Fire-fighting equipment fault joint detection method based on Internet of Things and monitoring center

Abstract

The invention provides a fire-fighting equipment fault joint detection method based on the Internet of Things and a monitoring center. The method comprises the following steps: acquiring an operation environment of fire-fighting equipment and original fire-fighting equipment performance data; establishing a fault prediction model, and substituting the operating environment and the original fire-fighting equipment performance data into the fault prediction model to predict the fault occurrence time of the fire-fighting equipment; if the fault occurrence time of the fire fighting equipment is within the maintenance time, notifying maintenance personnel to maintain before the fault occurrence time; after the fire fighting equipment is maintained, a maintenance factor is formed according to the maintenance degree, the maintenance factor is substituted into the fault prediction model, and new fault occurrence time is obtained; according to the method, the fault occurrence time of the fire-fighting equipment in different environments can be predicted, meanwhile, the maintenance factors are added, the fault time of the maintained fire-fighting equipment can be predicted again, the safety of the fire-fighting equipment is guaranteed, and the hidden danger that the fire-fighting equipment breaks down when needing to be used is prevented.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire-fighting equipment fault monitoring, and particularly relates to a fire-fighting equipment fault joint detection method based on Internet of Things and a monitoring center. BACKGROUND

[0002] In urban comprehensive management, it is also extremely important to widely set fire-fighting equipment, and the fire risk problems existing in urban construction need to be solved through the perfection of fire-fighting equipment, and the construction and maintenance of urban fire-fighting equipment play an extremely important role in ensuring urban safety; the timely extinguishing of fire and the fire-fighting passage and related fire-fighting equipment at the fire site are related, and the state of the existing fire-fighting equipment is mostly monitored by manual operation, which is prone to missing detection problems and time-consuming and laborious;

[0003] At the same time, since the installation of fire-fighting equipment is very scattered, it is necessary to have a new management method to real-time grasp the working state of the fire-fighting equipment. With the development of Internet of Things technology, through various wired and wireless networks, objects and the Internet can be integrated, and the information of the objects can be accurately transmitted to the Internet in real time. Therefore, by installing sensors on fire-fighting equipment to collect related information in real time and transmitting the information through the network, the running state of the scattered fire-fighting equipment can be collected. On this basis, the fire-fighting equipment monitoring platform software can realize the centralized management of the state of the scattered and large number of fire-fighting equipment, and overcome the problems encountered in the current manual management of fire-fighting equipment.

[0004] Therefore, the present application provides a fire-fighting equipment fault joint detection method based on Internet of Things and a monitoring center. SUMMARY

[0005] In order to solve the above problems, the present application provides a fire-fighting equipment fault joint detection method based on Internet of Things and a monitoring center to more accurately solve the above-mentioned problems.

[0006] The main purpose of the present application is to establish a monitoring center of fire-fighting equipment, to obtain real-time working data of the fire-fighting equipment in working through a 5G mobile communication wireless transmission network, to predict the use and expected service life of the fire-fighting equipment by combining a fault prediction model, to remotely monitor the fire-fighting equipment, to repair the fire-fighting equipment before the fault occurs, and to replace the fire-fighting equipment before the service life arrives, so as to prevent the fire-fighting equipment from being unable to use when a fire accident occurs.

[0007] The present application is realized by the following technical scheme:

[0008] The present application provides a fire-fighting equipment fault joint detection method based on Internet of Things, which comprises:

[0009] S1: obtaining the running environment and original fire-fighting equipment performance data of the fire-fighting equipment;

[0010] S2: establishing a fault prediction model, and substituting the running environment and the original fire-fighting equipment performance data into the fault prediction model to predict the time of failure of the fire-fighting equipment;

[0011] S3: if the time of failure of the fire-fighting equipment is within the maintenance time, notifying the maintenance personnel to perform maintenance before the time of failure;

[0012] S4: after the fire-fighting equipment is maintained, a maintenance factor is formed according to the degree of maintenance, and the maintenance factor is substituted into the fault prediction model to obtain a new time of failure.

[0013] Further, the fire-fighting equipment fault joint detection method and the monitoring center based on the Internet of Things, in the S1, the original fire-fighting equipment performance data is compared by the real-time running parameter of the fire-fighting equipment and the running parameter rule;

[0014]

[0015] Wherein c is a comparison value, r i and s i respectively are the i-th characteristic value in the real-time running parameter and the i-th characteristic value in the running parameter rule;

[0016] c is 1 in the normal state, and the value of c is less than 1 in different running environments.

[0017] Further, the fire-fighting equipment fault joint detection method based on the Internet of Things, in the S2, the method for establishing a fault prediction model is:

[0018] Collecting historical data of the same type of fire-fighting equipment;

[0019] Building training data, pairing the historical data of the fire-fighting equipment in the same environment to obtain the historical data of the fire-fighting equipment in the same environment;

[0020] Building a training model, putting the historical data of the fire-fighting equipment in the same environment into the training model to obtain the correlation thereof with the environment;

[0021] According to the correlation, the influence factor of the environment on the fire-fighting equipment is calculated;

[0022] According to the influence factor, the working life of the fire-fighting equipment in this environment is determined.

[0023] Further, the fire-fighting equipment fault joint detection method based on the Internet of Things comprises:

[0024] Collecting the failure time of the fire-fighting equipment in the same environment, and obtaining a fault prediction model according to a multiple fitting formula:

[0025] Y = AX 2 + BX + C;

[0026] Wherein, A, B, C are constants, X is the original fire-fighting equipment performance data, Y is the predicted fire-fighting equipment performance data.

[0027] Further, the fire-fighting equipment fault joint detection method based on the Internet of Things comprises:

[0028]

[0029] Wherein t is the time running in the same environment, a is the influence factor;

[0030] The threshold value of c is set, when c falls to a fixed threshold value, the fire-fighting equipment will fail;

[0031] Then:

[0032]

[0033] t can be accurately calculated.

[0034] Further, the fire-fighting equipment fault joint detection method based on the Internet of Things, in the S4, the method for obtaining the maintenance factor comprises:

[0035] The maintenance factor is obtained according to the ratio of the performance data of the fire-fighting equipment before and after maintenance, and the maintenance factor represents the maintenance degree of the fire-fighting equipment. In an environment, the performance data of the fire-fighting equipment will weaken with time, and regular maintenance will restore part of the performance data of the fire-fighting equipment. It is assumed that the performance degradation data of the fire-fighting equipment in an environment is a curve, the starting point of the curve is 1, when it falls to a fixed threshold value, the fire-fighting equipment cannot work normally, and in the process of falling, the maintenance personnel will regularly maintain the fire-fighting equipment to restore part of the performance data of the fire-fighting equipment. The attenuation coefficient of the performance data of the fire-fighting equipment in this environment will change.

[0036] Further, the fire-fighting equipment fault joint detection method based on the Internet of Things comprises:

[0037]

[0038] T is the fixed maintenance time, that is, the working time of the fire-fighting equipment in the same environment, Y' is the performance data of the fire-fighting equipment when the fire-fighting equipment is maintained, a is the influence factor, f is the curve, there are n Y' on the curve, and the value of a changes after maintenance, that is, the slope of each segment of the curve is different.

[0039] The application discloses a fire-fighting equipment fault joint monitoring center based on Internet of Things, and relates to the technical field of fire-fighting equipment fault joint monitoring.

[0040] The application discloses a fire-fighting equipment fault joint monitoring center based on Internet of Things, and relates to the technical field of fire-fighting equipment fault joint monitoring.

[0041] The application discloses a fire-fighting equipment fault joint monitoring center based on Internet of Things, and relates to the technical field of fire-fighting equipment fault joint monitoring.

[0042] The application discloses a fire-fighting equipment fault joint monitoring center based on Internet of Things, and relates to the technical field of fire-fighting equipment fault joint monitoring.

[0043] The application discloses a fire-fighting equipment fault joint monitoring center based on Internet of Things, and relates to the technical field of fire-fighting equipment fault joint monitoring.

[0044] Further, the fire-fighting equipment fault joint monitoring center based on Internet of Things further comprises the following steps: data acquisition and transmission into the monitoring center by using 5G mobile information transmission technology; data judgment by the monitoring center by using a fault prediction model; and determination of the fault occurrence time and the service life of the fire-fighting equipment.

[0045] The application discloses a fire-fighting equipment fault joint monitoring center based on Internet of Things, and relates to the technical field of fire-fighting equipment fault joint monitoring.

[0046] Compared with the prior art, the fire-fighting equipment monitoring in the prior art generally adopts manual verification, and the time cost is too high; the fire-fighting equipment fault monitoring cannot realize real-time monitoring; real-time working data of the fire-fighting equipment during working is acquired through a 5G mobile communication wireless transmission network, the fault prediction model is combined to predict the fault time of the fire-fighting equipment, the maintenance factor is used to predict the fault time of the fire-fighting equipment after maintenance, the fire-fighting equipment is remotely monitored, and the fire-fighting equipment is maintained before the fault of the fire-fighting equipment occurs, so that the situation that the fire-fighting equipment cannot be used when a fire accident occurs is prevented.

[0047] The fire-fighting equipment fault joint monitoring center based on Internet of Things can predict the fault occurrence time of the fire-fighting equipment under different environments, and the maintenance factor is added to predict the fault time of the fire-fighting equipment after maintenance, so that the safety of the fire-fighting equipment is ensured, and the hidden danger that the fire-fighting equipment fails when needed is prevented.

[0048] The application proposes the establishment of a monitoring center, which eliminates the limitations of manual inspection of fire-fighting equipment and is conducive to the core idea of scientific and technological development. BRIEF DESCRIPTION OF DRAWINGS

[0049] Fig. 1 A flowchart of the fire-fighting equipment fault joint detection method based on the Internet of Things according to the application;

[0050] Fig. 2 A fire-fighting equipment performance data diagram in an embodiment of the application;

[0051] Fig. 3 A remote monitoring center system principle diagram in an embodiment of the application. DETAILED DESCRIPTION

[0052] In order to more clearly and completely illustrate the technical solutions of the application, the application will be further described below with reference to the drawings.

[0053] Please refer to Figs. 1-3 The application proposes a fire-fighting equipment fault joint detection method based on the Internet of Things and a monitoring center.

[0054] In this embodiment, a fire-fighting equipment fault joint detection method based on the Internet of Things includes:

[0055] S1: Obtain the running environment of the fire-fighting equipment and the original fire-fighting equipment performance data;

[0056] S2: Establish a fault prediction model, and substitute the running environment and the original fire-fighting equipment performance data into the fault prediction model to predict the time of failure of the fire-fighting equipment;

[0057] S3: If the time of failure of the fire-fighting equipment is within the maintenance time, notify the maintenance personnel to perform maintenance before the time of failure;

[0058] S4: After the fire-fighting equipment is maintained, form a maintenance factor according to the degree of maintenance, substitute the maintenance factor into the fault prediction model, and obtain a new time of failure.

[0059] In a specific embodiment, it is assumed that the fire-fighting system of a large commercial building includes smoke detectors, water spray fire extinguishing systems, and alarm systems.

[0060] Data collection:

[0061] Equipment running environment: The average indoor temperature of the building is 25℃, and the humidity is 60%.

[0062] Original performance data: Real-time acquisition of parameters such as reaction time, battery voltage and sensor sensitivity of the smoke detector; at the same time, comparison with standard parameters provided by the manufacturer;

[0063] Establishment of failure prediction model:

[0064] Collect historical failure data of smoke detectors in the same environment;

[0065] Use these data to build a training model and calculate the environmental impact factor of the smoke detector, such as its reaction time extension, the reaction time of the factory state is 0.2S, and the failure reaction time is 2S;

[0066] Suppose we get the following model through multiple fitting: (Y = AX 2 + BX + C), where A, B, and C are constants, X is the original fire-fighting equipment performance data, and Y is the predicted performance data;

[0067] Prediction and notification:

[0068] Suppose our model predicts that the smoke detector will fail in 3 months under the current operating environment and performance data;

[0069] If routine maintenance has been planned within these 3 months;

[0070] Maintenance and update:

[0071] The maintenance team maintains the smoke detector before the predicted failure time;

[0072] After maintenance, the performance data of the smoke detector has recovered, for example, the reaction time has increased from 0.9 seconds to 0.5 seconds;

[0073] According to the performance data before and after maintenance, the maintenance factor is calculated, and then this factor is substituted into the prediction model to update the failure prediction time; for example, through maintenance, the new predicted failure time may be extended to 5 months later.

[0074] In S1, the original fire-fighting equipment performance data is compared with the operating parameter law through the real-time operating parameters of the fire-fighting equipment;

[0075]

[0076] Where c is the comparison value, r i and s i are the i-th characteristic value in the real-time operating parameter and the i-th characteristic value in the operating parameter law, respectively;

[0077] Under normal conditions, c is 1, and in different operating environments, the value of c is less than 1.

[0078] In S2, the method for establishing the fault prediction model is:

[0079] Collecting historical data of the same type of fire-fighting equipment;

[0080] Building training data, pairing the historical data of the fire-fighting equipment in the same environment to obtain the historical data of the fire-fighting equipment in the same environment;

[0081] Building a training model, putting the historical data of the fire-fighting equipment in the same environment into the training model to obtain the correlation with the environment;

[0082] According to the correlation, calculating the influence factor of the environment on the fire-fighting equipment;

[0083] According to the influence factor, determining the working life of the fire-fighting equipment in this environment.

[0084] Collecting the time of failure of the fire-fighting equipment in the same environment, and obtaining the fault prediction model according to the multiple fitting formula:

[0085] Y = AX + BX + C; 2

[0086] Wherein, A, B, C are constants, X is the original fire-fighting equipment performance data, and Y is the predicted fire-fighting equipment performance data.

[0087]

[0088] Wherein t is the running time in the same environment, and a is the influence factor;

[0089] Setting a threshold value for c, when c falls below the fixed threshold value, the fire-fighting equipment will fail;

[0090] Then:

[0091]

[0092] t can be accurately calculated.

[0093] In S4, the method for obtaining the maintenance factor includes:

[0094] ​The maintenance factor is obtained according to the ratio of performance data of the fire-fighting equipment before and after maintenance, and represents the maintenance degree of the fire-fighting equipment. In an environment, the performance data of the fire-fighting equipment will weaken over time, and regular maintenance can restore part of the performance data of the fire-fighting equipment. Assuming that the performance degradation data of the fire-fighting equipment in an environment is a curve, the starting point of the curve is 1, and when it falls to a fixed threshold, the fire-fighting equipment cannot work normally. During the falling process, the maintenance personnel will regularly maintain the fire-fighting equipment to restore part of the performance data of the fire-fighting equipment. The attenuation coefficient of the performance data of the fire-fighting equipment in this environment will change.

[0095]

[0096] T is the fixed maintenance time, that is, the working time of the fire-fighting equipment in the same environment, Y' is the performance data of the fire-fighting equipment when it is maintained, a is the influence factor, f is the curve, there are n Y' on the curve, and the value of a changes after maintenance, that is, the slope of each segment of the curve is different.

[0097] In another embodiment, data collection:

[0098] First, collect the operating environment and original performance data of all fire-fighting equipment (such as fire pumps, fire alarms, etc.). For example, the real-time operating parameters of a fire pump may include its speed, pressure, current, etc. These data are compared with standard operating parameter rules (such as parameters provided by the manufacturer or historical data) to obtain comparison values c.

[0099] Model establishment:

[0100] Then, use historical data to establish a failure prediction model. For example, the failure data of the same type of fire pump in the same environment in the past five years may be collected.

[0101] Using these data, a training model can be constructed to calculate the influence factor of the environment on the equipment and determine the expected service life of the equipment in a specific environment.

[0102] For example, it may be found that the expected service life of the fire pump will be shortened by 10% in a high-temperature and high-humidity environment.

[0103] Failure prediction:

[0104] Then, the fire department will substitute the current operating environment and performance data into the failure prediction model to predict the failure time of the fire-fighting equipment.

[0105] For example, if it is summer and the environmental temperature and humidity are high, the model may predict that the fire pump may fail in the next three months.

[0106] Maintenance notification:

[0107] If the predicted failure time is within the maintenance time, such as the next three months, the fire station will notify the maintenance personnel for maintenance before the failure occurs.

[0108] Maintenance and model update:

[0109] The maintenance personnel will maintain the equipment according to the notification.

[0110] After maintenance, the performance data of the equipment are obtained, such as the speed, pressure, and current of the fire pump, and then the maintenance factor is calculated.

[0111] This maintenance factor is substituted into the failure prediction model to obtain a new failure prediction time.

[0112] A fire equipment failure joint monitoring center based on Internet of Things, the monitoring center is used to realize any one of the fire equipment failure joint monitoring center based on Internet of Things;

[0113] Acquisition unit: acquire the running environment and original fire equipment performance data of the fire equipment;

[0114] Establishment unit: establish a failure prediction model, substitute the running environment and original fire equipment performance data into the failure prediction model to predict the time of failure of the fire equipment;

[0115] Judgment unit: if the time of failure of the fire equipment is within the maintenance time, notify the maintenance personnel for maintenance before the time of failure;

[0116] Calculation unit: after the fire equipment is maintained, form a maintenance factor according to the degree of maintenance, substitute the maintenance factor into the failure prediction model to obtain a new time of failure.

[0117] Further, the fire equipment failure joint monitoring center based on Internet of Things, the monitoring center further comprises using 5G mobile information transmission technology, acquiring and transmitting data to the monitoring center, using the failure prediction model to judge the data by the monitoring center, and the judged result is the failure occurrence time and service life of the fire equipment; the monitoring center is composed of four parts of field control system, 5G mobile information transmission technology, remote monitoring system, and failure prediction model, the equipment owner and user acquire and view the real-time operation state of the fire equipment through the monitoring system, acquire the recent operation state of the equipment through the query statistical function, and realize the prediction of the failure time of the fire equipment.

[0118] In one embodiment, sensor network, data mining and machine learning, fault diagnosis system, remote monitoring and remote control are respectively used to realize the above-mentioned fire equipment failure joint detection method based on Internet of Things.

[0119] Sensor network: By deploying various types of sensors such as temperature sensors, humidity sensors, pressure sensors, etc. in fire-fighting equipment, the running state of the equipment and environmental parameters are monitored in real time. These sensors can collect a large amount of data and transmit it to the central server for analysis and processing. By analyzing these data, abnormal behavior and potential failures of the equipment can be found.

[0120] Data mining and machine learning: Use data mining and machine learning algorithms to analyze historical data and establish a fault prediction model; by studying the running data of the equipment, different failure modes and rules can be found, so as to predict the failure of the equipment in advance; these algorithms can be adjusted and optimized according to real-time data to improve the prediction accuracy.

[0121] Fault diagnosis system: Based on the fault prediction model and expert experience, a fault diagnosis system is developed, which can automatically identify equipment failures and provide corresponding maintenance suggestions; this can reduce manual intervention and improve the efficiency of fault detection and maintenance.

[0122] Remote monitoring and remote control: Combined with Internet of Things and 5G technology, remote monitoring and remote control of fire-fighting equipment are realized. Through remote monitoring, the running state and parameters of the equipment can be obtained in real time, and real-time analysis and judgment can be made. At the same time, through the remote control system, the equipment can be operated and maintained remotely, reducing the need for personnel to go on-site maintenance.

[0123] Of course, the present application can have other various embodiments, and based on the embodiments, other embodiments obtained by those skilled in the art without any creative labor fall within the scope of the present application.

Claims

1. A method for joint fault detection of fire-fighting equipment based on the Internet of Things, characterized in that, include: S1: Obtain the operating environment and raw performance data of the fire-fighting equipment; S2: Establish a fault prediction model, and substitute the operating environment and original fire equipment performance data into the fault prediction model to predict the time when the fire equipment will fail. S3: If the fire-fighting equipment malfunctions during the maintenance period, the maintenance personnel shall be notified to perform maintenance before the malfunction occurs. S4: After the fire-fighting equipment has been maintained, a maintenance factor is formed based on the degree of maintenance. The maintenance factor is then substituted into the fault prediction model to obtain the new time of failure.

2. The method and monitoring center for joint fault detection of fire-fighting equipment based on the Internet of Things as described in claim 1, characterized in that, In step S1, the original performance data of the fire-fighting equipment is compared with the real-time operating parameters of the fire-fighting equipment based on the pattern of the operating parameters. Where c is the comparison value, and r i and s i These are the i-th feature value in the real-time operating parameters and the i-th feature value in the pattern of operating parameters, respectively. Under normal conditions, c is 1. However, in different operating environments, the value of c is less than 1.

3. The method for joint detection of fire equipment faults based on the Internet of Things according to claim 1, characterized in that, In S2, the method for establishing the fault prediction model is as follows: Collect historical data on the same type of fire-fighting equipment; Training data is constructed by pairing historical data of fire-fighting equipment in the same environment to obtain historical data of fire-fighting equipment in the same environment. A training model is constructed by inputting historical data of fire-fighting equipment under the same environment into the training model to obtain its correlation with the environment. The influence factors of the environment on the fire-fighting equipment are calculated based on the correlation. The service life of the fire-fighting equipment under this environment is determined based on the influencing factors.

4. The method for joint detection of fire equipment faults based on the Internet of Things according to claim 3, characterized in that, include: By collecting the failure times of fire-fighting equipment under the same environment, a failure prediction model is obtained based on multiple fitting formulas. Y=AX 2 +BX+C; Where A, B, and C are constants, X is the original performance data of the fire-fighting equipment, and Y is the predicted performance data of the fire-fighting equipment.

5. The method for joint fault detection of fire-fighting equipment based on the Internet of Things according to claim 4, characterized in that, include: Where t is the time spent running under the same environment, and a is the influencing factor; Set a threshold for c; when c drops to a fixed threshold, the fire-fighting equipment will malfunction. Then we have: t can be calculated accurately.

6. The method for joint detection of fire equipment faults based on the Internet of Things according to claim 5, characterized in that, In step S4, the method for obtaining the maintenance factor includes: The maintenance factor is obtained by comparing the performance data of the fire-fighting equipment before and after maintenance. The maintenance factor represents the degree of maintenance of the fire-fighting equipment. Under certain conditions, the performance data of the fire-fighting equipment will weaken over time. Regular maintenance will restore some of the performance data of the fire-fighting equipment. Assuming that the performance degradation data of the fire-fighting equipment under certain conditions is a curve with the starting point of the curve being 1, when it drops to a fixed threshold, the fire-fighting equipment cannot work normally. During the decline, maintenance personnel will regularly maintain the fire-fighting equipment to restore some of the performance data. The attenuation coefficient of the performance data of the fire-fighting equipment under this condition will change.

7. The method for joint fault detection of fire-fighting equipment based on the Internet of Things according to claim 6, characterized in that, include: T is the fixed maintenance time, which is the working time of the fire-fighting equipment under the same environment. Y' is the performance data of the fire-fighting equipment during maintenance. a is the influencing factor. f is a curve with n Y's. After maintenance, the value of a will change, that is, the slope of each segment of the curve is different.

8. A joint monitoring center for fire equipment faults based on the Internet of Things, characterized in that, The monitoring center is used to implement the Internet of Things-based joint monitoring center for fire equipment failures as described in any one of claims 1-7; Acquisition Unit: Acquires the operating environment and raw performance data of the fire-fighting equipment; Establishment Unit: Establish a fault prediction model, and substitute the operating environment and original fire equipment performance data into the fault prediction model to predict the time when the fire equipment will fail; Judgment Unit: If the fire-fighting equipment malfunctions within the maintenance period, then the maintenance personnel will be notified to perform maintenance before the malfunction occurs. Calculation unit: After the fire-fighting equipment has been maintained, a maintenance factor is formed based on the degree of maintenance. The maintenance factor is then substituted into the fault prediction model to obtain the new time of failure.

9. The IoT-based joint monitoring center for fire equipment faults according to claim 8, characterized in that, The monitoring center also utilizes 5G mobile information transmission technology to acquire and transmit data. The monitoring center then uses a fault prediction model to make data judgments, and the judgment results include the failure time and service life of the fire-fighting equipment. The monitoring center consists of four parts: a field control system, 5G mobile information transmission technology and a remote monitoring system, and a fault prediction model. Equipment owners and users can view the real-time operating status of the fire-fighting equipment through the monitoring system, and obtain the recent operating status of the equipment through query and statistical functions, thereby predicting the failure time of the fire-fighting equipment.

Images