking or air flow turbulence. At this time, the "mill outlet fire" alarm is issued

[0361] (3) Sudden explosion alarm

[0362] When the differential pressure fluctuates violently instantly, the temperature rise occurs later. This indicates that a deflagration has occurred inside the pulverized coal. The reason is that the deflagration causes a sudden change in the differential pressure, but the heat takes time to transfer to the outlet. At this time, a "sudden deflagration" alarm is issued.

[0363] (4) Serious explosion alarm occurs

[0364] When the differential pressure fluctuates violently and increases, and the outlet temperature rises rapidly, the deflagration increases the differential pressure, indicating that the deflagration has caused coking, blockage, and other phenomena, indicating that the combustion is serious. At this time, the "serious deflagration" alarm is issued.

[0365] In terms of early warning and alarm, this application realizes the integration of full-cycle dynamic early warning and precise alarm through multi-parameter collaborative monitoring and real-time comparison of dynamic thresholds with theoretical models, and dynamically adjusts thresholds based on moving standard deviations and working condition data, breaking through the limitations of single-parameter static alarms and avoiding false alarms; constructing a multi-level alarm system and locating the fire source based on the time series characteristics of parameters, forming a phased fire identification and graded response mechanism, allowing operators to respond accurately and reduce "one-size-fits-all" downtime losses; using spatiotemporal feature analysis to achieve three-dimensional diagnosis of fire source location and type, improving the ability to locate and diagnose fire source types; using an association rule engine to incorporate multiple fault parameters into the decision tree, achieving multi-fault coupling risk prevention and control, and reducing the risk of misjudgment; with a dynamic calibration mechanism, it can correct theoretical models and optimize coefficients in real time based on historical data, enhancing model self-learning and reliability. Its key links include dynamic multi-parameter fusion monitoring and threshold optimization, a graded response system of early warning-alarm-location, fire source location logic based on time series characteristics, a multi-fault coupling association analysis engine, and a self-learning model and dynamic calibration mechanism.

[0366] The beneficial effects of the present application are: obtaining a variety of preset parameters of the medium-speed coal mill during its operation; judging whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill; and issuing an early warning when the medium-speed coal mill has a fire risk. Since the coal mill is judged to have a fire risk based on a variety of preset parameters, the situation where a single parameter monitoring cannot capture the fire risk under complex working conditions is avoided. In addition, automatic judgment based on preset parameters improves the real-time nature of the early warning. In addition, the present application improves the sensitivity and accuracy of anomaly recognition through multi-parameter collaborative analysis, integration of multi-dimensional data, and calculation of deviations through dynamic models.

[0367] In one embodiment, when the preset parameters include an expected value of the grinding bowl pressure difference, the above step S101 may be implemented as the following steps A1-A4:

[0368] In step A1, the operation of the grinding system is monitored;

[0369] In step A2, when the grinding system is already in operation, the fire alarm function is activated;

[0370] In step A3, when the fire alarm function is activated, the primary air volume, pulverized coal mass flow rate, speed, and separator pressure difference of the medium-speed coal mill are obtained;

[0371] In step A4, the expected value of the grinding bowl differential pressure of the medium-speed coal mill is determined according to the primary air volume, the coal powder mass flow rate, the rotation speed, and the separator pressure difference;

[0372] The above step S102 can be implemented as the following steps A5-A6:

[0373] In step A5, the deviation between the expected value of the grinding bowl differential pressure of the medium-speed coal mill and the actual value of the grinding bowl differential pressure of the medium-speed coal mill is determined;

[0374] In step A6, when the deviation is greater than a first dynamic threshold, it is determined that the medium-speed coal mill has a fire risk and an early warning message is issued, wherein the first dynamic threshold is obtained by the moving standard deviation of the deviation.

[0375] In one embodiment, when the preset parameters include temperature difference and temperature rise rate, the above step S101 can be implemented as the following steps B1-B3:

[0376] In step B1, the hot primary air volume, hot primary air temperature, cold primary air volume, cold primary air temperature and actual outlet temperature of the medium-speed coal mill are obtained;

[0377] In step B2, the theoretical outlet temperature of the medium-speed coal mill is determined by substituting the hot primary air volume, hot primary air temperature, cold primary air volume and cold primary air temperature of the medium-speed coal mill into an outlet temperature model;

[0378] In step B3, the temperature difference is calculated based on the actual outlet temperature value and the theoretical outlet temperature value of the medium-speed coal mill, and the temperature rise rate is calculated based on the actual outlet temperature value;

[0379] The above step S102 can be implemented as the following steps B4-B5:

[0380] In step B4, when the temperature difference exceeds a preset threshold or the temperature rise rate exceeds a normal temperature rise rate range, it is determined that the outlet temperature of the medium-speed coal mill has abnormally increased;

[0381] In step B5, when the outlet temperature of the medium-speed coal mill increases abnormally, it is determined that the medium-speed coal mill has a fire risk.

[0382] In one embodiment, when the preset parameters include powder hose blockage, the above step S101 may be implemented as the following steps C1-C3:

[0383] In step C1, the total primary air pressure of the medium-speed coal mill and the primary air flow rate of each powder pipe are obtained;

[0384] In step C2, the current working condition is determined based on the moving average value of the total primary air pressure;

[0385] In step C3, the weight coefficient of each powder hose air volume to the total air volume is calculated based on the moving average of the primary air flow of each powder hose;

[0386] In step C4, whether the powder hose is blocked is determined based on the current working condition and the weight coefficient of each powder hose air volume to the total air volume;

[0387] The above step S102 can be implemented as the following step C5:

[0388] In step C5 , when the powder pipe is blocked, it is determined that the medium-speed coal mill has a fire risk.

[0389] In one embodiment, the above step C3 may be implemented as follows:

[0390] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0391]

[0392] Among them, W i,current Indicates the weight coefficient of the i-th powder hose air volume to the total air volume; F i,MA Represents the moving average of the primary air flow rate of the i-th pipeline.

[0393] In one embodiment, when the preset parameters include safety information of the primary air system, the above step S101 may be implemented as the following steps D1-D2:

[0394] In step D1, the primary air inlet temperature, primary air temperature rise rate, valve failure and valve jam detection results are obtained;

[0395] In step D2, safety information of the primary air system is determined based on at least one of the primary air inlet temperature, the primary air temperature rise rate, valve failure, and valve jam detection results;

[0396] The above step S102 can be implemented as the following step D5:

[0397] In step D3, when at least one of the following conditions occurs, it is determined that the medium-speed coal mill has a fire risk:

[0398] The primary air inlet temperature is greater than the primary air explosion temperature of the coal mill;

[0399] The primary air temperature rise rate is greater than the maximum temperature rise rate of the primary air system;

[0400] The valve failure detection result indicates that the valve has failed;

[0401] The valve sticking test result indicates that the valve is stuck.

[0402] In one embodiment, when the preset parameters include the medium-speed coal mill purge result, the above step S102 may be implemented as the following steps E1-E2:

[0403] In step E1, the most recent historical purge result of the medium-speed coal mill is obtained;

[0404] In step E2, when the historical purging results indicate that the purging of the medium-speed coal mill has failed, it is determined that there is a fire risk in the medium-speed coal mill.

[0405] In one embodiment, the process of determining the purge result may be implemented as follows: Steps F1-F8:

[0406] In step F1, when the coal mill meets the purging conditions, the type of steam used to purge the coal mill is determined according to the coal type information of the residual coal powder in the coal mill;

[0407] In step F2, the corresponding type of purge steam is injected into the coal mill;

[0408] In step F3, the type and pressure of the injected steam are checked to see if they are qualified;

[0409] In step F4, when the steam type and steam pressure are both qualified, it is determined whether the steam flow rate meets the minimum purge steam flow rate requirement;

[0410] In step F5, when the steam flow rate meets the minimum purge steam flow rate requirement, the purge time is counted;

[0411] In step F6, during the purging process, the internal pressure of the coal mill is monitored, and the steam pressure is adjusted according to the internal pressure of the coal mill so that the internal pressure of the coal mill increases at a specific rate;

[0412] In step F7, when the timed purge duration reaches a preset duration, the oxygen content inside the coal mill is monitored;

[0413] In step F8 , when the oxygen content inside the coal mill is lower than a preset content, it is determined that the purging is successful.

[0414] Figure 2 FIG. 1 is a structural diagram of a fire warning device for a medium-speed coal mill according to an embodiment of the present application. Figure 2 As shown, the device includes:

[0415] The acquisition module 201 is used to acquire various preset parameters of the medium-speed coal mill during its operation;

[0416] A judgment module 202 is configured to judge whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill;

[0417] The early warning module 203 is used to issue an early warning when there is a fire risk in the medium-speed coal mill.

[0418] In one embodiment, when the preset parameter includes an expected value of the grinding bowl pressure difference, the acquisition module includes:

[0419] Monitoring submodule, used to monitor the operation status of the grinding system;

[0420] The activation submodule is used to activate the fire alarm function when the grinding system is put into operation;

[0421] The first acquisition submodule is configured to acquire the primary air volume, pulverized coal mass flow rate, rotation speed, and separator pressure difference of the medium-speed coal mill when the fire alarm function is activated;

[0422] A first determination submodule is configured to determine an expected value of the grinding bowl differential pressure of the medium-speed coal mill according to the primary air volume, the coal powder mass flow rate, the rotational speed, and the separator pressure difference;

[0423] The judgment module includes:

[0424] The second determination submodule is used to determine the deviation between the expected value of the grinding bowl differential pressure of the medium-speed coal mill and the actual value of the grinding bowl differential pressure of the medium-speed coal mill;

[0425] The second determination submodule is further configured to determine that the medium-speed coal mill has a fire risk and issue an early warning message when the deviation is greater than a first dynamic threshold, wherein the first dynamic threshold is obtained by a moving standard deviation of the deviation.

[0426] In one embodiment, when the preset parameters include temperature difference and temperature rise rate, the acquisition module includes:

[0427] The second acquisition submodule is used to obtain the hot primary air volume, hot primary air temperature, cold primary air volume, cold primary air temperature and actual outlet temperature of the medium-speed coal mill;

[0428] a third determination submodule, configured to determine a theoretical outlet temperature value of the medium-speed coal mill by substituting the hot primary air volume, hot primary air temperature, cold primary air volume and cold primary air temperature of the medium-speed coal mill into an outlet temperature model;

[0429] a first calculation submodule, configured to calculate a temperature difference between an actual outlet temperature value and a theoretical outlet temperature value of the medium-speed coal mill, and to calculate a temperature rise rate based on the actual outlet temperature value;

[0430] The judgment module includes:

[0431] a fourth determining submodule, configured to determine that the outlet temperature of the medium-speed coal mill has abnormally increased when the temperature difference exceeds a preset threshold or the temperature rise rate exceeds a normal temperature rise rate range;

[0432] The fourth determining submodule is further configured to determine that there is a fire risk in the medium-speed coal mill when the outlet temperature of the medium-speed coal mill increases abnormally.

[0433] In one embodiment, when the preset parameters include powder hose blockage, the acquisition module includes:

[0434] The third acquisition submodule is used to obtain the total primary air pressure of the medium-speed coal mill and the primary air flow rate of each powder pipe;

[0435] A fifth determination submodule is configured to determine a current operating condition based on a moving average of the total primary air pressure;

[0436] The second calculation submodule is used to calculate the weight coefficient of each powder hose air volume to the total air volume based on the moving average of the primary air flow of each powder hose;

[0437] The judgment submodule is used to judge whether there is a powder hose blockage based on the current working conditions and the weight coefficient of each powder hose air volume to the total air volume;

[0438] The judgment module is further configured to:

[0439] When the powder pipe is blocked, it is determined that the medium-speed coal mill has a fire risk.

[0440] In one embodiment, the second calculation submodule is further configured to:

[0441] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0442]

[0443] Among them, W i,current Indicates the weight coefficient of the i-th powder hose air volume to the total air volume; F i,MA Represents the moving average of the primary air flow rate of the i-th pipeline.

[0444] In one embodiment, when the preset parameters include safety information of the primary air system, the acquisition module includes:

[0445] The fourth acquisition submodule is used to obtain the primary air inlet temperature, primary air temperature rise rate, valve failure and valve jam detection results;

[0446] a sixth determining submodule, configured to determine safety information of the primary air system based on at least one of the primary air inlet temperature, the primary air temperature rise rate, the valve failure, and the valve jam detection results;

[0447] The judgment module is further configured to:

[0448] When at least one of the following conditions occurs, it is determined that there is a fire risk in the medium-speed coal mill:

[0449] The primary air inlet temperature is greater than the primary air explosion temperature of the coal mill;

[0450] The primary air temperature rise rate is greater than the maximum temperature rise rate of the primary air system;

[0451] The valve failure detection result indicates that the valve has failed;

[0452] The valve sticking test result indicates that the valve is stuck.

[0453] In one embodiment, when the preset parameters include the medium-speed coal mill purge result, the judgment module includes:

[0454] The fifth acquisition submodule is used to obtain the latest historical purge results of the medium-speed coal mill;

[0455] The seventh determining submodule is configured to determine that the medium-speed coal mill has a fire risk when the historical purging result indicates that the purging of the medium-speed coal mill has failed.

[0456] In one embodiment, the purge result determination process is as follows:

[0457] When the coal mill meets the purging conditions, determining the type of steam used to purge the coal mill according to the coal type information of the residual coal powder in the coal mill;

[0458] injecting the corresponding type of purge steam into the coal mill;

[0459] Check whether the type and pressure of injected steam are qualified;

[0460] When the steam type and steam pressure are qualified, determine whether the steam flow meets the minimum purge steam flow requirement;

[0461] When the steam flow rate meets the minimum purge steam flow rate requirement, the purge time is counted;

[0462] During the purging process, the internal pressure of the coal mill is monitored, and the steam pressure is adjusted according to the internal pressure of the coal mill so that the internal pressure of the coal mill increases at a specific rate;

[0463] When the timed purge time reaches the preset time, the oxygen content inside the coal mill is monitored;

[0464] When the oxygen content inside the coal mill is lower than the preset content, it is determined that the purging is successful.

[0465] Figure 3 FIG. 1 is a schematic diagram of the hardware structure of a medium-speed coal mill fire warning system according to an embodiment of the present application. Figure 3 As shown, the medium-speed coal mill fire warning system includes:

[0466] at least one processor 320; and,

[0467] A memory 304 in communication with the at least one processor 320; wherein,

[0468] The memory 304 stores instructions that can be executed by the at least one processor 320 , and the instructions are executed by the at least one processor 320 to implement the medium-speed coal mill fire warning method described in any of the above embodiments.

[0469] Reference Figure 3 The medium-speed coal mill fire warning system 300 may include one or more of the following components: a processing component 302, a memory 304, a power supply component 306, a multimedia component 308, an audio component 310, an input / output (I / O) interface 312, a sensor component 314, and a communication component 316.

[0470] Processing component 302 generally controls the overall operation of medium-speed coal mill fire warning system 300. Processing component 302 may include one or more processors 320 to execute instructions to perform all or part of the steps of the method described above. Furthermore, processing component 302 may include one or more modules to facilitate interaction between processing component 302 and other components. For example, processing component 302 may include a multimedia module to facilitate interaction between multimedia component 308 and processing component 302.

[0471] The memory 304 is configured to store various types of data to support the operation of the medium-speed coal mill fire warning system 300. Examples of such data include instructions for any application or method operating on the medium-speed coal mill fire warning system 300, such as text, images, videos, etc. The memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0472] The power supply assembly 306 provides power to various components of the medium speed coal mill fire warning system 300. The power supply assembly 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the medium speed coal mill fire warning system 300.

[0473] The multimedia component 308 includes a screen that provides an output interface between the medium-speed coal mill fire warning system 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 may also include a front camera and / or a rear camera. When the medium-speed coal mill fire warning system 300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0474] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC), which is configured to receive external audio signals when the medium-speed coal mill fire warning system 300 is in an operating mode, such as an alarm mode, a recording mode, a voice recognition mode, and a voice output mode. The received audio signal can be further stored in the memory 304 or transmitted via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting the audio signal.

[0475] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0476] The sensor assembly 314 includes one or more sensors for providing various status assessments of the medium-speed coal mill fire warning system 300. For example, the sensor assembly 314 may include an acoustic sensor. Furthermore, the sensor assembly 314 may detect the on / off status of the medium-speed coal mill fire warning system 300, the relative positioning of components, such as the display and keypad of the medium-speed coal mill fire warning system 300, and the operating status of the medium-speed coal mill fire warning system 300 or a component thereof, such as the operating status, structural status, or operating status of the discharge scraper, the orientation or acceleration / deceleration of the medium-speed coal mill fire warning system 300, and temperature changes within the medium-speed coal mill fire warning system 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 314 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, a material stack thickness sensor, or a temperature sensor.

[0477] The communication component 316 is configured to enable the medium-speed coal mill fire warning system 300 to provide the ability to communicate with other devices and cloud platforms in a wired or wireless manner. The medium-speed coal mill fire warning system 300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0478] In an exemplary embodiment, the medium-speed coal mill fire warning system 300 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the medium-speed coal mill fire warning method described in any of the above embodiments.

[0479] The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by the processor corresponding to the medium-speed coal mill fire warning system, the medium-speed coal mill fire warning system can implement the medium-speed coal mill fire warning method recorded in any of the above embodiments.

[0480] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) that contain computer-usable program code.

[0481] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0482] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0483] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0484] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A medium-speed coal mill fire warning method, characterized in that: include: During the operation of the medium-speed coal mill, various preset parameters of the medium-speed coal mill are obtained; determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill; When there is a fire risk in the medium-speed coal mill, an early warning will be issued.

2. The method according to claim 1, wherein When the preset parameters include the expected value of the grinding bowl pressure difference, the method of obtaining multiple preset parameters of the medium-speed coal mill includes: Monitor the operation of the grinding system; When the grinding system is put into operation, the fire alarm function is activated; When the fire alarm function is activated, the primary air volume, pulverized coal mass flow rate, speed and separator pressure difference of the medium-speed coal mill are obtained; Determining an expected value of the grinding bowl differential pressure of the medium-speed coal mill according to the primary air volume, coal powder mass flow rate, rotation speed, and separator pressure difference; The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes: Determine the deviation between the expected value of the grinding bowl differential pressure of the medium-speed coal mill and the actual value of the grinding bowl differential pressure of the medium-speed coal mill; When the deviation is greater than a first dynamic threshold, it is determined that the medium-speed coal mill has a fire risk and an early warning message is issued, wherein the first dynamic threshold is obtained by a moving standard deviation of the deviation.

3. The method according to claim 1, wherein When the preset parameters include temperature difference and temperature rise rate, the method of obtaining multiple preset parameters of the medium-speed coal mill includes: Obtaining the hot primary air volume, hot primary air temperature, cold primary air volume, cold primary air temperature and actual outlet temperature of the medium-speed coal mill; Substituting the hot primary air volume, hot primary air temperature, cold primary air volume and cold primary air temperature of the medium-speed coal mill into an outlet temperature model to determine a theoretical outlet temperature value of the medium-speed coal mill; Calculating a temperature difference based on an actual outlet temperature value and a theoretical outlet temperature value of the medium-speed coal mill, and calculating a temperature rise rate based on the actual outlet temperature value; The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes: When the temperature difference exceeds a preset threshold or the temperature rise rate exceeds a normal temperature rise rate range, it is determined that the outlet temperature of the medium-speed coal mill has abnormally increased; When the outlet temperature of the medium-speed coal mill increases abnormally, it is determined that the medium-speed coal mill has a fire risk.

4. The method according to claim 1, wherein When the preset parameters include powder pipe blockage, the multiple preset parameters of the medium-speed coal mill are obtained, including: Obtain the total primary air pressure of the medium-speed coal mill and the primary air flow of each powder pipe; Determine the current working condition based on the moving average of the total primary air pressure; The weight coefficient of each powder hose air volume to the total air volume is calculated based on the moving average of the primary air flow of each powder hose; Determine whether the powder hose is blocked based on the current working conditions and the weight coefficient of each powder hose air volume to the total air volume; The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes: When the powder pipe is blocked, it is determined that the medium-speed coal mill has a fire risk.

5. The method according to claim 4, wherein The weight coefficient of each powder hose air volume in the total air volume is calculated based on the moving average of the primary air flow of each powder hose, including: The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula: Among them, W i,current Indicates the weight coefficient of the i-th powder hose air volume to the total air volume; F i,MA Represents the moving average of the primary air flow rate of the i-th pipeline.

6. The method according to claim 1, wherein When the preset parameters include safety information of the primary air system, the obtaining of multiple preset parameters of the medium-speed coal mill includes: Obtain primary air inlet temperature, primary air temperature rise rate, valve failure, and valve jam detection results; Determining safety information of the primary air system based on at least one of the primary air inlet temperature, the primary air temperature rise rate, valve failure, and valve jam detection results; The determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes: When at least one of the following conditions occurs, it is determined that there is a fire risk in the medium-speed coal mill: The primary air inlet temperature is greater than the primary air explosion temperature of the coal mill; The primary air temperature rise rate is greater than the maximum temperature rise rate of the primary air system; The valve failure detection result indicates that the valve has failed; The valve sticking test result indicates that the valve is stuck.

7. The method according to claim 1, wherein When the preset parameters include a medium-speed coal mill purge result, the step of determining whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill includes: Get the latest historical purge results of the medium-speed coal mill; When the historical purging results indicate that the purging of the medium-speed coal mill has failed, it is determined that the medium-speed coal mill has a fire risk.

8. A medium-speed coal mill fire warning device, characterized in that: include: An acquisition module is used to obtain various preset parameters of the medium-speed coal mill during its operation; a judgment module, configured to judge whether the medium-speed coal mill has a fire risk based on at least one preset parameter of the medium-speed coal mill; The early warning module is used to issue an early warning when there is a fire risk in the medium-speed coal mill.

9. A medium-speed coal mill fire warning system, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the medium-speed coal mill fire warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor corresponding to the medium-speed coal mill fire warning system, the medium-speed coal mill fire warning system can implement the medium-speed coal mill fire warning method according to any one of claims 1 to 7.

Images