Distributed sensing and evaluation method of regional corrosion environment based on air conditioner operation data

Abstract

The application provides a kind of area corrosion environment distributed sensing and evaluation method based on air conditioner operation data.The method follows the technical route of distributed data acquisition,operation parameter acquisition,equipment level corrosion feature extraction,multi-device data aggregation,spatial location correlation,area corrosion environment inversion,corrosion grade division and result output,specifically comprising the following steps:distributed equipment data acquisition,operation parameter acquisition,equipment level corrosion feature extraction,multi-device data aggregation,spatial location correlation,area corrosion environment inversion,corrosion grade division and result output.The application has the advantages of significantly reducing the hardware investment and operation and maintenance cost of corrosion environment monitoring,covering a large area that is difficult to achieve by traditional monitoring methods,accurately depicting the corrosion environment differences within the area,providing dynamic support for predictive corrosion management,optimizing the allocation of corrosion protection resources,improving protection effect and resource utilization efficiency,and having strong engineering promotion prospects.

Description

Technical Field

[0001] This invention relates to the field of corrosion environment monitoring and industrial big data analysis technology, specifically to a method for regional corrosion environment perception and assessment based on the operating data of distributed air conditioning equipment. In particular, it is a distributed perception method that uses widely deployed air conditioning equipment as sensing nodes to invert the spatial distribution of regional corrosion environment through its operating parameters, thereby achieving large-scale, high-resolution, and low-cost corrosion environment monitoring. Background Technology

[0002] The corrosion behavior of materials during service is closely related to environmental factors. Environmental parameters such as temperature, relative humidity, concentration of corrosive media (e.g., chloride ions, sulfur dioxide), and frequency of wet-dry alternation collectively determine the corrosion rate and failure mode of materials. Accurately obtaining the spatial distribution of regional corrosion environments is of significant engineering value for optimizing the selection of engineering materials, predicting equipment corrosion life, and developing differentiated protection strategies.

[0003] In existing technologies, monitoring of corrosive environments mainly relies on the following methods: First, deploying standard corrosion test pieces in the target area and periodically weighing them to obtain corrosion weight loss data, thereby estimating the corrosion rate. While this method can directly reflect the corrosion response of the material, the deployment and retrieval cycle of test pieces is long, the spatial resolution is low, and real-time monitoring is not possible. Second, deploying electrochemical corrosion sensors to monitor parameters such as corrosion current or polarization resistance in real time. This method can obtain continuous corrosion data, but the sensors themselves are expensive, and they also face the problem of failure in highly corrosive environments, making large-scale deployment uneconomical. Third, deploying environmental monitoring stations to measure parameters such as temperature, relative humidity, and chloride ion deposition, and then indirectly assessing corrosivity based on empirical models. This method can obtain environmental parameters, but the number of monitoring stations is limited, making it difficult to cover a large area, and there is a discrepancy between the environmental parameters and the actual corrosion response of the material.

[0004] The above methods generally have the following technical limitations: the monitoring equipment is expensive, making it difficult to achieve large-scale, high-density deployment; the monitoring points are limited, the coverage area is small, the spatial resolution is low, and it is difficult to reflect the differences in the corrosion environment within the region; data acquisition is mostly intermittent, making it difficult to achieve dynamic and continuous corrosion environment assessment; the workload of sensor deployment and maintenance is large, and it is difficult to operate stably for a long time.

[0005] Meanwhile, air conditioning equipment is widely distributed in modern cities and industrial facilities. During operation, these devices continuously collect a large amount of multi-source parameter data reflecting environmental conditions and operating status through IoT systems, including outdoor ambient temperature, relative humidity, compressor operating time, and system load. This data, to a certain extent, reflects the local environmental characteristics of the area where the equipment is located. Furthermore, the wide spatial distribution, large number of air conditioning devices, and continuous data collection provide a potential data foundation for distributed sensing of regional corrosion environments. However, current technology has not yet established an effective method for using the operational data of these distributed devices to achieve regional corrosion environment sensing and assessment.

[0006] Therefore, there is an urgent need to provide a new technical solution that uses widely deployed air conditioning equipment as sensing nodes and utilizes their operational data to invert the spatial distribution of regional corrosion environment, thereby achieving low-cost, large-scale, high-resolution, and dynamic continuous corrosion environment monitoring and assessment. Summary of the Invention

[0007] The purpose of this invention is to overcome the technical shortcomings of existing corrosion environment monitoring technologies, such as reliance on dedicated sensors, high costs, limited coverage, and low spatial resolution. It provides a distributed sensing and assessment method for regional corrosion environments based on air conditioning operation data. This method utilizes widely distributed air conditioning equipment as sensing nodes. By collecting their operating parameters, extracting equipment-level corrosion characteristics, aggregating data from multiple equipment, and combining spatial location information for regional inversion, it achieves low-cost, high-resolution, and dynamically continuous sensing and assessment of corrosion environments over a large area.

[0008] To achieve the above-mentioned objectives, this invention provides a distributed sensing and assessment method for regional corrosion environment based on air conditioning operation data. This method follows a technical route of "distributed data acquisition, operational parameter acquisition, equipment-level corrosion feature extraction, multi-equipment data aggregation, spatial location correlation, regional corrosion environment inversion, corrosion level classification, and result output," and specifically includes the following steps: S1: Distributed device data acquisition Within the target monitoring area, widely deployed air conditioning equipment serves as distributed sensing nodes. Through the built-in IoT system of each device or external data acquisition terminals, operational data is continuously collected and uploaded to the data processing platform in real time. The air conditioning equipment is spatially distributed, covering different geographical locations within the monitoring area, forming a sensing node network. The data acquisition frequency can be set according to monitoring needs, typically at the minute or hourly level, to ensure dynamic tracking capabilities of regional environmental changes.

[0009] S2: Obtaining runtime parameters Multi-source operational parameters reflecting environmental conditions and equipment operational characteristics are extracted from the distributed device operational data collected in step S1. These operational parameters include at least one or more of the following categories: Environmental condition parameters: These reflect the thermal and humidity characteristics of the location of the equipment, including but not limited to outdoor ambient temperature, outdoor relative humidity, and the temperature and humidity of the microenvironment near the outdoor unit. Operating condition parameters: These reflect the operating status and load level of the equipment, including but not limited to compressor operating frequency, fan speed, cumulative running time, number of start-stop cycles, and continuous running time. Heat exchange process parameters: These reflect the heat exchange efficiency and condensation characteristics of the heat exchanger, including but not limited to the evaporator inlet and outlet air temperature difference, condenser inlet and outlet air temperature difference, refrigerant pressure, and refrigerant temperature. Electrical and control parameters: These reflect the energy consumption and control behavior of the equipment, including but not limited to compressor current, system input power, electronic expansion valve opening, and control mode.

[0010] The above operating parameters are collected by the Internet of Things system at a preset frequency to form time series datasets for each device.

[0011] S3: Equipment-level corrosion feature extraction Based on the operating parameters of each device obtained in step S2, corrosion characteristic information representing the local environmental corrosion characteristics of the area where the device is located is extracted. The extraction of device-level corrosion characteristics involves inputting the operating parameters into a pre-constructed corrosion characteristic extraction model, which outputs a corrosion intensity characterization measure of the device's location. Specifically, one or a combination of the following methods can be used: Parameter combination characteristics: Based on the corrosion mechanism, multiple operating parameters are combined into corrosion-sensitive characteristics with physical meaning, such as cumulative condensation time (calculated by the combination of temperature and humidity), frequency of dry and wet alternation (calculated by the combination of running time and number of start and stop), and cumulative effect of temperature and humidity. Mapping model features: Utilizing an established mapping relationship model between operating parameters and corrosion rate (which can be constructed using laboratory accelerated testing or field exposure test data), the equipment operating parameters are mapped to the equivalent corrosion rate or corrosion level at that location; Machine learning features: Using a trained machine learning model (such as random forest, neural network, etc.), with the running parameters as input, the output is the corrosion risk index at that location.

[0012] The result of the equipment-level corrosion feature extraction is a quantitative expression of the corrosion intensity of the local area where each air conditioning device is located, denoted as the corrosion feature value of each sensing node.

[0013] S4: Multi-device data aggregation The corrosion feature data from multiple devices (sensing nodes) obtained in step S3 are aggregated to form a node-level corrosion feature dataset covering the monitoring area. This dataset contains a unique identifier for each sensing node, spatial location information (latitude and longitude or coordinates), timestamp, and corresponding corrosion feature value. During the data aggregation process, data from different time points can be synchronized to ensure temporal consistency of the data used for regional inversion.

[0014] S5: Spatial Location Association The spatial location information of each air conditioning unit is obtained, and the corrosion feature data collected in step S4 is associated with its spatial location to establish a correspondence between data and space. The spatial location information can be obtained in the following ways: latitude and longitude coordinates recorded during equipment installation; geographic location based on the equipment's IP address or network access point; or geographic information based on the building to which the equipment belongs. The spatial location association results form a spatial distribution dataset, where each data point contains spatial coordinates (x, y) and its corresponding corrosion feature value.

[0015] S6: Regional Corrosion Environment Inversion Based on the spatial distribution dataset formed in step S5, spatial interpolation or spatial statistical methods are used to infer the corrosion environment characteristics at any location within the monitoring area where no equipment is deployed, thereby achieving regional-scale corrosion environment inversion. The regional corrosion environment inversion can employ one or a combination of the following methods: Spatial interpolation methods: Using methods such as Kriging interpolation, inverse distance weighted interpolation, or radial basis function interpolation, based on the corrosion characteristic values ​​of known nodes (location of air conditioning equipment), the corrosion characteristic values ​​of other locations in the region are estimated to generate a continuous spatial distribution map of corrosion characteristics. Spatial statistical methods: Spatial autocorrelation analysis, geographically weighted regression, and other methods are used to analyze the spatial distribution patterns and variation characteristics of corrosion features; Machine learning methods: Spatial interpolation machine learning methods (such as random forest spatial interpolation and deep neural network spatial interpolation) are used to integrate geographical auxiliary variables (such as topography and land use type) to improve inversion accuracy.

[0016] The inversion result is a continuous spatial field, expressed as a function or raster map of corrosion characteristic values ​​varying with spatial location.

[0017] S7: Corrosion Level Classification Based on the regional corrosion environment distribution results obtained from step S6, and combined with the preset corrosion level classification standards, the corrosion degree at different locations within the monitoring area is determined. The corrosion level classification standards can be preset according to material type, service requirements, or industry specifications. For example, they can be divided into multiple levels based on equivalent corrosion rate, such as slight corrosion (<0.1 mm / year), moderate corrosion (0.1-0.3 mm / year), and severe corrosion (>0.3 mm / year); or into low-risk, medium-risk, and high-risk levels based on the corrosion risk index. The classification results form a regional corrosion level distribution map.

[0018] S8: Output Results Output the regional corrosion environment assessment results obtained in step S7. The output format includes, but is not limited to: Corrosion level distribution map: Displays the corrosion level at different locations within the monitoring area in the form of a visual map, using color gradients or contour lines; Corrosion feature spatial distribution data: output in raster or vector data form for subsequent analysis and system integration; Regional statistical report: Outputs information such as the distribution area, proportion, and statistical characteristics of different corrosion levels within the region; Dynamic change analysis: Based on the inversion results at different time points, the temporal change trend and spatial migration characteristics of the corrosive environment are output.

[0019] The output evaluation results can be used to guide the selection of materials, differentiated operation and maintenance of equipment, and optimization of corrosion protection strategies within the region.

[0020] Advantages of this invention: Compared with existing technologies, the regional corrosion environment distributed sensing and assessment method based on air conditioning operation data provided by this invention has the following significant advantages: By utilizing existing equipment to achieve corrosion environment perception, the monitoring cost is greatly reduced: This invention eliminates the need for additional dedicated corrosion sensors or environmental monitoring stations. It makes full use of the widely deployed air conditioning equipment and its Internet of Things system as sensing nodes, realizing the deep mining and reuse of existing resources, and significantly reducing the hardware investment and operation and maintenance costs of corrosion environment monitoring.

[0021] Achieving wide-area coverage through distributed devices: Air conditioning devices are widely distributed and numerous in cities, parks, and building complexes. This invention uses these devices as sensing nodes to naturally form a high-density distributed sensing network, which can cover a wide area that is difficult to reach with traditional monitoring methods.

[0022] Significantly improves the spatial resolution of regional corrosion environments: Traditional monitoring methods have only sparse monitoring points and low spatial resolution. This invention utilizes data from a large number of distributed devices and, through spatial interpolation and inversion techniques, can generate continuous, high-resolution regional corrosion environment distribution maps, precisely depicting the differences in corrosion environments within a region.

[0023] Achieving dynamic and continuous corrosion environment assessment: The air conditioning equipment operation data is collected in real time and continuously. The invention can dynamically refresh the inversion results as the data is updated, realizing the time evolution tracking and spatial migration analysis of the regional corrosion environment, and providing dynamic support for predictive corrosion management.

[0024] Supporting differentiated and precise corrosion protection strategies: By acquiring high-resolution regional corrosion environment distribution, differentiated material selection and protection strategies can be formulated for regions with different corrosion levels, thereby optimizing the allocation of corrosion protection resources and improving protection effectiveness and resource utilization efficiency.

[0025] It has good engineering application value and scalability: This invention does not depend on specific models or brands of air conditioning equipment. As long as it has the ability to collect basic operating parameters, it can be applied. It is suitable for corrosion environment monitoring at various scales such as city, park and enterprise, and has strong prospects for engineering promotion. Attached Figure Description

[0026] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments: Figure 1 This is a schematic diagram of the overall process of the regional corrosion environment distributed sensing and assessment method based on air conditioning operation data described in this invention, which shows the complete technical route from distributed data acquisition to regional corrosion level output. Figure 2 This is a schematic diagram of the distributed device sensing node deployment according to the present invention, showing the spatial distribution of air conditioning equipment as sensing nodes in the monitoring area, forming a high-density sensing network covering the area; Figure 3 This is a schematic diagram of the regional corrosion environment inversion and classification described in this invention. It shows the process of generating a continuous corrosion feature distribution field based on distributed node corrosion feature values ​​through spatial interpolation, and dividing it into regions of different corrosion levels according to a preset threshold. Detailed Implementation

[0027] The present invention will be further explained below with reference to specific implementation schemes, but it is not limited to the present invention. The structures, proportions, sizes, etc. shown in the accompanying drawings are only used to complement the content disclosed in the specification, so as to enable those skilled in the art to understand and read, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modification of the structure, change of the proportion relationship or adjustment of the size, without affecting the effect and purpose that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0028] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below with reference to specific embodiments.

[0029] Example 1: Urban-level Regional Corrosion Environment Assessment S1: Distributed device data acquisition A typical area of ​​approximately 5 square kilometers was selected in a coastal city, containing about 300 air conditioning units distributed across residential buildings, commercial buildings, and public facilities. Operating data for each air conditioning unit was continuously collected for one year via an Internet of Things (IoT) platform, with a data collection frequency of once per hour.

[0030] S2: Obtaining runtime parameters The operating parameters of each device are extracted from the collected data, including: outdoor ambient temperature, outdoor relative humidity, cumulative compressor runtime, number of system start-ups and shutdowns, and condenser inlet and outlet air temperature difference.

[0031] S3: Equipment-level corrosion feature extraction A pre-built corrosion feature extraction model was used, taking the operating parameters of each device as input, and outputting the equivalent corrosion rate at the location of that device. This model was established based on laboratory accelerated testing and field exposure test data. Input parameters included cumulative condensation time (calculated from temperature and humidity), average relative humidity, and average daily compressor operating time. The output was the equivalent corrosion rate (mm / year). Corrosion feature values ​​for each node were calculated for 300 devices individually.

[0032] S4: Multi-device data aggregation The corrosion feature values ​​of 300 devices were aggregated to form a node-level corrosion feature dataset. Each record contains the device ID, latitude and longitude coordinates, time (corresponding to the data collection period), and equivalent corrosion rate.

[0033] S5: Spatial Location Association Corrosion characteristic values ​​were correlated with spatial location using the latitude and longitude coordinates recorded during the installation of each device. The processed data distribution shows that the device density is higher in areas near the coastline and relatively lower in inland areas, but the overall coverage is uniform.

[0034] S6: Regional Corrosion Environment Inversion Using ordinary kriging interpolation based on data from 300 nodes, spatial interpolation was performed on the monitoring area to generate a spatial distribution map of the equivalent corrosion rate with a resolution of 50 m × 50 m. The interpolation results show that the equivalent corrosion rate in the coastal area is between 0.35 and 0.50 mm / year, gradually decreasing to 0.10-0.20 mm / year towards the inland areas. In the urban center, due to the heat island effect and traffic pollution, the corrosion rate exhibits a localized high value zone (0.25-0.35 mm / year).

[0035] S7: Corrosion Level Classification Based on the preset corrosion level standards (slight corrosion <0.1 mm / year, moderate corrosion 0.1-0.3 mm / year, severe corrosion >0.3 mm / year), the inversion results are classified into levels: Severely corroded areas: coastal areas and some industrial zones, accounting for approximately 18% of the total area; Moderate corrosion zone: Urban center and coastal areas, accounting for approximately 52% of the total area; Areas with slight corrosion: Inland areas and ecological green spaces, accounting for approximately 30% of the total area.

[0036] S8: Output Results The output map shows the corrosion level distribution of the region, displayed in a gradient of red (severe corrosion), yellow (moderate corrosion), and green (slight corrosion). A statistical report is also output, detailing the area and percentage of each corrosion level. This result guides the development of differentiated operation and maintenance strategies for air conditioning equipment in different regions of the city; for example, a 3-month cleaning cycle is used for severely corroded areas, a 6-month cleaning cycle for moderately corroded areas, and a 12-month cleaning cycle for slightly corroded areas.

[0037] Example 2: Dynamic Monitoring and Trend Analysis of Corrosion Environment at the Industrial Park Level S1 to S2: Data Acquisition and Parameter Acquisition Fifty air conditioning units were selected as sensing nodes within an industrial park, and operational data was collected continuously for six months at a frequency of once per day (aggregated data). Parameters included average daily temperature, average daily relative humidity, average daily operating time, and weekly start-up and shutdown frequency.

[0038] S3: Equipment-level corrosion feature extraction A random forest model was used as the corrosion feature extractor, taking the operating parameters as input and outputting a corrosion risk index (range 0-1). The model was trained based on historical corrosion detection data. The corrosion risk index was calculated monthly for 50 devices.

[0039] S4 to S5: Data Convergence and Spatial Correlation The corrosion risk index of 50 devices was correlated with their spatial location on a monthly basis, forming a spatial distribution dataset at 6 time points.

[0040] S6 to S7: Regional Corrosion Environment Inversion and Classification For each time point, an inverse distance weighted interpolation is used to generate a spatial distribution map of the corrosion risk index, and the index is divided into three levels: low risk (<0.3), medium risk (0.3-0.6), and high risk (>0.6) according to the index value.

[0041] S8: Result Output (Dynamic Analysis) The system outputs a 6-month dynamic animation showing the changing trend of the corrosion risk area over time. The results show that in January and February, the high-risk area was mainly concentrated in the wet areas of the park; in March and April, with the arrival of the rainy season, the high-risk area expanded to the entire eastern part of the park; and in May and June, with the completion of the ventilation system upgrade, the high-risk area significantly shrank. This dynamic analysis provides data support for optimizing the park's equipment protection strategy and verifies the ability of the method of this invention to dynamically track changes in the corrosive environment.

[0042] Example 3: Method Validation and Accuracy Evaluation To verify the reliability of the method of the present invention, the regional corrosion level distribution obtained by inversion in Example 1 was compared with the measured data of 5 traditional environmental monitoring stations in the region.

[0043] Verification method At each monitoring station location, the equivalent corrosion rate is extracted from the inversion results; The corrosion rate was compared with that measured at the same site using the standard test piece method during the same period.

[0044] Verification results

[0045] The average relative error was 8.1%, and the inversion results showed good consistency with the measured results, verifying the reliability and accuracy of the method of the present invention.

[0046] Example 4: Monitoring of Cross-Seasonal Corrosion Environment Changes Based on Example 1, representative periods of four seasons (one month each) were selected to perform regional corrosion environment inversion and analyze the seasonal variation characteristics of the corrosion environment.

[0047] Seasonal data Spring (March): Average temperature 18℃, average humidity 70%, corrosion risk index is relatively evenly distributed, and severely corroded areas are limited to within 200 meters of the coastline. Summer (July): Average temperature 32℃, average humidity 85%. High humidity and high temperature lead to a general increase in the corrosion risk index, and the severely corroded area extends inland to 500 meters. Autumn (October): Average temperature 24℃, average humidity 65%, corrosion risk index drops, and severely corroded areas shrink. Winter (January): Average temperature 12℃, average humidity 60%, overall corrosion risk index is lowest.

[0048] Output A comparative map of corrosion level distribution across the four seasons was generated, visually demonstrating the spatiotemporal evolution of the corrosive environment with seasonal changes. This result provides a scientific basis for developing seasonal maintenance strategies for air conditioning equipment, such as appropriately increasing monitoring frequency and intervention intensity during the high-humidity summer season.

[0049] Matters not covered in this invention are common knowledge.

[0050] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A distributed sensing and assessment method for regional corrosion environment based on air conditioning operation data, characterized in that, Includes the following steps: S1: Within the monitoring area, multiple distributed air conditioning devices are used as sensing nodes, and operational data are collected through the Internet of Things system of each device to form a distributed sensing network. S2: Extract operating parameters from the collected operating data. The operating parameters include at least one of the following: environmental state parameters, operating condition parameters, heat exchange process parameters, or electrical and control parameters. S3: Based on the extracted operating parameters, extract the equipment-level corrosion features of the local area where each device is located. The equipment-level corrosion features are used to quantitatively characterize the corrosion intensity at that location. S4: Aggregate the device-level corrosion feature data from multiple devices to form a node-level corrosion feature dataset; S5: Obtain the spatial location information of each air conditioning unit, and associate the aggregated corrosion feature data with the spatial location to establish a correspondence between data and space; S6: Based on the spatial distribution dataset formed in step S5, spatial interpolation or spatial statistical methods are used to invert the corrosion environment characteristics of locations where no equipment is deployed within the monitoring area, and generate the spatial distribution of the corrosion environment at the regional scale. S7: Based on the regional corrosion environment distribution obtained from the inversion and combined with the preset corrosion level classification standard, the corrosion level of different locations within the monitoring area is determined. S8: Output the regional corrosion environment assessment results, which include at least a corrosion level distribution map or spatial distribution data of corrosion characteristics.

2. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The air conditioning equipment described in step S1 is spatially distributed, covering different geographical locations within the monitoring area to form a network of sensing nodes; the data acquisition frequency is on the minute or hour level, used to dynamically track changes in the regional environment.

3. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The environmental status parameters mentioned in step S2 include outdoor ambient temperature, outdoor relative humidity, or the temperature and humidity of the micro-environment near the outdoor unit; the operating condition parameters include compressor operating frequency, fan speed, cumulative running time, number of start-stop cycles, or continuous running time; the heat exchange process parameters include evaporator inlet and outlet air temperature difference, condenser inlet and outlet air temperature difference, refrigerant pressure, or refrigerant temperature; and the electrical and control parameters include compressor current, system input power, electronic expansion valve opening, or control mode.

4. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The equipment-level corrosion feature extraction described in step S3 can be performed using one of the following methods or a combination thereof: a parameter combination feature method that combines multiple operating parameters into corrosion-sensitive features with physical meaning; a mapping model method that utilizes the established mapping relationship between operating parameters and corrosion rate; or a machine learning feature method that uses a trained machine learning model to output a corrosion risk index.

5. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 4, characterized in that, The corrosion sensitivity features include cumulative condensation duration, frequency of wet-dry alternation, or cumulative temperature and humidity effects; the mapping model is constructed based on laboratory accelerated testing or field exposure test data; the machine learning model includes random forest or neural network models.

6. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The spatial interpolation methods described in step S6 include Kriging interpolation, inverse distance weighted interpolation, or radial basis function interpolation; the spatial statistical methods include spatial autocorrelation analysis or geographic weighted regression; and the inversion results are expressed in the form of a continuous spatial field as a function of corrosion characteristic values ​​varying with spatial location or a raster graph.

7. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The corrosion level classification standard mentioned in step S7 is based on material type, service requirements or industry standard preset, and classifies the degree of corrosion into slight corrosion, moderate corrosion and severe corrosion levels, or into low risk, medium risk and high risk levels.

8. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The regional corrosion environment assessment results output in step S8 also include regional statistical reports or dynamic change analysis based on inversion results at different time points. The dynamic change analysis is used to output the temporal evolution trend and spatial migration characteristics of the corrosion environment.

9. The regional corrosion environment distributed sensing and assessment method based on air conditioning operation data according to claim 1, characterized in that, The method utilizes widely deployed air conditioning equipment as sensing nodes to achieve large-scale, high-resolution, dynamic and continuous perception and assessment of the corrosive environment without the need for additional dedicated corrosion sensors.

Images