Automatic management method and system for pipe gallery parameters

Abstract

The invention discloses a pipe gallery parameter automatic management method and system, and relates to the technical field of automatic management. Comprising the following steps: designing and deploying a data acquisition device in the pipe gallery for acquiring parameter data in the pipe gallery, establishing a data storage platform for storing the data, marking an occurring abnormal condition, and storing the occurring abnormal condition and the corresponding parameter data before the occurrence of the abnormal condition as abnormal data; and inputting abnormal data into the neural network for learning to obtain a risk prediction model of the pipe gallery, inputting parameter data acquired by the data acquisition device in real time into the risk prediction model, and when the risk prediction model judges that the change of the parameter data in the pipe gallery may cause an abnormal condition of the pipe gallery, giving an alarm to realize monitoring of the interior of the pipe gallery. And meanwhile, when the parameter data possibly causes the change of the abnormal condition, namely the abnormal condition is not formed, an alarm is given in advance, the person goes to the place to check the abnormal condition, and the occurrence probability or occurrence time of the abnormal condition is reduced.

Description

Technical Field

[0001] The present application relates to the field of automated management, and specifically to a method and system for automated management of pipe gallery parameters. Background Art

[0002] Through pipelines, various substances can be transmitted in a directional manner. Therefore, various pipe gallery systems, as the infrastructure of modern urban construction, are responsible for the smooth operation of various municipal pipelines, including electricity, communications, gas, water supply and drainage, etc., which helps to reduce the repeated digging of roads in the city, improve the safety and disaster prevention capabilities of municipal pipelines, and enhance the aesthetics of the city. When the maintenance personnel of the pipe gallery are conducting daily inspections or abnormal situations occur in the pipe gallery, they enter through the inspection port reserved in the pipe gallery to conduct daily inspections or maintenance for abnormal situations. However, with the development of the times, people's demand for the timeliness of handling abnormal events has gradually increased. After problems occur in the pipe gallery and abnormal situations occur, the maintenance personnel are notified to go for maintenance. The time required to resolve the abnormality increases with the scale of the pipe gallery system. Therefore, it is gradually difficult to meet the current pipe gallery company's demand for maintenance efficiency and cost.

[0003] Therefore, the problem with the current existing technology is that after a problem occurs in the tunnel and an abnormal situation occurs, the maintenance personnel are notified to go for maintenance. The time to solve the abnormality will increase with the scale of the tunnel system, so it is gradually difficult to meet the current tunnel company's demand for maintenance efficiency and cost. Therefore, there is a need for an automatic management system for tunnel parameters, which can collect and monitor various data in real time by designing and deploying data acquisition devices in the tunnel. When an abnormal change trend occurs, the abnormal situation is predicted and an alarm is issued, and the maintenance personnel are notified to go for processing, thereby reducing the number of abnormal situations and shortening the time for handling abnormal situations. Summary of the invention

[0004] This application aims to solve the problem of slow processing time after abnormal situations caused by problems in the pipe gallery. By designing and deploying data acquisition devices in the pipe gallery, various data are collected and monitored in real time. When abnormal change trends occur, abnormal situations are predicted and alarms are issued, and maintenance personnel are notified to handle them, thereby reducing the number of abnormal situations and shortening the time for handling abnormal situations. The specific technical solutions are as follows: In a first aspect of the present application, a method for automatic management of pipe gallery parameters is provided, comprising: Design and deploy a data acquisition device in the pipe gallery, wherein the data acquisition device is used to collect parameter data in the pipe gallery, wherein the parameters include image, temperature, humidity, pressure and flow; Establishing a data storage platform, the data storage platform is used to store first data and second data, the first data is the parameter data acquired by the data acquisition device in the local pipe gallery, and the second data is the parameter data collected through the cloud; Marking the abnormal situations that have occurred from the first data and the second data, and saving the abnormal situations that have occurred and the corresponding parameter data before the abnormal situations occur as abnormal data; The abnormal data is input into the neural network for learning to obtain a risk prediction model for the pipeline corridor, and the parameter data acquired in real time by the data acquisition device is input into the risk prediction model. When the risk prediction model determines that the change of the parameter data in the pipeline corridor may cause an abnormal situation in the pipeline corridor, an alarm is issued.

[0005] In one embodiment of the present application, the step of designing and deploying a data acquisition device in the pipe gallery specifically includes spatial modeling of the pipe gallery, and deploying the data acquisition device within every threshold range in the pipe gallery and at each branch entrance and exit of the pipe gallery; The size of the tunnel is identified through the data acquisition device, and the transmission capacity levels of different tunnels are divided, and the maximum transmission values ​​corresponding to different transmission objects are used as the first transmission value; at the same time, the data acquisition device identifies the types of transmission objects in the tunnel, and different types of transmission objects correspond to different range values ​​of parameter data during the transmission process, which are used as the first range value; the minimum value of each data in the first range value and the first transmission value is taken as the tunnel safety range value.

[0006] In one embodiment of the present application, the data acquisition device identifies the transmission direction of the transported object in the corridor, and obtains an estimated data volume after the branch corridor in the transmission direction based on the parameter data of each branch corridor. The estimated data volume is compared with the real-time data volume collected by the data acquisition device after the branch corridor in the transmission direction. If the difference in the comparison result exceeds a threshold, it is automatically recorded as abnormal data.

[0007] In one embodiment of the present application, the event that causes the change in the parameter data is obtained, and the estimated occurrence time of the event within the coverage of the tunnel and the estimated change in the parameter data are obtained through the Internet of Things. If the actual data volume of the current parameter data plus the estimated change in the corresponding parameter exceeds the safety range value of the tunnel, an alarm is issued and processing is performed before the estimated occurrence time.

[0008] In one embodiment of the present application, the transmitted object includes municipal rainwater, and the data acquisition device obtains the first transmission value of each rainwater corridor, obtains the estimated change amount and the estimated occurrence time of the rainwater corridors at different positions, and calculates the estimated flow rate through each rainwater corridor in the future. When the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or reduces the time of exceeding the safety range value.

[0009] In one embodiment of the present application, the data storage platform also includes storing the usage time and maintenance records of the pipeline corridor. The longer the usage time of the pipeline corridor and the more maintenance records there are, the smaller the first range value of the pipeline corridor at that location. A corresponding model between the usage time and maintenance records and the first range value is established, and the value of the first range value is automatically updated with the usage time and maintenance records of the pipeline corridor.

[0010] In a second aspect of the present application, a pipe gallery parameter automatic management system is provided, comprising: Data acquisition module, designing and deploying data acquisition devices in the pipe gallery, the data acquisition devices are used to collect parameter data in the pipe gallery, the parameters include image, temperature, humidity, pressure and flow; A data storage module is used to establish a data storage platform, wherein the data storage platform is used to store first data and second data, wherein the first data is the parameter data acquired by the data acquisition device in the local pipe gallery, and the second data is the parameter data collected through the cloud; An abnormal data module, marking abnormal situations that have occurred from the first data and the second data, and saving the abnormal situations that have occurred and the corresponding parameter data before the abnormal situations occur as abnormal data; The risk prediction module inputs the abnormal data into the neural network for learning to obtain a risk prediction model for the pipeline corridor, and inputs the parameter data acquired in real time by the data acquisition device into the risk prediction model. When the risk prediction model determines that the change of the parameter data in the pipeline corridor may cause an abnormal situation in the pipeline corridor, an alarm is issued.

[0011] In one embodiment of the present application, the data acquisition module designs and deploys data acquisition devices in the pipe gallery, specifically including spatial modeling of the pipe gallery, and deploying the data acquisition devices within every threshold range in the pipe gallery and at each branch entrance and exit of the pipe gallery; It also includes an image recognition submodule, which identifies the size of the corridor through the data acquisition device, divides the transmission capacity levels of different corridors, and uses the maximum transmission value corresponding to different transmission objects as the first transmission value; at the same time, the data acquisition device identifies the type of transmission objects in the corridor, and different types of transmission objects correspond to different range values ​​of parameter data during the transmission process, which are used as the first range value; the minimum value of each data in the first range value and the first transmission value is taken as the corridor safety range value.

[0012] In one embodiment of the present application, it also includes an abnormality judgment module, wherein the data acquisition device identifies the transmission direction of the transmission object in the pipeline corridor, and obtains an estimated data volume after the branch pipeline corridor in the transmission direction based on the parameter data of each branch pipeline corridor. The estimated data volume is compared with the real-time data volume collected by the data acquisition device after the branch pipeline corridor in the transmission direction. If the difference in the comparison result exceeds a threshold, it is automatically recorded as abnormal data.

[0013] In one embodiment of the present application, a prediction module is also included to obtain the events that cause the parameter data to change, and obtain the estimated occurrence time of the events within the coverage of the corridor and the estimated change amount of the parameter data through the Internet of Things. If the actual data volume of the current parameter data plus the estimated change amount of the corresponding parameter exceeds the safety range value of the corridor, an alarm is issued and processing is performed before the estimated occurrence time.

[0014] In one embodiment of the present application, the prediction module also includes a rainwater drainage sub-module, the transmission object includes municipal rainwater, the data acquisition device obtains the first transmission value of each rainwater corridor, obtains the estimated change amount and estimated occurrence time of the rainwater corridors at different locations, calculates the estimated flow rate through each rainwater corridor in the future, and when the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or reduces the time exceeding the safety range value.

[0015] In one embodiment of the present application, the data storage platform also includes storing the usage time and maintenance records of the pipeline corridor. The longer the usage time of the pipeline corridor and the more maintenance records there are, the smaller the first range value of the pipeline corridor at that location. A corresponding model between the usage time and maintenance records and the first range value is established, and the value of the first range value is automatically updated with the usage time and maintenance records of the pipeline corridor.

[0016] This application has the following beneficial effects: 1. The first data and the second data are saved through the data storage platform, and abnormal data related to abnormal situations are extracted from the first data and the second data. The neural network is trained through the abnormal data, so that the obtained risk prediction model can identify the data that may cause abnormal situations. Specifically, the second data is cloud data, which can be collected through the Internet to collect the types of abnormal situations that may occur in the corridor under what kind of data changes. The cloud data is rich and covers many abnormal situations; the first data is the abnormal situations that occurred during the historical use of the local corridor system, and the corresponding parameter data before the abnormal situation occurred. The abnormal situation extracted from the first data is more representative of the corridor in the region, and the prediction accuracy is higher. The training proportion and weight of the two types of data are adjusted. When the data volume of the first data is insufficient, it is supplemented by the second data, so that the obtained risk prediction model inputs the parameter data input by the data acquisition device. On the one hand, the parameter data in the corridor is monitored in real time, and the situation in the corridor is clearer; on the other hand, when the parameter data changes that may cause abnormal situations, an alarm is issued at the early stage of the change, that is, when the abnormal situation has not yet formed, the staff receives the task and goes to check whether there is an abnormality, effectively reducing the probability or time of abnormal situation. For example, when cracks appear in the water supply pipe and water leakage occurs, the cracks are small at the beginning and the water supply pipe can still supply water normally without water outage. However, the risk prediction model determines that the flow, pressure and humidity parameter data are abnormal and alerts the staff. The staff will deal with it in advance before the abnormal situation occurs, thereby reducing the probability of abnormal situation that the crack continues to expand and directly leads to water outage. If the crack expands rapidly and still leads to water outage, the early departure of the staff can effectively reduce the occurrence time of the abnormal situation.

[0017] 2. The data acquisition device is set within a threshold range every other time in the tunnel to avoid a long space without a data acquisition device for data acquisition. If an abnormal situation occurs in this section of the tunnel, it will take a longer time to find and determine the task location. The specific threshold can be determined according to the scale and demand of the tunnel; at the same time, the data acquisition device is deployed at the entrance and exit of each branch of the tunnel to obtain the parameter data difference on both sides of the branch and obtain more comprehensive tunnel parameter data; the size of the tunnel is identified by the data acquisition device to obtain the maximum transmission value of the current tunnel for the transmission object. The first transmission value of different transmission objects is different. For example, the same tunnel is used to transmit different units and quantities of sewage and gas; the same When identifying the transmission object transmitted in the pipeline corridor according to the data acquisition device, the normal range value corresponding to various parameter data of the transmission object in the pipeline corridor is automatically matched. For example, in the power pipeline corridor, the normal range value of humidity is different from the normal range value of humidity in the gas pipeline corridor; the pipeline corridor and the type of transmission object transmitted in the pipeline corridor are respectively identified by the data acquisition device to obtain the first transmission volume of the pipeline corridor and the first range value of the transmission object, and the safety range value of each parameter data during the transmission of this part of the pipeline corridor is obtained. The risk prediction model uses the safety range value to determine whether there is an abnormal situation risk, so that pipeline corridors of different sizes can uniformly use the risk prediction model for risk prediction, effectively expanding the scope of application.

[0018] 3. The data volume of the transmission objects of each branch before and after entering the main pipeline can be obtained by the data acquisition device. The data volume of the transmission objects in the pipe gallery includes the water flow of the rainwater pipe gallery. However, since the collection of water flow data in the data acquisition device is usually obtained by the volume of the pipe gallery occupied by the water flow, the water flow data obtained in this way is prone to errors. For example, impurities in rainwater are prone to deposit silt impurities at the bottom of the pipe gallery, causing the measured water flow data to be higher than the actual water flow, especially when the height of the pipe gallery is flat or even the height of the water flow direction is higher than the height of the water inlet. Therefore, the water inflow of the branch and the water inflow of the pipe gallery before the branch are collected by the data acquisition device to obtain the estimated data volume, and then the real-time data volume collected by the data acquisition device is subtracted. If the difference in the comparison result exceeds the threshold, it means that the amount of impurity deposition at the bottom of the pipe gallery is large and needs to be cleaned to reduce the pressure on the pipe gallery and reduce the risk of blockage of the pipe gallery. Similarly, if there is a leak in the pipe gallery, resulting in the measured water flow data being lower than the water flow that should pass through there, it can also be concluded whether there is a leak in the pipe gallery by the above method. 4. The future rainfall in the corridor area is obtained through the Internet of Things. When a large area of ​​rainfall occurs that causes rainfall in the corridor area in the direction of water flow, the pressure in the corridor further back in the direction of water flow is greater. By calculating the estimated flow rate of each branch corridor due to rainfall, when the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the rainfall in each rainwater corridor is drained to the area with less rainfall or less pressure, and the pressure of the original corridor is shared, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or the time of exceeding the safety range value is reduced; at the same time, it can also be combined with the above-mentioned implementation method. When it is predicted through the Internet of Things that rainfall in the future may cause the estimated flow rate of the rainwater corridor to exceed the safety range value of the corridor, the staff can clean up the area with deposited impurities in the corridor in advance to restore the maximum transmission volume and reduce the risk of blockage when rainfall comes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0020] Figure 1 A schematic diagram of the electronic device structure of the hardware operating environment involved in an embodiment of the present application.

[0021] Figure 2 It is a step flow chart of a method for automatic management of pipeline gallery parameters provided in an embodiment of the present application.

[0022] Figure 3 It is a functional module diagram of a method for automatic management of pipeline gallery parameters provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0024] The solution of the present application is further described below in conjunction with the accompanying drawings.

[0025] like Figure 1As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0026] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0027] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module and an electronic program.

[0028] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device, and the electronic device calls a method for automatic management of corridor parameters stored in the memory 1005 through the processor 1001, and executes a method for automatic management of corridor parameters provided in an embodiment of the present application.

[0029] Based on the aforementioned hardware operating environment and system architecture, in the first aspect of the present application, refer to Figure 2 As shown, a method for automatic management of pipe gallery parameters is provided, comprising: Design and deploy a data acquisition device in the pipe gallery, wherein the data acquisition device is used to collect parameter data in the pipe gallery, wherein the parameters include image, temperature, humidity, pressure and flow; It should be noted that, in response to the detection requirements of parameter data of different transmission objects, corresponding types of parameter data are collected in the pipe gallery, for example, the rainwater pipe gallery needs flow parameter data, the power pipe gallery needs temperature parameter data, and the gas pipe gallery needs pressure parameter data; different types of parameter data can be collected separately through multiple data collection devices, and the corresponding data collection device is set according to the required parameter data; or a composite data collection device can be used to collect and open different data collection functions according to the required different types of parameter data; Establishing a data storage platform, the data storage platform is used to store first data and second data, the first data is the parameter data acquired by the data acquisition device in the local pipe gallery, and the second data is the parameter data collected through the cloud; Marking the abnormal situations that have occurred from the first data and the second data, and saving the abnormal situations that have occurred and the corresponding parameter data before the abnormal situations occur as abnormal data; The abnormal data is input into the neural network for learning to obtain a risk prediction model for the pipeline corridor, and the parameter data acquired in real time by the data acquisition device is input into the risk prediction model. When the risk prediction model determines that the change of the parameter data in the pipeline corridor may cause an abnormal situation in the pipeline corridor, an alarm is issued.

[0030] It should be noted that the pipeline corridor is a transportation system that can transport objects in a certain direction to a designated location. The objects include various types, such as electricity, communications, gas, water supply, sewage and rainwater, etc. According to the scale of the pipeline corridor, one pipeline corridor can undertake the transportation of one object. At the same time, a large integrated pipeline corridor system also includes a large pipeline corridor that transports multiple objects through multiple small pipelines. In this embodiment, the first data and the second data are saved by the data storage platform, and abnormal data related to abnormal situations are extracted from the first data and the second data. The neural network is trained by the abnormal data, so that the obtained risk prediction model can identify the data that may cause abnormal situations. Specifically, the second data is cloud data, which can be collected through the Internet to collect the types of abnormal situations that may occur in the corridor under what kind of data changes. The cloud data is rich and covers many abnormal situations; the first data is the abnormal situations that occurred during the historical use of the local corridor system, and the corresponding parameter data before the abnormal situation occurred. The abnormal situation extracted from the first data is more representative of the corridor in the region, and the prediction accuracy is higher. The training proportion and weight of the two types of data are adjusted. When the data volume of the first data is insufficient, it is supplemented by the second data, so that the obtained risk prediction model inputs the parameter data input by the data acquisition device. On the one hand, the parameter data in the corridor is monitored in real time, and the situation in the corridor is clearer; on the other hand, when the parameter data changes that may cause abnormal situations, an alarm is issued at the early stage of the change, that is, when the abnormal situation has not yet formed, the staff receives the task and goes to check whether there is an abnormality, effectively reducing the probability or time of abnormal situation. For example, when cracks appear in the water supply pipe and water leakage occurs, the cracks are small at the beginning and the water supply pipe can still supply water normally without water outage. However, the risk prediction model determines that the flow, pressure and humidity parameter data are abnormal and alerts the staff. The staff will deal with it in advance before the abnormal situation occurs, thereby reducing the probability of abnormal situation that the crack continues to expand and directly leads to water outage. If the crack expands rapidly and still leads to water outage, the early departure of the staff can effectively reduce the occurrence time of the abnormal situation.

[0031] In one embodiment of the present application, the step of designing and deploying a data acquisition device in the pipe gallery specifically includes spatial modeling of the pipe gallery, and deploying the data acquisition device within every threshold range in the pipe gallery and at each branch entrance and exit of the pipe gallery; The size of the tunnel is identified through the data acquisition device, and the transmission capacity levels of different tunnels are divided, and the maximum transmission values ​​corresponding to different transmission objects are used as the first transmission value; at the same time, the data acquisition device identifies the types of transmission objects in the tunnel, and different types of transmission objects correspond to different range values ​​of parameter data during the transmission process, which are used as the first range value; the minimum value of each data in the first range value and the first transmission value is taken as the tunnel safety range value.

[0032] It should be noted that by modeling the corridor space, the spatial position of the corridor is obtained, including the distance difference and height difference between different corridors, which can be obtained through corridor engineering information. If it cannot be obtained, the spatial position information of the corridor can also be collected through a mobile data acquisition device; In this embodiment, the data acquisition device is set within every threshold range in the tunnel to avoid a long space without a data acquisition device for data acquisition. If an abnormal situation occurs in this section of the tunnel, it will take a longer time to find and determine the task location. The specific threshold can be determined according to the scale and demand of the tunnel; at the same time, the data acquisition device is deployed at the entrance and exit of each branch of the tunnel, and the parameter data difference on both sides of the branch can be obtained to obtain more comprehensive tunnel parameter data; the size of the tunnel is identified by the data acquisition device, and the maximum transmission value of the current tunnel for the transmission object is obtained. The first transmission value of different transmission objects is different. For example, the same tunnel is used to transmit sewage and gas. The units and quantities are different. The same; at the same time, the transmission object transmitted in the pipeline corridor is identified according to the data acquisition device, and the normal range values ​​corresponding to various parameter data of the transmission object in the pipeline corridor are automatically matched. For example, in the power pipeline corridor, the normal range value of humidity is different from the normal range value of humidity in the gas pipeline corridor; the pipeline corridor and the type of transmission object transmitted in the pipeline corridor are identified by the data acquisition device respectively, and the first transmission volume of the pipeline corridor and the first range value of the transmission object are obtained, and the safety range values ​​of various parameter data when transmitting in this part of the pipeline corridor are obtained. The risk prediction model uses the safety range value to determine whether there is an abnormal situation risk, so that pipeline corridors of different sizes can uniformly use the risk prediction model for risk prediction, effectively expanding the scope of application.

[0033] In one embodiment of the present application, the data acquisition device identifies the transmission direction of the transported object in the corridor, and obtains an estimated data volume after the branch corridor in the transmission direction based on the parameter data of each branch corridor. The estimated data volume is compared with the real-time data volume collected by the data acquisition device after the branch corridor in the transmission direction. If the difference in the comparison result exceeds a threshold, it is automatically recorded as abnormal data.

[0034] In this embodiment, the data volume of the transmission objects of each branch before and after entering the main pipeline can be obtained by the data acquisition device. The data volume of the transmission objects in the pipe gallery includes the water flow of the rainwater pipe gallery. However, since the collection of water flow data in the data acquisition device is usually obtained by the volume of the pipe gallery occupied by the water flow, the water flow data obtained in this way is prone to errors. For example, impurities in rainwater are prone to deposit silt impurities at the bottom of the pipe gallery, causing the measured water flow data to be higher than the actual water flow, especially when the height of the pipe gallery is flat or even the height of the water flow direction is higher than the height of the water inlet. Therefore, the water inflow of the branch and the water inflow of the pipe gallery before the branch are collected by the data acquisition device to obtain the estimated data volume, and then the real-time data volume collected by the data acquisition device is subtracted. If the difference in the comparison result exceeds the threshold, it means that the amount of impurity deposition at the bottom of the pipe gallery is large and needs to be cleaned to reduce the pressure on the pipe gallery and reduce the risk of blockage in the pipe gallery. Similarly, if there is a leak in the pipe gallery, resulting in the measured water flow data being lower than the water flow that should pass through there, it can also be concluded whether there is a leak in the pipe gallery by the above method. In one embodiment of the present application, the event that causes the change in the parameter data is obtained, and the estimated occurrence time of the event within the coverage of the tunnel and the estimated change in the parameter data are obtained through the Internet of Things. If the actual data volume of the current parameter data plus the estimated change in the corresponding parameter exceeds the safety range value of the tunnel, an alarm is issued and processing is performed before the estimated occurrence time.

[0035] It should be noted that the matters causing the change of the parameter data are obtained. For example, rainfall will cause the water flow in the rainwater pipe gallery to increase. The Internet of Things combines various information sensing devices with the Internet, and collects and screens through Internet big data to obtain matters that will affect the parameter data in the area covered by the pipe gallery and its surroundings in the future, as well as the estimated changes caused by the matters. For example, it will rain in area A of the rainwater pipe gallery in 1 hour, and the rainfall is expected to cause the rainwater flow in area A of the rainwater pipe gallery to increase. The specific corresponding relationship between rainfall and rainwater flow increase can be measured on the spot according to the size of the pipe gallery and the ground conditions of area A of the rainwater pipe gallery; In one embodiment of the present application, the transmitted object includes municipal rainwater, and the data acquisition device obtains the first transmission value of each rainwater corridor, obtains the estimated change amount and the estimated occurrence time of the rainwater corridors at different positions, and calculates the estimated flow rate through each rainwater corridor in the future. When the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or reduces the time of exceeding the safety range value.

[0036] In this embodiment, the future rainfall in the corridor area is obtained through the Internet of Things. When a large area of ​​rainfall occurs that causes rainfall in the corridor area in the direction of water flow, the pressure in the corridor further back in the direction of water flow is greater. By calculating the estimated flow rate of each branch corridor due to rainfall, when the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the rainfall in each rainwater corridor is drained to the area with less rainfall or less pressure, and the pressure of the original corridor is shared, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or the time of exceeding the safety range value is reduced; at the same time, it can also be combined with the above-mentioned embodiment. When it is predicted through the Internet of Things that rainfall in the future may cause the estimated flow rate of the rainwater corridor to exceed the safety range value of the corridor, the staff can clean up the area with deposited impurities in the corridor in advance to restore the maximum transmission volume and reduce the risk of blockage when rainfall comes.

[0037] In one embodiment of the present application, the data storage platform also includes storing the usage time and maintenance records of the pipeline corridor. The longer the usage time of the pipeline corridor and the more maintenance records there are, the smaller the first range value of the pipeline corridor at that location. A corresponding model between the usage time and maintenance status and the first range value is established, and the value of the first range value is automatically updated with the usage time and maintenance records of the pipeline corridor.

[0038] In this embodiment, due to corrosion inside the tunnel or uneven stress at the repair patch, the maximum transmission capacity of the tunnel and the transmission pressure that the tunnel can withstand will gradually decrease with the service life and maintenance. Therefore, a corresponding model between the usage time and maintenance status and the first range value is established. The value of the first range value is automatically updated with the usage time and maintenance record of the tunnel, so as to avoid errors in the first range value that cause the tunnel to exceed the tolerable pressure range and cause damage.

[0039] In the second aspect of the present application, reference is made to Figure 3 As shown, a pipe gallery parameter automatic management system is provided, comprising: Data acquisition module, designing and deploying data acquisition devices in the pipe gallery, the data acquisition devices are used to collect parameter data in the pipe gallery, the parameters include image, temperature, humidity, pressure and flow; A data storage module is used to establish a data storage platform, wherein the data storage platform is used to store first data and second data, wherein the first data is the parameter data acquired by the data acquisition device in the local pipe gallery, and the second data is the parameter data collected through the cloud; An abnormal data module, marking abnormal situations that have occurred from the first data and the second data, and saving the abnormal situations that have occurred and the corresponding parameter data before the abnormal situations occur as abnormal data; The risk prediction module inputs the abnormal data into the neural network for learning to obtain a risk prediction model for the pipeline corridor, and inputs the parameter data acquired in real time by the data acquisition device into the risk prediction model. When the risk prediction model determines that the change of the parameter data in the pipeline corridor may cause an abnormal situation in the pipeline corridor, an alarm is issued.

[0040] In one embodiment of the present application, the data acquisition module designs and deploys data acquisition devices in the pipe gallery, specifically including spatial modeling of the pipe gallery, and deploying the data acquisition devices within every threshold range in the pipe gallery and at each branch entrance and exit of the pipe gallery; It also includes an image recognition submodule, which identifies the size of the corridor through the data acquisition device, divides the transmission capacity levels of different corridors, and uses the maximum transmission value corresponding to different transmission objects as the first transmission value; at the same time, the data acquisition device identifies the type of transmission objects in the corridor, and different types of transmission objects correspond to different range values ​​of parameter data during the transmission process, which are used as the first range value; the minimum value of each data in the first range value and the first transmission value is taken as the corridor safety range value.

[0041] In one embodiment of the present application, it also includes an abnormality judgment module, wherein the data acquisition device identifies the transmission direction of the transmission object in the pipeline corridor, and obtains an estimated data volume after the branch pipeline corridor in the transmission direction based on the parameter data of each branch pipeline corridor. The estimated data volume is compared with the real-time data volume collected by the data acquisition device after the branch pipeline corridor in the transmission direction. If the difference in the comparison result exceeds a threshold, it is automatically recorded as abnormal data.

[0042] In one embodiment of the present application, a prediction module is also included to obtain the events that cause the parameter data to change, and obtain the estimated occurrence time of the events within the coverage of the corridor and the estimated change amount of the parameter data through the Internet of Things. If the actual data volume of the current parameter data plus the estimated change amount of the corresponding parameter exceeds the safety range value of the corridor, an alarm is issued and processing is performed before the estimated occurrence time.

[0043] In one embodiment of the present application, the prediction module also includes a rainwater drainage sub-module, the transmission object includes municipal rainwater, the data acquisition device obtains the first transmission value of each rainwater corridor, obtains the estimated change amount and estimated occurrence time of the rainwater corridors at different locations, calculates the estimated flow rate through each rainwater corridor in the future, and when the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or reduces the time exceeding the safety range value.

[0044] In one embodiment of the present application, the data storage platform also includes storing the usage time and maintenance records of the pipeline corridor. The longer the usage time of the pipeline corridor and the more maintenance records there are, the smaller the first range value of the pipeline corridor at that location. A corresponding model between the usage time and maintenance records and the first range value is established, and the value of the first range value is automatically updated with the usage time and maintenance records of the pipeline corridor.

[0045] It should be noted that the specific implementation of an automatic management system for utility corridor parameters in an embodiment of the present application refers to the specific implementation of an automatic management method for utility corridor parameters proposed in the first aspect of the aforementioned embodiment of the present application, and will not be repeated here.

[0046] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that an article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the existence of other identical elements in the article or device including the elements.

[0047] The above is a detailed introduction to the provided method for automated management of corridor parameters. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method for automated management of corridor parameters of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for automatic management of pipe gallery parameters, characterized in that: include: Design and deploy a data acquisition device in the pipe gallery, wherein the data acquisition device is used to collect parameter data in the pipe gallery, wherein the parameters include image, temperature, humidity, pressure and flow; Establishing a data storage platform, the data storage platform is used to store first data and second data, the first data is the parameter data acquired by the data acquisition device in the local pipe gallery, and the second data is the parameter data collected through the cloud; Marking the abnormal situations that have occurred from the first data and the second data, and saving the abnormal situations that have occurred and the corresponding parameter data before the abnormal situations occur as abnormal data; The abnormal data is input into the neural network for learning to obtain a risk prediction model for the pipeline corridor, and the parameter data acquired in real time by the data acquisition device is input into the risk prediction model. When the risk prediction model determines that the change of the parameter data in the pipeline corridor may cause an abnormal situation in the pipeline corridor, an alarm is issued.

2. A method for automatic management of pipe gallery parameters according to claim 1, characterized in that: The step of designing and deploying the data acquisition device in the pipe gallery specifically includes performing spatial modeling on the pipe gallery, and deploying the data acquisition device within every threshold range in the pipe gallery and at each branch entrance and exit of the pipe gallery; The size of the tunnel is identified through the data acquisition device, and the transmission capacity levels of different tunnels are divided, and the maximum transmission values ​​corresponding to different transmission objects are used as the first transmission value; at the same time, the data acquisition device identifies the types of transmission objects in the tunnel, and different types of transmission objects correspond to different range values ​​of parameter data during the transmission process, which are used as the first range value; the minimum value of each data in the first range value and the first transmission value is taken as the tunnel safety range value.

3. A method for automatic management of pipe gallery parameters according to claim 2, characterized in that: The data acquisition device identifies the transmission direction of the transmission object in the pipeline corridor, and obtains an estimated data volume after the branch pipeline corridor in the transmission direction based on the parameter data of each branch pipeline corridor. The estimated data volume is compared with the real-time data volume collected by the data acquisition device after the branch pipeline corridor in the transmission direction. If the difference in the comparison result exceeds a threshold, it is automatically recorded as abnormal data.

4. A method for automatic management of pipe gallery parameters according to claim 2 or 3, characterized in that: Obtain the event that causes the parameter data to change, and obtain the estimated time of occurrence of the event within the coverage of the tunnel and the estimated change in the parameter data through the Internet of Things. If the actual data volume of the current parameter data plus the estimated change in the corresponding parameter exceeds the safety range value of the tunnel, an alarm is issued and processing is performed before the estimated occurrence time.

5. The method for automatic management of pipe gallery parameters according to claim 4 is characterized in that: The transmitted object includes municipal rainwater, and the data acquisition device obtains the first transmission value of each rainwater corridor, obtains the estimated change amount and the estimated occurrence time of the rainwater corridors at different positions, and calculates the estimated flow rate through each rainwater corridor in the future. When the estimated flow rate of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow rate exceeds the safety range value of the corridor, so that the estimated flow rate of each rainwater corridor does not exceed the safety range value of the corridor or reduces the time of exceeding the safety range value.

6. An automatic management system for pipe gallery parameters, characterized in that: include: Data acquisition module, designing and deploying data acquisition devices in the pipe gallery, the data acquisition devices are used to collect parameter data in the pipe gallery, the parameters include image, temperature, humidity, pressure and flow; A data storage module is used to establish a data storage platform, wherein the data storage platform is used to store first data and second data, wherein the first data is the parameter data acquired by the data acquisition device in the local pipe gallery, and the second data is the parameter data collected through the cloud; An abnormal data module, marking abnormal situations that have occurred from the first data and the second data, and saving the abnormal situations that have occurred and the corresponding parameter data before the abnormal situations occur as abnormal data; The risk prediction module inputs the abnormal data into the neural network for learning to obtain a risk prediction model for the pipeline corridor, and inputs the parameter data acquired in real time by the data acquisition device into the risk prediction model. When the risk prediction model determines that the change of the parameter data in the pipeline corridor may cause an abnormal situation in the pipeline corridor, an alarm is issued.

7. A method for automatic management of pipe gallery parameters according to claim 6, characterized in that: The data acquisition module designs and deploys data acquisition devices in the pipe gallery, specifically including spatial modeling of the pipe gallery, and deploying the data acquisition devices within every threshold range in the pipe gallery and at each branch entrance and exit of the pipe gallery; It also includes an image recognition submodule, which identifies the size of the corridor through the data acquisition device, divides the transmission capacity levels of different corridors, and uses the maximum transmission value corresponding to different transmission objects as the first transmission value; at the same time, the data acquisition device identifies the type of transmission objects in the corridor, and different types of transmission objects correspond to different range values ​​of parameter data during the transmission process, which are used as the first range value; the minimum value of each data in the first range value and the first transmission value is taken as the corridor safety range value.

8. The method for automatic management of pipe gallery parameters according to claim 7 is characterized in that: It also includes an abnormality judgment module, in which the data acquisition device identifies the transmission direction of the transmission object in the corridor, and obtains an estimated data volume after the branch corridor in the transmission direction based on the parameter data of each branch corridor. The estimated data volume is compared with the real-time data volume collected by the data acquisition device after the branch corridor in the transmission direction. If the difference in the comparison result exceeds a threshold, it is automatically recorded as abnormal data.

9. A method for automatic management of pipe gallery parameters according to claim 7 or 8, characterized in that: It also includes a prediction module to obtain the events that cause the parameter data to change, and obtain the estimated occurrence time of the event within the coverage of the corridor and the estimated change amount of the parameter data through the Internet of Things. If the actual data volume of the current parameter data plus the estimated change amount of the corresponding parameter exceeds the safety range value of the corridor, an alarm is issued and processing is performed before the estimated occurrence time.

10. A method for automatic management of pipe gallery parameters according to claim 9, characterized in that: The prediction module also includes a rainwater drainage sub-module, and the transmission object includes municipal rainwater. The data acquisition device obtains the first transmission value of each rainwater corridor, obtains the estimated change amount and estimated occurrence time of the rainwater corridors at different positions, and calculates the estimated flow through each rainwater corridor in the future. When the estimated flow of the rainwater corridor in the transmission direction exceeds the safety range value of the corridor, the valve switch of the rainwater corridor is used to control the municipal rainwater to change the transmission direction before the estimated flow exceeds the safety range value of the corridor, so that the estimated flow of each rainwater corridor does not exceed the safety range value of the corridor or reduces the time of exceeding the safety range value.

Images