Early warning method, device and system for powder pipe blockage and storage medium

Abstract

The invention discloses an early warning method, device and system for powder pipe blockage and a storage medium, which are used for improving the monitoring accuracy of powder pipe blockage. The method comprises the steps that parameter values of preset parameters of the medium-speed coal mill are obtained, the moving average value is solved, and the preset parameters comprise the total primary air pressure and the primary air flow of all powder pipes; the current working condition is determined according to the moving average value of the total primary air pressure; calculating the weight coefficient of the air volume of each powder pipe in the total air volume according to the moving average value of the primary air flow of each powder pipe; judging whether powder pipe blockage exists or not according to the current working condition and the weight coefficient of the air volume of each powder pipe in the total air volume; and when the powder pipe is blocked, corresponding alarm information is sent out. According to the method, the current working condition can be judged based on the total primary air pressure, and powder pipe blockage is judged in combination with the current working condition, so that the monitoring accuracy of powder pipe blockage is improved.

Description

Technical Field

[0001] The present application relates to the field of fault diagnosis technology, and in particular to a powder hose blockage early warning method, device, system and storage medium. Background Art

[0002] In coal-fired power generation systems, powder hose blockage is a common fault that affects combustion efficiency and equipment safety. Existing technologies often use powder hose flow monitoring based on a single threshold to determine whether the powder hose is blocked, ignoring the impact of operating conditions on flow distribution and resulting in a high false alarm rate. Manual inspections are prone to missed detections due to the inability to monitor in real time.

[0003] Therefore, how to provide an early warning method for powder hose blockage to improve the accuracy of powder hose blockage monitoring has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The present application provides a powder hose blockage early warning method, device, system and storage medium to improve the accuracy of powder hose blockage monitoring.

[0005] This application provides an early warning method for powder hose blockage, comprising:

[0006] Obtaining parameter values ​​of preset parameters of the medium-speed coal mill and calculating a moving average, wherein the preset parameters include a total primary air pressure and a primary air flow rate of each powder hose;

[0007] Determine the current working condition based on the moving average of the total primary air pressure;

[0008] 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;

[0009] 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;

[0010] When the powder hose is blocked, a corresponding alarm message will be issued.

[0011] The beneficial effects of the present application are: obtaining the parameter values ​​of the preset parameters of the medium-speed coal mill and calculating the moving average value, wherein the preset parameters include the total primary air pressure and the primary air flow rate of each powder hose; determining the current working condition based on the moving average value of the total primary air pressure; calculating the weight coefficient of each powder hose air volume in the total air volume based on the moving average value of the primary air flow rate of each powder hose; judging whether the powder hose is blocked based on the current working condition and the weight coefficient of each powder hose air volume in the total air volume; and issuing a corresponding alarm message when the powder hose is blocked. The present application can judge the current working condition based on the total primary air pressure, and judge the presence of powder hose blockage in combination with the current working condition, thereby improving the accuracy of monitoring powder hose blockage.

[0012] In one embodiment, determining the current operating condition based on the moving average value of the total primary air pressure includes:

[0013] The moving average value of the inlet total primary air pressure is matched with a pre-constructed total primary air pressure-operating condition correspondence table to determine the current operating condition.

[0014] In one embodiment, the construction process of the pre-constructed total primary air pressure-operating condition correspondence table is as follows:

[0015] Obtain historical data of total primary air pressure and perform moving average processing;

[0016] Perform cluster analysis on the moving average total primary air inlet pressure;

[0017] According to the clustering results, a total primary air pressure-operating condition correspondence table is constructed.

[0018] 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:

[0019] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0020]

[0021] 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.

[0022] In one embodiment, judging whether a powder hose is blocked according to the current working condition and the weight coefficient of the air volume of each powder hose in the total air volume includes:

[0023] Obtain the average and standard deviation of the historical weight coefficients of each powder hose corresponding to the current working condition;

[0024] Calculate the standardized score corresponding to each powder hose according to the weight coefficient of each powder hose air volume to the total air volume and the average value and standard deviation of the historical weight coefficients of each powder hose;

[0025] When there is a first powder hose whose standardized score is lower than a first preset value, marking the first powder hose as a potential blocked pipe, and performing compensation effect verification on the burner powder hose system of the medium-speed coal mill;

[0026] When the number of potentially blocked pipes is 1 and the compensation effect verification is passed, it is determined that the powder hose is blocked.

[0027] In one embodiment, the method further comprises:

[0028] When the number of potentially blocked pipes is 1 but the compensation effect verification fails, it is determined that the air volume sensor is abnormal and there is no powder hose blockage.

[0029] In one embodiment, the method further comprises:

[0030] When there are multiple potentially blocked pipes, it is determined that the powder hose is blocked.

[0031] The present application also provides a powder hose blockage early warning device, comprising:

[0032] a first acquisition module, configured to acquire parameter values ​​of preset parameters of the medium-speed coal mill and calculate a moving average thereof, wherein the preset parameters include a total primary air pressure and a primary air flow rate of each powder hose;

[0033] A first determining module is used to determine the current working condition according to the moving average value of the total primary air pressure;

[0034] A calculation module 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;

[0035] The judgment module 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;

[0036] The alarm module is used to issue corresponding alarm information when the powder hose is blocked.

[0037] In one embodiment, the determining module is further configured to:

[0038] The moving average value of the inlet total primary air pressure is matched with a pre-constructed total primary air pressure-operating condition correspondence table to determine the current operating condition range.

[0039] In one embodiment, the construction process of the pre-constructed total primary air pressure-operating condition correspondence table is as follows:

[0040] Obtain historical data of total primary air pressure and perform moving average processing;

[0041] Perform cluster analysis on the moving average total primary air inlet pressure;

[0042] According to the clustering results, a total primary air pressure-operating condition correspondence table is constructed.

[0043] In one embodiment, the computing module is further configured to:

[0044] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0045]

[0046] 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.

[0047] In one embodiment, the judgment module includes:

[0048] The acquisition submodule is used to obtain the average value and standard deviation of the historical weight coefficients of each powder hose corresponding to the current working condition;

[0049] A first calculation submodule is configured to calculate a standardized score corresponding to each powder hose based on a weight coefficient of the air volume of each powder hose to the total air volume and an average value and a standard deviation of the historical weight coefficients of each powder hose;

[0050] a verification submodule, configured to, when there is a first powder hose whose standardized score is lower than a first preset value, mark the first powder hose as a potential blocked pipe, and perform compensation effect verification on the burner powder hose system of the medium-speed coal mill;

[0051] The first determination submodule determines that a powder hose blockage exists when the number of potential blocked pipes is 1 and the compensation effect verification passes.

[0052] In one embodiment, the judgment module further includes:

[0053] The second determination submodule is used to determine that the air volume sensor is abnormal and there is no powder hose blockage when the number of potential blocked pipes is 1 but the compensation effect verification fails.

[0054] In one embodiment, the apparatus further comprises:

[0055] The third determining module is configured to determine that a powder hose is blocked when there are multiple potentially blocked pipes.

[0056] The present application also provides an early warning system for powder hose blockage, comprising:

[0057] at least one processor; and,

[0058] a memory communicatively connected to the at least one processor; wherein,

[0059] 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 powder hose blockage early warning method described in any one of the above embodiments.

[0060] The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor corresponding to the powder hose blockage warning system, the powder hose blockage warning system can implement the powder hose blockage warning method described in any of the above embodiments.

[0061] 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.

[0062] The technical solution of the present application is further described in detail below through the accompanying drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] 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:

[0064] Figure 1 This is a flow chart of a powder hose blockage early warning method in one embodiment of the present application;

[0065] Figure 2 This is a structural schematic diagram of a powder hose blockage early warning device in one embodiment of the present application;

[0066] Figure 3 Schematic diagram of the hardware structure of a powder hose blockage early warning system in one embodiment of the present application. DETAILED DESCRIPTION

[0067] 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.

[0068] After being ground in a medium-speed pulverizer, the pulverized coal is transported from a rotary separator to the burner's pre-burner pulverized coal pipe, where it then enters the burner. During this process, the pulverized coal must be sprayed into the furnace at an appropriate speed and direction for combustion. Long-term operation of the pre-burner pulverized coal pipe can lead to blockage due to the following main reasons: coal with high ash content, high moisture content, or strong viscosity, which easily agglomerates and causes pipe blockage; unstable pulverizer output, resulting in an increased proportion of coarse powder in certain areas, causing blockage; low primary air volume, insufficient to effectively carry the pulverized coal, leading to deposition and blockage; and long-term lack of cleaning and inspection, which can gradually develop into localized or even complete blockage.

[0069] Existing technologies have many drawbacks in detecting burner powder tube blockage in medium-speed coal mills: in terms of adaptability to multiple working conditions, a static model is used, which does not consider the impact of factors such as inlet pressure, coal type changes, and dynamic switching of working conditions on flow distribution. Fixed thresholds lead to misjudgment of high-pressure / low-pressure scenarios; the ability of multi-pipeline collaborative analysis is insufficient, and single-dimensional detection only relies on single-variable thresholds or multi-variable global deviations. It cannot effectively distinguish between local blockage of a single pipeline and collaborative anomalies of multiple pipelines, and it is difficult to capture the coordinated changes in multi-pipeline flow; the ability to locate blockages is insufficient, and the flow redistribution rules of non-blocked pipelines after blockage are ignored, which easily leads to missed detection of multi-pipeline blockages; and the data dependence is strong, and supervised learning requires a large amount of difficult-to-obtain fault data, which limits actual engineering applications. At the same time, some machine learning models have poor interpretability and are difficult to associate with physical mechanisms.

[0070] This application uses dynamic modeling and multi-dimensional statistical detection based on different working conditions, combined with real-time data and historical pattern matching, to achieve precise positioning and adaptive alarm of single / multi-pipeline blockage of the burner powder tube of a medium-speed coal mill, taking into account working condition changes, noise suppression and multi-pipeline synergy effects.

[0071] Figure 1 Flowchart of a powder hose blockage early warning method according to an embodiment of the present application. Figure 1 As shown, the method can be implemented as the following steps S101-S105:

[0072] In step S101, the parameter values ​​of the preset parameters of the medium-speed coal mill are obtained and a moving average is calculated, wherein the preset parameters include the total primary air pressure and the primary air flow rate of each powder hose;

[0073] In step S102, the current working condition is determined based on the moving average value of the total primary air pressure;

[0074] In step S103, 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;

[0075] In step S104, it is determined whether the powder hose is blocked based on the current working condition and the weight coefficient of the air volume of each powder hose to the total air volume;

[0076] In step S105, when the powder hose is blocked, a corresponding alarm message is issued.

[0077] In this application, the parameter values ​​of the preset parameters of the medium-speed coal mill are obtained and the moving average is calculated, wherein the preset parameters include the total primary air pressure and the primary air flow rate of each powder hose. After obtaining the real-time parameter values, the real-time inlet total primary air pressure and the primary air flow rate of each powder hose are preprocessed 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:

[0078]

[0079] 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.

[0080] Similarly, the moving average of the primary air flow of each powder hose is calculated using the following formula:

[0081]

[0082] 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.

[0083] 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.

[0084] The weight coefficient of each powder hose's air volume to the total air volume is calculated based on the moving average of each powder hose's primary air volume. Under certain working conditions, the distribution weight of each powder hose's primary air volume is basically fixed. Therefore, the weight coefficient of each powder hose is calculated using the following formula:

[0085]

[0086] Among them, W i，current represents the weight coefficient of the i-th powder tube; F i,MA Represents the moving average of the primary air flow rate of the i-th pipeline.

[0087] 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.

[0088] In order to accurately analyze the blockage condition of the powder hose under the current working condition, the weight coefficient of the current powder hose can be compared with the weight coefficient under the normal state of the working condition to determine whether the current weight coefficient deviates. Specifically, with the help of cluster analysis of the total primary air inlet pressure and modeling of different working conditions, the benchmark parameters (including mean and standard deviation) under different working conditions are calculated for the primary air flow and weight coefficient of each powder hose. Through this process, the current operating status of the powder hose can be accurately matched, and false alarms caused by cross-working conditions can be effectively avoided. In this application, the mean and standard deviation of the total air volume under each working condition, as well as the mean and standard deviation of the weight of each powder hose under each working condition, are obtained in advance.

[0089] (1) Mean and standard deviation of total air volume under various working conditions:

[0090] First, obtain the historical data of the primary air flow of each powder hose under each working condition, and calculate the corresponding moving average Then, the historical data of the total air volume of all powder hoses under the corresponding working conditions can be obtained.

[0091]

[0092] in, Indicates the 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.

[0093] For each working condition k, after obtaining the historical data of the total air volume of all powder hoses under each working condition, the mean and standard deviation of the historical total air volume are calculated using the following formula:

[0094]

[0095] Among them, μ k Represents the average value of the total historical air volume under working condition k; σ k represents the standard deviation of the historical total air volume 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.

[0096] (2) Mean and standard deviation of each powder hose weight under each working condition:

[0097] First, obtain the historical weight coefficient of each powder hose under each working condition:

[0098]

[0099] 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.

[0100] Then calculate the average value and standard deviation of the weight coefficient of each powder hose under each working condition:

[0101]

[0102] 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.

[0103] 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:

[0104]

[0105] 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.

[0106] 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 .

[0107] (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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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), ), indicating that the reduced air volume has not been compensated, it is determined that the air volume sensor is abnormal, triggering the sensor abnormality alarm.

[0113] (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.

[0114] 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.

[0115] 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:

[0116] 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:

[0117]

[0118] 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.

[0119] The calculation process of the historical normal compensation standard deviation is as follows:

[0120] Using historical data, first calculate the historical standard deviation of all fan tube weights and their benchmark mean:

[0121]

[0122] 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.

[0123] Then aggregate the historical deviation standard deviation to calculate the historical normal compensation standard deviation. Specifically, the σ 补偿 (tj ) to obtain the historical normal compensation standard deviation:

[0124]

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The beneficial effects of the present application are: obtaining the parameter values ​​of the preset parameters of the medium-speed coal mill and calculating the moving average value, wherein the preset parameters include the total primary air pressure and the primary air flow rate of each powder hose; determining the current working condition based on the moving average value of the total primary air pressure; calculating the weight coefficient of each powder hose air volume in the total air volume based on the moving average value of the primary air flow rate of each powder hose; judging whether the powder hose is blocked based on the current working condition and the weight coefficient of each powder hose air volume in the total air volume; and issuing a corresponding alarm message when the powder hose is blocked. The present application can judge the current working condition based on the total primary air pressure, and judge the presence of powder hose blockage in combination with the current working condition, thereby improving the accuracy of monitoring powder hose blockage.

[0132] In one embodiment, the above step S102 may be implemented as follows:

[0133] The moving average value of the inlet total primary air pressure is matched with a pre-constructed total primary air pressure-operating condition correspondence table to determine the current operating condition.

[0134] In one embodiment, the process of constructing the pre-constructed total primary air pressure-operating condition correspondence table can be implemented as follows: Steps A1-A3:

[0135] In step A1, historical data of total primary air pressure is obtained and moving average processing is performed;

[0136] In step A2, cluster analysis is performed on the moving average total primary air inlet pressure;

[0137] In step A3, a total primary air pressure-operating condition correspondence table is constructed based on the clustering results.

[0138] In one embodiment, the above step S103 may be implemented as follows:

[0139] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0140]

[0141] 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.

[0142] In one embodiment, the above step S104 may be implemented as the following steps B1-B4:

[0143] In step B1, the average value and standard deviation of the historical weight coefficients of each powder hose corresponding to the current working condition are obtained;

[0144] In step B2, a standardized score corresponding to each powder hose is calculated based on the weight coefficient of the air volume of each powder hose to the total air volume and the average value and standard deviation of the historical weight coefficients of each powder hose;

[0145] In step B3, when there is a first powder hose whose standardized score is lower than a first preset value, the first powder hose is marked as a potential blocked pipe, and a compensation effect verification is performed on the burner powder hose system of the medium-speed coal mill;

[0146] In step B4, when the number of potentially blocked pipes is 1 and the compensation effect verification is passed, it is determined that the powder hose is blocked.

[0147] In one embodiment, the method may also be implemented as follows:

[0148] When the number of potentially blocked pipes is 1 but the compensation effect verification fails, it is determined that the air volume sensor is abnormal and there is no powder hose blockage.

[0149] In one embodiment, the method may be further implemented as follows:

[0150] When there are multiple potentially blocked pipes, it is determined that the powder hose is blocked.

[0151] Figure 2 FIG. 1 is a structural diagram of a powder pipe blockage warning device according to an embodiment of the present application. Figure 2 As shown, the device includes:

[0152] A first acquisition module 201 is configured to acquire parameter values ​​of preset parameters of a medium-speed coal mill and calculate a moving average thereof, wherein the preset parameters include a total primary air pressure and a primary air flow rate of each powder hose;

[0153] A first determining module 202 is configured to determine a current operating condition based on a moving average of the total primary air pressure;

[0154] A calculation module 203 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;

[0155] The judgment module 204 is used to judge whether there is a powder hose blockage based on the current working condition and the weight coefficient of the air volume of each powder hose to the total air volume;

[0156] The alarm module 205 is used to issue a corresponding alarm message when the powder hose is blocked.

[0157] In one embodiment, the determining module is further configured to:

[0158] The moving average value of the inlet total primary air pressure is matched with a pre-constructed total primary air pressure-operating condition correspondence table to determine the current operating condition.

[0159] In one embodiment, the construction process of the pre-constructed total primary air pressure-operating condition correspondence table is as follows:

[0160] Obtain historical data of total primary air pressure and perform moving average processing;

[0161] Perform cluster analysis on the moving average total primary air inlet pressure;

[0162] According to the clustering results, a total primary air pressure-operating condition correspondence table is constructed.

[0163] In one embodiment, the computing module is further configured to:

[0164] The weight coefficient of each powder hose air volume to the total air volume is calculated according to the following formula:

[0165]

[0166] 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.

[0167] In one embodiment, the judgment module includes:

[0168] The acquisition submodule is used to obtain the average value and standard deviation of the historical weight coefficients of each powder hose corresponding to the current working condition;

[0169] A first calculation submodule is configured to calculate a standardized score corresponding to each powder hose based on a weight coefficient of the air volume of each powder hose to the total air volume and an average value and a standard deviation of the historical weight coefficients of each powder hose;

[0170] a first marking submodule, configured to mark a first powder hose as a potential blocked pipe when there is a first powder hose whose standardized score is lower than a first preset value;

[0171] The first determination submodule is configured to determine that the potentially blocked pipe is a target powder hose when there is a second powder hose whose standardized score is greater than a second preset value and a deviation between the total air volume of all powder hoses and an average value of the historical total air volume is within a preset range.

[0172] In one embodiment, the judgment module includes:

[0173] The acquisition submodule is used to obtain the average value and standard deviation of the historical weight coefficients of each powder hose corresponding to the current working condition;

[0174] A first calculation submodule is configured to calculate a standardized score corresponding to each powder hose based on a weight coefficient of the air volume of each powder hose to the total air volume and an average value and a standard deviation of the historical weight coefficients of each powder hose;

[0175] a verification submodule, configured to, when there is a first powder hose whose standardized score is lower than a first preset value, mark the first powder hose as a potential blocked pipe, and perform compensation effect verification on the burner powder hose system of the medium-speed coal mill;

[0176] The first determination submodule determines that a powder hose blockage exists when the number of potential blocked pipes is 1 and the compensation effect verification passes.

[0177] In one embodiment, the judgment module further includes:

[0178] The second determination submodule is used to determine that the air volume sensor is abnormal and there is no powder hose blockage when the number of potential blocked pipes is 1 but the compensation effect verification fails.

[0179] In one embodiment, the apparatus further comprises:

[0180] The third determining module is configured to determine that a powder hose is blocked when there are multiple potentially blocked pipes.

[0181] Figure 3 FIG. 1 is a schematic diagram of the hardware structure of a powder hose blockage early warning system according to an embodiment of the present application. Figure 3 As shown in FIG, the powder hose blockage early warning system includes:

[0182] at least one processor 320; and,

[0183] A memory 304 in communication with the at least one processor 320; wherein,

[0184] The memory 304 stores instructions that can be executed by the at least one processor 320 . The instructions are executed by the at least one processor 320 to implement the powder hose blockage early warning method described in any of the above embodiments.

[0185] Reference Figure 3 The powder hose blockage 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 .

[0186] The processing component 302 generally controls the overall operation of the powder hose blockage warning system 300. The 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, the processing component 302 may include one or more modules to facilitate interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate interaction between the multimedia component 308 and the processing component 302.

[0187] The memory 304 is configured to store various types of data to support the operation of the powder hose blockage warning system 300. Examples of such data include instructions for any application or method operating on the powder hose blockage 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.

[0188] The power supply assembly 306 provides power to the various components of the powder hose blocked 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 powder hose blocked warning system 300.

[0189] The multimedia component 308 includes a screen that provides an output interface between the powder hose clogged 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 a 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 powder hose clogged 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 a focal length and optical zoom capability.

[0190] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC) configured to receive external audio signals when the powder hose blockage warning system 300 is in an operating mode, such as an alarm mode, a recording mode, a voice recognition mode, or a voice output mode. The received audio signals may 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 signals.

[0191] 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.

[0192] The sensor assembly 314 includes one or more sensors for providing various status assessments for the powder hose blockage warning system 300. For example, the sensor assembly 314 may include an acoustic sensor. Furthermore, the sensor assembly 314 may detect the open / closed state of the powder hose blockage warning system 300, the relative positioning of components, such as the display and keypad of the powder hose blockage warning system 300, and the operating status of the powder hose blockage warning system 300 or a component thereof. 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 a magnetic sensor, a pressure sensor, a material accumulation thickness sensor, or a temperature sensor.

[0193] The communication component 316 is configured to enable the powder hose blockage warning system 300 to communicate with other devices and the cloud platform via wired or wireless communication. The powder hose blockage warning system 300 can access a wireless network based on communication standards, such as WiFi, 2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one 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.

[0194] In an exemplary embodiment, the powder hose blockage warning system 300 may 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 powder hose blockage warning method described in any of the above embodiments.

[0195] The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor corresponding to the powder hose blockage warning system, the powder hose blockage warning system can implement the powder hose blockage warning method described in any of the above embodiments.

[0196] 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.

[0197] 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 processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0198] 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.

[0199] 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.

[0200] 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 powder hose blockage early warning method, characterized in that: include: Obtaining parameter values ​​of preset parameters of the medium-speed coal mill and calculating a moving average, wherein the preset parameters include a total primary air pressure and a primary air flow rate of each powder hose; 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; When the powder hose is blocked, a corresponding alarm message will be issued.

2. The method according to claim 1, wherein Determining the current working condition based on the moving average value of the total primary air pressure includes: The moving average value of the inlet total primary air pressure is matched with a pre-constructed total primary air pressure-operating condition correspondence table to determine the current operating condition.

3. The method according to claim 2, wherein The construction process of the pre-constructed total primary air pressure-operating condition correspondence table is as follows: Obtain historical data of total primary air pressure and perform moving average processing; Perform cluster analysis on the moving average total primary air inlet pressure; According to the clustering results, a total primary air pressure-operating condition correspondence table is constructed.

4. The method according to claim 1, 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.

5. The method according to claim 1, wherein The determination of whether the powder hose is blocked based on the current working condition and the weight coefficient of each powder hose air volume to the total air volume includes: Obtain the average and standard deviation of the historical weight coefficients of each powder hose corresponding to the current working condition; Calculate the standardized score corresponding to each powder hose according to the weight coefficient of each powder hose air volume to the total air volume and the average value and standard deviation of the historical weight coefficients of each powder hose; When there is a first powder hose whose standardized score is lower than a first preset value, marking the first powder hose as a potential blocked pipe, and performing compensation effect verification on the burner powder hose system of the medium-speed coal mill; When the number of potentially blocked pipes is 1 and the compensation effect verification is passed, it is determined that the powder hose is blocked.

6. The method according to claim 5, wherein The method further comprises: When the number of potentially blocked pipes is 1 but the compensation effect verification fails, it is determined that the air volume sensor is abnormal and there is no powder hose blockage.

7. The method according to claim 5, wherein The method further comprises: When there are multiple potentially blocked pipes, it is determined that the powder hose is blocked.

8. A powder hose blockage warning device, characterized in that: include: a first acquisition module, configured to acquire parameter values ​​of preset parameters of the medium-speed coal mill and calculate a moving average thereof, wherein the preset parameters include a total primary air pressure and a primary air flow rate of each powder hose; A first determining module is used to determine the current working condition according to the moving average value of the total primary air pressure; A calculation module 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; The judgment module 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; The alarm module is used to issue corresponding alarm information when the powder hose is blocked.

9. A powder hose blockage early 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 powder hose blockage early 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 powder hose blockage early warning system, the powder hose blockage early warning system can implement the powder hose blockage early warning method according to any one of claims 1 to 7.

Images