A safety early warning method and system based on transient pressure monitoring of pipe network

Abstract

The application relates to the technical field of pipe networks, and provides a safety early warning method and system based on pipe network transient pressure monitoring, which comprises the following steps: acquiring first data; calculating second data according to the first data, wherein the second data comprises transient pressure of a preset position at a future time; judging a first danger score of the preset position at the future time according to the transient pressure of the preset position at the future time; acquiring third data, wherein the third data is environmental information of a pipe network at the future time, and the environmental information comprises geographical position information, seasonal information and temperature information; inputting the environmental information into a pre-trained danger score model to obtain a second danger score of the preset position at the future time; obtaining a final danger score according to the first danger score and the second danger score; and performing early warning according to the final danger score. The method can be used for more accurate early warning processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipe network, in particular to a safety early warning method and system based on pipe network transient pressure monitoring. BACKGROUND

[0002] At present, the normal operation of the pipe network is very important to the life of residents, and at present, the staff is often sent to repair after the pipe network fails, which cannot solve the problem in time, and the life of residents will be inevitably affected, so we need to closely monitor the operation state of the pipe network, and perform early warning processing according to the predicted operation data, so as to reduce the influence on the life of residents. SUMMARY

[0003] The purpose of the present application is to provide a safety early warning method and system based on pipe network transient pressure monitoring to improve the above problems.

[0004] In order to achieve the above purpose, the embodiments of the present application provide the following technical scheme:

[0005] On the one hand, the present application provides a safety early warning method based on pipe network transient pressure monitoring, which comprises:

[0006] Obtaining first data, the first data comprising transient pressure at a preset position at different historical time points within a preset historical period;

[0007] Calculating second data according to the first data, the second data comprising transient pressure of the preset position at a future time point; judging a first risk score of the preset position at the future time point according to the transient pressure of the preset position at the future time point;

[0008] Obtaining third data, the third data being environmental information of the pipe network at the future time point, the environmental information comprising geographical position information, seasonal information and temperature information;

[0009] Inputting the environmental information into a pre-trained risk score model to obtain a second risk score of the preset position at the future time point, obtaining a final risk score according to the first risk score and the second risk score, and performing early warning according to the final risk score.

[0010] Secondly, the present application provides a safety early warning system based on pipe network transient pressure monitoring, which comprises a first obtaining module, a calculating module, a second obtaining module and a predicting module.

[0011] The first obtaining module is used for obtaining first data, the first data comprising transient pressure at a preset position at different historical time points within a preset historical period;

[0012] a calculation module configured to calculate second data according to the first data, the second data comprising transient pressure of the preset position at a future time; and determine a first danger score of the preset position at the future time according to the transient pressure of the preset position at the future time;

[0013] a second acquisition module configured to acquire third data, the third data being environmental information of the pipe network at the future time, the environmental information comprising geographic position information, seasonal information and temperature information;

[0014] a prediction module configured to input the environmental information into a pre-trained danger score model to obtain a second danger score of the preset position at the future time, obtain a final danger score according to the first danger score and the second danger score, and perform early warning according to the final danger score.

[0015] In a third aspect, an embodiment of the present application provides a safety early warning device based on pipe network transient pressure monitoring, the device comprising a memory and a processor. The memory is configured to store a computer program; and the processor is configured to execute the computer program to implement the steps of the safety early warning method based on pipe network transient pressure monitoring.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, the readable storage medium storing a computer program, the computer program being executed by a processor to implement the steps of the safety early warning method based on pipe network transient pressure monitoring.

[0017] The present application has the following beneficial effects:

[0018] 1. In the present application, whether the transient pressure at the future time is abnormal is considered, and the difficulty level of maintenance at the future time is also considered. The method in the present application can perform early warning processing more accurately compared with only using one factor or performing early warning by an artificial method.

[0019] 2. In the present application, the transient pressure at the future time is predicted according to the transient pressure at the preset position at different historical times, and the threshold range is determined according to the transient pressure at the preset position at different historical times. The transient pressure at the future time can be dynamically predicted according to the predicted transient pressure and the threshold range. Then, considering that if a fault occurs, maintenance is needed, and the progress of maintenance can be related to geographic position information, seasonal information and temperature information, some information related to maintenance is acquired in the present application, and then the corresponding second danger score at the future time can be quickly identified through the constructed model. Finally, the final score obtained according to the first danger score and the second danger score can better reflect the rigor and accuracy of early warning.

[0020] Other features and advantages of the present application will be set forth in the descriptions that follow, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0022] Figure 1 is a flow diagram of the safety early warning method based on transient pressure monitoring of pipe network described in the embodiments of the present application;

[0023] Figure 2 is a structural diagram of the safety early warning system based on transient pressure monitoring of pipe network described in the embodiments of the present application;

[0024] Figure 3 is a structural diagram of the safety early warning device based on transient pressure monitoring of pipe network described in the embodiments of the present application. DETAILED DESCRIPTION

[0025] In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art without creative labor on the basis of the embodiments in the present application belong to the scope of protection of the present application.

[0026] It should be noted that: similar reference numerals or letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0027] Embodiment 1

[0028] As Figure 1As shown, the embodiment provides a safety warning method based on transient pressure monitoring of pipe network, which comprises steps S1, S2, S3 and S4.

[0029] Step S1, obtaining first data, wherein the first data comprises transient pressure at a preset position at different historical time points within a preset historical period;

[0030] In this step, the preset historical period can be the past one month, the past three months or the past half year; meanwhile, the preset position in this step can be artificially set, for example, the position of the pipe network where frequent failures occur can be artificially selected as the preset position;

[0031] Step S2, calculating second data according to the first data, wherein the second data comprises transient pressure of the preset position at a future time point; judging a first risk score of the preset position at the future time point according to the transient pressure of the preset position at the future time point;

[0032] In this step, the future data is predicted by using the historical data, and the corresponding risk score is calculated according to the predicted value, so that the transient pressure at the future time point can be monitored and judged, and the specific implementation steps include steps S21 and S22;

[0033] Step S21, processing the first data by using the least square method to obtain a trend equation, and obtaining trend values corresponding to different historical time points based on the trend equation and the first data;

[0034] In this step, in addition to the least square method, other trend equations can also be used;

[0035] Step S22, subtracting the transient pressure corresponding to different historical time points from the trend values to obtain difference results corresponding to different historical time points, calculating a threshold range of the preset position at the future time point according to the difference results, and calculating the first risk score according to the transient pressure of the preset position at the future time point and the threshold range of the preset position at the future time point.

[0036] The specific implementation steps of this step include steps S221 and S222;

[0037] Step S221, performing mean and variance calculation on all difference results to sequentially obtain fourth data and fifth data, performing summation processing on the fourth data and the fifth data to obtain sixth data; obtaining seventh data based on the trend equation, wherein the seventh data comprises a first transient pressure at a future time point;

[0038] In this step, the seventh data is obtained based on the trend equation, specifically, the future time is brought into the trend equation, and the first transient pressure at the future time is obtained.

[0039] In step S222, the seventh data and the sixth data are summed and subtracted respectively to obtain eighth data and ninth data, and the numerical interval formed by the eighth data and the ninth data is a threshold range; the first data is denoised by using a Kalman filtering algorithm, a difference autoregressive moving average prediction model is constructed according to the denoised data, the transient pressure at the future time is predicted by using the difference autoregressive moving average prediction model, it is judged whether the transient pressure falls within the threshold range, a judgment result is obtained, and a corresponding first risk score is obtained according to the judgment result.

[0040] In this step, the threshold at the future time is dynamically generated in real time by the transient pressures corresponding to different historical times, which eliminates the process of manually setting the threshold, and compared with the way of manually setting the threshold range, the method in this step is more accurate; after generating the threshold range, the transient pressure at the future time is predicted by using other prediction methods, and finally it is judged whether the transient pressure falls within the threshold range, wherein a scoring system can be constructed, and there is a corresponding score for falling within the threshold range and a corresponding score for not falling within the threshold range, so that the first risk score can be obtained;

[0041] In step S3, third data is obtained, the third data being environmental information of the pipe network at the future time, and the environmental information including geographic location information, seasonal information and temperature information.

[0042] In this step, in addition to considering the transient pressure at the future time, it is also considered that if the transient pressure is too large, a fault may occur, and maintenance is needed when a fault occurs, and the maintenance process is related to the geographic location information, seasonal information and temperature information of the pipe network, for example, if the geographic location is too remote, the maintenance time may be longer, for example, in summer, water is used more frequently, so timely maintenance is definitely needed, and the maintenance needs more effort, for example, at low temperature, the maintenance progress may be relatively slow, therefore, when maintenance is needed, the geographic location information, seasonal information and temperature information need to be considered.

[0043] The temperature information at the future time can be obtained by a conventional weather prediction method.

[0044] In step S4, the environmental information is input into a pre-trained risk score model to obtain a second risk score of the preset position at the future time, a final risk score is obtained according to the first risk score and the second risk score, and a warning is given according to the final risk score.

[0045] In this step, the second risk score can be understood as a maintenance difficulty score, and finally a final score is obtained according to the first risk score and the second risk score. Specifically, the first risk score and the second risk score can be pre-set weights, and finally a weighted sum is obtained to obtain a final risk score. After obtaining the final risk score, the final risk score can be compared with the pre-set risk score threshold value. For example, if it is greater than the pre-set risk score threshold value, a warning is given. At the same time, the final risk score and the pre-set risk score threshold value can also be calculated by difference, and the warning level is determined according to the difference calculation result. Different warning methods are selected according to different warning levels to give a warning. The specific implementation steps of this step include step S41.

[0046] Step S41, obtain a plurality of historical environment information, and mark the risk score of each historical environment information. After marking, each historical environment information is taken as a sample, and all samples are divided into a first training set and a second training set. The first training set is used to train the convolutional neural network model to obtain a first model. Each historical environment information in the second training set is input into the first model to obtain a predicted value corresponding to each historical environment information. The second risk score of the preset position at a future time is obtained according to the predicted value corresponding to each historical environment information and the first model.

[0047] The specific implementation steps of this step include steps S411 and S412.

[0048] Step S411, in the second training set, all historical environment information corresponding to the same risk score is collected to obtain a data set. The maximum value in the data set is recorded as the tenth data. The predicted values corresponding to all historical environment information in the data set are calculated by mean value to obtain the eleventh data. The eleventh data and the data set are collected, and the maximum value in the collection is selected as the twelfth data.

[0049] Step S412, the tenth data and the twelfth data are summed to obtain the thirteenth data. The risk score prediction error value is obtained according to the thirteenth data and a pre-set formula. The risk score prediction error value is used to adjust the parameters of the first model. When the pre-set stopping condition is reached, the parameter adjustment is stopped, the risk score model is obtained, and the environment information is input into the risk score model to obtain the second risk score of the preset position at a future time.

[0050] In this step, the pre-set formula is:

[0051] t;(1)

[0052] (2)

[0053] In the formula (1) and the formula (2), p is the tenth data; t is the thirteenth data; F is a dangerous score prediction error value, n is the number of dangerous scores entering the model in the current iteration round, i is the serial number of the dangerous score entering the model in the current iteration round, w is the eleventh data, and d is a dangerous score corresponding to the eleventh data; n can be understood as follows: if 20 different dangerous scores are contained in the current iteration round, then n is 20, that is, there are L different dangerous scores, and then n is equal to L; the dangerous score corresponding to the eleventh data can be understood as follows: "collect all historical environmental information corresponding to the same dangerous score to obtain a data set, record the maximum value in the data set as the tenth data, and calculate the mean value of the prediction values of all historical environmental information in the data set to obtain the eleventh data"; it can be concluded from the above that each dangerous score corresponds to an eleventh data.

[0054] Meanwhile, in this step, the stop condition can be that the dangerous score prediction error value is less than a preset dangerous score prediction error value threshold.

[0055] In this embodiment, firstly, the transient pressure at the preset position at different historical moments is used to predict the transient pressure at the future moment, and the transient pressure at the preset position at different historical moments is used to determine the threshold range, so that the transient pressure at the future moment can be dynamically predicted according to the predicted transient pressure and the threshold range; then, considering that if a fault occurs, maintenance needs to be performed, and the progress of the maintenance can be related to geographical location information, seasonal information and temperature information, therefore, some information related to the maintenance is obtained in this embodiment, and then the corresponding second dangerous score at the future moment can be quickly identified through the constructed model; finally, according to the first dangerous score and the second dangerous score, the final score obtained can better reflect the rigor and accuracy of the early warning.

[0056] Embodiment 2

[0057] As shown in Figure 2 The embodiment provides a safety early warning system based on transient pressure monitoring of a pipe network, and the system comprises a first acquisition module 701, a calculation module 702, a second acquisition module 703 and a prediction module 704.

[0058] The first acquisition module 701 is used for acquiring first data, and the first data comprises transient pressures at a preset position at different historical moments within a preset historical period.

[0059] The calculation module 702 is used for calculating second data according to the first data, and the second data comprises a transient pressure of the preset position at a future moment; and a first dangerous score of the preset position at the future moment is judged according to the transient pressure of the preset position at the future moment.

[0060] The second acquisition module 703 is configured to acquire third data, the third data being environment information of the pipe network at the future moment, the environment information including geographical position information, seasonal information and temperature information.

[0061] The prediction module 704 is configured to input the environment information into a pre-trained danger score model to obtain a second danger score of the preset position at the future moment, obtain a final danger score according to the first danger score and the second danger score, and perform early warning according to the final danger score.

[0062] In an embodiment of the present disclosure, the calculation module 702 further includes a first calculation unit 7021 and a second calculation unit 7022.

[0063] The first calculation unit 7021 is configured to process the first data by using a least square method to obtain a trend equation, and obtain trend values corresponding to different historical moments based on the trend equation and the first data.

[0064] The second calculation unit 7022 is configured to subtract the transient pressure corresponding to different historical moments from the trend values to obtain difference results corresponding to different historical moments, calculate a threshold range of the preset position at the future moment according to the difference results, and calculate the first danger score according to the transient pressure of the preset position at the future moment and the threshold range of the preset position at the future moment.

[0065] In an embodiment of the present disclosure, the second calculation unit 7022 further includes a third calculation unit 70221 and a fourth calculation unit 70222.

[0066] The third calculation unit 70221 is configured to perform mean and variance calculation on all the difference results to sequentially obtain fourth data and fifth data, perform summation processing on the fourth data and the fifth data to obtain sixth data, obtain seventh data based on the trend equation, and the seventh data including a first transient pressure at the future moment.

[0067] The fourth calculation unit 70222 is configured to perform summation and difference calculation on the seventh data and the sixth data respectively to obtain eighth data and ninth data, the numerical interval formed by the eighth data and the ninth data being a threshold range, perform denoising processing on the first data by using a Kalman filtering algorithm, construct a difference autoregressive moving average prediction model according to the denoised data, predict the transient pressure at the future moment by using the difference autoregressive moving average prediction model, judge whether the transient pressure falls within the threshold range to obtain a judgment result, and obtain the corresponding first danger score according to the judgment result.

[0068] In an embodiment of the present disclosure, the prediction module 704 further comprises an acquisition unit 7041.

[0069] The acquisition unit 7041 is configured to acquire a plurality of historical environment information, perform dangerous score labeling on each of the historical environment information, take each of the historical environment information as a sample after the labeling, divide all the samples into a first training set and a second training set, train a convolutional neural network model by using the first training set to obtain a first model, input each of the historical environment information in the second training set into the first model to obtain a prediction value corresponding to each of the historical environment information, and obtain a second dangerous score of the preset position at a future time according to the prediction value corresponding to each of the historical environment information and the first model.

[0070] In an embodiment of the present disclosure, the acquisition unit 7041 further comprises a collection unit 70411 and a fifth calculation unit 70412.

[0071] The collection unit 70411 is configured to collect all the historical environment information corresponding to a same dangerous score in the second training set to obtain a data set, take a maximum value in the data set as a tenth data, perform mean value calculation on the prediction values of all the historical environment information in the data set to obtain an eleventh data, and collect the eleventh data and the data set to select a maximum value in the collection as a twelfth data.

[0072] The fifth calculation unit 70412 is configured to perform summation processing on the tenth data and the twelfth data to obtain a thirteenth data, obtain a dangerous score prediction error value according to the thirteenth data and a preset formula, perform parameter adjustment on the first model by using the dangerous score prediction error value, stop the parameter adjustment when a preset stop condition is reached, obtain a dangerous score model, input the environment information into the dangerous score model to obtain the second dangerous score of the preset position at the future time.

[0073] It should be noted that, as to the system in the above embodiments, the specific manner in which each module performs an operation has been described in detail in the embodiments of the method, and will not be described in detail here.

[0074] Embodiment 3

[0075] Corresponding to the above method embodiments, the present disclosure also provides a safety warning device based on pipe network transient pressure monitoring. The safety warning device based on pipe network transient pressure monitoring described below can be mutually corresponding and referred to the safety warning method based on pipe network transient pressure monitoring described above.

[0076] Figure 3is a block diagram of a safety warning device 800 based on pipe network transient pressure monitoring according to an exemplary embodiment. As shown Figure 3 The safety warning device 800 based on pipe network transient pressure monitoring can include a processor 801, a memory 802, as shown. The safety warning device 800 based on pipe network transient pressure monitoring can also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0077] The processor 801 is configured to control overall operation of the safety warning device based on transient pressure monitoring of pipe network 800 to accomplish all or part of the steps in the safety warning method based on transient pressure monitoring of pipe network described above. The memory 802 is configured to store various types of data to support the operation of the safety warning device based on transient pressure monitoring of pipe network 800, which may, for example, include instructions for any application or method operating on the safety warning device based on transient pressure monitoring of pipe network 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen may, for example, be a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to enable wired or wireless communication between the safety warning device based on transient pressure monitoring of pipe network 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0078] In an example embodiment, the safety warning device 800 based on transient pressure monitoring of pipe network can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the safety warning method based on transient pressure monitoring of pipe network described above.

[0079] In another example embodiment, a computer readable storage medium including program instructions that, when executed by a processor, implement the steps of the safety warning method based on transient pressure monitoring of pipe network described above is also provided. For example, the computer readable storage medium can be the memory 802 described above including program instructions executable by the processor 801 of the safety warning device 800 based on transient pressure monitoring of pipe network to complete the safety warning method based on transient pressure monitoring of pipe network described above.

[0080] Embodiment 4

[0081] Corresponding to the method embodiments above, the embodiments of the present disclosure also provide a readable storage medium, which can be referred to each other below and above in the description of the safety warning method based on transient pressure monitoring of pipe network.

[0082] A readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the steps of the safety warning method based on transient pressure monitoring of pipe network of the method embodiments described above.

[0083] The readable storage medium can be specifically a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0084] The above only describes preferred embodiments of the present disclosure and is not used to limit the present disclosure. For those skilled in the art, the present disclosure can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A safety early warning method based on pipe network transient pressure monitoring, characterized in that, The method comprises the following steps: acquiring first data, the first data comprising transient pressure at a preset location at different historical time points within a preset historical period; calculating second data according to the first data, the second data comprising transient pressure of the preset location at a future time point; judging a first risk score of the preset location at the future time point according to the transient pressure of the preset location at the future time point; acquiring third data, the third data being environmental information of a pipe network at the future time point, the environmental information comprising geographical position information, seasonal information and temperature information; inputting the environmental information into a pre-trained risk score model to obtain a second risk score of the preset location at the future time point, obtaining a final risk score according to the first risk score and the second risk score, and performing early warning according to the final risk score; calculating second data according to the first data, the second data comprising transient pressure of the preset location at a future time point; judging a first risk score of the preset location at the future time point according to the transient pressure of the preset location at the future time point, comprising: processing the first data by using a least square method to obtain a trend equation, and obtaining trend values corresponding to different historical time points based on the trend equation and the first data; subtracting the transient pressure corresponding to different historical time points from the trend values to obtain difference results corresponding to different historical time points, calculating a threshold range of the preset location at the future time point according to the difference results, and calculating the first risk score according to the transient pressure of the preset location at the future time point and the threshold range of the preset location at the future time point; calculating a threshold range of the preset location at the future time point according to the difference results, and calculating the first risk score according to the transient pressure of the preset location at the future time point and the threshold range of the preset location at the future time point, comprising: performing mean and variance calculation on all the difference results to sequentially obtain fourth data and fifth data, performing summation processing on the fourth data and the fifth data to obtain sixth data, obtaining seventh data based on the trend equation, the seventh data comprising a first transient pressure at the future time point; performing summation and difference calculation on the seventh data and the sixth data respectively to obtain eighth data and ninth data, the eighth data and the ninth data forming a threshold range; performing denoising processing on the first data by using a Kalman filtering algorithm, constructing a difference autoregressive moving average prediction model according to the denoised data, predicting transient pressure at the future time point by using the difference autoregressive moving average prediction model, judging whether the transient pressure falls within the threshold range to obtain a judgment result, and obtaining the corresponding first risk score according to the judgment result.

2. The safety warning method based on pipe network transient pressure monitoring according to claim 1, characterized in that, inputting the environmental information into a pre-trained risk score model to obtain a second risk score of the preset location at the future time point, comprising: The plurality of historical environment information is obtained, each historical environment information is marked with a danger score, each historical environment information after marking is taken as a sample, all samples are divided into a first training set and a second training set, the first training set is used to train a convolutional neural network model to obtain a first model; each historical environment information in the second training set is input into the first model to obtain a predicted value corresponding to each historical environment information; and a second danger score of the preset position at a future time is obtained according to the predicted value corresponding to each historical environment information and the first model.

3. The safety warning method based on pipe network transient pressure monitoring according to claim 2, characterized in that, The second danger score of the preset position at the future time is obtained according to the predicted value corresponding to each historical environment information and the first model, comprising: In the second training set, all historical environment information corresponding to the same danger score is collected to obtain a data set, a maximum value in the data set is recorded as a tenth data, and a mean value of the predicted values of all historical environment information in the data set is calculated to obtain an eleventh data; the eleventh data and the data set are collected, and a maximum value in the collection is selected as a twelfth data; The tenth data and the twelfth data are summed to obtain a thirteenth data, a danger score prediction error value is obtained according to the thirteenth data and a preset formula, the first model is parameter adjusted by using the danger score prediction error value, and when a preset stop condition is reached, the parameter adjustment is stopped to obtain the danger score model; the environment information is input into the danger score model to obtain the second danger score of the preset position at the future time.

4. A safety warning system based on transient pressure monitoring of a pipe network, characterized in that, Comprising: The first acquisition module is configured to acquire first data, wherein the first data comprises transient pressure at a preset position at different historical times within a preset historical period; The calculation module is configured to calculate second data according to the first data, wherein the second data comprises transient pressure of the preset position at a future time; The first danger score of the preset position at the future time is determined according to the transient pressure of the preset position at the future time; The second acquisition module is configured to acquire third data, wherein the third data is environment information of a pipe network at the future time, and the environment information comprises geographic location information, seasonal information and temperature information; The prediction module is configured to input the environment information into a pre-trained danger score model to obtain a second danger score of the preset position at the future time, to obtain a final danger score according to the first danger score and the second danger score, and to perform early warning according to the final danger score; The calculation module comprises: The first calculation unit is configured to process the first data by using a least square method to obtain a trend equation, and to obtain trend values corresponding to different historical times based on the trend equation and the first data; The second calculation unit is configured to subtract the transient pressure corresponding to different historical moments from the trend value to obtain a difference result corresponding to different historical moments, calculate a threshold range of the preset position at a future moment according to the difference result, and calculate the first risk score according to the transient pressure of the preset position at the future moment and the threshold range of the preset position at the future moment. The second calculation unit comprises: The third calculation unit is configured to perform mean and variance calculation on all the difference results to sequentially obtain fourth data and fifth data, perform summation processing on the fourth data and the fifth data to obtain sixth data, obtain seventh data based on the trend equation, and the seventh data comprises the first transient pressure at the future moment. The fourth calculation unit is configured to perform summation and difference calculation on the seventh data and the sixth data respectively to obtain eighth data and ninth data, a numerical interval formed by the eighth data and the ninth data is a threshold range, perform denoising processing on the first data by using a Kalman filtering algorithm, construct a difference autoregressive moving average prediction model according to the denoised data, predict the transient pressure at the future moment by using the difference autoregressive moving average prediction model, judge whether the transient pressure falls within the threshold range to obtain a judgment result, and obtain the corresponding first risk score according to the judgment result.

5. The safety warning system based on transient pressure monitoring of pipe network according to claim 4, characterized in that, The prediction module comprises: The acquisition unit is configured to acquire a plurality of historical environment information, perform risk score labeling on each historical environment information, take each historical environment information as a sample after labeling, divide all the samples into a first training set and a second training set, train a convolutional neural network model by using the first training set to obtain a first model, input each historical environment information in the second training set into the first model to obtain a prediction value corresponding to each historical environment information, and obtain a second risk score of the preset position at a future moment according to the prediction value corresponding to each historical environment information and the first model.

6. The safety warning system based on transient pressure monitoring of pipe network according to claim 5, characterized in that, The acquisition unit comprises: The set unit is configured to set all historical environment information corresponding to the same risk score in the second training set to obtain a data set, take a maximum value in the data set as tenth data, perform mean calculation on prediction values of all historical environment information in the data set to obtain eleventh data, and set the eleventh data and the data set to obtain a maximum value in the set as twelfth data. The fifth calculation unit is configured to perform summation processing on the tenth data and the twelfth data to obtain thirteenth data, obtain a risk score prediction error value according to the thirteenth data and a preset formula, adjust parameters of the first model by using the risk score prediction error value, stop parameter adjustment when a preset stop condition is reached, obtain a risk score model, and input the environment information into the risk score model to obtain the second risk score of the preset position at the future moment.

Images