A heating device for a vehicle braking system and a control method thereof

Abstract

The present invention relates to the field of data processing technology, and in particular to a heating device for a vehicle braking system and a control method thereof, comprising a split heating module, a data fusion control module, a partition coordination module and a self-test module. The split heating module sets a heat exchange unit linked to the cockpit in the front vehicle brake assembly, and constructs an aluminum insulation chamber in the rear vehicle and integrates multi-zone heating tape, distributed temperature control probes and mechanical gap sensors to generate initial heat distribution parameters; the data fusion control module constructs a dynamic temperature control model based on the hydraulic unit temperature, seal deformation and ambient temperature data, and generates partition heating instructions in combination with the global optimization of the genetic algorithm; through multi-source data fusion, dynamic parameter calibration and gradient power reduction mechanism, the temperature field imbalance and energy consumption redundancy problems of the split vehicle body at low temperatures are solved, and the braking response speed and system reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a heating device for a vehicle braking system and a control method thereof. Background Art

[0002] The split-body braking system is a specialized braking device for articulated vehicles designed to withstand low temperatures and complex terrain. Its core feature is the split layout of the brake unit and the vehicle structure, which utilizes a flexible connection mechanism to achieve dynamic separation and coordinated control of the front and rear vehicle bodies. In low-temperature environments, the system must simultaneously address physical effects such as deterioration of the brake fluid's viscosity-temperature characteristics, low-temperature embrittlement of sealing materials, and abnormal clearances caused by shrinkage of metal components. The split structure further complicates thermal management.

[0003] In low-temperature environments, the braking system of a split-body vehicle lacks independent in-cabin heating support from the rear vehicle. Existing temperature control solutions that rely on a single heat source or static insulation struggle to achieve coordinated temperature regulation across multiple zones, leading to heating lag or localized overheating risks in key components such as the hydraulic unit, seals, and brake fluid under dynamic conditions. Specifically, existing control methods fail to establish a closed-loop feedback mechanism to account for differences in thermal conductivity and component thermal capacity within the split-body structure. These methods are unable to dynamically adjust heating strategies based on real-time data on changes in brake fluid viscosity, seal deformation, and mechanical clearances. This results in an unbalanced temperature field distribution and redundant energy consumption, which in turn weakens brake response speed and system reliability in low-temperature environments. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a heating device for a vehicle braking system and a control method thereof, which are used to solve the problems of insufficient coordination of heating areas, unbalanced temperature field distribution and energy consumption redundancy caused by the lack of a closed-loop control mechanism based on multi-source sensor data in a split-body braking system under low-temperature conditions, thereby improving the braking response speed and system reliability.

[0005] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0006] In a first aspect, the present invention provides a heating device for a vehicle brake system, comprising:

[0007] The split heating module is configured to install a first heat exchange unit in the front vehicle brake assembly that is linked to the thermal environment of the cockpit, and to construct an aluminum insulation chamber in the rear vehicle brake system. The aluminum insulation chamber integrates multi-zone heating cables, distributed temperature control probes, and mechanical gap sensors to generate initial thermal distribution parameters and transmit them to the data fusion control module;

[0008] The data fusion control module is connected to the split heating module and is used to receive hydraulic unit temperature data, seal deformation data, and ambient temperature data from the distributed temperature control probes, and access the brake pressure history parameters of the vehicle bus. Based on the hydraulic unit temperature data, seal deformation data, and ambient temperature data, a dynamic temperature control model is constructed, and closed-loop control parameters including zone heating power instructions are output to the zone collaboration module.

[0009] The partition coordination module is connected to the data fusion control module to divide the aluminum insulation chamber into the main heating zone and the auxiliary heating zone. It receives closed-loop control parameters and implements the continuous heating strategy and pulse heating frequency adjustment. The main heating zone controls the power output of the heating tape based on the continuous heating strategy, and the auxiliary heating zone adjusts the pulse heating frequency based on the real-time feedback data of the mechanical gap sensor.

[0010] The self-check module is connected to the partition coordination module and periodically collects the impedance of the heating cable loop and the calibration deviation data of the temperature control probe. When an impedance anomaly or an excessive calibration deviation is detected, abnormal data including the fault area identification is generated and transmitted to the data fusion control module;

[0011] Among them, the data fusion control module iteratively optimizes the control parameters of the dynamic temperature control model based on the initial heat distribution parameters and abnormal data, and sends the updated closed-loop control parameters to the partition collaboration module, forming a closed-loop control link from data acquisition, model optimization to instruction execution.

[0012] Furthermore, the present invention is used for a heating device of a vehicle braking system, and the data fusion control module includes:

[0013] A genetic algorithm optimization unit is used to generate an initial control parameter set based on the initial temperature field data set of the distributed temperature control probe and the deformation sensor data of the aluminum insulation chamber, and transmit the initial control parameter set to the model fine-tuning unit;

[0014] The model fine-tuning unit receives the real-time change of the mechanical clearance sensor and the estimated value of the brake fluid viscosity, performs online calibration of the initial control parameter set based on the dynamic temperature control model, and outputs the calibrated pulse frequency weight to the pulse heating controller of the auxiliary heating zone;

[0015] The delay compensation unit uses the historical temperature rise curve data stored in the self-test module to predict the thermal inertia delay time, dynamically adjusts the triggering timing of the gradient power reduction mechanism, and sends the adjusted timing instructions to the heating belt drive circuit of the main heating zone through the CAN bus;

[0016] Among them, the pulse frequency weight output by the model fine-tuning unit and the timing instructions of the delay compensation unit together constitute the closed-loop control parameters, driving the partition collaboration module to execute the heating strategy.

[0017] Furthermore, in the heating device for a vehicle brake system of the present invention, the delay compensation unit performs the following operations:

[0018] When the hydraulic unit temperature is lower than the critical threshold, a high-power rapid heating command is sent to the heating cable drive circuit of the main heating zone;

[0019] After the temperature reaches the preset safety range, the thermal inertia delay time is calculated based on the thermal inertia parameters of the dynamic temperature control model and the slope of the historical temperature rise curve, and the gradient reduction power coefficient is superimposed to generate the maintenance power instruction;

[0020] The maintenance power instruction is used as part of the closed-loop control parameters and is written into the instruction queue of the partition coordination module synchronously with the pulse frequency adjustment instruction of the auxiliary heating zone.

[0021] Furthermore, the heating device for a vehicle braking system of the present invention, the model fine-tuning unit includes:

[0022] The deformation compensation submodule uses the gap compensation algorithm of the dynamic temperature control model to correct the target temperature setting value of the main heating zone based on the deformation of the composite insulation board of the aluminum insulation chamber;

[0023] The viscosity feedback submodule calculates the brake fluid viscosity in real time based on the temperature-viscosity relationship curve, and dynamically adjusts the continuous heating power of the main heating zone and the pulse heating duty cycle of the auxiliary heating zone through fuzzy control rules;

[0024] Among them, the gap compensation coefficient output by the deformation compensation submodule and the viscosity adjustment parameter of the viscosity feedback submodule are input into the genetic algorithm optimization unit together as the optimization boundary conditions of the next generation control parameter set.

[0025] Furthermore, the present invention is used for a heating device of a vehicle braking system, and the self-test module includes:

[0026] The impedance detection unit periodically collects the resistance change rate of the heating cable loop. When abnormal resistance fluctuations are detected, it sends a backup loop activation instruction to the partition coordination module.

[0027] The deviation calibration unit reconstructs the temperature compensation coefficient of the temperature control probe based on the historical mean data and writes the reconstructed coefficient into the calibration parameter table of the dynamic temperature control model;

[0028] The redundant control unit switches to a heat distribution model based on the brake fluid circulation flow data of the preceding vehicle when detecting that the accuracy of the mechanical clearance sensor exceeds a limit, and feeds back the reconstructed distribution coefficient to the genetic algorithm optimization unit.

[0029] In a second aspect, the present invention provides a heating control method for a vehicle brake system, which is applied to a heating device for a vehicle brake system, comprising:

[0030] Obtain the temperature data of the front vehicle's cockpit and the hydraulic unit temperature and seal deformation data collected by the distributed temperature control probes of the rear vehicle's aluminum insulation compartment. The data are integrated into an initial temperature field dataset and input into the genetic algorithm optimization process.

[0031] Perform global optimization on the initial temperature field data set based on a genetic algorithm to generate an initial control parameter set including proportional coefficient and integration time and transmit it to the parameter calibration interface of the dynamic temperature control model;

[0032] Based on the real-time mechanical clearance change and the estimated brake fluid viscosity, the initial control parameter set is fine-tuned online through the dynamic temperature control model, and the calibrated pulse frequency weight and continuous heating power command are output to the partitioned collaborative control queue.

[0033] The pulse frequency weight is sent to the heating cable circuit of the auxiliary heating zone of the rear vehicle. At the same time, the historical temperature rise curve data stored in the self-test module is called up to dynamically adjust the maintenance power of the main heating zone based on the gradient power reduction mechanism and update the power allocation parameters of the dynamic temperature control model.

[0034] When abnormal impedance of the heating cable loop or excessive deviation of the temperature control probe is detected, the system switches to redundant heating mode and reconstructs the heat distribution coefficient of the dynamic temperature control model based on the brake fluid circulation flow data of the preceding vehicle. The reconstructed coefficient is fed back to the genetic algorithm optimization process as a constraint condition for the next generation parameter set.

[0035] Furthermore, the heating control method for a vehicle brake system of the present invention performs online fine-tuning of an initial control parameter set through a dynamic temperature control model based on real-time mechanical clearance change and estimated brake fluid viscosity, and outputs calibrated pulse frequency weights and continuous heating power instructions to a partitioned collaborative control queue, including:

[0036] According to the deformation of the composite insulation board of the aluminum insulation bin, the gap compensation algorithm of the dynamic temperature control model is called to dynamically correct the target temperature setting value of the main heating zone;

[0037] The brake fluid viscosity change rate is calculated in real time based on the temperature-viscosity relationship curve, and the heating power of the main heating area and the pulse duty cycle of the auxiliary heating area are synchronously adjusted through fuzzy control rules.

[0038] The revised target temperature setting value and pulse duty cycle parameter are written into the parameter constraint table of the genetic algorithm optimization unit to update the next generation control parameter set.

[0039] Furthermore, the heating control method for a vehicle brake system of the present invention calculates the brake fluid viscosity change rate in real time based on a temperature-viscosity relationship curve, and synchronously adjusts the heating power of the main heating zone and the pulse duty cycle of the auxiliary heating zone through fuzzy control rules, including:

[0040] When the feedback data of the mechanical gap sensor exceeds the threshold set by the self-test module, a pulse frequency weight increment instruction is sent to the delay compensation unit;

[0041] According to the correlation between the brake fluid viscosity change rate and the historical temperature rise curve, the continuous heating power slope of the main heating zone is dynamically adjusted and a power reduction instruction is generated;

[0042] The adjusted parameters are synchronously sent to the heating cable drive unit via the CAN bus, and the execution log is recorded in the historical database for genetic algorithm iteration.

[0043] Furthermore, the heating control method for a vehicle brake system of the present invention switches to a redundant heating mode when an abnormal heating cable loop impedance or an excessive temperature control probe deviation is detected. The method reconstructs the heat distribution coefficient of the dynamic temperature control model based on the brake fluid circulation flow data of the preceding vehicle, and feeds the reconstructed coefficient back into the genetic algorithm optimization process as the constraint conditions of the next-generation parameter set, including:

[0044] After activating the backup heating cable circuit, the optimal flow rate for transferring heat to the following vehicle is calculated based on the brake fluid circulation flow sensor data of the leading vehicle;

[0045] Reconstruct the heat loss compensation coefficient of the dynamic temperature control model based on the optimal flow rate and the deformation sensor data of the aluminum insulation chamber;

[0046] The reconstructed compensation coefficients are input into the model fine-tuning process to generate partition heating instructions suitable for the fault scenario and write them into the instruction queue.

[0047] Furthermore, the heating control method for a vehicle brake system of the present invention further includes:

[0048] The resistance change rate data of the heating cable loop is collected periodically. When three consecutive sampling values ​​are detected to be outside the tolerance range of the impedance detection unit, the redundant heating mode is triggered.

[0049] In redundant heating mode, based on the temperature stability parameters of historical average data, the deformation compensation algorithm is called to redistribute the power ratio between the main heating zone and the auxiliary heating zone;

[0050] The redistributed power ratio is integrated with the brake fluid circulation flow data of the preceding vehicle to generate a new heat distribution instruction which is transmitted to the partition coordination module via the vehicle bus.

[0051] Beneficial effects of the present invention:

[0052] The present invention effectively solves the thermal management problem of the split-body braking system in low-temperature environments through the coordinated optimization of multi-source sensor data fusion and closed-loop control architecture. Based on real-time data from distributed temperature control probes and mechanical gap sensors within the aluminum insulation chamber, the dynamic temperature control model combines a gap compensation algorithm with fuzzy control rules to achieve dynamic correction of the target temperature set value of the main heating zone and synchronous adjustment of the pulse duty cycle of the auxiliary heating zone, thereby suppressing the loss of heat conduction efficiency caused by the shrinkage and deformation of the composite insulation board. The initial temperature field data set is globally optimized through a genetic algorithm to generate a control parameter set suitable for low-temperature working conditions. The thermal inertia delay time is predicted by the delay compensation unit, and the triggering timing of the gradient power reduction mechanism is dynamically adjusted to optimize the matching between the regional heating strategy and energy consumption. In the redundant heating mode, the heat loss compensation coefficient is reconstructed based on the brake fluid circulation flow data of the preceding vehicle, and the zone heating instructions are generated in combination with the deformation sensor feedback to improve the temperature field stability in fault scenarios. The self-test module periodically collects loop impedance and probe deviation data. Through the iterative feedback mechanism of the historical database and parameter constraint table, a closed-loop control link is formed from anomaly detection, model reconstruction to genetic algorithm optimization, enhancing the system's anti-interference ability and long-term operation reliability in complex low-temperature environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0054] Figure 1 The present invention provides a flowchart of a method for controlling a heating device of a vehicle braking system.

[0055] Figure 2 A schematic diagram of the appearance of an aluminum insulation chamber for a method for controlling a heating device of a vehicle braking system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The technical solutions provided by each embodiment of the present invention are described in detail below in conjunction with the drawings. In order to better understand the purpose of the present invention, the present invention is further described in detail below.

[0057] In a first aspect, the present invention provides a heating device for a vehicle brake system, comprising:

[0058] The split heating module is configured to install a first heat exchange unit in the front vehicle brake assembly that is linked to the thermal environment of the cockpit, and to construct an aluminum insulation chamber in the rear vehicle brake system. The aluminum insulation chamber integrates multi-zone heating cables, distributed temperature control probes, and mechanical gap sensors to generate initial thermal distribution parameters and transmit them to the data fusion control module;

[0059] The data fusion control module is connected to the split heating module and is used to receive hydraulic unit temperature data, seal deformation data, and ambient temperature data from the distributed temperature control probes, and access the brake pressure history parameters of the vehicle bus. Based on the hydraulic unit temperature data, seal deformation data, and ambient temperature data, a dynamic temperature control model is constructed, and closed-loop control parameters including zone heating power instructions are output to the zone collaboration module.

[0060] The partition coordination module is connected to the data fusion control module to divide the aluminum insulation chamber into the main heating zone and the auxiliary heating zone. It receives closed-loop control parameters and implements the continuous heating strategy and pulse heating frequency adjustment. The main heating zone controls the power output of the heating tape based on the continuous heating strategy, and the auxiliary heating zone adjusts the pulse heating frequency based on the real-time feedback data of the mechanical gap sensor.

[0061] The self-check module is connected to the partition coordination module and periodically collects the impedance of the heating cable loop and the calibration deviation data of the temperature control probe. When an impedance anomaly or an excessive calibration deviation is detected, abnormal data including the fault area identification is generated and transmitted to the data fusion control module;

[0062] Among them, the data fusion control module iteratively optimizes the control parameters of the dynamic temperature control model based on the initial heat distribution parameters and abnormal data, and sends the updated closed-loop control parameters to the partition collaboration module, forming a closed-loop control link from data acquisition, model optimization to instruction execution.

[0063] Specifically, the present invention is used for a heating device of a vehicle braking system, and the data fusion control module includes:

[0064] A genetic algorithm optimization unit is used to generate an initial control parameter set based on the initial temperature field data set of the distributed temperature control probe and the deformation sensor data of the aluminum insulation chamber, and transmit the initial control parameter set to the model fine-tuning unit;

[0065] The model fine-tuning unit receives the real-time change of the mechanical clearance sensor and the estimated value of the brake fluid viscosity, performs online calibration of the initial control parameter set based on the dynamic temperature control model, and outputs the calibrated pulse frequency weight to the pulse heating controller of the auxiliary heating zone;

[0066] The delay compensation unit uses the historical temperature rise curve data stored in the self-test module to predict the thermal inertia delay time, dynamically adjusts the triggering timing of the gradient power reduction mechanism, and sends the adjusted timing instructions to the heating belt drive circuit of the main heating zone through the CAN bus;

[0067] Among them, the pulse frequency weight output by the model fine-tuning unit and the timing instructions of the delay compensation unit together constitute the closed-loop control parameters, driving the partition collaboration module to execute the heating strategy.

[0068] Specifically, the present invention is used for a heating device of a vehicle brake system, and the delay compensation unit performs the following operations:

[0069] When the hydraulic unit temperature is lower than the critical threshold, a high-power rapid heating command is sent to the heating cable drive circuit of the main heating zone;

[0070] After the temperature reaches the preset safety range, the thermal inertia delay time is calculated based on the thermal inertia parameters of the dynamic temperature control model and the slope of the historical temperature rise curve, and the gradient reduction power coefficient is superimposed to generate the maintenance power instruction;

[0071] The maintenance power instruction is used as part of the closed-loop control parameters and is written into the instruction queue of the partition coordination module synchronously with the pulse frequency adjustment instruction of the auxiliary heating zone.

[0072] Specifically, the present invention is a heating device for a vehicle braking system, wherein the model fine-tuning unit comprises:

[0073] The deformation compensation submodule uses the gap compensation algorithm of the dynamic temperature control model to correct the target temperature setting value of the main heating zone based on the deformation of the composite insulation board of the aluminum insulation chamber;

[0074] The viscosity feedback submodule calculates the brake fluid viscosity in real time based on the temperature-viscosity relationship curve, and dynamically adjusts the continuous heating power of the main heating zone and the pulse heating duty cycle of the auxiliary heating zone through fuzzy control rules;

[0075] Among them, the gap compensation coefficient output by the deformation compensation submodule and the viscosity adjustment parameter of the viscosity feedback submodule are input into the genetic algorithm optimization unit together as the optimization boundary conditions of the next generation control parameter set.

[0076] Specifically, the present invention is a heating device for a vehicle braking system, wherein the self-test module comprises:

[0077] The impedance detection unit periodically collects the resistance change rate of the heating cable loop. When abnormal resistance fluctuations are detected, it sends a backup loop activation instruction to the partition coordination module.

[0078] The deviation calibration unit reconstructs the temperature compensation coefficient of the temperature control probe based on the historical mean data and writes the reconstructed coefficient into the calibration parameter table of the dynamic temperature control model;

[0079] The redundant control unit switches to a heat distribution model based on the brake fluid circulation flow data of the preceding vehicle when detecting that the accuracy of the mechanical clearance sensor exceeds a limit, and feeds back the reconstructed distribution coefficient to the genetic algorithm optimization unit.

[0080] See also Figure 1 In a second aspect, the present invention provides a heating control method for a vehicle brake system, which is applied to a heating device for a vehicle brake system, comprising:

[0081] Step S101: Acquire the temperature data of the driver's cabin of the leading vehicle and the temperature and deformation data of the hydraulic unit collected by the distributed temperature control probe of the aluminum insulation compartment of the trailing vehicle, integrate the data into an initial temperature field data set and input it into the genetic algorithm optimization process;

[0082] In the heating control method of the present invention, step S101 provides reliable input conditions for genetic algorithm optimization through the coordinated collection and preprocessing of multi-source sensor data. The leading vehicle's cabin temperature data is collected in real time by a temperature sensor integrated into the cabin's air conditioning vents. The sensor uses a thermocouple to measure air temperature, and the data is transmitted to the trailing vehicle's control module via an onboard bus. Distributed temperature control probes, located within the trailing vehicle's aluminum insulation compartment, are layered along the hydraulic unit piping, seal mounting points, and brake disc surface. Platinum resistance temperature sensors are used to collect hydraulic unit surface temperature, and strain gauge sensors are used to monitor seal deformation and displacement. The data sampling frequency is dynamically adjusted based on changes in brake pressure.

[0083] The collected multi-source data is then integrated into an initial temperature field dataset after timestamp alignment and noise filtering. The timestamp alignment module uses a GPS-synchronized clock signal to ensure temporal consistency between the leading and following vehicle data. Noise filtering uses a sliding window mean algorithm to eliminate signal jumps caused by environmental electromagnetic interference. The integrated dataset, consisting of a spatial temperature distribution matrix, deformation displacement vectors, and ambient temperature scalars, is mapped into a three-dimensional temperature field model, serving as the physical field input for genetic algorithm optimization. After conversion to a standardized format, the dataset is written into the data buffer of the genetic algorithm optimization unit, completing the unified interface adaptation of multi-source heterogeneous data.

[0084] The logic behind constructing the initial temperature field dataset supports subsequent control parameter optimization. The leading vehicle's cabin temperature data reflects the heat source input efficiency of the heat exchange unit, while the trailing vehicle's hydraulic unit temperature and seal deformation data characterize the brake system's real-time thermal load. The data integration process uses spatial interpolation algorithms to fill in sensor coverage blind spots. For example, Kriging interpolation is used to generate temperature estimates for areas within the aluminum insulation compartment where no probes are deployed. When this integrated dataset is input into the genetic algorithm optimization process, the algorithm uses key node data from the temperature field model to generate an initial set of control parameters suitable for low-temperature scenarios, providing benchmark parameters for the online calibration of the dynamic temperature control model.

[0085] The aforementioned steps form a closed-loop technology loop through a hierarchical process of data acquisition, preprocessing, and model input. Multi-sensor deployment addresses spatial coverage issues within the split vehicle body, data integration eliminates discrepancies in heterogeneous data, and the temperature field model provides physical constraints for algorithm optimization. The data and command flows between these links operate collaboratively via the vehicle bus and data buffer queues, enabling the genetic algorithm to generate a globally optimal control strategy based on real-world operating data, laying the foundation for subsequent zoned heating control.

[0086] Step S102: performing global optimization on the initial temperature field data set based on a genetic algorithm to generate an initial control parameter set including a proportional coefficient and an integration time, and transmitting the set to a parameter calibration interface of the dynamic temperature control model;

[0087] In the heating control method of the present invention, step S102 generates an initial control strategy adapted to low-temperature scenarios through the global optimization and parameter adaptation mechanism of the genetic algorithm. After receiving the initial temperature field data set, the genetic algorithm optimization unit constructs a multi-objective fitness function to comprehensively evaluate temperature uniformity, energy efficiency, and response speed indicators. The fitness function maps the spatial temperature distribution matrix in the temperature field data set into a thermal conductivity efficiency score, converts the seal deformation and displacement data into a mechanical stability weight, and uses the ambient temperature scalar as a heat loss correction factor to form a multi-dimensional optimization target space. The algorithm screens the parent parameter combination through a roulette wheel selection strategy, performs a crossover mutation operation to generate a new generation parameter set, and iterates the optimization until the fitness score converges.

[0088] The generated initial control parameter set includes a proportional coefficient, integral time, and fuzzy rule weights, corresponding to the error adjustment rate, cumulative deviation compensation, and nonlinear control threshold in the dynamic temperature control model, respectively. The parameter set is encapsulated using a standardized format conversion module to match the parameter calibration interface protocol of the dynamic temperature control model. The calibration interface uses a bidirectional verification mechanism to verify the compatibility of the parameter value range with the model input constraints. For example, the proportional coefficient must not exceed the maximum thermal stress threshold of the aluminum insulation bin material. Once verified, the parameter set is written to the parameter storage area of ​​the dynamic temperature control model via a high-speed data bus, completing the data connection between the algorithm layer and the model layer.

[0089] During parameter transmission, the calibration interface simultaneously generates metadata tags, recording the optimized version of the parameter set, timestamp, and associated temperature field characteristics. This metadata is transmitted via the vehicle bus to the self-test module's historical database, serving as a reference for subsequent model fine-tuning and anomaly diagnosis. The global optimization results of the initial control parameter set provide a baseline input for the dynamic temperature control model, enabling rapid online calibration based on real-time operating data. This reduces control lag during cold start and improves the thermal management response efficiency of the braking system at low temperatures.

[0090] The above steps form a closed technical loop through a three-level process consisting of objective function construction, parameter optimization, and interface adaptation: temperature field data drives algorithm optimization, parameter set encapsulation ensures model compatibility, and metadata recording supports iterative traceability. Each step relies on a collaborative architecture of genetic algorithms and dynamic temperature control models to solve the control parameter initialization challenge during the initial heating phase of split-body vehicles, providing an optimized starting point for multi-zone coordinated heating.

[0091] Step S103: Based on the real-time mechanical clearance change and the estimated brake fluid viscosity, the initial control parameter set is fine-tuned online using the dynamic temperature control model, and the calibrated pulse frequency weight and continuous heating power command are output to the partitioned collaborative control queue.

[0092] In the heating control method of the present invention, step S103 uses a dynamic temperature control model to calibrate the initial control parameters in real time, dynamically matching the heating strategy with changing operating conditions. Real-time mechanical gap changes are collected by distributed mechanical gap sensors within the aluminum insulation chamber. These sensors use the Hall effect principle to measure the gap increment caused by the shrinkage of the composite insulation board. This data is filtered through a Kalman filter to eliminate measurement noise and then fed into the dynamic temperature control model. The estimated brake fluid viscosity is calculated in real time using the temperature-viscosity relationship curve. Combined with temperature feedback data from the main heating zone, a polynomial fitting algorithm is used to generate a viscosity change rate curve, which serves as an input parameter for model fine-tuning.

[0093] The dynamic temperature control model calls the gap compensation algorithm and fuzzy control rules to perform online fine-tuning. The gap compensation algorithm dynamically corrects the target temperature setting value of the main heating zone based on the mapping relationship between the deformation of the composite insulation board and the heat conduction efficiency. For example, for every 0.5mm increase in deformation, the target temperature increases by 1.5°C to compensate for heat loss. The fuzzy control rule divides the viscosity change rate into three control domains of "low-medium-high", adjusts the rising slope of the continuous heating power of the main heating zone according to the preset fuzzy inference table, and proportionally adjusts the pulse duty cycle of the auxiliary heating zone at the same time to prevent overheating and deformation of the seal due to sudden changes in viscosity. The calibrated pulse frequency weight and continuous power instruction are converted into standardized control instructions through the data encapsulation module and written into the partition collaborative control queue according to priority.

[0094] During the calibration process, the revised target temperature setpoint and pulse duty cycle parameters are synchronously written into the parameter constraint table of the genetic algorithm optimization unit. The constraint table records the relationship between the current control parameters and the temperature field distribution. For example, when the temperature fluctuation in the main heating zone exceeds ±2°C, the constraint table automatically limits the maximum adjustment range of the pulse duty cycle to ±15%. Based on the boundary conditions in the constraint table, the genetic algorithm recalculates the combination of proportional coefficient and integration time in the next generation of parameter optimization, forming a technical closed loop from model fine-tuning to algorithm iteration. The calibrated control instructions are sent to the heating cable drive unit in real time via the CAN bus, and the execution status log is encrypted and stored in a historical database, providing data support for redundant control and parameter optimization.

[0095] The above steps achieve precise generation of heating commands for each zone through a multi-level collaboration of sensor data acquisition, model algorithm invocation, and parameter constraint updates. Mechanical clearance deformation data drives the temperature compensation logic, while the viscosity change rate triggers the fuzzy control strategy. The parameter constraint mechanism ensures the stability of the control commands, ultimately resolving the heating lag and energy consumption redundancy issues of split-type brake systems at low temperatures.

[0096] Step S104: The pulse frequency weight is sent to the heating cable circuit of the auxiliary heating zone of the rear vehicle. At the same time, the historical temperature rise curve data stored in the self-test module is called up to dynamically adjust the maintenance power of the main heating zone based on the gradient power reduction mechanism and update the power allocation parameters of the dynamic temperature control model.

[0097] In the heating control method of the present invention, step S104 dynamically optimizes the zone-specific heating strategy through a coordinated mechanism of command issuance and power adjustment. Pulse frequency weights are encapsulated into control command packets via the CAN bus protocol. These packets include the zone code, frequency value, and timestamp information. These packets are prioritized and transmitted to the heating cable drive unit in the auxiliary heating zone of the rear vehicle. After parsing the command packets, the drive unit adjusts the heating cable operating frequency according to a preset pulse waveform template. For example, the weighted values ​​are mapped to pulse signals ranging from 0.5Hz to 5Hz to match the real-time feedback rhythm of the mechanical gap sensor and mitigate the risk of localized overheating caused by gap deformation.

[0098] When the self-test module calls historical temperature rise curve data, it uses a sliding window algorithm to extract the average temperature rise rate within the last 30 minutes. Combined with the actual temperature value of the current main heating zone, the gradient power reduction mechanism is used to calculate the adjustment slope for maintaining the power. The gradient power reduction mechanism is based on a thermal inertia delay time prediction model. For example, when the average temperature rise rate is lower than 80% of the historical peak value, the heating power is gradually reduced by 0.2°C / min. At the same time, the adjusted slope value is written into the power allocation parameter table of the dynamic temperature control model. After the parameter table is updated, the model recalculates the power allocation weights for the main heating zone and the auxiliary heating zone, generates a new instruction queue, and overwrites the old parameters to avoid control instruction failure due to parameter conflicts.

[0099] After the updated power distribution parameters are verified for logical consistency by the data verification module, they are synchronized to the historical database of the genetic algorithm optimization unit. The database records the parameter version number, update timestamp and associated temperature field characteristics as a reference for subsequent redundant control or parameter iteration. The maintenance power adjustment results of the main heating zone are fed back to the self-test module in real time, triggering the dynamic refresh of the temperature rise curve data, forming a closed-loop link from instruction execution to data update. The above steps solve the energy consumption redundancy problem of the split body during the continuous heating stage through the hierarchical processing of instruction issuance, power adjustment and parameter refresh, thereby improving the stability and energy efficiency of temperature field control.

[0100] Step S105: When an abnormal impedance of the heating cable loop is detected or the temperature control probe deviation exceeds the limit, the redundant heating mode is switched to and the heat distribution coefficient of the dynamic temperature control model is reconstructed based on the brake fluid circulation flow data of the preceding vehicle. The reconstructed coefficient is fed back to the genetic algorithm optimization process as a constraint condition for the next generation parameter set.

[0101] In the heating control method of the present invention, step S105 solves the problem of thermal management fault-tolerant control of the split-body brake system under abnormal working conditions through a redundant heating mode and a dynamic parameter reconstruction mechanism. When the self-test module detects that the impedance of the heating cable circuit is abnormal or the calibration deviation of the temperature control probe exceeds the preset threshold, the redundant control unit immediately triggers the hardware switching logic: the backup heating cable circuit is activated through the relay control circuit, and the real-time data of the brake fluid circulation flow sensor of the leading vehicle is read at the same time. The flow sensor uses a turbine flowmeter to collect flow rate information. The data is filtered through a sliding window and then input into the heat distribution model to calculate the optimal flow rate for transferring heat to the following vehicle. The calculation of the optimal flow rate is combined with the heat loss coefficient under historical fault scenarios. For example, when the flow rate exceeds the safety threshold, the heat transfer rate is automatically limited to avoid excessive thermal stress in the brake fluid pipeline.

[0102] When reconstructing the heat distribution coefficient of the dynamic temperature control model, the system synchronously calls the shrinkage deformation data collected by the aluminum insulation chamber deformation sensor. The deformation data and the optimal flow rate are jointly analyzed through a thermodynamic coupling model to calculate the influence weight of the composite insulation board deformation on the heat conduction path. The model dynamically corrects the gradient parameters of the heat loss compensation coefficient based on the influence weight. For example, for every 1mm increase in deformation, the compensation coefficient is increased by 0.3% to offset the loss of thermal efficiency caused by structural deformation. The corrected compensation coefficient is written into the fine-tuning module of the dynamic temperature control model through the model interface, replacing the original parameter set of the fault area and generating a zoned heating instruction suitable for the current abnormal scenario.

[0103] Generated instructions are written into the instruction queue according to priority encoding. High-priority instructions are sent to the heating cable drive unit in real time via the CAN bus, while low-priority instructions are temporarily stored in a buffer queue and executed in batches according to temperature control requirements. During execution, temperature response data and energy consumption indicators are synchronously recorded in a historical database and converted into constraint parameters for the genetic algorithm optimization unit through a feature extraction module. The constraint parameters define the search boundaries for the next generation of control parameter sets, for example, limiting the power adjustment range of the main heating zone to within the safety threshold of the fault scenario. The reconstructed heat distribution coefficient and historical data together form the input conditions for algorithm iteration, forming a closed-loop control chain from abnormal response to parameter optimization, improving the system's robustness and temperature stability under low-temperature conditions.

[0104] The above steps form a closed technical loop through a hierarchical process of anomaly detection, model reconstruction, and command execution: hardware switching ensures basic heating functionality, parameter reconstruction optimizes heat distribution strategies, and data feedback drives algorithm iteration. Each link relies on the data fusion hub of the dynamic temperature control model to achieve cross-module collaboration, resolving the issues of temperature field control and energy consumption imbalance in fault scenarios in existing solutions, thereby enhancing the fault tolerance and long-term reliability of the split braking system.

[0105] The heating control method for a vehicle brake system provided by the present invention achieves precise temperature control of a split-body brake system through multi-source data fusion and a closed-loop control mechanism. The specific implementation process is as follows:

[0106] First, the front vehicle's cabin temperature sensor and the rear vehicle's aluminum insulation compartment's distributed temperature control probes collect real-time data on the hydraulic unit's surface temperature, seal deformation and displacement, and mechanical clearance changes. After timestamp alignment and noise filtering, these data are integrated into an initial temperature field dataset, which serves as input for the genetic algorithm optimization. This initial dataset includes spatial temperature distribution characteristics and deformation-related parameters, providing physical field boundary constraints for subsequent global optimization.

[0107] When performing a global optimization search for the initial temperature field dataset using a genetic algorithm, a multi-objective fitness function is employed to evaluate the temperature control performance of different control parameter combinations. This fitness function comprehensively considers temperature uniformity, energy efficiency, and response speed. Through a crossover and mutation operation, an initial control parameter set, including the proportional coefficient, integration time, and fuzzy rule weights, is generated. The optimized parameter set is transmitted via the vehicle bus to the parameter calibration interface of the dynamic temperature control model, completing the data connection between the algorithm and model layers.

[0108] The dynamic temperature control model receives real-time mechanical clearance sensor data and estimated brake fluid viscosity, initiating online fine-tuning. The model invokes a clearance compensation algorithm to dynamically adjust the target temperature setpoint for the main heating zone based on the deformation of the aluminum insulation compartment's composite insulation panels. Simultaneously, based on the temperature-viscosity relationship curve, the model uses fuzzy control rules to synchronously adjust the continuous heating power of the main heating zone and the pulse duty cycle of the auxiliary heating zone. The calibrated pulse frequency weights and continuous heating power commands are written to the partitioned collaborative control queue to ensure that command issuance timing matches execution priority.

[0109] During the command execution phase, the pulse frequency weight is transmitted via the CAN bus to the heating cable drive unit in the auxiliary heating zone of the rear vehicle, triggering pulse heating frequency adjustment. The main heating zone's maintenance power is dynamically adjusted based on historical temperature rise curve data stored in the self-test module. A gradient power reduction mechanism is employed to gradually reduce the heating power slope based on the predicted temperature rise rate to avoid temperature overshoot. The dynamic temperature control model simultaneously updates the power allocation parameters and feeds the actual temperature control results back to the genetic algorithm optimization unit, forming the basis for parameter iteration.

[0110] If the self-test module detects abnormal impedance in the heating cable circuit or an excessive temperature probe calibration deviation, the system switches to redundant heating mode. In this mode, the optimal heat transfer flow rate is calculated based on data from the preceding vehicle's brake fluid circulation flow sensor. The heat loss compensation coefficients of the dynamic temperature control model are reconstructed using feedback from the aluminum insulation chamber's deformation sensor. These reconstructed compensation coefficients are input into the model fine-tuning process, generating zoned heating instructions appropriate for the fault scenario. These instructions are then distributed to the corresponding heating zones via the instruction queue. Temperature stability data generated during the redundant control process is synchronously written to a historical database for optimizing the robustness boundary conditions of the next-generation control parameter set.

[0111] Each step interacts in a closed-loop via a data bus and control instructions: initial data collection provides input for algorithm optimization, model fine-tuning results drive execution-level operations, anomaly detection data triggers redundant control, and ultimately feeds back into the parameter iteration process. This hierarchical control architecture, from data fusion and model optimization to execution feedback, effectively solves the thermal management coordination challenges of split-body vehicles at low temperatures, improving system reliability and energy efficiency.

[0112] Specifically, the heating control method for a vehicle brake system of the present invention fine-tunes the initial control parameter set online through a dynamic temperature control model based on the real-time mechanical clearance change and the estimated brake fluid viscosity, and outputs the calibrated pulse frequency weight and continuous heating power command to the partitioned collaborative control queue, including:

[0113] According to the deformation of the composite insulation board of the aluminum insulation bin, the gap compensation algorithm of the dynamic temperature control model is called to dynamically correct the target temperature setting value of the main heating zone;

[0114] The brake fluid viscosity change rate is calculated in real time based on the temperature-viscosity relationship curve, and the heating power of the main heating area and the pulse duty cycle of the auxiliary heating area are synchronously adjusted through fuzzy control rules.

[0115] The revised target temperature setting value and pulse duty cycle parameter are written into the parameter constraint table of the genetic algorithm optimization unit to update the next generation control parameter set.

[0116] The present invention is used in a heating control method for a vehicle braking system. The online fine-tuning process of the dynamic temperature control model achieves precise temperature control through multi-dimensional parameter collaborative optimization. In specific implementation, the change in the mechanical gap caused by the low-temperature deformation of the composite insulation board of the aluminum insulation chamber is collected in real time by a distributed sensor and input into the gap compensation algorithm of the dynamic temperature control model. Based on the mapping relationship between the deformation amount and the heat conduction efficiency, the algorithm dynamically corrects the target temperature setting value of the main heating zone. For example, when the gap of the composite insulation board expands due to cold shrinkage, the target temperature is automatically increased to compensate for heat loss and maintain temperature balance between the hydraulic unit and the brake fluid pipeline.

[0117] The estimated brake fluid viscosity is calculated in real time using the temperature-viscosity relationship curve. Combined with temperature feedback data from the primary heating zone, this triggers fuzzy control rules to coordinate adjustments to the heating power and pulse duty cycle. Based on the magnitude and trend of viscosity deviation, the fuzzy controller divides the control domains into "low viscosity - rapid heating" and "high viscosity - slow-release heating." It dynamically adjusts the output slope of the continuous heating power in the primary heating zone and simultaneously adjusts the pulse duty cycle of the auxiliary heating zone according to a preset ratio to prevent further deformation of the seal due to localized overheating. The adjusted parameters are written to the partitioned collaborative control queue via the vehicle bus and dispatched in batches according to command priority.

[0118] After verification, the revised target temperature setpoint and pulse duty cycle parameters are written into the parameter constraint table of the genetic algorithm optimization unit. The constraint table records the relationship between the current control parameters and the temperature field distribution, serving as the optimization boundary conditions for the next generation of control parameter sets. For example, when the temperature fluctuation in the main heating zone exceeds a preset threshold, the constraint table automatically limits the maximum adjustment range of the pulse duty cycle to prevent system oscillation caused by excessive correction. Based on the boundary conditions in the constraint table, the genetic algorithm recalculates the optimal combination of proportional coefficient and integration time, iteratively generates an updated parameter set adapted to low-temperature scenarios, and completes the closed-loop control process from model fine-tuning to algorithm optimization.

[0119] These steps form a closed technical loop through the hierarchical transmission of data flows and control instructions: mechanical clearance data drives temperature compensation, viscosity changes trigger fuzzy control, and parameter correction results feed back into genetic algorithm optimization. Data interaction between these links is uniformly scheduled through a dynamic temperature control model, achieving a dynamic balance between regional heating strategies and global energy consumption targets, resolving the conflict between temperature lag and local overheating in existing solutions.

[0120] Specifically, the heating control method for a vehicle brake system of the present invention calculates the brake fluid viscosity change rate in real time based on a temperature-viscosity relationship curve, and synchronously adjusts the heating power of the main heating zone and the pulse duty cycle of the auxiliary heating zone through fuzzy control rules, including:

[0121] When the feedback data of the mechanical gap sensor exceeds the threshold set by the self-test module, a pulse frequency weight increment instruction is sent to the delay compensation unit;

[0122] According to the correlation between the brake fluid viscosity change rate and the historical temperature rise curve, the continuous heating power slope of the main heating zone is dynamically adjusted and a power reduction instruction is generated;

[0123] The adjusted parameters are synchronously sent to the heating cable drive unit via the CAN bus, and the execution log is recorded in the historical database for genetic algorithm iteration.

[0124] In the heating control method of the present invention, a fuzzy control strategy based on the temperature-viscosity relationship curve achieves dynamic optimization of heating parameters through the collaboration of multi-source data. When the mechanical clearance sensor detects that the mating clearance value exceeds the deformation threshold preset by the self-test module, the system automatically triggers the abnormal response mechanism: the self-test module calls the clearance safety range data in the historical operating condition database, compares the deviation rate of the current clearance increment with the preset threshold, generates a pulse frequency weight increment instruction, and transmits it to the delay compensation unit via the control bus. This threshold is dynamically set based on the thermal expansion coefficient of the aluminum insulation bin material and historical deformation data to avoid the risk of mechanical interference caused by low-temperature embrittlement.

[0125] The brake fluid viscosity change rate is calculated by fitting real-time data collected by the temperature sensor with the temperature-viscosity curve. Combined with records of similar operating conditions from a historical temperature rise curve database, the correlation between viscosity change trends and temperature rise rates is analyzed. If the viscosity drop rate exceeds the historical average, the dynamic temperature control model activates a power reduction protection mechanism. Based on the viscosity-power mapping table in the fuzzy control rules, the rising slope of the continuous heating power in the main heating zone is reduced according to a preset gradient, and the adjusted slope value is simultaneously written to the power reduction command queue. The trigger threshold for the power reduction command is linked to the standard deviation of the historical temperature rise curve to prevent misadjustments caused by sudden viscosity fluctuations.

[0126] The adjusted heating power parameters and pulse frequency weights are packaged into a control instruction set via the CAN bus protocol and synchronously distributed to the heating cable drive units in the primary and auxiliary heating zones in order of priority. The instruction set includes timestamp identification and zone coding, ensuring that the timing control of the multi-zone heaters precisely matches the rhythm of mechanical gap changes. During execution, temperature response data, energy consumption indicators, and instruction execution status are generated into an operation log, which is encrypted and stored in a historical database in time series. A feature extraction module converts this log data into optimization parameters recognizable by a genetic algorithm. This is used to calculate the fitness function of the next-generation control parameter set, completing a closed-loop data loop from execution feedback to algorithm iteration.

[0127] These steps form a closed-loop technology loop through a three-tiered processing mechanism: abnormal response, trend analysis, and data logging. Clearance anomalies trigger immediate control commands, viscosity trend analysis drives power protection strategies, and execution data feeds back into algorithm optimization. These steps, leveraging the data dispatching hub of the dynamic temperature control model, coordinate commands, resolving the mismatch between mechanical deformation and thermal management response in existing solutions and improving the thermal stability and control accuracy of the braking system at low temperatures.

[0128] Specifically, the present invention is a heating control method for a vehicle brake system. When an abnormal heating cable loop impedance or an excessive temperature control probe deviation is detected, the method switches to a redundant heating mode and reconstructs the heat distribution coefficient of a dynamic temperature control model based on the brake fluid circulation flow data of the preceding vehicle. The reconstructed coefficient is fed back into the genetic algorithm optimization process as a constraint condition for the next generation parameter set, including:

[0129] After activating the backup heating cable circuit, the optimal flow rate for transferring heat to the following vehicle is calculated based on the brake fluid circulation flow sensor data of the leading vehicle;

[0130] Reconstruct the heat loss compensation coefficient of the dynamic temperature control model based on the optimal flow rate and the deformation sensor data of the aluminum insulation chamber;

[0131] The reconstructed compensation coefficients are input into the model fine-tuning process to generate partition heating instructions suitable for the fault scenario and write them into the instruction queue.

[0132] In the heating control method of the present invention, the switching of redundant heating modes and the reconstruction of the dynamic temperature control model realize thermal management fault-tolerant control under fault scenarios through multi-source data linkage. When the self-test module detects that the impedance of the heating tape loop is abnormal or the calibration deviation of the temperature control probe exceeds the preset safety range, the redundant control module immediately triggers the hardware switching logic of the backup heating tape loop. The activation instruction of the backup loop is sent to the drive unit of the aluminum insulation compartment of the rear vehicle through the redundant control bus, and at the same time, the real-time flow rate data of the brake fluid circulation flow sensor of the front vehicle is read, and the optimal flow rate for delivering heat to the rear vehicle is calculated based on the flow-heat transfer efficiency model. The calculation process of the optimal flow rate is combined with the heat loss coefficient under historical fault scenarios to avoid excessive thermal stress in the brake fluid circulation pipeline due to excessive flow rate.

[0133] When reconstructing the heat loss compensation coefficient of the dynamic temperature control model, the system synchronously calls the shrinkage deformation data of the aluminum insulation warehouse collected by the deformation sensor. The deformation data and the optimal flow rate are coupled and calculated through a thermodynamic simulation model to analyze the weight of the influence of the deformation of the composite insulation board on the heat conduction path, and dynamically correct the gradient parameters of the heat loss compensation coefficient. The corrected compensation coefficient is input into the fine-tuning module of the dynamic temperature control model through the model interface, replacing the original parameter set of the fault area. Based on the matching degree between the compensation coefficient and the current temperature field distribution data, the fine-tuning module generates a zone heating instruction suitable for the fault scenario. The instruction includes the power reduction slope limit of the main heating zone and the pulse frequency safety threshold of the auxiliary heating zone.

[0134] Generated zone heating commands are written into a command queue according to priority coding. The queue management module sorts these commands based on command type and execution urgency. High-priority commands are sent to the heating cable drive unit in real time via the CAN bus, while low-priority commands are temporarily stored in a buffer queue awaiting execution. Temperature response data and energy consumption metrics generated during command execution are synchronously recorded in a historical database. After feature extraction, these data are converted into constraint parameters for the genetic algorithm optimization unit. Constraint parameters are used to limit the search space for the next generation of control parameter sets, for example, limiting the power adjustment range of the main heating zone to a safety threshold in a fault scenario, thereby improving the stability of the redundant control process.

[0135] These steps form a closed-loop technology loop through a three-level fault-tolerance mechanism consisting of hardware switching, model reconstruction, and instruction scheduling. Fault detection triggers backup circuit activation and data reconstruction, model fine-tuning generates a safe heating strategy, and execution feedback optimizes algorithm parameter boundaries. These steps leverage the data fusion hub of the dynamic temperature control model to achieve cross-module collaboration, resolving the issue of temperature field uncontrollability in fault scenarios in existing solutions and enhancing the robustness of the split-type braking system in low-temperature environments.

[0136] Specifically, the heating control method for a vehicle brake system of the present invention further includes:

[0137] The resistance change rate data of the heating cable loop is collected periodically. When three consecutive sampling values ​​are detected to be outside the tolerance range of the impedance detection unit, the redundant heating mode is triggered.

[0138] In redundant heating mode, based on the temperature stability parameters of historical average data, the deformation compensation algorithm is called to redistribute the power ratio between the main heating zone and the auxiliary heating zone;

[0139] The redistributed power ratio is integrated with the brake fluid circulation flow data of the preceding vehicle to generate a new heat distribution instruction which is transmitted to the partition coordination module via the vehicle bus.

[0140] In the heating control method of the present invention, the triggering of the redundant heating mode and the optimization of power allocation achieve adaptive thermal management under abnormal operating conditions through the collaboration of multi-source data. When periodically collecting the resistance change rate data of the heating cable loop, the impedance detection unit uses a sliding window averaging algorithm to process three consecutive sampling values, and the window width is dynamically adjusted based on the historical fault frequency. When the sampled value exceeds the tolerance range, the system calls the resistance-temperature correlation model in the historical database to verify the validity of the abnormal data and then trigger the redundant heating mode. The tolerance range is set based on the thermal resistance characteristics of the aluminum insulation bin material and the heating cable aging curve to prevent false triggering due to occasional interference.

[0141] After redundant heating mode is activated, the self-test module extracts temperature stability parameters from the historical database, including the standard deviation of the temperature rise rate in the primary heating zone and the pulse frequency fluctuation coefficient in the auxiliary heating zone. The deformation compensation algorithm dynamically calculates power allocation weights based on the deformation data of the composite insulation board in the current aluminum insulation chamber, combined with the temperature stability parameters. For example, if an increase in the shrinkage of the composite insulation board is detected, the algorithm automatically increases the power share of the primary heating zone to compensate for the loss of heat conduction efficiency, while limiting the maximum pulse frequency in the auxiliary heating zone to prevent deformation accumulation in the seal due to local overheating.

[0142] The redistributed power ratio is integrated with the brake fluid circulation flow data of the leading vehicle through a thermodynamic coupling model. Based on the correlation between the brake fluid flow rate data of the leading vehicle and the heat loss coefficient of the trailing vehicle, the model makes a weighted correction to the power allocation weights of the primary and auxiliary heating zones. The fused data generates a heat allocation instruction set with a zone code and timestamp. This instruction set is encapsulated via the vehicle bus protocol and transmitted to the partition coordination module. During bus transmission, a priority scheduling mechanism is implemented, with high-priority instructions being issued in real time to the heating cable drive unit. Low-priority instructions are temporarily stored in a buffer queue and executed in batches according to temperature control requirements. The execution result data is synchronously written to a historical database, providing constraint parameters for genetic algorithm optimization, forming a closed-loop control chain from anomaly detection to parameter iteration.

[0143] The above steps achieve a closed-loop technology through a hierarchical process of anomaly verification, weight optimization, and command scheduling: resistance anomalies trigger mode switching, historical data guides power allocation, and data fusion generates control commands. Each link leverages the data hub of the dynamic temperature control model to achieve cross-module collaboration, resolving the redundant control response lag and energy efficiency imbalances in existing solutions, and improving the temperature field control accuracy and system reliability of the split brake system under complex operating conditions.

[0144] The various technical features in the technical solution of the present invention are explained as follows:

[0145] Split Heating Module: A heat exchange unit linked to the thermal environment of the cockpit is installed in the front vehicle's brake assembly, utilizing waste heat from the cockpit to improve the efficiency of the front vehicle's braking system. An aluminum insulation compartment is constructed in the rear vehicle's brake system, integrating multi-zone heating cables, distributed temperature control probes, and mechanical gap sensors. Physical isolation and a flexible thermally conductive layer are designed to adapt to the dynamic separation structure of the split vehicle body, resolving the issue of differing heat conduction paths between the front and rear vehicles.

[0146] The data fusion control module receives data on hydraulic unit temperature and seal deformation from distributed temperature control probes, as well as historical brake pressure parameters from the vehicle bus. It integrates this multi-source sensor data to build a dynamic temperature control model. Based on fuzzy control rules and genetic algorithm optimization, this model generates zoned heating power commands, dynamically matching the heating strategy to real-time operating conditions. For example, it adjusts pulse frequency weights based on changes in mechanical clearance to mitigate temperature field imbalances.

[0147] Partitioned collaborative module: The aluminum insulation chamber is divided into a main heating zone and an auxiliary heating zone. The main heating zone implements a continuous heating strategy to maintain the temperature of the brake fluid circulation pipeline. The auxiliary heating zone dynamically adjusts the pulse heating frequency based on the real-time feedback data of the mechanical gap sensor. Through differentiated control of heating timing and power, the efficiency of multi-zone collaborative heating is improved.

[0148] Self-Test Module: This module periodically collects data on the heating cable circuit impedance and temperature control probe calibration deviation. If a resistance anomaly or calibration deviation exceeds the specified limit is detected, it generates abnormal data, including the fault area identification, and triggers redundant heating mode. For example, if the impedance detection unit identifies three consecutive abnormal sampling times using a sliding window algorithm, it activates the backup heating cable circuit, preventing single-point failures from causing system failure.

[0149] Genetic algorithm optimization unit: Based on the initial temperature field data set and deformation sensor data, the control parameters are globally optimized through a multi-objective fitness function (such as temperature uniformity and energy efficiency). The initial control parameter set including proportional coefficient, integration time and fuzzy rule weight is generated, providing an optimization starting point for the dynamic temperature control model and reducing the risk of local optimality caused by manual parameter adjustment.

[0150] Dynamic temperature control model: Using real-time mechanical clearance changes, estimated brake fluid viscosity, and historical temperature rise curve data, the clearance compensation algorithm and fuzzy control rules are applied to calibrate initial control parameters online. For example, the target temperature setpoint for the main heating zone is dynamically adjusted based on the deformation of the composite insulation board, and the pulse duty cycle is adjusted synchronously with the viscosity change rate to achieve a real-time balance between heating power and heat loss.

[0151] Redundant heating mode: When an anomaly is detected in the heating cable circuit or temperature control probe, the heat distribution coefficient is reconstructed based on the brake fluid circulation flow data of the preceding vehicle. The optimal flow rate is calculated using a thermodynamic coupling model, and the heat loss compensation coefficient is corrected in combination with deformation sensor data. This generates zoned heating instructions suitable for the fault scenario, ensuring temperature stability under abnormal operating conditions.

[0152] Gradient power reduction mechanism: The thermal inertia delay time is predicted based on the historical temperature rise curve. After the temperature reaches the preset safety range, the maintenance power of the main heating zone is dynamically reduced according to the slope decreasing rule to avoid temperature overshoot due to thermal inertia. At the same time, the power reduction command and the auxiliary heating zone pulse adjustment command are issued synchronously to optimize overall energy efficiency.

[0153] Deformation compensation algorithm: Based on the shrinkage deformation data of the composite insulation board of the aluminum insulation warehouse, the gap compensation logic in the dynamic temperature control model is called to correct the target temperature setting value of the main heating zone. For example, for every 1mm increase in deformation, the target temperature is increased by 2°C to compensate for the loss of heat conduction efficiency caused by structural deformation.

[0154] These technical features work together through a closed-loop control architecture that integrates multi-source data fusion, model optimization, and execution feedback to address issues such as heating lag, local overheating, and energy redundancy in split-type vehicles at low temperatures, thereby improving the response speed and reliability of the braking system.

[0155] Dynamic Temperature Control Model: This real-time control model is built based on multi-source sensor data (hydraulic unit temperature, seal deformation, mechanical clearance change, and ambient temperature). This model uses fuzzy control rules to handle nonlinear temperature variations. For example, it maps the rate of change in brake fluid viscosity into a heating power adjustment gradient. It also uses a clearance compensation algorithm to correct for thermal conductivity deviations caused by aluminum insulation chamber deformation. The model outputs include continuous power commands for the primary heating zone and pulse frequency weights for the auxiliary heating zones, achieving a dynamic balance between temperature distribution and energy consumption.

[0156] Genetic Algorithm Optimization Unit: This is a global optimization model used to generate an initial set of control parameters. Its input is the initial temperature field dataset collected by distributed temperature control probes and deformation sensor data. It uses a fitness function to evaluate the temperature control performance of different parameter combinations (such as temperature uniformity and energy consumption indicators) and outputs parameters such as the proportional coefficient and integration time. The optimized parameter set serves as the input to the dynamic temperature control model, resolving local optimality issues caused by manual parameter adjustment and providing a benchmark for subsequent model fine-tuning.

[0157] Fuzzy control rule base: A logical decision-making module embedded in the dynamic temperature control model, used to handle uncertainty and nonlinear inputs. For example, when feedback from the mechanical gap sensor exceeds a threshold, the fuzzy controller converts the gap increment into a weighted pulse frequency increment based on a preset "gap to pulse frequency" mapping table. It also limits the adjustment range based on historical temperature rise curve data to prevent sudden changes in control commands from causing system oscillations.

[0158] The deformation compensation algorithm, a submodule of the dynamic temperature control model, specifically processes low-temperature deformation data for the composite insulation panels in aluminum insulation silos. Based on the correlation between deformation and heat conduction paths, the algorithm dynamically adjusts the target temperature setpoint for the primary heating zone. For example, if it detects gap expansion due to shrinkage in the composite insulation panels, the algorithm raises the target temperature by a preset compensation factor to offset the increased heat loss caused by structural deformation.

[0159] Delay Compensation Unit: A timing control model that predicts the effects of thermal inertia based on historical temperature rise curves. This unit calculates the thermal inertia delay time based on the slope of the temperature rise curve and dynamically adjusts the triggering timing of the gradient power reduction mechanism. For example, after the temperature in the main heating zone reaches the safe range, the delay compensation unit generates a maintenance power command based on the power reduction slope fitted by historical data to avoid temperature overshoot caused by thermal inertia lag.

[0160] Heat Allocation Model: This emergency control model, enabled in redundant heating mode, reconfigures thermal management strategies in fault scenarios. The model calculates the optimal heat transfer rate based on brake fluid circulation flow data from the preceding vehicle. Incorporating feedback from the aluminum insulation chamber's deformation sensor, it dynamically adjusts the heat loss compensation coefficient and generates zoned heating instructions. For example, if the heating cable circuit experiences an anomaly, the model prioritizes increasing the power contribution of the primary heating zone while limiting the maximum pulse frequency of the auxiliary heating zone to maintain temperature stability in critical areas.

[0161] These models operate collaboratively via a data bus and command queue: a genetic algorithm provides initial parameters for global optimization, a dynamic temperature control model performs real-time fine-tuning, fuzzy control and deformation compensation handle nonlinear inputs, and delay compensation and heat distribution models address timing and fault scenarios. The data exchange and command coordination between these models form a closed-loop control chain, ultimately resolving the issues of insufficient heating coordination and redundant energy consumption in split-body braking systems at low temperatures.

[0162] A specific embodiment of the present invention achieves precise thermal management for split-body braking systems operating in low-temperature environments through multi-source sensor data fusion and a closed-loop control architecture. In the front vehicle's brake assembly, thermocouple temperature sensors are integrated into the cockpit air conditioning vents to collect real-time cockpit thermal environment data, which is transmitted to the rear vehicle's control module via the vehicle bus. Platinum resistance temperature sensors and strain gauge deformation sensors are layered within the rear vehicle's aluminum insulation compartment, along the hydraulic unit piping, seal mounting areas, and brake disc surface. These sensors sample the hydraulic unit surface temperature and seal displacement at a sampling rate of twice per second. Combined with a mechanical gap sensor, they detect the shrinkage of the composite insulation board, generating an initial temperature field dataset consisting of a spatial temperature distribution matrix, displacement vectors, and gap change values. The data fusion control module uses a genetic algorithm to globally optimize the initial dataset. The fitness function integrates temperature uniformity, energy efficiency, and response speed. Using genetic operations with a crossover probability of 0.8 and a mutation probability of 0.01, the initial control parameter set for proportionality coefficients, integration time, and fuzzy rule weights is iteratively generated. These parameters are then transmitted to the parameter calibration interface of the dynamic temperature control model via the CAN bus protocol. The dynamic temperature control model uses the brake fluid viscosity calculated from the real-time mechanical clearance change and the temperature-viscosity curve to dynamically adjust the target temperature setpoint for the main heating zone. Every 0.5mm increase in deformation corresponds to a 1.2°C increase in the target temperature. A fuzzy controller simultaneously maps the viscosity change rate into a power adjustment gradient, adjusting the continuous power slope of the main heating zone and the pulse duty cycle of the auxiliary heating zone according to preset "low viscosity-high power" and "high viscosity-slow-release heating" rules. The zone coordination module distributes the calibrated pulse frequency weights to the auxiliary heating zone heating cable circuits within an adjustable range of 0.5Hz-5Hz. The main heating zone initiates a gradient power reduction mechanism based on historical temperature rise curve data. When the average temperature rise rate falls below 75% of the historical peak, the maintenance power is gradually reduced at a slope of 0.15°C / min. The self-test module uses a sliding window algorithm to monitor the impedance data of the heating cable circuit. If three consecutive sampled values ​​exceed the ±10% tolerance of the thermal resistivity of the aluminum insulation chamber material, the redundant control unit is triggered to activate the backup heating cable circuit. The redundant control unit then reconstructs the heat loss compensation coefficient based on the turbine flow rate data from the preceding vehicle's brake fluid circulation flow sensor. Using a thermodynamic coupling model, the module calculates the optimal heat transfer flow rate, limiting it to 2.5 L / min, and generates a partitioning instruction to increase the power share of the main heating zone to 65%. The reconstructed parameters are written into a genetic algorithm constraint table, defining the search boundaries for the next generation of control parameter sets. This creates a closed-loop control chain from data acquisition and model optimization to anomaly recovery, addressing the temperature field imbalance caused by low-temperature deformation and differential heat conduction in split-body vehicles.

[0163] The present invention solves the problem of thermal management coordination of split-type vehicle body brake systems in low-temperature environments by constructing a closed-loop control mechanism for multi-source sensor data fusion. The split heating module deploys heat exchange units and aluminum insulation chambers in the front and rear vehicle brake systems respectively, integrates multi-zone heating cables and distributed temperature control probes, and collects hydraulic unit temperature, seal deformation and mechanical clearance data in real time. The data fusion control module constructs a dynamic temperature control model based on the above-mentioned multi-source data, combines genetic algorithms to perform global optimization of the initial control parameters, and generates partitioned heating power instructions. The partition coordination module divides the aluminum insulation chamber into main and auxiliary heating zones according to the instructions. The main heating zone implements a continuous heating strategy, and the auxiliary heating zone dynamically adjusts the pulse frequency based on mechanical clearance feedback to achieve coordinated control of the heating zones and balanced distribution of the temperature field.

[0164] The dynamic temperature control model optimizes energy redundancy through fuzzy control rules and a delay compensation mechanism. The model fine-tuning unit uses a gap compensation algorithm to correct the target temperature of the main heating zone based on the real-time brake fluid viscosity change rate and the deformation of the composite insulation plate, and simultaneously adjusts the pulse duty cycle of the auxiliary heating zone. The delay compensation unit predicts the thermal inertia delay time based on the historical temperature rise curve, dynamically adjusts the triggering timing of the gradient power reduction mechanism, and combines CAN bus command issuance with execution log feedback to achieve real-time matching of heating power and energy consumption. During the iterative optimization process of the genetic algorithm, abnormal data collected by the self-test module and historical mean reconstruction parameters are used as constraints to limit the search space of the next generation of control parameter sets, reducing ineffective energy consumption and improving control accuracy.

[0165] The redundant heating mode and self-test module work together to ensure system reliability. When an impedance anomaly in the heating cable circuit or an excessive deviation in the temperature control probe is detected, the self-test module triggers activation of the backup heating cable circuit and reconstructs the heat distribution coefficient of the dynamic temperature control model based on the brake fluid circulation flow data of the preceding vehicle. The reconstructed compensation coefficient is input into the model fine-tuning process, generating zone heating instructions appropriate for the fault scenario. These instructions are then sent to the zone coordination module via the vehicle bus. A historical database records execution data and feeds it back to the genetic algorithm, optimizing the robustness boundary conditions of the parameter set. This forms a closed-loop control chain from fault response to parameter iteration, enhancing the braking system's anti-interference capability and operational stability at low temperatures.

[0166] In response to the thermal management requirements of a split-body brake system in a low-temperature environment, the present invention provides a heating device and control method for a vehicle brake system. Taking a certain articulated low-temperature operation vehicle as an example, it adopts a front and rear split-body structure. The rear vehicle does not have an independent air conditioning system, and the brake system needs to be equipped with a separate heating device. The following is an example of an aluminum insulation chamber for the rear brake system of this vehicle. Figure 2 , the contents of the embodiments are as follows.

[0167] The rear vehicle's brake system utilizes an aluminum insulation chamber as its foundational structure. The chamber houses integrated multi-zone heating cables, distributed temperature control probes, and a mechanical clearance sensor. The aluminum chamber's interior is covered with a 10mm thick composite insulation board with a thermal conductivity of less than 0.021 W / mK. This low thermal conductivity reduces heat exchange losses inside and outside the chamber. The heating cables operate at a DC-24V voltage, compatible with the vehicle's onboard power system, providing heat for key braking system components (such as the hydraulic unit, seals, and brake fluid lines).

[0168] The split heating module installs a heat exchange unit in the brake assembly of the leading vehicle that is linked to the thermal environment of the cockpit, using the residual heat from the cockpit to assist in heating the braking system of the leading vehicle. In the aluminum insulation compartment of the rear vehicle, multi-zone heating cables are arranged according to the thermal requirements of different components of the braking system. Distributed temperature control probes are arranged in layers along the surface of the hydraulic unit, the seal installation position, and the circumference of the brake disc to collect real-time data on the hydraulic unit temperature, seal deformation data, and ambient temperature. Mechanical gap sensors are deployed at the joints of the composite insulation panels to monitor changes in mechanical gap caused by low-temperature shrinkage. The above sensors generate initial thermal distribution parameters and transmit them to the data fusion control module.

[0169] After receiving multi-source data, the data fusion control module constructs a dynamic temperature control model based on hydraulic unit temperature, seal deformation, ambient temperature, and historical brake pressure parameters from the vehicle bus. This model, combined with a genetic algorithm, performs a global optimization of the initial temperature field dataset to generate an initial set of control parameters, including proportional coefficients and integration time. Simultaneously, the model fine-tuning unit dynamically calibrates control parameters based on the real-time changes in the mechanical gap sensor and the brake fluid viscosity calculated from the temperature-viscosity curve. When the composite insulation board shrinks, causing the gap to expand, the gap compensation algorithm is invoked to adjust the target temperature setpoint in the main heating zone (for example, for every 0.5mm increase in deformation, the target temperature is increased by 1.2°C). Fuzzy control rules are used to synchronously adjust the continuous heating power slope of the main heating zone and the pulse heating duty cycle of the auxiliary heating zone based on the rate of change of the brake fluid viscosity (for example, when the viscosity drops rapidly, the power ramp rate of the main heating zone is reduced to avoid local overheating).

[0170] The zone coordination module divides the aluminum insulation chamber into a primary heating zone (covering the hydraulic unit and brake fluid lines) and an auxiliary heating zone (covering seals and sensitive mechanical clearances). The primary heating zone controls the heating cable power output based on a continuous heating strategy. When the hydraulic unit temperature falls below a critical threshold, high-power rapid heating is initiated. Once the temperature reaches a safe range, the delay compensation unit uses historical temperature rise curve data to predict the thermal inertia delay time and superimposes the gradient power reduction coefficient to generate a maintenance power command. The auxiliary heating zone dynamically adjusts the pulse heating frequency based on feedback from the mechanical clearance sensor (for example, if the clearance increment exceeds the threshold, the pulse frequency is increased to compensate for heat loss).

[0171] The self-test module periodically collects data on the impedance of the heating cable circuit and the calibration deviation of the temperature control probe. The impedance detection unit uses a sliding window algorithm to monitor the resistance change rate. When three consecutive sampling values ​​exceed the tolerance range (±10%), the redundant heating mode is triggered and the backup heating cable circuit is activated. The deviation calibration unit reconstructs the temperature control probe compensation coefficient based on the historical average value and writes it into the dynamic temperature control model calibration parameter table. When the accuracy of the mechanical gap sensor exceeds the limit, the redundant control unit switches to the heat distribution model driven by the brake fluid circulation flow data of the leading vehicle, calculates the optimal flow rate for heat transfer to the following vehicle (for example, limited to within 2.5L / min), and reconstructs the heat loss compensation coefficient based on the deformation data of the aluminum insulation bin to generate zone heating instructions for the fault scenario.

[0172] Through the above-mentioned structure and control method, the rear vehicle braking system can achieve multi-zone coordinated temperature control in a low-temperature environment: distributed sensors provide real-time feedback on the thermal status, and the dynamic temperature control model is combined with genetic algorithm optimization and online calibration to accurately adjust the power distribution of the main and auxiliary heating zones; the self-test module and redundant mode ensure temperature stability under abnormal working conditions; the aluminum insulation compartment and low thermal conductivity insulation material reduce heat loss, and the DC-24V heating cable is adapted to the on-board power supply, effectively solving the temperature field imbalance, heating lag and energy consumption redundancy problems caused by low temperature in the split body braking system, thereby improving the braking response speed and system reliability.

Claims

1. A heating device for a vehicle braking system, characterized in that: include: The split heating module is configured to install a first heat exchange unit in the front vehicle brake assembly that is linked to the thermal environment of the cockpit, and to construct an aluminum insulation chamber in the rear vehicle brake system. The aluminum insulation chamber integrates multi-zone heating cables, distributed temperature control probes, and mechanical gap sensors to generate initial thermal distribution parameters and transmit them to the data fusion control module; The data fusion control module is connected to the split heating module and is used to receive hydraulic unit temperature data, seal deformation data, and ambient temperature data from the distributed temperature control probes, and access the brake pressure history parameters of the vehicle bus. Based on the hydraulic unit temperature data, seal deformation data, and ambient temperature data, a dynamic temperature control model is constructed, and closed-loop control parameters including zone heating power instructions are output to the zone collaboration module. The partition coordination module is connected to the data fusion control module to divide the aluminum insulation chamber into the main heating zone and the auxiliary heating zone. It receives closed-loop control parameters and implements the continuous heating strategy and pulse heating frequency adjustment. The main heating zone controls the power output of the heating tape based on the continuous heating strategy, and the auxiliary heating zone adjusts the pulse heating frequency based on the real-time feedback data of the mechanical gap sensor. The self-check module is connected to the partition coordination module and periodically collects the impedance of the heating cable loop and the calibration deviation data of the temperature control probe. When an impedance anomaly or an excessive calibration deviation is detected, abnormal data including the fault area identification is generated and transmitted to the data fusion control module; Among them, the data fusion control module iteratively optimizes the control parameters of the dynamic temperature control model based on the initial heat distribution parameters and abnormal data, and sends the updated closed-loop control parameters to the partition collaboration module, forming a closed-loop control link from data acquisition, model optimization to instruction execution.

2. The heating device for a vehicle brake system according to claim 1, characterized in that: The data fusion control module includes: A genetic algorithm optimization unit is used to generate an initial control parameter set based on the initial temperature field data set of the distributed temperature control probe and the deformation sensor data of the aluminum insulation chamber, and transmit the initial control parameter set to the model fine-tuning unit; The model fine-tuning unit receives the real-time change of the mechanical clearance sensor and the estimated value of the brake fluid viscosity, performs online calibration of the initial control parameter set based on the dynamic temperature control model, and outputs the calibrated pulse frequency weight to the pulse heating controller of the auxiliary heating zone; The delay compensation unit uses the historical temperature rise curve data stored in the self-test module to predict the thermal inertia delay time, dynamically adjusts the triggering timing of the gradient power reduction mechanism, and sends the adjusted timing instructions to the heating belt drive circuit of the main heating zone through the CAN bus; Among them, the pulse frequency weight output by the model fine-tuning unit and the timing instructions of the delay compensation unit together constitute the closed-loop control parameters, driving the partition collaboration module to execute the heating strategy.

3. The heating device for a vehicle brake system according to claim 2, characterized in that: The delay compensation unit performs the following operations: When the hydraulic unit temperature is lower than the critical threshold, a high-power rapid heating command is sent to the heating cable drive circuit of the main heating zone; After the temperature reaches the preset safety range, the thermal inertia delay time is calculated based on the thermal inertia parameters of the dynamic temperature control model and the slope of the historical temperature rise curve, and the gradient reduction power coefficient is superimposed to generate the maintenance power instruction; The maintenance power instruction is used as part of the closed-loop control parameters and is written into the instruction queue of the partition coordination module synchronously with the pulse frequency adjustment instruction of the auxiliary heating zone.

4. The heating device for a vehicle brake system according to claim 3, characterized in that: The model fine-tuning unit includes: The deformation compensation submodule uses the gap compensation algorithm of the dynamic temperature control model to correct the target temperature setting value of the main heating zone based on the deformation of the composite insulation board of the aluminum insulation chamber; The viscosity feedback submodule calculates the brake fluid viscosity in real time based on the temperature-viscosity relationship curve, and dynamically adjusts the continuous heating power of the main heating zone and the pulse heating duty cycle of the auxiliary heating zone through fuzzy control rules; Among them, the gap compensation coefficient output by the deformation compensation submodule and the viscosity adjustment parameter of the viscosity feedback submodule are input into the genetic algorithm optimization unit together as the optimization boundary conditions of the next generation control parameter set.

5. The heating device for a vehicle brake system according to claim 4, characterized in that: The self-test module includes: The impedance detection unit periodically collects the resistance change rate of the heating cable loop. When abnormal resistance fluctuations are detected, it sends a backup loop activation instruction to the partition coordination module. The deviation calibration unit reconstructs the temperature compensation coefficient of the temperature control probe based on the historical mean data and writes the reconstructed coefficient into the calibration parameter table of the dynamic temperature control model; The redundant control unit switches to a heat distribution model based on the brake fluid circulation flow data of the preceding vehicle when detecting that the accuracy of the mechanical clearance sensor exceeds a limit, and feeds back the reconstructed distribution coefficient to the genetic algorithm optimization unit.

6. A heating control method for a vehicle brake system, applied to the heating device for a vehicle brake system according to any one of claims 1 to 5, characterized in that: include: Obtain the temperature data of the front vehicle's cockpit and the hydraulic unit temperature and seal deformation data collected by the distributed temperature control probes of the rear vehicle's aluminum insulation compartment. The data are integrated into an initial temperature field dataset and input into the genetic algorithm optimization process. Perform global optimization on the initial temperature field data set based on a genetic algorithm to generate an initial control parameter set including proportional coefficient and integration time and transmit it to the parameter calibration interface of the dynamic temperature control model; Based on the real-time mechanical clearance change and the estimated brake fluid viscosity, the initial control parameter set is fine-tuned online through the dynamic temperature control model, and the calibrated pulse frequency weight and continuous heating power command are output to the partitioned collaborative control queue. The pulse frequency weight is sent to the heating cable circuit of the auxiliary heating zone of the rear vehicle. At the same time, the historical temperature rise curve data stored in the self-test module is called up to dynamically adjust the maintenance power of the main heating zone based on the gradient power reduction mechanism and update the power allocation parameters of the dynamic temperature control model. When abnormal impedance of the heating cable loop or excessive deviation of the temperature control probe is detected, the system switches to redundant heating mode and reconstructs the heat distribution coefficient of the dynamic temperature control model based on the brake fluid circulation flow data of the preceding vehicle. The reconstructed coefficient is fed back to the genetic algorithm optimization process as a constraint condition for the next generation parameter set.

7. The heating control method for a vehicle brake system according to claim 6, wherein: Based on the real-time mechanical clearance change and the estimated brake fluid viscosity, the initial control parameter set is fine-tuned online through the dynamic temperature control model. The calibrated pulse frequency weight and continuous heating power command are output to the partitioned collaborative control queue, including: According to the deformation of the composite insulation board of the aluminum insulation bin, the gap compensation algorithm of the dynamic temperature control model is called to dynamically correct the target temperature setting value of the main heating zone; The brake fluid viscosity change rate is calculated in real time based on the temperature-viscosity relationship curve, and the heating power of the main heating area and the pulse duty cycle of the auxiliary heating area are synchronously adjusted through fuzzy control rules. The revised target temperature setting value and pulse duty cycle parameter are written into the parameter constraint table of the genetic algorithm optimization unit to update the next generation control parameter set.

8. The heating control method for a vehicle brake system according to claim 7, wherein: Based on the temperature-viscosity relationship curve, the brake fluid viscosity change rate is calculated in real time, and the heating power of the main heating area and the pulse duty cycle of the auxiliary heating area are synchronously adjusted through fuzzy control rules. When the feedback data of the mechanical gap sensor exceeds the threshold set by the self-test module, a pulse frequency weight increment instruction is sent to the delay compensation unit; According to the correlation between the brake fluid viscosity change rate and the historical temperature rise curve, the continuous heating power slope of the main heating zone is dynamically adjusted and a power reduction instruction is generated; The adjusted parameters are synchronously sent to the heating cable drive unit via the CAN bus, and the execution log is recorded in the historical database for genetic algorithm iteration.

9. The heating control method for a vehicle brake system according to claim 8, wherein: When abnormal heating cable loop impedance or temperature control probe deviation is detected, the system switches to redundant heating mode and reconstructs the heat distribution coefficient of the dynamic temperature control model based on the brake fluid circulation flow data of the leading vehicle. The reconstructed coefficient is fed back into the genetic algorithm optimization process as the constraint conditions for the next-generation parameter set. The following are included: After activating the backup heating cable loop, the optimal flow rate for heat transfer to the following vehicle is calculated based on the brake fluid circulation flow sensor data of the leading vehicle; Reconstruct the heat loss compensation coefficient of the dynamic temperature control model based on the optimal flow rate and the deformation sensor data of the aluminum insulation chamber; The reconstructed compensation coefficients are input into the model fine-tuning process to generate partition heating instructions suitable for the fault scenario and write them into the instruction queue.

10. The heating control method for a vehicle brake system according to claim 9, wherein: Also includes: The resistance change rate data of the heating cable loop is collected periodically. When three consecutive sampling values ​​are detected to be outside the tolerance range of the impedance detection unit, the redundant heating mode is triggered. In redundant heating mode, based on the temperature stability parameters of historical average data, the deformation compensation algorithm is called to redistribute the power ratio between the main heating zone and the auxiliary heating zone; The redistributed power ratio is integrated with the brake fluid circulation flow data of the preceding vehicle to generate a new heat distribution instruction which is transmitted to the partition coordination module via the vehicle bus.

Images