A unified correlation modeling method of air conditioner operating parameters and multi-material corrosion behavior

Abstract

The application relates to the technical field of material corrosion behavior modeling and industrial equipment data analysis, and provides a unified correlation modeling method for air conditioner operation parameters and multi-material corrosion behavior; the technical route is as follows: operation parameter collection, corrosion data acquisition, data matching and alignment, sensitive parameter screening, single-material response construction, multi-material unified modeling and model verification output, and the method specifically comprises the following steps: air conditioner operation parameter collection, multi-material corrosion data acquisition, data matching and alignment, corrosion sensitive parameter screening, single-material corrosion response relationship construction, multi-material unified modeling, model verification and output. The application has the following advantages: unified modeling of corrosion behaviors of various engineering materials is realized, the generalization ability of the model among different materials is improved, the model interpretability and engineering practicability are enhanced, the comparability expression of corrosion behaviors of different materials is realized, scientific decision of material selection is supported, and the application is suitable for large-scale deployment and corrosion management of various air conditioning systems.

Description

Technical Field

[0001] This invention relates to the field of material corrosion behavior modeling and industrial equipment data analysis technology, specifically to a unified correlation modeling method between air conditioning operating parameters and the corrosion behavior of multiple materials, and in particular, a modeling method that achieves comparable expression and prediction of the corrosion behavior of multiple materials such as copper, aluminum, steel and coatings by establishing a unified parameter system and corrosion response relationship. Background Technology

[0002] Materials inevitably corrode during service due to environmental factors. Accurate description and prediction of corrosion behavior are of significant engineering value for material selection, life assessment, and the development of protection strategies. Numerous studies have shown that the corrosion rate of materials is closely related to factors such as temperature, relative humidity, concentration of corrosive media, and duration of exposure. Therefore, establishing a quantitative relationship between environmental factors and material corrosion behavior is one of the core foundations of corrosion science research and engineering applications.

[0003] In practical engineering, air conditioning equipment continuously collects a large amount of parameter data reflecting environmental conditions and operating status through its Internet of Things (IoT) system during operation, including outdoor ambient temperature, relative humidity, compressor operating time, and system load changes. This data not only reflects the macroscopic environmental characteristics of the equipment but also contains key information affecting the corrosion process, such as the cumulative effect of temperature and humidity, condensation duration, and frequency of wet-dry alternation. Therefore, these operating parameters provide a rich data foundation for corrosion behavior modeling.

[0004] However, existing technologies have significant limitations in corrosion behavior modeling. First, current methods typically focus on a single material. Whether it's accelerated corrosion experiments in the laboratory or field exposure tests, most focus on a specific material (such as aluminum alloys or carbon steel), lacking a unified modeling framework that can simultaneously cover multiple engineering materials. Second, existing methods struggle to achieve comparative analysis between different materials. Due to differences in corrosion mechanisms and sensitive environmental factors among different materials, traditional single-material models cannot uniformly express and compare the corrosion behavior of different materials under the same parameter system, limiting the model's application value in material selection and protection scheme optimization. Third, existing models often have highly specific requirements for input parameters, making it difficult to directly utilize existing operating parameter data from air conditioning equipment, leading to a waste of data resources.

[0005] Therefore, there is an urgent need to provide a new technical solution that uses the operating parameters of air conditioning equipment as the core input to establish a unified correlation model that can simultaneously express the corrosion behavior of multiple engineering materials, so as to achieve the comparability of different materials under the same parameter system, thereby improving the generalization ability and engineering applicability of the model. Summary of the Invention

[0006] The purpose of this invention is to overcome the technical shortcomings of existing corrosion behavior modeling, which focuses on single materials, lacks a unified parameter system, and is difficult to achieve comparative analysis of multiple materials. This invention provides a unified correlation modeling method between air conditioning operating parameters and the corrosion behavior of multiple materials. This method establishes a unified parameter system with air conditioning operating parameters as the core input, constructs corrosion response relationships for different materials, and on this basis, achieves a unified expression and comparable modeling of the corrosion behavior of multiple materials, providing a scientific basis for material selection and corrosion protection.

[0007] To achieve the above-mentioned objectives, this invention provides a unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior. This method follows a technical route of "operating parameter acquisition, corrosion data acquisition, data matching and alignment, sensitive parameter screening, single-material response construction, unified multi-material modeling, and model verification output," and specifically includes the following steps: S1: Air Conditioner Operating Parameter Collection The system continuously collects multi-source operating parameters generated by the air conditioning unit during operation via its built-in IoT system or an external data acquisition terminal, and uploads them to the data processing platform in real time. These air conditioning operating parameters include at least one or more of the following categories: Environmental condition parameters: These reflect the thermal and humidity characteristics and corrosive conditions of the environment in which the equipment is located, including but not limited to outdoor ambient temperature, outdoor relative humidity, indoor return air temperature, and indoor return air humidity. Operating parameters: These represent 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.

[0008] The above parameters are collected by the Internet of Things system at a preset frequency (such as minute-level or hour-level) to form a continuous time series dataset, which serves as the basic input for subsequent modeling.

[0009] S2: Acquisition of Multi-Material Corrosion Data Corrosion data of various engineering materials under corresponding environmental conditions were obtained. The materials covered commonly used engineering materials in air conditioning heat exchange systems and related components, including at least the following categories: Copper and copper alloys: used in air conditioning pipes and fittings, their corrosion behavior is mainly affected by humidity, salt spray and air pollutants; Aluminum and aluminum alloys: used in heat exchanger fins, sensitive to temperature, humidity and condensation conditions; Steel and stainless steel: used for structural supports and fasteners, their corrosion behavior is significantly affected by chloride ions and alternating wet and dry conditions; Surface coating materials: used for heat exchanger and shell protection, their failure behavior is closely related to environmental aging factors.

[0010] The corrosion data includes, but is not limited to, corrosion rate (corrosion weight loss or corrosion depth per unit time), corrosion morphology characteristics (such as pitting density, corrosion area ratio, corrosion depth distribution), or corrosion level (slight corrosion, moderate corrosion, severe corrosion). Corrosion data can be obtained through accelerated corrosion experiments in the laboratory, natural environment exposure tests, or on-site corrosion detection.

[0011] S3: Data Matching and Alignment The air conditioning operating parameters collected in step S1 are matched and aligned with the multi-material corrosion data obtained in step S2 based on time and environmental conditions to ensure that data from different sources are comparable under the same spatiotemporal conditions. The matching and alignment includes: Time alignment: Synchronize the time nodes of corrosion data with the time series of operating parameters to ensure that the environmental conditions corresponding to the corrosion data are consistent with the environmental conditions reflected by the operating parameters in time; Environmental condition matching: For data obtained from laboratory accelerated corrosion experiments, it is necessary to establish a mapping relationship between the corresponding environmental conditions (temperature, humidity, salt spray concentration, etc.) and the environmental state parameters in the air conditioning operation parameters; Operating condition matching: For corrosion data of different materials and different batches, ensure that their corresponding operating conditions (such as load level and running time) are comparable.

[0012] Through the alignment process described above, a unified dataset of "running parameters and corrosion data" is constructed, laying the foundation for subsequent modeling.

[0013] S4: Screening of Corrosion-Sensitive Parameters Based on corrosion mechanism analysis and statistical data methods, key parameters that significantly influence the corrosion behavior of each material are selected from the operating parameters collected in step S1. The selection of corrosion-sensitive parameters can be achieved through the following methods: Mechanism analysis and screening: Based on the principle of corrosion electrochemistry, identify environmental factors (such as temperature, relative humidity, and condensation time) that are closely related to the corrosion rate, as well as parameters that reflect the operating status of the equipment (such as operating time, start-up and shutdown frequency, and dry-wet alternation cycle). Correlation analysis: For each material, calculate the Pearson correlation coefficient, Spearman rank correlation coefficient, or mutual information value between each operating parameter and its corrosion data, and screen out parameters with significant correlation (such as the absolute value of the correlation coefficient being greater than the set threshold); Feature importance assessment: Machine learning methods (such as random forest feature importance and gradient boosting tree feature importance) are used to identify the operating parameters that have the greatest impact on the corrosion state of different materials.

[0014] The selected set of corrosion-sensitive parameters is the core input feature for the subsequent construction of single-material response relationships.

[0015] S5: Construction of Single Material Corrosion Response Relationship For each engineering material, a response relationship model between air conditioning operating parameters and material corrosion behavior is established to describe the corrosion trend of the material under different operating parameter conditions. The construction of the single-material corrosion response relationship can be achieved using the following method: Parametric regression models, such as multiple linear regression, generalized linear models, or logistic regression, are suitable for scenarios where the mapping relationship is relatively linear. Nonlinear regression models, such as multinomial regression and support vector regression, are suitable for scenarios with nonlinear relationships. Machine learning models, such as random forests, gradient boosting trees, or deep neural networks, are suitable for high-dimensional features and complex nonlinear mapping relationships. Physical information model: Combining corrosion kinetics with data-driven methods, an interpretable hybrid model is constructed.

[0016] For each material, the constructed response relationship model can be expressed as:

[0017] in, This is a quantitative value for the corrosion rate or degree of corrosion of the m-th material. This is the set of corrosion-sensitive parameters selected. For the duration of action, Let be the corrosion response function of the m-th material.

[0018] S6: Unified Modeling of Multiple Materials A unified expression of the single-material corrosion response relationships of different materials is established, and a unified correlation model of multi-material corrosion behavior is constructed to make different materials comparable under the same operating parameter system. The unified modeling includes the following steps: Normalization: Normalize the quantified values ​​of corrosion rate or corrosion degree of different materials to a uniform numerical range (e.g., [0,1]) to eliminate the differences in the dimensions and numerical range of corrosion rate of different materials. Unified parameter space: Using the corrosion-sensitive parameters selected in step S4 as unified inputs, the corrosion response relationship of all materials is expressed as a set of functions under the same parameter space; Comparative modeling: Construct a multi-output model that can simultaneously output the corrosion states of multiple materials, such as a multi-output regression model or a multi-task learning framework, so that the model can capture the differentiated responses of different materials to the same environmental conditions. Relative sensitivity expression: Material type is introduced as an input variable into the unified model to establish a unified model that includes material characteristics, enabling direct comparison of the corrosion behavior of different materials.

[0019] The result of multi-material unified modeling is a unified model that takes air conditioning operating parameters as input and the corrosion states of multiple materials as output, which can be represented as:

[0020] in, For material type identification, To unify the association model.

[0021] S7: Model Validation and Output The unified correlation model constructed in step S6 was validated using actual or experimental data to confirm its ability to express and predict the corrosion behavior of multiple materials. Validation methods included: Cross-validation: Divide the dataset into training and test sets to evaluate the model's predictive performance on data that was not used in the training process; Comparative verification: Compare the model prediction results with independent experimental data or field detection data, and calculate the prediction error (such as mean absolute error, root mean square error). Consistency test: This test examines whether the ranking of corrosion degrees of different materials predicted by the model is consistent with the actual corrosion patterns, and verifies the model's relative sensitivity and expressive power.

[0022] After successful verification, a unified correlation model of multi-material corrosion behavior is output, including model structure, parameter configuration and material corrosion response relationship, which can be used for subsequent material selection, corrosion prediction and protection strategy optimization.

[0023] Advantages of this invention: Achieving unified modeling of corrosion behavior of multiple engineering materials: This invention breaks through the limitations of traditional methods that only target a single material, and establishes a unified model framework that can simultaneously express the corrosion behavior of multiple materials such as copper, aluminum, steel and coatings, providing technical support for corrosion management of multi-material systems.

[0024] Improving the model's generalization ability across different materials: By unifying the parameter system and normalizing the process, this invention enables the model to uniformly express the corrosion response of different materials, avoiding the workload of building a separate model for each material, and improving modeling efficiency and model scalability.

[0025] Enhancing the interpretability and engineering applicability of the model: This invention uses the existing operating parameters of the air conditioning equipment as the core input, enabling the model to directly utilize real-time data collected by the Internet of Things system without the need to acquire additional environmental monitoring data, thereby reducing the implementation cost and data acquisition difficulty of the model application.

[0026] Achieving comparable expression of corrosion behavior of different materials: Through a unified modeling framework and relative sensitivity expression, this invention enables quantitative comparison of corrosion differences of different materials under the same environmental conditions, providing a direct decision-making basis for material selection and protection scheme optimization.

[0027] Scientific decision-making to support material selection: Based on a unified model, the corrosion degree of different materials can be predicted for specific operating environments, thereby guiding the material selection and coating design of key components of air conditioning equipment and improving the environmental adaptability and service life of the equipment.

[0028] It has good engineering application value: 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 and is suitable for large-scale deployment and corrosion management of various air conditioning systems. Attached Figure Description

[0029] 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 unified correlation modeling method between air conditioning operating parameters and multi-material corrosion behavior described in this invention, which shows the complete technical route from data acquisition to model verification output. Figure 2 This is a schematic diagram illustrating the relationship between operating parameters and corrosion response as described in this invention, demonstrating the process of establishing a mapping from operating parameters to corrosion rate through sensitive parameter screening and single-material response relationship construction. Figure 3 This is a schematic diagram of the multi-material unified modeling described in this invention, illustrating the process of incorporating the corrosion response relationships of different materials into a unified framework to achieve comparability of multiple materials under the same parameter system. Detailed Implementation

[0030] 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.

[0031] 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.

[0032] Example 1: Single Material Modeling and Verification S1: Operation Parameter Acquisition In a coastal industrial park, a central air conditioning unit was selected as the data collection target. Operating data was continuously collected for one year through an air conditioning IoT platform, with a collection frequency of once per hour. The collected parameters included: outdoor ambient temperature, outdoor relative humidity, cumulative compressor runtime, system start / stop count, and condenser inlet / outlet air temperature difference.

[0033] S2: Acquisition of Material Corrosion Data 3003 aluminum alloy (used for air conditioner fins) was selected as the research object. Under laboratory conditions, a series of accelerated corrosion experiments were conducted on the aluminum alloy samples, controlling different temperature and humidity combinations and wet-dry cycle periods. The corrosion weight loss and corrosion current density of the samples under each condition were measured to obtain corrosion rate data. Simultaneously, standard aluminum test pieces were deployed within the industrial park for a one-year natural exposure test to obtain on-site corrosion rate data.

[0034] S3: Data Matching and Alignment By mapping and matching the environmental condition parameters of the laboratory accelerated experiment with the environmental state parameters in the air conditioning operation parameters, and by aligning the corrosion data of the natural exposure experiment with the air conditioning operation parameters at the corresponding time points, a "operation parameters and corrosion rate" associated dataset is constructed.

[0035] S4: Screening of Corrosion-Sensitive Parameters Based on corrosion mechanism analysis and correlation analysis, sensitive parameters that significantly affect aluminum alloy corrosion were selected. The results showed that the correlation coefficients between cumulative condensation time (estimated by the combination of temperature and humidity), average relative humidity, and average daily compressor operating time and corrosion rate were 0.82, 0.76, and 0.68, respectively, and these parameters were selected as the set of sensitive parameters.

[0036] S5: Construction of Single Material Corrosion Response Relationship Using sensitive parameters as input and corrosion rate as output, a multivariate nonlinear regression method is employed to construct a corrosion response model for aluminum alloys. The model expression is as follows:

[0037] in, This is the cumulative condensation duration (hours / day). The average relative humidity is (%). This represents the average daily operating time (in hours) of the compressor. The model's goodness of fit on the training set. It is 0.85.

[0038] S6 and S7: Verification and Output The model was applied to the operating data of another air conditioning unit in the same area to predict its aluminum alloy corrosion rate, and the results were compared with the measured results of a standard aluminum test piece placed at the same location. The average relative error between the predicted and measured values ​​was 12.5%, indicating that the model has good predictive accuracy.

[0039] Example 2: Unified Modeling of Multiple Materials S1 to S2: Data Acquisition and Corrosion Data Acquisition Three typical engineering materials were selected: T2 copper (for air conditioning piping), 3003 aluminum alloy (for fins), and Q235 carbon steel (for structural support), as well as an epoxy anti-corrosion coating (for heat exchanger protection). Under laboratory conditions, a series of accelerated corrosion experiments were conducted on the four materials, and environmental parameters and corrosion data were recorded simultaneously. At the same time, operating parameters of multiple air conditioning units in different areas were collected.

[0040] S3: Data Matching and Alignment The environmental conditions of the laboratory accelerated experiments were mapped and matched with the air conditioning operating parameters to construct a unified dataset of "operating parameters and multi-material corrosion data". The corrosion rate of each material was normalized and transformed to the [0,1] interval.

[0041] S4: Screening of Corrosion-Sensitive Parameters Through comprehensive correlation analysis and feature importance assessment, a unified set of sensitive parameters that have a significant impact on the corrosion behavior of various materials was selected, including: average relative humidity, cumulative condensation duration, average daily operating time, and wet-dry alternation frequency (calculated by a combination of start-stop times and operating time).

[0042] S5: Construction of Single Material Corrosion Response Relationship Single-material corrosion response models were constructed for four different materials. The results showed that copper was most sensitive to humidity and alternating wet and dry conditions; aluminum alloys were sensitive to condensation duration and operating time; carbon steel was sensitive to humidity and salt spray; and coatings were sensitive to ultraviolet radiation and temperature-humidity cycling. The goodness of fit for each model was above 0.80.

[0043] S6: Unified Modeling of Multiple Materials A multi-task learning framework is employed to model the corrosion response relationship of four materials in a unified manner. The model takes a unified sensitivity parameter as input and outputs the normalized corrosion degree of each of the four materials. The model uses a shared low-level feature extraction network and top-level networks that predict the corrosion states of different materials separately. During training, a multi-task loss function is used for joint optimization.

[0044] S7: Model Validation and Output The model was applied to a real air conditioning system, and its operating parameters were input to predict the corrosion degree of four materials. The prediction results are as follows: Under the same operating conditions, aluminum alloy showed the highest corrosion degree (normalized value 0.72), followed by copper (0.58), then carbon steel (0.45), and the coating showed the lowest (0.28). This ranking result is consistent with the actual corrosion pattern (aluminum fins are most sensitive to temperature and humidity, followed by copper pipes). Comparing the prediction results with field detection data, the mean absolute error was 0.07, verifying the effectiveness of the model. Finally, a unified correlation model of multi-material corrosion behavior was output to guide the material selection and protection optimization of this air conditioning system.

[0045] Example 3: Model Engineering Application Verification Application scenarios An air conditioning manufacturer, in its new product development, needs to select the optimal heat exchanger material and coating scheme for the tropical marine climate market. Using the unified correlation model established in this invention, and inputting predicted air conditioning operating parameters for the target market (based on historical climate data and expected operating modes), the corrosion degree of three candidate material schemes is predicted. Option A: Pure aluminum fins + ordinary hydrophilic coating; Option B: Aluminum alloy fins + reinforced epoxy coating; Option C: Copper fins (uncoated).

[0046] Model prediction results Option A: Normalized corrosion level 0.75 (high risk); Option B: Normalized corrosion level 0.35 (low risk); Option C: Normalized corrosion level 0.52 (medium risk).

[0047] Engineering Decisions Based on the model's predictions, the company selected Option B as its product configuration for the tropical marine climate market and adjusted its production plan and coating process accordingly. Subsequent market feedback showed that the corrosion complaint rate for Option B products in the region was approximately 70% lower than that of the original Option A, validating the effectiveness of the method of this invention in supporting engineering decisions.

[0048] Matters not covered in this invention are common knowledge.

[0049] 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 unified correlation modeling method for air conditioning operating parameters and corrosion behavior of multiple materials, characterized in that, Includes the following steps: S1: Collect air conditioning operating parameters through the Internet of Things (IoT) system of the air conditioning equipment. The air conditioning operating parameters include at least one of the following: environmental status parameters, operating condition parameters, heat exchange process parameters, or electrical and control parameters. S2: Obtain corrosion data for various engineering materials, wherein the materials include at least two of the following: copper and copper alloys, aluminum and aluminum alloys, steel and stainless steel, or surface coating materials, and the corrosion data includes corrosion rate, corrosion morphology, or corrosion level. S3: Match and align the air conditioning operating parameters collected in step S1 with the multi-material corrosion data obtained in step S2 based on time and environmental conditions to construct a unified "operating parameters - corrosion data" associated dataset. S4: Based on corrosion mechanism analysis and data statistics methods, a set of corrosion-sensitive parameters that have a significant impact on the corrosion behavior of each material are selected from the operating parameters; S5: For each material, establish a single-material corrosion response relationship model between air conditioning operating parameters and the corrosion behavior of the material, and describe the corrosion change trend of the material under different operating parameter conditions; S6: Based on the corrosion response relationships of each single material constructed in step S5, a unified correlation model of the corrosion behavior of multiple materials is constructed through normalization, unified parameter space mapping or multi-task learning framework, so that different materials are comparable under the same operating parameter system. S7: Verify the unified correlation model using actual or experimental data to confirm its ability to express and predict the corrosion behavior of multiple materials, and output the modeling results.

2. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The environmental status parameters mentioned in step S1 include outdoor ambient temperature, outdoor relative humidity, indoor return air temperature or indoor return air humidity; 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; the electrical and control parameters include compressor current, system input power, electronic expansion valve opening degree or control mode.

3. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The corrosion rate mentioned in step S2 includes corrosion weight loss or corrosion depth per unit time; the corrosion morphology includes pitting density, corrosion area ratio or corrosion depth distribution; and the corrosion level includes slight corrosion, moderate corrosion or severe corrosion.

4. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The data matching and alignment described in step S3 includes: time alignment of synchronizing the time nodes of corrosion data with the time series of operating parameters, and environmental condition matching of establishing a mapping relationship between the environmental conditions of the laboratory accelerated corrosion experiment and the environmental state parameters in the air conditioning operating parameters.

5. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The corrosion-sensitive parameter screening described in step S4 uses Pearson correlation coefficient, Spearman rank correlation coefficient, mutual information method or random forest feature importance method to calculate the correlation between each operating parameter and material corrosion data, and screens out parameters with significant correlation or high feature importance ranking.

6. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The single-material corrosion response model described in step S5 is constructed using multiple linear regression, multinomial regression, support vector regression, random forest, gradient boosting tree, deep neural network, or physical information machine learning model.

7. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The multi-material unified correlation model described in step S6 is constructed using a multi-output regression model or a multi-task learning framework. It takes a unified sensitive parameter as input and outputs the corrosion state of multiple materials. It also introduces material type identifiers as model input variables to achieve direct comparison of the corrosion behavior of different materials.

8. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The model validation described in step S7 uses cross-validation, comparative validation, or consistency testing methods to evaluate the model's predictive performance on data not used in the training and the consistency between the model's predicted ranking of corrosion degrees of different materials and the actual corrosion patterns.

9. The unified correlation modeling method for air conditioning operating parameters and multi-material corrosion behavior according to claim 1, characterized in that, The method uses the existing IoT operating parameters of the air conditioning equipment as the core input to construct a unified correlation model that can simultaneously express the corrosion behavior of multiple engineering materials, which is used for material selection and corrosion protection strategy optimization.

Images