A fire hydrant status monitoring method and system based on the Internet of Things

Abstract

The present invention provides a fire hydrant status monitoring method and system based on the Internet of Things, which belongs to the technical field of the Internet of Things, and specifically includes: when determining that the fire hydrant is not in a water use or impact state based on a valve opening signal and an acceleration signal, judging whether the pressure change of the water pressure of the fire hydrant within a first time threshold is greater than the first threshold; if so, monitoring the water temperature of the fire hydrant to obtain a water temperature signal, and based on the water temperature signal, the water pressure signal, the pressure change within the first time threshold, and the water pressure signal at the same time of the previous day as an input set, adopting a prediction model based on an intelligent algorithm to obtain the water pressure data of the fire hydrant after the second time threshold; obtaining the status signal of the fire hydrant based on the water pressure data of the fire hydrant after the second time threshold, thereby further improving the accuracy of fire hydrant status monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things, and in particular relates to a fire hydrant status monitoring method and system based on the Internet of Things. Background Art

[0002] Municipal fire hydrants, as essential urban water supply facilities, are a key component of public firefighting infrastructure, playing a crucial role in providing water for firefighting and rescue efforts. Their proper functioning directly impacts the timely and effective extinguishing of fires and is crucial for protecting public life and property. However, in practice, due to scattered installation locations, lax management, and a lack of public legal awareness, municipal fire hydrants are often damaged, in disrepair, experiencing insufficient water pressure, leaks, and illegal water use. This not only impacts public access to water but also hinders firefighting and rescue efforts, posing serious safety risks. According to statistics, over 70% of the enormous economic losses and casualties caused by fires in my country each year are due to poor fire hydrant management, which delays the optimal time for firefighting and rescue efforts.

[0003] To monitor the status of fire hydrants, in his master's thesis, "Design and Implementation of an Intelligent Monitoring System for Fire Water Supply," author Zong Wenjie designed an Internet of Things (IoT) monitoring terminal to measure water pressure, temperature, and other parameters. Given that fire water pressure fluctuations are affected by multiple complex factors and are prone to both linear and nonlinear characteristics, he optimized a single ARIMA model and, leveraging the advantages of the SVR support vector regression machine in handling nonlinear problems, adopted a fire water pressure prediction method based on a combined ARIMA-SVR model. Experiments showed that the optimized model significantly improved the accuracy of the single ARIMA model. However, the decision to predict water pressure based on the water pressure monitoring results was not based on the water pressure monitoring results. Since the water pressure of many fire hydrants is normal, water pressure prediction should only be performed when the water pressure monitoring results show a trend problem, otherwise it would result in unnecessary energy waste. Furthermore, the impact of temperature changes on water pressure prediction was ignored during water pressure prediction, resulting in low water pressure prediction accuracy under different temperature conditions.

[0004] Based on the above technical problems, it is necessary to design a fire hydrant status monitoring method and system based on the Internet of Things. Summary of the Invention

[0005] The purpose of the present invention is to provide a fire hydrant status monitoring method and system based on the Internet of Things.

[0006] In order to solve the above technical problems, the first aspect of the present invention provides a fire hydrant status monitoring method based on the Internet of Things, comprising:

[0007] S11 collects the water pressure, valve opening state, and acceleration of the fire hydrant to obtain a water pressure signal, a valve opening signal, and an acceleration signal, and determines whether the fire hydrant is in a water use or impact state based on the valve opening signal and the acceleration signal. If not, proceeds to step S12;

[0008] S12 determines whether the pressure change of the water pressure of the fire hydrant within the first time threshold is greater than the first threshold. If so, it is determined that the water pressure of the fire hydrant is in a potential abnormal state and the process proceeds to step S13. If not, a fire hydrant normal state signal is output;

[0009] S13 monitors the water temperature of the fire hydrant to obtain a water temperature signal, and uses the water temperature signal, the water pressure signal, the pressure change within the first time threshold, and the water pressure signal at the same time the previous day as an input set, using a prediction model based on an intelligent algorithm to obtain water pressure data of the fire hydrant after a second time threshold;

[0010] S14 obtains a status signal of the fire hydrant based on the water pressure data of the fire hydrant after a second time threshold.

[0011] By judging the valve opening state and acceleration of the fire hydrant, it is possible to accurately judge whether the fire hydrant is in a water use or impact state. When it is not in a water use or impact state, the change in the water pressure of the fire hydrant is judged to determine whether the fire hydrant is in a potential abnormal state. When it is in a potential abnormal state, an input set is formed based on the water temperature signal, water pressure signal, pressure change within the first time threshold, and the water pressure signal at the same time of the previous day, so that the water pressure data after the second time threshold can be obtained, and the status signal of the fire hydrant is obtained based on the above water pressure data, thereby solving the original problem of low accuracy caused by not considering temperature data and the technical problem of unnecessary energy loss caused by not predicting water pressure based on water pressure monitoring conditions, further improving accuracy and reducing energy consumption.

[0012] By determining whether the fire hydrant is in a water use or impact state based on the valve opening signal and the acceleration signal, the above two states are excluded, thereby further enhancing the influence of external factors on water pressure and improving the accuracy of prediction.

[0013] By monitoring the pressure changes of fire hydrants within the first time threshold, the accuracy of judging abnormal water pressure signals is further improved, and the possibility of misjudgment caused by normal fluctuations in water pressure is reduced. On the basis of improving accuracy, the efficiency of prediction is also guaranteed.

[0014] When in a potential abnormal state, the water pressure data after the second time threshold is predicted based on the temperature data and the most recent water pressure data. This not only eliminates the impact of temperature data on water pressure changes, but also fully considers the guiding significance of the most recent water pressure data, so that the accuracy of the final prediction of the water pressure data of the fire hydrant after the second time threshold is improved to a certain extent.

[0015] By using predicted water pressure data to judge the status of fire hydrants, the status of fire hydrants can be accurately obtained based on the water pressure data of fire hydrants after a period of time, rather than just considering current or historical records. Not only has the stability and accuracy been greatly improved, but the final status signal can also accurately reflect the true status of the fire hydrant, thereby ensuring the safe and reliable operation of the fire hydrant and reducing fire hazards caused by fire hydrants.

[0016] A further technical solution is that the specific steps of determining the impact state of the fire hydrant are:

[0017] S21 determines whether there is an acceleration signal on the fire hydrant, and if so, proceeds to step S22;

[0018] S22 determines whether the acceleration signal of the fire hydrant is greater than a first acceleration threshold, and if so, proceeds to step S23;

[0019] S23 determines that the fire hydrant is in a collision state, and records the number of times the fire hydrant has an acceleration signal.

[0020] By setting the first acceleration threshold, misjudgment of the fire hydrant in a non-collision state can be avoided, unnecessary interference is eliminated, and accuracy is improved.

[0021] A further technical solution is that the specific steps of determining whether the water pressure of a fire hydrant is in a potential abnormal state are as follows:

[0022] S31 determines whether the pressure change of the water pressure of the fire hydrant within the first time threshold is greater than the first threshold. If so, proceed to step S32;

[0023] S32 determines whether the water pressure of the fire hydrant is in a gradually decreasing state within a third time threshold, wherein the third time threshold is greater than the first time threshold. If so, proceed to step S33;

[0024] S33 determines that the water pressure of the fire hydrant is in a potential abnormal state.

[0025] By predicting the pressure change and judging the state of gradually decreasing water pressure over a long period of time, the accuracy of judging potential abnormal conditions can be further improved, and the true state of the fire hydrant can be evaluated from a higher time dimension, greatly reducing the impact of external abnormal interference.

[0026] A further technical solution is that the first time threshold and the first threshold are determined according to the rated water pressure of the fire hydrant and the importance of the location of the fire hydrant.

[0027] A further technical solution is that the intelligent algorithm is a prediction model based on the LSTM-ARIMA algorithm.

[0028] By adopting the LSTM-ARMA algorithm's prediction model, we can combine the LSTM algorithm's technical advantage of being able to approximate complex nonlinear relationships with the ARIMA algorithm's technical advantage of having a simple model but not requiring the help of exogenous variables. At the same time, it also avoids the ARIMA algorithm's technical problem of intelligently handling linear relationships, further improving the accuracy of predictions.

[0029] A further technical solution is that the specific steps of obtaining the water pressure data of the fire hydrant after the second time threshold are:

[0030] S41 transmits the input set to a prediction model based on an LSTM algorithm based on the input set to obtain an LSTM prediction result;

[0031] S42 transmits the input set to a prediction model based on the ARIMA algorithm based on the input set to obtain an ARIMA prediction result;

[0032] S43 obtains water pressure data of the fire hydrant after a second time threshold based on the LSTM prediction result and the ARIMA prediction result.

[0033] A further technical solution is that the specific formula for the water pressure data of the fire hydrant after the second time threshold is:

[0034]

[0035] K1, K2, and K3 are weights, L1 and R1 are the LSTM prediction results and the ARIMA prediction results respectively.

[0036] By adding the compensation term, the proportion of LSTM prediction results is increased, thereby improving the accuracy of the final algorithm to a certain extent.

[0037] A further technical solution is that the specific steps of constructing the fire hydrant status signal are:

[0038] S51 obtains a correction value based on the age of the fire hydrant and the number of times the fire hydrant has an acceleration signal;

[0039] S52 corrects the second threshold value based on the correction value to obtain a first correction threshold value, and determines whether the water pressure data of the fire hydrant after the second time threshold value is less than the first correction threshold value. If so, the process proceeds to step S52; if not, the process outputs a fire hydrant normal state signal;

[0040] S53 outputs a fire hydrant abnormal state signal.

[0041] By setting the correction value, the first correction threshold can be dynamically corrected, thereby further improving the accuracy of judging the abnormal state signal of the fire hydrant and ensuring the safe and reliable use of the fire hydrant.

[0042] A further technical solution is that the correction value is predicted using a correction value prediction model based on the GM algorithm.

[0043] A further technical solution is that the calculation formula of the first correction threshold is:

[0044]

[0045] Where D2 and X2 are the second threshold and correction value respectively, wherein the correction value ranges from 0 to 10, and X max is 10.

[0046] By setting the first correction threshold, the universality of the first correction threshold is further improved, and the reliability of the overall model is improved.

[0047] On the other hand, the present invention provides a fire hydrant status monitoring system based on the Internet of Things, which adopts the above-mentioned fire hydrant status monitoring method based on the Internet of Things, including a signal monitoring module, a signal judgment module, a water pressure data prediction module, and a status signal evaluation module; wherein the signal monitoring module is responsible for collecting the water pressure, valve opening status, and acceleration of the fire hydrant to obtain a water pressure signal, a valve opening signal, and an acceleration signal;

[0048] The signal judgment module is responsible for judging the water pressure signal, valve opening signal, and acceleration signal, and transmitting data based on the judgment results;

[0049] The water pressure data prediction module is responsible for predicting the water pressure data of the fire hydrant after the second time threshold, and transmitting the water pressure data of the fire hydrant after the second time threshold to the state signal evaluation module;

[0050] The status signal evaluation module is responsible for obtaining a status signal of the fire hydrant based on water pressure data of the fire hydrant after a second time threshold.

[0051] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings.

[0054] Figure 1 This is a flow chart of a fire hydrant status monitoring method based on the Internet of Things according to Example 1.

[0055] Figure 2 4 is a flowchart of specific steps for determining the impact state of a fire hydrant according to Example 1.

[0056] Figure 3 This is a flowchart of specific steps for determining whether the water pressure of a fire hydrant is in a potential abnormal state according to Example 1.

[0057] Figure 4 This is a flowchart of specific steps for obtaining the water pressure data of the fire hydrant after the second time threshold according to Example 1.

[0058] Figure 5 This is a flowchart of specific steps constructed based on the status signal of the fire hydrant in Example 1.

[0059] Figure 6 This is a structural diagram of a fire hydrant status monitoring system based on the Internet of Things according to Example 2. DETAILED DESCRIPTION

[0060] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the figures represent like or similar structures, and thus their detailed description will be omitted.

[0061] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0062] Example 1

[0063] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a fire hydrant status monitoring method based on the Internet of Things is provided, including:

[0064] S11 collects the water pressure, valve opening state, and acceleration of the fire hydrant to obtain a water pressure signal, a valve opening signal, and an acceleration signal, and determines whether the fire hydrant is in a water use or impact state based on the valve opening signal and the acceleration signal. If not, proceeds to step S12;

[0065] To give a specific example, when there is a valve opening signal, it means that the fire hydrant is using water at this time. When there is an acceleration signal, it means that the fire hydrant is in an impact state and is hit by an external object.

[0066] S12 determines whether the pressure change of the water pressure of the fire hydrant within the first time threshold is greater than the first threshold. If so, it is determined that the water pressure of the fire hydrant is in a potential abnormal state and the process proceeds to step S13. If not, a fire hydrant normal state signal is output;

[0067] For example, if the pressure change within 20 seconds is greater than 20 MPa, it is determined that the water pressure of the fire hydrant is in a potential abnormal state.

[0068] S13 monitors the water temperature of the fire hydrant to obtain a water temperature signal, and uses the water temperature signal, the water pressure signal, the pressure change within the first time threshold, and the water pressure signal at the same time the previous day as an input set, using a prediction model based on an intelligent algorithm to obtain water pressure data of the fire hydrant after a second time threshold;

[0069] S14 obtains a status signal of the fire hydrant based on the water pressure data of the fire hydrant after a second time threshold.

[0070] For example, if the water pressure data after the second time threshold is 240 MPa, it means that the water pressure of the fire hydrant is too low or there is an abnormal leakage.

[0071] By judging the valve opening state and acceleration of the fire hydrant, it is possible to accurately judge whether the fire hydrant is in a water use or impact state. When it is not in a water use or impact state, the change in the water pressure of the fire hydrant is judged to determine whether the fire hydrant is in a potential abnormal state. When it is in a potential abnormal state, an input set is formed based on the water temperature signal, water pressure signal, pressure change within the first time threshold, and the water pressure signal at the same time of the previous day, so that the water pressure data after the second time threshold can be obtained, and the status signal of the fire hydrant is obtained based on the above water pressure data, thereby solving the original problem of low accuracy caused by not considering temperature data and the technical problem of unnecessary energy loss caused by not predicting water pressure based on water pressure monitoring conditions, further improving accuracy and reducing energy consumption.

[0072] By determining whether the fire hydrant is in a water use or impact state based on the valve opening signal and the acceleration signal, the above two states are excluded, thereby further enhancing the influence of external factors on water pressure and improving the accuracy of prediction.

[0073] By monitoring the pressure changes of fire hydrants within the first time threshold, the accuracy of judging abnormal water pressure signals is further improved, and the possibility of misjudgment caused by normal fluctuations in water pressure is reduced. On the basis of improving accuracy, the efficiency of prediction is also guaranteed.

[0074] When in a potential abnormal state, the water pressure data after the second time threshold is predicted based on the temperature data and the most recent water pressure data. This not only eliminates the impact of temperature data on water pressure changes, but also fully considers the guiding significance of the most recent water pressure data, so that the accuracy of the final prediction of the water pressure data of the fire hydrant after the second time threshold is improved to a certain extent.

[0075] By using predicted water pressure data to judge the status of fire hydrants, the status of fire hydrants can be accurately obtained based on the water pressure data of fire hydrants after a period of time, rather than just considering current or historical records. Not only has the stability and accuracy been greatly improved, but the final status signal can also accurately reflect the true status of the fire hydrant, thereby ensuring the safe and reliable operation of the fire hydrant and reducing fire hazards caused by fire hydrants.

[0076] In another possible embodiment, Figure 2 As shown, the specific steps for determining the impact state of a fire hydrant are:

[0077] S21 determines whether there is an acceleration signal on the fire hydrant, and if so, proceeds to step S22;

[0078] S22 determines whether the acceleration signal of the fire hydrant is greater than a first acceleration threshold, and if so, proceeds to step S23;

[0079] S23 determines that the fire hydrant is in a collision state, and records the number of times the fire hydrant has an acceleration signal.

[0080] By setting the first acceleration threshold, misjudgment of the fire hydrant in a non-collision state can be avoided, unnecessary interference is eliminated, and accuracy is improved.

[0081] In another possible embodiment, Figure 3 As shown in the figure, the specific steps to determine if the water pressure of a fire hydrant is in a potential abnormal state are:

[0082] S31 determines whether the pressure change of the water pressure of the fire hydrant within the first time threshold is greater than the first threshold. If so, proceed to step S32;

[0083] S32 determines whether the water pressure of the fire hydrant is in a gradually decreasing state within a third time threshold, wherein the third time threshold is greater than the first time threshold. If so, proceed to step S33;

[0084] For example, if the water pressure of the fire hydrant is gradually decreasing within 20 minutes, the process goes to step S33.

[0085] S33 determines that the water pressure of the fire hydrant is in a potential abnormal state.

[0086] By predicting the pressure change and judging the state of gradually decreasing water pressure over a long period of time, the accuracy of judging potential abnormal conditions can be further improved, and the true state of the fire hydrant can be evaluated from a higher time dimension, greatly reducing the impact of external abnormal interference.

[0087] In another possible embodiment, the first time threshold and the first threshold are determined according to the rated water pressure of the fire hydrant and the importance of the location of the fire hydrant.

[0088] For example, the more important the location of the fire hydrant is, the smaller the first time threshold and the first threshold are set to. The greater the rated water pressure is, the larger the first time threshold and the first threshold are set to.

[0089] In another possible embodiment, the intelligent algorithm is a prediction model based on the LSTM-ARIMA algorithm.

[0090] By adopting the LSTM-ARMA algorithm's prediction model, we can combine the LSTM algorithm's technical advantage of being able to approximate complex nonlinear relationships with the ARIMA algorithm's technical advantage of having a simple model but not requiring the help of exogenous variables. At the same time, it also avoids the ARIMA algorithm's technical problem of intelligently handling linear relationships, further improving the accuracy of predictions.

[0091] In another possible embodiment, Figure 4 As shown, the specific steps of obtaining the water pressure data of the fire hydrant after the second time threshold are:

[0092] S41 transmits the input set to a prediction model based on an LSTM algorithm based on the input set to obtain an LSTM prediction result;

[0093] S42 transmits the input set to a prediction model based on the ARIMA algorithm based on the input set to obtain an ARIMA prediction result;

[0094] S43 obtains water pressure data of the fire hydrant after a second time threshold based on the LSTM prediction result and the ARIMA prediction result.

[0095] In another possible embodiment, the specific formula for the water pressure data of the fire hydrant after the second time threshold is:

[0096]

[0097] K1, K2, and K3 are weights, L1 and R1 are the LSTM prediction results and the ARIMA prediction results respectively.

[0098] By adding the compensation term, the proportion of LSTM prediction results is increased, thereby improving the accuracy of the final algorithm to a certain extent.

[0099] In another possible embodiment, Figure 5 As shown, the specific steps of constructing the fire hydrant status signal are:

[0100] S51 obtains a correction value based on the age of the fire hydrant and the number of times the fire hydrant has an acceleration signal;

[0101] S52 corrects the second threshold value based on the correction value to obtain a first correction threshold value, and determines whether the water pressure data of the fire hydrant after the second time threshold value is less than the first correction threshold value. If so, the process proceeds to step S52; if not, the process outputs a fire hydrant normal state signal;

[0102] S53 outputs a fire hydrant abnormal state signal.

[0103] By setting the correction value, the first correction threshold can be dynamically corrected, thereby further improving the accuracy of judging the abnormal state signal of the fire hydrant and ensuring the safe and reliable use of the fire hydrant.

[0104] In another possible embodiment, the correction value is predicted by a correction value prediction model based on a GM algorithm.

[0105] In another possible embodiment, the calculation formula of the first correction threshold is:

[0106]

[0107] Where D2 and X2 are the second threshold and correction value respectively, wherein the correction value ranges from 0 to 10, and X max is 10.

[0108] By setting the first correction threshold, the universality of the first correction threshold is further improved, and the reliability of the overall model is improved.

[0109] Example 2

[0110] like Figure 6 As shown, a fire hydrant status monitoring system based on the Internet of Things adopts the above-mentioned fire hydrant status monitoring method based on the Internet of Things, including a signal monitoring module, a signal judgment module, a water pressure data prediction module, and a status signal evaluation module; wherein the signal monitoring module is responsible for collecting the water pressure, valve opening status, and acceleration of the fire hydrant to obtain a water pressure signal, a valve opening signal, and an acceleration signal;

[0111] The signal judgment module is responsible for judging the water pressure signal, valve opening signal, and acceleration signal, and transmitting data based on the judgment results;

[0112] The water pressure data prediction module is responsible for predicting the water pressure data of the fire hydrant after the second time threshold, and transmitting the water pressure data of the fire hydrant after the second time threshold to the state signal evaluation module;

[0113] The status signal evaluation module is responsible for obtaining a status signal of the fire hydrant based on water pressure data of the fire hydrant after a second time threshold.

[0114] In the embodiments of the present invention, the term "plurality" refers to two or more, unless otherwise specified. Terms such as "installed," "connected," and "fixed" should be interpreted broadly. For example, "connected" can refer to a fixed connection, a detachable connection, or an integral connection. Those skilled in the art will understand the specific meanings of these terms in the embodiments of the present invention based on specific circumstances.

[0115] In the description of the embodiments of the present invention, it should be understood that the terms "upper" and "lower" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the embodiments of the present invention.

[0116] Throughout this specification, terms such as "one embodiment" and "a preferred embodiment" mean that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0117] The above is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations are possible in the present invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A fire hydrant status monitoring method based on the Internet of Things, characterized in that: Specifically include: S11 collects the water pressure, valve opening state, and acceleration of the fire hydrant to obtain a water pressure signal, a valve opening signal, and an acceleration signal, and determines whether the fire hydrant is in a water use or impact state based on the valve opening signal and the acceleration signal. If not, proceeds to step S12; S12 determines whether the pressure change of the water pressure of the fire hydrant within the first time threshold is greater than the first threshold. If so, it is determined that the water pressure of the fire hydrant is in a potential abnormal state and the process proceeds to step S13. If not, a fire hydrant normal state signal is output; S13 monitors the water temperature of the fire hydrant to obtain a water temperature signal, and uses the water temperature signal, the water pressure signal, the pressure change within the first time threshold, and the water pressure signal at the same time the previous day as an input set, using a prediction model based on an intelligent algorithm to obtain water pressure data of the fire hydrant after a second time threshold; S14 obtains a status signal of the fire hydrant based on the water pressure data of the fire hydrant after a second time threshold; The specific steps to determine if the water pressure at a fire hydrant is in a potentially abnormal state are: S31 determines whether the pressure change of the water pressure of the fire hydrant within the first time threshold is greater than the first threshold. If so, proceed to step S32; S32 determines whether the water pressure of the fire hydrant is in a gradually decreasing state within a third time threshold, wherein the third time threshold is greater than the first time threshold. If so, proceed to step S33; S33: determining that the water pressure of the fire hydrant is in a potential abnormal state; The specific formula for the water pressure data of the fire hydrant after the second time threshold is: Among them, K1, K2, and K3 are weights, L1 and R1 are LSTM prediction results and ARIMA prediction results respectively.

2. The fire hydrant status monitoring method according to claim 1, characterized in that: The specific steps to determine the impact status of a fire hydrant are: S21 determines whether there is an acceleration signal on the fire hydrant, and if so, proceeds to step S22; S22 determines whether the acceleration signal of the fire hydrant is greater than a first acceleration threshold, and if so, proceeds to step S23; S23 determines that the fire hydrant is in a collision state, and records the number of times the fire hydrant has an acceleration signal.

3. The fire hydrant status monitoring method according to claim 1, wherein: The first time threshold and the first threshold are determined according to the rated water pressure of the fire hydrant and the importance of the location of the fire hydrant.

4. The fire hydrant status monitoring method according to claim 1, wherein: The intelligent algorithm is a prediction model based on the LSTM-ARIMA algorithm.

5. The fire hydrant status monitoring method according to claim 4, characterized in that: The specific steps of obtaining the water pressure data of the fire hydrant after the second time threshold are: S41 transmits the input set to a prediction model based on an LSTM algorithm based on the input set to obtain an LSTM prediction result; S42 transmits the input set to a prediction model based on the ARIMA algorithm based on the input set to obtain an ARIMA prediction result; S43 obtains water pressure data of the fire hydrant after a second time threshold based on the LSTM prediction result and the ARIMA prediction result.

6. The fire hydrant status monitoring method according to claim 1, characterized in that: The specific steps of constructing the fire hydrant status signal are: S51 obtains a correction value based on the age of the fire hydrant and the number of times the fire hydrant has an acceleration signal; S52 corrects the second threshold value based on the correction value to obtain a first correction threshold value, and determines whether the water pressure data of the fire hydrant after the second time threshold value is less than the first correction threshold value. If so, the process proceeds to step S52; if not, the process outputs a fire hydrant normal state signal; S53 outputs a fire hydrant abnormal state signal.

7. A fire hydrant status monitoring system based on the Internet of Things, employing the fire hydrant status monitoring method based on the Internet of Things according to any one of claims 1 to 6, comprising a signal monitoring module, a signal judgment module, a water pressure data prediction module, and a status signal evaluation module; wherein the signal monitoring module is responsible for collecting the water pressure, valve opening status, and acceleration of the fire hydrant to obtain a water pressure signal, a valve opening signal, and an acceleration signal; The signal judgment module is responsible for judging the water pressure signal, valve opening signal, and acceleration signal, and transmitting data based on the judgment results; The water pressure data prediction module is responsible for predicting the water pressure data of the fire hydrant after the second time threshold, and transmitting the water pressure data of the fire hydrant after the second time threshold to the state signal evaluation module; The status signal evaluation module is responsible for obtaining a status signal of the fire hydrant based on water pressure data of the fire hydrant after a second time threshold.

Images