Cloud-edge collaborative intelligent temperature control brake disc base system

Abstract

The invention relates to the technical field of vehicle brake temperature control, and discloses a cloud-edge cooperative intelligent temperature control brake disc base system. The system comprises a cloud data server, an edge end feature extraction module, a response learning unit and a temperature control decision engine. The cloud data server obtains brake disc temperature data, environmental parameter data and vehicle running state data to form a brake disc database; the edge end feature extraction module classifies and divides a database according to data attributes; the response learning unit obtains a brake disc temperature response array through a response model by using the divided data, and learns temperature response characteristics; and the temperature control decision engine generates a temperature control instruction based on the array, and if the temperature is indicated to be abnormal or in a risk state, the brake disc is set to be in a temperature adjusting mode or a safety protection mode. According to the system, multi-dimensional data integration and deep analysis are achieved through cloud-side cooperation, temperature control accuracy and reliability are improved, and vehicle braking safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of vehicle brake temperature control technology, specifically a cloud-edge collaborative intelligent temperature control brake disc base system. Background Technology

[0002] During vehicle operation, the brake disc, as a critical braking component, directly affects the vehicle's braking performance and driving safety due to its temperature. With increasing vehicle speed, load capacity, and the frequency of encountering complex road conditions, the brake disc generates a significant amount of heat due to friction during braking. If this heat cannot be dissipated in time or the temperature is not properly controlled, brake disc overheating can easily occur. When the brake disc temperature is too high, it not only leads to accelerated wear of the brake pads, shortening the lifespan of the braking system, but may also cause a decline in braking performance, and in severe cases, even brake failure, posing a significant threat to the lives of drivers and passengers. Most technical solutions for brake disc temperature control focus on optimizing passive heat dissipation structures, such as improving the design of brake disc ventilation channels and using high thermal conductivity materials to enhance heat dissipation efficiency. However, these passive temperature control methods rely solely on the heat dissipation capacity of the structure itself and cannot dynamically adjust according to real-time temperature changes of the brake disc and external environmental conditions. In scenarios such as frequent braking, prolonged downhill driving, or high-load operation, the heat dissipation effect often fails to meet actual needs. Some technical solutions attempt to introduce temperature monitoring devices, acquiring real-time temperature data by installing temperature sensors near the brake discs and triggering simple cooling measures based on preset temperature thresholds. However, such solutions have significant limitations: relying solely on single temperature data for judgment, without considering the impact of environmental parameters and vehicle operating conditions on brake disc temperature changes, leads to insufficient accuracy in temperature judgment and a tendency for false or missed triggers; data processing is mostly done locally, limited by edge computing capabilities, making it impossible to perform in-depth analysis of large amounts of historical and real-time multi-dimensional data, making it difficult to accurately identify patterns in brake disc temperature changes and potential risks, and thus unable to formulate targeted temperature control strategies. Existing technologies lack effective data integration and analysis mechanisms, making it impossible to build a comprehensive brake disc operation database and hindering continuous learning and optimization of brake disc temperature response characteristics. When vehicles are in complex and variable operating environments, brake disc temperature changes are influenced by a combination of factors. Traditional technical solutions cannot accurately capture the correlation between these factors, resulting in temperature control measures lacking scientific rigor and effectiveness. They are ill-suited to the temperature control requirements of different operating conditions and cannot fundamentally solve the problem of dynamic brake disc temperature control. Summary of the Invention

[0003] The purpose of this invention is to provide a cloud-edge collaborative intelligent temperature-controlled brake disc base system to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides a cloud-edge collaborative intelligent temperature-controlled brake disc base system, the system comprising: A cloud-based data server is used to acquire brake disc temperature data, environmental parameter data, and vehicle operating status data to form a brake disc database; the environmental parameter data includes ambient temperature, ambient humidity, and vibration intensity; the vehicle operating status data includes vehicle speed, braking frequency, and load weight. The edge feature extraction module is used to classify the attribute data of the brake disc database according to data attributes, and obtain the divided brake disc database. The response learning unit uses data from the partitioned brake disc database to obtain the brake disc temperature response array through a response model, thereby learning the temperature response characteristics of the brake disc. The temperature control decision engine is used to generate temperature control commands based on the brake disc temperature response array. If the brake disc temperature response array indicates an abnormal temperature or a risky state, the brake disc is set to a temperature adjustment mode or a safety protection mode.

[0005] Preferably, the data attribute classification includes environmental attribute classification and operational attribute classification; Using the environmental attribute classification, the attribute data of the brake disc database is used to label the environmental parameter data, resulting in environmental parameter data with different labels; Using the aforementioned operational attribute classification, the attribute data of the brake disc database is used to label the vehicle operational status data, resulting in vehicle operational status data with different labels. Among them, environmental parameter data with different markings correspond to vehicle operating status data with different markings.

[0006] Preferably, the attribute data of the brake disc database is used to attribute-label the vehicle operating status data to obtain vehicle operating status data with different labels, including: The vehicle operating status data is divided into multiple data subsets, and each data subset includes at least one vehicle operating status data. Each of the data subsets is labeled, and the label is configured as a sequence identifier set by time series, wherein the sequence identifier sequentially arranges the data subsets and assigns time pointers; Obtain vehicle operating status data with different markers that are time-directed and arranged in sequence.

[0007] Preferably, the response learning unit includes: Based on the data in the brake disc database, a reference temperature depth is determined; The brake disc temperature data and environmental parameter data of the first data partition are obtained. Based on the position coordinates of the first data partition and the reference temperature depth, a comparison partition is selected for response feature learning to obtain the temperature response value corresponding to the first data partition. After obtaining the brake disc temperature data and environmental parameter data corresponding to other data partitions, the temperature response value corresponding to each data partition is determined in the same way, and the array is filled according to the data partition distribution map to obtain the brake disc temperature response array.

[0008] Preferably, the temperature control decision engine includes: Construct a temperature knowledge base, which includes concept nodes, attribute edges, and relation edges; The brake disc temperature response array is mapped to the temperature knowledge base to obtain temperature response concept nodes, and a temperature response diagram is formed based on the temperature response concept nodes. Based on the temperature response diagram and preset temperature control rules, reasoning and analysis are performed to form a preliminary temperature control decision; The preliminary temperature control decision is quantitatively scored to obtain a decision quantitative score; The final temperature control command is generated based on the decision quantification score and the preliminary temperature control decision.

[0009] Preferably, the preliminary temperature control decision is quantitatively scored to obtain a decision quantitative score, including: Based on temperature control standards, determine the quantitative dimensions and quantitative indicators; Assign weight ratios to the quantification dimension and the quantification indicator; Based on the quantitative indicators and the weight ratios, the preliminary temperature control decision is quantitatively scored to obtain the decision quantitative score.

[0010] Preferably, the temperature control decision engine further includes: Obtain the real-time temperature response value of the current brake disc partition and the static temperature response value in the brake disc temperature response array; Calculate the response deviation between the real-time temperature response value and the static temperature response value; When the response deviation exceeds a preset deviation threshold, correction parameters are determined based on the environmental parameter data of the current brake disc partition. The temperature control command is adjusted using the calibration parameters.

[0011] Preferably, adjusting the temperature control command using the calibration parameters includes: If the brake disc is in working condition, determine whether the real-time temperature response value is less than the preset temperature threshold. If so, perform temperature control adjustment during the first adjustment period. If the brake disc is not in operation, determine whether the real-time temperature response value is less than the preset temperature threshold. If yes, perform temperature control adjustment during the second adjustment period; otherwise, perform temperature control adjustment during the third adjustment period.

[0012] Preferably, the adjustment speed of the second adjustment period is greater than the adjustment speed of the first adjustment period; The adjustment speed during the third adjustment period is greater than the adjustment speed during the second adjustment period.

[0013] Preferably, the first adjustment period is determined based on the difference between the real-time temperature response value and the preset temperature threshold; The second adjustment period is determined based on the difference between the real-time temperature response value and the preset temperature threshold. The third adjustment period is determined based on the temperature change rate of the brake disc when it is not in operation.

[0014] Compared with the prior art, the beneficial effects of the present invention are: In terms of data acquisition and integration, the system utilizes a cloud-based data server to collect brake disc temperature data, environmental parameter data, and vehicle operating status data, and constructs a complete brake disc database. Compared to the limitations of traditional technologies that rely solely on single temperature data, this system achieves comprehensive collection of multi-dimensional data. It incorporates external environmental factors such as ambient temperature, humidity, and vibration intensity, as well as vehicle operating status factors such as vehicle speed, braking frequency, and load weight into the data system. This allows for a more comprehensive reflection of the factors influencing brake disc temperature changes, providing a rich and comprehensive data foundation for subsequent temperature analysis and judgment, and avoiding temperature judgment bias caused by limited data. The edge feature extraction module categorizes the brake disc database based on data attribute classification. This design fully considers the characteristic differences of different types of data, enabling the grouping of structurally similar and semantically related data. This not only improves the organization of data processing but also provides more targeted data input for subsequent response model calculations. Through attribute segmentation, the edge can quickly filter out data subsets closely related to brake disc temperature changes, reducing interference from irrelevant data in the calculation process, improving data processing efficiency, reducing data transmission volume between the edge and the cloud, minimizing network resource consumption, ensuring real-time data processing, and meeting the temperature control response speed requirements during vehicle operation. The response learning unit utilizes the partitioned database data to acquire the brake disc temperature response array through a response model, thereby learning the temperature response characteristics. This process overcomes the limitations of traditional technologies in terms of in-depth data analysis. Based on a large amount of historical and real-time data, it can uncover the correlation between different environmental parameters, vehicle operating states, and brake disc temperature changes, accurately identifying the temperature change patterns of the brake disc under different operating conditions. With data accumulation and model iteration, the response model's learning of temperature response characteristics will continuously optimize, enabling more accurate prediction of brake disc temperature change trends and early identification of potential temperature anomalies. This provides a scientific basis for subsequent temperature control decisions, avoiding the problems of delayed or inappropriate temperature control measures caused by a lack of in-depth data analysis in traditional technologies. The temperature control decision engine generates temperature control commands based on a temperature response array and switches between temperature adjustment mode and safety protection mode according to the state indicated by the array, achieving dynamic and precise control of brake disc temperature. When the temperature response array indicates abnormal temperature or potential risk, the system can promptly trigger the corresponding temperature control mode. Compared to the simple control method based on fixed thresholds in traditional technologies, this decision mechanism is more flexible and targeted. In the early stages of an abnormal temperature, the temperature adjustment mode can promptly take heat dissipation or temperature control measures to prevent further temperature increases. When the temperature reaches a risky state, the activation of the safety protection mode can take more stringent control measures to ensure the safe operation of the braking system. This hierarchical temperature control decision-making method can formulate appropriate control strategies based on the actual temperature state and risk level of the brake disc, avoiding resource waste caused by over-control and preventing safety hazards caused by under-control. It effectively improves the reliability and effectiveness of brake disc temperature control, ensures stable vehicle braking performance, extends the service life of the braking system, and provides stronger protection for the safety of drivers and passengers. The cloud-edge collaborative architecture fully leverages the strengths of both the cloud and the edge: the cloud, with its powerful storage and computing capabilities, enables long-term storage and complex analysis of large-scale data, supporting the training and optimization of response models; while the edge, relying on localized processing capabilities, enables rapid data filtering and preliminary calculations, ensuring real-time temperature control decisions. This collaborative approach solves the problem of insufficient computing power in traditional edge systems while avoiding the response latency caused by relying solely on the cloud, forming a highly efficient and collaborative temperature control system capable of adapting to the operational needs of vehicles under different road conditions, loads, and environmental environments, significantly improving the adaptability and practicality of the brake disc temperature control system. Attached Figure Description

[0015] Figure 1 This is a timing diagram of the cloud-edge collaborative intelligent temperature-controlled brake disc base system described in this invention; Figure 2 A flowchart illustrating the principles of data attribute classification. Figure 3 A flowchart illustrating the working principle of the responsive learning unit; Figure 4 A flowchart illustrating the principle of quantitative scoring for preliminary temperature control decision-making. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 The present invention provides a cloud-edge collaborative intelligent temperature-controlled brake disc base system, the system comprising: a cloud data server, an edge feature extraction module, a response learning unit, and a temperature control decision engine.

[0018] The cloud-based data server is responsible for acquiring brake disc temperature data, environmental parameter data, and vehicle operating status data. Environmental parameter data includes ambient temperature, humidity, and vibration intensity, while vehicle operating status data includes vehicle speed, braking frequency, and load weight. This data is integrated and stored as a brake disc database. The edge feature extraction module categorizes the attribute data in the brake disc database according to data attributes, thus obtaining a segmented brake disc database. The response learning unit uses the data in the segmented brake disc database to process and generate a brake disc temperature response array through a response model, thereby learning the characteristics of the brake disc temperature response. The temperature control decision engine generates temperature control commands based on the brake disc temperature response array; if the brake disc temperature response array indicates an abnormal temperature or a risky state, the brake disc is set to temperature regulation mode or safety protection mode to ensure safe system operation.

[0019] Example 1: See Figure 2In the implementation of the cloud-edge collaborative intelligent temperature-controlled brake disc base system, data attribute classification is a fundamental step in processing massive amounts of heterogeneous information. This system refines the attribute data in the brake disc database through environmental attribute classification and operational attribute classification. Environmental parameter data is collected by a sensor network distributed throughout the vehicle, which continuously monitors ambient temperature, humidity, and vibration intensity. For example, an ambient temperature sensor is installed near the brake disc in a location unaffected by direct heat radiation to obtain accurate ambient air temperature; a humidity sensor is located in the chassis to measure atmospheric humidity levels; and a vibration sensor is directly mounted on the brake disc base to capture mechanical vibration signals during braking. This raw data is transmitted to a cloud data server via the onboard communication unit. The server preprocesses the data, including data cleaning, format standardization, and timestamp alignment, and finally integrates it into a unified brake disc database.

[0020] Operational attribute classification focuses on vehicle operating status data. Vehicle speed data is provided by the vehicle's bus system, typically from wheel speed sensors or GPS modules; braking frequency data is obtained by counting the number of brake pedal triggers per unit time; and load weight data is estimated by suspension system pressure sensors or vehicle load calculation models. This data is also uploaded to a cloud server and correlated with environmental parameter data over time to form a complete database record.

[0021] When labeling environmental parameter data, the system assigns a unique identifier based on the data's physical meaning and source. For example, an environmental temperature reading containing degrees Celsius is labeled "env_temp_001," where "env" represents the environmental class, "temp" refers to the temperature, and "001" is the serial number. Humidity data is labeled "env_humid_002," and vibration data is labeled "vibr_int_003." These labels not only contain data type information but also implicitly encode the physical location of the sensor; for example, "vibr_int_003" might correspond to the vibration sensor on the left front wheel brake disc.

[0022] The processing of vehicle operation status data is more complex. The system divides the continuous data stream into data subsets according to time windows. Each time window is set to a fixed duration, such as 100 milliseconds, and each subset contains all operation status data points within that window. For a subset containing vehicle speed, braking frequency, and load weight, the system first normalizes it, converting vehicle speed to meters per second, braking frequency to Hertz, and load weight to kilograms. Then, each subset is labeled using a compound sequence identifier, such as "seq_t20230901_120000_001", where "t20230901_120000" represents the timestamp (September 1, 2023, 12:00:00), and "001" indicates the first subset within that time window. This labeling method ensures that each data subset has a unique time reference, and all subsets are strictly arranged in chronological order.

[0023] During the tagging process, the system also establishes relationships between data subsets. For example, when a sudden increase in braking frequency is detected, the system adds the "braking_event" tag to the relevant data subset and associates it with the corresponding environmental parameter data subset. This association is achieved through cross-table indexing, enabling rapid matching of environmental data subsets and runtime data subsets with the same timestamp.

[0024] A spatiotemporal mapping establishes a correspondence between environmental parameter data with different tags and vehicle operating status data. The system maintains a mapping table that records the correspondence rules between each environmental data tag and the operating data tag. For example, data tagged "env_temp_001" may correspond to a subset of operating data tagged "seq_t20230901_120000_001" because they have the same timestamp and spatial attributes (both originating from the left front wheel area). This correspondence is implemented through foreign key constraints in the database to ensure data consistency. The system checks the uniqueness of each tag to prevent duplicate identification; verifies the continuity of the time series to ensure no data is missing; and checks the reasonableness of the data range to filter outliers. All tagged data is stored in a new database table, with the table structure including original data fields, tag fields, and timestamp fields for easy subsequent querying and analysis.

[0025] The entire attribute partitioning process is implemented through a distributed computing framework. The cloud server distributes database query tasks to multiple computing nodes, with each node processing one data partition and performing data partitioning and labeling operations in parallel. The edge feature extraction module is responsible for coordinating these computing tasks and monitoring the processing progress. The partitioned data is then reassembled to form a partitioned brake disc database, providing structured input data for subsequent response feature learning.

[0026] This implementation transforms massive amounts of raw data into structured data with clearly defined semantic tags, where each data point carries rich contextual information. Time-series identifiers not only ensure the temporal characteristics of the data but also provide a foundation for analyzing the patterns of data change over time. The correspondences between different categories of data enable the system to comprehensively analyze multiple factors, providing complete data support for learning temperature response characteristics.

[0027] Example 2: See Figure 3 The implementation of the response learning unit begins with a deep analysis of the brake disc database. This unit first processes preprocessed data from the cloud data server and the edge feature extraction module. This data has already been attribute-divided and labeled, forming a structured dataset. Determining the reference temperature depth is the baseline step in the entire process. The system calculates this reference value by analyzing historical brake disc temperature data. Specifically, the system selects a sufficiently long time period, such as continuous monitoring data from the past 30 days, to extract the distribution characteristics of temperature readings. These temperature data are arranged in a time series, and the system uses a sliding window algorithm to analyze the temperature change trend within each time window, calculating the temperature extremes, averages, and rates of change within the window. By weighting and synthesizing these statistical indicators, the system generates a dynamic reference temperature depth value that reflects the temperature baseline of the brake disc under typical operating conditions.

[0028] After determining the reference temperature depth, the system begins processing the first data partition. Each data partition corresponds to a specific physical area of ​​the brake disc, and these partitions are divided using a predefined grid structure. For example, a standard brake disc surface is divided into an 8×8 grid, resulting in 64 partitions. Each partition has a unique coordinate identifier, such as (1,1) representing the center area and (8,8) representing the edge area. The system acquires brake disc temperature data and environmental parameter data for the first data partition. This data comes from temperature sensors and environmental sensors installed at the corresponding locations within that partition. The temperature data includes real-time measurements and historical averages, while the environmental parameter data includes ambient temperature, humidity, and vibration intensity measured near the partition.

[0029] Based on the location coordinates and reference temperature depth of the first data partition, the system selects comparison partitions for response feature learning. The selection of comparison partitions is based on the principles of spatial proximity and environmental similarity. For example, for the partition with coordinates (4,4), the system selects its four neighboring partitions (4,3), (4,5), (3,4), and (5,4) as comparison partitions. The system compares the temperature data and environmental parameter data of the first data partition with those of each comparison partition, analyzing the differences and correlations between them. This comparison includes calculating indicators such as temperature gradient and environmental parameter difference, thereby evaluating the partition's response characteristics to temperature changes.

[0030] The calculation of the temperature response value is a multi-factor comprehensive evaluation process. The system considers the deviation between the real-time temperature reading of the zone and the reference temperature depth, the rate of temperature change of the zone, and the degree of influence of environmental parameters on temperature. By inputting these factors into a trained response model, the system outputs a quantified temperature response value. This value reflects the thermal behavior characteristics of the zone under current conditions, including its sensitivity to temperature changes and heat dissipation characteristics.

[0031] After processing the first data partition, the system processes all other data partitions sequentially. For each partition, the same process is repeated: acquiring the partition's temperature and environmental data, selecting a suitable comparison partition based on its location coordinates, and calculating the temperature response value using a response model. During this process, the system considers the interactions between partitions, such as the heat conduction effect between adjacent partitions; these factors are taken into account in the response model.

[0032] After the temperature response values ​​of all partitions are calculated, the system begins array filling. The data partition distribution map is a two-dimensional matrix structure corresponding to the physical brake disc structure. The system fills the corresponding position of each calculated temperature response value into the matrix, forming a complete brake disc temperature response array. This array not only contains numerical information but also retains the spatial location information of each value, thus intuitively displaying the temperature response distribution of different areas on the brake disc surface. The system adopts a distributed computing architecture to improve processing efficiency, with multiple computing nodes processing different data partitions in parallel, each node responsible for calculating the response values ​​of one partition group. The master node is responsible for coordinating these computing tasks, integrating the calculation results, and performing the final array filling operation. This architecture enables the system to efficiently process large-scale temperature data and meet real-time requirements. The system verifies the validity of the input sensor data, removing outliers and noisy data. When calculating the temperature response values, the system performs multiple iterative calculations to ensure the stability and reliability of the results. The final generated brake disc temperature response array undergoes a consistency check to ensure that it accurately reflects the temperature response characteristics of the brake disc.

[0033] This implementation method enables the system to comprehensively and accurately learn the temperature response characteristics of the brake disc. Through zonal processing and multi-factor comprehensive analysis, the system can not only acquire local temperature characteristics but also grasp the overall temperature distribution pattern. The generated temperature response array provides detailed and accurate input data for subsequent temperature control decisions, enabling the system to make precise temperature regulation decisions. The entire implementation process emphasizes data accuracy and processing reliability to ensure the system can operate effectively under various operating conditions.

[0034] Example 3: See Figure 4The implementation of the temperature control decision engine begins with the construction of a temperature knowledge base. This knowledge base is organized using a graph structure, containing three basic elements: concept nodes, attribute edges, and relationship edges. Concept nodes represent temperature-related entities or states, such as "brake disc temperature," "ambient temperature," "heat dissipation rate," and "risk level." Each concept node has a unique identifier and type definition. Attribute edges describe the characteristics of concept nodes, such as "temperature value," "timestamp," and "location coordinates," and these edges carry specific numerical attributes. Relationship edges define the logical connections between concept nodes, including semantic relationships such as "cause," "impact," and "related," forming a directed connection network.

[0035] The construction process begins by defining a core set of concept nodes, including basic temperature concepts extracted from the brake disc temperature response array and derived concepts derived from the system's knowledge base. Each concept node is rigorously defined using an ontological approach, clearly defining its semantic scope and interrelationships. Attribute edges are established based on data schema mapping, associating fields in the brake disc database with the attributes of the concept nodes. The construction of relation edges relies on predefined business rules and physical laws, such as causal relationships like "high temperature causes thermal stress" and "vibration affects heat dissipation efficiency." When mapping the brake disc temperature response array to the temperature knowledge base, the system first parses each temperature response value in the array, instantiating it into a specific temperature response concept node. Each node contains numerical attributes, spatial location attributes, and temporal attributes. The mapping process employs a rule-based transformation algorithm, automatically classifying nodes into different concept categories based on the magnitude and distribution characteristics of the response values. For example, nodes with response values ​​exceeding a specific threshold are labeled as "high temperature response" concepts, while nodes with large gradient changes are labeled as "unstable response" concepts.

[0036] When generating the temperature response map, the system establishes connections between nodes based on spatial proximity and numerical similarity. Conceptual nodes corresponding to adjacent partitions are connected by edges based on "spatial proximity," while nodes with similar values ​​are connected by edges based on "numerical similarity." Simultaneously, the system also establishes cross-level connections, associating specific temperature response nodes with abstract temperature state concepts, forming a multi-layered knowledge representation structure.

[0037] When performing reasoning analysis based on the temperature response map and preset temperature control rules, the system employs a graph traversal algorithm to extract key information from the temperature response map. The reasoning process begins by identifying abnormal nodes, tracing possible impact paths and causal chains through relational edges. The temperature control rules exist in the form of production rules, such as "If the temperature response value of a certain area continues to rise and the ambient humidity is high, it is recommended to enhance heat dissipation." The system matches the actual state in the graph with the rule premises to generate preliminary temperature control decisions, which may include adjusting the cooling intensity, changing the operating mode, or issuing warning signals.

[0038] When quantifying and scoring preliminary temperature control decisions, the system first determines the quantification dimensions and indicators based on temperature control standards. Quantification dimensions include response timeliness, control accuracy, energy efficiency, and safety. Specific quantification indicators are set for each dimension, such as response time, temperature deviation, power consumption, and safety factor. When assigning weights to these dimensions and indicators, the system uses the analytic hierarchy process (AHP), comparing each factor pairwise to determine its importance and ultimately generating a weight vector.

[0039] The quantitative scoring process uses the following formula for calculation:

[0040] in: Quantitative scoring of representative decisions This represents the total number of quantitative indicators. It is the first The weighting coefficients of each indicator It is the first The actual measured value of each indicator It is the first The standardized function of each indicator. The weight coefficients satisfy the normalization condition. Standardization functions transform index values ​​with different dimensions to a unified scoring scale, typically using piecewise linear functions or sigmoid functions.

[0041] When generating the final temperature control command based on the decision quantification score and preliminary temperature control decision, the system sets multiple score threshold ranges. Each range corresponds to a different command adjustment strategy. For decisions with high scores, the system directly adopts the preliminary solution; for decisions with medium scores, the system optimizes and adjusts the parameters; for decisions with low scores, the system may initiate a re-reasoning process or adopt a conservative backup plan. The final generated temperature control command includes specific control parameters, execution time, and expected target. These commands are encapsulated in a standard format and sent to the execution unit.

[0042] The system emphasizes continuous updates and optimization of the knowledge base. New temperature response data is constantly being added to the knowledge base, and machine learning algorithms are used to adjust the attributes of concept nodes and the strength of relational edges. Temperature control rules are also dynamically adjusted based on actual operational results, enabling the system's decision-making capabilities to continuously improve over time. This implementation approach ensures that temperature control decisions are not only based on the current temperature state but also incorporate historical experience and domain knowledge, forming a more intelligent and adaptive temperature control mechanism.

[0043] Example 4: The implementation of the temperature control decision engine includes a dynamic adjustment mechanism for real-time operating status. The system continuously monitors the temperature status of each zone of the brake disc and makes control decisions by comparing real-time data with historical baseline data. The implementation process begins with the data acquisition phase. The system reads the current temperature value from an array of temperature sensors mounted on the brake disc surface. These sensors collect data several times per second and preprocess it through edge computing nodes. Simultaneously, the system retrieves the corresponding static temperature response values ​​from the storage unit. These values ​​originate from the brake disc temperature response array previously generated by the response learning unit, representing the temperature characteristic baseline under standard operating conditions.

[0044] After data acquisition, the system performs response deviation calculations. This calculation process is conducted independently for each monitoring zone, comparing and analyzing real-time temperature readings with static reference values. The deviation calculation considers not only absolute numerical differences but also the consistency of trends. The system employs a sliding time window algorithm to analyze deviation change patterns over a recent period, identifying different scenarios such as persistent or sudden deviations. The calculated response deviation values ​​are assigned positive or negative signs to indicate whether the temperature deviation is higher or lower than the expected baseline.

[0045] When the response deviation exceeds a preset threshold, the system initiates a correction parameter calculation process. This threshold is dynamically adjusted based on the brake disc's material properties, operating environment, and usage history, and is not a fixed value. The correction parameters are determined based on environmental parameter data for the current zone, including ambient temperature, humidity, and vibration intensity. The system establishes a multi-parameter correlation model to analyze the comprehensive impact of environmental factors on the temperature response. For example, in high-temperature and high-humidity environments, the same temperature deviation may require more significant correction measures; while under conditions of high vibration intensity, the system will adopt a more conservative correction strategy to avoid over-adjustment.

[0046] The calculated calibration parameters are used to adjust existing temperature control commands. The adjustment process employs a gradual optimization method to avoid system instability caused by drastic command changes. The system maintains a command adjustment queue and executes parameter corrections according to priority. After each calibration cycle, the system reassesses the response deviation and determines whether further adjustments are needed based on the latest data. See Table 1 for temperature data under different operating conditions.

[0047] Table 1: Brake disc zone temperature monitoring and calibration data.

[0048] Partition Number Real-time temperature (°C) Static reference (°C) Response deviation (°C) Ambient temperature (°C) Ambient humidity (%) Vibration intensity (g) Work status Correction parameters A01 125.6 118.2 +7.4 32.1 65.2 0.12 Work status 0.85 B03 134.2 142.8 -8.6 28.7 58.4 0.09 Non-working status 1.12 C05 118.9 115.3 +3.6 35.2 72.1 0.15 Work status 0.95 D12 142.7 135.4 +7.3 31.8 68.3 0.11 Non-working status 1.08 During the adjustment process, the system distinguishes between the working and non-working states of the brake discs. When the brake discs are in the working state, the system first checks whether the real-time temperature response value is lower than a preset temperature threshold. If it is lower than the threshold, the system uses the first adjustment period for temperature control adjustment. The first adjustment period is characterized by a relatively gentle adjustment rhythm to avoid interfering with braking performance during braking. During the adjustment process, the system comprehensively considers the current braking intensity, vehicle speed, and load, and dynamically adjusts the output power of the temperature control device. When the brake discs are in the non-working state, the system's judgment logic is different. First, it checks whether the real-time temperature response value is lower than a preset threshold. If it is confirmed to be lower than the threshold, the second adjustment period is activated for temperature adjustment. The second adjustment period has a faster adjustment speed than the first adjustment period, taking advantage of the time when the brake discs are not working to perform more proactive temperature management. If the real-time temperature response value is higher than the preset threshold, the system activates the third adjustment period. The third adjustment period uses the most aggressive adjustment strategy, typically used to handle abnormally high temperatures and prevent material damage caused by overheating.

[0049] The system continuously monitors the calibration effect and optimizes the calibration parameters through a feedback loop. After each adjustment, the system records the temperature change data before and after the adjustment to improve the temperature response model and calibration algorithm. This implementation method enables the temperature control system to adapt to various operating conditions, maintain the brake disc temperature within the ideal range, and avoid unnecessary energy consumption and equipment wear.

[0050] Example 5: The implementation of the adjustment period in the temperature control decision engine involves the fine-tuning of the temperature adjustment speed under different operating conditions. Based on the real-time operating status and temperature conditions of the brake discs, the system employs differentiated adjustment strategies to achieve optimal temperature control. The determination of the adjustment period is based on continuous temperature monitoring and status recognition. The system acquires temperature data from each zone of the brake discs through a multi-source sensor network and makes a comprehensive judgment in conjunction with vehicle operating status information.

[0051] During implementation, the system first compares and sets the adjustment speed for different adjustment periods. The adjustment speed for the second adjustment period is set higher than that for the first adjustment period; this difference reflects the rate of temperature change. The second adjustment period is typically used when the brake discs are not in operation but the temperature conditions are relatively good. In this case, the system can use a faster adjustment speed because it does not need to consider the sensitivity of braking operation to temperature changes. The first adjustment period is used for temperature adjustment during operation, employing a relatively slow adjustment rhythm to avoid the potential impact of rapid temperature changes on braking performance. The third adjustment period has the highest adjustment speed set, primarily used to address abnormally high temperatures during non-operational conditions, requiring rapid intervention to prevent overheating risks.

[0052] The determination of the adjustment period is based on real-time calculation of multiple parameters. For the first adjustment period, the system mainly relies on the difference between the real-time temperature response value and the preset temperature threshold. This difference reflects the gap between the current temperature state and the ideal target. The system converts the difference into specific time period parameters through a predefined mapping relationship. A larger temperature difference usually corresponds to a longer adjustment period or a more gradual adjustment speed to ensure a smooth transition in the working state. The system also considers the trend of temperature difference changes; if the temperature difference is detected to be rapidly decreasing, the adjustment period may be appropriately shortened. The determination of the second adjustment period is also based on the calculation of the difference between the real-time temperature response value and the preset temperature threshold, but a different parameter mapping relationship is used. Since the system is in a non-working state, it can accept a larger temperature adjustment, so the same temperature difference may correspond to a shorter adjustment period or a faster adjustment speed. The system will comprehensively consider the ambient temperature factor during calculation; under lower ambient temperature conditions, the adjustment speed may be further accelerated to improve temperature control efficiency by utilizing good heat dissipation conditions. The mechanism for determining the third adjustment period is more complex, mainly based on the temperature change rate of the brake disc in the non-working state. The temperature change rate is calculated by monitoring the amount of temperature change per unit time. The system uses a sliding time window algorithm to track temperature change trends. A higher temperature change rate usually means that immediate intervention is needed, and the system will correspondingly shorten the third adjustment period or increase the adjustment speed. The calculation of the temperature change rate also takes into account historical data; the system compares the current change rate with typical values ​​under similar operating conditions to make a more accurate judgment.

[0053] The system establishes a time-period decision matrix that maps various parameter combinations to specific time-period settings. This matrix, trained on extensive experimental data, can output the optimal adjustment strategy based on real-time input parameters. The system also incorporates a transition mechanism that smoothly switches between different time-period settings when the operating state changes, preventing sudden changes in temperature control strategies.

[0054] The entire adjustment period implementation process emphasizes dynamic adaptability. The system continuously monitors the adjustment effect and fine-tunes the period parameters based on actual temperature changes. If the adjustment speed is detected to be too fast or too slow, the system automatically corrects the parameter mapping relationship, making the adjustment process more precise. This adaptive implementation method enables the temperature control system to flexibly cope with various operating conditions, optimizing temperature control performance while ensuring safety. The implementation of the adjustment period also considers equipment lifespan and energy consumption factors. Too fast an adjustment speed may increase the load on the temperature control equipment, while too slow an adjustment may affect the control effect. The system seeks a balance among multiple objectives through optimization algorithms, ensuring both timely temperature control and long-term reliable operation of the equipment. All adjustment period settings can be adjusted through a remote configuration interface, allowing the system to adapt to the specific requirements of different vehicle models and operating environments.

[0055] This differentiated adjustment period implementation allows the temperature control system to make the most appropriate adjustment decisions based on real-time conditions. Careful adjustments during operation ensure stable braking performance, rapid response during non-operational operation improves temperature management efficiency, and emergency handling of abnormal situations ensures system safety. Through refined time period configuration and dynamic adjustment mechanisms, the system achieves precise and intelligent temperature control.

[0056] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0057] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A cloud-edge collaborative intelligent temperature-controlled brake disc base system, characterized in that, include: A cloud-based data server is used to acquire brake disc temperature data, environmental parameter data, and vehicle operating status data to form a brake disc database; the environmental parameter data includes ambient temperature, ambient humidity, and vibration intensity; the vehicle operating status data includes vehicle speed, braking frequency, and load weight. The edge feature extraction module is used to classify the attribute data of the brake disc database according to data attributes, and obtain the divided brake disc database. The response learning unit uses data from the partitioned brake disc database to obtain the brake disc temperature response array through a response model, thereby learning the temperature response characteristics of the brake disc. The temperature control decision engine is used to generate temperature control commands based on the brake disc temperature response array. If the brake disc temperature response array indicates an abnormal temperature or a risky state, the brake disc is set to a temperature adjustment mode or a safety protection mode.

2. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 1, characterized in that, The data attribute classification includes environmental attribute classification and operational attribute classification; Using the environmental attribute classification, the attribute data of the brake disc database is used to label the environmental parameter data, resulting in environmental parameter data with different labels; Using the aforementioned operational attribute classification, the attribute data of the brake disc database is used to label the vehicle operational status data, resulting in vehicle operational status data with different labels. Among them, environmental parameter data with different markings correspond to vehicle operating status data with different markings.

3. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 2, characterized in that, The attribute data from the brake disc database is used to assign attribute tags to the vehicle operating status data, resulting in vehicle operating status data with different tags, including: The vehicle operating status data is divided into multiple data subsets, and each data subset includes at least one vehicle operating status data. Each of the data subsets is labeled, and the label is configured as a sequence identifier set by time series, wherein the sequence identifier sequentially arranges the data subsets and assigns time pointers; Obtain vehicle operating status data with different markers that are time-directed and arranged in sequence.

4. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 1, characterized in that, The response learning unit includes: Based on the data in the brake disc database, a reference temperature depth is determined; The brake disc temperature data and environmental parameter data of the first data partition are obtained. Based on the position coordinates of the first data partition and the reference temperature depth, a comparison partition is selected for response feature learning to obtain the temperature response value corresponding to the first data partition. After obtaining the brake disc temperature data and environmental parameter data corresponding to other data partitions, the temperature response value corresponding to each data partition is determined in the same way, and the array is filled according to the data partition distribution map to obtain the brake disc temperature response array.

5. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 1, characterized in that, The temperature control decision engine includes: Construct a temperature knowledge base, which includes concept nodes, attribute edges, and relation edges; The brake disc temperature response array is mapped to the temperature knowledge base to obtain temperature response concept nodes, and a temperature response diagram is formed based on the temperature response concept nodes. Based on the temperature response diagram and preset temperature control rules, reasoning and analysis are performed to form a preliminary temperature control decision; The preliminary temperature control decision is quantitatively scored to obtain a decision quantitative score; The final temperature control command is generated based on the decision quantification score and the preliminary temperature control decision.

6. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 5, characterized in that, The preliminary temperature control decision is quantitatively scored to obtain a decision quantitative score, including: Based on temperature control standards, determine the quantitative dimensions and quantitative indicators; Assign weight ratios to the quantification dimension and the quantification indicator; Based on the quantitative indicators and the weight ratios, the preliminary temperature control decision is quantitatively scored to obtain the decision quantitative score.

7. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 1, characterized in that, The temperature control decision engine also includes: Obtain the real-time temperature response value of the current brake disc partition and the static temperature response value in the brake disc temperature response array; Calculate the response deviation between the real-time temperature response value and the static temperature response value; When the response deviation exceeds a preset deviation threshold, correction parameters are determined based on the environmental parameter data of the current brake disc partition. The temperature control command is adjusted using the calibration parameters.

8. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 7, characterized in that, Adjusting the temperature control command using the calibration parameters includes: If the brake disc is in working condition, determine whether the real-time temperature response value is less than the preset temperature threshold. If so, perform temperature control adjustment during the first adjustment period. If the brake disc is not in operation, determine whether the real-time temperature response value is less than the preset temperature threshold. If yes, perform temperature control adjustment during the second adjustment period; otherwise, perform temperature control adjustment during the third adjustment period.

9. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 8, characterized in that, The adjustment speed during the second adjustment period is greater than the adjustment speed during the first adjustment period; The adjustment speed during the third adjustment period is greater than the adjustment speed during the second adjustment period.

10. The cloud-edge collaborative intelligent temperature-controlled brake disc base system according to claim 8, characterized in that, The first adjustment period is determined based on the difference between the real-time temperature response value and the preset temperature threshold. The second adjustment period is determined based on the difference between the real-time temperature response value and the preset temperature threshold. The third adjustment period is determined based on the temperature change rate of the brake disc when it is not in operation.

Images