Emergency safety early warning platform for special scene

Abstract

The invention discloses an emergency safety early warning platform for a special scene, and relates to the technical field of filtering safety early warning, and the platform is characterized in that the pressure of two sides of a filtering element in a high-pressure backwashing filtering station is detected, filtering pressure difference information is obtained through calculation, and filtering fracture safety risk information is obtained; obtaining a blocking parameter of the filter element; the optimal backwashing pressure and the optimal filter element damage probability are obtained; the method comprises the following steps: acquiring flushing pressure difference information, performing pipeline fracture safety risk analysis, acquiring flushing fracture safety risk information, calculating to obtain a safety risk coefficient of the high-pressure backwashing filter station, and performing emergency safety early warning. The technical problems that an existing high-pressure backwash filter station lacks real-time and accurate monitoring and evaluation on the state of a filter element, the pipeline fracture risk and the backwash effect, and then the high-pressure backwash filter station is low in filter efficiency and inaccurate in safety risk evaluation are solved. The technical effect of improving the filtering efficiency and the security risk assessment accuracy is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to filtering safety warning, and specifically to an emergency safety warning platform for special scenarios. Background Art

[0002] High-pressure backwash filter stations play a vital role in industrial production and water treatment. They are mainly responsible for removing impurities from fluids to ensure the stable operation of subsequent processes and the safety of equipment. However, in high-pressure, high-flow operating environments, filter elements are susceptible to problems such as wear and blockage, which not only affects the filtration efficiency, but may also cause serious safety accidents such as pipeline ruptures. Traditional filter station monitoring systems can often only provide basic pressure, flow and other parameter monitoring, and lack in-depth analysis and early warning of filter element blockage, backwashing effects and potential safety risks. As a result, in actual operation, manual intervention is often required to determine whether the filter element needs to be replaced or cleaned, and whether the backwashing pressure setting is reasonable, making the entire production process inefficient and difficult to accurately assess the safety risks of high-pressure backwash filter stations, which brings great hidden dangers to production.

[0003] Therefore, in the current high-pressure backwash filter station safety warning related technologies, there is a lack of real-time and accurate monitoring and evaluation of the status of filter elements, the risk of pipeline rupture and the backwashing effect, which in turn leads to technical problems such as low filtration efficiency and inaccurate safety risk assessment of high-pressure backwash filter stations. Summary of the invention

[0004] This application solves the technical problems of low filtration efficiency and inaccurate safety risk assessment in existing high-pressure backwashing filter stations by providing an emergency safety warning platform for special scenarios, thereby achieving the technical effect of improving filtration efficiency and the accuracy of safety risk assessment.

[0005] The present application provides an emergency safety warning platform for special scenarios, the platform comprising: a pipeline rupture safety risk analysis module, which is used to detect the pressure on both sides of the filter element in the high-pressure backwashing filter station during the operation of the high-pressure backwashing filter station, obtain initial pressure information and filtration pressure information, calculate and obtain filtration pressure difference information, perform pipeline rupture safety risk analysis, and obtain filtration rupture safety risk information; a filter element blockage analysis module, which is used to perform blockage analysis of the filter element according to the filtration pressure difference information and obtain blockage parameters of the filter element; a backwashing optimization module, which is used to obtain a backwashing pressure space for backwashing the filter element, and perform backwashing optimization within the backwashing pressure space to maximize the degree of cleanliness of the blockage flushing and minimize the probability of damage to the filter element, obtain the optimal backwashing pressure, and the optimal probability of damage to the filter element; a safety risk coefficient acquisition module, which is used to simulate backwashing according to the optimal backwashing pressure, obtain flushing pressure difference information, perform pipeline rupture safety risk analysis, obtain flushing rupture safety risk information, and calculate the safety risk coefficient of the high-pressure backwashing filter station in combination with the filtration rupture safety risk information and the probability of damage to the filter element, and perform emergency safety warning.

[0006] In a possible implementation, the pipeline rupture safety risk analysis module further performs the following processing: detecting the pressure on both sides of the filter element in the high-pressure backwash filter station to obtain initial pressure information and filtration pressure information; calculating and obtaining the filtration pressure difference information of the filter element based on the initial pressure information and the filtration pressure information; pre-training a pipeline rupture risk predictor; using the pipeline rupture risk predictor to perform pipeline rupture safety risk analysis and prediction on the filtration pressure difference information input to obtain filtration rupture safety risk information, wherein the filtration rupture safety risk information includes the probability of pipeline rupture.

[0007] In a possible implementation, the pipeline rupture safety risk analysis module also performs the following processing: based on the historical maintenance data of the pipeline in the high-pressure backwash filter station, a set of sample pressure difference information intervals is collected, and the proportion of pipeline rupture under different sample pressure difference information intervals is collected, and marked as a sample pipeline rupture probability set; the sample pressure difference information interval set and the sample pipeline rupture probability set are constructed as supervised training data and verification data, and the pipeline rupture risk predictor is trained until convergence.

[0008] In a possible implementation, the filter element blockage analysis module also performs the following processing: based on the historical maintenance data of the filter element in the high-pressure backwash filter station, collect a set of sample filter pressure difference information intervals, and collect the blockage ratio of the filter element under different sample filter pressure difference information intervals, and mark them as sample blockage parameter sets; construct a mapping relationship between the sample filter pressure difference information interval set and the sample blockage parameter set to obtain a blockage classifier; input the filter pressure difference information into the blockage classifier, and obtain the blockage parameters of the filter element through mapping and classification. In a possible implementation, the backwash optimization module also performs the following processing: obtain the backwash pressure space for backwashing the filter element; randomly extract the first backwash pressure in the backwash pressure space; perform a flushing prediction based on the first backwash pressure and the blockage parameter to obtain the first blockage flushing cleaning level and the first filter element damage probability; calculate the first flushing fitness based on the first blockage flushing cleaning level and the first filter element damage probability, as shown in the following formula: Among them, RA is the flushing adaptability, and is the weight, R is the clogging flushing cleaning level, Q is a positive integer, and K is the probability of filter element damage; the backwashing pressure is continuously optimized in the backwashing pressure space until the convergence optimization times are reached, the backwashing pressure with the maximum flushing fitness is output, the optimal backwashing pressure is obtained, and the probability of filter element damage at the optimal backwashing pressure is obtained as the optimal probability of filter element damage.

[0009] In a possible implementation, the backwash optimization module also performs the following processing: based on the backwash history data of the filter element, a sample blockage parameter set and a sample backwash pressure set are collected, and the blockage flushing cleaning level and the filter element damage ratio under backwashing with different sample blockage parameters and sample backwashing pressures are collected, and the sample blockage flushing cleaning level set and the sample filter element damage probability set are obtained by marking; the sample blockage parameter set, the sample backwashing pressure set, the sample blockage flushing cleaning level set and the sample filter element damage probability set are used as supervised training data and verification data to train a backwash predictor until convergence; the backwash predictor is used to perform flushing prediction on the first backwash pressure and blockage parameter input to obtain a first blockage flushing cleaning level and a first filter element damage probability.

[0010] In a possible implementation, the safety risk factor acquisition module also performs the following processing: based on the backwashing history data of the filter element, the pressure difference of the filter element under backwashing with different sample blockage parameters and sample backwashing pressures is collected to obtain a sample flushing pressure difference information set; the sample blockage parameter set, the sample backwashing pressure set and the sample flushing pressure difference information set are used to train a backwashing pressure difference simulator; the backwashing pressure difference simulator is used to simulate backwashing of the first backwash pressure and blockage parameter to obtain flushing pressure difference information.

[0011] In a possible implementation, the safety risk coefficient acquisition module also performs the following processing: inputting the flushing pressure difference information into the pipeline rupture risk predictor, analyzing and predicting the pipeline rupture safety risk, and obtaining the flushing rupture safety risk information; weighted calculation of the flushing rupture safety risk information, the filtration rupture safety risk information and the probability of filter element damage to obtain the safety risk coefficient of the high-pressure backwashing filter station; determining whether the safety risk coefficient is greater than or equal to the safety risk threshold value, and if so, issuing an emergency safety warning, and if not, not issuing an emergency safety warning.

[0012] Through the emergency safety warning platform for a special scenario proposed in this application, the pressure on both sides of the filter element in the high-pressure backwash filter station is detected, the filter pressure difference information is calculated, and the filter rupture safety risk information is obtained; the filter element blockage parameters are obtained; the optimal backwash pressure and the optimal filter element damage probability are obtained; the flushing pressure difference information is obtained, and the pipeline rupture safety risk analysis is performed, the flushing rupture safety risk information is obtained, and the safety risk coefficient of the high-pressure backwash filter station is calculated to perform an emergency safety warning. This solves the technical problem of the lack of real-time and accurate monitoring and evaluation of the filter element status, pipeline rupture risk and backwashing effect in the existing high-pressure backwash filter station, which leads to low filtration efficiency and inaccurate safety risk assessment of the high-pressure flushing filter station, and achieves the technical effect of improving filtration efficiency and the accuracy of safety risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure are briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0014] Figure 1 A schematic diagram of the structure of an emergency safety warning platform for a special scenario provided in an embodiment of the present application; Figure 2A schematic diagram of the execution flow of a filter element blockage analysis module in an emergency safety warning platform for a special scenario provided in an embodiment of the present application.

[0015] Explanation of reference numerals: pipeline rupture safety risk analysis module 10 , filter element blockage analysis module 20 , backwash optimization module 30 , safety risk coefficient acquisition module 40 . DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or components that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application embodiment provides an emergency safety warning platform for special scenarios, such as Figure 1 As shown, the emergency safety warning platform for a special scenario includes: a pipeline rupture safety risk analysis module 10, a filter element blockage analysis module 20, a backwash optimization module 30, and a safety risk coefficient acquisition module 40.

[0020] The pipeline rupture safety risk analysis module 10 is used to detect the pressure on both sides of the filter element in the high-pressure backwash filter station during the operation of the high-pressure backwash filter station, obtain initial pressure information and filtration pressure information, calculate the filtration pressure difference information, perform pipeline rupture safety risk analysis, and obtain filtration rupture safety risk information.

[0021] Preferably, the operating principle of the high-pressure backwash filter station includes filtration and backwashing. Specifically, the high-pressure pump pushes the fluid to be filtered to the filter station through the water inlet. The fluid carries impurities, particles or suspended matter into the filtration system. The fluid passes through multiple layers or filter media of a specific precision. Impurities and particles are intercepted on the surface or inside of the filter medium, and the clean fluid after filtration passes through the filter medium and enters the water outlet. The filter station is usually equipped with a differential pressure sensor to monitor the pressure changes on both sides of the filter medium in real time. When impurities gradually accumulate and the pressure difference on both sides of the medium increases to a certain set value, it is judged that the filter needs to be cleaned, that is, when the filter When the impurities in the filter accumulate to a certain extent, hindering the normal flow of the fluid, when the pressure difference reaches the set threshold, the backwash mode is turned on by the automatic control device. At this time, the normal filtration fluid channel is closed and the backwash channel is opened. The backwash fluid (usually clean water or gas) enters the filter medium from the opposite direction of the filter at high pressure, and the reverse fluid pressure is used to flush out impurities and particles from the surface and inside of the filter medium. The backwash high-pressure fluid carries these impurities out of the filter station through the sewage outlet. After the backwash process is completed, the backwash channel is closed, the normal filtration process is restored, and the filter medium is cleaned and put back into use.

[0022] Preferably, before the filtration operation of the high-pressure backwash filter station begins, a pressure sensor installed at the inlet side of the filter element is used to detect and record the fluid pressure at this time as initial pressure information, and a pressure sensor installed at the outlet side of the filter element is used to continuously detect and record the fluid pressure at this time as filtration pressure information. Then, the initial pressure information and the filtration pressure information are used to calculate the pressure difference between the inlet side and the outlet side of the filter element, that is, the filtration pressure difference information, which reflects the change in resistance of the filter element during the operation of the high-pressure backwash filter station. When a certain amount of pollutants accumulate inside the filter element, the normal flow of the fluid will be hindered, resulting in an increase in the pressure on the inlet side and a decrease in the pressure on the outlet side. Based on the filtration pressure difference information, combined with the operating parameters of the filtration station (such as flow rate, temperature, etc.) and the material, structure and other characteristics of the filter element, a pipeline rupture safety risk analysis is carried out, that is, by analyzing the changing trend and fluctuation range of the filtration pressure difference and whether it exceeds the preset safety threshold, it is judged whether there is a safety risk of pipeline rupture. According to the results of the pipeline rupture safety risk analysis, the pipeline rupture probability is obtained as the filtration rupture safety risk information; among them, when the actual filtration pressure difference increases abnormally or exceeds the safety threshold, the early warning mechanism is automatically triggered to remind the operator to take timely intervention measures, such as cleaning or replacing the filter element, adjusting the operating parameters, etc., to prevent the occurrence of safety accidents such as pipeline rupture.

[0023] The filter element clogging analysis module 20 is used to perform clogging analysis on the filter element according to the filter pressure difference information to obtain clogging parameters of the filter element.

[0024] Preferably, the real-time changes of the filter pressure difference are recorded according to the filter pressure difference information analysis, that is, the blockage of the filter element is analyzed. Generally speaking, as the use time of the filter element increases, the filter pressure difference will gradually increase. When the filter pressure difference exceeds the preset safety threshold, it is considered that the filter element is at risk of blockage. The blockage parameters of the filter element are obtained through blockage analysis. Specifically, the blockage parameters mainly include blockage levels, such as blockage levels 1 to 10. The blockage degree of the filter element is evaluated by comparing the difference between the current filter pressure difference and the initial filter pressure difference (or the historical average filter pressure difference). The larger the difference in the filter pressure difference, the more serious the blockage degree and the higher the blockage level; it may also include the blockage speed, blockage position and other blockage-related parameters, such as the blockage frequency, the blockage period, etc., wherein, by analyzing the change trend of the filter pressure difference over time, the blockage speed, that is, the increase in the filter pressure difference per unit time, can be calculated, reflecting the speed of the filter element blockage; in some cases, by analyzing the change of the filter pressure difference at different positions, the location where the blockage occurs can also be roughly determined. For example, if the filter pressure difference in a certain area increases abnormally, it may mean that the filter element in that area is blocked. During the operation of the high-pressure backwash filter station, the operating parameters of the filter station (such as flow rate, pressure, etc.) can be adjusted according to the analysis results of the blockage parameters to slow down the blockage speed and extend the service life of the filter element.

[0025] The backwashing optimization module 30 is used to obtain the backwashing pressure space for backwashing the filter element, and to optimize the backwashing in the backwashing pressure space to maximize the degree of cleaning of the blockage flushing and minimize the probability of damage to the filter element, thereby obtaining the optimal backwashing pressure and the optimal probability of damage to the filter element.

[0026] Preferably, the backwashing pressure space for backwashing the filter element is determined based on factors such as the actual situation of the filter station, the material and characteristics of the filter element, and the properties of the fluid. The backwashing pressure space refers to the range in which the backwashing pressure may vary during the backwashing operation. When determining the backwashing pressure space, ensure that the backwashing pressure does not exceed the pressure limit of the filter element to prevent damage to the element. At the same time, consider the properties of different fluids and the operating parameters of the filter station, such as flow rate, temperature, etc. For example, a high-viscosity fluid requires a higher backwashing pressure to remove pollutants. The greater the backwashing pressure for backwashing the filter element, the greater the degree of cleaning, but the greater the probability of damaging the filter element. Conversely, the smaller the backwashing pressure, the smaller the degree of cleaning, and the smaller the probability of damaging the filter element. Backwashing optimization is performed within the backwashing pressure space to find the optimal The optimal backwashing pressure and the optimal probability of filter element damage, that is, the maximum clogging flushing cleanliness and the minimum probability of filter element damage. Specifically, an initial backwashing pressure is selected in the backwashing pressure space for testing, and the parameters such as the cleanliness of the filter element, flushing time, and flushing water volume during the backwashing process are recorded to evaluate the backwashing effect. The damage probability of the filter element is evaluated by observing and analyzing the state of the filter element after backwashing, such as checking whether the element has cracks, deformation or wear. According to the evaluation results of the backwashing effect and the probability of filter element damage, the backwashing pressure is adjusted for repeated backwashing to find the optimal backwashing pressure and the optimal filter element damage probability that can maximize the clogging flushing cleanliness and minimize the probability of filter element damage within the backwashing pressure space, thereby maximizing the filtration efficiency and minimizing the cost of the high-pressure backwashing filter station.

[0027] The safety risk coefficient acquisition module 40 is used to simulate backwashing according to the optimal backwashing pressure, obtain the flushing pressure difference information, perform pipeline rupture safety risk analysis, obtain flushing rupture safety risk information, combine the filtration rupture safety risk information and the probability of filter element damage, calculate the safety risk coefficient of the high-pressure backwashing filter station, and issue an emergency safety warning.

[0028] Preferably, the optimal backwashing pressure is used to simulate backwashing, and the pressure difference change on both sides of the filter element is monitored and recorded in real time, that is, the flushing pressure difference information is used to reflect the change in the resistance of the filter element during the backwashing process. Then, based on the flushing pressure difference information, combined with the operating parameters of the filter station (such as flow rate, temperature, etc.) and the characteristics of the pipeline material and structure, a pipeline rupture safety risk analysis is performed. For example, by analyzing the change trend and fluctuation range of the flushing pressure difference and whether it exceeds the preset safety threshold, it is determined whether there is a safety risk of pipeline rupture. According to the results of the pipeline rupture safety risk analysis, the flushing rupture safety risk information, that is, the pipeline rupture probability, is obtained. Combined with the filtration rupture safety risk information and the probability of filter element damage, based on multiple factors such as the degree of blockage of the filter element, the stability of the backwashing pressure, and the strength of the pipeline material, the safety risk coefficient of the high-pressure backwashing filter station is calculated to obtain the safety risk coefficient, which reflects the possibility and severity of a safety accident occurring in the filter station under the current operating state. According to the calculation result of the safety risk coefficient, an emergency safety warning is issued, such as early warning intervention by adjusting the backwashing pressure, checking and replacing damaged filter elements, etc., to reduce the probability and severity of accidents and ensure the safe operation of the high-pressure backwashing filter station.

[0029] Furthermore, the specific configuration of the pipeline rupture safety risk analysis module 10 also includes detecting the pressure on both sides of the filter element in the high-pressure backwash filter station to obtain initial pressure information and filtration pressure information; calculating the filtration pressure difference information of the filter element based on the initial pressure information and the filtration pressure information; pre-training a pipeline rupture risk predictor; using the pipeline rupture risk predictor to perform pipeline rupture safety risk analysis and prediction on the filtration pressure difference information input to obtain filtration rupture safety risk information, wherein the filtration rupture safety risk information includes the probability of pipeline rupture.

[0030] Preferably, in the high-pressure backwash filter station, pressure sensors on both sides of the filter element (such as a filter screen or a filter element) are used to detect the pressure before and after the filter element, which are used as initial pressure information and filter pressure information respectively. By comparing the initial pressure information and the filter pressure information, the pressure difference before and after the filter element, i.e., the filter pressure difference information, is calculated, which reflects the resistance of the filter element to the fluid (such as gas or liquid). Then, a prediction model is constructed based on machine learning (such as decision trees, random forests, neural networks, etc.), and the prediction model is trained using historical data (such as past pipeline rupture events and related factor data) to obtain a pipeline rupture risk predictor, which can more accurately predict the future The calculated filter pressure difference information is input into the trained pipeline rupture risk predictor. The pipeline rupture risk predictor performs safety risk analysis and prediction based on the input filter pressure difference information and other possible related factors (such as pipeline material, usage time, environmental factors, etc.), and outputs filter rupture safety risk information. Among them, the most important part of the filter rupture safety risk information is the probability of pipeline rupture. The pipeline rupture probability indicates the possibility of pipeline rupture under current conditions. The pipeline rupture risk predictor predicts and evaluates the pipeline rupture risk, helps to timely discover and deal with potential pipeline rupture risks, and ensures the safe operation of the filter station.

[0031] Furthermore, the specific configuration of the pipeline rupture safety risk analysis module 10 also includes, based on the historical maintenance data of the pipeline in the high-pressure backwash filter station, collecting a set of sample pressure difference information intervals, and collecting the proportion of pipeline ruptures under different sample pressure difference information intervals, marking them as a sample pipeline rupture probability set; constructing the sample pressure difference information interval set and the sample pipeline rupture probability set as supervised training data and verification data, and training the pipeline rupture risk predictor until convergence.

[0032] Preferably, based on the historical maintenance data of the pipeline in the high-pressure backwashing filter station, a sample pressure difference information interval set is collected and a sample pipeline rupture probability set is labeled, and these data are used to train a pipeline rupture risk predictor. Specifically, the pressure difference information of the pipeline is extracted from the historical maintenance data of the high-pressure backwashing filter station, reflecting the pressure change of the fluid inside the pipeline. The extracted pressure difference information is then divided into different intervals according to certain rules, such as the size of the pressure difference and the range of change. The divided pressure difference information intervals are used as a sample pressure difference information interval set, which contains multiple different pressure difference information intervals, each of which represents the pressure state of the pipeline under certain conditions; based on the historical maintenance records, the pipeline rupture events occurring in each pressure difference information interval are found, and each pressure difference information interval is matched with the corresponding pipeline rupture event. For each pressure difference information interval, the proportion of pipeline ruptures in the interval is calculated, and the calculated pipeline rupture proportion is used as a sample pipeline rupture probability set, which contains the pipeline rupture probability corresponding to each pressure difference information interval, for subsequent risk prediction. The sample pressure difference information interval set and the sample pipeline rupture probability set are divided into supervised training data and verification data. A model is constructed based on machine learning models such as logistic regression, decision tree, random forest, support vector machine or neural network. The prediction model is trained using the supervised training data to learn the association between the pressure difference information and the pipeline rupture probability. The trained pipeline rupture risk predictor is verified using the verification data until the performance of the prediction model reaches the preset standard or no longer improves significantly. It is considered that the training process has converged, and a pipeline rupture risk predictor is obtained.

[0033] Further, such as Figure 2 As shown, the specific configuration of the filter element blockage analysis module 20 also includes, based on the historical maintenance data of the filter elements in the high-pressure backwash filter station, collecting a set of sample filter pressure difference information intervals, and collecting the blockage ratios of the filter elements under different sample filter pressure difference information intervals, which are marked as sample blockage parameter sets; constructing a mapping relationship between the sample filter pressure difference information interval set and the sample blockage parameter set to obtain a blockage classifier; inputting the filter pressure difference information into the blockage classifier, mapping and classifying to obtain the blockage parameters of the filter element.

[0034] Preferably, the filtration pressure difference information of the filter element is extracted from the historical maintenance data of the high-pressure backwash filter station, and the extracted filtration pressure difference information is divided into different intervals. The divided filtration pressure difference information intervals are used as a sample filtration pressure difference information interval set, which includes multiple different filtration pressure difference information intervals, each interval represents the filtration state of the filter element under certain conditions, and the filter element blockage events occurring in each filtration pressure difference information interval are found out through the historical maintenance records, and each filtration pressure difference information interval is mapped and matched with the corresponding filter element blockage event. For each filtration pressure difference information interval, the proportion of filter element blockage in the interval is calculated, and the calculated blockage event is used as the filter element blockage event. The blockage ratio is used as a sample blockage parameter set; a mapping relationship between a sample filter pressure difference information interval set and a sample blockage parameter set is constructed, a blockage classifier is constructed based on machine learning (such as decision tree, random forest, support vector machine, etc.), and the sample filter pressure difference information interval set and the sample blockage parameter set are used as training data to train the blockage classifier, and then the filter pressure difference information of the filter element in the current high-pressure backwashing filter station is input into the trained blockage classifier, and the blockage classifier searches for the corresponding blockage parameter in the internal mapping relationship according to the input filter pressure difference information, and outputs the blockage parameter of the filter element through mapping classification, which reflects the blockage state of the current filter element. Further, the specific configuration of the backwashing optimization module 30 also includes obtaining a backwashing pressure space for backwashing the filter element; randomly extracting a first backwashing pressure in the backwashing pressure space; performing a flushing prediction based on the first backwashing pressure and the blockage parameter to obtain a first blockage flushing cleaning level and a first filter element damage probability; and calculating and obtaining a first flushing fitness based on the first blockage flushing cleaning level and the first filter element damage probability, as shown in the following formula: ; Among them, RA is the flushing adaptability, and is the weight, R is the clogging flushing cleaning level, Q is a positive integer, and K is the probability of filter element damage; the backwashing pressure is continuously optimized in the backwashing pressure space until the convergence optimization times are reached, the backwashing pressure with the maximum flushing fitness is output, the optimal backwashing pressure is obtained, and the probability of filter element damage at the optimal backwashing pressure is obtained as the optimal probability of filter element damage.

[0035] Preferably, all possible backwashing pressure values ​​used when backwashing the filter element are used as the backwashing pressure space, and the minimum and maximum backwashing pressure values ​​constitute the boundary of the backwashing pressure space to ensure that the backwashing process is both effective and does not cause excessive damage to the filter element. Then, in the backwashing pressure space, a backwashing pressure value is randomly selected as the first backwashing pressure, and the effect and potential risk of backwashing under this pressure are evaluated, which helps to determine the optimal backwashing pressure value to balance the cleaning effect and the risk of filter element damage; a flushing prediction model is constructed based on machine learning, and the first backwashing pressure and blockage parameters are used as inputs to perform flushing predictions, and output the first blockage flushing cleaning level and the first filter element damage probability, wherein the first blockage flushing cleaning level indicates the degree or efficiency of the filter element blockage being cleared under a given backwashing pressure, and the first filter element damage probability indicates the possibility of damage (such as rupture, deformation, etc.) to the filter element under a given backwashing pressure. Preferably, the first flushing fitness is calculated based on the first blockage flushing cleaning level and the first filter element damage probability, and the calculation formula is as follows: ; Among them, RA is the flushing adaptability, and is the weight, R is the clogging flushing cleaning level, Q is a positive integer, and K is the probability of filter element damage; then the backwashing pressure is optimized in the backwashing pressure space until the convergence optimization times are reached, and the backwashing pressure with the maximum flushing fitness is output as the optimal backwashing pressure, and the probability of filter element damage corresponding to the optimal backwashing pressure is obtained as the optimal probability of filter element damage, thereby achieving a balance between the cleaning effect and the risk of filter element damage.

[0036] Furthermore, the specific configuration of the backwash optimization module 30 also includes, based on the backwash history data of the filter element, collecting a sample blockage parameter set and a sample backwash pressure set, and collecting the blockage flushing cleaning level and the filter element damage ratio under backwashing with different sample blockage parameters and sample backwashing pressures, and marking to obtain a sample blockage flushing cleaning level set and a sample filter element damage probability set; using the sample blockage parameter set, sample backwashing pressure set, sample blockage flushing cleaning level set and sample filter element damage probability set as supervised training data and verification data to train a backwash predictor until convergence; using the backwash predictor to perform flushing prediction on the first backwash pressure and blockage parameter input to obtain a first blockage flushing cleaning level and a first filter element damage probability.

[0037] Preferably, from the backwashing history data of the filter element, the blockage parameters before each backwashing are extracted as a sample blockage parameter set, and the backwashing pressure value used in each backwashing is recorded to form a sample backwashing pressure set. At the same time, the degree or efficiency of the blockage being flushed and cleared during each backwashing is evaluated and recorded, that is, the blockage flushing cleaning level, such as a qualitative classification (such as excellent, good, average, poor), and then the damage of the filter element after each backwashing (including rupture, deformation, wear, etc.), including the number or proportion of damage, is recorded, and then these data are annotated to obtain the sample blockage flushing cleaning level set and the sample filter element damage probability set; using this These sample sets are divided into supervised training data and verification data, and a prediction model is constructed based on machine learning (such as neural networks, decision trees, etc.). The prediction model is trained using the training data to learn the association between the clogging parameters, backwashing pressure, clogging flushing cleaning level, and filter element damage probability, and a backwash predictor is obtained. The trained backwash predictor is verified using the verification data, and then the first backwashing pressure and clogging parameters are input into the trained backwash predictor, and the first clogging flushing cleaning level and the first filter element damage probability are output as prediction results, which is helpful to optimize the backwashing operation and improve the cleaning effect and service life of the filter element.

[0038] Furthermore, the specific configuration of the safety risk factor acquisition module 40 also includes, based on the backwashing history data of the filter element, collecting the pressure difference of the filter element under backwashing with different sample blockage parameters and sample backwashing pressures, and obtaining a sample flushing pressure difference information set; using the sample blockage parameter set, sample backwashing pressure set and sample flushing pressure difference information set to train a backwashing pressure difference simulator; using the backwashing pressure difference simulator to simulate backwashing of the first backwash pressure and blockage parameter to obtain flushing pressure difference information.

[0039] Preferably, the blockage parameters before each backwashing are extracted from the backwashing history data of the filter element, which may include the degree of blockage, the type of blockage material, the blockage distribution, etc., and the backwashing pressure value used in each backwashing is recorded to form a sample backwashing pressure set. When backwashing is performed under different sample blockage parameters and sample backwashing pressures, the pressure difference before and after the filter element is measured and recorded, and compiled into a sample flushing pressure difference information set. A backwashing pressure difference simulator is constructed based on machine learning models such as linear regression, decision tree, and neural network. The sample blockage parameter set, sample backwash pressure set, and sample flushing pressure difference information set collected above are used as training data sets to train the backwashing pressure difference simulator, learn the relationship between the blockage parameters, backwashing pressure, and flushing pressure difference, and obtain the final backwashing pressure difference simulator. Then, the first backwash pressure and blockage parameters are input into the backwashing pressure difference simulator to simulate backwashing. The backwashing pressure difference simulator outputs flushing pressure difference information as a prediction result based on the input parameters. This flushing pressure difference information reflects the change in resistance of the filter element during the backwashing process under given blockage parameters and backwashing pressure.

[0040] Furthermore, the specific configuration of the safety risk coefficient acquisition module 40 also includes: inputting the flushing pressure difference information into the pipeline rupture risk predictor, analyzing and predicting the pipeline rupture safety risk, and obtaining the flushing rupture safety risk information; weighted calculation of the flushing rupture safety risk information, the filtration rupture safety risk information and the probability of filter element damage to obtain the safety risk coefficient of the high-pressure backwashing filter station; judging whether the safety risk coefficient is greater than or equal to the safety risk threshold value, and if so, issuing an emergency safety warning, and if not, not issuing an emergency safety warning.

[0041] Preferably, the flushing pressure difference information obtained from the backwashing pressure difference simulator is input into a trained pipeline rupture risk predictor, which analyzes and predicts the pipeline rupture safety risk based on the input flushing pressure difference information and other possible pipeline parameters (such as pipeline material, wall thickness, working pressure, etc.), and outputs the pipeline rupture safety risk information under a given flushing pressure difference, that is, the flushing rupture safety risk information, which indicates the possibility of pipeline rupture. Different weights are then assigned to the flushing rupture safety risk information, the filtration rupture safety risk information, and the probability of filter element damage. These weights are used to perform weighted calculations on the flushing rupture safety risk information, the filtration rupture safety risk information, and the probability of filter element damage to obtain a high pressure backwashing safety risk information. The safety risk coefficient of the flushing filter station reflects the overall safety risk level of the high-pressure backwashing filter station under the current operating conditions; the calculated safety risk coefficient is compared with a preset safety risk threshold value. If the safety risk coefficient is greater than or equal to the safety risk threshold value, it indicates that the safety risk under the current operating conditions is high and an emergency safety warning is required immediately, such as stopping the backwashing operation, reducing the working pressure, checking and repairing potential safety hazards, etc.; if the safety risk coefficient is less than the safety risk threshold value, it indicates that the safety risk under the current operating conditions is within an acceptable range and no emergency safety warning is required; among them, the safety risk threshold value is set according to the safety standards and acceptable risk level of the high-pressure backwashing filter station.

[0042] Although the present application makes various references to certain components in the platform according to the embodiments of the present application, any number of different components can be used and run on the user terminal and / or server, and the various units and components included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention. The above specific implementation methods do not constitute limitations on the scope of protection of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the scope of protection of this application.

Claims

1. An emergency safety warning platform for special scenarios, characterized in that: The platform includes: The pipeline rupture safety risk analysis module is used to detect the pressure on both sides of the filter element in the high-pressure backwashing filter station during the operation of the high-pressure backwashing filter station, obtain the initial pressure information and the filtering pressure information, calculate the filtering pressure difference information, perform pipeline rupture safety risk analysis, and obtain the filtering rupture safety risk information; A filter element clogging analysis module, used to perform clogging analysis of the filter element according to the filter pressure difference information to obtain clogging parameters of the filter element; A backwashing optimization module is used to obtain a backwashing pressure space for backwashing the filter element, and to optimize the backwashing in the backwashing pressure space to maximize the degree of cleaning of the blockage flushing and minimize the probability of damage to the filter element, thereby obtaining an optimal backwashing pressure and an optimal probability of damage to the filter element; The safety risk coefficient acquisition module is used to simulate backwashing according to the optimal backwashing pressure, obtain the flushing pressure difference information, perform pipeline rupture safety risk analysis, obtain flushing rupture safety risk information, combine the filtration rupture safety risk information and the probability of filter element damage, calculate the safety risk coefficient of the high-pressure backwashing filter station, and issue an emergency safety warning.

2. The emergency safety warning platform for special scenarios according to claim 1 is characterized in that: The pressure on both sides of the filter element in the high-pressure backwash filter station is detected to obtain initial pressure information and filter pressure information, filter pressure difference information is calculated, pipeline rupture safety risk analysis is performed, and filter rupture safety risk information is obtained, including: Detecting the pressure on both sides of the filter element in the high-pressure backwash filter station to obtain initial pressure information and filtering pressure information; Calculating and obtaining the filtering pressure difference information of the filtering element according to the initial pressure information and the filtering pressure information; Pre-trained pipeline rupture risk predictor; The pipeline rupture risk predictor is used to perform pipeline rupture safety risk analysis and prediction on the filter pressure difference information input to obtain filter rupture safety risk information, wherein the filter rupture safety risk information includes the probability of pipeline rupture.

3. The emergency safety warning platform for special scenarios according to claim 2 is characterized in that: Pre-trained pipeline rupture risk predictor, including: According to the historical maintenance data of the pipeline in the high-pressure backwash filter station, a set of sample pressure difference information intervals is collected, and the proportion of pipeline rupture in different sample pressure difference information intervals is collected and marked as a sample pipeline rupture probability set; The sample pressure difference information interval set and the sample pipeline rupture probability set are constructed as supervised training data and verification data, and the pipeline rupture risk predictor is trained until convergence.

4. The emergency safety warning platform for special scenarios according to claim 1 is characterized in that: According to the filter pressure difference information, the filter element clogging analysis is performed to obtain the clogging parameters of the filter element, including: According to the historical maintenance data of the filter elements in the high-pressure backwash filter station, a set of sample filter pressure difference information intervals is collected, and the blockage ratio of the filter elements under different sample filter pressure difference information intervals is collected and marked as a sample blockage parameter set; Constructing a mapping relationship between the sample filtering pressure difference information interval set and the sample blocking parameter set to obtain a blocking classifier; The filter pressure difference information is input into the blockage classifier, and the blockage parameter of the filter element is obtained by mapping and classifying.

5. The emergency safety warning platform for special scenarios according to claim 1 is characterized in that: A backwashing pressure space for backwashing the filter element is obtained, and backwashing optimization is performed in the backwashing pressure space to maximize the degree of flushing cleaning and minimize the probability of damage to the filter element, including: Acquire a backwashing pressure space for backwashing the filter element; In the backwash pressure space, randomly extracting a first backwash pressure; According to the first backwashing pressure and the clogging parameter, a flushing prediction is performed to obtain a first clogging flushing cleaning level and a first filter element damage probability; according to the first clogging flushing cleaning level and the first filter element damage probability, a first flushing fitness is calculated, as shown in the following formula: ; Among them, RA is the flushing adaptability, and is the weight, R is the clogging flushing cleaning level, Q is a positive integer, and K is the probability of filter element damage; the backwashing pressure is continuously optimized in the backwashing pressure space until the convergence optimization times are reached, the backwashing pressure with the maximum flushing fitness is output, the optimal backwashing pressure is obtained, and the probability of filter element damage at the optimal backwashing pressure is obtained as the optimal probability of filter element damage.

6. The emergency safety warning platform for special scenarios according to claim 5 is characterized in that: According to the first backwashing pressure and the blockage parameter, a flushing prediction is performed, including: According to the backwashing history data of the filter element, a sample blockage parameter set and a sample backwashing pressure set are collected, and the blockage flushing cleaning level and the filter element damage ratio under backwashing with different sample blockage parameters and sample backwashing pressures are collected, and the sample blockage flushing cleaning level set and the sample filter element damage probability set are obtained by annotation; Using the sample clogging parameter set, the sample backwashing pressure set, the sample clogging flushing cleaning level set and the sample filter element damage probability set as supervised training data and verification data, training the backwash predictor until convergence; The backwash predictor is used to perform a backwash prediction on the first backwash pressure and the clogging parameter input to obtain a first clogging flushing cleaning level and a first filter element damage probability.

7. The emergency safety warning platform for special scenarios according to claim 5, characterized in that: Performing simulated backwashing according to the optimal backwashing pressure to obtain backwashing pressure difference information includes: According to the backwashing history data of the filter element, the pressure difference of the filter element under backwashing with different sample clogging parameters and sample backwashing pressures is collected to obtain a sample flushing pressure difference information set; Using the sample blockage parameter set, the sample backwash pressure set and the sample flushing pressure difference information set, training a backwash pressure difference simulator; The backwashing differential pressure simulator is used to simulate backwashing of the first backwashing pressure and the blockage parameter to obtain the backwashing differential pressure information.

8. The emergency safety warning platform for special scenarios according to claim 3 is characterized in that: Conduct pipeline rupture safety risk analysis to obtain flushing rupture safety risk information, combine the filtration rupture safety risk information and the probability of filter element damage, and calculate the safety risk factor of the high-pressure backwashing filter station, including: The flushing pressure difference information is input into the pipeline rupture risk predictor, and the pipeline rupture safety risk is analyzed and predicted to obtain flushing rupture safety risk information; A weighted calculation is performed on the flushing rupture safety risk information, the filtering rupture safety risk information and the probability of filter element damage to obtain a safety risk coefficient for the high-pressure backwashing filter station; a determination is made as to whether the safety risk coefficient is greater than or equal to a safety risk threshold value, if so, an emergency safety warning is issued, if not, no emergency safety warning is issued.

Images