Method and device for testing corrosion resistance of product in ammonia salt gas environment

Abstract

The application discloses a product corrosion resistance performance test method and device in an ammonia salt gas environment, and relates to the technical field of data processing.The method comprises the following steps: constructing a device-working condition test sample group according to a device type label library and a working condition database, performing response test under an ammonia salt gas environment sample, outputting a corrosion response sample group, combining the device-working condition test sample group to construct a device-working condition-corrosion sample triple, performing model training, obtaining a corrosion resistance performance prediction model, importing real-time data into a monitoring management terminal of a target area, and outputting a device corrosion resistance prediction distribution of the target area.The application solves the technical problem that the prior art cannot accurately simulate the corrosion performance of a device under a complex ammonia salt gas environment and working condition, and the precision of corrosion resistance risk prediction is insufficient, and achieves the technical effect of improving the corrosion resistance performance test precision by realizing dynamic simulation of a device under a complex environment and real-time corrosion resistance risk prediction.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and apparatus for testing the corrosion resistance of products in an ammonia salt gas environment. Background Technology

[0002] With the continuous development of industrialization, equipment and materials are often exposed to harsh environments, especially under the influence of corrosive gases such as ammonia salts. Therefore, the corrosion resistance of equipment has become a key factor in ensuring its long-term stable operation. Existing corrosion resistance testing methods are mainly focused on laboratory conditions and cannot effectively simulate the corrosion performance of equipment in complex and dynamic real-world working environments. Furthermore, traditional testing methods often ignore the influence of different operating conditions and environmental factors on the corrosion rate, resulting in low accuracy of prediction results. Summary of the Invention

[0003] This application provides a method and apparatus for testing the corrosion resistance of products in an ammonia salt gas environment, which is used to solve the technical problem that the existing technology cannot accurately simulate the corrosion performance of equipment in complex ammonia salt gas environments and operating conditions, resulting in insufficient accuracy in corrosion risk prediction.

[0004] The first aspect of this application provides a method for testing the corrosion resistance of products under an ammonia-salt gas environment. The method includes: constructing an equipment type label library and an operating condition database; constructing an equipment-operating condition test sample group based on the equipment type label library and the operating condition database; setting up an ammonia-salt gas environment sample, performing response tests under the ammonia-salt gas environment sample according to the equipment-operating condition test sample group, and outputting a corrosion response sample group, wherein the corrosion response sample group includes corrosion response data for each device under different operating conditions, and the corrosion response data includes the corrosion increase rate; constructing an equipment-operating condition-corrosion sample triplet using the equipment-operating condition test sample group and the corrosion response sample group; obtaining a corrosion resistance prediction model by training the equipment-operating condition-corrosion sample triplet; connecting the corrosion resistance prediction model to a monitoring and management terminal in a target area for real-time data import, and outputting the predicted corrosion resistance distribution of equipment in the target area.

[0005] A second aspect of this application provides a device for testing the corrosion resistance of products under an ammonia-salt gas environment. The device includes: a database construction module for constructing an equipment type tag library and an operating condition database; a test sample group construction module for constructing an equipment-operating condition test sample group based on the equipment type tag library and the operating condition database; and a response testing module for setting up an ammonia-salt gas environment sample, performing a response test under the ammonia-salt gas environment sample according to the equipment-operating condition test sample group, and outputting a corrosion response sample group, wherein the corrosion response... The sample set includes corrosion response data for each device under different operating conditions, including the corrosion rate of increase; a sample triplet construction module is used to construct a device-operating condition-corrosion sample triplet using the device-operating condition test sample set and the corrosion response sample set; a corrosion resistance prediction module is used to obtain a corrosion resistance performance prediction model by training the device-operating condition-corrosion sample triplet, and then connect the corrosion resistance prediction model to the monitoring and management terminal of the target area for real-time data import, outputting the predicted corrosion resistance distribution of the devices in the target area.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The corrosion resistance testing method and apparatus for products in an ammonia-salt gas environment provided in this application relate to the field of data processing technology. By constructing an equipment type tag library and an operating condition database, and combining corrosion response tests with ammonia-salt gas environment samples, a triplet of equipment-operating condition-corrosion sample is constructed. This triplet is then used to train a corrosion resistance prediction model, enabling real-time output of the predicted corrosion resistance distribution of the equipment. This solves the technical problem that existing technologies cannot accurately simulate the corrosion performance of equipment in complex ammonia-salt gas environments and operating conditions, resulting in insufficient accuracy in corrosion risk prediction. The method and apparatus achieve the technical effect of improving the accuracy of corrosion resistance testing by constructing a corrosion resistance prediction model to realize dynamic simulation and real-time corrosion risk prediction of equipment in complex environments. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 A schematic diagram of the process for testing the corrosion resistance of products in an ammonia salt gas environment, provided in an embodiment of this application;

[0010] Figure 2 The step response diagram for controlling the ammonia gas environment in the product corrosion resistance test method under ammonia gas environment provided in the embodiments of this application;

[0011] Figure 3 This is a scatter plot comparing the corrosion rate predicted by the model with the actual measured value in the product corrosion resistance test method under ammonia salt gas environment provided in the embodiments of this application.

[0012] Figure 4 The residual distribution of the prediction error of corrosion rate in the product corrosion resistance test method under ammonia salt gas environment provided in the embodiments of this application;

[0013] Figure 5 A schematic diagram of the structure of the product corrosion resistance testing device under ammonia salt gas environment provided in the embodiments of this application.

[0014] Figure labeling: Database construction module 11, Test sample group construction module 12, Response test module 13, Sample triplet construction module 14, Corrosion resistance prediction module 15. Detailed Implementation

[0015] This application provides a method and apparatus for testing the corrosion resistance of products in an ammonia salt gas environment, which is used to solve the technical problem that the existing technology cannot accurately simulate the corrosion performance of equipment in complex ammonia salt gas environments and operating conditions, resulting in insufficient accuracy in corrosion risk prediction.

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0018] Example 1, as Figure 1As shown, this application provides a method for testing the corrosion resistance of products in an ammonia salt gas environment, the method comprising:

[0019] P10a: Configure a monitoring and management terminal for the target area. The monitoring and management terminal includes an ammonia gas environment monitoring and management terminal, which is connected to an ammonia gas environment simulation device. The ammonia gas environment simulation device includes an ammonia flow controller and an ammonium chloride flow controller. The mixed gas in the reaction chamber is dynamically adjusted by the ammonia flow controller and the ammonium chloride flow controller to obtain an ammonia gas environment sample.

[0020] Specifically, the first step is to configure a monitoring and management terminal for the target area. This terminal should have ammonia gas environment monitoring and management function and be connected to an ammonia gas environment simulation device. The core function of the ammonia gas environment simulation device is to simulate an ammonia gas environment that meets experimental requirements by controlling the concentration and flow rate of the gas, thus providing realistic test conditions for testing the corrosion resistance of the equipment.

[0021] The ammonia-salt gas environment simulation device consists of an ammonia flow controller and an ammonium chloride flow controller. These two controllers work together to dynamically regulate the ammonia-salt gas mixture within the reaction chamber. The ammonia flow controller precisely regulates the ammonia flow rate, ensuring a stable and consistent ammonia concentration during the experiment by adjusting the ammonia input according to the experimental settings. Simultaneously, the ammonium chloride flow controller controls the salt flow rate and regulates the ammonium chloride concentration, which is crucial for the formation of the ammonia-salt gas environment, as the ammonium chloride concentration directly affects the salt spray density, thus influencing the equipment's corrosion rate.

[0022] Through precise coordination between these two controllers, the ammonia salt gas within the reaction chamber can be dynamically adjusted within a set range, ensuring that the concentrations of ammonia and salt spray meet specific standards throughout the experiment. Whenever experimental conditions change, the ammonia salt gas environmental monitoring and management terminal monitors these changes in real time and adjusts the controller's operating status through a feedback system to maintain a stable experimental environment.

[0023] In practice, the monitoring and management terminal must first be connected to the ammonia salt gas environment simulation device, and the device initialization settings must be completed. Then, according to the test requirements, the flow parameters of ammonia and ammonium chloride, as well as environmental parameters such as temperature and humidity within the reaction chamber, are set on the monitoring and management terminal. After starting the ammonia flow controller and the ammonium chloride flow controller, the device will dynamically adjust the composition and concentration of the mixed gas within the reaction chamber according to the preset parameters, generating an ammonia salt gas environment sample. Figure 2The step response diagram of the controlled ammonia gas environment shown can intuitively demonstrate the dynamic adjustment capability of this scheme. The dashed line (Set Point) represents the target concentration command received by the system, which instantly changes from 0 ppm to 100 ppm at t=50s. The solid line (Actual Concentration) represents the actual ammonia gas concentration change curve measured within the reaction chamber of the environmental simulation device. Throughout the process, the monitoring and management terminal monitors the environmental parameters within the reaction chamber in real time and automatically adjusts the parameters of the flow controller based on the monitoring data to ensure the stability and consistency of the ammonia gas environment sample. For example, the response delay can be monitored, i.e., the time required for the concentration to begin to rise significantly after the target concentration command is issued; the rise time, i.e., the time required for the concentration to rise from 0 to close to 100 ppm, is shown in the diagram as approximately 15 seconds, indicating a rapid system response; and the overshoot, i.e., the magnitude by which the actual concentration first exceeds 100 ppm. A good control system should have minimal overshoot. Steady-state error, which is the continuous deviation between the actual concentration and the target concentration (100 ppm) after the system stabilizes, is shown in the figure to be extremely small (<±1ppm), proving that the control accuracy of this scheme is very high and can generate accurate test environment samples, i.e. ammonia salt gas environment samples.

[0024] In this way, the ammonia gas environment simulation device can accurately simulate various corrosive gas environments, ensuring that the corrosion resistance of the equipment under real or extreme operating conditions can be fully evaluated.

[0025] P10: Build a device type tag library and an operating condition database.

[0026] Furthermore, the monitoring and management terminal also includes a device operation monitoring and management terminal, which is connected to the devices in the target area to build a device type tag library. Step P10 in this embodiment further includes:

[0027] P11: Obtain surface attribute information of each device within the target area, including surface structure information, surface treatment information, and surface material information; P12: Extract corrosion sensitivity factors of each device within the target area to obtain structured labels for each device; P13: Vectorize the structured labels of each device to output structured label vectors for each device; P14: Calculate the similarity between the structured label vectors of each device and classify each device according to the first similarity calculation result to obtain a device type label library.

[0028] It should be understood that, in order to achieve comprehensive monitoring and management of equipment within the target area, it is necessary to connect to the equipment in the target area through an equipment operation monitoring and management terminal to obtain the equipment's operating information in real time. This terminal will be able to record the equipment's working status, fault data, and maintenance records, etc., and this information will be aggregated and stored in an operating condition database to provide data support for subsequent analysis of the equipment's working environment.

[0029] Next, to better identify the corrosion characteristics of different equipment, it is first necessary to obtain the surface attribute information of each piece of equipment within the target area. This surface attribute information includes the equipment's surface structure, surface treatment, and surface material information. For example, surface structure information involves the morphology and roughness of the equipment surface; surface treatment information includes the type and effect of anti-corrosion coatings and platings; and surface material information refers to the specific materials used on the equipment surface. These factors directly affect the equipment's corrosion performance in an ammonia-salt gas environment. After obtaining this information, detailed surface attribute labels can be assigned to each piece of equipment to support subsequent classification.

[0030] Simultaneously, it is necessary to further extract corrosion susceptibility factors for each piece of equipment. These factors include the equipment material, surface treatment, and exposure to specific working environments. By analyzing these susceptibility factors, the corrosion resistance of each piece of equipment in an ammonia gas environment can be more accurately assessed. Integrating this data creates a structured label for each piece of equipment, reflecting its corrosion susceptibility and protective capabilities under different environments.

[0031] These structured tags will then undergo vectorization, transforming them into numerical feature vectors for the device. Vectorization is the process of converting structured tags into numerical vectors that can be efficiently processed within mathematical models. Through vectorization, complex corrosion susceptibility factors can be transformed into easily manipulated and analyzed numerical forms, thus providing a foundation for subsequent similarity calculations. Vectorization methods can include techniques such as one-hot encoding and word embedding; the specific method chosen depends on the type and complexity of the structured tags.

[0032] Finally, by calculating the similarity of the structured tag vectors of each device, and classifying the devices according to the first similarity calculation result, a device type tag library is obtained. Similarity calculation is the process of evaluating the degree of similarity between corrosion susceptibility factors of different devices. Commonly used similarity calculation methods include Euclidean distance and cosine similarity. Based on the calculated similarity results, devices with similar corrosion susceptibility characteristics are grouped into the same category, thus constructing the device type tag library. For example, as shown in Table 1:

[0033] Table 1 Equipment Type Tag Library

[0034] ;

[0035] The establishment of the equipment type label library provides a classification basis for subsequent corrosion resistance testing and model training, helping to more accurately assess the corrosion resistance of different types of equipment in an ammonia-salt gas environment. This process will help create a systematic equipment management system, enabling the accurate recording and classification of equipment type, performance, and corrosion resistance under different operating conditions. This provides a scientific and executable data support system for subsequent testing, evaluation, and maintenance, ensuring that the performance of each piece of equipment can be accurately predicted and optimized in real-world environments.

[0036] Furthermore, in constructing the operating condition database, step P10 of this embodiment also includes:

[0037] P15: Obtain the historical operating condition dataset of each device within the target area. The historical operating condition dataset includes the electrical parameters, thermal parameters, and mechanical parameters of each device. P16: By vectorizing the electrical parameters, thermal parameters, and mechanical parameters of each device, obtain the operating condition label vector of each device. P17: By performing similarity calculation on the operating condition label vector of each device, classify the operating conditions of each device according to the output second similarity calculation result to obtain the operating condition database.

[0038] Optionally, in further constructing the operational condition database, it is first necessary to obtain historical operational condition datasets for each device within the target area. This dataset should contain all key operating parameters of the devices during past use, including electrical, thermal, and mechanical parameters. Electrical parameters involve electrical performance indicators such as voltage, current, and power; thermal parameters include data related to the thermal state of the devices, such as temperature changes and heat flow; and mechanical parameters refer to mechanical load, vibration, and speed during operation. This historical operational condition data can be collected through various means, such as sensors integrated into the devices, data acquisition systems, or technical documents provided by the equipment manufacturers, to ensure the comprehensiveness and accuracy of the data.

[0039] After collecting this historical operating data, the next step is to vectorize the electrical, thermal, and mechanical parameters of each device. This process mainly involves converting these complex operating parameters into numerical vectors so that they can be effectively processed and analyzed in subsequent mathematical models. Vectorization typically includes data standardization steps to eliminate differences in dimensions and numerical ranges between different parameters. Common standardization methods include min-max normalization and Z-score standardization. Through standardization, different types of parameters can be unified to the same numerical range, thereby improving data consistency and comparability.

[0040] After vectorization, the operating condition label vectors for each device are obtained. Subsequently, similarity calculations are performed on these operating condition label vectors. The purpose of similarity calculation is to assess the degree of similarity between different devices in their operating conditions. Commonly used similarity calculation methods include Euclidean distance and cosine similarity. Based on the calculated second similarity results, the operating conditions of each device are classified, ultimately constructing an operating condition database. The establishment of this database provides detailed operating condition classification criteria for subsequent corrosion resistance testing, enabling the tests to more accurately simulate the actual operating conditions of the equipment, thereby more accurately evaluating the corrosion resistance performance of the equipment.

[0041] Through these steps, the operating condition database will effectively record the historical operating conditions of the equipment and provide important data support for the performance evaluation and optimization of the equipment.

[0042] P20: Construct a device-operating condition test sample group based on the device type tag library and the operating condition database.

[0043] Specifically, after completing the construction of the equipment type label library and the operating condition database, the next step is to build equipment-operating condition test sample groups based on these two databases. This process is a key step in the corrosion resistance testing method, aiming to combine the type characteristics of the equipment with actual operating conditions to form specific sample groups for testing, so as to more comprehensively and accurately evaluate the corrosion resistance performance of the equipment under different operating conditions.

[0044] Specifically, firstly, structured tag vectors for each piece of equipment are extracted from the equipment type tag library. These vectors contain key information such as corrosion susceptibility factors and accurately reflect the type characteristics of the equipment. Simultaneously, operating condition tag vectors for each piece of equipment are obtained from the operating condition database. These vectors record detailed operating condition data, including electrical, thermal, and mechanical parameters, of the equipment during its historical operation.

[0045] Then, the structured label vector of the equipment is combined with the corresponding operating condition label vector to form equipment-operating condition test sample groups. Each sample group represents a test scenario for a specific piece of equipment under a specific operating condition, covering two important dimensions: equipment type and operating conditions. In this way, it can be ensured that the test sample groups can fully reflect the diversity of equipment in actual use, providing rich and representative test scenarios for subsequent corrosion resistance testing.

[0046] For example, a specific type of equipment may exhibit different corrosion resistance under high temperature and high humidity conditions, while displaying different performance characteristics under normal temperature and low humidity conditions. By constructing an equipment-operating condition test sample group, the performance of this equipment under different operating conditions can be included in the test scope, thereby more comprehensively evaluating its corrosion resistance. Table 2 shows the operating condition database for a certain equipment:

[0047] Table 2 Operating Condition Database

[0048] ;

[0049] Furthermore, the construction of the equipment-operating condition test sample groups provides a foundation for subsequent data analysis and model training. These sample groups allow for the collection and analysis of corrosion response data of equipment under different operating conditions, enabling the construction of models that can accurately predict the corrosion resistance performance of equipment. This not only helps in the early detection of potential corrosion problems but also provides a scientific basis for equipment maintenance, management, and decision-making.

[0050] P30: Set up an ammonia gas environment sample, and perform response tests under the ammonia gas environment sample according to the equipment-operating condition test sample group, and output a corrosion response sample group, wherein the corrosion response sample group includes corrosion response data of each device under different operating conditions, and the corrosion response data includes the corrosion increase rate.

[0051] Furthermore, step P30 in this embodiment of the application also includes:

[0052] P31: Under the ammonium salt gas environment sample, conduct response tests according to the equipment-operating condition test sample group, and record the response change data of each device. The response change data includes surface defect changes and electrochemical response changes. P32: Calculate the corrosion rate according to the surface defect changes and electrochemical response changes respectively, and output the surface corrosion rate curve and the electrochemical corrosion rate curve. P33: Differentiate the surface corrosion rate curve and the electrochemical corrosion rate curve, and identify the corrosion increase rate as the output of the corrosion response sample group.

[0053] It should be understood that after constructing the equipment-operating condition test sample group, an ammonia-salt gas environment sample is further set up. This environment sample is generated using an ammonia-salt gas environment simulation device, which can precisely control the flow rates of ammonia and ammonium chloride, thereby dynamically adjusting the composition and concentration of the mixed gas within the reaction chamber to meet the test requirements. After setting up the ammonia-salt gas environment sample, response tests are conducted according to the equipment-operating condition test sample group, and the response change data of each device under different operating conditions are recorded. These response change data are important bases for evaluating the corrosion resistance performance of the equipment, specifically including changes in surface defects and electrochemical response changes.

[0054] Surface defect changes refer to microscopic or macroscopic defects that appear on the equipment surface during corrosion, such as pitting corrosion, crevice corrosion, and intergranular corrosion. These changes can be observed and recorded using optical microscopy, scanning electron microscopy (SEM), and other detection methods. Electrochemical response changes refer to changes in the electrochemical properties of the equipment during corrosion, such as electrode potential, polarization resistance, and corrosion current density. These changes can be measured and recorded using electrochemical testing methods, such as polarization curve testing and electrochemical impedance spectroscopy (EIS).

[0055] Specifically, response tests were first conducted under an ammonia-salt gas environment, following a set of equipment-operating-condition test samples, and detailed data on the response changes of each piece of equipment were recorded. This data includes not only changes in surface defects but also changes in electrochemical responses. By recording and analyzing this data, a comprehensive understanding of the corrosion behavior of the equipment under different operating conditions can be achieved.

[0056] Subsequently, corrosion rates were calculated based on the recorded response change data. For changes in surface defects, a surface corrosion rate curve was calculated; for changes in electrochemical response, an electrochemical corrosion rate curve was calculated. The surface corrosion rate can be calculated by the relationship between the area or depth of defect expansion and time, while the electrochemical corrosion rate is calculated by the relationship between current density and the electrochemical reaction rate. The surface corrosion rate curve reflects the rate of change of equipment surface defects over time, while the electrochemical corrosion rate curve reflects the rate of change of equipment electrochemical properties over time. These two curves can describe the corrosion process of the equipment from different perspectives.

[0057] Finally, the corrosion rate curves of the surface corrosion rate and the electrochemical corrosion rate curves were differentiated to identify the corrosion escalation rate. The corrosion escalation rate is the rate of change of the corrosion rate over time, reflecting the acceleration or deceleration trend of the corrosion process. Identifying the corrosion escalation rate by differentiation allows for a more accurate assessment of the corrosion risk of equipment under different operating conditions. Using these corrosion escalation rates as the output of the corrosion response sample set provides crucial data support for training subsequent corrosion resistance prediction models.

[0058] Once these steps are completed, the corrosion response sample set will provide accurate data for subsequent equipment corrosion resistance assessments. In particular, it can help identify the extent of corrosion aggravation in equipment under different operating conditions in an ammonia salt gas environment, thereby providing strong support for equipment maintenance and performance optimization.

[0059] P40: Construct a triplet of equipment-operating condition-corrosion samples using the equipment-operating condition test sample group and the corrosion response sample group.

[0060] Optionally, a triplet of equipment-operating condition-corrosion samples can be constructed using the already established equipment-operating condition test sample set and corrosion response sample set. This triplet provides a systematic data structure for subsequent model training and corrosion performance analysis, ensuring the comprehensiveness and accuracy of corrosion testing.

[0061] First, test samples for each device under specific operating conditions are extracted from the device-operating condition test sample group. These samples already include the device type characteristics (obtained through the device type tag library) and operating condition characteristics (obtained through the operating condition database). The device type characteristics reflect the basic attributes of the device, such as materials, structure, and surface treatment; the operating condition characteristics describe the electrical, thermal, and mechanical parameters experienced by the device during actual operation.

[0062] Next, corrosion response data corresponding to the equipment-operating condition test sample group were extracted from the corrosion response sample group. This corrosion response data was obtained through response testing under a specific ammonia salt gas environment, and includes key indicators such as corrosion rate increase, surface corrosion rate curves, and electrochemical corrosion rate curves. This data can intuitively reflect the corrosion behavior and extent of the equipment under different operating conditions.

[0063] Then, each sample in the equipment-operating condition test sample group is associated with the corresponding corrosion response data to form an equipment-operating condition-corrosion sample triplet. Each triplet contains information in three dimensions: equipment type, operating condition, and corrosion response. This data structure can comprehensively describe the corrosion of the equipment under specific operating conditions, providing rich information for subsequent analysis and model training.

[0064] For example, suppose a device A was tested under high temperature and high humidity conditions, and its corrosion response data indicates a high rate of corrosion increase. Then, the test sample of device A under high temperature and high humidity conditions, together with the corresponding corrosion response data, constitutes a device-operating condition-corrosion sample triplet. In this way, multiple triplets can be constructed to cover the corrosion of different devices under different operating conditions. Example, as shown in Table 3, is a partial training data set for the device-operating condition-corrosion sample triplet:

[0065] Table 3 Training Data Table of Equipment-Operating Condition-Corrosion Sample Triple Pair

[0066] Sample ID Device ID Operating Condition ID Environment ID Corrosion increase rate (mm / year) Pitting depth (μm) Stress corrosion index Corrosion product thickness (μm) Corrosion resistance rating S001 DEV001 wC001 ENV001 0.025 5.2 0.15 2.1 A S002 DEV001 wC001 ENV002 0.048 8.7 0.28 3.8 B S003 DEV001 WC001 ENV003 0.089 15.3 0.45 6.9 C S004 DEV001 wC001 ENV004 0.156 28.9 0.72 12.4 D SO05 DEV001 wC002 ENV001 0.042 7.8 0.22 3.5 B S006 DEV001 wC002 ENV002 0.078 12.4 0.38 5.9 B S007 DEV001 wC002 ENV003 0.134 22.1 0.58 9.8 C S008 DEV001 wC002 ENV004 0.223 39.5 0.85 17.2 D S009 DEV001 wC003 ENV001 0.067 11.3 0.31 4.8 B S010 DEV001 WC003 ENV002 0.118 18.9 0.49 7.8 C S011 DEV001 wc003 ENV003 0.189 31.2 0.71 13.1 D S012 DEV001 WC003 ENV004 0.298 52.8 0.95 22.4 E S013 DEV002 wC001 ENV001 0.156 18.5 0.42 8.9 C S014 DEV002 WC001 ENV002 0.234 28.3 0.59 13.7 C S015 DEV002 wC001 ENV003 0.342 41.8 0.78 19.8 D S016 DEV002 wC001 ENV004 0.489 63.2 0.92 28.9 E S017 DEV002 WC002 ENV001 0.198 23.7 0.51 11.2 C S018 DEV002 wC002 ENV002 0.287 35.9 0.68 16.8 D S019 DEV002 WC002 ENV003 0.401 51.4 0.84 24.1 D S020 DEV002 wC002 ENV004 0.567 74.8 0.98 34.2 E S021 DEV003 WC001 ENV001 0.038 6.9 0.19 3.1 A S022 DEV003 wc001 ENV002 0.072 11.2 0.34 5.4 B S023 DEV003 WC001 ENV003 0.128 19.8 0.52 8.9 C S024 DEV003 WC001 ENV004 0.209 34.1 0.74 15.3 D S025 DEV004 WC001 ENV001 0.298 35.8 0.63 17.4 D S026 DEV004 wc001 ENV002 0.421 52.3 0.79 24.9 D

[0067] As shown in the table, the corrosion resistance of equipment in an ammonia gas environment is determined by evaluating the equipment's corrosion response data under different operating conditions. The environment ID is used to identify different experimental environments or test conditions. Each environment ID represents a specific set of experimental parameters or conditions, such as ammonia gas concentration, temperature, and humidity. These environmental conditions affect the equipment's corrosion performance during testing; therefore, distinguishing different environments using environment IDs allows for a more accurate assessment of the equipment's corrosion resistance under various operating conditions.

[0068] For example, the environment IDs in Table 3 may correspond to the following different environment conditions:

[0069] Environment ID=ENV001: Represents a normal temperature and humidity environment, with a temperature of 25°C, humidity of 60%, and ammonia gas concentration of 50 ppm; Environment ID=ENV002: Represents a medium temperature and high humidity environment, with a temperature of 40°C, humidity of 70%, and ammonia gas concentration of 100 ppm; Environment ID=ENV003: Represents a high temperature and high humidity environment, with a temperature of 60°C, humidity of 80%, and ammonia gas concentration of 150 ppm. The environment ID clearly identifies the test results of each device under specific environmental conditions. For example, the corrosion response data of device DEV001 under ENV001 environment differs from that under ENV002 environment. The environment ID allows for clear identification and differentiation of these data, facilitating subsequent analysis. Specifically, corrosion response data includes important parameters such as corrosion rate, pitting depth, stress corrosion index, and the thickness of corrosion products. This data comprehensively reflects the corrosion behavior and performance of the equipment under specific environmental conditions. Among them, the corrosion rate of increase is the rate at which corrosion of equipment intensifies under a specific environment, measuring the degree of acceleration of corrosion. A higher corrosion rate of increase indicates that the equipment is corroded more rapidly under that environment. Pitting depth refers to the depth of pitting defects appearing on the equipment surface. Pitting is a form of localized corrosion; the greater the depth, the more severe the corrosion. Stress corrosion index assesses the corrosion susceptibility of equipment under stress. A high stress corrosion index usually means that the equipment is prone to stress corrosion cracking under specific conditions. Corrosion product thickness represents the thickness of the corrosion product layer formed on the equipment surface during corrosion. The thickness of the corrosion product layer can reflect the formation of a protective film on the equipment surface. Specifically, the corrosion resistance levels in Table 3 can be evaluated based on threshold settings of these data, for example:

[0070] First, set appropriate thresholds for these corrosion response data. For example:

[0071] Corrosion rate increase: less than 0.1 mm / year may be considered Grade A, 0.1-0.5 mm / year is Grade B, and more than 0.5 mm / year is Grade C; Pitting depth: less than 10 μm is Grade A, 10-50 μm is Grade B, and more than 50 μm is Grade C; Stress corrosion index: less than 0.2 is Grade A, 0.2-0.5 is Grade B, and more than 0.5 is Grade C; Corrosion product thickness: less than 5 μm is Grade A, 5-20 μm is Grade B, and more than 20 μm is Grade C.

[0072] Next, the corrosion response data of the equipment under different operating conditions are compared with the above standards. Under each operating condition, each corrosion parameter of the equipment is assigned a corrosion level (such as level A, level B, level C).

[0073] Furthermore, by considering the corrosion levels under different operating conditions, the final corrosion resistance level is determined:

[0074] Grade A: The equipment exhibits excellent corrosion response data under all test conditions, with a low corrosion rate, small pitting depth, low stress corrosion index, thin corrosion products, and superior corrosion resistance.

[0075] Grade B: The equipment exhibits moderate corrosion under certain operating conditions, and there may be some degree of corrosion aggravation (such as moderate corrosion rate and slightly larger pitting depth).

[0076] Grade C or lower (such as Grade D or Grade E): The equipment exhibits severe corrosion under most operating conditions, with a high rate of corrosion increase, large pitting depth, high stress corrosion index, thick corrosion product layer, and poor corrosion resistance.

[0077] Finally, all the constructed equipment-operating condition-corrosion sample triples are integrated into a single database, forming a complete dataset. This dataset will serve as the foundation for training subsequent corrosion resistance prediction models. By learning from the data in these triples, the models will identify the intrinsic relationships between equipment type, operating conditions, and corrosion response, thereby gaining the ability to predict the corrosion resistance performance of new equipment under new operating conditions.

[0078] Therefore, by organically combining the equipment-operating condition test sample group and the corrosion response sample group, a three-element equipment-operating condition-corrosion sample can be constructed, which can provide structured and comprehensive data support for training the corrosion resistance performance prediction model.

[0079] P50: By training the model on the equipment-operating condition-corrosion sample triplet, a corrosion resistance prediction model is obtained. The corrosion resistance prediction model is then connected to the monitoring and management terminal of the target area for real-time data import, and the predicted distribution of equipment corrosion resistance in the target area is output.

[0080] Furthermore, the corrosion resistance prediction model is connected to the monitoring and management terminal of the target area for real-time data import. In this embodiment, step P50 further includes:

[0081] P51: The monitoring and management terminal of the target area obtains the distribution location of the ammonia gas environment simulation device; P52: Based on the distribution location of the ammonia gas environment simulation device, gas diffusion simulation is performed, and the spatial distribution of ammonia gas concentration in the target area is output; P53: The monitoring and management terminal of the target area obtains the distribution location of each device in the target area; P54: Based on the distribution location of each device in the target area, the spatial distribution of ammonia gas concentration is identified to obtain the real-time ammonia gas concentration corresponding to each device, and the real-time ammonia gas concentration corresponding to each device is imported into the corrosion resistance prediction model.

[0082] Specifically, the model is first trained using a triplet of equipment-operating condition-corrosion sample to obtain a corrosion resistance prediction model. This model can learn the complex relationship between equipment type, operating condition, and corrosion response, enabling it to predict the corrosion resistance of equipment. Model training can employ machine learning or deep learning algorithms, such as random forests, support vector machines (SVMs), and neural networks, with the specific choice depending on data complexity and prediction accuracy requirements. After model training is complete, it is connected to a monitoring and management terminal in the target area. This terminal is responsible for collecting real-time equipment operation data and environmental data within the target area and importing them into the corrosion resistance prediction model to achieve real-time prediction of equipment corrosion resistance.

[0083] Furthermore, the monitoring and management terminal first acquires the distribution locations of the ammonia gas environment simulation devices within the target area. This information is crucial for subsequent gas diffusion simulations, as it determines the initial distribution of ammonia gas within the target area. Distribution locations can be obtained through Geographic Information System (GIS) data, equipment installation records, or on-site mapping, ensuring data accuracy and completeness. Based on the distribution locations of the ammonia gas environment simulation devices, gas diffusion simulations are performed, outputting the spatial distribution of ammonia gas concentration within the target area. Gas diffusion simulations can employ computational fluid dynamics (CFD) models or empirical formulas, considering the influence of factors such as airflow, temperature, and humidity within the target area on gas diffusion. Through simulation, a distribution map of ammonia gas concentration at different locations within the target area is obtained, providing an environmental basis for subsequent prediction of equipment corrosion resistance.

[0084] Subsequently, the monitoring and management terminal further acquires the distribution location of each device within the target area. This information is equally important because it determines the specific location of the devices within the target area and the ammonia gas concentration environment in which they are situated. Device distribution locations can be obtained through equipment installation records, GIS data, or on-site mapping, ensuring the accuracy and completeness of the data. Based on the distribution location of each device within the target area, the ammonia gas concentration is identified within the spatial distribution of ammonia gas concentration, yielding the real-time ammonia gas concentration corresponding to each device. This process can be achieved using Geographic Information System (GIS) technology or spatial analysis algorithms, matching device locations with ammonia gas concentration distribution maps to obtain the real-time ammonia gas concentration at each device's location. These real-time ammonia gas concentration data are then imported into the corrosion resistance prediction model.

[0085] Finally, based on real-time imported ammonia gas concentration data and equipment operating data, the corrosion resistance prediction model outputs a predicted corrosion resistance distribution for equipment in the target area. This distribution visually displays the corrosion resistance of different equipment at different locations within the target area, providing a scientific basis for equipment maintenance, management, and decision-making. For example, by predicting the distribution, equipment or areas with poor corrosion resistance can be identified in advance, allowing for timely maintenance or adjustments to reduce corrosion risks and extend equipment lifespan.

[0086] Furthermore, step P54 in this embodiment of the application also includes:

[0087] P54-1: Construct the first spatial coordinate system of the target area; P54-2: Perform coordinate transformation on the spatial distribution of ammonia gas concentration according to the first spatial coordinate system, and output the spatial distribution of ammonia gas concentration in the first spatial coordinate system; P54-3: Perform coordinate transformation on the distribution position of each device according to the first spatial coordinate system, and output the distribution position of the device in the first spatial coordinate system; P54-4: Identify the spatial distribution of ammonia gas concentration and the distribution position of the device in the first spatial coordinate system, and obtain the real-time ammonia gas concentration corresponding to each device.

[0088] In one possible embodiment of this application, in order to more accurately identify the real-time ammonia gas concentration corresponding to each device, a detailed spatial coordinate transformation and identification method may be provided.

[0089] First, a primary spatial coordinate system for the target area is constructed. This coordinate system provides the foundation for subsequent spatial data processing. By defining the origin and axes within the target area, a unified reference framework can be provided for the location of equipment and the distribution of gas concentrations throughout the region. Constructing this coordinate system is a crucial step in ensuring subsequent spatial coordinate transformations and data matching.

[0090] Next, based on the first spatial coordinate system, a coordinate transformation is needed to analyze the spatial distribution of ammonia gas concentration. Since the spatial distribution of ammonia gas concentration can be affected by various factors such as airflow, obstacles, and gas sources, this transformation process aims to align the simulated ammonia gas concentration distribution with the spatial coordinate system of the target area. After the coordinate transformation, the ammonia gas concentration data will be referenced to the first spatial coordinate system, ensuring an accurate match between the concentration data and the actual location of the target area.

[0091] Next, the distribution locations of each device are transformed according to the first spatial coordinate system, and the device distribution locations in the first spatial coordinate system are output. This process also ensures that the device distribution data is represented in a unified spatial coordinate system, which facilitates matching with the ammonia gas concentration data, so that the location of each device can correspond to its ammonia gas concentration environment. Through this coordinate transformation, the spatial location of each device and its corresponding gas concentration environment can be accurately identified.

[0092] Finally, the spatial distribution of ammonia gas concentration and the location of equipment in the first spatial coordinate system are identified to obtain the real-time ammonia gas concentration for each piece of equipment. This process can be achieved through spatial analysis algorithms or Geographic Information System (GIS) technology, accurately matching the equipment location with the ammonia gas concentration distribution map to obtain the real-time ammonia gas concentration at each equipment location. Subsequently, this real-time ammonia gas concentration data is imported into the corrosion resistance prediction model.

[0093] These steps further refine the correlation between equipment location and gas concentration, ensuring that real-time data accurately reflects the corrosion status of equipment in an ammonia salt gas environment, and providing a scientific basis for equipment operation safety.

[0094] Furthermore, step P54-4 of the embodiments of this application also includes:

[0095] P54-41: Identify the surrounding sensing space based on the distribution location of the devices according to the preset coordinate step size; P54-42: Extract the average concentration of ammonia gas corresponding to the surrounding sensing space as the real-time ammonia gas concentration output of each device according to the spatial distribution of ammonia gas concentration in the first spatial coordinate system.

[0096] Specifically, in order to more accurately identify the real-time ammonia gas concentration corresponding to each device, more detailed spatial sensing and concentration extraction methods can be provided to ensure that a more accurate real-time ammonia gas concentration value is provided for each device.

[0097] First, a sensing space surrounding the equipment's location is identified based on a preset coordinate step size. The preset coordinate step size refers to the spatial range divided at certain intervals (steps) with the equipment as the center in a spatial coordinate system. This sensing space can be flexibly adjusted according to the characteristics of the equipment, the properties of gas diffusion, or the needs of the experiment. In this way, an appropriate area can be constructed around the equipment's location, and the ammonia gas concentration within this area will be considered as the reference concentration for the equipment's location. This method ensures more accurate calculation of the ammonia gas concentration in the environment surrounding each device.

[0098] Next, based on the spatial distribution of ammonia gas concentration in the first spatial coordinate system, the ammonia gas concentration data in the surrounding sensing space related to the equipment's location is extracted. Specifically, the system compares the sensing space defined by the coordinate step size with the spatial distribution of ammonia gas concentration to extract the average ammonia gas concentration in the surrounding sensing space. This average concentration data will be output as the real-time ammonia gas concentration at the equipment's location. This method allows for more accurate calculation of the gas concentration around the equipment, rather than relying solely on concentration data from a fixed point, effectively avoiding concentration fluctuations caused by local airflow or other environmental factors, and providing more stable real-time data. This improvement ensures that the gas environment of each device can be comprehensively assessed under complex environmental conditions, providing more reliable input data for corrosion resistance prediction and thus improving the accuracy of model predictions.

[0099] Furthermore, the corrosion resistance prediction model is connected to the monitoring and management terminal of the target area for real-time data import. In this embodiment, step P50 further includes:

[0100] P55: Based on the monitoring and management terminal of the target area, obtain the equipment type and real-time operating status of each device; P56: Based on the monitoring and management terminal of the target area, obtain the real-time ammonia gas concentration of each device; P57: Input the equipment type, real-time operating status, and real-time ammonia gas concentration as input triples into the corrosion resistance prediction model for prediction, and obtain the predicted distribution of equipment corrosion resistance in the target area.

[0101] Optionally, to enable real-time data import and prediction functions for the corrosion resistance performance prediction model, more detailed data acquisition and model input methods can be provided.

[0102] First, based on the monitoring and management terminal of the target area, the equipment type and real-time operating status of each device are obtained. Equipment type information includes the device model, surface treatment, and material, which directly affect the device's corrosion characteristics in specific environments. Real-time operating status refers to the current working condition of the device, such as parameters like temperature, humidity, and electrical load. This operating status data helps to accurately assess the corrosion risks that the equipment may encounter during actual use. Therefore, the monitoring and management terminal needs to collect and update this data in real time to ensure that the predictive model can make accurate predictions based on the latest equipment status.

[0103] Next, the monitoring and management terminal also needs to obtain the real-time ammonia gas concentration for each device. This data is obtained by matching the spatial distribution of ammonia gas concentration constructed in the previous steps with the device distribution location. By monitoring the ammonia gas concentration in real time, it can be ensured that the data input to the model reflects the actual environment in which the device is currently located, thereby improving the accuracy of corrosion prediction. For example, the real-time ammonia gas concentration test data is shown in Table 4:

[0104] Table 4 Real-time ammonia gas concentration test data

[0105] ;

[0106] Finally, the equipment type, real-time operating conditions, and real-time ammonia gas concentration are used as input triplets and imported into the corrosion resistance prediction model for prediction. This input data includes the characteristics of the equipment, its operating environment, and the actual concentration of corrosive gases, providing multi-dimensional real-time data support for the model. By inputting this data into the model, the prediction model can output the predicted corrosion resistance distribution of each device within the target area based on the patterns learned during training. For example, ... Figure 3 The scatter plot shown compares the corrosion rate predicted by the corrosion resistance prediction model with the actual measured values. Each point in the plot represents a sample. The closer the point is to the dashed line (y=x), the more accurate the prediction. The position of the point reflects the magnitude and direction of the prediction error (residual) (above the dashed line indicates overestimation, below the dashed line indicates underestimation). R and MAE in the plot quantify the overall performance of the model. And as shown... Figure 4The residual plot showing the distribution of the prediction error for the corrosion rate illustrates the relationship between the residuals (prediction error) and the actual corrosion rate. If the scatter points are randomly and uniformly distributed around the dashed line (y=0), it indicates that the model has no systematic prediction bias. The histogram shows the shape of the residual distribution. An ideal model should have residuals that approximately follow a normal distribution with a mean of 0. The solid line represents the average residual, which should be very close to 0. This distribution visually demonstrates the corrosion resistance of different equipment at different locations within the target area, providing a scientific basis for equipment maintenance, management, and decision-making. For example, by predicting the distribution, equipment or areas with poor corrosion resistance can be identified in advance, allowing for timely maintenance or adjustments to reduce corrosion risk.

[0107] This process not only improves the accuracy of corrosion prediction, but also provides a scientific basis for equipment management and maintenance, helping to optimize equipment operation, extend service life, and reduce the risk of failure due to corrosion.

[0108] In summary, the embodiments of this application have at least the following technical effects:

[0109] This application, by combining equipment type, operating conditions, and ammonia gas environment, can more accurately simulate the corrosion performance of equipment in actual applications, thereby improving the accuracy of corrosion resistance testing. By importing real-time data into the corrosion resistance prediction model, it enables real-time corrosion risk prediction of equipment under different operating conditions and environments, helping to take timely protective measures and avoid equipment failure. By simulating the behavior of equipment in complex ammonia gas environments and variable operating conditions, it overcomes the limitations of traditional static testing methods and can reflect the performance of equipment in real environments. Ultimately, through accurate corrosion risk assessment, it improves the long-term reliability and safety of equipment, extends equipment service life, and reduces failures and maintenance costs caused by corrosion.

[0110] This achieves the technical effect of improving the accuracy of corrosion resistance testing by constructing a corrosion resistance prediction model to enable dynamic simulation and real-time corrosion risk prediction of equipment in complex environments.

[0111] Example 2, based on the same inventive concept as the product corrosion resistance test method under ammonia salt gas environment in the foregoing examples, such as... Figure 5 As shown, this application provides a device for testing the corrosion resistance of products in an ammonia salt gas environment. The device and method embodiments in this application are based on the same inventive concept. The device includes:

[0112] Database construction module 11 is used to construct a device type tag library and an operating condition database.

[0113] Test sample group construction module 12 is used to construct equipment-operating condition test sample groups based on the equipment type tag library and the operating condition database.

[0114] The response test module 13 is used to set up an ammonia gas environment sample, and to perform response tests under the ammonia gas environment sample according to the equipment-operating condition test sample group, and output a corrosion response sample group. The corrosion response sample group includes corrosion response data of each device under different operating conditions, and the corrosion response data includes the corrosion increase rate.

[0115] The sample triplet construction module 14 is used to construct a device-operating condition-corrosion sample triplet using the device-operating condition test sample group and the corrosion response sample group.

[0116] The corrosion resistance prediction module 15 is used to obtain a corrosion resistance performance prediction model by training the equipment-operating condition-corrosion sample triplet, and to connect the corrosion resistance prediction model to the monitoring and management terminal of the target area for real-time data import, and output the predicted distribution of equipment corrosion resistance in the target area.

[0117] Furthermore, the database construction module 11 is also used to perform the following steps:

[0118] A monitoring and management terminal is configured for the target area. The monitoring and management terminal includes an ammonia gas environment monitoring and management terminal, which is connected to an ammonia gas environment simulation device. The ammonia gas environment simulation device includes an ammonia flow controller and an ammonium chloride flow controller. The mixed gas in the reaction chamber is dynamically adjusted by the ammonia flow controller and the ammonium chloride flow controller to obtain an ammonia gas environment sample.

[0119] Furthermore, the database construction module 11 is also used to perform the following steps:

[0120] The surface attribute information of each device within the target area is obtained, including surface structure information, surface treatment information, and surface material information; corrosion sensitivity factors of each device within the target area are extracted to obtain structured labels for each device; the structured labels of each device are vectorized to output structured label vectors for each device; similarity calculation is performed on the structured label vectors of each device, and each device is classified according to the first similarity calculation result to obtain a device type label library.

[0121] Furthermore, the database construction module 11 is also used to perform the following steps:

[0122] Obtain historical operating condition datasets for each device within the target area. These datasets include electrical, thermal, and mechanical parameters of each device. Vectorize the electrical, thermal, and mechanical parameters of each device to obtain operating condition label vectors for each device. Perform similarity calculations on the operating condition label vectors of each device and classify the operating conditions of each device according to the output second similarity calculation results to obtain an operating condition database.

[0123] Furthermore, the response testing module 13 is also used to perform the following steps:

[0124] Under the ammonium salt gas environment sample, response tests were conducted according to the equipment-operating condition test sample group, and response change data of each device were recorded. The response change data included surface defect changes and electrochemical response changes. Corrosion rates were calculated according to the surface defect changes and electrochemical response changes, and surface corrosion rate curves and electrochemical corrosion rate curves were output. The derivatives of the surface corrosion rate curves and electrochemical corrosion rate curves were calculated, and the corrosion increase rate was identified as the output of the corrosion response sample group.

[0125] Furthermore, the corrosion resistance prediction module 15 is also used to perform the following steps:

[0126] The monitoring and management terminal of the target area acquires the distribution location of the ammonia gas environment simulation device; performs gas diffusion simulation based on the distribution location of the ammonia gas environment simulation device, and outputs the spatial distribution of ammonia gas concentration in the target area; the monitoring and management terminal of the target area acquires the distribution location of each device in the target area; identifies each device in the spatial distribution of ammonia gas concentration based on the distribution location of each device in the target area, obtains the real-time ammonia gas concentration corresponding to each device, and imports the real-time ammonia gas concentration corresponding to each device into the corrosion resistance prediction model.

[0127] Furthermore, the corrosion resistance prediction module 15 is also used to perform the following steps:

[0128] Construct a first spatial coordinate system for the target area; perform coordinate transformation on the spatial distribution of ammonia gas concentration according to the first spatial coordinate system, and output the spatial distribution of ammonia gas concentration in the first spatial coordinate system; perform coordinate transformation on the distribution position of each device according to the first spatial coordinate system, and output the device distribution position in the first spatial coordinate system; identify the spatial distribution of ammonia gas concentration and the device distribution position in the first spatial coordinate system to obtain the real-time ammonia gas concentration corresponding to each device.

[0129] Furthermore, the corrosion resistance prediction module 15 is also used to perform the following steps:

[0130] Identify the surrounding sensing space based on the distribution location of the devices according to a preset coordinate step size; extract the average concentration of ammonia gas corresponding to the surrounding sensing space as the real-time ammonia gas concentration output of each device according to the spatial distribution of ammonia gas concentration in the first spatial coordinate system.

[0131] Furthermore, the corrosion resistance prediction module 15 is also used to perform the following steps:

[0132] Based on the monitoring and management terminal of the target area, the equipment type and real-time operating status of each device are obtained; based on the monitoring and management terminal of the target area, the real-time ammonia gas concentration of each device is obtained; the equipment type, real-time operating status, and real-time ammonia gas concentration are used as input triples and imported into the corrosion resistance prediction model for prediction, thereby obtaining the predicted distribution of equipment corrosion resistance in the target area.

[0133] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0134] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0135] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for testing the corrosion resistance of products in an ammonia salt gas environment, characterized in that, The method includes: Build an equipment type label library and an operating condition database; Based on the equipment type tag library and the operating condition database, construct equipment-operating condition test sample groups; Set up an ammonia salt gas environment sample, and conduct response tests under the ammonia salt gas environment sample according to the equipment-operating condition test sample group to output a corrosion response sample group. The corrosion response sample group includes corrosion response data of each device under different operating conditions, and the corrosion response data includes the corrosion increase rate. A ternary set of equipment-operating condition-corrosion samples is constructed using the equipment-operating condition test sample set and the corrosion response sample set. By training the equipment-operating condition-corrosion sample triplet, a corrosion resistance prediction model is obtained. The corrosion resistance prediction model is then connected to the monitoring and management terminal of the target area for real-time data import, and the predicted distribution of equipment corrosion resistance in the target area is output. The monitoring and management terminal also includes a device operation monitoring and management terminal, which is connected to the devices in the target area. The method for constructing the device type tag library includes: Obtain surface attribute information of each device within the target area, including surface structure information, surface treatment information, and surface material information; The corrosion sensitivity factors of each device within the target area are extracted to obtain the structured labels of each device; The structured tags of each device are vectorized, and the structured tag vectors of each device are output. By calculating the similarity of the structured tag vectors of each device, and classifying each device according to the first similarity calculation result, a device type tag library is obtained. Methods for building a runtime condition database include: Obtain historical operating condition datasets for each device within the target area. The historical operating condition datasets include electrical parameters, thermal parameters, and mechanical parameters of each device. By vectorizing the electrical, thermal, and mechanical parameters of each device, the operating condition label vector of each device is obtained. By calculating the similarity of the operating condition label vectors of each device, and classifying the operating conditions of each device according to the output of the second similarity calculation result, an operating condition database is obtained. The structured label vector of the device is combined with the corresponding operating condition label vector to form the device-operating condition test sample group; Under the ammonium salt gas environment sample, response tests were conducted according to the equipment-operating condition test sample group, and response change data of each device were recorded. The response change data included changes in surface defects and changes in electrochemical response. Corrosion rates are calculated based on the changes in surface defects and electrochemical response, and surface corrosion rate curves and electrochemical corrosion rate curves are output. Differentiate the surface corrosion rate curve and the electrochemical corrosion rate curve, and identify the corrosion increase rate as the output of the corrosion response sample group.

2. The method as described in claim 1, characterized in that, The monitoring and management terminal includes an ammonia gas environment monitoring and management terminal, which is connected to an ammonia gas environment simulation device. The ammonia gas environment simulation device includes an ammonia flow controller and an ammonium chloride flow controller. The mixed gas in the reaction chamber is dynamically adjusted by the ammonia flow controller and the ammonium chloride flow controller to obtain an ammonia gas environment sample.

3. The method as described in claim 2, characterized in that, The corrosion resistance prediction model is connected to the monitoring and management terminal of the target area for real-time data import, and the method includes: The monitoring and management terminal in the target area obtains the distribution location of the ammonia salt gas environment simulation device; Based on the distribution location of the ammonia salt gas environment simulation device, gas diffusion simulation is performed, and the spatial distribution of ammonia salt gas concentration within the target area is output. The monitoring and management terminal of the target area obtains the distribution location of each device within the target area; Based on the distribution location of each device within the target area, the spatial distribution of ammonia salt gas concentration is identified to obtain the real-time ammonia salt gas concentration corresponding to each device, and the real-time ammonia salt gas concentration corresponding to each device is imported into the corrosion resistance prediction model.

4. The method as described in claim 3, characterized in that, Based on the distribution location of each device within the target area, the spatial distribution of ammonia gas concentration is identified to obtain the real-time ammonia gas concentration corresponding to each device. The method includes: Construct a first spatial coordinate system for the target region; The spatial distribution of ammonia salt gas concentration is transformed according to the first spatial coordinate system, and the spatial distribution of ammonia salt gas concentration in the first spatial coordinate system is output. The distribution positions of each device are transformed according to the first spatial coordinate system, and the distribution positions of the devices in the first spatial coordinate system are output. The spatial distribution of ammonia gas concentration and the location of equipment in the first spatial coordinate system are identified to obtain the real-time ammonia gas concentration corresponding to each equipment.

5. The method as described in claim 4, characterized in that, The method for identifying the spatial distribution of ammonia salt gas concentration and the location of equipment in the first spatial coordinate system includes: Identify the surrounding sensing space based on the distribution location of the device according to a preset coordinate step size; Based on the spatial distribution of ammonia gas concentration in the first spatial coordinate system, the average concentration of ammonia gas corresponding to the surrounding sensing space is extracted as the real-time ammonia gas concentration output of each device.

6. The method as described in claim 1, characterized in that, The corrosion resistance prediction model is connected to the monitoring and management terminal of the target area for real-time data import, and the method includes: Based on the monitoring and management terminal of the target area, obtain the equipment type and real-time operating status of each device; According to the monitoring and management terminal of the target area, the real-time ammonia gas concentration of each device is obtained; The equipment type, real-time operating conditions, and real-time ammonia gas concentration are used as input triplets and imported into the corrosion resistance prediction model for prediction, thereby obtaining the predicted distribution of equipment corrosion resistance in the target area.

7. A device for testing the corrosion resistance of products in an ammonia salt gas environment, characterized in that, The apparatus is used to perform the method according to any one of claims 1 to 6, the apparatus comprising: A database construction module, which is used to construct a device type tag library and an operating condition database; A test sample group construction module is used to construct equipment-operating condition test sample groups based on the equipment type tag library and the operating condition database. The response testing module is used to set up an ammonia gas environment sample, and perform response tests under the ammonia gas environment sample according to the equipment-operating condition test sample group, and output a corrosion response sample group, wherein the corrosion response sample group includes corrosion response data of each device under different operating conditions, and the corrosion response data includes the corrosion increase rate. A sample triplet construction module is used to construct a device-operating condition-corrosion sample triplet using the device-operating condition test sample group and the corrosion response sample group. The corrosion resistance prediction module is used to obtain a corrosion resistance performance prediction model by training the equipment-operating condition-corrosion sample triplet, and to connect the corrosion resistance prediction model to the monitoring and management terminal of the target area for real-time data import, and output the predicted distribution of equipment corrosion resistance in the target area.

Images