Application for improving wear resistance of connector based on electron deep protective agent

Abstract

The invention discloses an application for improving the wear resistance of a connector based on an electronic deep protective agent, and relates to the technical field of electric power. Data collected by a sensor in real time and a simulation result of a digital twinborn model are combined, a complex environment is dynamically adapted, the wear progress is predicted and controlled, and the wear resistance of the connector is improved. The connector can keep good performance under different working conditions; the abrasion trend is predicted through a deep learning model, a potential high-abrasion area is recognized in advance, the thickness and the lubricating frequency of a protective layer are adjusted through an electronic deep protective agent, the thickness of the protective layer and the abrasion state are made to change synchronously, the abrasion speed is obviously decreased, the maintenance frequency is reduced, and the maintenance time is shortened; therefore, the service life of the key component is estimated, maintenance personnel can reasonably arrange the maintenance period according to the actual state of the equipment, premature or late maintenance is avoided, the maintenance time is optimized, cost waste caused by excessive maintenance is avoided, and the equipment management efficiency is improved.

Description

Technical Field

[0001] The invention relates to the field of electric power technology, in particular to an application of improving the wear resistance of a connector based on an electronic depth protective agent. Background Art

[0002] Connectors are key basic components in mechanical and electronic systems, mainly used to transmit power and signals, and are widely used in industrial automation, aerospace, energy, medical equipment, transportation and other fields. In these environments, connectors are often faced with high-frequency vibrations, complex loads, and extreme temperature and humidity conditions, so their wear resistance and reliability are required to be extremely high. The traditional way to improve the wear resistance of connectors mainly relies on material selection or surface coating in specific environments. However, under complex working conditions, the wear rate is difficult to predict, the maintenance cost is high, and the life is short.

[0003] In order to solve the above problems, traditional solutions usually make improvements in materials and structures. For example, high-hardness or self-lubricating materials are used to improve wear resistance, or corrosion-resistant coatings are used to delay the impact of environmental factors on materials. In addition, some connector designs also use composite structures or distributed loads to reduce contact stress and reduce wear risks. These methods enhance the wear resistance of connectors at the physical level, enabling them to effectively resist mechanical friction and environmental erosion for a certain period of time. However, although these solutions perform well under experimental conditions, in actual working conditions, the wear rate and type are often difficult to predict. Traditional material and structural improvements make it difficult to dynamically feedback and adjust the wear process, resulting in a lack of adaptability in wear-resistant designs.

[0004] In addition, this type of traditional solution lacks real-time wear monitoring and life prediction methods, making it difficult to detect potential wear problems in a timely manner. Once wear occurs, it is often irreversible, which may lead to increased overall equipment loss and even cause failures. This not only increases maintenance costs, but also fails to optimize maintenance cycles, increasing the risk of sudden system failures. Therefore, there is an urgent need for an application solution based on electronic deep protective agents to improve the wear resistance of connectors to solve such problems. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides an application based on electronic depth protective agent to improve the wear resistance of connectors to solve the problems that the current wear resistance method lacks real-time data feedback during use, it is difficult to accurately judge the wear state and remaining life of the connector, lacks intelligent monitoring and control means, and it is difficult to meet the durability requirements of the connector under complex working conditions.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] The present invention provides an application of improving the wear resistance of connectors based on an electronic depth protective agent, which comprises:

[0009] Step S1, establish a digital twin model,

[0010] Based on the geometric structure and material properties of the connector, a digital twin model is built to simulate the stress, wear and temperature changes of the connector in different environments;

[0011] Step S2, wear prediction and life estimation based on deep learning,

[0012] Based on the historical and real-time data obtained in step S1 and the simulation results, a deep learning model is constructed and trained to identify the association between the wear rate and the environmental parameters and form a wear trend graph;

[0013] Step S3, adaptive optimization and dynamic application of electronic depth protectant,

[0014] Combined with the wear prediction data of step S2, an optimization algorithm is used to adjust the pressure and load distribution of the connector contact part to reduce stress in high wear areas;

[0015] Introduce electronic deep protection agent in high wear areas to form an intelligent lubrication protection layer: increase lubrication frequency in high wear or high temperature areas according to wear severity and real-time temperature;

[0016] Electronic deep protection agent forms a thin dynamic protective layer on the contact surface, isolating direct friction, reducing wear rate and increasing wear life.

[0017] Furthermore, in step S1, real-time data is obtained: micro sensors are installed at key parts of the connector, including the contact surface, contact pins and locking parts, to collect temperature, stress and vibration data in real time, and temperature, humidity and dust environment sensors are arranged to obtain environmental condition data of the connector;

[0018] Real-time data includes: temperature, stress and vibration data and environmental condition data; the real-time data is input into the digital twin model, the wear and stress distribution of the connector in the actual use environment is dynamically simulated, and the simulation results are output.

[0019] Furthermore, in step S1, the steps of constructing the digital twin model include:

[0020] The digital twin model is initialized based on the geometric structure and material properties of the connector, and the force and stress distribution of the connector are modeled. The Archard wear model is used to predict wear based on contact pressure, sliding distance, and material wear coefficient: Where W represents the wear amount, k is the wear coefficient, F is the normal force on the contact surface, d is the sliding distance, and H is the hardness of the material;

[0021] A thermal-mechanical coupling model is constructed to model the temperature field for friction heating under high load. Assuming the temperature field is T(x, y, z, t), then: Where ρ is the material density, c is the specific heat capacity of the material, T(x,y,z,t) is the temperature field, which varies with position (x,y,z) and time t, and k th is the thermal conductivity, q is the frictional heating term, q = τ·v, where v is the sliding velocity and τ is the shear stress;

[0022] Acquire real-time data from sensors and input it into the digital twin model for dynamic simulation updates.

[0023] Further, in step S2, the deep learning model predicts the wear development trend and the life limit of key parts based on the input data, and provides early warning for the impending wear risk; the input data is historical and real-time data and simulation results;

[0024] At the same time, the deep learning model identifies potential high wear areas.

[0025] Furthermore, in step S2, the wear prediction and life estimation method based on deep learning is:

[0026] Assume that the historical wear data is W hist , the real-time temperature is T real , real-time stress is σ real , the real-time vibration frequency is f vib , the real-time contact pressure is p real , the simulation output data of the digital twin model is W sim Based on the above data, preprocessing and feature extraction are performed, and the features include: wear rate R wear and environmental characteristics, Where ΔW is the wear amount in a certain time interval, Δt is the time interval, and the combination of environmental features is defined as, which serves as the input of the deep learning model;

[0027] A neural network model based on long short-term memory (LSTM) is used to capture the time series characteristics of wear. The input is the time series feature X env and historical wear rate R wear (t), the output is the predicted future wear rate The loss function is defined as the mean square error between the predicted wear rate and the actual rate: Where L represents the prediction error, N represents the total number of time steps, and t i represents the time step, i represents the time step index, and Δt is the interval between adjacent time steps.

[0028] Furthermore, in step S2, the method of performing wear prediction and life estimation also includes:

[0029] Based on predicted future wear rates Calculate the cumulative wear of key connector parts:

[0030] Where Δt is the interval between adjacent time steps, W cumulative (t) and W cumulative (t+Δt) are the cumulative wear amounts of two adjacent time steps;

[0031] Assume the durability limit is W limit , using the current wear and durability limit to estimate the remaining life of key parts:

[0032] Among them, t life Indicates the remaining time until the wear endurance reaches the limit, i.e. the remaining life;

[0033] Based on real-time data and simulation results, the local wear distribution function W is applied local (x,y) Identify high wear areas: Where R wear (x, y, τ) is the wear rate at position (x, y) at time τ. local Areas of high (x,y) values ​​identify potential high wear locations.

[0034] Furthermore, in step S3, the digital twin model is linked with the deep learning model to adjust the electronic depth protectant and lubrication parameters in real time according to the wear status fed back by the sensor, so that the protective layer is synchronized with the wear changes.

[0035] Furthermore, in step S3, the pressure distribution of the connector contact part is adjusted in combination with the wear prediction data of step S2, specifically:

[0036] The objective function J of the total stress is defined in the high wear area. The function describes the deviation between the current stress distribution and the target stress distribution. The optimization purpose is to adjust the pressure distribution p(x, y) so that the actual stress is close to the target value. The objective function J is defined as: J = ∫ Ω (σ(x,y)-σ goal ) 2 dA, where Ω is the high wear area, dA represents any small area unit in the integral area Ω, σ(x,y) represents the actual stress at the position (x,y), calculated based on the current pressure p(x,y), and σ goal is the desired target stress value, which is used to optimize the stress concentration area, reduce wear, and minimize J to reduce stress concentration in the wear area;

[0037] Actual stress σ(x,y) = α·p(x,y), where α is the proportionality coefficient and p(x,y) is the contact pressure at position (x,y). Adjusting p(x,y) controls the distribution of σ(x,y) to make it close to the target stress σ goal ;

[0038] Add constraints:

[0039] Total load constraint: The total load P in the contact area total Keep constant, that is, ∫ Ω p(x,y)dA=P total ;

[0040] Pressure non-negative constraint: The contact pressure p(x,y) is non-negative, that is, p(x,y)≥0;

[0041] The Lagrange multiplier method is used to combine the objective function with the constraint conditions, and the contact pressure p(x,y) is iteratively adjusted using the optimization algorithm to define the Lagrangian function:

[0042] Where λ is the Lagrange multiplier, and we need to solve and Get the optimized p(x,y) distribution;

[0043] Based on the pressure distribution of the optimization results, the contact pressure in high wear areas is updated to relieve stress concentration in these areas in real time.

[0044] Furthermore, in step S3, the protective agent and lubrication parameters are adjusted in the following manner:

[0045] Based on the wear amount W(t) and wear rate R(t) fed back by the sensor, the optimal thickness h(t) of the electronic depth protector is calculated in real time, h(t) = β·R(t), where h(t) is the thickness of the protector at time t. is the wear rate, β is the adjustment coefficient;

[0046] Future wear rate prediction based on deep learning model Dynamic adjustment of lubrication frequency:

[0047] Where, f(t) is the lubrication frequency, f min is the minimum lubrication frequency, γ is the adjustment parameter, is the predicted wear rate at time t+Δt. When the predicted wear rate increases, the lubrication frequency is automatically increased, thereby strengthening protection in areas with increased wear.

[0048] Furthermore, in step S3, the method of adjusting the protective agent and lubrication parameters also includes:

[0049] The wear state is fed back into the digital twin model to calculate the protective agent thickness distribution h(x, y, t) and lubrication frequency f(x, y, t) at each position, and the optimization objective function J is used to dynamically balance the amount of protective agent used and the coverage effect:

[0050] Where J is the objective function, which represents the deviation between the wear rate and the protective agent coverage effect, Ω is the contact area, α is the proportionality coefficient, which is related to the protective agent effect, h(x,y,t) is the protective agent thickness at time t at position (x,y), and f(x,y,t) is the lubrication frequency at this position;

[0051] The linkage control strategy is: sensor data input, collecting real-time wear amount and wear rate; model calculation: calculating the protective agent thickness and lubrication frequency according to the current wear state; optimization adjustment: feedback h(x, y, t) and f(x, y, t), the protective layer dynamically adapts to the current wear condition.

[0052] The beneficial effects of the present invention are:

[0053] The present invention realizes real-time monitoring and simulation of wear rate and environment through digital twin models and deep learning algorithms, combines the data collected by sensors in real time with the simulation results of the digital twin models, dynamically adapts to complex environments, predicts and controls the progression of wear, and enables the connector to maintain good performance under different working conditions; predicts wear trends through deep learning models, identifies potential high-wear areas in advance, and adjusts the thickness of the protective layer and the frequency of lubrication through electronic depth protectants, so that the thickness of the protective layer changes synchronously with the wear state, significantly slows down the wear rate, reduces the number and time of maintenance, and reduces maintenance costs.

[0054] The present invention can dynamically adjust the lubrication frequency and the thickness of the protective agent in real time according to the wear prediction data, so that the use of the protective agent is more intelligent and accurate, the waste of materials is reduced, and the duration of the protective effect is prolonged.

[0055] The present invention can predict the wear trend and thus estimate the life of key components. Maintenance personnel can reasonably arrange maintenance cycles according to the actual status of the equipment, avoid premature or late maintenance, optimize maintenance time, avoid cost waste caused by excessive maintenance, and improve the efficiency of equipment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use 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 ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0057] Figure 1 The present invention is a schematic flow chart of an application method for improving the wear resistance of connectors based on an electronic depth protectant. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0061] Example 1, reference Figure 1 This embodiment provides an application of improving the wear resistance of connectors based on an electronic depth protector, comprising the following steps:

[0062] Step S1, establish a digital twin model,

[0063] Based on the geometric structure and material properties of the connector, a digital twin model is built to simulate the stress, wear and temperature changes of the connector in different environments;

[0064] Acquiring real-time data in step S1: installing micro sensors at key parts of the connector, including the contact surface, contact pins and locking parts, to collect temperature, stress and vibration data in real time, and arranging temperature, humidity and dust environment sensors to obtain environmental condition data of the connector;

[0065] Real-time data includes: temperature, stress and vibration data and environmental condition data; input the real-time data into the digital twin model, dynamically simulate the wear and stress distribution of the connector in the actual use environment, and output the simulation results;

[0066] In step S1, the steps of building a digital twin model include:

[0067] The digital twin model is initialized based on the geometric structure and material properties of the connector, and the force and stress distribution of the connector are modeled. The Archard wear model is used to predict wear based on contact pressure, sliding distance, and material wear coefficient: Where W represents the wear amount, k is the wear coefficient, F is the normal force on the contact surface, d is the sliding distance, and H is the hardness of the material;

[0068] A thermal-mechanical coupling model is constructed to model the temperature field for friction heating under high load. Assuming the temperature field is T(x, y, z, t), then: Where ρ is the material density, c is the specific heat capacity of the material, T(x,y,z,t) is the temperature field, which varies with position (x,y,z) and time t, and k th is the thermal conductivity, q is the frictional heating term, q = τ·v, where v is the sliding velocity and τ is the shear stress;

[0069] Obtain real-time data from sensors and input the real-time data into the digital twin model for dynamic simulation updates;

[0070] Specifically, based on the geometry and material properties of the connector, a digital twin model is established to simulate the real-world stress, temperature and wear distribution, provide real-time simulation data, and combine the data fed back by the actual sensors to dynamically reflect the wear status of the connector under different working conditions. The wear trend is predicted through a deep learning model, the correlation between the wear rate and environmental parameters is identified, the wear trend is analyzed to estimate the life of key parts, timely warnings are provided for high-wear areas, and protective measures are taken in advance before high-wear areas occur.

[0071] Step S2, wear prediction and life estimation based on deep learning,

[0072] Based on the historical and real-time data obtained in step S1 and the simulation results, a deep learning model is constructed and trained to identify the association between the wear rate and the environmental parameters and form a wear trend graph;

[0073] In step S2, the deep learning model predicts the wear development trend and the life limit of key parts based on the input data, and provides early warning for the impending wear risk; the input data is historical and real-time data and simulation results;

[0074] At the same time, the deep learning model identifies potential high-wear areas;

[0075] In step S2, the wear prediction and life estimation method based on deep learning is:

[0076] Assume that the historical wear data is W hist , the real-time temperature is T real , real-time stress is σ real , the real-time vibration frequency is f vib , the real-time contact pressure is p real , the simulation output data of the digital twin model is W simBased on the above data, preprocessing and feature extraction are performed, and the features include: wear rate R wear and environmental characteristics, Where ΔW is the wear amount in a certain time interval, Δt is the time interval, and the combination of environmental features is defined as, which serves as the input of the deep learning model;

[0077] A neural network model based on long short-term memory (LSTM) is used to capture the time series characteristics of wear. The input is the time series feature X env and historical wear rate R wear (t), the output is the predicted future wear rate The loss function is defined as the mean square error between the predicted wear rate and the actual rate: Where L represents the prediction error, N represents the total number of time steps, and t i represents the time step, i represents the time step index, and Δt is the interval between adjacent time steps;

[0078] In step S2, the method of performing wear prediction and life estimation also includes:

[0079] Based on predicted future wear rates Calculate the cumulative wear of key connector parts:

[0080] Where Δt is the interval between adjacent time steps, W cumulative (t) and W cumulative (t+Δt) are the cumulative wear amounts of two adjacent time steps;

[0081] Assume the endurance limit is w limit , using the current wear and durability limit to estimate the remaining life of key parts:

[0082] Among them, t life Indicates the remaining time until the wear endurance reaches the limit, i.e. the remaining life;

[0083] Based on real-time data and simulation results, the local wear distribution function w is applied local (x,y) Identify high wear areas: Where R wear (x, y, τ) is the wear rate at position (x, y) at time τ. local Areas with high values ​​of (x,y) identify potential high wear locations;

[0084] Specifically, with the support of predictive data, an optimization algorithm is used to intelligently adjust the contact pressure and load distribution to accurately reduce stress concentration in high wear areas.

[0085] Step S3, adaptive optimization and dynamic application of electronic depth protectant,

[0086] Combined with the wear prediction data of step S2, an optimization algorithm is used to adjust the pressure and load distribution of the connector contact part to reduce stress in high wear areas;

[0087] Introduce electronic deep protection agent in high wear areas to form an intelligent lubrication protection layer: increase lubrication frequency in high wear or high temperature areas according to wear severity and real-time temperature;

[0088] Electronic deep protective agent forms a thin dynamic protective layer on the contact surface, isolating direct friction, reducing wear rate, and increasing wear life;

[0089] In step S3, the digital twin model is linked with the deep learning model to adjust the electronic depth protection agent and lubrication parameters in real time according to the wear status fed back by the sensor, so that the protection layer is synchronized with the wear change;

[0090] In step S3, the pressure distribution of the connector contact part is adjusted in combination with the wear prediction data of step S2, specifically:

[0091] The objective function I of the total stress is defined in the high wear area. The function describes the deviation between the current stress distribution and the target stress distribution. The optimization purpose is to adjust the pressure distribution p(x, y) so that the actual stress is close to the target value. The objective function J is defined as: J = ∫ Ω (σ(x,y)-σ goal ) 2 dA, where Ω is the high wear area, dA represents any small area unit in the integral area Ω, σ(x,y) represents the actual stress at the position (x,y), calculated based on the current pressure p(x,y), and σ goal is the desired target stress value, which is used to optimize the stress concentration area, reduce wear, and minimize J to reduce stress concentration in the wear area;

[0092] Actual stress σ(x,y) = α·p(x,y), where α is the proportionality coefficient and p(x,y) is the contact pressure at position (x,y). Adjusting p(x,y) controls the distribution of σ(x,y) to make it close to the target stress σ goal ;

[0093] Add constraints:

[0094] Total load constraint: The total load P in the contact area total Keep constant, that is, ∫ Ω p(x,y)dA=P total ;

[0095] Pressure non-negative constraint: The contact pressure p(x,y) is non-negative, that is, p(x,y)≥0;

[0096] The Lagrange multiplier method is used to combine the objective function with the constraint conditions, and the contact pressure p(x,y) is iteratively adjusted using the optimization algorithm to define the Lagrangian function:

[0097] Where λ is the Lagrange multiplier, and we need to solve and Get the optimized p(x,y) distribution;

[0098] Based on the pressure distribution of the optimization results, the contact pressure in high wear areas is updated to reduce the stress concentration in these areas in real time;

[0099] In step S3, the protective agent and lubrication parameters are adjusted as follows:

[0100] Based on the wear amount W(t) and wear rate R(t) fed back by the sensor, the optimal thickness h(t) of the electronic depth protector is calculated in real time, h(t) = β·R(t), where h(t) is the thickness of the protector at time t. is the wear rate, β is the adjustment coefficient;

[0101] Future wear rate prediction based on deep learning model Dynamic adjustment of lubrication frequency:

[0102] Where, f(t) is the lubrication frequency, f min is the minimum lubrication frequency, γ is the adjustment parameter, is the predicted wear rate at time t+Δt. When the predicted wear rate increases, the lubrication frequency is automatically increased, thereby strengthening protection in areas with increased wear;

[0103] In step S3, the method of adjusting the protective agent and lubrication parameters also includes:

[0104] The wear state is fed back into the digital twin model to calculate the protective agent thickness distribution h(x, y, t) and lubrication frequency f(x, y, t) at each position, and the optimization objective function J is used to dynamically balance the amount of protective agent used and the coverage effect:

[0105] Where J is the objective function, which represents the deviation between the wear rate and the protective agent coverage effect, Ω is the contact area, α is the proportionality coefficient, which is related to the protective agent effect, h(x,y,t) is the protective agent thickness at time T at position (x,y), and f(x,y,t) is the lubrication frequency at this position;

[0106] The linkage control strategy is:

[0107] Sensor data input to collect real-time wear amount and wear rate;

[0108] Model calculation: Calculate the protective agent thickness and lubrication frequency according to the current wear status;

[0109] Optimization and adjustment: Feedback h(x,y,t) and f(x,y,t), the protective layer dynamically adapts to the current wear conditions;

[0110] Specifically, dynamic linkage control of protective agents and lubrication parameters is realized in high-wear areas. The digital twin model and deep learning model continuously optimize the distribution of protective agents and lubrication frequency based on real-time wear data. Based on the Lagrangian optimization algorithm, the contact pressure distribution in high-wear areas is adjusted to minimize the deviation between actual stress and target stress, thereby reducing the degree of wear concentration and improving the reliability and stability of the connector in extreme environments.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An application of improving the wear resistance of connectors based on an electronic depth protective agent, characterized in that: The application steps include, Step S1, establishing a digital twin model, based on the geometric structure and material properties of the connector, constructing a digital twin model to simulate the stress, wear and temperature changes of the connector under different environments; Step S2, wear prediction and life estimation based on deep learning, based on the historical and real-time data obtained in step S1 and the simulation results, build and train a deep learning model to identify the correlation between wear rate and environmental parameters and form a wear trend graph; Step S3, adaptive optimization and dynamic application of electronic depth protectant, combined with the wear prediction data of step S2, using an optimization algorithm to adjust the pressure and load distribution of the connector contact parts to reduce stress in high wear areas; Introducing electronic deep protection agent in high wear areas to form an intelligent lubrication protection layer: according to the severity of wear and real-time temperature, the lubrication frequency is increased in high wear or high temperature areas.

2. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 1, characterized in that: Acquiring real-time data in step S1: installing micro sensors at key parts of the connector, including the contact surface, contact pins and locking parts, to collect temperature, stress and vibration data in real time, and arranging temperature, humidity and dust environment sensors to obtain environmental condition data of the connector; Real-time data includes: temperature, stress and vibration data and environmental condition data; the real-time data is input into the digital twin model, the wear and stress distribution of the connector in the actual use environment is dynamically simulated, and the simulation results are output.

3. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 2, characterized in that: In step S1, the steps of building a digital twin model include: The digital twin model is initialized based on the geometric structure and material properties of the connector, and the force and stress distribution of the connector are modeled. The Archard wear model is used to predict wear based on contact pressure, sliding distance, and material wear coefficient: Where W represents the wear amount, k is the wear coefficient, F is the normal force on the contact surface, d is the sliding distance, and H is the hardness of the material; A thermal-mechanical coupling model is constructed to model the temperature field for friction heating under high load. Assuming the temperature field is T(x, y, z, t), then: Where ρ is the material density, c is the specific heat capacity of the material, T(x,y,z,t) is the temperature field, which varies with position (x,y,z) and time t, and k th is the thermal conductivity, q is the frictional heat generation term, q = τ·v, where v is the sliding velocity and τ is the shear stress; Acquire real-time data from sensors and input it into the digital twin model for dynamic simulation updates.

4. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 3 is characterized in that: In step S2, the deep learning model predicts the wear development trend and life limit of key parts based on the input data, and provides early warning for impending wear risks; The input data are historical and real-time data as well as simulation results; At the same time, the deep learning model identifies potential high wear areas.

5. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 4, characterized in that: In step S2, the wear prediction and life estimation method based on deep learning is: Assume that the historical wear data is W hist , the real-time temperature is T real , real-time stress is σ real , the real-time vibration frequency is f vib , the real-time contact pressure is p real , the simulation output data of the digital twin model is W sim Based on the above data, preprocessing and feature extraction are performed, and the features include: wear rate R wear and environmental characteristics, Where ΔW is the wear amount in a certain time interval, Δt is the time interval, and the combination of environmental features is defined as, which serves as the input of the deep learning model; A neural network model based on long short-term memory (LSTM) is used to capture the time series characteristics of wear. The input is the time series feature X env and historical wear rate R wear (t), the output is the predicted future wear rate The loss function is defined as the mean square error between the predicted wear rate and the actual rate: L = Among them, K represents the prediction error, N represents the total number of time steps, and t i represents the time step, i represents the time step index, and Δt is the interval between adjacent time steps.

6. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 5, characterized in that: In step S2, the method of performing wear prediction and life estimation also includes: Based on predicted future wear rates Calculate the cumulative wear of key connector parts: Where Δt is the interval between adjacent time steps, W cumulative (t) and W cumulative (t+Δt) are the cumulative wear amounts of two adjacent time steps; Assume the durability limit is W limit , using the current wear and durability limit to estimate the remaining life of key parts: Among them, t life Indicates the remaining time until the wear endurance reaches the limit, i.e. the remaining life; Based on real-time data and simulation results, the local wear distribution function W is applied local (x,y) Identify high wear areas: Where R wear (x, y, τ) is the wear rate at position (x, y) at time τ. local Areas of high (x,y) values ​​identify potential high wear locations.

7. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 6, characterized in that: In step S3, the digital twin model is linked with the deep learning model to adjust the electronic depth protectant and lubrication parameters in real time according to the wear status fed back by the sensor, so that the protective layer is synchronized with the wear changes.

8. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 7, characterized in that: In step S3, the pressure distribution of the connector contact part is adjusted in combination with the wear prediction data of step S2, specifically: The objective function I of the total stress is defined in the high wear area. The function describes the deviation between the current stress distribution and the target stress distribution. The optimization purpose is to adjust the pressure distribution p(x, y) so that the actual stress is close to the target value. The objective function J is defined as: J = f Ω (σ(x,y)-σ goal ) 2 dA, where Ω is the high wear area, dA represents any small area unit in the integral area Ω, σ(x, y) represents the actual stress at the position (x, y), calculated based on the current pressure p(x, y), and σ goal is the desired target stress value, which is used to optimize the stress concentration area and reduce wear; Actual stress σ(x, y) = α·p(x, y), where α is the proportionality coefficient and p(x, y) is the contact pressure at position (x, y). Adjust p(x, y) to control the distribution of σ(x, y) so that it is close to the target stress σ goal ; Add constraints: Total load constraint: The total load P in the contact area total Keep constant, that is, f Ω p(x,y)dA=P total ; Pressure non-negative constraint: the contact pressure p(x, y) is non-negative, that is, p(x, y) ≥ 0; The Lagrange multiplier method is used to combine the objective function with the constraint conditions, and the contact pressure p(x, y) is iteratively adjusted using the optimization algorithm to define the Lagrangian function: Where λ is the Lagrange multiplier, and we need to solve and Get the optimized p(x, y) distribution.

9. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 8, characterized in that: In step S3, the protective agent and lubrication parameters are adjusted as follows: Based on the wear amount W(t) and wear rate R(t) fed back by the sensor, the optimal thickness h(t) of the electronic depth protector is calculated in real time, h(t) = β·R(t), where h(t) is the thickness of the protector at time t. is the wear rate, β is the adjustment coefficient; Future wear rate prediction based on deep learning model Dynamic adjustment of lubrication frequency: Where, f(t) is the lubrication frequency, f min is the minimum lubrication frequency, γ is the adjustment parameter, is the predicted wear rate at time t+Δt. When the predicted wear rate increases, the lubrication frequency automatically increases.

10. The application of the electronic depth protection agent for improving the wear resistance of connectors according to claim 9, characterized in that: In step S3, the method of adjusting the protective agent and lubrication parameters also includes: The wear state is fed back into the digital twin model, the protective agent thickness distribution h(x, y, t) and lubrication frequency f(x, y, t) at each position are calculated, and the optimization objective function J is used to dynamically balance the amount of protective agent used and the coverage effect: Among them, J is the objective function, which represents the deviation between the wear rate and the protective agent coverage effect, Ω is the contact area, α is the proportionality coefficient, which is related to the protective agent effect, h(x, y, t) is the protective agent thickness at time t at the position (x, y), and f(x, y, t) is the lubrication frequency at this position.

Images