Intelligent parking braking system for railway wagon

Abstract

The invention discloses an intelligent parking braking system for a railway wagon, relates to the technical field of railway wagon braking, and solves the technical problems that in the prior art, parking scenes and the abrasion condition of parking brake pads are not accurately considered, so that potential safety hazards exist in parking braking, and the parking effect is poor. The theoretical required torque is calculated according to the road surface gradient; calculating the wear degree of the brake pad according to the brake pad parameters; calculating an actual demand torque according to the theoretical demand torque and the wear degree of the brake pad, and then generating a brake current; the corresponding motor is adjusted according to the braking current; an alarm signal is generated according to the wear degree of the brake pad, the required torque required for braking of the truck is calculated in real time, corresponding braking torque is distributed to a plurality of braking drives of the truck in a self-adaptive mode, and the wear condition of the brake pad is dynamically calculated by considering the inconsistency of damage to the brake pad caused by the truck under different braking conditions, so that the braking effect of the truck is improved.

Description

Technical Field

[0001] This application belongs to the technical field of railway freight car braking, and specifically relates to an intelligent parking brake system for railway freight cars. Background Art

[0002] Railway freight cars are vehicles specifically used for transporting goods in railway transportation. They are not equipped with power devices and need to be towed by locomotives to run on railways. Railway freight cars can transport coal, grains, liquids, livestock, ammunition, cement, various large goods, and various materials, etc., and are an important part of railway transportation. Parking brake is a safety auxiliary braking device on vehicles such as automobiles and railway freight cars. Its main function is to lock the drive shaft or rear wheels after the vehicle stops to ensure that the vehicle will not move by itself due to factors such as gravity, wind, or slopes, thereby improving the safety of the vehicle.

[0003] Traditional railway freight car parking brake systems mostly adopt mechanical braking methods, which have problems such as slow braking response, cumbersome operation, and the braking effect being easily affected by environmental factors. With the continuous development of intelligent technologies, electronic parking brake systems have been widely used in the automotive field and have shown remarkable braking performance and operation convenience. In the application background of railway freight cars, the existing technologies lack accurate consideration of parking scenarios and the wear conditions of parking brake pads, resulting in potential safety hazards and poor parking effects in parking braking; for example, the impact of frequent parking on brake pad wear is higher than that of normal parking, and the braking torque of parking also varies depending on the state of the vehicle; therefore, further improvement of the intelligent parking brake system is still needed. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes an intelligent parking brake system for railway freight cars to solve the technical problems that the existing technologies lack accurate consideration of parking scenarios and the wear conditions of parking brake pads, resulting in potential safety hazards and poor parking effects in parking braking.

[0005] To achieve the above object, the first aspect of this application provides an intelligent parking brake system for railway freight cars, including: a data acquisition module, a data analysis module, an early warning module, and a database;

[0006] The data acquisition module: obtains motor data, environmental data, and vehicle data through data acquisition devices; the motor data includes motor ID, braking voltage, braking current, braking torque, and brake pad parameters; the environmental data includes temperature, humidity, and road surface gradient; the vehicle data includes vehicle ID and vehicle load;

[0007] The data analysis module: calculates the theoretical required torque according to the road surface gradient; calculates the wear degree of the brake pads according to the brake pad parameters; generates a braking current after calculating the actual required torque based on the theoretical required torque and the wear degree of the brake pads; adjusts the corresponding motor according to the braking current; generates an alarm signal according to the wear degree of the brake pads;

[0008] The early warning module: makes a prompt according to the alarm signal and contacts the management personnel;

[0009] The database is used to store the data collected by the data collection device and the historical data required for storing the training model.

[0010] This application calculates the theoretical required torque according to the road surface gradient; calculates the wear degree of the brake pads according to the brake pad parameters; generates a braking current after calculating the actual required torque based on the theoretical required torque and the wear degree of the brake pads; adjusts the corresponding motor according to the braking current; generates an alarm signal according to the wear degree of the brake pads, calculates the required torque for truck braking in real time, and adaptively distributes the corresponding braking torque for several braking drives of the vehicle, considering that the damage caused to the brake pads under different braking conditions of the vehicle is inconsistent, and dynamically calculates the wear condition of the brake pads, so as to improve the braking effect of the truck.

[0011] Further, the calculating the theoretical required torque according to the road surface gradient includes:

[0012] Obtain the road surface gradient LP, vehicle weight m, wheel radius r, and basic braking force JZL;

[0013] Calculate the theoretical required torque LXL through the formula LXL = (JZL + m × g × LP) × r; where g is the acceleration due to gravity.

[0014] Further, the calculating the wear degree of the brake pads according to the brake pad parameters includes:

[0015] Obtain several historical brake pad parameters; the historical brake pad parameters include historical working time points and their corresponding historical working durations, historical working torques, and historical working environments;

[0016] Divide several historical time clusters according to the historical working time points;

[0017] Calculate the historical environment influence coefficient according to the historical working environment;

[0018] Generate the wear degree of the brake pads according to the historical event clusters and the historical environment influence coefficient.

[0019] Further, the dividing several historical time clusters according to the historical working time points includes:

[0020] Obtain several historical working time points T i ;

[0021] Create a clustering list JL and a cluster list CL; the clustering list is used to store all historical time clusters; the cluster list is used to store several historical working time points in the historical time cluster;

[0022] Select T in sequence i ;

[0023] When CL is an empty list, put T i into CL;

[0024] Otherwise, calculate the time difference between T i and the last historical working time point in CL;

[0025] Judge whether the time difference is less than the difference threshold; if yes, put T i into the CL; if not, put the CL into JL and create a new CL.

[0026] Further, calculating the historical environment impact coefficient according to the historical working environment includes:

[0027] Obtain the environmental temperature HW, environmental humidity HS corresponding to the historical working time point and the standard working temperature BW;

[0028] Through the formula Calculate the historical environment impact coefficient HYX; where E represents the apparent activation energy of the wear process, reflecting the sensitivity of temperature to material softening; R represents the ideal gas constant; β represents the humidity sensitivity coefficient; ΔG represents the change in Gibbs free energy of the humidity-driven oxidation reaction.

[0029] Further, generating the brake pad wear degree according to the historical event cluster and the historical environment impact coefficient includes:

[0030] Obtain the clustering list JL, the historical environment impact coefficient HYX, the historical working duration GT and the historical working torque GL; the clustering list contains several cluster lists; the cluster list contains several historical working time points;

[0031] Through the formula Calculate the brake pad wear degree ZMD; where MS max represents the theoretical maximum wear amount, min() and max() are used to make the brake pad wear degree ZMD∈(0, 1); and MS j =(∑ k MS j,k )×(1 + δ×max{k} α ), where max{k} represents the number of historical working time points in the cluster list, δ is the time point density impact coefficient, δ>0, α is the strengthening index, α>0;

[0032] Among them, GTY represents the working hours threshold, and h represents the wear acceleration coefficient after exceeding the threshold, where h > 1.

[0033] Furthermore, generating the braking current after calculating the actual required torque according to the theoretical required torque and the brake pad wear degree includes:

[0034] Obtaining the theoretical required torque LXL and vehicle data; the vehicle data includes the vehicle direction and several braking loads;

[0035] Inputting the vehicle direction and several braking loads into the torque distribution model to obtain several braking weights; the torque distribution model is constructed by an artificial intelligence model;

[0036] Through the formula Calculate several actual required torques SXL m ; where m represents the brake number corresponding to several brake pads, and ZQ m Represents the braking weights corresponding to several brakes;

[0037] Generate several braking currents according to the actual required torque.

[0038] Furthermore, generating several braking currents according to the actual required torque includes:

[0039] Obtain the actual required torques SXL corresponding to several brakes m ;

[0040] Calculate several braking currents through the formula where LC is the torque constant, and LC > 0.

[0041] Furthermore, constructing the torque distribution model by an artificial intelligence model includes:

[0042] Obtain several historical vehicle directions, historical several braking loads, and their corresponding historical several braking weights; divide several historical vehicle directions, historical several braking loads, and their corresponding historical several braking weights into training data, validation data, and test data; perform data preprocessing on the training data, validation data, and test data to obtain a training set, a validation set, and a test set;

[0043] Select an artificial intelligence model as the basic model;

[0044] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain a pre-trained model;

[0045] Verify the pre-trained model on the test set, and finally obtain a torque distribution model that inputs the vehicle direction and several braking loads and outputs several braking weights.

[0046] Further, generating an alarm signal according to the wear degree of the brake pad includes:

[0047] Obtain the wear degree of the brake pad;

[0048] Judge whether the wear degree of the brake pad is greater than the scrap threshold;

[0049] If yes, generate a brake pad scrap alarm signal;

[0050] If no, judge whether the wear degree of the brake pad is greater than D times the scrap threshold. If yes, generate a warning signal that the brake pad is about to be scrapped; if no, do nothing; where D is a proportionality coefficient, D ∈ (0, 1).

[0051] This application can respond in a timely manner when an alarm signal or a warning signal appears for the brake pad by monitoring the damage of the brake pad in real time, avoiding potential safety hazards and improving the safety of the truck during driving and braking.

[0052] Compared with the prior art, the beneficial effects of this application are:

[0053] 1. This application calculates the theoretical required torque according to the road surface gradient; calculates the wear degree of the brake pad according to the brake pad parameters; generates the braking current after calculating the actual required torque according to the theoretical required torque and the wear degree of the brake pad; adjusts the corresponding motor according to the braking current; generates an alarm signal according to the wear degree of the brake pad, calculates the required torque for the truck braking in real time, and adaptively distributes the corresponding braking torque to several braking drives of the vehicle, considering that the damage caused to the brake pad under different braking conditions of the vehicle is inconsistent, and dynamically calculates the wear condition of the brake pad to improve the braking effect of the truck.

[0054] 2. This application clusters and divides the historical working time points of the brake pad. Considering that the damage caused by the frequent use of the brake pad in a short period of time is more serious than in other cases, the damage of the brake pad in each time period can be effectively calculated through clustering and division, so that the damage condition of the brake pad can be obtained more accurately, improving the accuracy of the braking effect determination.

[0055] 3. This application adaptively distributes the braking torque borne by several brakes according to the vehicle direction of the vehicle and the braking loads corresponding to several brakes, and automatically calculates the reasonable actual required torque according to the damage degree of each brake pad, avoiding the situation that the torque required by a single brake exceeds its maximum range and causing adverse consequences, improving the braking effect and the safety of the truck during driving. Description of the Drawings

[0056] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0057] Figure 1 It is a schematic diagram of the principle of an intelligent parking brake system for railway freight cars of the present application;

[0058] Figure 2 It is a flowchart of an intelligent parking brake method for railway freight cars of the present application;

[0059] Figure 3 It is a flowchart for generating an alarm signal of the present application. Specific embodiments

[0060] The following will clearly and completely describe the technical solutions of the present application in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0061] Please refer to Figure 1 - Figure 2 , the first aspect embodiment of the present application provides an intelligent parking brake system for railway freight cars, including: a data acquisition module, a data analysis module, an early warning module, and a database;

[0062] Data acquisition module: Obtain motor data, environmental data, vehicle data, etc. through data acquisition devices; Motor data includes motor ID, braking voltage, braking current, braking torque, and brake pad parameters; Environmental data includes temperature, humidity, and road surface gradient; Vehicle data includes vehicle ID, vehicle load, and braking signal, etc.; Data acquisition devices include various sensors, etc.;

[0063] Data analysis module: Calculate the theoretical required torque according to the road surface gradient. The theoretical required torque is the torque required without considering brake pad wear; Calculate the brake pad wear degree according to the brake pad parameters. The brake pad wear degree refers to the degree of wear of the brake pad; Generate the actual required torque after calculating the actual required torque based on the theoretical required torque and the brake pad wear degree. The actual required torque is the torque required after considering brake pad wear, and the braking current is the number of currents required to reach the actual required torque; Adjust the corresponding motor according to the braking current; Generate an alarm signal according to the brake pad wear degree;

[0064] Early warning module: Make a prompt according to the alarm signal and contact the management personnel; The alarm signal includes a brake pad scrapping alarm signal, a brake pad about to be scrapped early warning signal, etc.;

[0065] The database is used to store the data collected by the data acquisition device and the historical data required for storing the training model.

[0066] Calculating the theoretical required torque according to the road surface gradient in this embodiment includes:

[0067] Obtain the road surface gradient LP, vehicle weight m, wheel radius r, and basic braking force JZL; the basic braking forces of different vehicles are different;

[0068] Calculate the theoretical required torque LXL through the formula LXL = (JZL + m×g×LP)×r; where g is the acceleration due to gravity, g = 9.8m / s 2 ; LP is the calculation result of the sine value of the gradient; as the basic braking force and gradient data increase, the theoretical required torque will gradually increase.

[0069] This embodiment calculates the theoretical required torque of the vehicle through multi-source data, and based on the theoretical required torque, provides strong data support for subsequent vehicle braking to ensure that the vehicle can brake in a timely and effective manner.

[0070] Calculating the brake pad wear degree according to the brake pad parameters in this embodiment includes:

[0071] Obtain a number of historical brake pad parameters; the historical brake pad parameters include historical working time points and their corresponding historical working durations, historical working torques, and historical working environments;

[0072] Divide a number of historical time clusters according to the historical working time points; dividing the historical time clusters is to separately consider the wear of the brake pads caused by frequent braking, so that the wear of the brake pads can be accurately calculated;

[0073] Calculate the historical environment influence coefficient according to the historical working environment; each time braking is performed through the brake pads, the corresponding environmental data will cause different degrees of damage to the brake pads; for example, braking at low temperature will cause more serious effects than normal temperature;

[0074] Generate the brake pad wear degree according to the historical event clusters and the historical environment influence coefficient.

[0075] Dividing a number of historical time clusters according to the historical working time points in this embodiment includes:

[0076] Obtain a number of historical working time points T i ;

[0077] Create a cluster list JL and a cluster list CL; the cluster list is used to store all historical time clusters; the cluster list is used to store a number of historical working time points in the historical time clusters;

[0078] Select T sequentially i ;

[0079] When CL is an empty list, place T i into CL;

[0080] Otherwise, calculate the time difference between T i and the last historical working time point in CL;

[0081] Judge whether the time difference is less than the difference threshold; the difference threshold is set according to experience; if yes, place T i into CL; if no, place CL into JL and create a new CL.

[0082] In this embodiment, a time series clustering analysis method is innovatively adopted to dynamically divide the working conditions of the brake pads. Aiming at the cumulative effect of brake pad damage under high-frequency intermittent braking conditions, through establishing a damage assessment model, refined damage measurement within the braking cycle is achieved, significantly improving the prediction accuracy of the remaining life of the brake pads, enhancing the braking efficiency, and providing a reliable quantitative basis for intelligent decision-making.

[0083] Calculating the historical environment influence coefficient according to the historical working environment in this embodiment includes:

[0084] Obtain the environmental temperature HW, environmental humidity HS corresponding to the historical working time point, and the standard working temperature BW;

[0085] Through the formula Calculate the historical environment influence coefficient HYX; where E represents the apparent activation energy of the wear process, reflecting the sensitivity of temperature to material softening; R represents the ideal gas constant, and the specific value of R in this embodiment is R = 8.314 J / (mol·K); β represents the humidity sensitivity coefficient; ΔG represents the Gibbs free energy change of the humidity-driven oxidation reaction, and the specific value is set according to the material characteristics. The apparent activation energy, humidity sensitivity coefficient, etc. corresponding to brake pads of different materials are different; in the formula, the first half refers to the temperature term; the second half refers to the influence generated by the synergistic effect of temperature and humidity; on the basis that other parameters except temperature and humidity remain unchanged, as the temperature and humidity increase, the environment influence coefficient increases accordingly.

[0086] Generating the brake pad wear degree according to the historical event clustering and the historical environment influence coefficient in this embodiment includes:

[0087] Obtain the clustering list JL, the historical environment influence coefficient HYX, the historical working duration GT, and the historical working torque GL; the clustering list contains several cluster lists; the cluster list contains several historical working time points;

[0088] Through the formula Calculate the brake pad wear degree ZMD; where MS max is expressed as the theoretical maximum wear amount, and the specific value is set according to experience, or can be calculated by taking the average value of multiple experiments under multiple extreme working conditions; min() and max() are used to make the brake pad wear degree ZMD ∈ (0, 1); on the basis of determining the theoretical maximum wear amount, the brake pad wear degree increases with the increase of the corresponding brake pad wear degrees of several clusters; and MS j =(∑ k MS j,k )×(1 + δ×max{k} α ), where max{k} represents the number of historical working time points in the cluster list, δ is the time point density influence coefficient, δ > 0, α is the strengthening index, α > 0; the specific values are set according to experience; in this embodiment, δ is set to 0.18 and α is set to 1.1; the setting of the strengthening index is to reflect the situation that the more time points there are, the more serious the wear; as the number of historical working time points in the cluster list increases, the brake pad wear degree corresponding to this cluster will increase accordingly;

[0089] Among them, GTY is expressed as the working duration threshold, and the specific value is set according to experience, or can be determined by gradually increasing GT under fixed GL and HYX and observing the mutation point of the wear rate; h is the wear acceleration coefficient after exceeding the threshold, h > 1, and the specific value is set according to experience. If h is set to 2, the brake pad wear of the part exceeding the working duration threshold is equivalent to 2 times the increase; when the historical working duration of the brake pad in the historical working time point exceeds the working duration threshold, the damage caused to the brake pad will gradually increase, and as the historical environment influence coefficient, historical working torque, and historical working duration increase, the brake pad wear degree of this historical working time point will also increase accordingly.

[0090] Through the above steps, this embodiment not only focuses on the working time points of the brake pads, but also carefully considers the working duration of the brake pads. Through multi-dimensional comprehensive consideration, it can accurately evaluate the wear condition of the brake pads, provide detailed data support for the subsequent optimization of braking performance, and thus significantly improve the efficiency and reliability of freight car braking.

[0091] After calculating the actual required torque according to the theoretical required torque and the brake pad wear degree in this embodiment, generating a braking current includes:

[0092] Obtain the theoretical required torque LXL and vehicle data; the vehicle data includes the vehicle direction and several braking loads; the vehicle direction refers to whether the vehicle head is in the downhill direction or the uphill direction, and the actual required torque of the brake for different directions of the vehicle head is different;

[0093] Input the vehicle direction and several braking loads into the moment distribution model to obtain several braking weights; the moment distribution model is constructed by an artificial intelligence model; when the vehicle is in different docking directions, brakes at different positions require different degrees of braking torque for braking. Therefore, during braking, corresponding braking torques need to be allocated to different brakes for braking;

[0094] Through the formula Calculate several actual required torques SXL m ; where m represents the brake numbers corresponding to several brake pads, and ZQ m represents the braking weights corresponding to several brakes; The more severe the wear is reflected, the exponential growth of the compensation torque is required, but through the square term ZMD 2 the growth rate can be slowed down to avoid infinite divergence; as the wear degree of the brake pads increases, the corresponding actual required torque will also increase;

[0095] Generate several braking currents according to the actual required torques.

[0096] Generating several braking currents according to the actual required torques in this embodiment includes:

[0097] Obtain the actual required torques SXL corresponding to several brakes m ;

[0098] Calculate several braking currents through the formula where LC is the torque constant, LC > 0, and the specific value is set according to experience, and the torque constants corresponding to different brakes are different; among the same type of brakes, the braking current increases with the increase of the actual required torque.

[0099] This embodiment flexibly allocates the braking torques that each brake should bear based on the vehicle direction of the vehicle and the braking loads borne by multiple brakes; at the same time, the system will also intelligently calculate the reasonable torques they actually need according to the wear conditions of the brake pads of each brake, so as to effectively prevent the required torque of any single brake from exceeding its maximum bearing range, avoid potential risks, and thus enhance the braking efficiency and improve the overall safety of the truck operation.

[0100] The moment distribution model in this embodiment is constructed by an artificial intelligence model, including:

[0101] Obtain a number of historical vehicle directions, a number of historical braking loads, and their corresponding a number of historical braking weights; divide the number of historical vehicle directions, the number of historical braking loads, and their corresponding a number of historical braking weights into training data, validation data, and test data; perform data preprocessing on the training data, validation data, and test data to obtain a training set, a validation set, and a test set; the ratio among the training set, the test set, and the validation set is 7:2:1;

[0102] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a convolutional neural network model, etc.;

[0103] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain a pre-trained model;

[0104] Verify the pre-trained model on the test set, and finally obtain a torque distribution model that takes the input vehicle direction and a number of braking loads and outputs a number of braking weights.

[0105] In this embodiment, adjusting the corresponding motor according to the braking current includes:

[0106] Obtain the braking current, its corresponding brake parameters, and a braking signal; the braking signal includes a manual braking signal and a remote braking signal;

[0107] When the braking signal is a manual braking signal, assign the braking current to the corresponding parameter in the brake parameters to achieve the braking effect;

[0108] When the braking signal is a remote braking signal, assign the braking current to the corresponding parameter in the brake parameters to achieve the braking effect; realizing dual braking modes of manual braking and remote braking improves the braking efficiency.

[0109] Please refer to Figure 3 , generating an alarm signal according to the brake pad wear degree in this embodiment includes:

[0110] Obtain the brake pad wear degree;

[0111] Judge whether the brake pad wear degree is greater than the scrap threshold; the scrap threshold is set according to experience;

[0112] Yes, generate a brake pad scrap alarm signal;

[0113] No, judge whether the brake pad wear degree is greater than D times the scrap threshold. If yes, generate a warning signal that the brake pad is about to be scrapped; if no, do nothing; where D is a proportionality coefficient, D ∈ (0, 1), and the specific value is set according to experience. In this embodiment, D is set to 0.6.

[0114] Some of the data in the above formula is the numerical value obtained by removing the dimension. The formula is the one closest to the actual situation obtained through software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0115] The working principle of this application: By obtaining motor data, environmental data, and vehicle data; calculating the theoretical required torque according to the road surface gradient; calculating the brake pad wear degree according to the brake pad parameters; generating a braking current after calculating the actual required torque based on the theoretical required torque and the brake pad wear degree; adjusting the corresponding motor according to the braking current; generating an alarm signal according to the brake pad wear degree; making a prompt according to the alarm signal and contacting the management personnel, calculating in real time the required torque for the truck braking, and adaptively distributing the corresponding braking torque for several braking drives of the vehicle. Considering that the damage to the brake pads caused by the vehicle under different braking conditions is inconsistent, dynamically calculating the wear condition of the brake pads, so as to improve the braking effect of the truck, avoiding the problems in the prior art of lacking accurate consideration of the parking scenario and the wear condition of the parking brake pads, resulting in potential safety hazards in the parking brake and poor parking effect.

[0116] The above embodiments are only used to illustrate the technical method of this application and not to limit it. Although this application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of this application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of this application.

Claims

1. An intelligent parking brake system for railway freight cars, characterized in that: include: Data collection module, data analysis module, early warning module and database; The data acquisition module acquires motor data, environmental data and vehicle data through a data acquisition device; the motor data includes motor ID, brake voltage, brake current and brake torque as well as brake pad parameters; the environmental data includes temperature, humidity and road slope; the vehicle data includes vehicle ID and vehicle load; The data analysis module calculates the theoretical required torque according to the road slope and calculates the brake pad wear according to the brake pad parameters; Generate a braking current after calculating the actual required torque based on the theoretical required torque and the brake pad wear; adjust the corresponding motor according to the braking current; generate an alarm signal based on the brake pad wear; The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

2. The intelligent parking brake system for railway freight cars according to claim 1, characterized in that: The calculating of the theoretical required torque according to the road surface slope includes: Obtain the road slope LP, vehicle weight m, wheel radius r and basic braking force JZL; The theoretical required torque LXL is calculated by the formula LXL=(JZL+m×g×LP)×r, where g is the acceleration due to gravity.

3. The intelligent parking brake system for railway freight cars according to claim 1, characterized in that: The calculating the brake pad wear degree according to the brake pad parameters includes: Obtaining several historical brake pad parameters; the historical brake pad parameters include historical working time points and their corresponding historical working durations, historical working torques and historical working environments; Divide several historical time clusters according to historical work time points; Calculate the historical environmental impact coefficient based on the historical working environment; The brake pad wear degree is generated based on historical event clustering and historical environmental impact coefficient.

4. The intelligent parking brake system for railway freight cars according to claim 3, characterized in that: The historical time clusters are divided according to the historical working time points, including: Get several historical working time points T i ; Create a cluster list JL and a cluster list CL; the cluster list is used to store all historical time clusters; the cluster list is used to store several historical working time points in the historical time clusters; Select T i ; When CL is an empty list, T i Place in CL; Otherwise, calculate T i The time difference between the last historical working time point in CL; Determine whether the time difference is less than the difference threshold; if so, set T i Place it into the CL; otherwise, place the CL into the JL and create a new CL.

5. The intelligent parking brake system for railway freight cars according to claim 3, characterized in that: The calculation of the historical environmental impact coefficient based on the historical working environment includes: Obtain the ambient temperature HW and ambient humidity HS and standard operating temperature BW corresponding to the historical working time point; By formula Calculate the historical environmental impact coefficient HYX; where E represents the apparent activation energy of the wear process; R represents the ideal gas constant; β represents the humidity sensitivity coefficient; ΔG represents the change in Gibbs free energy of the humidity-driven oxidation reaction.

6. The intelligent parking brake system for railway freight cars according to claim 3, characterized in that: The generating of the brake pad wear degree according to the historical event clustering and the historical environmental impact coefficient includes: Obtain a cluster list JL, a historical environmental impact coefficient HYX, a historical working time GT, and a historical working moment GL; the cluster list includes several cluster lists; the cluster list includes several historical working time points; By formula Calculate the brake pad wear ZMD; where MS max It is expressed as the theoretical maximum wear amount, min() and max() are to make the brake pad wear ZMD∈(0,1); and MS j =(∑ k MS j,k )×(1+δ×max{k} α ), where max{k} represents the number of historical working time points in the cluster list, δ is the time point density influence coefficient, δ>0, and α is the reinforcement index, α>0; in, GTY represents the working time threshold, h represents the wear acceleration coefficient after exceeding the threshold, and h>

1.

7. The intelligent parking brake system for railway freight cars according to claim 5, characterized in that: The step of calculating the actual required torque according to the theoretical required torque and the brake pad wear and then generating the braking current comprises: Obtaining a theoretical required torque LXL and vehicle data; the vehicle data includes a vehicle direction and a number of braking loads; Inputting the vehicle direction and a number of braking loads into a torque distribution model to obtain a number of braking weights; the torque distribution model is constructed by an artificial intelligence model; By formula Calculate some actual required moments SXL m ; Among them, m represents the brake number corresponding to a number of brake pads, ZQ m It is expressed as the braking weights corresponding to a number of brakes; Generates a certain amount of braking current according to the actual required torque.

8. The intelligent parking brake system for railway freight cars according to claim 7, characterized in that: The generating of a plurality of braking currents according to the actual required torque includes: Get the actual required torque SXL corresponding to several brakes m ; Calculate several braking currents by formula Where LC is the torque constant, LC>

0.

9. The intelligent parking brake system for railway freight cars according to claim 7, characterized in that: The torque distribution model is constructed by an artificial intelligence model, including: Acquire a number of historical vehicle directions and a number of historical braking loads and their corresponding historical braking weights; divide the number of historical vehicle directions and a number of historical braking loads and their corresponding historical braking weights into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally get a torque distribution model that inputs vehicle direction and several braking loads and outputs several braking weights.

10. The intelligent parking brake system for railway freight cars according to claim 1, characterized in that: The generating of an alarm signal according to the brake pad wear degree comprises: Get the brake pad wear degree; Determine whether the brake pad wear is greater than the scrap threshold; Yes, a brake pad scrap alarm signal is generated; No, determine whether the brake pad wear is greater than D times the scrap threshold. If yes, generate a warning signal that the brake pad is about to be scrapped; if no, do nothing; where D is the proportional coefficient, D∈(0,1).

Images