A fire hydrant consumable parts life cycle detection system
By designing a life cycle detection system for consumable parts in the fire hydrant, using the prediction curve to predict the remaining time of consumable parts and generating an alarm signal, the problem of difficult to predict the life of consumable parts in the existing technology is solved, and the reliability of the use of the fire hydrant is improved and fire extinguishing effect.
Patent Information
- Application Number
- CN202410878034.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-02
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-07-02
AI Technical Summary
It is difficult for existing fire hydrant systems to effectively predict the service life of each fire hydrant component through the use of fire hydrant components, resulting in abnormalities that may occur during the use of fire hydrant, which will affect the fire extinguishing effect.
A life cycle detection system for fire hydrant consumable parts is designed, including a central processing module, a data acquisition module, an early warning module and a database. By obtaining the data of the consumable parts and the current use of the fire hydrant, a prediction curve is generated, the remaining working time and idle time of the consumable parts are predicted, and an alarm signal is generated based on the prediction results.
The life expectancy of fire hydrant wearable parts is achieved, and relevant personnel are promptly reminded to repair or replace them, avoid abnormal situations during use of fire hydrants and improve the fire extinguishing effect.
Smart Images

Figure CN118505206B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of fire protection and relates to fire protection technology, specifically a life cycle detection system for fire hydrant consumable parts. Background Art
[0002] The prior art (invention patent with announcement number CN111375166B) discloses a smart fire hydrant control method, including: the server determines the fire hydrant to be selected according to the current position of the firefighter and the pre-stored fire hydrant position information; the server activates the fire hydrant to be selected and receives the water pressure information of the fire hydrant to be selected; the server allocates a counter for each fire hydrant to be selected; the server determines whether the water pressure information sent by each fire hydrant to be selected is consistent with the preset standard water pressure information; the alarm level is determined according to the degree and duration of the water pressure value of the fire hydrant to be selected being lower than the standard water pressure threshold; the preferred strength of non-abnormal fire hydrants and fire hydrants without feedback is calculated, and the fire hydrant with the largest preferred strength is determined; the server determines the fire hydrant with the largest preferred strength as the selected fire hydrant, and sends the navigation information of the selected fire hydrant to the firefighter. The beneficial effect of the present invention is that the selection of smart fire hydrants at the fire extinguishing site is more accurate.
[0003] The above-mentioned fire hydrant control system selects a candidate fire hydrant according to the position of the firefighter, determines whether the fire hydrant is abnormal according to the current water pressure of the fire hydrant, and selects the optimal fire hydrant; the above-mentioned selection of the optimal fire hydrant only determines whether the fire hydrant is abnormal according to the water pressure, and it is difficult to predict the service life of each component of the fire hydrant according to the usage of the components of the fire hydrant, which may lead to abnormalities during the use of the fire hydrant, and then lead to poor fire extinguishing effect.
[0004] Therefore, a fire hydrant wearing parts life cycle detection system is needed. Summary of the invention
[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a fire hydrant consumable parts life cycle detection system, which is used to solve the technical problem that the existing fire hydrant system is difficult to predict the service life of each component of the fire hydrant through the usage of the fire hydrant components. The present application solves the above problem by predicting the life of each consumable part of the current fire hydrant based on the consumable parts data and the current usage of the fire hydrant.
[0006] To achieve the above objectives, the first aspect of the present application provides a fire hydrant consumable parts life cycle detection system, including: a central processing module, a data acquisition module, an early warning module and a database
[0007] The data acquisition module is used to obtain the current water pressure through the data acquisition device connected thereto;
[0008] The central processing module: obtains a number of vulnerable parts data through a database connected thereto, extracts a number of usage data and corresponding service life from the vulnerable parts data; divides the usage data according to the service life and usage data to obtain a number of usage data groups; generates a prediction curve under a corresponding water pressure range according to the number of usage data in the usage data groups; and,
[0009] Acquire the current water pressure and historical data, and generate predicted life data according to the water pressure, historical data and prediction curve; sort the predicted life data of each wearing part to obtain a life ranking table; generate an early warning signal according to the life ranking table;
[0010] Early warning module: obtain early warning signals and issue early warnings.
[0011] The present application obtains data on a number of wearing parts, groups the usage data according to the service life and usage data in the wearing parts data, and obtains a number of usage data groups; generates a prediction curve based on the usage data in the usage data group; obtains historical data and water pressure data of the current fire hydrant, predicts the remaining working time and remaining idle time of the corresponding wearing parts based on the historical data, water pressure data and the prediction curve, and generates an alarm signal based on the remaining working time and remaining idle time of each wearing part; promptly reminds relevant personnel that a wearing part of the fire hydrant is about to become abnormal and needs to be repaired or replaced; and avoids the occurrence of abnormalities in the use of the fire hydrant.
[0012] Preferably, the usage data is divided according to the service life and the usage data to obtain a plurality of usage data groups, including:
[0013] Extracting the water pressure in the usage data; grouping the usage data according to the minimum water pressure step to obtain water pressure groups, and numbering the water pressure groups in ascending order of water pressure;
[0014] The optimal service life in each water pressure group is obtained, and the water pressure groups are integrated according to the optimal service life to generate a usage data group; wherein the optimal service life is the maximum service life among the service lives corresponding to each usage data in the water pressure group; the wearing parts data includes the usage data and its corresponding service life; the usage data includes the water pressure and the usage time; and the minimum water pressure step is set based on experience.
[0015] Preferably, the step of integrating the usage water pressure groups according to the optimal service life to generate the usage data group comprises the following steps:
[0016] A: Select the smallest numbered water pressure group as the reference data group; obtain the optimal service life of the water pressure group whose number is adjacent to the reference data group; calculate the difference between the optimal service life and the optimal service life corresponding to the reference data group;
[0017] B: Determine whether the difference is less than life difference threshold 1;
[0018] If yes, then the water pressure group is combined with the reference data group to obtain a new reference data group; and A is entered;
[0019] No, when the difference is greater than the life difference threshold 2; then the water pressure group is equally divided according to the water pressure to obtain two new water pressure groups; and the water pressure groups are renumbered; enter A; otherwise, the several usage data and service life corresponding to the reference data group are integrated into the usage data group, and the range between the minimum and maximum water pressures corresponding to the reference data group is recorded as the water pressure range of the usage data group; at the same time, the next group of water pressures is used as the reference data group; proceed to A; until all water pressure groups are integrated into several usage data groups. It can be understood that the fire hydrant has not been used under the corresponding water pressure, and the life of the wearing parts.
[0020] The present application first groups the usage data by using water pressure, and then merges the groups according to the optimal service life in each group, so as to group the usage data according to the influence of water pressure on wearing parts. When the influence of water pressure change on the life of corresponding wearing parts is large, the range of water pressure division is small; when the influence of water pressure change on the life of existing wearing parts is small, the range of water pressure division is large, so that the grouping of usage data is more in line with the influence of water pressure on corresponding wearing parts, so as to increase the accuracy of subsequent predictions.
[0021] Preferably, generating a prediction curve under a corresponding water pressure range according to a plurality of usage data in the usage data group includes:
[0022] Extract several working time marks as GSi, idle time marks as XSi and service life marks as SYi in the usage data group;
[0023] Integrate working time GSi, idle time XSi and service life SYi into a prediction vector YCi=[GSi, XSi, SYi];
[0024] Each prediction vector is fitted into a prediction curve corresponding to the usage data group; wherein i is the number of each usage data in the usage data group; usage time includes working time and idle time; it can be understood that the service life, working time and idle time satisfy the formula SYi=GSi+XSi; working time is the sum of the time when the fire hydrant is used from the installation of the fire hydrant, and idle time is the sum of the time when the fire hydrant is not used from the installation of the fire hydrant; one wearing part corresponds to several prediction curves, and the water pressure range of each prediction curve is different.
[0025] Preferably, generating the predicted life data according to the use water pressure, historical data and prediction curve includes:
[0026] Obtaining the used water pressure, and obtaining a prediction curve including the used water pressure in the water pressure range corresponding to each wearing part;
[0027] Extract the idle time and working time from the historical data, input the idle time, working time and several prediction curves into the prediction model to obtain the remaining working time and remaining idle time corresponding to each wearing part; the predicted life data includes the remaining working time and the remaining idle time; wherein, the prediction model is obtained according to the training of the artificial intelligence model.
[0028] Preferably, the prediction model is obtained by training an artificial intelligence model, including:
[0029] Obtaining a number of prediction curves, idle time and working time, and a number of groups of remaining working time and remaining idle time according to the idle time, working time and prediction curves;
[0030] Integrate the prediction curve, idle time, working time, remaining idle time and remaining working time to generate several sets of training data and test data;
[0031] The artificial intelligence model is trained by training data, and the trained artificial intelligence model is tested by using test data; finally, the input is idle time, working time and several prediction curves; the output is a prediction model of several groups of remaining working time and remaining idle time corresponding to each prediction curve; wherein the artificial intelligence model includes BP model and RBF model.
[0032] Preferably, obtaining the remaining working time and the remaining idle time according to the idle time, the working time and the prediction curve includes:
[0033] The working time is recorded as the original working time, and the idle time is recorded as the original idle time;
[0034] The working time is set to 0, the original idle time and the working time are substituted into the corresponding prediction curve to obtain the service life one, the service life one and the original idle time are substituted into the prediction curve to obtain the working time one, and the difference between the working time one and the original working time is recorded as the remaining working time;
[0035] The idle time is set to 0, the original working time and the idle time are substituted into the corresponding prediction curve to obtain the service life 2, the service life 2 and the original working time are substituted into the prediction curve to obtain the idle time 1, and the difference between the idle time 1 and the original idle time is recorded as the remaining idle time.
[0036] It is worth noting that the remaining working time indicates the time during which the corresponding wearing parts are in working condition and can work from the beginning of the prediction; the remaining idle time indicates the time during which the corresponding wearing parts are in idle condition and can be idle from the beginning of the prediction.
[0037] Preferably, the predicted life data of each wearing part is sorted to obtain the life sorting table, including:
[0038] Obtain the remaining working time of each wearing part, arrange the remaining working time in ascending order, and generate a remaining working timetable;
[0039] Obtain the remaining idle time of each wearing part, arrange the remaining idle time in ascending order, and generate a remaining idle time table;
[0040] The working time and idle time are obtained in real time. When the interval between the working time and the last generation of predicted life data is greater than update interval one, or the interval between the idle time and the last generation of predicted life data is greater than update interval two, the remaining working time and the remaining idle time are regenerated; and the remaining working timetable and the remaining idle timetable are regenerated; wherein the life sorting table includes the remaining working timetable and the remaining idle timetable; update interval one and update interval two are set according to experience, and update interval one is less than update interval two.
[0041] Preferably, generating a warning signal according to the life ranking table includes:
[0042] Extract the remaining idle time corresponding to the first-ranked consumable part in the remaining idle timetable and the remaining working time corresponding to the first-ranked consumable part in the remaining working timetable;
[0043] When the remaining idle time is 0, or the remaining working time is 0, a replacement warning signal is generated; otherwise, when the remaining idle time is less than the safe idle time threshold, or the remaining working time is less than the safe working time threshold, a maintenance warning signal is generated; wherein the warning signal includes a replacement warning signal and a maintenance warning signal.
[0044] Preferably, the central processing module is also used to update the predicted life data according to the real-time water pressure usage, including: obtaining the water pressure usage and the water pressure difference in real time; when the water pressure difference is greater than the water pressure difference threshold; generating an update signal, and updating the predicted life data according to the update signal.
[0045] The predicted life data is updated according to the update signal, including: obtaining water pressure data in the historical data, extracting several historical water pressures and corresponding water pressure times in the water pressure data, and generating the remaining idle time and remaining working time of each historical water pressure according to the prediction curves corresponding to each historical water pressure, idle time, working time and historical water pressure;
[0046] The water pressure time corresponding to the historical water pressure is recorded as SCj; the corresponding remaining idle time is recorded as SXSj; and the corresponding remaining working time is recorded as SGSj;
[0047] The comprehensive remaining idle time ZXS is calculated by the formula ZXS=∑[SXSj×SCj / ∑(SCj)];
[0048] The comprehensive remaining working time ZGS is calculated by the formula ZGS=∑[SGSj×SCj / ∑(SCj)];
[0049] The comprehensive remaining idle time ZXS is used as the remaining idle time in the predicted life data; the comprehensive remaining working time ZGS is used as the remaining working time in the predicted life data.
[0050] Compared with the prior art, the beneficial effects of this application are:
[0051] 1. The present application obtains data on a number of wearing parts, groups the usage data according to the service life and usage data in the wearing parts data, and obtains a number of usage data groups; generates a prediction curve based on the usage data in the usage data group; obtains historical data and water pressure data of the current fire hydrant, predicts the remaining working time and remaining idle time of the corresponding wearing parts based on the historical data, water pressure data and the prediction curve, and generates an alarm signal based on the remaining working time and remaining idle time of each wearing part; promptly reminds relevant personnel that the fire hydrant is about to become abnormal and needs to be repaired or replaced; and avoids the occurrence of abnormal situations during the use of the fire hydrant.
[0052] 2. The present application groups the usage data by first using water pressure, and then merges the groups according to the optimal service life in each group, so as to group the usage data according to the impact of water pressure on wearing parts. When the impact of water pressure changes on the life of corresponding wearing parts is large, the range of water pressure division is smaller; when the impact of water pressure changes on the life of existing wearing parts is small, the range of water pressure division is larger, so that the grouping of usage data is more in line with the impact of water pressure on corresponding wearing parts, which is convenient for increasing the accuracy of subsequent predictions. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0054] Figure 1 This is a schematic diagram of the principle of this application;
[0055] Figure 2 A schematic diagram of the method steps of this application;
[0056] Figure 3 A flow chart for generating warning signals in this application. DETAILED DESCRIPTION
[0057] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.
[0058] See also Figure 1-Figure 2 The first embodiment of the present application provides a fire hydrant consumable parts life cycle detection system, including: a central processing module, a data acquisition module, an early warning module and a database
[0059] Data acquisition module: obtains the current water pressure through the data acquisition device connected to it; the data acquisition device includes a water pressure measuring instrument;
[0060] Central processing module: obtains some consumable parts data through the database connected to it. It is worth noting that the consumable parts data is the data recorded when the consumable parts produced in the same batch as the corresponding consumable parts of the fire hydrants are used; extracts some usage data and corresponding service life from the consumable parts data; the service life is the length of time from the beginning of use to the damage of the corresponding consumable parts; divides the usage data according to the service life and usage data to obtain several usage data groups; generates a prediction curve under the corresponding water pressure range according to some usage data in the usage data group; and,
[0061] Obtain the current water pressure and historical data, and generate predicted life data based on the water pressure, historical data and prediction curve; sort the predicted life data of each wearing part to obtain a life ranking table; generate an early warning signal based on the life ranking table;
[0062] Early warning module: obtain early warning signals and issue early warnings;
[0063] Communication module: used for communication between the system and other devices or platforms, supports remote monitoring and management, and ensures real-time transmission and sharing of relevant data;
[0064] Display module: used to display the remaining working time, remaining idle time and early warning signals of each wearing part of the fire hydrant in real time.
[0065] The present application obtains data on a number of wearing parts, groups the usage data according to the service life and usage data in the wearing parts data, and obtains a number of usage data groups; generates a prediction curve based on the usage data in the usage data group; obtains historical data and water pressure data of the current fire hydrant, predicts the remaining working time and remaining idle time of the corresponding wearing parts based on the historical data, water pressure data and the prediction curve, and generates an alarm signal based on the remaining working time and remaining idle time of each wearing part; promptly reminds relevant personnel that the fire hydrant is about to become abnormal and needs to be repaired or replaced; and avoids the occurrence of abnormal situations during the use of the fire hydrant.
[0066] This application predicts the life of the corresponding consumable parts on the current fire hydrant by obtaining the usage status of consumable parts produced in the same batch of each consumable part as reference data, so that the prediction result is more accurate.
[0067] The usage data is divided into several usage data groups according to service life and usage data, including:
[0068] Extracting the water pressure in the usage data; grouping the usage data according to the minimum water pressure step to obtain water pressure groups, and numbering the water pressure groups in ascending order of water pressure;
[0069] The optimal service life in each water pressure group is obtained, and the water pressure groups are integrated according to the optimal service life to generate a usage data group; wherein the optimal service life is the maximum service life among the service lives corresponding to each usage data in the water pressure group; the wearing parts data includes the usage data and its corresponding service life; the usage data includes the water pressure and the usage time; and the minimum water pressure step is set based on experience.
[0070] The use water pressure group is integrated according to the optimal service life to generate a use data group, including the following steps:
[0071] A: Select the smallest numbered water pressure group as the reference data group; obtain the optimal service life of the water pressure group with a number adjacent to the reference data group; calculate the difference between the optimal service life and the optimal service life corresponding to the reference data group;
[0072] B: Determine whether the difference is less than the life difference threshold 1;
[0073] If yes, then merge the used water pressure group with the reference data group to obtain a new reference data group; proceed to A;
[0074] No, when the difference is greater than the life difference threshold 2; then the water pressure group is equally divided according to the water pressure to obtain two new water pressure groups; and the water pressure groups are renumbered; enter A; otherwise, several usage data and service life corresponding to the reference data group are integrated into the usage data group, and the range between the minimum and maximum water pressures corresponding to the reference data group is recorded as the water pressure range of the usage data group; at the same time, the next group of water pressures is used as the reference data group; proceed to A; until all water pressure groups are integrated into several usage data groups; the life difference threshold 1 and the life difference threshold 2 are both set according to the inspection, and the life difference threshold 1 is less than the life difference threshold 2. It can be understood that the fire hydrant has not been used under the corresponding water pressure, and the life of the wearing parts.
[0075] The present application first groups the usage data by using water pressure, and then merges the groups according to the optimal service life in each group, so as to group the usage data according to the influence of water pressure on wearing parts. When the influence of water pressure change on the life of corresponding wearing parts is large, the range of water pressure division is small; when the influence of water pressure change on the life of existing wearing parts is small, the range of water pressure division is large, so that the grouping of usage data is more in line with the influence of water pressure on corresponding wearing parts, so as to increase the accuracy of subsequent predictions.
[0076] In this embodiment, the usage data are grouped according to the minimum water pressure step to obtain 30 usage water pressure groups; the difference in the optimal service life within the first 5 groups is small, and the difference in the optimal service life between the 6th group and the first 5 groups is large, so the first 5 groups are merged to generate one usage data group, and the difference in the optimal service life between the 6th group and the 8th group is small, so the 6th group to the 8th group are merged to generate another usage data group; and so on, until all usage water pressure groups are divided into usage data groups.
[0077] A prediction curve under a corresponding water pressure range is generated according to several usage data in the usage data group, including:
[0078] Extract several working time marks as GSi, idle time marks as XSi and service life marks as SYi in the usage data group;
[0079] Integrate working time GSi, idle time XSi and service life SYi into a prediction vector YCi=[GSi, XSi, SYi];
[0080] Each prediction vector is fitted into a prediction curve corresponding to the usage data group; wherein i is the number of each usage data in the usage data group; usage time includes working time and idle time; it can be understood that the service life, working time and idle time satisfy the formula SYi=GSi+XSi; working time is the sum of the time when the fire hydrant is used from the installation of the fire hydrant, and idle time is the sum of the time when the fire hydrant is not used from the installation of the fire hydrant; one wearing part corresponds to several prediction curves, and the water pressure range of each prediction curve is different.
[0081] Generates predicted life data based on water pressure, historical data and prediction curves, including:
[0082] Obtain the used water pressure, and obtain the prediction curve of the used water pressure in the corresponding water pressure range of each wearing part;
[0083] The idle time and working time in the historical data are extracted, and the idle time, working time and several prediction curves are input into the prediction model to obtain the remaining working time and remaining idle time corresponding to each wearing part; the predicted life data includes the remaining working time and the remaining idle time; wherein, the prediction model is obtained according to the training of the artificial intelligence model.
[0084] The present application generates a prediction curve by fitting the usage data in different usage data groups, and each prediction curve corresponds to a water pressure range of a wearing part; the usage data groups of different wearing parts are divided differently, so that the prediction of different wearing parts is more targeted, and thus the prediction results of different wearing parts are more accurate.
[0085] The prediction model is trained based on the artificial intelligence model, including:
[0086] Obtaining a number of prediction curves, idle time and working time, and a number of groups of remaining working time and remaining idle time according to the idle time, working time and prediction curves;
[0087] Integrate the prediction curve, idle time, working time, remaining idle time and remaining working time to generate several sets of training data and test data;
[0088] The artificial intelligence model is trained with training data, and the trained artificial intelligence model is tested with test data; specifically, the prediction curve, idle time and working time in the test data are input into the trained artificial intelligence model to obtain the output of the remaining working time and the remaining idle time. When the remaining working time is within the threshold one of the remaining working time in the test data; and the remaining idle time is within the threshold two of the remaining idle time in the test data, the next set of test data is tested; otherwise, the corresponding parameters are adjusted and the current set of test data is re-tested; until the expected requirements are met, that is, the remaining working time is within the threshold one of the remaining working time in the test data; and the remaining idle time is within the threshold two of the remaining idle time in the test data; finally, a prediction model is obtained with the input of idle time, working time and several prediction curves; the output is several sets of remaining working time and remaining idle time corresponding to each prediction curve; wherein the artificial intelligence model includes a BP model and an RBF model.
[0089] The remaining working time and remaining idle time are obtained based on the idle time, working time and prediction curve, including:
[0090] Record working time as original working time and idle time as original idle time;
[0091] Set the working time to 0, substitute the original idle time and working time into the corresponding prediction curve to obtain the service life one, substitute the service life one and the original idle time into the prediction curve to obtain the working time one, and record the difference between the working time one and the original working time as the remaining working time;
[0092] Set the idle time to 0, substitute the original working time and idle time into the corresponding prediction curve to obtain the second service life, substitute the second service life and the original working time into the prediction curve to obtain the first idle time, and record the difference between the first idle time and the original idle time as the remaining idle time.
[0093] It is worth noting that the remaining working time indicates the time during which the corresponding wearing parts are in working condition and can work from the beginning of the prediction; the remaining idle time indicates the time during which the corresponding wearing parts are in idle condition and can be idle from the beginning of the prediction.
[0094] The predicted life data of each wearing part is sorted to obtain a life sorting table, including:
[0095] Obtain the remaining working time of each wearing part, arrange the remaining working time in ascending order, and generate a remaining working timetable;
[0096] Obtain the remaining idle time of each wearing part, arrange the remaining idle time in ascending order, and generate a remaining idle time table;
[0097] The working time and idle time are obtained in real time. When the interval between the working time and the last generation of predicted life data is greater than update interval one, or the interval between the idle time and the last generation of predicted life data is greater than update interval two, the remaining working time and the remaining idle time are regenerated; and the remaining working timetable and the remaining idle timetable are regenerated; wherein the life sorting table includes the remaining working timetable and the remaining idle timetable; update interval one and update interval two are set according to experience, and update interval one is less than update interval two.
[0098] See also Figure 3 , generate warning signals based on the life ranking table, including:
[0099] Extract the remaining idle time corresponding to the first-ranked consumable part in the remaining idle timetable and the remaining working time corresponding to the first-ranked consumable part in the remaining working timetable;
[0100] When the remaining idle time is 0, or the remaining working time is 0, a replacement warning signal is generated; otherwise, when the remaining idle time is less than the safe idle time threshold, or the remaining working time is less than the safe working time threshold, a maintenance warning signal is generated; wherein the warning signal includes a replacement warning signal and a maintenance warning signal.
[0101] The present application determines whether the minimum remaining working time and the minimum remaining idle time of each wearing part of the fire hydrant are less than the corresponding threshold value. If so, a corresponding warning signal is generated; otherwise, no operation is performed; so that a warning can be issued in time according to the actual situation of the fire hydrant.
[0102] The central processing module is also used to update the predicted life data according to the real-time water pressure, including: obtaining the water pressure and the water pressure difference in real time; when the water pressure difference is greater than the water pressure difference threshold; generating an update signal, and updating the predicted life data according to the update signal.
[0103] The predicted life data is updated according to the update signal, including: obtaining water pressure data in the historical data, extracting several historical water pressures and corresponding water pressure times in the water pressure data, and generating the remaining idle time and remaining working time of each historical water pressure according to the prediction curves corresponding to each historical water pressure, idle time, working time and historical water pressure;
[0104] The water pressure time corresponding to the historical water pressure is recorded as SCj; the corresponding remaining idle time is recorded as SXSj; the corresponding remaining working time is recorded as SGSj; j is the number of the historical water pressure; when the historical water pressure of the same fire hydrant is within the water pressure range of different usage data groups, the corresponding historical water pressure is assigned different numbers; the historical water pressure within the water pressure range of the same usage data group has the same number;
[0105] The comprehensive remaining idle time ZXS is calculated by the formula ZXS=∑[SXSj×SCj / ∑(SCj)];
[0106] The comprehensive remaining working time ZGS is calculated by the formula ZGS=∑[SGSj×SCj / ∑(SCj)];
[0107] The comprehensive remaining idle time ZXS is used as the remaining idle time in the predicted life data; the comprehensive remaining working time ZGS is used as the remaining working time in the predicted life data.
[0108] The central processing module is also used to monitor the water pressure in real time. When the water pressure is abnormal, a water pressure warning signal is generated, including: real-time acquisition of the water pressure and the water pressure difference; when the water pressure is not within the safe water pressure threshold, or the water pressure difference exceeds the safe water pressure difference, a water pressure warning signal is generated to remind relevant personnel that the water pressure of the fire hydrant is abnormal and needs to be tested. It can be understood that the warning signal also includes a water pressure warning signal.
[0109] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.
[0110] How this application works:
[0111] The present application obtains data on a number of wearing parts, groups the usage data according to the service life and usage data in the wearing parts data, and obtains a number of usage data groups; generates a prediction curve based on the usage data in the usage data group; obtains historical data and water pressure data of the current fire hydrant, predicts the remaining working time and remaining idle time of the corresponding wearing parts based on the historical data, water pressure data and the prediction curve, and generates an alarm signal based on the remaining working time and remaining idle time of each wearing part; promptly reminds relevant personnel that the fire hydrant is about to become abnormal and needs to be repaired or replaced; and avoids the occurrence of abnormal situations during the use of the fire hydrant.
[0112] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.
Claims
1. A fire hydrant consumable parts life cycle detection system, characterized in that: include: Central processing module, data acquisition module, early warning module and database The data acquisition module is used to obtain the current water pressure through the data acquisition device connected thereto; The central processing module: obtains a number of vulnerable parts data through a database connected thereto, extracts a number of usage data and corresponding service life from the vulnerable parts data; divides the usage data according to the service life and usage data to obtain a number of usage data groups; generates a prediction curve under a corresponding water pressure range according to the number of usage data in the usage data groups; and, Acquire the current water pressure and historical data, and generate predicted life data according to the water pressure, historical data and prediction curve; sort the predicted life data of each wearing part to obtain a life sorting table; Generate early warning signals based on the life ranking table; The usage data is divided according to the service life and the usage data to obtain a plurality of usage data groups, including: extracting the usage water pressure in the usage data; grouping the usage data according to the minimum water pressure step to obtain the usage water pressure groups, and numbering the usage water pressure groups in the order of the usage water pressure from small to large; obtaining the optimal service life in each usage water pressure group, and integrating the usage water pressure groups according to the optimal service life to generate the usage data group; wherein the optimal service life is the maximum service life among the service lives corresponding to each usage data in the usage water pressure group; the wearing parts data includes the usage data and its corresponding service life; the usage data includes the usage water pressure and the usage time; The step of integrating the use water pressure groups according to the optimal service life to generate the use data group includes the following steps: A: selecting the use water pressure group with the smallest number as the reference data group; obtaining the optimal service life of the use water pressure group with a number adjacent to the reference data group; calculating the difference between the optimal service life and the optimal service life corresponding to the reference data group; B: Determine whether the difference is less than the life difference threshold 1; if yes, merge the water pressure group with the reference data group to obtain a new reference data group; proceed to A; No, when the difference is greater than the life difference threshold 2; divide the water pressure group equally according to the water pressure to obtain two new water pressure groups; and renumber the water pressure groups; proceed to A; otherwise, integrate the several usage data and service life corresponding to the reference data group into a usage data group, and record the range between the minimum and maximum water pressures corresponding to the reference data group as the water pressure range of the usage data group; and use the next group of water pressures as the reference data group; proceed to A; until all water pressure groups are integrated into several usage data groups; Early warning module: obtain early warning signals and issue early warnings.
2. A fire hydrant consumable parts life cycle detection system according to claim 1, characterized in that: The method of generating a prediction curve under a corresponding water pressure range according to the plurality of usage data in the usage data group includes: Extract several working time marks as GSi, idle time marks as XSi and service life marks as SYi in the usage data group; Integrate working time GSi, idle time XSi and service life SYi into a prediction vector YCi=[GSi, XSi, SYi]; Each prediction vector is fitted into a prediction curve corresponding to the usage data group; wherein i is the number of each usage data in the usage data group; and the usage time includes working time and idle time.
3. A fire hydrant consumable parts life cycle detection system according to claim 1, characterized in that: Generating the predicted life data according to the use water pressure, historical data and prediction curve includes: Obtaining the used water pressure, and obtaining a prediction curve including the used water pressure in the water pressure range corresponding to each wearing part; Extract the idle time and working time from the historical data, input the idle time, working time and several prediction curves into the prediction model to obtain the remaining working time and remaining idle time corresponding to each wearing part; the predicted life data includes the remaining working time and the remaining idle time; wherein, the prediction model is obtained according to the training of the artificial intelligence model.
4. A fire hydrant consumable parts life cycle detection system according to claim 3, characterized in that: The prediction model is obtained by training an artificial intelligence model, and includes: Obtaining a number of prediction curves, idle time and working time, and a number of groups of remaining working time and remaining idle time according to the idle time, working time and prediction curves; Integrate the prediction curve, idle time, working time, remaining idle time and remaining working time to generate several sets of training data and test data; The artificial intelligence model is trained by training data, and the trained artificial intelligence model is tested by using test data; finally, the input is idle time, working time and several prediction curves; the output is a prediction model of several groups of remaining working time and remaining idle time corresponding to each prediction curve; wherein the artificial intelligence model includes BP model and RBF model.
5. A fire hydrant consumable parts life cycle detection system according to claim 1, characterized in that: The predicted life data of each wearing part is sorted to obtain the life sorting table, including: Obtain the remaining working time of each wearing part, arrange the remaining working time in ascending order, and generate a remaining working timetable; Obtain the remaining idle time of each wearing part, arrange the remaining idle time in ascending order, and generate a remaining idle time table; The working time and idle time are obtained in real time. When the interval between the working time and the last generation of predicted life data is greater than update interval one, or the interval between the idle time and the last generation of predicted life data is greater than update interval two, the remaining working time and the remaining idle time are regenerated; and the remaining working timetable and the remaining idle timetable are regenerated; wherein, the life sorting table includes the remaining working timetable and the remaining idle timetable; and the update interval one is less than the update interval two.
6. A fire hydrant consumable parts life cycle detection system according to claim 1, characterized in that: Generate early warning signals based on the life ranking table, including: Extract the remaining idle time corresponding to the first-ranked consumable part in the remaining idle timetable and the remaining working time corresponding to the first-ranked consumable part in the remaining working timetable; When the remaining idle time is 0, or the remaining working time is 0, a replacement warning signal is generated; otherwise, when the remaining idle time is less than the safe idle time threshold, or the remaining working time is less than the safe working time threshold, a maintenance warning signal is generated; wherein the warning signal includes a replacement warning signal and a maintenance warning signal.
7. A fire hydrant consumable parts life cycle detection system according to claim 1, characterized in that: The central processing module is also used to update the predicted life data according to the real-time water pressure, including: obtaining the water pressure and the water pressure difference in real time; when the water pressure difference is greater than the water pressure difference threshold; generating an update signal, and updating the predicted life data according to the update signal.
Citation Information
Patent Citations
A smart fire hydrant control method and a smart fire hydrant control system
CN111375166B
Storage life calculation method and flash memory
CN114005480A
