Protective facility health monitoring method, device, medium and electronic equipment

Abstract

The embodiments of the present application disclose a method, device, medium and electronic device for health monitoring of protective facilities. The method includes: feature matching the target image monitoring data of the protective facilities to be predicted with the candidate image monitoring data in the protective facilities corrosion sample database, and selecting similar image monitoring data for the target image monitoring data from the candidate image monitoring data; based on the association relationship between the image monitoring data and the sensor monitoring data, selecting at least two sensor monitoring data associated with the similar image monitoring data from the protective facilities corrosion sample database as target sensor monitoring data; using the target image monitoring data and the target sensor monitoring data as input data of the protective facilities remaining life prediction model to obtain the remaining life of the protective facilities to be predicted. Executing the technical solution provided in the embodiments of the present application can improve the accuracy of the remaining life prediction of protective facilities.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer application technology, and in particular, to a method, device, medium and electronic equipment for monitoring the health of protective facilities. Background Art

[0002] As an important safety infrastructure, protective facilities can be installed on the high slopes of highways to effectively prevent rock and soil collapse; protective facilities can be installed on both sides of elevated bridges to effectively prevent stones and other debris from falling from the bridges, avoiding injuries to pedestrians under the bridges. Protective facilities will corrode if exposed to the outdoors for a long time, which will endanger the health of the protective facilities, affect the service life of the protective facilities, and reduce the protective effect.

[0003] At present, most of the methods for monitoring the health of protective facilities and predicting the remaining service life of protective facilities are to set up corrosion monitoring sensors at limited locations of protective facilities and predict the remaining service life of protective facilities based on the corrosion monitoring data collected by the corrosion monitoring sensors. The microenvironment differences at different locations of protective facilities result in different corrosion conditions at different locations of protective facilities. The limited number and single type of corrosion monitoring data are difficult to reflect the actual health of protective facilities. This method often has the problem of inaccurate life prediction. Summary of the invention

[0004] The embodiments of the present application provide a protective facility health monitoring method, device, medium and electronic equipment, which can improve the accuracy of protective facility life prediction.

[0005] In a first aspect, an embodiment of the present application provides a method for monitoring the health of a protective facility, the method comprising:

[0006] Perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data;

[0007] According to the association relationship between the image monitoring data and the sensor monitoring data, at least two sensor monitoring data associated with the similar image monitoring data are selected from the protection facility corrosion sample database as target sensor monitoring data;

[0008] The target image monitoring data and the target sensor monitoring data are used as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0009] In a second aspect, an embodiment of the present application provides a protective facility health monitoring device, the device comprising:

[0010] A feature matching module is used to perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data;

[0011] a target sensor monitoring data determination module, configured to select at least two sensor monitoring data associated with the similar image monitoring data from the protection facility corrosion sample database as target sensor monitoring data according to the association relationship between the image monitoring data and the sensor monitoring data;

[0012] The module for determining the remaining life of the protective facility to be predicted is used to use the target image monitoring data and the target sensor monitoring data as input data of the protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0013] In a third aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the protective facility health monitoring method as described in the embodiment of the present application is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the protective facility health monitoring method as described in the embodiment of the present application is implemented.

[0015] The technical solution provided in the embodiment of the present application realizes associating the target sensor monitoring data in the protection facility corrosion sample database with the target image monitoring data by selecting similar image monitoring data for the target image monitoring data from the candidate image monitoring data in the protection facility corrosion sample database, and using at least two types of sensor monitoring data associated with the similar image monitoring data as the target sensor monitoring data, thereby expanding the data dimension used to predict the remaining life of the protection facility. The embodiment of the present application uses the target image monitoring data and the target sensor monitoring data as input data of the protection facility remaining life prediction model to obtain the remaining life of the protection facility to be predicted, thereby realizing the prediction of the remaining life of the protection facility through the protection facility remaining life prediction model based on multi-dimensional data, and improving the prediction accuracy of the remaining life of the protection facility. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a protective facility health monitoring method provided in Example 1 of the present application;

[0017] Figure 2 This is a flow chart of a protective facility health monitoring method provided in Example 2 of the present application;

[0018] Figure 3 It is a structural schematic diagram of a protective facility health monitoring device provided in Example 3 of the present application;

[0019] Figure 4 It is a structural schematic diagram of an electronic device provided in Example 5 of the present application. DETAILED DESCRIPTION

[0020] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0021] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0022] Embodiment 1

[0023] Figure 1 This is a flowchart of a protective facility health monitoring method provided in Example 1 of the present application. This embodiment can be applied to the case of predicting the remaining life of protective facilities. The method can be executed by the protective facility health monitoring device provided in the embodiment of the present application. The device can be implemented by software and / or hardware, and can be integrated into the electronic device running this system.

[0024] like Figure 1 As shown, the protective facility health monitoring method includes:

[0025] S110, feature matching is performed on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and similar image monitoring data is selected from the candidate image monitoring data for the target image monitoring data.

[0026] Among them, the protective facilities to be predicted refer to protective facilities that need to be monitored for health conditions and whose remaining life is predicted based on their health conditions. Exemplarily, the protective facilities to be predicted are slope protection nets, anti-throw nets, and guardrails. The target image monitoring data is used to reflect the corrosion conditions of the protective facilities to be predicted, such as corrosion morphology and corrosion degree. Optionally, the target image monitoring data is monitoring image feature data obtained by preprocessing the collected monitoring images of the protective facilities and extracting features of the color, texture, shape, etc. of the preprocessed monitoring images of the protective facilities.

[0027] The method of collecting monitoring images of protective facilities is not limited here. For example, it can be obtained by real-time collection of image acquisition equipment such as cameras installed on or around the protective facilities to be predicted, or it can be collected by unmanned aircraft equipped with image acquisition equipment during routine inspections of in-service protective facilities.

[0028] Among them, the protective facility corrosion sample database is pre-built by relevant technical personnel based on a variety of protective facility monitoring data. Among them, the protective facility monitoring data is the data related to the corrosion of protective facilities. The various protective facility monitoring data reflect the corrosion conditions of protective facilities from different angles such as corrosion causes, corrosion degrees, corrosion rates and corrosion forms. Optionally, the protective facility monitoring data includes: image monitoring data and at least two types of sensor monitoring data. The protective facility corrosion sample database provides data support for the remaining life prediction of protective facilities.

[0029] The candidate image monitoring data is generated from the image monitoring data in the protection facility corrosion sample database. The similar image monitoring data refers to the candidate image monitoring data having similar features to the target image monitoring data.

[0030] The target image monitoring data of the protective facilities to be predicted and the candidate image monitoring data are feature matched, and the candidate image monitoring data that successfully matches the target image monitoring data is used as similar image monitoring data.

[0031] In an optional embodiment, the target image monitoring data of the protection facility to be predicted is feature matched with the candidate image monitoring data in the protection facility corrosion sample database, and similar image monitoring data is selected for the target image monitoring data from the candidate image monitoring data, including: calculating the feature similarity between the target image monitoring data and each candidate image monitoring data; and selecting similar image monitoring data for the target image monitoring data from the candidate image monitoring data based on the feature similarity.

[0032] The feature similarity refers to the degree of feature similarity between the target image monitoring data and each candidate image monitoring data.

[0033] Calculate the feature similarity between the target image monitoring data and each candidate image monitoring data; select similar image monitoring data for the target image monitoring data from the candidate image monitoring data according to the feature similarity. Specifically, use a feature similarity calculation method or a feature similarity calculation model to calculate the feature similarity between the target image monitoring data and each candidate image monitoring data, and sort the obtained feature similarities. According to the feature similarity sorting result, select the image monitoring data that is most similar to the target image monitoring data from the candidate image monitoring data as the similar image monitoring data.

[0034] S120. According to the association relationship between the image monitoring data and the sensor monitoring data, at least two types of sensor monitoring data associated with the similar image monitoring data are selected from the protection facility corrosion sample database as target sensor monitoring data.

[0035] It can be known that, under normal circumstances, protective facilities have a certain spatial span. For example, the slope protection net installed on the high slope of the highway may be several kilometers or more than ten kilometers long. A certain spatial span may cause differences in the local environment between different areas of the protective facilities. Environmental factors are the main factors affecting the corrosion of protective facilities. Differences in local environments will lead to different degrees of corrosion of protective facilities, and there will also be differences in external visual performance. For example, if the local environment has high salt concentration, low light intensity, high air humidity, poor air quality, and low pH value, the protective facilities will be easily corroded; if the local environment has low salt concentration, high light intensity, low air humidity, high air quality, and high pH value, the protective facilities will not be easily corroded.

[0036] The local environment of the area captured by the image acquisition device can be acquired by sensors deployed within the shooting area. The image monitoring data collected by the image acquisition device is a visual representation of the corrosion status of the protective facilities within the shooting area. Optionally, the image acquisition device is deployed in the protective facility area where the sensor is deployed, so as to ensure that the historical image monitoring data and the historical sensor monitoring data belong to the same protective facility area.

[0037] The image monitoring data and sensor monitoring data with an associated relationship jointly reflect the corrosion situation in the same area of ​​the protective facility. The visual appearance of the corrosion situation is strongly correlated with the local environment of the protective facility. When the visual appearance of the corrosion situation of the protective facility is known, based on the association between the image monitoring data and the sensor monitoring data, at least two sensor monitoring data associated with similar image monitoring data are selected from the protective facility corrosion sample database as target sensor monitoring data. That is, from the visual appearance of the corrosion situation of the protective facility, the local environment that forms this visual appearance is traced back, and the degree of corrosion is determined.

[0038] The target sensor monitoring data is associated with the similar image monitoring data, because the similar image monitoring data is the candidate image monitoring data having similar features to the target image monitoring data. Therefore, the target sensor monitoring data is also associated with the target image monitoring data.

[0039] In an optional embodiment, the sensor monitoring data includes: at least two of corrosion parameters, mechanical parameters and environmental parameters. The corrosion parameters are collected by the corrosion sensor and can be used to reflect the corrosion rate; the mechanical parameters are collected by the mechanical sensor and can be used to reflect the degree of corrosion. Optionally, the mechanical parameters include: at least one of vibration parameters, tensile parameters and stress parameters; the environmental parameters are collected by the environmental sensor and can be used to reflect the local environment. Optionally, the environmental parameters include: at least one of salt concentration, air quality, air humidity, light intensity and pH value parameters. Different sensor monitoring data reflect the corrosion of protective facilities from different angles. Compared with only a single type of sensor monitoring data, comprehensive consideration of multiple sensor monitoring data can more accurately determine the corrosion of protective facilities, thereby improving the accuracy of the remaining life prediction of protective facilities.

[0040] S130. Using the target image monitoring data and the target sensor monitoring data as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0041] Among them, the remaining life prediction model of protective facilities is pre-built by relevant technical personnel and is a model used to predict the remaining life of protective facilities based on image monitoring data and sensor monitoring data.

[0042] The target image monitoring data and the target sensor monitoring data are used as input data of the protective facility remaining life prediction model, and the protective facility remaining life prediction model outputs the remaining life of the protective facility to be predicted.

[0043] Optionally, after obtaining the life of the protective facility to be predicted, an overall or local maintenance strategy for the protective facility can be formulated based on the remaining life of the protective facility, combined with factors such as the geographical location of the protective facility to be predicted and the frequency of accidents at the geographical location.

[0044] The embodiments of the present application take into account the huge economic cost and feasibility of deploying sensors on the entire protective facility, and generally only deploy sensors in some areas of the protective facility. This makes the sensor monitoring data of the protective facility limited. By selecting similar image monitoring data from the candidate image monitoring data in the protective facility corrosion sample database, at least two sensor monitoring data associated with the similar image monitoring data are used as target sensor monitoring data. In this way, the sensor monitoring data in the protective facility corrosion sample database can be migrated to the area where the sensors are not deployed in the undeployed protective facilities. It can be known that the protective facility health monitoring method provided in the embodiments of the present application is not limited to predicting the remaining life of protective facilities such as protective nets, but is also applicable to other basic equipment built earlier and facing corrosion and aging problems, such as bridges, buildings and tunnels built of reinforced concrete, etc. It can also be used for monitoring the health of old equipment such as ships, airplanes, cars, escalators, elevators and industrial equipment, as well as remaining life prediction and maintenance.

[0045] The technical solution provided in the embodiment of the present application realizes associating the target sensor monitoring data in the protection facility corrosion sample database with the target image monitoring data by selecting similar image monitoring data for the target image monitoring data from the candidate image monitoring data in the protection facility corrosion sample database, and using at least two types of sensor monitoring data associated with the similar image monitoring data as the target sensor monitoring data, thereby expanding the data dimension used to predict the remaining life of the protection facility. The embodiment of the present application uses the target image monitoring data and the target sensor monitoring data as input data of the protection facility remaining life prediction model to obtain the remaining life of the protection facility to be predicted, thereby realizing the prediction of the remaining life of the protection facility through the protection facility remaining life prediction model based on multi-dimensional data, and improving the prediction accuracy of the remaining life of the protection facility.

[0046] Embodiment 2

[0047] Figure 2 It is a flow chart of another protective facility health monitoring method provided in Example 2 of the present application. This embodiment is further optimized on the basis of the above-mentioned embodiment. Specifically, before selecting at least two sensor monitoring data associated with the similar image monitoring data from the protective facility corrosion sample database as target sensor monitoring data based on the association relationship between the image monitoring data and the sensor monitoring data, the method also includes: obtaining historical image monitoring data and historical sensor monitoring data of the protective facility; establishing an association relationship between the historical image monitoring data and the historical sensor monitoring data according to the data collection position in the historical image monitoring data and the historical sensor monitoring data; based on the association relationship, constructing the protective facility corrosion sample database according to the historical image monitoring data and the sensor monitoring data.

[0048] like Figure 2 As shown, the protective facility health monitoring method includes:

[0049] S210. Acquire historical image monitoring data and historical sensor monitoring data of protective facilities.

[0050] The historical image monitoring data and the historical sensor monitoring data are respectively the monitoring data collected by the image acquisition device and the monitoring data collected by the sensor for the target protection facility area within the preset time. The preset time is determined by relevant technical personnel according to the actual situation and is not limited here. For example, it can be several months or several years.

[0051] S220: Establish an association relationship between the historical image monitoring data and the historical sensor monitoring data according to data collection positions in the historical image monitoring data and the historical sensor monitoring data.

[0052] The data collection location of historical image monitoring data refers to the location where historical image monitoring data is collected; the data collection location of historical sensor monitoring data refers to the location where historical sensor monitoring data is collected;

[0053] There are corresponding protection facility areas for the data collection locations of historical image monitoring data and the data collection locations of historical sensor monitoring data.

[0054] According to the data collection positions in the historical image monitoring data and the historical sensor monitoring data, an association relationship between the historical image monitoring data and the historical sensor monitoring data is established. Specifically, it is determined whether the protection facility area covered by the historical image monitoring data intersects with the protection facility area covered by the historical sensor monitoring data.

[0055] In an optional embodiment, an association relationship between the historical image monitoring data and the historical sensor monitoring data is established based on the data collection positions in the historical image monitoring data and the historical sensor monitoring data, including: determining the geographical coverage of the historical image monitoring data based on the data collection position of the historical image monitoring data and the image collection device configuration parameters; if the data collection position of the historical sensor monitoring data is within the geographical coverage, then associating the historical sensor monitoring data to the historical sensor monitoring data. The embodiment of the present application determines the geographical coverage of the historical image monitoring data, and constructs an association relationship between the historical image monitoring data and the historical sensor monitoring data based on the relative positional relationship between the data collection position of the historical monitoring data and the geographical coverage, thereby providing a data basis for migrating the sensor monitoring data in the protective facility corrosion sample database to areas in the protective facilities where sensors are not deployed.

[0056] The data acquisition location of the historical image monitoring data can be determined according to the installation location of the image acquisition device. For example, the configuration parameters of the image acquisition device can be the distance from the protective facility and the installation angle. The data acquisition location in the historical sensor monitoring data can be determined according to the installation location of the sensor.

[0057] The geographic coverage of the historical sensor monitoring data is determined based on the data collection location of the historical image monitoring data and the configuration parameters of the image acquisition device. If the data collection location of the historical sensor monitoring data is within the geographic coverage, the historical sensor monitoring data is associated with the historical sensor monitoring data. Specifically, the historical sensor monitoring data with a collection distance less than the preset distance threshold can be associated with the historical image monitoring data by calculating the collection distance between the data collection location of the historical sensor monitoring data and the data collection location of the historical image monitoring data and comparing the collection distance with a preset distance threshold.

[0058] S230: Based on the association relationship, construct the protection facility corrosion sample database according to the historical image monitoring data and the sensor monitoring data.

[0059] Based on the association relationship, the protection facility corrosion sample database is constructed according to the historical image monitoring data and the sensor monitoring data. Optionally, the same location identifier can be assigned to the historical image monitoring data and the sensor monitoring data that have the association relationship, and the historical image monitoring data and the sensor monitoring data with the location identifier are stored in the protection facility sample database. In this way, when any one of the image monitoring data or the sensor monitoring data is determined, the other monitoring data can be queried according to the location identifier.

[0060] S240, feature matching is performed on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and similar image monitoring data is selected from the candidate image monitoring data for the target image monitoring data.

[0061] S250. According to the association relationship between the image monitoring data and the sensor monitoring data, at least two sensor monitoring data associated with the similar image monitoring data are selected from the protection facility corrosion sample database as target sensor monitoring data.

[0062] S260: Use the target image monitoring data and the target sensor monitoring data as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0063] In an optional embodiment, the protective facility remaining life prediction model is a neural network model, and the protective facility remaining life prediction model is trained in the following manner: using the historical image monitoring data and the sensor monitoring data associated with the historical image monitoring data as training samples of the protective facility remaining life prediction model; using the remaining life of the protective facility as label data of the training sample; and training the protective facility remaining life model based on the training sample and the label data.

[0064] Among them, the historical image monitoring data and the sensor monitoring data associated with the historical image monitoring data can be obtained from the protection facility corrosion sample database. The protection facility corrosion sample database provides strong data support for training the protection facility remaining life prediction model. The historical image monitoring data and historical sensor monitoring data in the protection facility corrosion sample database can be used as training samples for the protection facility remaining life prediction model. Exemplarily, the protection facility remaining life prediction model is an ANN neural network or a CNN neural network with a multi-layer perceptron. The remaining life of the protection facility is used as the label data of the training sample. Among them, the label data of the training sample can be obtained by manual annotation.

[0065] The embodiment of the present application uses multi-dimensional protection facility monitoring data as input to the protection facility remaining life prediction model, and uses artificial intelligence technology to predict the remaining life of the protection facility to be predicted, thereby improving the accuracy of the remaining life prediction of the protection facility.

[0066] The technical solution provided in the embodiment of the present application obtains the historical image monitoring data and historical sensor monitoring data of the protective facilities; establishes the association relationship between the historical image monitoring data and the historical sensor monitoring data according to the data collection position in the historical image monitoring data and the historical sensor monitoring data; and constructs the protection facility corrosion sample database based on the historical image monitoring data and the sensor monitoring data based on the association relationship. The association between the historical image monitoring data and the historical sensor data is established, and the protection facility corrosion sample database is constructed, which provides data support for the remaining life prediction of the protection facilities.

[0067] Embodiment 3

[0068] Figure 3 This is a protective facility health monitoring device provided in the third embodiment of the present application. This embodiment can be applied to the situation of predicting the remaining life of protective facilities. The device can be implemented by software and / or hardware, and can be integrated into electronic devices such as smart terminals.

[0069] like Figure 3As shown, the device may include: a feature matching module 310, a target sensor monitoring data determination module 320 and a to-be-predicted remaining life determination module 330 for protective facilities.

[0070] The feature matching module 310 is used to perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data;

[0071] a target sensor monitoring data determination module 320, configured to select at least two sensor monitoring data associated with the similar image monitoring data from the protection facility corrosion sample database as target sensor monitoring data according to the association relationship between the image monitoring data and the sensor monitoring data;

[0072] The remaining life determination module 330 of the protective facility to be predicted is used to use the target image monitoring data and the target sensor monitoring data as input data of the protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0073] The technical solution provided in the embodiment of the present application realizes associating the target sensor monitoring data in the protection facility corrosion sample database with the target image monitoring data by selecting similar image monitoring data for the target image monitoring data from the candidate image monitoring data in the protection facility corrosion sample database, and using at least two types of sensor monitoring data associated with the similar image monitoring data as the target sensor monitoring data, thereby expanding the data dimension used to predict the remaining life of the protection facility. The embodiment of the present application uses the target image monitoring data and the target sensor monitoring data as input data of the protection facility remaining life prediction model to obtain the remaining life of the protection facility to be predicted, thereby realizing the prediction of the remaining life of the protection facility through the protection facility remaining life prediction model based on multi-dimensional data, and improving the prediction accuracy of the remaining life of the protection facility.

[0074] Optionally, the device also includes: a protective facility monitoring data acquisition module, used to obtain historical image monitoring data and historical sensor monitoring data of the protective facility before selecting at least two sensor monitoring data associated with the similar image monitoring data from the protective facility corrosion sample database as target sensor monitoring data based on the association relationship between the image monitoring data and the sensor monitoring data; a monitoring data association relationship establishment module, used to establish an association relationship between the historical image monitoring data and the historical sensor monitoring data according to the data collection positions in the historical image monitoring data and the historical sensor monitoring data; and a database construction module, used to construct the protective facility corrosion sample database based on the historical image monitoring data and the sensor monitoring data based on the association relationship.

[0075] Optionally, the monitoring data association relationship establishing module includes: a geographic coverage sub-module, used to determine the geographic coverage of the historical image monitoring data based on the data collection location and image collection device configuration parameters of the historical image monitoring data; a monitoring data association relationship establishing sub-module, used to associate the historical sensor monitoring data with the historical sensor monitoring data if the data collection location of the historical sensor monitoring data is within the geographic coverage.

[0076] Optionally, the protective facility remaining life prediction model is a neural network model, and the protective facility remaining life prediction model is trained in the following manner: using the historical image monitoring data and the sensor monitoring data associated with the historical image monitoring data as training samples of the protective facility remaining life prediction model; using the remaining life of the protective facility as label data of the training sample; and training the protective facility remaining life model based on the training sample and the label data.

[0077] Optionally, the feature matching module 310 includes: a feature similarity calculation submodule, used to calculate the feature similarity between the target image monitoring data and each candidate image monitoring data; and a similar image monitoring data determination submodule, used to select similar image monitoring data for the target image monitoring data from the candidate image monitoring data based on the feature similarity.

[0078] Optionally, the sensor monitoring data includes: at least two of corrosion parameters, mechanical parameters and environmental parameters.

[0079] A protective facility health monitoring device provided in an embodiment of the present invention can execute a protective facility health monitoring method provided in any embodiment of the present invention, and has corresponding performance modules and beneficial effects for executing a protective facility health monitoring method.

[0080] Embodiment 4

[0081] Embodiment 4 of the present application further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a protective facility health monitoring method when executed by a computer processor, the method comprising:

[0082] Perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data;

[0083] According to the association relationship between the image monitoring data and the sensor monitoring data, at least two sensor monitoring data associated with the similar image monitoring data are selected from the protection facility corrosion sample database as target sensor monitoring data;

[0084] The target image monitoring data and the target sensor monitoring data are used as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0085] Storage media refers to any of various types of memory electronic devices or storage electronic devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system, which is connected to the computer system via a network (such as the Internet). The second computer system can provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different unknowns (for example, in different computer systems connected via a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0086] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application, whose computer executable instructions are not limited to the remaining life prediction operation of the protective facility as described above, can also execute related operations in the protective facility health monitoring method provided in any embodiment of the present application.

[0087] Embodiment 5

[0088] Embodiment 5 of the present application provides an electronic device, in which the protective facility health monitoring device provided in the embodiment of the present application can be integrated. The electronic device can be configured within the system, or can be a device that executes part or all of the performance within the system. Figure 4 Schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present application. Figure 4As shown, this embodiment provides an electronic device 400, which includes: one or more processors 420; a storage device 410, which is used to store one or more programs. When the one or more programs are executed by the one or more processors 420, the one or more processors 420 implement the protective facility health monitoring method provided in the embodiment of the present application. The method includes:

[0089] Perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data;

[0090] According to the association relationship between the image monitoring data and the sensor monitoring data, at least two sensor monitoring data associated with the similar image monitoring data are selected from the protection facility corrosion sample database as target sensor monitoring data;

[0091] The target image monitoring data and the target sensor monitoring data are used as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted.

[0092] Of course, those skilled in the art will appreciate that the processor 420 also implements the technical solution of the protective facility health monitoring method provided in any embodiment of the present application.

[0093] Figure 4 The electronic device 400 shown is merely an example and should not bring any limitation to the performance and scope of use of the embodiments of the present application.

[0094] like Figure 4 As shown, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of the processor 420 in the electronic device can be one or more. Figure 4 A processor 420 is taken as an example; the processor 420, the storage device 410, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 4 The connection via bus 450 is taken as an example.

[0095] The storage device 410, as a computer-readable storage medium, can be used to store software programs, computer executable programs and module units, such as program instructions corresponding to the protective facility health monitoring method in the embodiment of the present application.

[0096] The storage device 410 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for performance; the data storage area may store data created according to the use of the terminal, etc. In addition, the storage device 410 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 410 may further include a memory remotely arranged relative to the processor 420, and these remote memories may be connected via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0097] The input device 430 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and performance control of the electronic device. The output device 440 may include electronic devices such as a display screen and a speaker.

[0098] The protective facility health monitoring device, medium, and electronic device provided in the above embodiments can execute the protective facility health monitoring method provided in any embodiment of the present application, and have the corresponding performance modules and beneficial effects of executing the method. For technical details not described in detail in the above embodiments, please refer to the protective facility health monitoring method provided in any embodiment of the present application.

[0099] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for monitoring the health of protective facilities, characterized in that: The method comprises: Perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data; According to the association relationship between the image monitoring data and the sensor monitoring data, at least two sensor monitoring data associated with the similar image monitoring data are selected from the protection facility corrosion sample database as target sensor monitoring data; Using the target image monitoring data and the target sensor monitoring data as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted; The target image monitoring data is used to reflect the corrosion situation of the protective facilities to be predicted, and the protective facility corrosion sample database is pre-constructed by the protective facility monitoring data, and the protective facility monitoring data includes image monitoring data and at least two types of sensor monitoring data; the image monitoring data and the sensor monitoring data are associated with each other and jointly reflect the corrosion situation of the same geographical area in the protective facilities; The protective facility remaining life prediction model is a pre-built model that predicts the protective facility remaining life based on image monitoring data and sensor monitoring data.

2. The method according to claim 1, characterized in that Before selecting at least two types of sensor monitoring data associated with the similar image monitoring data from the protection facility corrosion sample database as target sensor monitoring data according to the association relationship between the image monitoring data and the sensor monitoring data, the method further includes: Obtain historical image monitoring data and historical sensor monitoring data of protective facilities; Establishing an association relationship between the historical image monitoring data and the historical sensor monitoring data according to data collection locations in the historical image monitoring data and the historical sensor monitoring data; Based on the association relationship, the protection facility corrosion sample database is constructed according to the historical image monitoring data and the sensor monitoring data.

3. The method according to claim 2, characterized in that Establishing an association relationship between the historical image monitoring data and the historical sensor monitoring data according to the data collection positions in the historical image monitoring data and the historical sensor monitoring data includes: Determining the geographical coverage of the historical image monitoring data according to the data acquisition location of the historical image monitoring data and the configuration parameters of the image acquisition device; If the data collection location of the historical sensor monitoring data is within the geographical coverage, the historical sensor monitoring data is associated with the historical image monitoring data.

4. The method according to claim 2, characterized in that: in, The protective facility remaining life prediction model is a neural network model, and the protective facility remaining life prediction model is trained in the following manner: Using the historical image monitoring data and the sensor monitoring data associated with the historical image monitoring data as training samples for the remaining life prediction model of the protective facility; Using the remaining life of the protective facility as label data of the training sample; The protective facility remaining life model is trained based on the training samples and the label data.

5. The method according to claim 1, characterized in that The target image monitoring data of the protection facility to be predicted is feature matched with the candidate image monitoring data in the protection facility corrosion sample database, and similar image monitoring data is selected from the candidate image monitoring data for the target image monitoring data, including: Calculating feature similarity between the target image monitoring data and each candidate image monitoring data; According to the feature similarity, similar image monitoring data is selected for the target image monitoring data from the candidate image monitoring data.

6. The method according to claim 1, characterized in that in, The sensor monitoring data includes at least two of corrosion parameters, mechanical parameters and environmental parameters.

7. A protective facility health monitoring device, characterized in that: The device comprises: A feature matching module is used to perform feature matching on the target image monitoring data of the protection facility to be predicted and the candidate image monitoring data in the protection facility corrosion sample database, and select similar image monitoring data for the target image monitoring data from the candidate image monitoring data; a target sensor monitoring data determination module, configured to select at least two sensor monitoring data associated with the similar image monitoring data from the protection facility corrosion sample database as target sensor monitoring data according to the association relationship between the image monitoring data and the sensor monitoring data; A module for determining the remaining life of the protective facility to be predicted, used to use the target image monitoring data and the target sensor monitoring data as input data of a protective facility remaining life prediction model to obtain the remaining life of the protective facility to be predicted; The target image monitoring data is used to reflect the corrosion situation of the protective facilities to be predicted, and the protective facility corrosion sample database is pre-constructed by the protective facility monitoring data, and the protective facility monitoring data includes image monitoring data and at least two types of sensor monitoring data; the image monitoring data and the sensor monitoring data are associated with each other and jointly reflect the corrosion situation of the same geographical area in the protective facilities; The protective facility remaining life prediction model is a pre-built model that predicts the protective facility remaining life based on image monitoring data and sensor monitoring data.

8. The device according to claim 7, characterized in that The device also includes: a protection facility monitoring data acquisition module, configured to acquire historical image monitoring data and historical sensor monitoring data of the protection facility before selecting at least two types of sensor monitoring data associated with the similar image monitoring data from the protection facility corrosion sample database as target sensor monitoring data according to the association relationship between the image monitoring data and the sensor monitoring data; A monitoring data association relationship establishment module, used to establish an association relationship between the historical image monitoring data and the historical sensor monitoring data according to the data collection positions in the historical image monitoring data and the historical sensor monitoring data; A database construction module is used to construct the protection facility corrosion sample database based on the association relationship, according to the historical image monitoring data and the sensor monitoring data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the protective facility health monitoring method as described in any one of claims 1 to 6 is implemented.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the protective facility health monitoring method according to any one of claims 1 to 6 is implemented.

Images