Humidity sensor configuration method and system based on environmental characteristic analysis

Abstract

The invention relates to the technical field of sensor installation, in particular to a humidity sensor configuration method and system based on environmental characteristic analysis. Obtaining predicted characteristic environment parameters of each sub-region, and importing the predicted characteristic environment parameters into the corrosion resistance prediction model for prediction; screening, judging and analyzing each sub-region according to the corresponding predicted corrosion resistance change data set when the to-be-configured humidity sensor executes the preset monitoring task in each sub-region, and screening out configurable sub-regions; and performing installation suitability analysis on each configurable sub-region according to each actual scene three-dimensional model diagram, and performing analysis to obtain a final configuration sub-region of the to-be-configured humidity sensor. According to the method, the service life of the humidity sensor is prolonged, the working reliability of the humidity sensor is improved, the accuracy of monitoring data is improved, meanwhile, the sensor can be installed at a proper spatial position, and efficient humidity monitoring is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor installation, and in particular to a humidity sensor configuration method and system based on environmental feature analysis. Background Art

[0002] With the rapid development of technologies such as the Internet of Things, smart cities, and smart agriculture, the demand for environmental monitoring is growing. As an important environmental parameter, humidity is crucial to many fields in terms of accurate monitoring. Traditional humidity sensor configuration methods often rely on experience and manual judgment, lack of scientific basis, resulting in unreasonable sensor configuration positions, insufficient accuracy of monitoring data, and affecting the monitoring effect and service life of the sensor. For example, in certain corrosive environments, humidity sensors are prone to failure, resulting in abnormal monitoring data or system failure. Therefore, there is an urgent need for a method that can scientifically and reasonably configure humidity sensors according to environmental characteristics to improve monitoring accuracy, extend sensor service life, and reduce maintenance costs.

[0003] In the existing technology, some studies focus on the performance optimization and anti-interference ability improvement of humidity sensors, but few studies focus on sensor configuration methods based on environmental feature analysis. Environmental features, such as temperature, humidity, pH, salinity, etc., have a significant impact on the corrosion resistance and working stability of humidity sensors. Therefore, it is necessary to establish a humidity sensor configuration method that can take into account the influence of environmental features, and predict the corrosion resistance of sensors in different environments by analyzing environmental feature parameters, so as to screen out suitable installation areas. Summary of the invention

[0004] The present invention overcomes the deficiencies of the prior art and provides a humidity sensor configuration method and system based on environmental feature analysis.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0006] The present invention discloses a humidity sensor configuration method based on environmental feature analysis, comprising the following steps:

[0007] Obtaining the corrosion resistance change data of the humidity sensor to be configured when it works under various characteristic environmental parameter conditions, and building a corrosion resistance prediction model according to the corrosion resistance change data when it works under various characteristic environmental parameter conditions;

[0008] Obtaining a preset configuration range area of ​​the humidity sensor to be configured, and dividing the preset configuration range area into a plurality of sub-areas;

[0009] Obtain predicted characteristic environmental parameters of each sub-area, import the predicted characteristic environmental parameters into the corrosion resistance prediction model for prediction, and obtain a predicted corrosion resistance change data set corresponding to when the humidity sensor to be configured performs a preset monitoring task in each sub-area;

[0010] Screening, judging and analyzing each sub-area according to the predicted anti-corrosion capacity change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area, and screening out the configurable sub-area;

[0011] The actual scene three-dimensional model diagram of each configurable sub-area is obtained, and the installation adaptability analysis of each configurable sub-area is performed according to each actual scene three-dimensional model diagram to obtain the final configuration sub-area of ​​the humidity sensor to be configured.

[0012] Preferably, the corrosion resistance change data of the humidity sensor to be configured when working under various characteristic environmental parameter conditions are obtained, and the corrosion resistance prediction model is constructed according to the corrosion resistance change data when working under various characteristic environmental parameter conditions, specifically:

[0013] Obtain the corrosion resistance change data of the humidity sensor to be configured when working under various characteristic environmental parameter conditions through the big data network;

[0014] A decision tree algorithm is introduced, the characteristic environmental parameters are used as decision attributes, the corrosion resistance change data are used as target attributes, and a root node is initialized according to the decision attributes and the target attributes;

[0015] Starting from the root node, the tree is split according to the value range of different characteristic environmental parameters. Each branch corresponds to a value interval, and the tree hierarchy is gradually constructed. During the construction process, the best split attribute is selected based on information gain.

[0016] Finally, the decision tree is converted into a topological structure diagram, and a relationship matrix between various characteristic environmental parameters and corresponding corrosion resistance change data is obtained according to the topological structure diagram; wherein the nodes of the decision tree correspond to the nodes in the topological structure diagram, and the branches correspond to the edges;

[0017] A prediction model is constructed based on a deep learning network, and the relationship matrix is ​​embedded in the prediction model for coding learning training. After the model prediction accuracy meets the preset requirements, the final parameters of the model are saved and the corrosion resistance prediction model is output.

[0018] Preferably, the predicted characteristic environmental parameters of each sub-area are obtained, and the predicted characteristic environmental parameters are imported into the corrosion resistance prediction model for prediction, and the predicted corrosion resistance change data set corresponding to the humidity sensor to be configured performing the preset monitoring task in each sub-area is obtained, specifically:

[0019] Obtaining a preset working time period of the humidity sensor to be configured, performing discretization time processing on the preset working time period, and obtaining a preset working timestamp when the humidity sensor to be configured performs a preset monitoring task;

[0020] Based on the meteorological software, the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp are obtained;

[0021] Importing the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp into the corrosion resistance prediction model for prediction;

[0022] By prediction, a predicted anti-corrosion capability change data set corresponding to when the humidity sensor to be configured performs a preset monitoring task in each sub-area is obtained;

[0023] The predicted corrosion resistance change data set is a data collection of the predicted corrosion resistance data corresponding to the humidity sensor to be configured at each preset working timestamp.

[0024] Preferably, the sub-regions are screened, judged and analyzed according to the predicted anti-corrosion capacity change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-region, and the configurable sub-regions are screened out, specifically:

[0025] Preset the anti-corrosion capability threshold of the humidity sensor to be configured, and obtain the predicted anti-corrosion capability change data set corresponding to when the humidity sensor to be configured performs the preset monitoring task in each sub-area;

[0026] Compare the predicted corrosion resistance data corresponding to each preset working timestamp in the predicted corrosion resistance change data set corresponding to the execution of the preset monitoring task in each sub-area with the corrosion resistance threshold value;

[0027] Mark the preset working timestamp corresponding to the predicted corrosion resistance data being less than the corrosion resistance threshold as a potential corrosion risk timestamp; mark the preset working timestamp corresponding to the predicted corrosion resistance data being greater than the corrosion resistance threshold as a safe working timestamp;

[0028] And so on, until all the predicted corrosion resistance data in each predicted corrosion resistance change data set are analyzed and compared, the total number of potential corrosion risk timestamps and the total number of safe working timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area are counted;

[0029] The total number of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area is ratioed to the total number of safe working timestamps to obtain the ratio of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area.

[0030] Preferably, screening, judging and analyzing each sub-region according to the predicted anti-corrosion capability change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-region, and screening out the configurable sub-regions, further includes the following steps:

[0031] Compare the potential corrosion risk timestamp ratio when the humidity sensor to be configured performs the preset monitoring task in each sub-area with the preset ratio value;

[0032] If the proportion of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in a certain sub-area is greater than the preset proportion value, the sub-area is marked as a corrosive sub-area;

[0033] If the proportion of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in a certain sub-area is not greater than the preset proportion value, the sub-area is marked as a safety sub-area;

[0034] The safety sub-area is marked as a configurable sub-area, and the corrosion sub-area is marked as a non-configurable sub-area.

[0035] Preferably, the actual scene three-dimensional model diagram of each configurable sub-area is obtained, and the installation adaptability analysis of each configurable sub-area is performed according to each actual scene three-dimensional model diagram, and the final configuration sub-area of ​​the humidity sensor to be configured is obtained by analysis, specifically:

[0036] Acquire actual scene image information of each configurable sub-area, and construct an actual scene three-dimensional model image of each configurable sub-area according to the actual scene image information;

[0037] Obtain a standard installation scenario model diagram of the humidity sensor to be configured; introduce a cosine similarity algorithm, and calculate the cosine similarity between each actual scene three-dimensional model diagram and the standard installation scenario model diagram based on the cosine similarity algorithm;

[0038] Constructing a sorting table, importing the calculated cosine similarities into the sorting table for sorting, sorting out the maximum cosine similarity, and obtaining the configurable sub-region corresponding to the maximum cosine similarity;

[0039] The configurable sub-region corresponding to the maximum cosine similarity is marked as the final configuration sub-region output.

[0040] The present invention also discloses a humidity sensor configuration system based on environmental feature analysis, the humidity sensor configuration system includes a memory and a processor, the memory stores a humidity sensor configuration method program, when the humidity sensor configuration method program is executed by the processor, any one of the humidity sensor configuration method steps is implemented.

[0041] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: the humidity sensor configuration method based on environmental feature analysis can comprehensively consider the impact of environmental features on the corrosion resistance of the humidity sensor and the installation adaptability requirements. First, by constructing a corrosion resistance prediction model, the corrosion resistance of sensors in different sub-areas is predicted, and sub-areas that are feasible in terms of corrosion resistance are screened out, and then the most suitable final configuration sub-area for installation is determined based on the actual scene three-dimensional model diagram. This helps to improve the service life, working reliability and accuracy of monitoring data of the humidity sensor, while ensuring that the sensor can be installed in a suitable spatial position to achieve efficient humidity monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0043] Figure 1 This is a flow chart of the first method of the humidity sensor configuration method based on environmental feature analysis;

[0044] Figure 2 This is a flow chart of a second method of the humidity sensor configuration method based on environmental feature analysis;

[0045] Figure 3 This is the system block diagram of the humidity sensor configuration system based on environmental feature analysis. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0048] like Figure 1 As shown, the present invention discloses a humidity sensor configuration method based on environmental feature analysis, comprising the following steps:

[0049] S102: Acquire corrosion resistance change data of the humidity sensor to be configured when it works under various characteristic environmental parameter conditions, and construct a corrosion resistance prediction model according to the corrosion resistance change data when it works under various characteristic environmental parameter conditions;

[0050] S104: obtaining a preset configuration range area of ​​the humidity sensor to be configured, and dividing the preset configuration range area into a plurality of sub-areas;

[0051] S106: Obtain predicted characteristic environmental parameters of each sub-area, import the predicted characteristic environmental parameters into the corrosion resistance prediction model for prediction, and obtain a predicted corrosion resistance change data set corresponding to when the humidity sensor to be configured performs a preset monitoring task in each sub-area;

[0052] S108: Screening, judging and analyzing each sub-region according to the predicted anti-corrosion capability change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-region, and screening out the configurable sub-region;

[0053] S110: Acquire the actual scene three-dimensional model diagram of each configurable sub-area, perform installation adaptability analysis on each configurable sub-area according to each actual scene three-dimensional model diagram, and obtain the final configuration sub-area for the humidity sensor to be configured through analysis.

[0054] It should be noted that the corrosion resistance change data of the humidity sensor to be configured when working under various characteristic environmental parameters should be obtained first. Environmental parameters include temperature, humidity, pH, chemical concentration, etc., because different combinations of environmental parameters will have different effects on the corrosion resistance of the sensor. Then, a corrosion resistance prediction model is constructed based on these data. This model is the basis of the entire configuration method. It can predict the corrosion resistance of the sensor based on the input environmental parameters and provide a basis for the subsequent screening of suitable configuration areas. The preset configuration range area of ​​the humidity sensor to be configured is obtained and divided into several sub-areas. This division helps to analyze the impact of environmental characteristics of different local areas on the humidity sensor in more detail. Different sub-areas have different environmental characteristics. For example, factors such as terrain, vegetation coverage, and pollution source distribution may cause differences in environmental parameters between sub-areas. For each sub-area, its predicted characteristic environmental parameters are obtained, and then these parameters are imported into the corrosion resistance prediction model for prediction, so as to obtain the predicted corrosion resistance change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area. This step links the environmental characteristics of the sub-area with the corrosion resistance of the sensor, and quantifies the change of the corrosion resistance of the sensor in different sub-areas over time (during the execution of the preset monitoring task) through the prediction model. The sub-areas are screened and analyzed according to the predicted corrosion resistance change data set. By setting certain screening criteria, such as comparing whether the corrosion resistance meets the minimum requirements or whether the change in corrosion resistance is within an acceptable range, the configurable sub-areas are screened. This step excludes those sub-areas that may cause serious corrosion to the humidity sensor, affecting its normal operation and service life. For the screened configurable sub-areas, obtain their actual scene three-dimensional model diagrams. These three-dimensional model diagrams contain information such as the actual spatial layout of the sub-areas and the distribution of obstacles. Then, based on these three-dimensional model diagrams, the installation adaptability analysis of the configurable sub-areas is performed, such as considering the convenience of sensor installation and the coordination with the surrounding environment. Through this analysis, the final configuration sub-area of ​​the humidity sensor to be configured is finally determined, which is the best choice in terms of corrosion resistance and installation adaptability.

[0055] This humidity sensor configuration method based on environmental feature analysis can comprehensively consider the impact of environmental features on the corrosion resistance of humidity sensors and installation adaptability requirements. First, by building a corrosion resistance prediction model, the corrosion resistance of sensors in different sub-areas is predicted, and sub-areas that are feasible in terms of corrosion resistance are screened out. Then, the most suitable final configuration sub-area for installation is determined based on the actual scene three-dimensional model diagram. This helps to improve the service life, working reliability and accuracy of monitoring data of humidity sensors, while ensuring that the sensors can be installed in appropriate spatial locations to achieve efficient humidity monitoring.

[0056] Preferably, the corrosion resistance change data of the humidity sensor to be configured when working under various characteristic environmental parameter conditions are obtained, and the corrosion resistance prediction model is constructed according to the corrosion resistance change data when working under various characteristic environmental parameter conditions, such as Figure 2 As shown, specifically:

[0057] S202: Obtaining, through a big data network, data on changes in the corrosion resistance of the humidity sensor to be configured when it works under various characteristic environmental parameter conditions;

[0058] S204: introducing a decision tree algorithm, taking the characteristic environmental parameter as a decision attribute and the corrosion resistance change data as a target attribute, and initializing a root node according to the decision attribute and the target attribute;

[0059] S206: Starting from the root node, splitting is performed according to the value ranges of different characteristic environment parameters, each branch corresponds to a value interval, and the hierarchical structure of the tree is gradually constructed; wherein, during the construction process, the best splitting attribute is selected based on information gain;

[0060] S208: Finally, the decision tree is converted into a topological structure diagram, and a relationship matrix between various characteristic environmental parameters and corresponding corrosion resistance change data is obtained according to the topological structure diagram; wherein the nodes of the decision tree correspond to the nodes in the topological structure diagram, and the branches correspond to the edges;

[0061] S210: Build a prediction model based on a deep learning network, and embed the relationship matrix into the prediction model for coding learning training until the model prediction accuracy meets the preset requirements, save the final parameters of the model, and output the corrosion resistance prediction model.

[0062] It should be noted that the decision tree algorithm is introduced, and the characteristic environmental parameters are used as decision attributes and the corrosion resistance change data are used as target attributes to initialize the root node. This step is the starting point for building a decision tree, and clarifies the relationship between the input (characteristic environmental parameters) and the output (corrosion resistance change data) in the decision tree. Starting from the root node, split according to the value range of different characteristic environmental parameters. Each branch corresponds to a value interval, and the hierarchical structure of the tree is gradually constructed. In this process, the best split attribute is selected based on information gain. Information gain can measure the degree of influence of a certain attribute on the classification result. Selecting the attribute with the largest information gain for splitting can make the decision tree classify the data more effectively, thereby better reflecting the relationship between the characteristic environmental parameters and the corrosion resistance change data. The decision tree is converted into a topological structure diagram, and the nodes of the decision tree correspond to the nodes in the topological structure diagram, and the branches correspond to the edges. Then, the relationship matrix between various characteristic environmental parameters and the corresponding corrosion resistance change data is obtained according to the topological structure diagram. This relationship matrix is ​​a quantitative representation of the relationship between the characteristic environmental parameters and the corrosion resistance change data, which can clearly show the intrinsic connection between different environmental parameters and corrosion resistance. A prediction model is built based on a deep learning network, and the relationship matrix is ​​embedded in the prediction model for coding learning training. The deep learning network has a strong learning ability and can learn and optimize the complex relationships in the relationship matrix. During the training process, the parameters of the model are continuously adjusted until the model prediction accuracy meets the preset requirements. The final parameters of the model are saved and the corrosion resistance prediction model is output. This prediction model can accurately predict the changes in the corrosion resistance of the humidity sensor based on the input characteristic environmental parameters.

[0063] The corrosion resistance prediction model constructed in this step can make full use of the data resources in the big data network, use the decision tree algorithm to mine the intrinsic relationship between the characteristic environmental parameters and the corrosion resistance change data, and quantify this relationship in the form of a relationship matrix. Then, the powerful learning ability of the deep learning network is used to learn and train this relationship. The final corrosion resistance prediction model can accurately predict the corrosion resistance change of the humidity sensor according to different characteristic environmental parameters, providing a key basis for the subsequent reasonable configuration of the humidity sensor, which helps to improve the reliability of the humidity sensor in different environments, extend its service life, and optimize the configuration layout of the sensor.

[0064] Preferably, the predicted characteristic environmental parameters of each sub-area are obtained, and the predicted characteristic environmental parameters are imported into the corrosion resistance prediction model for prediction, and the predicted corrosion resistance change data set corresponding to the humidity sensor to be configured performing the preset monitoring task in each sub-area is obtained, specifically:

[0065] Obtaining a preset working time period of the humidity sensor to be configured, performing discretization time processing on the preset working time period, and obtaining a preset working timestamp when the humidity sensor to be configured performs a preset monitoring task;

[0066] Based on the meteorological software, the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp are obtained;

[0067] Importing the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp into the corrosion resistance prediction model for prediction;

[0068] By prediction, a predicted anti-corrosion capability change data set corresponding to when the humidity sensor to be configured performs a preset monitoring task in each sub-area is obtained;

[0069] The predicted corrosion resistance change data set is a data collection of the predicted corrosion resistance data corresponding to the humidity sensor to be configured at each preset working timestamp.

[0070] It should be noted that the preset working time period of the humidity sensor to be configured is first obtained, and the preset working time stamp is obtained by discretizing the time period. Discrete time processing is to divide the continuous time period into discrete time points. These time points (preset working time stamps) help to more accurately analyze the situation of the humidity sensor at different times. This is because the environmental parameters may change at different times. In this way, the influence of time factors on the operation of the humidity sensor can be considered more carefully. Based on the meteorological software, the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp are obtained. The meteorological software can provide environmental parameter prediction information about each sub-area. These predicted characteristic environmental parameters are factors closely related to the working environment of the humidity sensor, such as temperature, humidity, air pressure and other environmental factors that may affect the corrosion resistance of the sensor. By obtaining these parameters at each preset working time stamp, the environmental conditions of the sub-area at different times can be fully grasped. The predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp are imported into the corrosion resistance prediction model for prediction. Since the corrosion resistance prediction model is based on a previously constructed model that can reflect the relationship between characteristic environmental parameters and corrosion resistance changes, by inputting these predicted characteristic environmental parameters, the corrosion resistance prediction results of the humidity sensor to be configured when performing the preset monitoring tasks in each sub-area can be obtained. The predicted corrosion resistance change data set finally obtained is a collection of predicted corrosion resistance data corresponding to the humidity sensor to be configured at each preset working timestamp. This data set comprehensively reflects the corrosion resistance prediction of the humidity sensor in different sub-areas and different preset working timestamps, and provides detailed data support for subsequent screening, judgment and analysis. Through the above steps, the predicted corrosion resistance change data set of the humidity sensor to be configured when performing the preset monitoring tasks in each sub-area can be comprehensively and accurately obtained.

[0071] Preferably, the sub-regions are screened, judged and analyzed according to the predicted anti-corrosion capacity change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-region, and the configurable sub-regions are screened out, specifically:

[0072] Preset the anti-corrosion capability threshold of the humidity sensor to be configured, and obtain the predicted anti-corrosion capability change data set corresponding to when the humidity sensor to be configured performs the preset monitoring task in each sub-area;

[0073] Compare the predicted corrosion resistance data corresponding to each preset working timestamp in the predicted corrosion resistance change data set corresponding to the execution of the preset monitoring task in each sub-area with the corrosion resistance threshold value;

[0074] Mark the preset working timestamp corresponding to the predicted corrosion resistance data being less than the corrosion resistance threshold as a potential corrosion risk timestamp; mark the preset working timestamp corresponding to the predicted corrosion resistance data being greater than the corrosion resistance threshold as a safe working timestamp;

[0075] And so on, until all the predicted corrosion resistance data in each predicted corrosion resistance change data set are analyzed and compared, the total number of potential corrosion risk timestamps and the total number of safe working timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area are counted;

[0076] The total number of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area is ratioed to the total number of safe working timestamps to obtain the ratio of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area.

[0077] It should be noted that, first, the corrosion resistance threshold of the humidity sensor to be configured is preset, and this threshold is a key criterion for judging whether the sub-area is suitable for configuring the humidity sensor. At the same time, the predicted corrosion resistance change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area is obtained, and this data set contains the corrosion resistance prediction data of the sensor at different preset working timestamps. For the predicted corrosion resistance change data set of each sub-area, the predicted corrosion resistance data corresponding to each preset working timestamp is compared with the corrosion resistance threshold. If the predicted corrosion resistance data is less than the threshold, the corresponding preset working timestamp is marked as a potential corrosion risk timestamp; if it is greater than the threshold, it is marked as a safe working timestamp. This marking method can clearly distinguish the corrosion risk situation that the sensor may face at different times. After all the predicted corrosion resistance data in each predicted corrosion resistance change data set are analyzed and compared, the total number of potential corrosion risk timestamps and the total number of safe working timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area are counted. Then the total number of potential corrosion risk timestamps and the total number of safe working timestamps are processed by ratio, and the proportion of potential corrosion risk timestamps is obtained. This ratio can comprehensively reflect the relative degree of corrosion risk faced by the humidity sensor in each sub-area during the entire preset monitoring task.

[0078] Through the above steps, the total number of potential corrosion risk timestamps and the total number of safe working timestamps in each sub-area can be counted based on the comparison results of the corrosion resistance prediction data of each timestamp in the predicted corrosion resistance change data set with the preset threshold, and then the proportion of potential corrosion risk timestamps can be obtained. This proportion can quantitatively evaluate the degree of corrosion risk faced by the humidity sensor when performing the preset monitoring tasks in each sub-area, so as to screen out the configurable sub-areas, that is, those sub-areas with relatively low potential corrosion risks, and provide an effective screening basis based on corrosion resistance for the reasonable configuration of the humidity sensor, which helps to improve the service life of the humidity sensor and the reliability of the monitoring data.

[0079] Preferably, screening, judging and analyzing each sub-region according to the predicted anti-corrosion capability change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-region, and screening out the configurable sub-regions, further includes the following steps:

[0080] Compare the potential corrosion risk timestamp ratio when the humidity sensor to be configured performs the preset monitoring task in each sub-area with the preset ratio value;

[0081] If the proportion of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in a certain sub-area is greater than the preset proportion value, the sub-area is marked as a corrosive sub-area;

[0082] If the proportion of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in a certain sub-area is not greater than the preset proportion value, the sub-area is marked as a safety sub-area;

[0083] The safety sub-area is marked as a configurable sub-area, and the corrosion sub-area is marked as a non-configurable sub-area.

[0084] It should be noted that the potential corrosion risk timestamp ratio of the humidity sensor to be configured when performing the preset monitoring task in each sub-area is first compared with the preset ratio value. This preset ratio value is a pre-set standard used to distinguish the degree of corrosion of the sub-area. Through this comparison, the situation of each sub-area relative to this standard can be clarified. If the potential corrosion risk timestamp ratio of the humidity sensor to be configured when performing the preset monitoring task in a sub-area is greater than the preset ratio value, it means that in this sub-area, the sensor faces a relatively long time of corrosion risk, so the sub-area is marked as a corrosive sub-area. This marking indicates that the sub-area may pose a greater challenge to the corrosion resistance of the humidity sensor and is not suitable for the configuration of the sensor. On the contrary, if the potential corrosion risk timestamp ratio is not greater than the preset ratio value, it means that in this sub-area, the sensor faces a relatively short time of corrosion risk, and the sub-area is marked as a safety sub-area. This means that the sub-area has little effect on the corrosion resistance of the humidity sensor and is a relatively safe area. Finally, the safety sub-area is marked as a configurable sub-area, and the corrosive sub-area is marked as a non-configurable sub-area. In this way, the potential corrosion risk level of the humidity sensor is clearly classified according to the sub-area, and it is determined which sub-areas are suitable for configuring humidity sensors and which are not.

[0085] Through the above steps, the sub-areas can be accurately divided into corrosive sub-areas and safety sub-areas according to the comparison result of the potential corrosion risk timestamp ratio of the humidity sensor to be configured in each sub-area with the preset ratio value, and then the configurable sub-areas and non-configurable sub-areas can be determined. This method provides a clear basis for the reasonable configuration of humidity sensors, helps to avoid configuring humidity sensors in highly corrosive areas, thereby increasing the service life of humidity sensors, reducing sensor performance degradation or failures caused by corrosion, and ensuring the accuracy and reliability of humidity monitoring data.

[0086] Preferably, the actual scene three-dimensional model diagram of each configurable sub-area is obtained, and the installation adaptability analysis of each configurable sub-area is performed according to each actual scene three-dimensional model diagram, and the final configuration sub-area of ​​the humidity sensor to be configured is obtained by analysis, specifically:

[0087] Acquire actual scene image information of each configurable sub-area, and construct an actual scene three-dimensional model image of each configurable sub-area according to the actual scene image information;

[0088] Obtain a standard installation scenario model diagram of the humidity sensor to be configured; introduce a cosine similarity algorithm, and calculate the cosine similarity between each actual scene three-dimensional model diagram and the standard installation scenario model diagram based on the cosine similarity algorithm;

[0089] Constructing a sorting table, importing the calculated cosine similarities into the sorting table for sorting, sorting out the maximum cosine similarity, and obtaining the configurable sub-region corresponding to the maximum cosine similarity;

[0090] The configurable sub-region corresponding to the maximum cosine similarity is marked as the final configuration sub-region output.

[0091] It should be noted that the actual scene image information of each configurable sub-area is first obtained, and then the actual scene three-dimensional model map of each configurable sub-area is constructed based on this information. The actual scene image information contains various spatial information of the sub-area, such as terrain, landform, distribution of surrounding objects, etc. Constructing a three-dimensional model map can more intuitively and comprehensively reflect the actual scene situation of the sub-area, and provide a detailed spatial information basis for the subsequent installation adaptability analysis. The standard installation scene model map of the humidity sensor to be configured is obtained, and this standard installation scene model map represents the ideal installation scene of the humidity sensor. Then the cosine similarity algorithm is introduced, and the cosine similarity between each actual scene three-dimensional model map and the standard installation scene model map is calculated based on the algorithm. Cosine similarity is an indicator to measure the similarity between two vectors, and is used here to measure the similarity between the actual scene and the standard scene. By calculating this similarity, the degree of proximity of each configurable sub-area to the ideal installation scene can be quantitatively expressed. A sorting table is constructed, and the calculated cosine similarities are imported into the sorting table for sorting, so as to find the maximum cosine similarity. The configurable sub-area corresponding to the maximum cosine similarity is the sub-area that is most similar to the standard installation scene. Finally, this sub-region is calibrated as the final configuration sub-region and output. This means that this sub-region is the best choice in terms of installation adaptability and can meet the installation requirements of the humidity sensor to the greatest extent. Through the above steps, the final configuration sub-region that is most suitable for the installation of the humidity sensor can be found according to the cosine similarity between the actual scene three-dimensional model diagram of each configurable sub-region and the standard installation scene model diagram of the humidity sensor to be configured. This method uses the three-dimensional model diagram to comprehensively consider the spatial factors of the actual scene, and uses the cosine similarity algorithm for quantitative comparison, thereby realizing the selection of the sub-region with the best installation adaptability from multiple configurable sub-regions, which helps to ensure the performance of the humidity sensor in the actual installation environment and improve the working efficiency and monitoring accuracy of the sensor.

[0092] In addition, the method further comprises the following steps:

[0093] Pre-installing the humidity sensor to be configured on the final configuration sub-area, and after pre-installation, performing sensitivity tests on the pre-installed humidity sensor at several preset time nodes, obtaining sensitivity data of the humidity sensor at the preset time nodes, and obtaining dynamic sensitivity change data of the humidity sensor within a preset time period;

[0094] The Bezier curve algorithm is introduced, and the sensitivity data corresponding to the preset time nodes are regarded as the control points of the Bezier curve;

[0095] The sensitivity data of the first time node is used as the starting point of the curve. Then, according to the characteristics of the Bezier curve, the influence weight of each control point on the curve shape is determined.

[0096] The curve is gradually constructed by calculating the Bessel basis function. Starting from the starting point, the dynamic change data of the humidity sensor sensitivity is fitted into a Bessel curve according to the control point sequence and corresponding weights;

[0097] Obtaining a required sensitivity range value of the humidity sensor, taking the maximum value of the required sensitivity range value as the upper constraint boundary, and taking the minimum value of the required sensitivity range value as the lower constraint boundary;

[0098] Determine the constraint domain of the Bezier curve according to the upper constraint edge line and the lower constraint edge line; calculate the total length of the line segments in the Bezier curve that are within the constraint domain, and calculate the total length of the line segments in the Bezier curve that are outside the constraint domain;

[0099] Comparing the length of the bus segment outside the constraint domain with the length of the bus segment outside the constraint domain to obtain a constraint deviation rate; comparing the constraint deviation rate with a preset threshold;

[0100] If the restraint deviation rate is not greater than the preset threshold, the installation position of the humidity sensor is not adjusted; if the restraint deviation rate is greater than the preset threshold, the installation position of the humidity sensor is readjusted.

[0101] It should be noted that the humidity sensor to be configured is first pre-installed on the final configuration sub-area, and then the sensitivity test is performed on it at multiple preset time nodes to obtain the dynamic change data of sensitivity within the preset time period. Then the Bezier curve algorithm (Bezier curve algorithm) is introduced, and the sensitivity data corresponding to the preset time node is used as the control point of the Bezier curve. The sensitivity data of the first time node is used as the starting point of the curve. The influence weight of each control point on the curve shape is determined according to the characteristics of the Bezier curve, and then the curve is constructed through the Bezier basis function to fit the dynamic change data of sensitivity into a Bezier curve. This series of steps converts discrete sensitivity data into a continuous curve form for subsequent analysis. The required sensitivity range value of the humidity sensor is obtained, and the maximum value is determined as the upper constraint edge line and the minimum value is determined as the lower constraint edge line, thereby determining the constraint domain of the Bezier curve. After that, the total length of the line segments in and outside the constraint domain of the Bezier curve is calculated, and the total length of the bus segment outside the constraint domain is compared with the total length of the bus segment (inside the constraint domain + outside the constraint domain) to obtain the constraint deviation rate. This constraint deviation rate reflects the degree of deviation of the actual sensitivity change of the humidity sensor from the required range. Compare the constraint deviation rate with the preset threshold. If the constraint deviation rate is not greater than the preset threshold, it means that the sensitivity change of the humidity sensor is within the acceptable range and the installation position does not need to be adjusted. If the constraint deviation rate is greater than the preset threshold, it means that the sensitivity change of the humidity sensor exceeds the acceptable range, indicating that there are interference factors (such as electromagnetic interference, etc.) at this position and the installation position needs to be readjusted. By collecting the dynamic change data of the sensitivity of the humidity sensor within the preset time period and constructing the Bezier curve, the constraint domain is determined according to the required sensitivity range of the sensor and the constraint deviation rate is calculated. Finally, it is compared with the preset threshold to decide whether to adjust the installation position of the humidity sensor. This method can effectively evaluate the sensitivity stability of the humidity sensor after pre-installation in the final configuration sub-area, ensure that the sensitivity change of the sensor is within a reasonable range, thereby improving the reliability and accuracy of the humidity sensor and ensuring its effectiveness in applications such as environmental monitoring.

[0102] The present invention also discloses a humidity sensor configuration system based on environmental feature analysis, such as Figure 3 As shown, the humidity sensor configuration system includes a memory 20 and a processor 80. The memory 20 stores a humidity sensor configuration method program. When the humidity sensor configuration method program is executed by the processor 80, any one of the humidity sensor configuration method steps is implemented.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0104] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0105] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0106] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0107] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0108] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A humidity sensor configuration method based on environmental feature analysis, characterized in that: The following steps are involved: Obtaining the corrosion resistance change data of the humidity sensor to be configured when it works under various characteristic environmental parameter conditions, and building a corrosion resistance prediction model according to the corrosion resistance change data when it works under various characteristic environmental parameter conditions; Obtaining a preset configuration range area of ​​the humidity sensor to be configured, and dividing the preset configuration range area into a plurality of sub-areas; Obtain predicted characteristic environmental parameters of each sub-area, import the predicted characteristic environmental parameters into the corrosion resistance prediction model for prediction, and obtain a predicted corrosion resistance change data set corresponding to when the humidity sensor to be configured performs a preset monitoring task in each sub-area; Screening, judging and analyzing each sub-area according to the predicted anti-corrosion capacity change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area, and screening out the configurable sub-area; The actual scene three-dimensional model diagram of each configurable sub-area is obtained, and the installation adaptability analysis of each configurable sub-area is performed according to each actual scene three-dimensional model diagram to obtain the final configuration sub-area of ​​the humidity sensor to be configured.

2. A humidity sensor configuration method based on environmental feature analysis according to claim 1, characterized in that: Obtain the corrosion resistance change data of the humidity sensor to be configured when it works under various characteristic environmental parameter conditions, and build a corrosion resistance prediction model based on the corrosion resistance change data when it works under various characteristic environmental parameter conditions, specifically: Obtain the corrosion resistance change data of the humidity sensor to be configured when working under various characteristic environmental parameter conditions through the big data network; A decision tree algorithm is introduced, the characteristic environmental parameters are used as decision attributes, the corrosion resistance change data are used as target attributes, and a root node is initialized according to the decision attributes and the target attributes; Starting from the root node, the tree is split according to the value range of different characteristic environmental parameters. Each branch corresponds to a value interval, and the tree hierarchy is gradually constructed. During the construction process, the best split attribute is selected based on information gain. Finally, the decision tree is converted into a topological structure diagram, and a relationship matrix between various characteristic environmental parameters and corresponding corrosion resistance change data is obtained according to the topological structure diagram; wherein the nodes of the decision tree correspond to the nodes in the topological structure diagram, and the branches correspond to the edges; A prediction model is constructed based on a deep learning network, and the relationship matrix is ​​embedded in the prediction model for coding learning training. After the model prediction accuracy meets the preset requirements, the final parameters of the model are saved and the corrosion resistance prediction model is output.

3. A humidity sensor configuration method based on environmental feature analysis according to claim 1, characterized in that: The predicted characteristic environmental parameters of each sub-area are obtained, and the predicted characteristic environmental parameters are imported into the corrosion resistance prediction model for prediction, and the predicted corrosion resistance change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area is obtained, specifically: Obtaining a preset working time period of the humidity sensor to be configured, performing discretization time processing on the preset working time period, and obtaining a preset working timestamp when the humidity sensor to be configured performs a preset monitoring task; Based on the meteorological software, the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp are obtained; Importing the predicted characteristic environmental parameters corresponding to each sub-area at each preset working time stamp into the corrosion resistance prediction model for prediction; By prediction, a predicted anti-corrosion capability change data set corresponding to when the humidity sensor to be configured performs a preset monitoring task in each sub-area is obtained; The predicted corrosion resistance change data set is a data collection of the predicted corrosion resistance data corresponding to the humidity sensor to be configured at each preset working timestamp.

4. The humidity sensor configuration method based on environmental feature analysis according to claim 1, characterized in that: According to the predicted anti-corrosion capacity change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area, each sub-area is screened, judged and analyzed to select the configurable sub-areas, specifically: Preset the anti-corrosion capability threshold of the humidity sensor to be configured, and obtain the predicted anti-corrosion capability change data set corresponding to when the humidity sensor to be configured performs the preset monitoring task in each sub-area; Compare the predicted corrosion resistance data corresponding to each preset working timestamp in the predicted corrosion resistance change data set corresponding to the execution of the preset monitoring task in each sub-area with the corrosion resistance threshold value; Marking a preset working timestamp corresponding to a time when the predicted corrosion resistance data is less than the corrosion resistance threshold as a potential corrosion risk timestamp; Marking the preset working timestamp corresponding to the predicted corrosion resistance data being greater than the corrosion resistance threshold as a safe working timestamp; And so on, until all the predicted corrosion resistance data in each predicted corrosion resistance change data set are analyzed and compared, the total number of potential corrosion risk timestamps and the total number of safe working timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area are counted; The total number of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area is ratioed to the total number of safe working timestamps to obtain the ratio of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in each sub-area.

5. A humidity sensor configuration method based on environmental feature analysis according to claim 4, characterized in that: Screening and analyzing each sub-area according to the predicted anti-corrosion capability change data set corresponding to the humidity sensor to be configured when performing the preset monitoring task in each sub-area, and screening out the configurable sub-area, further comprising the following steps: Compare the potential corrosion risk timestamp ratio when the humidity sensor to be configured performs the preset monitoring task in each sub-area with the preset ratio value; If the proportion of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in a certain sub-area is greater than the preset proportion value, the sub-area is marked as a corrosive sub-area; If the proportion of potential corrosion risk timestamps when the humidity sensor to be configured performs the preset monitoring task in a certain sub-area is not greater than the preset proportion value, the sub-area is marked as a safety sub-area; The safety sub-area is marked as a configurable sub-area, and the corrosion sub-area is marked as a non-configurable sub-area.

6. The humidity sensor configuration method based on environmental feature analysis according to claim 1, characterized in that: The actual scene three-dimensional model diagram of each configurable sub-area is obtained, and the installation adaptability analysis of each configurable sub-area is performed according to each actual scene three-dimensional model diagram, and the final configuration sub-area of ​​the humidity sensor to be configured is obtained by analysis, specifically: Acquire actual scene image information of each configurable sub-area, and construct an actual scene three-dimensional model image of each configurable sub-area according to the actual scene image information; Obtain a standard installation scenario model diagram of the humidity sensor to be configured; introduce a cosine similarity algorithm, and calculate the cosine similarity between each actual scene three-dimensional model diagram and the standard installation scenario model diagram based on the cosine similarity algorithm; Constructing a sorting table, importing the calculated cosine similarities into the sorting table for sorting, sorting out the maximum cosine similarity, and obtaining the configurable sub-region corresponding to the maximum cosine similarity; The configurable sub-region corresponding to the maximum cosine similarity is marked as the final configuration sub-region output.

7. A humidity sensor configuration system based on environmental feature analysis, characterized in that: The humidity sensor configuration system includes a memory and a processor. The memory stores a humidity sensor configuration method program. When the humidity sensor configuration method program is executed by the processor, the humidity sensor configuration method steps according to any one of claims 1 to 6 are implemented.

Images