Fire-fighting facility maintenance system based on big data

Abstract

The invention discloses a fire-fighting facility maintenance system based on big data, and relates to the field of fire-fighting facility management. Comprising a data acquisition module which is connected with fire-fighting equipment through a sensing network and is used for acquiring operation parameters and environment data of the fire-fighting equipment; the data transmission module is used for encrypting the acquired data and uploading the encrypted data to a cloud server; the data storage and management module is used for cleaning, classifying and storing the received data, and the big data analysis and early warning module is used for carrying out deep learning and mode recognition on the stored data. All-day real-time monitoring of the state of the fire-fighting equipment, intelligent health diagnosis based on machine learning, fault risk predictive early warning and intelligent closed-loop management of the maintenance process can be achieved, so that passive response is changed into active maintenance, the maintenance efficiency is improved, and it is guaranteed that the equipment is in a good combat readiness state all the time.

Description

Technical Field

[0001] This invention relates to the field of fire protection facility management, and more particularly to a fire protection facility maintenance system based on big data. Background Technology

[0002] Traditional fire protection facility maintenance and management (such as fire extinguishers, fire hydrants, sprinkler systems, etc.) mainly relies on regular manual inspections. This method has many drawbacks: First, it is inefficient, consuming a lot of manpower and resources, and inspection records are prone to errors and falsification; second, it lacks timeliness, making it impossible to monitor the status of facilities in real time, and failing to promptly detect faults or damages that occur during inspection intervals (such as leaks in fire pipelines or depressurization of fire extinguishers); finally, it lacks foresight, unable to predict the performance degradation and potential failures of facilities, and can only perform reactive maintenance or fixed periodic replacements. This can lead to waste due to over-maintenance or failure due to insufficient maintenance, resulting in significant loss of life and property during a fire.

[0003] The development of IoT and big data technologies has made it possible to solve the above problems. However, some so-called intelligent fire protection systems at present only realize remote data collection and simple threshold alarms (such as alarms when the pressure is below a certain value). In essence, they are still "notifying after the fact" and have not carried out in-depth data mining and intelligent analysis, thus failing to achieve true "predictive maintenance" and intelligent management.

[0004] Therefore, this invention proposes a fire protection facility maintenance system based on big data. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a fire protection facility maintenance system based on big data.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A big data-based fire protection facility maintenance system includes: The data acquisition module is connected to the fire protection facilities via a sensor network and is used to collect the operating parameters of the fire protection facilities and environmental data. The data transmission module encrypts the collected data and uploads it to the cloud server. The data storage and management module cleans, classifies, and stores the received data. The big data analysis and early warning module performs deep learning and pattern recognition on the stored data to generate facility health assessment reports and predictive maintenance early warnings. The visualization interaction and maintenance management module presents the analysis results in a graphical way, generates and maintains intelligent work order processes, and realizes closed-loop management of the entire life cycle.

[0007] Preferably, the workflow of the big data-based fire protection facility maintenance system includes the following steps: S1: The data acquisition module collects data according to a preset period or triggering conditions, and uploads it after encryption by the data transmission module; S2: The data storage and management module receives and processes the data before storing it in the corresponding database; S3: The big data analysis and early warning module calls data periodically or in real time to perform model calculations and generate status reports and early warnings; S4: The early warning information is pushed to the visualization interaction and maintenance management module, which generates a maintenance work order and assigns it to the designated personnel; S5: Maintenance personnel perform tasks and provide feedback via mobile devices, creating a closed data loop.

[0008] Preferably, in step S2, the data storage and management module processes the data, including handling duplicate and missing values, specifically including the following steps: S21: Establish a two-dimensional coordinate system with the time axis as the horizontal axis and the data as the vertical axis; S22: Select the corresponding node on the horizontal axis based on the data acquisition frequency. S23: Fill the obtained data into the vertical coordinate of each node. If node data is missing, leave the corresponding gap. If node data is repeated, delete all duplicate values ​​to form a gap. S24: According to the formula Fill in the missing data located at the i-th node. For the data of the i-th node, This is for filling function logic; In step S24 or .

[0009] Preferably, the data acquisition module includes: Pressure sensors are used to monitor the pressure values ​​inside fire hydrants and fire extinguishers; Liquid level sensors are used to monitor the liquid level in fire water tanks and storage tanks; Temperature / humidity sensors are used to monitor the temperature and humidity of the facility environment; Image acquisition unit is used to identify the appearance of fire hydrants, fire extinguishers, and QR code labels; Electronic tags are used to provide a unique identifier for each facility.

[0010] Preferably, the data acquisition module initiates data acquisition through two mechanisms: periodic self-testing and event triggering, and converts the acquired analog signals into digital signals.

[0011] Preferably, the data transmission module adopts a multi-mode converged communication method, specifically including NB-IoT / LoRa wireless low-power wide area network technology, which is used for remote, low-power data transmission; it also includes Wi-Fi / Ethernet wired transmission technology, which is used for short-range, high-bandwidth data backhaul within the building; the data transmission module has a built-in data encryption chip, which uses the national cryptographic SM4 or AES algorithm to encrypt the transmitted data end-to-end.

[0012] Preferably: the data storage and management module is based on a cloud platform architecture, wherein: A distributed file system is used to store massive amounts of unstructured time-series data; Relational databases are used to store structured data such as facility attributes and user information; A time-series database is used to store and process the timestamped dynamic data streams uploaded by sensors.

[0013] Preferably, the big data analysis and early warning module has a built-in facility health assessment model and a fault prediction model.

[0014] Preferably, the health assessment model calculates a comprehensive health score by weighted fusion of multi-dimensional real-time data and static data, and assesses the health of the facility based on the comprehensive health score.

[0015] Preferably, the fault prediction model adopts an LSTM-based time series prediction model, the logic of which is as follows: A1: Use sensor data over a continuous period of time as input; A2: LSTM captures long-term dependencies and periodic patterns in data through its internal control mechanism, and outputs predicted values ​​of data points for a future period of time; A3: The deviation sequence between the predicted value and the actual measured value is input into the classifier again to determine whether there are potential abnormal patterns in the sequence and to identify the specific fault type.

[0016] The beneficial effects of this invention are as follows: This invention enables 24 / 7 real-time monitoring of fire protection facility status, intelligent health diagnosis based on machine learning, predictive early warning of fault risks, and intelligent closed-loop management of maintenance processes, thereby transforming passive response into proactive maintenance, improving maintenance efficiency, and ensuring that facilities are always in a good state of readiness. Attached Figure Description

[0017] Figure 1 This is a flowchart of the big data-based fire protection facility maintenance system proposed in this invention. Detailed Implementation

[0018] The technical solution of the present invention will be further described in detail below with reference to specific embodiments.

[0019] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "setting" should be interpreted broadly. For example, they can refer to a fixed connection or setting, a detachable connection or setting, or an integral connection or setting. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances. Example

[0020] A big data-based fire protection facility maintenance system includes: The data acquisition module is connected to the fire protection facilities via a sensor network and is used to collect the operating parameters of the fire protection facilities and environmental data. The data transmission module encrypts the collected data and uploads it to the cloud server. The data storage and management module cleans, classifies, and stores the received data. The big data analysis and early warning module performs deep learning and pattern recognition on the stored data to generate facility health assessment reports and predictive maintenance early warnings. The visualization interaction and maintenance management module presents the analysis results in a graphical way, generates and maintains intelligent work order processes, and realizes closed-loop management of the entire life cycle.

[0021] The workflow of the big data-based fire protection facility maintenance system includes the following steps: S1: The data acquisition module collects data according to a preset period or triggering conditions, and uploads it after encryption by the data transmission module; S2: The data storage and management module receives and processes the data before storing it in the corresponding database; S3: The big data analysis and early warning module calls data periodically or in real time to perform model calculations and generate status reports and early warnings; S4: The early warning information is pushed to the visualization interaction and maintenance management module, which generates a maintenance work order and assigns it to the designated personnel; S5: Maintenance personnel perform tasks and provide feedback via mobile devices, creating a closed data loop.

[0022] The data acquisition module includes: Pressure sensors are used to monitor the pressure values ​​inside fire hydrants and fire extinguishers; Liquid level sensors are used to monitor the liquid level in fire water tanks and storage tanks; Temperature / humidity sensors are used to monitor the temperature and humidity of the facility environment; Image acquisition unit is used to identify the appearance of fire hydrants, fire extinguishers, and QR code labels; Electronic tags are used to provide a unique identifier for each facility.

[0023] The data acquisition module initiates data acquisition through two mechanisms: periodic self-testing and event triggering, and converts the acquired analog signals into digital signals.

[0024] The data transmission module adopts a multi-mode converged communication approach, specifically including NB-IoT / LoRa wireless low-power wide area network technology, which is used for remote, low-power data transmission; it also includes Wi-Fi / Ethernet wired transmission technology, which is used for short-range, high-bandwidth data backhaul within buildings; the data transmission module has a built-in data encryption chip, which uses the national cryptographic SM4 or AES algorithm to encrypt the transmitted data end-to-end, ensuring the security and integrity of the data during transmission over public networks.

[0025] The data storage and management module is based on a cloud platform architecture, wherein: A distributed file system is used to store massive amounts of unstructured time-series data; Relational databases are used to store structured data such as facility attributes and user information; A time-series database is used to store and process the timestamped dynamic data streams uploaded by sensors.

[0026] The big data analysis and early warning module has a built-in facility health assessment model and a fault prediction model; The health assessment model calculates a comprehensive health score by weighted fusion of multi-dimensional real-time data and static data, and assesses the health of the facility based on the comprehensive health score. Example

[0027] A big data-based fire protection facility maintenance system includes: The data acquisition module is connected to the fire protection facilities via a sensor network and is used to collect the operating parameters of the fire protection facilities and environmental data. The data transmission module encrypts the collected data and uploads it to the cloud server. The data storage and management module cleans, classifies, and stores the received data. The big data analysis and early warning module performs deep learning and pattern recognition on the stored data to generate facility health assessment reports and predictive maintenance early warnings. The visualization interaction and maintenance management module presents the analysis results in a graphical way, generates and maintains intelligent work order processes, and realizes closed-loop management of the entire life cycle.

[0028] The workflow of the big data-based fire protection facility maintenance system includes the following steps: S1: The data acquisition module collects data according to a preset period or triggering conditions, and uploads it after encryption by the data transmission module; S2: The data storage and management module receives and processes the data before storing it in the corresponding database; S3: The big data analysis and early warning module calls data periodically or in real time to perform model calculations and generate status reports and early warnings; S4: The early warning information is pushed to the visualization interaction and maintenance management module, which generates a maintenance work order and assigns it to the designated personnel; S5: Maintenance personnel perform tasks and provide feedback via mobile devices, creating a closed data loop.

[0029] In step S2, the data storage and management module processes the data, including handling duplicate and missing values, specifically including the following steps: S21: Establish a two-dimensional coordinate system with the time axis as the horizontal axis and the data as the vertical axis; S22: Select the corresponding node on the horizontal axis based on the data acquisition frequency. S23: Fill the obtained data into the vertical coordinate of each node. If node data is missing, leave the corresponding gap. If node data is repeated, delete all duplicate values ​​to form a gap. S24: According to the formula Fill in the missing data located at the i-th node. For the data of the i-th node, This is for filling function logic.

[0030] In step S24 or .

[0031] The data acquisition module includes: Pressure sensors are used to monitor the pressure values ​​inside fire hydrants and fire extinguishers; Liquid level sensors are used to monitor the liquid level in fire water tanks and storage tanks; Temperature / humidity sensors are used to monitor the temperature and humidity of the facility environment; Image acquisition unit is used to identify the appearance of fire hydrants, fire extinguishers, and QR code labels; Electronic tags are used to provide a unique identifier for each facility.

[0032] The data acquisition module initiates data acquisition through two mechanisms: periodic self-testing and event triggering, and converts the acquired analog signals into digital signals.

[0033] The data transmission module adopts a multi-mode converged communication approach, specifically including NB-IoT / LoRa wireless low-power wide area network technology, which is used for remote, low-power data transmission; it also includes Wi-Fi / Ethernet wired transmission technology, which is used for short-range, high-bandwidth data backhaul within buildings; the data transmission module has a built-in data encryption chip, which uses the national cryptographic SM4 or AES algorithm to encrypt the transmitted data end-to-end, ensuring the security and integrity of the data during transmission over public networks.

[0034] The data storage and management module is based on a cloud platform architecture, wherein: A distributed file system is used to store massive amounts of unstructured time-series data; Relational databases are used to store structured data such as facility attributes and user information; A time-series database is used to store and process the timestamped dynamic data streams uploaded by sensors.

[0035] The big data analysis and early warning module has a built-in facility health assessment model and a fault prediction model; The health assessment model calculates a comprehensive health score by weighted fusion of multi-dimensional real-time data and static data, and assesses the health of the facility based on the comprehensive health score. The fault prediction model adopts a time-series prediction model based on LSTM (Long Short-Term Memory Network). Using historical normal operation data and historical fault data as training sets, it learns the mapping relationship between data and fault types to predict the probability of a fault occurring within a specific future time period. When the probability exceeds a preset threshold, it automatically generates a warning message. Specifically, it includes the following steps: A1: Input sensor data over a continuous period of time (such as pressure fluctuation sequences or temperature change sequences); A2: LSTM captures long-term dependencies and periodic patterns in data through its internal control mechanism, and outputs predicted values ​​of data points for a future period of time; A3: The deviation sequence between the predicted value and the actual measured value is input into the classifier again to determine whether there are potential abnormal patterns in the sequence and to identify the specific fault type.

[0036] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A fire protection facility maintenance system based on big data, characterized in that, include: The data acquisition module is connected to the fire protection facilities via a sensor network and is used to collect the operating parameters of the fire protection facilities and environmental data. The data transmission module encrypts the collected data and uploads it to the cloud server. The data storage and management module cleans, classifies, and stores the received data. The big data analysis and early warning module performs deep learning and pattern recognition on the stored data to generate facility health assessment reports and predictive maintenance early warnings. The visualization interaction and maintenance management module presents the analysis results in a graphical way, generates and maintains intelligent work order processes, and realizes closed-loop management of the entire life cycle.

2. The fire protection facility maintenance system based on big data according to claim 1, characterized in that, The workflow of the big data-based fire protection facility maintenance system includes the following steps: S1: The data acquisition module collects data according to a preset period or triggering conditions, and uploads it after encryption by the data transmission module; S2: The data storage and management module receives and processes the data before storing it in the corresponding database; S3: The big data analysis and early warning module calls data periodically or in real time to perform model calculations and generate status reports and early warnings; S4: The early warning information is pushed to the visualization interaction and maintenance management module, which generates a maintenance work order and assigns it to the designated personnel; S5: Maintenance personnel perform tasks and provide feedback via mobile devices, creating a closed data loop.

3. The fire protection facility maintenance system based on big data according to claim 2, characterized in that, In step S2, the data storage and management module processes the data, including handling duplicate and missing values, specifically including the following steps: S21: Establish a two-dimensional coordinate system with the time axis as the horizontal axis and the data as the vertical axis; S22: Select the corresponding node on the horizontal axis based on the data acquisition frequency. S23: Fill the obtained data into the vertical coordinate of each node. If node data is missing, leave the corresponding gap. If node data is repeated, delete all duplicate values ​​to form a gap. S24: According to the formula Fill in the missing data located at the i-th node. For the data of the i-th node, This is for filling function logic; In step S24 or .

4. The fire protection facility maintenance system based on big data according to claim 1, characterized in that, The data acquisition module includes: Pressure sensors are used to monitor the pressure values ​​inside fire hydrants and fire extinguishers; Liquid level sensors are used to monitor the liquid level in fire water tanks and storage tanks; Temperature / humidity sensors are used to monitor the temperature and humidity of the facility environment; Image acquisition unit is used to identify the appearance of fire hydrants, fire extinguishers, and QR code labels; Electronic tags are used to provide a unique identifier for each facility.

5. The fire protection facility maintenance system based on big data according to claim 1, characterized in that, The data acquisition module initiates data acquisition through two mechanisms: periodic self-testing and event triggering, and converts the acquired analog signals into digital signals.

6. The fire protection facility maintenance system based on big data according to claim 1, characterized in that, The data transmission module adopts a multi-mode converged communication method, specifically including NB-IoT / LoRa wireless low-power wide area network technology, which is used for remote, low-power data transmission; it also includes Wi-Fi / Ethernet wired transmission technology, which is used for short-range, high-bandwidth data backhaul within the building; The data transmission module has a built-in data encryption chip that uses the national cryptographic SM4 or AES algorithm to encrypt the transmitted data end-to-end.

7. The fire protection facility maintenance system based on big data according to claim 1, characterized in that, The data storage and management module is based on a cloud platform architecture, wherein: A distributed file system is used to store massive amounts of unstructured time-series data; Relational databases are used to store structured data such as facility attributes and user information; A time-series database is used to store and process the timestamped dynamic data streams uploaded by sensors.

8. The fire protection facility maintenance system based on big data according to claim 1, characterized in that, The big data analysis and early warning module has a built-in facility health assessment model and a fault prediction model.

9. The fire protection facility maintenance system based on big data according to claim 8, characterized in that, The health assessment model calculates a comprehensive health score by weighted fusion of multi-dimensional real-time data and static data, and assesses the health of the facility based on the comprehensive health score.

10. The fire protection facility maintenance system based on big data according to claim 8, characterized in that, The fault prediction model adopts an LSTM-based time series prediction model, and its logic is as follows: A1: Use sensor data over a continuous period of time as input; A2: LSTM captures long-term dependencies and periodic patterns in data through its internal control mechanism, and outputs predicted values ​​of data points for a future period of time; A3: The deviation sequence between the predicted value and the actual measured value is input into the classifier again to determine whether there are potential abnormal patterns in the sequence and to identify the specific fault type.

Images