Boiler fault detection method, device and equipment, storage medium and computer program product

Abstract

The invention relates to the technical field of boilers, and discloses a boiler fault detection method, device and equipment, a storage medium and a computer program product.The boiler fault detection method comprises the steps that in the boiler starting process, the main steam pressure and tube bundle heating time of a boiler are monitored in real time; when the main steam pressure is lower than the minimum pressure threshold value and the tube bundle heating time exceeds a first preset threshold value, a bypass valve opening value and a through-flow valve position set value of the boiler are obtained; and determining a fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the through-flow valve position set value. According to the method, the main steam pressure and the tube bundle heating time of the boiler in the starting process are synchronously monitored in real time, and the monitoring result is associated with the deviation between the opening degree of the bypass valve and the set value of the through-flow valve, so that accurate judgment of low-pressure and overtime heating load faults in the starting stage of the boiler is realized; and the false detection problem caused by parameter isolated analysis is avoided.

Description

Technical Field

[0001] This application relates to the technical field of boilers, and in particular, to a boiler fault detection method, device, equipment, storage medium, and computer program product. Background Art

[0002] As a key device for energy conversion and industrial production, boilers are in a complex working condition of high temperature, high pressure, and multi-variable coupling for a long time. Their failures may lead to safety accidents, shutdown losses, and increased economic costs. Existing boiler systems have strong coupling and non-linear characteristics. Traditional detection methods often result in untimely fault identification due to isolated parameter analysis or lag in dynamic response, and it is difficult to meet the requirements of high precision, real-time performance, and comprehensiveness. Summary of the Invention

[0003] The main purpose of this application is to provide a boiler fault detection method, device, equipment, storage medium, and computer program product, aiming to solve the technical problem that traditional boiler detection methods often result in untimely fault identification due to isolated parameter analysis or lag in dynamic response.

[0004] To achieve the above object, this application proposes a boiler fault detection method, which includes:

[0005] During the boiler startup process, the main steam pressure and the tube bundle heating time of the boiler are monitored in real time;

[0006] When the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold, obtain the bypass valve opening value and the flow valve position set value of the boiler;

[0007] Determine the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value, and the flow valve position set value.

[0008] Optionally, the step of determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value, and the flow valve position set value includes:

[0009] Calculate the basic deviation degree based on the real-time difference between the bypass valve opening value and the flow valve position set value;

[0010] Determine the fluctuation data of the main steam flow of the boiler within a specified time window according to the main steam pressure, and calculate the load change rate based on the fluctuation data;

[0011] Normalize the basic deviation degree, the main steam pressure, and the load change rate, and map the processing results to a three-dimensional space coordinate system to generate a dynamic feature vector;

[0012] Determine the fault detection result of the boiler according to the dynamic feature vector.

[0013] Optionally, the step of determining the fault detection result of the boiler according to the dynamic feature vector includes:

[0014] Perform clustering analysis on the historical fault data of the boiler to obtain fault mode clusters, where each cluster in the fault mode clusters represents a fault mode;

[0015] Calculate the Euclidean distance between the dynamic feature vector and each fault mode cluster to obtain a distance detection result;

[0016] Determine the fault type of the boiler according to the distance detection result and generate a boiler emergency pressure relief instruction.

[0017] Optionally, after the step of determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value, and the flow valve position set value, the following steps are further included:

[0018] When the boiler enters the pressure increase mode, collect the actual main steam pressure change rate during the pressure increase process of the boiler;

[0019] Calculate the dynamic deviation coefficient between the actual main steam pressure change rate and the preset pressure increase rate curve;

[0020] When the dynamic deviation coefficient exceeds the tolerance threshold and the bypass valve opening value reaches the tolerance range of the flow valve position set value, determine that the boiler has a pressure combustion mismatch fault, set a fault flag bit, and generate a fuel supply amount correction instruction.

[0021] Optionally, after the step of determining that the boiler has a pressure combustion mismatch fault, setting a fault flag bit, and generating a fuel supply amount correction instruction when the dynamic deviation coefficient exceeds the tolerance threshold and the bypass valve opening value reaches the tolerance range of the flow valve position set value, the following steps are further included:

[0022] Send the fuel supply amount correction instruction to the target terminal;

[0023] After receiving the correction signal returned by the target terminal, collect multiple pressure recovery values within a preset adjustment period;

[0024] When each of the pressure recovery values meets the preset recovery condition, reset the fault flag bit and generate a pressure increase process recovery confirmation signal.

[0025] Optionally, after the step of determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value, and the flow valve position set value, the following steps are further included:

[0026] When the boiler enters the constant pressure operation stage, collect the fluctuation amplitude of the main steam pressure and the rising gradient of the steam turbine speed;

[0027] When the fluctuation amplitude is higher than the preset fluctuation range and the rising gradient of the steam turbine speed is lower than the preset gradient setting value, determine that the boiler has a pressure-speed imbalance fault and generate a speed adjustment instruction.

[0028] In addition, to achieve the above object, the present application also proposes a boiler fault detection device, which includes:

[0029] A data monitoring module for real-time monitoring of the main steam pressure and the tube bundle heating time of the boiler during the boiler startup process;

[0030] A data acquisition module for obtaining the opening value of the bypass valve and the set value of the flow valve position of the boiler when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold;

[0031] A fault judgment module for determining the fault detection result of the boiler according to the main steam pressure, the opening value of the bypass valve and the set value of the flow valve position.

[0032] In addition, to achieve the above object, the present application also proposes a boiler fault detection device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the boiler fault detection method as described above.

[0033] In addition, to achieve the above object, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the boiler fault detection method as described above.

[0034] In addition, to achieve the above object, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the boiler fault detection method as described above.

[0035] In this application, during the boiler startup process, the main steam pressure and the tube bundle heating time of the boiler are monitored in real time; when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold, the opening value of the bypass valve and the set value of the flow valve position of the boiler are obtained; the fault detection result of the boiler is determined according to the main steam pressure, the opening value of the bypass valve and the set value of the flow valve position. By synchronously monitoring the main steam pressure and the tube bundle heating time of the boiler during the startup process in real time and correlating the monitoring results with the deviation of the bypass valve opening and the flow valve setting value, this application realizes the accurate determination of low-pressure and overtime heating load faults during the boiler startup stage, and avoids the problem of false detection caused by isolated parameter analysis. Description of the Drawings

[0036] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0037] In order to more clearly illustrate the technical solutions in the embodiments of this application or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a schematic flowchart of the first embodiment of the boiler fault detection method of this application;

[0039] Figure 2 It is a schematic flowchart of the second embodiment of the boiler fault detection method of this application;

[0040] Figure 3 It is a schematic flowchart of the third embodiment of the boiler fault detection method of this application;

[0041] Figure 4 It is a schematic diagram of the module structure of the boiler fault detection device in the embodiments of this application;

[0042] Figure 5 It is a schematic diagram of the device structure of the hardware operating environment involved in the boiler fault detection method in the embodiments of this application.

[0043] The realization of the purpose, the functional features and the advantages of this application will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0044] It should be understood that the specific embodiments described here are only used to explain the technical solutions of this application and are not used to limit this application.

[0045] To better understand the technical solution of this application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0046] The main solution of the embodiment of this application is: during the boiler startup process, the main steam pressure and the tube bundle heating time of the boiler are monitored in real time; when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold, the opening value of the bypass valve and the set value of the flow valve position of the boiler are obtained; the fault detection result of the boiler is determined according to the main steam pressure, the opening value of the bypass valve and the set value of the flow valve position.

[0047] As a key device for energy conversion and industrial production, the boiler is in a complex working condition of high temperature, high pressure and multi-variable coupling for a long time. Its faults may lead to safety accidents, downtime losses and increased economic costs. With the growth of power demand and the improvement of environmental protection requirements, the complexity of the boiler system has further increased, and traditional detection methods have been difficult to meet the requirements of high precision, real-time and comprehensiveness. For example, faults such as leakage of boiler heating surface tubes, unstable combustion, and pressure combustion mismatch occur frequently, and more intelligent detection technologies are urgently needed to ensure safe operation. Existing detection methods relying on physical models or manual experience judge faults by threshold comparison and cannot handle multi-variable coupling problems.

[0048] Therefore, this application provides a new boiler fault detection method. By monitoring the main steam pressure and the tube bundle heating time in real time and obtaining the relevant parameters of the bypass valve and the flow valve in time when abnormalities occur, potential fault hazards can be detected as early as possible during the boiler startup stage. Detect and give early warnings when the fault just appears or has not fully developed, so as to buy more time for the operator to take measures, avoid the further deterioration of the fault, and reduce the downtime and maintenance costs.

[0049] It should be noted that the execution subject of this embodiment can be a computing service device with data processing and program running functions, such as a monitoring computer, or an electronic device capable of realizing the above functions. The following takes the boiler status online detection system as an example to illustrate this embodiment and the following embodiments.

[0050] Based on this, the embodiment of this application provides a boiler fault detection method, referring to Figure 1 , Figure 1 is a schematic flowchart of the first embodiment of the boiler fault detection method of this application.

[0051] In this embodiment, the boiler fault detection method includes:

[0052] Step S10, during the boiler startup process, the main steam pressure and the tube bundle heating time of the boiler are monitored in real time.

[0053] It should be understood that the main steam pressure is the pressure value of the steam in the main steam pipeline during the operation of the boiler, measured in megapascals (MPa). The tube bundle heating time is the time required for the tube bundle (such as superheater, reheater, etc.) to reach a predetermined temperature from ignition during the boiler startup process, which can measure the heat transfer efficiency during the boiler startup process. An overly long heating time may lead to energy waste or the risk of equipment overheating.

[0054] It can be understood that the acquisition of boiler data such as the main steam pressure and the tube bundle heating time can be carried out through various sensors configured in the boiler.

[0055] In one example, the main steam pressure can use a high-precision pressure transmitter (such as a capacitive pressure sensor) to collect the pressure signal in the main steam pipeline in real time. The installation location is on the straight section of the main steam pipeline at the boiler outlet, avoiding areas prone to pressure fluctuations such as elbows or valves. The tube bundle heating time can arrange temperature measuring devices such as thermocouples or thermal resistors at key positions of the tube bundle (such as the outlet of the superheater and the inlet of the reheater). This embodiment is not limited thereto.

[0056] Step S20, when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold, obtain the opening value of the bypass valve and the set value of the flow valve position of the boiler.

[0057] It should be noted that the minimum pressure threshold is the lowest safety value that the main steam pressure should reach during the boiler startup process, such as 70% - 80% of the rated pressure. The first preset threshold is usually the upper limit of the preset tube bundle heating time, such as 110% - 120% of the designed heating time. The opening value of the bypass valve is the actual opening percentage of the bypass valve. The set value of the flow valve position is the target opening set value of the bypass valve calculated by the control system according to the current load demand.

[0058] It can be understood that during the actual boiler startup process, the main steam pressure and the tube bundle heating time may deviate from the preset pressure value and heating time due to different faults. There are various situations for the deviation value, such as the main steam pressure being lower than the minimum pressure threshold, the tube bundle heating time exceeding the first preset threshold, or both occurring simultaneously.

[0059] It should be understood that when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold, the boiler can be in different fault scenarios. For example, after the boiler is ignited, the main steam pressure rises slowly but always remains lower than the minimum pressure threshold. The reasons can include: insufficient fuel supply, reduced heat transfer efficiency due to tube bundle ash accumulation, incorrect opening of the bypass valve, diversion of the main steam flow, etc.

[0060] It should be understood that when the main steam pressure is lower than the minimum pressure threshold and the heating time of the tube bundle exceeds the first preset threshold, the cause of the boiler failure can also be the leakage of the main steam pipeline or the too high set value of the flow-through valve, resulting in insufficient actual opening, etc.

[0061] Specifically, after detecting that the main steam pressure is lower than the minimum pressure threshold and the heating time of the tube bundle exceeds the first preset threshold, the valve opening can be read in real time through a position sensor (such as a linear potentiometer or an encoder) deployed in the boiler, and the set value of the flow-through valve position can be directly retrieved from the database.

[0062] Step S30, determine the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the set value of the flow-through valve position.

[0063] It can be understood that the fault detection result includes the judgment conclusion on whether there is a fault in the boiler, the type and severity of the fault, which can provide a basis for subsequent maintenance and adjustment.

[0064] It should be understood that the fault detection result is based on the comprehensive analysis of the main steam pressure, the actual opening of the bypass valve and the target set value. If the deviation between the actual opening of the bypass valve and the set value exceeds the preset value, the fault detection result may be that the shunt regulation fails due to valve jamming, actuator failure or signal transmission lag. If the set value of the flow-through valve position does not match the actual load demand, such as the load decreases but the set value is not adjusted synchronously, it may cause the lag or overshoot of the main steam pressure regulation.

[0065] It can be understood that determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the set value of the flow-through valve position can be achieved by analyzing historical data, establishing a mathematical relationship model between the main steam pressure, the bypass valve opening value and the set value of the flow-through valve position, and setting thresholds corresponding to different fault types according to the mathematical model and actual operation experience. When the combination of the three parameters exceeds the corresponding threshold range, it is determined that there is a fault.

[0066] It can be understood that determining the fault detection result of the boiler can also be based on the established fault rule base, associating different parameter combinations with corresponding fault types. For example, when the main steam pressure is too low and the bypass valve opening is abnormally large, it is determined as a bypass valve leakage fault. Of course, classification algorithms can also be used to classify faults, and through learning a large amount of historical fault data, different fault modes can be automatically identified.

[0067] In one example, after obtaining the bypass valve opening value and the flow valve position set value, data such as the main steam pressure, bypass valve opening, combustion parameters (coal quantity, air volume), and tube bundle wall temperature need to be input into the real-time database, and feature extraction is performed through the edge computing node. Then, by comparing the pressure fluctuation amplitude, heating time with the historical operation curve, sensor false alarm interference is excluded, and a fault code (such as F001 for bypass valve fault, F002 for abnormal combustion) and maintenance suggestions (such as "check the coal feeder frequency converter" "clean the 3rd - 5th screens of the superheater") are generated.

[0068] Furthermore, in order to synchronously monitor the main steam pressure fluctuation and the steam turbine speed gradient during the constant pressure operation stage, identify the latent fault of pressure - speed imbalance, generate a dynamic speed regulation command to restore system balance, and avoid control lag caused by phased detection. After the step S30, the following steps are further included:

[0069] When the boiler enters the constant pressure operation stage, collect the fluctuation amplitude of the main steam pressure and the rising gradient of the steam turbine speed; when the fluctuation amplitude is higher than the preset fluctuation range and the rising gradient of the steam turbine speed is lower than the preset gradient set value, determine that the boiler has a pressure - speed imbalance fault, and generate a speed adjustment command.

[0070] It should be noted that the constant pressure operation stage is the operation state in which the boiler, after reaching the rated pressure, maintains the main steam pressure stable by adjusting the fuel quantity and steam flow, such as the stable load operation of a power station boiler after grid connection. The main steam pressure fluctuation amplitude is the maximum change difference of the main steam pressure per unit time, and this maximum change difference can be adjusted according to the boiler capacity and design parameters. The steam turbine speed rising gradient is the change rate of the steam turbine speed over time. When the boiler load increases, the speed gradient should match the steam flow increase rate. The pressure - speed imbalance fault is a fault that occurs simultaneously with abnormal fluctuation of the main steam pressure and insufficient response of the steam turbine speed, usually caused by fuel regulation lag or steam turbine regulation system jamming.

[0071] It can be understood that when the boiler enters the constant pressure operation stage, the pressure change rate is recorded by a dynamic pressure sensor. If it exceeds a fixed proportion of the rated pressure within a continuous time period, it is determined that the pressure is unstable. At the same time, the steam turbine speed rising gradient needs to match the load command. If the gradient is lower than the preset value, it indicates that the steam work efficiency has decreased, and the fault reason can be main steam valve throttling or blade fouling.

[0072] It should be understood that after determining that the boiler has a pressure - speed imbalance fault, a fuzzy PID controller can be used to adjust the steam turbine throttle valve opening in real - time according to the pressure - speed deviation, and synchronously optimize the boiler combustion (such as increasing the secondary air volume) to restore the energy balance.

[0073] In one example, when the power station boiler enters the constant pressure operation stage and the grid load suddenly increases, the piezoelectric dynamic pressure sensor detects that the main steam pressure rapidly drops from 16.5 MPa (rated pressure) to 16.2 MPa, and then fluctuates between 16.1 - 16.4 MPa, with a fluctuation amplitude of 0.3 MPa, exceeding the preset range of ±0.1 MPa. At the same time, the magnetic-electric speed probe at the turbine shaft end is used to monitor the speed rising gradient. If the turbine speed rises from 3000 r / min to 3015 r / min in 10 seconds, the speed rising gradient is 1.5 r / min², which is lower than the preset 30 r / min². The system immediately determines that it is a pressure-speed imbalance fault, and speculates that the reason is that the fuel control valve is stuck, resulting in insufficient steam supply, and at the same time, the turbine governor responds laggingly. Then, the DCS system is used to generate a speed adjustment instruction: the opening of the turbine inlet valve is reduced by 5% through a fuzzy PID controller to suppress the speed rise, and the secondary air volume of the boiler burner is adjusted in linkage, and at the same time, a variable frequency acceleration signal of the fuel pump is triggered.

[0074] In this embodiment, during the boiler startup process, the main steam pressure and the tube bundle heating time of the boiler are monitored in real time; when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold, the opening value of the bypass valve and the set value of the flow valve position of the boiler are obtained; the fault detection result of the boiler is determined according to the main steam pressure, the opening value of the bypass valve and the set value of the flow valve position. By synchronously monitoring the main steam pressure and the tube bundle heating time of the boiler during the startup process in real time, and correlating the monitoring results with the deviation of the bypass valve opening and the flow valve setting value, accurate determination of low pressure and overtime heating load faults during the boiler startup stage is achieved, avoiding misdetection problems caused by isolated parameter analysis.

[0075] Refer to Figure 2 , Figure 2 FIG. is a schematic flowchart of the second embodiment of the boiler fault detection method of the present application. Based on the above first embodiment, the second embodiment of the boiler fault detection method of the present application is proposed.

[0076] In the second embodiment, step S30 includes:

[0077] Step S301, calculating a basic deviation degree based on the real-time difference between the opening value of the bypass valve and the set value of the flow valve position.

[0078] It should be noted that the basic deviation degree can quantify the severity of the bypass valve execution deviation and is used to determine whether there are valve jams, actuator failures or abnormal control signals.

[0079] It should be understood that when collecting the opening value of the bypass valve, mechanical vibration interference can be eliminated by moving average filtering.

[0080] It can be understood that the basic deviation degree can be determined by the ratio of the difference between the bypass valve opening value and the flow valve position set value to the flow valve position set value. Among them, the bypass valve opening value can be obtained in real time through a position sensor, and the flow valve position set value can be read from a database through a DCS system or controller memory, etc. In the actual calculation process, if the flow valve position set value is 0, it is necessary to determine whether the bypass valve is misopened according to historical data and the current mode of the boiler.

[0081] Step S302: Determine the fluctuation data of the main steam flow of the boiler within a specified time window according to the main steam pressure, and calculate the load change rate based on the fluctuation data.

[0082] It should be noted that the main steam flow can be calculated through a pressure-flow correlation model or determined based on historical data through the main steam pressure. The specified time window needs to cover the boiler load adjustment cycle. For some boilers that need to quickly respond to load changes, a shorter time window can be selected, and for boilers with relatively stable operation, a longer time window can be selected.

[0083] It can be understood that the fluctuation data can reflect the change of the main steam flow relative to its average value within a specified time window, and is represented as a set of various data, such as the maximum value, minimum value, difference, etc. of the main steam flow.

[0084] In an example, the main steam flow Q of the boiler is calculated through a pressure-flow correlation model, and the formula is:

[0085]

[0086] Among them, P is the main steam pressure (MPa), T is the steam temperature (K), ρ is the steam density (kg / m 3 ), and K is the flow coefficient, which is calibrated by the pipeline characteristics.

[0087] For the fluctuation data of the specified time window, the quantization method can evaluate the flow stability by calculating the standard deviation (σ) of the flow data within the window and the peak difference (Q max -Q min ) of the main steam flow.

[0088] The specific load change rate is expressed as the percentage of the load change per unit time, and the formula is:

[0089]

[0090] Among them, Q rated is the rated flow, and Δt is the sampling interval. Q t and Q t-ΔtThey are the calculated values of the main steam flow rate per unit time respectively. A higher load change rate indicates that the boiler is undergoing a large-scale load adjustment. At this time, it is necessary to closely monitor the operating status of the boiler to ensure that all parameters are within the safe range.

[0091] Step S303: Normalize the basic deviation degree, the main steam pressure, and the load change rate, and map the processing results to a three-dimensional space coordinate system to generate a dynamic feature vector.

[0092] It should be understood that normalization can eliminate the dimensional differences of different parameters, making them on the same scale, which is convenient for multi-dimensional feature fusion and pattern recognition. The three-dimensional vector composed of the normalized parameters, such as V=(x, y, z), can represent the instantaneous characteristics of the boiler operating status.

[0093] It can be understood that in the three-dimensional space coordinate system, different coordinate axes can correspond to different processing results. For example, the x-axis is defined as the normalized basic deviation degree, the y-axis is defined as the normalized main steam pressure, and the z-axis is defined as the normalized load change rate. According to the results obtained from the normalization process, the corresponding coordinate points can be determined in the three-dimensional space coordinate system, and a dynamic feature vector can be constructed based on these coordinate points. This vector changes dynamically with the change of the boiler operating status and can reflect the operating characteristics of the boiler in real time.

[0094] Step S304: Determine the fault detection result of the boiler according to the dynamic feature vector.

[0095] It can be understood that for the three-dimensional space coordinate system where the dynamic feature vector is located, regional clustering can be performed through historical data to divide the fault mode regions and determine several most typical faults. Of course, in order to judge the severity of the fault, a convolutional neural network can also be used to analyze the image of the change of the dynamic feature vector to identify complex fault combinations. At the same time, the theoretical feature vector can be calculated reversely through the boiler heat balance equation and compared with the actual value to verify the authenticity of the fault.

[0096] Furthermore, in order to shorten the diagnostic delay and generate an emergency pressure relief instruction to block the spread of the fault.

[0097] The step S304 may include:

[0098] Perform cluster analysis on the historical fault data of the boiler to obtain fault mode clusters, where each cluster in the fault mode clusters represents a fault mode; calculate the Euclidean distance between the dynamic feature vector and each fault mode cluster to obtain a distance detection result; determine the fault type of the boiler according to the distance detection result and generate an emergency pressure relief instruction for the boiler.

[0099] It should be noted that the historical fault data of the boiler includes pressure, temperature, valve opening, load change rate and corresponding fault type label, etc. The command parameters in the boiler emergency pressure relief command include the target opening of the pressure relief valve and the pressure relief time.

[0100] In one example, the K-means algorithm is used to cluster historical fault data (including dynamic feature vectors, pressure relief operation records, etc.), and each cluster represents a typical fault mode (such as "bypass valve stuck", "main steam leakage", "combustion oscillation", etc.).

[0101] Each cluster is described by its centroid Ci = (xi, yi, zi) and radius Ri, for example:

[0102] Cluster 1 (bypass valve stuck): C1 = (0.38, 0.92, 0.55), R1 = 0.12;

[0103] Cluster 2 (main steam leakage): C2 = (0.05, 0.65, 0.82), R2 = 0.08.

[0104] The radius Ri represents the maximum Euclidean distance within the cluster. The calculation formula for the distance di between the real-time dynamic feature vector V = (x, y, z) and the centroid of each cluster is:

[0105]

[0106] If <Ri,则判定当前状态属于第i类故障模式;若同时满足多簇条件,则取最小距离的簇为优先诊断结果。

[0107] Among them, in this mode, the pressure relief triggering conditions are: 1. The fault mode is "main steam overpressure" (cluster 3) and d3<0.5R3; 2. The dynamic characteristic vector is located in the "burst risk area" (cluster 4) for 10 seconds.

[0108] The target opening of the pressure relief valve can be determined based on the fault mode, and the pressure relief duration needs to be dynamically adjusted according to the pressure drop rate. During the pressure relief period, the vector trajectory needs to be monitored in real time. If it does not leave the fault cluster, the boost stage release is triggered. If the pressure relief valve fails to execute, it will automatically switch to the backup pressure relief channel.

[0109] It can be understood that based on the Euclidean distance calculation between the real-time dynamic feature vector and the historical fault cluster, fast matching of fault modes can be achieved, which can shorten the diagnosis delay compared with the offline clustering method, and generate emergency pressure relief instructions to block the spread of faults.

[0110] In this embodiment, a basic deviation degree is calculated based on the real-time difference between the bypass valve opening value and the flow valve position set value; the fluctuation data of the main steam flow rate of the boiler within a specified time window is determined according to the main steam pressure, and a load change rate is calculated based on the fluctuation data; the basic deviation degree, the main steam pressure, and the load change rate are normalized, and the processing results are mapped into a three-dimensional space coordinate system to generate a dynamic feature vector; a fault detection result of the boiler is determined according to the dynamic feature vector. By introducing a three-dimensional dynamic feature vector, multi-dimensional parameters are normalized and mapped into a unified space, overcoming the limitations of single-parameter analysis and improving the sensitivity and comprehensiveness of fault detection.

[0111] Referring to Figure 3 , Figure 3 FIG. is a schematic flow chart of the third embodiment of the boiler fault detection method of the present application. Based on the above second embodiment, the third embodiment of the boiler fault detection method of the present application is proposed.

[0112] In the third embodiment, after step S30, the following is further included:

[0113] Step S401, when the boiler enters the pressure increase mode, collect the actual main steam pressure change rate during the pressure increase process of the boiler.

[0114] It can be understood that in the pressure increase mode, the main steam pressure of the boiler will continuously increase per unit time. In the initial stage, the boiler is allowed to increase the pressure rapidly to shorten the start-up time; in the middle stage, the growth rate needs to be reduced to avoid exceeding the thermal stress limit of the tube bundle; in the final stage, the main steam pressure needs to be finely controlled to ensure that the pressure is smoothly close to the target value.

[0115] It should be understood that the pressure increase rate needs to be coordinated with the wall temperature rise rate to prevent excessive temperature difference from causing fatigue cracks.

[0116] In one example, in the pressure increase mode, the increase value of the main steam pressure per unit time, with the unit of MPa / min. The calculation formula is:

[0117]

[0118] where Pt is the main steam pressure at the current moment, and Pt+Δt is the main steam pressure after Δt time.

[0119] Step S402, calculate the dynamic deviation coefficient between the actual main steam pressure change rate and the preset pressure increase rate curve.

[0120] It should be noted that the dynamic deviation coefficient is an index that reflects the deviation degree between the actual main steam pressure change rate and the preset pressure increase curve in real time, and can be calculated by weighted sliding root mean square error. The preset pressure increase rate curve is the pressure increase rate curve determined by the system through historical data.

[0121] In one example, when quantifying the real-time deviation degree between the actual main steam pressure change rate (dP / dt real ) and the preset curve (dP / dt set ), the weighted sliding root mean square error (RMSE) is mainly used to calculate the dynamic deviation coefficient Kd, and the formula is as follows:

[0122]

[0123] where T is the time window, representing the time range of the deviation coefficient; τ is the integration variable, representing the time point traced back from the current moment t to t - T. and are the real-time pressure increase rate and the preset pressure increase rate at the time point τ, respectively.

[0124] w(τ) is the weight function, usually the exponential decay function w(τ) = e -0.5(t-τ) , which can assign higher weights to recent deviations.

[0125] Step S403: When the dynamic deviation coefficient exceeds the tolerance threshold and the bypass valve opening value reaches the tolerance range of the flow valve position setting value, it is determined that the boiler has a pressure combustion mismatch fault, a fault flag bit is set, and a fuel supply amount correction instruction is generated.

[0126] It should be noted that the tolerance threshold is the pre-set allowable range of the deviation coefficient, usually obtained from historical experience data; the bypass valve opening tolerance range represents the allowable deviation between the actual opening of the bypass valve and the flow valve position setting value; the pressure combustion mismatch fault is a pressure out-of-control phenomenon caused by the mismatch between fuel supply and steam demand. The fault flag bit can identify whether the boiler has a fault. The fuel supply amount correction instruction may include sending an opening correction signal to the fuel regulating valve, interlocking to open the auxiliary burner (such as an oil gun) and so on to quickly respond to the pressure demand.

[0127] It can be understood that the fault flag bit is represented by a Boolean value stored in the control system.

[0128] Furthermore, in order to ensure the reliability of fault repair and prevent premature resetting of the fault flag bit from causing secondary out-of-control. After the step S403, it further includes:

[0129] Sending the fuel supply amount correction instruction to the target terminal; after receiving the correction signal returned by the target terminal, collecting multiple pressure recovery values within a preset adjustment period; when each of the pressure recovery values meets the preset recovery condition, resetting the fault flag bit and generating a pressure increase process recovery confirmation signal.

[0130] It should be noted that the pressure recovery value is the main steam pressure value collected after the fuel correction command is executed, and is used to verify whether the fault is eliminated. The preset recovery condition represents the set of conditions that the pressure recovery value needs to meet, including rate regression, pressure stability, and valve opening deviation compliance, etc. The pressure increase process recovery confirmation signal is used to notify the DCS system to continue executing the pressure increase process.

[0131] In this embodiment, when the boiler enters the pressure increase mode, the actual main steam pressure change rate during the pressure increase process of the boiler is collected; the dynamic deviation coefficient between the actual main steam pressure change rate and the preset pressure increase rate curve is calculated; when the dynamic deviation coefficient exceeds the tolerance threshold and the bypass valve opening value reaches the tolerance range of the set value of the flow valve position, it is determined that the boiler has a pressure combustion mismatch fault, and a fault flag bit is set, and a fuel supply amount correction command is generated. By quantifying the difference between the actual pressure increase rate and the preset curve through the dynamic deviation coefficient, and combining the double verification of the bypass valve opening tolerance range, the pressure combustion mismatch fault is accurately determined, avoiding misjudgment caused by a single parameter jump, and at the same time generating a fuel correction command to optimize the combustion efficiency.

[0132] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the boiler fault detection method of the present application. Based on this technical concept, more forms of simple transformations are within the protection scope of the present application.

[0133] The present application also provides a boiler fault detection device. Please refer to Figure 4 , the boiler fault detection device includes:

[0134] A data monitoring module 10, configured to monitor the main steam pressure and the tube bundle heating time of the boiler in real time during the boiler startup process;

[0135] A data acquisition module 20, configured to obtain the bypass valve opening value and the set value of the flow valve position of the boiler when the main steam pressure is lower than the minimum pressure threshold and the tube bundle heating time exceeds the first preset threshold;

[0136] A fault judgment module 30, configured to determine the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value, and the set value of the flow valve position.

[0137] The boiler fault detection device provided by the present application adopts the boiler fault detection method in the above embodiment, and can solve the technical problem that traditional boiler detection methods often cause untimely fault identification due to isolated parameter analysis or dynamic response lag. Compared with the prior art, the beneficial effects of the boiler fault detection device provided by the present application are the same as those of the boiler fault detection method provided by the above embodiment, and other technical features in the boiler fault detection device are the same as those disclosed in the above embodiment method, and will not be elaborated here.

[0138] The present application provides a boiler fault detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the boiler fault detection method in Embodiment 1 above.

[0139] Reference is made below Figure 5 , which shows a schematic structural diagram of a boiler fault detection device suitable for implementing the embodiments of the present application. The boiler fault detection device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description: tablet computers), PMPs (Portable Media Player: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The boiler fault detection device shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0140] As Figure 5 shown, the boiler fault detection device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the boiler fault detection device are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. An input / output interface 1006 is also connected to the bus. Generally, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the boiler fault detection device to communicate with other devices wirelessly or wireline to exchange data. Although the figure shows a boiler fault detection device having various systems, it should be understood that it is not required to implement or include all the systems shown. More or fewer systems may be alternatively implemented or included.

[0141] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0142] The boiler fault detection device provided by the present application adopts the boiler fault detection method in the above-mentioned embodiment, and can solve the technical problem that traditional boiler detection methods often result in untimely fault identification due to isolated parameter analysis or dynamic response lag. Compared with the prior art, the beneficial effects of the boiler fault detection device provided by the present application are the same as those of the boiler fault detection method provided by the above-mentioned embodiment, and other technical features in the boiler fault detection device are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0143] It should be understood that the various parts disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0144] As mentioned above, only the specific embodiments of the present application are described, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0145] The present application provides a computer-readable storage medium, which has computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the boiler fault detection method in the above-mentioned embodiment.

[0146] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0147] The above computer-readable storage medium can be included in the boiler fault detection device; or it can exist independently without being assembled into the boiler fault detection device.

[0148] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the boiler fault detection device, the boiler fault detection device is caused to execute the boiler fault detection method described above.

[0149] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0151] The modules described in the embodiments of the present application can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0152] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned boiler fault detection method, and can solve the technical problem that traditional boiler detection methods often result in untimely fault identification due to isolated parameter analysis or dynamic response lag. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the boiler fault detection method provided by the above embodiments, and will not be elaborated here.

[0153] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the above-mentioned boiler fault detection method.

[0154] The computer program product provided by the present application can solve the technical problem that traditional boiler detection methods often result in untimely fault identification due to isolated parameter analysis or dynamic response lag. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the boiler fault detection method provided by the above embodiments, and will not be elaborated here.

[0155] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A boiler fault detection method, characterized in that: The boiler fault detection method comprises: During the boiler startup process, real-time monitoring of the main steam pressure and tube bundle heating time of the boiler; When the main steam pressure is lower than a minimum pressure threshold and the tube bundle heating time exceeds a first preset threshold, obtaining a bypass valve opening value and a flow valve position setting value of the boiler; The fault detection result of the boiler is determined according to the main steam pressure, the bypass valve opening value and the flow valve position setting value.

2. The boiler fault detection method according to claim 1, characterized in that: The step of determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the throughflow valve position setting value comprises: Calculating a basic deviation based on a real-time difference between the bypass valve opening value and the flow valve position setting value; Determining fluctuation data of the main steam flow of the boiler within a specified time window according to the main steam pressure, and calculating the load change rate based on the fluctuation data; Normalizing the basic deviation, the main steam pressure and the load change rate, and mapping the processing results to a three-dimensional space coordinate system to generate a dynamic feature vector; A fault detection result of the boiler is determined according to the dynamic feature vector.

3. The boiler fault detection method according to claim 2, characterized in that: The step of determining the fault detection result of the boiler according to the dynamic feature vector comprises: Performing cluster analysis on the historical fault data of the boiler to obtain fault mode clusters, wherein each cluster in the fault mode clusters represents a fault mode; Calculating the Euclidean distance between the dynamic feature vector and each fault mode cluster to obtain a distance detection result; The fault type of the boiler is determined according to the distance detection result, and an emergency boiler pressure relief instruction is generated.

4. The boiler fault detection method according to any one of claims 1 to 3, characterized in that: After the step of determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the throughflow valve position setting value, the method further includes: When the boiler enters the pressure boosting mode, collecting the actual main steam pressure change rate during the boiler pressure boosting process; Calculating a dynamic deviation coefficient between the actual main steam pressure change rate and a preset pressure increase rate curve; When the dynamic deviation coefficient exceeds the tolerance threshold and the bypass valve opening value reaches the tolerance range of the flow valve position setting value, it is determined that the boiler has a pressure combustion mismatch fault, and a fault flag is set, and a fuel supply amount correction instruction is generated.

5. The boiler fault detection method according to claim 4, characterized in that: After the steps of determining that a pressure combustion mismatch fault occurs in the boiler, setting a fault flag, and generating a fuel supply amount correction instruction when the dynamic deviation coefficient exceeds the tolerance threshold and the bypass valve opening value reaches the tolerance range of the throughflow valve position setting value, the method further includes: sending the fuel supply amount correction instruction to a target terminal; After receiving the correction signal returned by the target terminal, collecting a plurality of pressure recovery values ​​within a preset adjustment period; When all the pressure recovery values ​​meet the preset recovery conditions, the fault flag is reset and a boost process recovery confirmation signal is generated.

6. The boiler fault detection method according to any one of claims 1 to 3, characterized in that: After the step of determining the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the throughflow valve position setting value, the method further includes: When the boiler enters the constant pressure operation stage, the fluctuation amplitude of the main steam pressure and the rising gradient of the turbine speed are collected; When the fluctuation amplitude is higher than the preset fluctuation range and the turbine speed rising gradient is lower than the preset gradient setting value, it is determined that the boiler has a pressure-speed imbalance fault and a speed adjustment instruction is generated.

7. A boiler fault detection device, characterized in that: The device comprises: A data monitoring module, used to monitor the main steam pressure and tube bundle heating time of the boiler in real time during the boiler startup process; A data acquisition module, configured to acquire a bypass valve opening value and a flow valve position setting value of the boiler when the main steam pressure is lower than a minimum pressure threshold and the tube bundle heating time exceeds a first preset threshold; A fault judgment module is used to determine the fault detection result of the boiler according to the main steam pressure, the bypass valve opening value and the flow valve position setting value.

8. A boiler fault detection device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the boiler fault detection method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the boiler fault detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the boiler fault detection method according to any one of claims 1 to 6 are implemented.

Images