Dust remover filter bag damage detection method and system, electronic equipment and storage medium

Abstract

The invention provides a dust remover filter bag damage detection method and system, electronic equipment and a storage medium, and belongs to the technical field of dust removers, the method comprises the following steps: obtaining dust concentration data passing through a filter bag and working condition parameter data of the filter bag within a target duration; preprocessing the dust concentration data to obtain first dust concentration data, obtaining a dust concentration waveform based on the first dust concentration data, performing feature extraction on the dust concentration waveform, and determining a dust concentration waveform type in combination with working condition parameter data of the filter bag; and positioning the fault position of the filter bag based on the dust concentration waveform type, and determining the reason for the damage of the filter bag based on the fault position of the filter bag, the pressure difference and temperature of the bin where the filter bag is located and the material level detection data of the hopper corresponding to the filter bag. According to the dust remover filter bag damage detection method and system, the electronic equipment and the storage medium provided by the invention, the filter bag damage position can be accurately positioned, and the filter bag damage reason can be determined.

Description

Technical Field

[0001] The present application belongs to the technical field of dust collectors, and more specifically, relates to a dust collector filter bag damage detection method and system, electronic equipment, and storage medium. Background Art

[0002] In the industrial production process, dust collectors are widely used in various production scenarios. They filter dust-laden gases through filter bags to separate dust from gas, thereby purifying the gas and reducing dust emissions, playing a vital role in environmental protection and production safety. However, filter bags are very prone to damage during long-term operation. Once the filter bag is damaged, it will not only reduce the dust removal efficiency, cause excessive dust emissions, and pollute the environment, but may also affect the normal operation of production equipment and even cause safety accidents. At present, the detection methods for dust collector filter bag damage mostly rely on manual labor or rely solely on dust concentration, making it difficult to detect the location and cause of filter bag damage. Summary of the Invention

[0003] The purpose of this application is to provide a dust collector filter bag damage detection method and system, electronic equipment, and storage medium to accurately locate the location of the filter bag damage and determine the cause of the filter bag damage.

[0004] A first aspect of an embodiment of the present application provides a dust collector filter bag damage detection method, comprising: Obtain the dust concentration data passing through the filter bag within the target time and the working parameter data of the filter bag; Preprocessing the dust concentration data to obtain first dust concentration data, obtaining a dust concentration waveform based on the first dust concentration data, extracting features from the dust concentration waveform, and determining a type of the dust concentration waveform in combination with operating parameter data of the filter bag; Determine whether the filter bag is damaged based on the dust concentration waveform type. If the filter bag is damaged, locate the fault position of the filter bag based on the dust concentration waveform type. Determine the cause of the filter bag damage based on the fault position of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag.

[0005] A second aspect of the embodiments of the present application provides a dust collector filter bag damage detection system, comprising: The data acquisition module is used to obtain the dust concentration data passing through the filter bag within the target time and the working parameter data of the filter bag; a data analysis module for preprocessing the dust concentration data to obtain first dust concentration data, obtaining a dust concentration waveform based on the first dust concentration data, extracting features from the dust concentration waveform, and determining a type of the dust concentration waveform in combination with operating parameter data of the filter bag; The damage detection module is used to determine whether the filter bag is damaged based on the dust concentration waveform type. If the filter bag is damaged, the fault position of the filter bag is located based on the dust concentration waveform type. The cause of the filter bag damage is determined based on the fault position of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag.

[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned dust collector filter bag damage detection method are implemented.

[0007] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned dust collector filter bag damage detection method are implemented.

[0008] The dust collector filter bag damage detection method and system, electronic device, and storage medium provided in the embodiments of the present application have the following beneficial effects: First, this application obtains dust concentration data and operating parameter data within a target time period, pre-processes the dust concentration data and performs waveform analysis. Based on the dust concentration waveform type, the fault location of the filter bag is located, allowing for rapid identification of the specific location of the damaged filter bag. This method of integrating multiple aspects of information to determine whether a filter bag is damaged and the location of the fault can reduce misjudgments and missed detections, helping personnel quickly locate the problematic filter bag and avoid blind investigations, thereby improving detection accuracy.

[0009] Secondly, this application combines the fault location of the filter bag, the pressure difference and temperature of the chamber in which it is located, and the material level detection data of the hopper to determine the cause of the filter bag damage. It can deeply analyze the root cause of the filter bag damage from multiple angles such as equipment operating conditions and environmental conditions, which is more accurate than the traditional single judgment method. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0011] Figure 1 A schematic flow chart of a dust collector filter bag damage detection method provided in one embodiment of the present application; Figure 2 This is a structural block diagram of a dust collector filter bag damage detection system provided in one embodiment of the present application; Figure 3A schematic block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. To further clarify the objectives, technical solutions, and advantages of the present application, the following description will be provided with reference to specific embodiments in conjunction with the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A flowchart of a dust collector filter bag damage detection method provided in an embodiment of the present application, which can be executed by an electronic device, may include: S101: Obtain dust concentration data passing through the filter bag within a target time period and operating parameter data of the filter bag.

[0014] In this embodiment, a dust collector is a device used in industrial production to separate dust particles from dust-laden gases, achieving gas purification and dust recovery. It is widely used in mining, metallurgy, chemical engineering, power generation, and other fields. Dust collectors remove dust from gases through filtration, electrostatic adsorption, centrifugal separation, and other methods, reducing dust emissions, protecting the environment, and ensuring the normal operation of production equipment.

[0015] A dust collector generally consists of a clean air layer, a filter layer, an ash conveying layer, and a control unit. The filter bag in the filter layer is the core component of the dust collector. It is usually made of fiber materials (such as polyester, PTFE, etc.) and has a bag-shaped structure. It is used to intercept dust particles in dust-laden gas.

[0016] The target duration refers to a specific, pre-set time period for data collection, such as one hour, eight hours, or a production cycle. By limiting the time range for data collection, this embodiment facilitates analysis of the filter bag's operating status within a specific time period, eliminates interference from short-term fluctuations or abnormal data, and obtains statistically significant regular data.

[0017] Dust concentration refers to the mass or number of dust particles per unit volume of dust-laden gas, typically expressed in mg / m³ (mass concentration) or particles / m³ (number concentration). Dust concentration is a key indicator of filter bag performance. During normal operation, dust concentration downstream of the filter bag should remain low. If the filter bag is damaged, dust will penetrate directly through the damaged area, significantly increasing the dust concentration downstream.

[0018] Filter bag operating parameters reflect various parameters of the filter bag's operating environment and status, typically including but not limited to: cleaning frequency, cleaning time, pulse jet interval, vibration intensity, gas flow rate, etc. The operating frequency of the dust collector's cleaning system or the duration of a single cleaning cycle can reflect the system's operating status. Improper cleaning can increase filter bag wear or lead to secondary dust adsorption.

[0019] In this embodiment, during the operation of the dust collector, it is necessary to collect the dust concentration value passing through the filter bag within a specific time period (i.e., the target duration) to reflect the filtering effect of the filter bag; at the same time, various operating parameter data of the filter bag during operation are collected, such as cleaning time / frequency, gas flow, etc., to characterize the working environment and status of the filter bag; by obtaining these two types of data, basic data support is provided for subsequent analysis of whether the filter bag is damaged and locating the cause of the fault.

[0020] S102: Preprocess the dust concentration data to obtain first dust concentration data, obtain a dust concentration waveform based on the first dust concentration data, extract features of the dust concentration waveform, and determine the type of the dust concentration waveform in combination with operating parameter data of the filter bag.

[0021] In this embodiment, preprocessing dust concentration data involves cleaning, noise reduction, and artifact removal of the raw dust concentration data. Examples include removing outliers, filling in missing data, and smoothing fluctuations. The goal is to improve data accuracy and prevent interference with subsequent analysis. The first dust concentration data is standardized after preprocessing and more accurately reflects the actual filtration status of the filter bag.

[0022] In this embodiment, the dust concentration waveform is a waveform graph plotted as a time series of the first dust concentration data, visually displaying the dynamic trend of dust concentration changes over a target duration. Features such as the waveform's shape, peak value, and fluctuation frequency can be used to analyze the filter bag's operating status. Feature extraction is the process of extracting key parameters or patterns from the dust concentration waveform that reflect the filter bag's operating status. Dust concentration waveform types include, but are not limited to, periodic fluctuation waveforms, gradually rising waveforms, random pulse waveforms, and stable platform waveforms.

[0023] In this embodiment, the original dust concentration data is first preprocessed to remove noise, correct outliers, etc., to obtain more accurate first dust concentration data; based on this data, a dust concentration waveform is plotted in a time series to intuitively present the dynamic changes in dust concentration. Secondly, key features such as peak value and fluctuation frequency are extracted from the dust concentration waveform, and at the same time, combined with the operating parameter data such as the cleaning time / frequency of the filter bag, the pulse injection interval, and the gas flow rate, a comprehensive judgment is made as to which type of dust concentration waveform it belongs to. Different types of waveforms are formed for different reasons and in different locations, so this method helps to determine whether the filter bag is damaged and locate the leakage location, thereby achieving effective monitoring of the filter bag operating status.

[0024] S103: Determine whether the filter bag is damaged based on the dust concentration waveform type. If the filter bag is damaged, locate the fault position of the filter bag based on the dust concentration waveform type. Determine the cause of the filter bag damage based on the fault position of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag.

[0025] In this embodiment, filter bag damage refers to structural damage caused by factors such as material aging, mechanical wear, or external impact, resulting in cracks, holes, or seal failure, allowing dust to leak without being effectively filtered. By analyzing the dust concentration waveform and dust collector structure, the specific area (e.g., a chamber, a group of filter bags, or a single filter bag) where the filter bag is damaged can be determined.

[0026] The chambers in a dust collector are the spaces where the filter bags are grouped. The pressure differential within these chambers is the difference in air pressure between different chambers (the independent spaces where the filter bags are grouped) or between the inlet and outlet ports of different filter bags within the dust collector. This reflects the degree of dust accumulation on the bag surface and the resistance to airflow. A high pressure differential may be caused by excessive dust accumulation on the bag surface (inadequate cleaning) or decreased bag permeability. A low pressure differential may be due to bag damage.

[0027] Chamber temperature refers to the gas temperature in the chamber where the filter bags are located. It is affected by the process heat source, ambient temperature, and dust properties (such as endothermic reactions). Excessively high temperatures can cause carbonization and melting of the filter bag material, while sudden temperature changes can cause fatigue and damage to the filter bags due to thermal expansion and contraction.

[0028] Hopper level detection data is a real-time monitoring of the dust accumulation height or weight in the hopper at the bottom of the dust collector. It can be obtained by a level meter. Abnormally high levels will lead to poor cleaning performance of the filter bags.

[0029] In this embodiment, the filter bag is first determined to be damaged based on the dust concentration waveform type, compared with normal operating characteristics (such as regular fluctuations and concentration thresholds), achieving preliminary fault identification. Once damage is confirmed, the waveform's timing, amplitude changes, and the dust collector's compartment structure are used to identify the compartment or group where the damaged filter bag is located, solving the problem of "locating the location of the damage." Finally, the fault location is combined with the compartment pressure differential (to determine whether dust accumulation or airflow short-circuiting caused the damage), temperature (to analyze whether insufficient high-temperature tolerance caused material damage), and hopper material level (to investigate cleaning system failure or dust leakage) to comprehensively infer the root cause of the damage, such as mechanical wear, thermal aging, or abnormal cleaning.

[0030] From the above, we can conclude that, first, this application obtains dust concentration data and operating parameter data within the target time period, pre-processes the dust concentration data and performs waveform analysis, and locates the fault position of the filter bag based on the dust concentration waveform type, which can quickly determine the specific location of the damaged filter bag. This method of comprehensively judging whether the filter bag is damaged and determining the fault location based on multiple aspects of information can reduce misjudgments and missed judgments, help staff quickly find the problem filter bag, avoid blind investigation, and thus improve the accuracy of detection.

[0031] Secondly, this application combines the fault location of the filter bag, the pressure difference and temperature of the chamber in which it is located, and the material level detection data of the hopper to determine the cause of the filter bag damage. It can deeply analyze the root cause of the filter bag damage from multiple angles such as equipment operating conditions and environmental conditions, which is more accurate than the traditional single judgment method.

[0032] In one embodiment of the present application, the operating parameter data of the filter bag includes the pulse spraying interval; Extract the characteristics of the dust concentration waveform and determine the type of dust concentration waveform based on the operating parameter data of the filter bag, including: Extracting the dust concentration waveform in the time domain to obtain a first eigenvector, and extracting the dust concentration waveform in the frequency domain to obtain a second eigenvector; Adjusting the feature weights corresponding to the first eigenvector and the second eigenvector based on the pulse injection interval, and performing weighted fusion based on the first eigenvector, the second eigenvector and their corresponding feature weights to obtain a target feature vector; The dust concentration waveform type is obtained based on the target feature vector and classification model.

[0033] In this embodiment, feature extraction is performed on the dust concentration waveform, including feature extraction from both the time domain and the frequency domain. The time domain allows for direct observation of the waveform's shape along the time axis, while the frequency domain converts the waveform into frequency components. This multi-dimensional feature extraction avoids misjudgments caused by insufficient information from a single dimension.

[0034] In this embodiment, time-domain feature extraction refers to analyzing waveform characteristics from the time dimension and extracting parameters directly related to time. Time-domain feature extraction of the dust concentration waveform to obtain a first feature vector includes extracting time-domain feature parameters such as peak value, valley value, number of peaks, number of valleys, rise time, fall time, pulse width, and the average dust concentration between peaks.

[0035] The peak value represents the maximum dust concentration within a period, while the valley value represents the minimum dust concentration within a period. The number of peaks and valleys represent the number of peaks and valleys, respectively, within the target duration. The rise time represents the time from the adjacent valley point to any peak point; the fall time represents the time from any peak point to the adjacent valley point. The pulse width represents the duration that the dust concentration exceeds the target concentration threshold.

[0036] The peak value, valley value, number of peak values, number of valley values, rise time, fall time, pulse width, and average value of dust concentration between peaks are used as the first eigenvector. In this embodiment, the first eigenvector quantizes the time domain characteristic parameters into a numerical vector as a mathematical expression of the waveform's time domain characteristics.

[0037] In this embodiment, frequency domain feature extraction is performed on the dust concentration waveform to obtain a second eigenvector, including extracting frequency domain feature parameters such as frequency, amplitude, and phase. The second eigenvector quantizes the frequency domain feature parameters into a numerical vector, which serves as a mathematical expression of the waveform's frequency domain features.

[0038] In this embodiment, the operating parameter data of the filter bag includes the pulse injection interval. The pulse injection interval refers to the time interval between two adjacent pulse injections during dust collector bag cleaning, which can reflect the working rhythm of the filter layer cleaning structure. Adjusting the feature weights corresponding to the first eigenvector and the second eigenvector based on the pulse injection interval can be achieved using the following formula: .

[0039] in, represents the feature weight corresponding to the first eigenvector, represents the feature weight corresponding to the second eigenvector, Indicates the pulse injection interval, Indicates the benchmark value of the sensitive interval of time domain features, Indicates the width of the sensitive interval of time domain features, represents the pulse jet intensity correction factor, represents the frequency domain attenuation coefficient, represents the frequency domain gain constant, Represents the zero-proof constant, which can be .

[0040] The target feature vector is obtained by weighted fusion based on the first feature vector, the second feature vector and their corresponding feature weights, which can be achieved according to the following formula: .

[0041] in, Indicates channel splicing operation, is the target feature vector, is the first eigenvector, is the second eigenvector.

[0042] In this embodiment, when ≈ hour, , the base weight is 0.5, This means that the longer the injection interval, the more important the time domain characteristics are. It indicates that the shorter the injection interval, the more intensified the frequency domain analysis needs to be. It approaches 1 for short intervals and approaches 0 for long intervals. It means that the shorter the injection interval, the greater the frequency domain feature weight.

[0043] In this embodiment, each feature in the target feature vector is input into a classification model. The classification model determines the probability value of each type of dust concentration waveform. When the probability value is greater than a preset probability threshold, the model outputs the dust concentration waveform type corresponding to that probability value. When the probability value is less than or equal to the preset probability threshold, the model does not output the dust concentration waveform corresponding to that probability value. The preset probability threshold in this embodiment is set when the classification model is initialized. The purpose of setting the preset probability threshold is to enable the model to determine whether to output the corresponding dust concentration waveform type based on the calculated probability value. The classification model can be a decision tree model, a convolutional neural network model, or the like.

[0044] As can be seen from the above, this embodiment adjusts the weights of time-domain and frequency-domain features based on the pulsed injection interval, enabling the model to sensitively capture the impact of the injection period on dust concentration (for example, a short injection interval may lead to more pronounced periodic fluctuations), avoiding the situation where a single fixed weight would ignore differences in operating conditions. This embodiment also integrates time-domain and frequency-domain features, combining them with the operating parameters of the filter bag to form a target feature vector. This fully characterizes the waveform's amplitude changes, frequency characteristics, and correlation with the injection period, improving classification accuracy under complex operating conditions.

[0045] In one embodiment of the present application, the training process of the classification model includes: The historical dust concentration waveforms were grouped based on the pulse injection interval to obtain multiple analysis training sets; Based on multiple sets of analysis training sets, the main loss function and the similarity constraint loss function are calculated, and the target loss function is obtained by weighted fusion of the main loss function and the similarity constraint loss function; In response to the target loss function satisfying the preset conditions, a trained classification model is obtained.

[0046] In this embodiment, the formula of the similarity constraint loss function is: .

[0047] Among them, i and j represent the numbers of the two samples in the sample pair selected in the multi-group analysis training set. represents the similarity constraint loss value, represents the feature extraction function, represents the dust concentration waveform of the i-th sample, represents the dust concentration waveform of the jth sample, represents the 2-norm, 、 Respectively represent the pulse injection interval of the i-th sample and the j-th sample, represents the working condition attenuation coefficient, represents the pulse injection interval difference penalty function.

[0048] In this embodiment, the similarity constraint mechanism is that samples in the same pulse interval time group are clustered in the feature space, while samples in different pulse interval time groups are automatically unconstrained. This is done to strengthen feature aggregation and thus improve the robustness of the classification model.

[0049] The traditional classification model training process involves inputting all training samples into the classification model to obtain a trained model. However, this training method can easily lead to the same type of damage being misclassified as different dust concentration waveform types at different puffing intervals, and different types of damage being misclassified at the same puffing interval. To address this, this embodiment adds a similarity-constrained loss function to the classification model training process. This loss function only applies to sample pairs selected from multiple analysis training sets, significantly improving the robustness of the model.

[0050] In this embodiment, the main loss function and the similarity constraint loss function are calculated based on multiple analysis training sets. The main loss function is responsible for the basic classification task, ensuring the accuracy of the model's classification of waveform types (such as periodic fluctuations, random pulses, etc.). The similarity constraint loss function constrains the feature space distribution through the following logic: Sample pair similarity constraint: If two samples come from the same working condition group (similar pulse injection interval), their feature vectors are forced to be close in space; if they come from different working condition groups, the feature distance is widened by penalizing sample pairs with large interval differences. Working condition attenuation coefficient The constraint strength can be adjusted to avoid over-reliance on the injection interval, which may lead to a decrease in the generalization ability of the model.

[0051] The objective loss function is a weighted summation of the main loss function and the similarity constraint loss function, so that the model achieves a balance between classification accuracy and decoupling of working condition characteristics. In this embodiment, the model parameters are updated by optimizing the objective loss function. When the loss value meets the preset threshold or convergence condition, the training is stopped to obtain a classification model that can capture the waveform characteristics and the association with the working condition at the same time. The preset threshold in this embodiment refers to a pre-set value, which is a constant. For example, the preset threshold is P. When the loss value is less than or equal to P, the model stops training. The convergence condition can be a user-defined condition. For example, the convergence condition can be that the model stops training when the number of training times is greater than R times.

[0052] From the above, it can be concluded that this embodiment focuses on the waveform characteristics under different injection intervals based on the working condition grouping. The similarity constraint loss function forces the clustering of sample features under the same working condition and the separation of sample features under different working conditions, thereby strengthening the correlation between the working condition and the waveform. The fusion of the main loss function and the constraint loss function improves the classification accuracy while making the feature space distribution more consistent with physical logic, avoiding confusion of cross-working condition features, enhancing the model's adaptability and generalization ability to complex working conditions, and providing more reliable model support for the accurate classification and fault diagnosis of the filter bag operating status.

[0053] In one embodiment of the present application, preprocessing the dust concentration data to obtain first dust concentration data includes: Establish a dynamic baseline model for dust concentration, which is used to determine the reference baseline for dust concentration; The dust concentration data is input into the dynamic baseline model of dust concentration, and the dynamic standard deviation algorithm is used to identify outliers. The outliers exceeding ±a times the standard deviation in N consecutive sampling periods are replaced with the average value of the dust concentration data in the N+1th sampling period to obtain the first dust concentration data.

[0054] In this embodiment, the dynamic baseline model of dust concentration can provide a real-time updated reference baseline for dust concentration data. This baseline is not a fixed value, but is dynamically adjusted over time based on historical data to reflect the fluctuation trend of dust concentration under normal operating conditions. The dynamic standard deviation algorithm is a statistical method for real-time analysis of data volatility. The core is to calculate the standard deviation based on the dynamic baseline of the data to identify abnormal fluctuations in the data. N consecutive sampling cycles are the time window unit for data acquisition, which is used to avoid false judgments triggered by a single random noise point. For example, when N=3, only when the data for three consecutive cycles exceeds the threshold is it determined to be a true anomaly, rather than an accidental fluctuation. ±a times the standard deviation is the threshold range for outlier judgment. a is an adjustable coefficient (such as a=2 or 3), representing the fluctuation amplitude in units of dynamic standard deviation. ±a times the standard deviation corresponds to the confidence interval of the data (such as a=2 corresponds to a 95% confidence interval). Data outside this range is considered "abnormal."

[0055] In this embodiment, when an abnormal value is identified, the abnormal value that exceeds ±a times the standard deviation in N consecutive sampling periods can be replaced by the average value of the dust concentration data in the sampling period before and after the abnormal value, for example, the average value of the dust concentration data in the N+1th sampling period, so that the first dust concentration data obtained is smooth data.

[0056] As can be seen from the above, this embodiment adapts to operating condition changes through a dynamic baseline model, combined with a dynamic standard deviation algorithm to accurately identify outliers. Once an outlier is identified, continuous cycle judgment is used to improve the reliability of model identification, and the outlier is corrected using the lag cycle mean. This method effectively removes noise and sudden interference from dust concentration data, retaining true signal characteristics. This provides high-quality data for subsequent feature extraction and classification model training, enhancing the accuracy and robustness of operating condition analysis.

[0057] In one embodiment of the present application, the cause of filter bag damage is determined based on the fault location of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag, including: When the fault location is the bag opening, the pressure difference in the bag opening area is compared with a preset pressure difference threshold to obtain a first comparison result, and the temperature at the bag opening is compared with the temperature at other locations of the filter bag to obtain a second comparison result. The cause of the filter bag damage is determined based on the first comparison result and the second comparison result; When the fault location is the bottom of the bag, the first proportion of the material level detection data greater than the height threshold within the target time is calculated, and the second proportion of the time period of synchronous changes in pressure difference and temperature within the target time is calculated. The cause of filter bag damage is determined based on the first proportion and the second proportion.

[0058] In this embodiment, when the fault location is the bag opening, the pressure differential in the bag opening area is first compared with a preset threshold. If the pressure differential exceeds the threshold, it could be due to a loose bag opening seal, causing an airflow short circuit, or a clogged filter bag, increasing resistance. If the pressure differential is below the threshold, it could be due to a damaged bag opening, causing air leakage and reduced airflow resistance. Next, the bag opening temperature is compared with the temperatures at other locations. If the bag opening temperature is significantly higher than that at other locations, it could be due to improper installation, causing localized frictional heating, or high-temperature flue gas directly flushing the bag opening. If the bag opening temperature is significantly lower than that at other locations, it could be due to external cold air leaking in (e.g., due to a damaged bag opening seal).

[0059] Therefore, if the pressure difference at the bag opening area during the target duration is less than the preset pressure difference threshold, and the bag opening temperature is significantly lower than the temperature at other locations, the filter bag damage may be caused by seal failure. If the pressure difference at the bag opening area during the target duration is greater than the preset pressure difference threshold, and the temperature at the bag opening is the same as the temperature at other locations of the filter bag, the filter bag damage may be caused by airflow erosion and wear.

[0060] In this embodiment, when the fault location is the bag bottom, the first proportion of material level detection data exceeding the height threshold within the target duration is calculated. If the first proportion is greater than m1, it indicates that the hopper has been operating with high material levels for a long time, and the bag bottom may have been damaged by friction from dust accumulation or material impact. If the first proportion is less than or equal to m1, the cause of damage is not related to the material level. Next, the proportion of time that the pressure differential and temperature change synchronously is calculated. If the second proportion is greater than m2, it indicates that the pressure differential changes affect the temperature, or vice versa, and the cause of filter bag damage is not related to the pressure differential and temperature. If the second proportion is less than or equal to m2, it indicates that the pressure differential and temperature do not change synchronously. If the pressure differential is abnormal and the first proportion is greater than m1, the cause of filter bag damage may be dust accumulation at the bag bottom. If the pressure differential and temperature fluctuate abnormally and the first proportion is less than or equal to m1, the cause of damage is determined to be sparks carried by the dust return airflow that burned through the bag bottom. In this embodiment, m1 can be any constant between 0.4 and 0.8, and m2 can be any constant between 0.6 and 1.0.

[0061] From the above, it can be concluded that this embodiment designs differentiated analysis indicators for different fault locations of the bag opening and bag bottom, which can improve the accuracy of locating the cause of the damage.

[0062] Corresponding to the dust collector filter bag damage detection method of the above embodiment, Figure 2 This is a structural block diagram of a dust collector filter bag damage detection system provided by an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 2 The dust collector filter bag damage detection system 20 includes: a data acquisition module 21, a data analysis module 22 and a damage detection module 23. The data acquisition module 21 is used to obtain the dust concentration data passing through the filter bag and the working parameter data of the filter bag within the target time period; A data analysis module 22 is configured to pre-process the dust concentration data to obtain first dust concentration data, obtain a dust concentration waveform based on the first dust concentration data, extract features from the dust concentration waveform, and determine the type of the dust concentration waveform in combination with operating parameter data of the filter bag; The damage detection module 23 is used to determine whether the filter bag is damaged based on the dust concentration waveform type. If the filter bag is damaged, the fault position of the filter bag is located based on the dust concentration waveform type. The cause of the filter bag damage is determined based on the fault position of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag.

[0063] In one embodiment of the present application, the operating parameter data of the filter bag includes a pulse spraying interval.

[0064] The data analysis module 22 is specifically used for: Extract the characteristics of the dust concentration waveform and determine the type of dust concentration waveform based on the operating parameter data of the filter bag, including: Extracting the dust concentration waveform in the time domain to obtain a first eigenvector, and extracting the dust concentration waveform in the frequency domain to obtain a second eigenvector; Adjusting the feature weights corresponding to the first eigenvector and the second eigenvector based on the pulse injection interval, and performing weighted fusion based on the first eigenvector, the second eigenvector and their corresponding feature weights to obtain a target feature vector; The dust concentration waveform type is obtained based on the target feature vector and classification model.

[0065] In one embodiment of the present application, the data analysis module 22 is specifically configured to: In one embodiment of the present application, the peak value, valley value, number of peak values, number of valley values, rise time, fall time, pulse width, and average value of dust concentration between peak values ​​of the dust concentration waveform are extracted; The peak value, valley value, number of peak values, number of valley values, rise time, fall time, pulse width, and average value of dust concentration between peak values ​​are taken as the first eigenvector; The rise time indicates the time from the adjacent valley point to any peak point; the fall time indicates the time from the peak point to the adjacent valley point; and the pulse width indicates the duration that the dust concentration is greater than the target concentration threshold.

[0066] In one embodiment of the present application, the data analysis module 22 is further configured to: The historical dust concentration waveforms were grouped based on the pulse injection interval to obtain multiple analysis training sets; Based on multiple sets of analysis training sets, the main loss function and the similarity constraint loss function are calculated, and the target loss function is obtained by weighted fusion of the main loss function and the similarity constraint loss function; In response to the target loss function satisfying the preset conditions, a trained classification model is obtained.

[0067] In one embodiment of the present application, the formula of the similarity constraint loss function is: .

[0068] Among them, i and j represent the numbers of the two samples in the sample pair selected in the multi-group analysis training set. represents the similarity constraint loss value, represents the feature extraction function, represents the dust concentration waveform of the i-th sample, represents the dust concentration waveform of the jth sample, represents the 2-norm, 、 Respectively represent the pulse injection interval of the i-th sample and the j-th sample, represents the working condition attenuation coefficient, represents the pulse injection interval difference penalty function.

[0069] In one embodiment of the present application, the data analysis module 22 is used to: Establish a dynamic baseline model for dust concentration, which is used to determine the reference baseline for dust concentration; The dust concentration data is input into the dynamic baseline model of dust concentration, and the dynamic standard deviation algorithm is used to identify outliers. The outliers exceeding ±a times the standard deviation in N consecutive sampling periods are replaced with the average value of the dust concentration data in the N+1th sampling period to obtain the first dust concentration data.

[0070] In one embodiment of the present application, the damage detection module 23 is specifically configured to: When the fault location is the bag opening, the pressure difference in the bag opening area is compared with a preset pressure difference threshold to obtain a first comparison result, and the temperature at the bag opening is compared with the temperature at other locations of the filter bag to obtain a second comparison result. The cause of the filter bag damage is determined based on the first comparison result and the second comparison result; When the fault location is the bottom of the bag, the first proportion of the material level detection data greater than the height threshold within the target time is calculated, and the second proportion of the time period of synchronous changes in pressure difference and temperature within the target time is calculated. The cause of filter bag damage is determined based on the first proportion and the second proportion.

[0071] See also Figure 3 , Figure 3This is a schematic block diagram of an electronic device provided in one embodiment of the present application. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned system embodiments, such as Figure 2 The functions of the data acquisition module 21, the data analysis module 22 and the damage detection module 23 are shown.

[0072] It should be understood that in the embodiment of the present application, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0073] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0074] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a nonvolatile random access memory.

[0075] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiment of the present application can execute the implementation method described in the dust collector filter bag damage detection method provided in the embodiment of the present application, and can also execute the implementation method of the electronic device described in the embodiment of the present application, which will not be repeated here.

[0076] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0077] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0078] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0079] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0081] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0082] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0083] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A dust collector filter bag damage detection method, characterized in that: include: Obtain the dust concentration data passing through the filter bag within the target time and the working parameter data of the filter bag; Preprocessing the dust concentration data to obtain first dust concentration data, obtaining a dust concentration waveform based on the first dust concentration data, performing feature extraction on the dust concentration waveform and determining a type of the dust concentration waveform in combination with operating parameter data of the filter bag; Whether the filter bag is damaged is determined based on the dust concentration waveform type. If the filter bag is damaged, the fault position of the filter bag is located based on the dust concentration waveform type. The cause of the filter bag damage is determined based on the fault position of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag.

2. The dust collector filter bag damage detection method according to claim 1, characterized in that: The operating parameter data of the filter bag includes pulse spraying interval; The feature extraction of the dust concentration waveform and determination of the dust concentration waveform type in combination with the operating parameter data of the filter bag include: Performing time domain feature extraction on the dust concentration waveform to obtain a first feature vector, and performing frequency domain feature extraction on the dust concentration waveform to obtain a second feature vector; Adjusting the feature weights corresponding to the first feature vector and the second feature vector respectively based on the pulse injection interval, and performing weighted fusion based on the first feature vector, the second feature vector and the feature weights corresponding thereto to obtain a target feature vector; The dust concentration waveform type is obtained based on the target feature vector and the classification model.

3. The dust collector filter bag damage detection method according to claim 2, characterized in that: The step of extracting the time domain features of the dust concentration waveform to obtain a first feature vector includes: Extracting the peak value, valley value, number of peak values, number of valley values, rise time, fall time, pulse width, and average value of dust concentration between peak values ​​of the dust concentration waveform; The peak value, the valley value, the number of peak values, the number of valley values, the rise time, the fall time, the pulse width, and the average value of the dust concentration between peak values ​​are used as a first eigenvector; Among them, the rising time represents, for any peak point, the time from the adjacent valley point to the peak point; the falling time represents, for any peak point, the time from the peak point to the adjacent valley point; the pulse width represents the duration that the dust concentration is greater than the target concentration threshold.

4. The dust collector filter bag damage detection method according to claim 2, characterized in that: The training process of the classification model includes: The historical dust concentration waveforms were grouped based on the pulse injection interval to obtain multiple analysis training sets; Based on multiple sets of analysis training sets, the main loss function and the similarity constraint loss function are calculated, and the target loss function is obtained by weighted fusion of the main loss function and the similarity constraint loss function; In response to the target loss function satisfying a preset condition, a trained classification model is obtained.

5. The dust collector filter bag damage detection method according to claim 4, characterized in that: The formula of the similarity constraint loss function is: Among them, i and j represent the numbers of the two samples in the sample pair selected in the multi-group analysis training set. represents the similarity constraint loss value, represents the feature extraction function, represents the dust concentration waveform of the i-th sample, represents the dust concentration waveform of the jth sample, represents the 2-norm, 、 Respectively represent the pulse injection interval of the i-th sample and the j-th sample, represents the working condition attenuation coefficient, represents the pulse injection interval difference penalty function.

6. The dust collector filter bag damage detection method according to claim 1, characterized in that: The preprocessing of the dust concentration data to obtain first dust concentration data includes: Establishing a dynamic baseline model for dust concentration, wherein the dynamic baseline model for dust concentration is used to determine a reference baseline for dust concentration; The dust concentration data is input into the dynamic baseline model of dust concentration, and the dynamic standard deviation algorithm is used to identify outliers. The outliers exceeding ±a times the standard deviation in N consecutive sampling periods are replaced with the average value of the dust concentration data in the N+1th sampling period to obtain the first dust concentration data.

7. The dust collector filter bag damage detection method according to claim 1, characterized in that: The method of determining the cause of filter bag damage based on the fault location of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag includes: When the fault location is the bag opening, the pressure difference in the bag opening area is compared with a preset pressure difference threshold to obtain a first comparison result, and the temperature at the bag opening is compared with the temperature at other locations of the filter bag to obtain a second comparison result. The cause of the filter bag damage is determined based on the first comparison result and the second comparison result; When the fault location is the bottom of the bag, the first proportion of the material level detection data greater than the height threshold within the target time is calculated, and the second proportion of the time period of synchronous changes in pressure difference and temperature within the target time is calculated. Based on the first proportion and the second proportion, the cause of filter bag damage is determined.

8. A dust collector filter bag damage detection system, characterized in that: include: The data acquisition module is used to obtain the dust concentration data passing through the filter bag within the target time and the working parameter data of the filter bag; a data analysis module, configured to pre-process the dust concentration data to obtain first dust concentration data, obtain a dust concentration waveform based on the first dust concentration data, perform feature extraction on the dust concentration waveform, and determine a type of the dust concentration waveform in combination with operating parameter data of the filter bag; a damage detection module for determining whether the filter bag is damaged based on the dust concentration waveform type; locating the fault position of the filter bag based on the dust concentration waveform type if the filter bag is damaged; and determining the cause of the filter bag damage based on the fault position of the filter bag, the pressure difference and temperature of the chamber where the filter bag is located, and the material level detection data of the hopper corresponding to the filter bag.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images