Electric system management method, device and vehicle

Abstract

The application relates to the technical field of vehicles, in particular to an electrical system management method and device and a vehicle, wherein the method comprises the following steps: acquiring vehicle parameters, wherein the vehicle parameters comprise working condition parameters and electrical parameters; preprocessing the vehicle parameters, and inputting the preprocessed target vehicle parameters into a pre-constructed protection threshold decision model; the protection threshold decision model outputs target protection thresholds of an electrical circuit and electrical appliances of the vehicle; acquiring current operation parameters of the electrical circuit and the electrical appliances; and managing the electrical system according to the current operation parameters and the target protection thresholds. Thus, the problems of low protection accuracy and the like caused by electrical management based on fixed thresholds in the related art are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to an electrical system management method, device and vehicle. Background Technology

[0002] As automotive functions continue to expand, the vehicle electrical system has evolved from a single power supply circuit into a complex network with multiple domains working together. The body domain alone includes dozens of electrical appliances such as headlights, wipers, power seats, and air conditioning, while the power domain's high-voltage circuit involves core components such as batteries, motors, and electronic controls. Therefore, it is necessary to protect and manage the entire vehicle's electrical system.

[0003] The electrical management method in related technologies is to preset fixed protection thresholds for each electrical circuit and appliance. However, due to the complex and variable operating conditions of vehicles, fixed protection thresholds are prone to malfunctions or protection failures, resulting in low protection accuracy. Summary of the Invention

[0004] This application provides an electrical system management method, device, and vehicle to solve the problems of low protection accuracy caused by electrical management based on fixed thresholds in related technologies.

[0005] The first aspect of this application provides an electrical system management method, comprising the following steps: acquiring vehicle parameters, wherein the vehicle parameters include operating condition parameters and electrical parameters; preprocessing the vehicle parameters and inputting the preprocessed target vehicle parameters into a pre-constructed protection threshold decision model, wherein the protection threshold decision model outputs the target protection thresholds for the vehicle's electrical circuits and electrical appliances; acquiring the current operating parameters of the electrical circuits and electrical appliances, and managing the electrical system according to the current operating parameters and the target protection thresholds.

[0006] Optionally, the operating parameters include at least one of the following: engine speed, motor speed, battery SOC, high-voltage battery SOH, coolant temperature, engine oil temperature, vehicle speed, braking status, steering angle, ambient temperature, interior temperature, light intensity, number of in-vehicle screens open, and audio volume level.

[0007] Optionally, the electrical parameters include at least one of the following: current, voltage, circuit temperature, wire resistance of each electrical circuit, and operating status and load level of each electrical appliance.

[0008] Optionally, the protection threshold decision model is a fuzzy neural network model, which includes a fuzzification layer, an inference layer, and a defuzzification layer.

[0009] Optionally, the fuzzification layer is used to calculate the membership degree of the target vehicle parameters on each fuzzy set; the inference layer is used to match at least one target rule from the preset fuzzy rule base based on the target vehicle parameters, extract the target vehicle parameters and reference thresholds contained in each target rule, and select the minimum value among the membership degrees corresponding to the target vehicle parameters as the activation intensity of the corresponding target rule; the defuzzification layer is used to use the activation intensity of each target rule as the weight of the corresponding rule, and calculate the target protection threshold of the electrical circuit and electrical appliances by weighting based on the weight of each target rule and the reference threshold.

[0010] Optionally, before managing the electrical system based on the current operating parameters and the target protection threshold, the method further includes: correcting the target protection threshold when a conflict is detected with the reference threshold corresponding to the target rule; and managing the electrical system based on the corrected target protection threshold and the current operating parameters.

[0011] Optionally, the target protection threshold is corrected by: identifying the category of each target rule; determining the safety weight of the corresponding target rule based on the category and / or vehicle parameters; and calculating the corrected target protection threshold by weighting the safety weight of each target rule with a reference threshold.

[0012] Optionally, managing the electrical system based on current operating parameters and target protection thresholds includes: determining the corresponding protection level based on the current operating parameters and target protection thresholds; determining the corresponding management strategy based on the protection level; and managing the electrical system based on the management strategy.

[0013] Optionally, determining the protection level based on the ratio includes: obtaining a first correspondence between the ratio and the protection level; and determining the corresponding protection level based on the ratio and the first correspondence.

[0014] Optionally, determining the corresponding management strategy based on the protection level includes: obtaining a second correspondence between the protection level and the management strategy; and determining the corresponding management strategy based on the protection level and the second correspondence.

[0015] A second aspect of this application provides an electrical system management device, comprising: an acquisition module for acquiring vehicle parameters, wherein the vehicle parameters include operating condition parameters and electrical parameters; an input module for preprocessing the vehicle parameters and inputting the preprocessed target vehicle parameters into a pre-built protection threshold decision model, wherein the protection threshold decision model outputs target protection thresholds for the vehicle's electrical circuits and electrical appliances; and a management module for acquiring the current operating parameters of the electrical circuits and electrical appliances and managing the electrical system according to the current operating parameters and the target protection thresholds.

[0016] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the electrical system management method as described above.

[0017] A fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which are executed by a processor to perform the electrical system management method as described above.

[0018] A fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the electrical system management method as described in the above embodiments.

[0019] Therefore, this application has at least the following beneficial effects: This application embodiment allows vehicle parameters to be input into a pre-built protection threshold decision model. The protection threshold decision model outputs a target protection threshold that matches the current actual state of the vehicle. This enables the determination of the target protection threshold based on the current actual state of the vehicle, achieving a match between the target protection threshold and the actual state. Furthermore, the electrical system is managed based on the current operating parameters of electrical circuits and appliances and the target protection threshold. This improves the accuracy of electrical system protection under different states, avoids false triggering or insufficient protection due to fixed thresholds when operating conditions change, and ultimately improves the operational reliability of the electrical system, ensuring its safe operation. Therefore, it solves the technical problems of low protection accuracy in related technologies based on fixed thresholds for electrical protection.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of an electrical system management method provided according to an embodiment of this application; Figure 2 This is a schematic diagram of a sensor network provided according to an embodiment of this application; Figure 3 This is a schematic diagram illustrating the adjustment of the overcurrent threshold of the vehicle's high-voltage circuit under different operating conditions according to embodiments of this application; Figure 4 This is a schematic diagram of a hierarchical management electrical system provided according to an embodiment of this application; Figure 5 This is a complete flowchart of the electrical system management method provided according to the embodiments of this application; Figure 6 This is an example diagram of an electrical system management device provided according to an embodiment of this application; Figure 7 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0022] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0023] The use of fixed threshold management in related technologies has the following problems: 1. Low protection accuracy, prone to false triggering or protection failure: Vehicle operating conditions are complex and variable. For example, during cold start, the battery needs to provide a large instantaneous current (up to 200-300A) to the starter motor. If the conventional overcurrent threshold (such as 180A) is used, the protection will be falsely triggered, resulting in start failure. In high-temperature environments (such as when the engine compartment temperature exceeds 80°C after being exposed to the sun in summer), the insulation performance of the wires decreases and the circuit's current withstand capability is reduced. However, if the fixed threshold is not adjusted, the wires may overheat and burn out, posing a fire risk.

[0024] 2. Significant energy waste in the system: To cover extreme operating conditions, traditional solutions typically set the protection threshold to 1.5-2 times the component's rated value, causing the electrical system to operate in a low-load utilization range for extended periods. For example, an electric air conditioner has a rated current of 15A under normal operating conditions and a fixed overcurrent threshold of 25A. In actual operation, the current is consistently maintained at 10-12A, resulting in wasted power supply resources. This is especially true for pure electric vehicles, as it shortens their driving range.

[0025] 3. Poor vehicle platform compatibility and high development costs: Electrical appliance configurations vary significantly between different vehicle models (e.g., compact sedans, mid-size SUVs). The installation location and heat dissipation conditions of the same electrical appliance also differ between models (e.g., the wire length of electric seats can differ by up to 1.5 meters between sedans and SUVs, resulting in different current losses due to varying resistance). Fixed threshold solutions require individual threshold calibration for each vehicle model, with a development cycle of 3-6 months. Furthermore, they are incompatible with newly added electrical appliances in subsequent model updates (e.g., lidar, in-vehicle refrigerators), necessitating a redesign of protection logic.

[0026] 4. Lack of system-wide coordinated protection: Traditional solutions use "point-to-point" protection, with each circuit's protection action independent, failing to consider the interconnectivity of the entire vehicle's electrical system. For example, when the on-board charging gun and air conditioning are turned on simultaneously, the high-voltage battery needs to supply power to two high-power electrical appliances. If only fixed thresholds are set for the charging circuit and the air conditioning circuit separately, it may cause the battery's total output current to exceed the limit, triggering a forced power-off by the battery management system and affecting the user experience.

[0027] To address this, this application provides an electrical system management method that collects real-time vehicle operating parameters and system electrical parameters to construct a dynamic protection threshold model, thereby achieving precise protection for all electrical circuits and appliances in the vehicle. Simultaneously, it iteratively optimizes the model in the cloud to improve system adaptability and long-term reliability, reduce vehicle development costs, and optimize vehicle energy efficiency, thus solving at least one of the above technical problems.

[0028] Specifically, Figure 1 This is a flowchart illustrating an electrical system management method provided in an embodiment of this application.

[0029] like Figure 1 As shown, the electrical system management method includes the following steps: In step S101, the vehicle parameters are obtained, including operating parameters and electrical parameters.

[0030] The operating parameters include at least one of the following: engine speed, motor speed, battery SOC (State of Charge), high-voltage battery SOH (State of Health), coolant temperature, engine oil temperature, vehicle speed, braking status, steering angle, ambient temperature, interior temperature, light intensity, number of in-vehicle screens open, and audio volume level; the electrical parameters include at least one of the following: current, voltage, circuit temperature, wire resistance of each electrical circuit, and operating status and load level of each electrical appliance.

[0031] Specifically, embodiments of this application can utilize a sensor network deployed across various domains of the vehicle, such as... Figure 2 As shown, two types of core parameters are collected in real time at a frequency of no less than 100Hz to ensure the timeliness of the data, including: Vehicle operating parameters: covering the power domain (engine speed, motor speed, battery SOC, high-voltage battery SOH, coolant temperature, engine oil temperature), chassis domain (vehicle speed, braking status, steering angle), body domain (ambient temperature, interior temperature, light intensity), and intelligent cockpit domain (number of in-vehicle screens open, audio volume level), are transmitted to the central processing unit via CAN / LIN / Ethernet bus.

[0032] Vehicle electrical parameters include real-time current, voltage, circuit temperature, and wire resistance (calculated from current and voltage) of each electrical circuit (power circuit, body circuit, low-voltage auxiliary circuit, and high-voltage circuit), as well as the operating status of each electrical appliance (on / off, load level, such as the air conditioner being set to load levels 1-5 corresponding to different cooling power). Each electrical appliance and circuit is equipped with an independent current and voltage sensor to ensure that there are no blind spots in parameter acquisition.

[0033] In step S102, the vehicle parameters are preprocessed, and the preprocessed target vehicle parameters are input into the pre-built protection threshold decision model. The protection threshold decision model outputs the target protection thresholds for the vehicle's electrical circuits and electrical appliances.

[0034] The preprocessing may include filtering, outlier removal, standardization and correlation processing; the protection threshold decision model is a fuzzy neural network model; the target protection threshold may include overcurrent threshold, overvoltage threshold, undervoltage threshold, temperature threshold, etc.

[0035] It is understood that the embodiments of this application can preprocess the vehicle parameters and input the preprocessed target vehicle parameters into a pre-built protection threshold decision model. The protection threshold decision model outputs the target protection thresholds for the vehicle's electrical circuits and electrical appliances, thereby enabling the determination of the target protection threshold based on the actual state of the current vehicle and achieving the matching between the target protection threshold and the actual state.

[0036] The preprocessing process may include: Filtering: The Kalman filter algorithm is used to remove high-frequency interference signals, such as current fluctuations caused by electromagnetic interference generated by motor operation (the fluctuation range is usually ±2A), so that the parameter fluctuation range is controlled within ±0.5A to ensure data stability.

[0037] Outlier removal: Identify abnormal data based on the 3σ principle (multiple of standard deviation), such as a sudden change in current value to 0 or exceeding the rated value of the component by 3 times due to sensor failure. At the same time, combine the data trend of adjacent time moments to judge (e.g., if the current suddenly increases from 10A to 50A within 10ms, it is judged as abnormal) and trigger sensor failure warning, and record the fault location and time.

[0038] Standardization and correlation processing: Parameters with different dimensions are converted into standardized values ​​in the 0-1 range (e.g., engine speed 0-6000rpm corresponds to 0-1, voltage 12-14.5V corresponds to 0-1). At the same time, parameter correlation models are established, such as the coupling relationship between high-voltage battery SOC and power circuit current, to provide a data foundation for subsequent threshold calculation.

[0039] In one embodiment of this application, the fuzzy neural network model includes a fuzzification layer, an inference layer, and a defuzzification layer. The fuzzification layer is used to calculate the membership degree of the target vehicle parameters on each fuzzy set. The inference layer is used to match at least one target rule from a preset fuzzy rule library based on the target vehicle parameters, extract the target vehicle parameters and reference thresholds contained in each target rule, and select the minimum value among the membership degrees corresponding to the target vehicle parameters as the activation intensity of the corresponding target rule. The defuzzification layer is used to use the activation intensity of each target rule as the weight of the corresponding rule, and calculate the target protection threshold of the electrical circuit and the electrical appliances by weighting based on the weight of each target rule and the reference threshold.

[0040] Among them, the fuzzy set is a linguistic partition set for the range of values ​​of a certain parameter, such as high temperature, normal temperature, and low temperature forming the fuzzy set of ambient temperature; the membership degree is the degree to which a certain parameter belongs to a certain fuzzy set; the fuzzy rule set is a preset IF-THEN rule set, and each rule includes preconditions, reference thresholds, and category labels; the activation strength is the degree of matching between the current input and a certain rule.

[0041] This application embodiment can employ a fuzzy neural network model as the protection threshold decision model. The model includes a fuzzification layer, an inference layer, and a defuzzification layer, wherein... The fuzzification layer can calculate the membership degree of each vehicle parameter on each fuzzy set; The inference layer can traverse the preset fuzzy rule library, select matching target rules from the preset fuzzy rule library, extract the target vehicle parameters and reference thresholds contained in each target rule, and select the minimum value of the membership degree corresponding to the target vehicle parameters as the activation strength of the corresponding target rule. The deblurring layer uses activation intensity as the weight, and calculates the target protection threshold based on the reference threshold and the weighted average.

[0042] Specifically, the specific structure of the protection threshold decision model in this application and the processing procedure of each layer are as follows: 1. Fuzziness layer, used to convert precise numerical inputs into linguistic fuzzy variables to simulate human cognition of high, low, moderate and medium states.

[0043] The processing procedure is as follows: Define 3 to 5 fuzzy sets for each input parameter (e.g., {extremely low, low, medium, high, extremely high}). Gaussian or triangular membership functions can be used to calculate the membership degree of each parameter on different fuzzy sets. The output of each input parameter is represented as its membership degree vector on multiple fuzzy sets. For example, ambient temperature 38℃ → {low temperature: 0.1, normal temperature: 0.2, high temperature: 0.8}.

[0044] II. Rule Activation and Inference Layer: This layer is used to perform logical reasoning based on a preset fuzzy rule base to identify the protection strategy that should be triggered under the current operating conditions.

[0045] The fuzzy rule base is derived from expert experience and historical data analysis, and may include, but is not limited to, the following rules: R1: IF (engine speed > 3500 rpm) AND (battery SOC > 85%), THEN reduce the overcurrent threshold of non-critical circuits (reduction of 8%-12%). R2: IF (ambient temperature > 35℃) AND (loop temperature > 65℃), THEN increase the overcurrent threshold of the high-voltage loop (increase by 15%-20%), and decrease the overvoltage threshold (decrease by 5%). R3: IF (battery voltage <12V), THEN lower the undervoltage threshold to 11.2V to avoid malfunction; R4: IF (Air conditioning + seat heating + charging gun simultaneously turn on ≥3 high-power electrical appliances), THEN start priority weighted scheduling algorithm to dynamically allocate protection threshold.

[0046] The processing procedure is as follows: the preconditions of each rule are used to calculate the matching degree through a fuzzy AND operation (taking the minimum membership degree); the matching degree is used as the activation strength of the rule. The output is a set of suggested reference thresholds and their confidence levels.

[0047] For example, if a rule is based on the premise of "high temperature AND loop heat", and the membership degrees of the two terms are 0.8 and 0.7 respectively, then the activation intensity of the rule is min(0.8, 0.7) = 0.7.

[0048] III. Deblurring and Preliminary Threshold Generation Layer.

[0049] The defuzzification layer uses a weighted average method to convert the fuzzy inference results into preliminary threshold suggestions. The formula is as follows: ; in, Let be the activation strength of the i-th rule. This is the corresponding reference threshold.

[0050] For each object to be protected (such as starter circuit, air conditioning circuit, etc.), a target protection threshold is generated.

[0051] For example, if the three rules suggest that the air conditioner overcurrent thresholds are 20A (weight 0.6), 22A (weight 0.3), and 18A (weight 0.1) respectively, then the initial output is: (0.6×20 + 0.3×22 + 0.1×18) / (0.6+0.3+0.1) = (12 + 6.6 +1.8) / 1 = 20.4A.

[0052] The calculation logic of the priority weighted scheduling algorithm in this application embodiment can be as follows: First, calculate the current demand current based on the product of the rated current of each electrical appliance and the current load level, and assign priority weights according to functional importance and user perception sensitivity. High-priority electrical appliances are given a higher safety margin coefficient to calculate the candidate protection threshold. Then, check whether the sum of each candidate threshold exceeds the current maximum output capacity of the battery. If it does, start from the low-priority electrical appliances and lower their candidate thresholds until the constraints are met. Finally, output the independent target protection threshold for each electrical appliance.

[0053] For example, when the air conditioner, seat heater, and charging gun are turned on simultaneously, their current requirements are 30A, 9A, and 120A, respectively. After allocating safety margins according to the priority weights of 0.50 for the charging gun, 0.35 for the air conditioner, and 0.15 for the seat heater, the protection thresholds are 138A, 33A, and 9.45A, respectively. The total of 180.45A exceeds the battery capacity of 180A. The protection threshold for the lower priority seat heater is then lowered to 9.0A, resulting in a final output of 138A for the charging gun, 33A for the air conditioner, and 9.0A for the seat heater. The total threshold of the three circuits equals 180A.

[0054] The calculation logic for the protection threshold in this application embodiment is as follows: When the power domain operating parameters are adjusted: engine speed > 3500 rpm and battery SOC > 85% (gasoline vehicle), or motor speed > 8000 rpm and high-voltage battery SOC > 90% (electric vehicle), the vehicle's power supply capacity is at its peak. The overcurrent threshold of non-critical circuits (such as audio and ambient lighting) is reduced by 8%-12%, from the conventional 20A to 17.6-18.4A, reducing ineffective energy consumption. When environmental and temperature parameters trigger adjustments: When the ambient temperature > 35℃ and the circuit temperature > 65℃, the temperature tolerance of the wire insulation layer decreases. Therefore, the overcurrent threshold of all high-voltage electrical circuits (such as the power battery power supply circuit, motor drive circuit, and on-board charger circuit) is increased by 15%-20% (e.g., from 80A to 92-96A), while the overvoltage threshold is decreased by 5% (e.g., from 380V to 361V) to prevent component overheating and damage. The adjustment of the overcurrent threshold of the vehicle's high-voltage circuit under different operating conditions is as follows: Figure 3 As shown; When multiple electrical appliances work together, the adjustment is triggered: When three or more high-power electrical appliances (such as air conditioner, seat heater, and on-board charging gun) are turned on at the same time, the total current demand of the vehicle is calculated. The total current demand of the vehicle is calculated based on the sum of the products of the rated current of each high-power electrical appliance and its current load level. The overcurrent threshold of each circuit is dynamically allocated based on its functional importance, user perception sensitivity, and system margin through a priority weighted scheduling algorithm to ensure that the total current does not exceed the battery output capacity.

[0055] When the load level of an appliance changes, the adjustment is triggered: When the load of an appliance rises to level 4-5 (high load), such as when the air conditioner is at its maximum cooling setting or both seats are heated, the overcurrent threshold of the corresponding circuit is increased by 12%-18% to avoid false triggering of protection due to the increase in instantaneous load.

[0056] Threshold calibration mechanism: For different vehicle models, by inputting basic parameters such as vehicle wheelbase, electrical configuration, and wire specifications (e.g., cross-sectional area of ​​1.5mm² or 2.5mm²), the model automatically calibrates the threshold calculation coefficients. The threshold calculation coefficients include wire resistance correction coefficients, heat dissipation efficiency factors, and electrical configuration weights, which are used to adapt to the physical characteristics of different vehicle models and achieve rapid cross-platform deployment.

[0057] In step S103, the current operating parameters of the electrical circuits and appliances are obtained, and the electrical system is managed according to the current operating parameters and the target protection threshold.

[0058] The current operating parameters may include current, temperature, load, voltage, etc.

[0059] It is understood that the embodiments of this application can obtain the current operating parameters of electrical circuits and appliances, and manage the electrical system based on the current operating parameters and target protection thresholds.

[0060] This application embodiment can input vehicle parameters into a pre-built protection threshold decision model. The protection decision threshold model outputs a target protection threshold that matches the current actual state of the vehicle. This enables the determination of the target protection threshold based on the current actual state of the vehicle, achieving a match between the target protection threshold and the actual state. Furthermore, the electrical system can be managed based on the current operating parameters of the electrical circuits and appliances and the target protection threshold. This improves the accuracy of electrical system protection under different states, avoids false triggering or insufficient protection when fixed thresholds change operating conditions, and thus improves the operational reliability of the electrical system and ensures its safe operation.

[0061] In one embodiment of this application, before managing the electrical system according to the current operating parameters and the target protection threshold, the method further includes: correcting the target protection threshold when a conflict is detected with the reference threshold corresponding to the target rule; and managing the electrical system according to the corrected target protection threshold and the current operating parameters.

[0062] Among them, conflict occurs when the reference thresholds given by different rules have opposite directions or significant numerical differences.

[0063] It is understood that the embodiments of this application can identify when there is a conflict between the reference threshold corresponding to the target rule and correct the target protection threshold. The electrical system is managed according to the corrected target protection threshold and the current operating parameters to prevent erroneous actions caused by contradictions and conflicts.

[0064] In one embodiment of this application, correcting the target protection threshold includes: identifying the category of each target rule; determining the safety weight of the corresponding target rule based on the category and / or vehicle parameters; and calculating the corrected target protection threshold by weighting the safety weight of each target rule with a reference threshold.

[0065] The category refers to the safety priority type to which the rule belongs, including temperature safety, voltage safety, current safety, energy efficiency optimization, etc.

[0066] It is understood that, in the embodiments of this application, the weight of the target rule can be determined according to the category of each rule and the vehicle parameters, and the corrected target protection threshold can be calculated by weighting the safety weight of each target rule and the reference threshold, so as to ensure that the final output target protection threshold is more secure.

[0067] Specifically, in this embodiment of the application, when multiple operating parameters trigger conflicting threshold adjustment commands, arbitration is performed based on a preset safety priority, and a weighted fusion algorithm is used to generate a corresponding protection threshold. This protection threshold is then used as the final corrected target protection threshold. That is, in the case of conflicting protection thresholds, the target protection threshold is determined in the following manner, as detailed below: 1. Establish a four-level safety priority system: P1: Temperature safety (preventing overheating and fire), basic weight value 0.4–0.6; P2: Voltage safety (preventing system crash), basic weight value 0.3–0.4; P3: Current safety (preventing component burnout), basic weight value 0.2–0.3; P4: Energy efficiency optimization (energy saving and consumption reduction), basic weight value 0.1–0.2.

[0068] 2. Dynamic weight adjustment.

[0069] If the ambient temperature is >40℃, the weight of the "temperature safety" category of instructions will increase to 0.6; If the battery SOC is less than 20%, the weight of "voltage safety" is increased to 0.4. If there are already warning records, the weight of the relevant category will be increased by 10%.

[0070] 3. Weighted average fusion calculation.

[0071] ; in, The corrected target protection threshold. The normalized overall weight, This is a reference threshold.

[0072] 4. Boundary verification and anomaly handling: The output value shall not exceed 110% of the component's rated value; the undervoltage threshold shall not be lower than 10.8V.

[0073] Furthermore, it should be noted that, in the embodiments of this application, when a conflict is determined, the activation strength and security category weights mentioned above can be considered together as the total weight of the corresponding rule, and then the final protection threshold can be calculated based on the total weight of each rule and the reference threshold.

[0074] In one embodiment of this application, managing an electrical system based on current operating parameters and a target protection threshold includes: determining a corresponding protection level based on the current operating parameters and the target protection threshold; determining a corresponding management strategy based on the protection level; and managing the electrical system based on the management strategy.

[0075] It is understood that the embodiments of this application can determine the corresponding protection level based on the current operating parameters and the target protection threshold, determine the corresponding management strategy based on the protection level, and then manage the electrical system according to the management strategy, thereby realizing hierarchical management of the electrical system, improving the precision of electrical protection, reducing unnecessary power outages and minimizing the impact on the normal use of the vehicle while ensuring safety.

[0076] In one embodiment of this application, determining the corresponding protection level based on the current operating parameters and the target protection threshold includes: calculating the ratio between the current operating parameters and the target protection threshold; and determining the protection level based on the ratio.

[0077] It is understood that the embodiments of this application can calculate the ratio between the current operating parameters and the target protection threshold, and determine the corresponding protection level based on the ratio.

[0078] In one embodiment of this application, determining the protection level based on the ratio includes: obtaining a first correspondence between the ratio and the protection level; and determining the corresponding protection level based on the ratio and the first correspondence.

[0079] The protection level can be divided into multiple protection levels, without specific limitations; the first correspondence is the mapping relationship between a pre-set ratio and the protection level.

[0080] For example, the first correspondence stores a ratio of 1, which corresponds to the first protection level, and a ratio of 2, which corresponds to the second protection level.

[0081] In one embodiment of this application, determining the corresponding management strategy based on the protection level includes: obtaining a second correspondence between the protection level and the management strategy; and determining the corresponding management strategy based on the protection level and the second correspondence.

[0082] The second correspondence is the mapping relationship between the pre-defined protection level and the management strategy.

[0083] For example, embodiments of this application perform hierarchical electrical management based on current operating parameters and target protection thresholds, such as... Figure 4 As shown, it includes: 1. Level 1 Warning (Warning Level): When the parameter reaches 90% of the target protection threshold, that is, when the ratio is greater than 0.9, such as when the overcurrent threshold is 20A and the current reaches 18A, a warning message (such as "the electrical load of the vehicle body is too high") will be displayed on the vehicle instrument panel, and a voice prompt will be sent to the smart cockpit to remind the driver to turn off unnecessary electrical appliances. 2. Secondary protection (regulation level): If the parameter exceeds the threshold by less than 5%, that is, the ratio is greater than 1 but less than 1.05, the load adjustment is automatically performed, such as reducing the air conditioner load level (from level 5 to level 3), turning off the ambient light and the rear screen, and reducing the circuit current to within the threshold range without disconnecting the electrical appliances. 3. Level 3 protection (emergency level): If the parameter exceeds the threshold by more than 10%, i.e. the ratio is greater than 1.1, or the circuit temperature exceeds 90℃, the power supply of the corresponding circuit will be cut off immediately through the relay. At the same time, the fault data (operating condition, parameters, protection action) will be recorded and the fault information will be uploaded to the cloud to prevent the electrical system from burning or catching fire.

[0084] In summary, the implementation flow of the electrical system management method in this application embodiment is as follows: Figure 5 As shown, it includes the following steps: Step 1: Collect all vehicle parameters.

[0085] By deploying a sensor network across various areas of the vehicle, two types of operating parameters and electrical parameters are collected in real time at a frequency of no less than 100Hz to ensure data timeliness.

[0086] Step 2: Parameter preprocessing and anomaly diagnosis.

[0087] The collected global parameters are processed in multiple dimensions to ensure the accuracy and validity of the input data, including Kalman filtering, 3σ outlier removal, standardization and critical modeling.

[0088] Step 3: Calculate the dynamic protection threshold.

[0089] A threshold calculation model based on a fuzzy neural network is constructed. The preprocessed global parameters are input, and the protection thresholds (including overcurrent threshold, overvoltage threshold, undervoltage threshold, and temperature threshold) of each electrical circuit and appliance in the vehicle are calculated in real time. The calculation delay of the model does not exceed 50ms, which meets the real-time requirements.

[0090] Step 4: Threshold update and hierarchical protection execution.

[0091] The central processing unit synchronizes the calculated dynamic protection thresholds to each domain controller (power domain controller, body domain controller, etc.) via the bus, updates the original fixed thresholds, and monitors the parameters of each circuit and electrical appliance in real time, triggering graded protection actions: Level 1 warning (warning level): When the parameter reaches 90% of the threshold, such as when the overcurrent threshold is 20A and the current reaches 18A, a warning message (such as "the electrical load on the vehicle body is too high") is displayed on the vehicle instrument panel, and a voice prompt is sent to the smart cockpit to remind the driver to turn off unnecessary electrical appliances. Level 2 protection (regulation level): When the parameter exceeds the threshold but does not reach the danger value (e.g., exceeding the threshold by less than 5%), the load adjustment is automatically performed, such as reducing the air conditioner load level (from level 5 to level 3), turning off the ambient light and the rear screen, and reducing the circuit current to within the threshold range without disconnecting the electrical appliances; Level 3 protection (emergency level): If the parameter exceeds the danger threshold (e.g., exceeds the threshold by more than 10%) or the circuit temperature exceeds 90°C, the power supply to the corresponding circuit will be immediately cut off through the relay. At the same time, the fault data (operating condition, parameters, protection action) will be recorded and the fault information will be uploaded to the cloud to prevent the electrical system from burning or catching fire.

[0092] Step 5: Data storage and model iterative optimization.

[0093] Establish a closed-loop data system between the vehicle and the cloud to continuously optimize the threshold calculation model. Vehicle data storage: The vehicle T-BOX stores the operating parameters, electrical parameters, and protection action results of each threshold adjustment. The storage period is 6 months or 10,000 kilometers, and the data capacity is no less than 16GB. It supports local export of fault data (such as via USB interface). Cloud data upload: Every 500 kilometers or every month, the stored data is automatically uploaded to the cloud server, and a massive vehicle database (covering vehicle data of different brands, models and mileage) is built in the cloud. Model Iterative Optimization: The gradient boosting tree algorithm is used in the cloud to optimize the parameters of the threshold calculation model (such as the weight coefficients of the fuzzy neural network) based on massive amounts of data. For example, for vehicles in high-temperature areas in the south, the influence coefficient of temperature parameters on the threshold is adjusted so that the model can accurately calculate the threshold under different regional and climatic conditions. The optimized model is pushed to the vehicle's central processing unit through OTA (Over-the-Air) technology to achieve one-time development and continuous optimization.

[0094] The electrical system management method based on this application can achieve: Improved protection accuracy: Fixed thresholds in related technologies may falsely trigger vehicle protection actions. This application can dynamically adjust the protection threshold to avoid false protection actions and improve protection accuracy. System energy efficiency optimization: The threshold of non-critical circuits (speakers, ambient lighting) is lowered to reduce energy consumption and improve battery life; Improved platform compatibility: The model is automatically calibrated to fit the compact car, eliminating the need for separate development of protection logic and shortening the development cycle.

[0095] The electrical system management method of this application embodiment is described below through a specific example, taking the cold start condition of a fuel vehicle in winter as an example.

[0096] Step 1: Collect all vehicle parameters.

[0097] Sensor deployment and data sources: based on Figure 2 The vehicle parameter acquisition network layout diagram shows that the engine speed sensor, battery SOC sensor, and coolant temperature sensor are deployed in the power domain; the ambient temperature sensor, air conditioning load sensor, and seat heating load sensor are deployed in the body domain; and the starter current / voltage sensor and air conditioning circuit current sensor are deployed in the low-voltage auxiliary circuit. All sensors communicate with the central processing unit via the CAN bus, and the acquisition frequency is set to 120Hz.

[0098] The specific data collected includes: real-time engine speed of 1200 rpm, battery SOC of 70%, coolant temperature of -5℃, ambient temperature of -15℃, starter instantaneous current of 220A, air conditioning circuit current of 18A, seat heating circuit current of 12A, battery voltage of 11.6V, and circuit temperature of -8℃.

[0099] Step 2: Parameter preprocessing and anomaly diagnosis.

[0100] Filtering: To address the electromagnetic interference (current fluctuation ±3A) generated by the starter motor, a Kalman filter algorithm is used to control the current fluctuation range within ±0.4A, ensuring stable starter motor current data (220A±0.4A).

[0101] Outlier removal: Based on the 3σ principle, the collected battery voltage of 11.6V is verified (the voltage fluctuation within 10ms decreases from 11.8V to 11.6V, the trend is reasonable, and it is judged as valid data); if a sensor failure causes the current to suddenly drop to 0A, a fault warning will be triggered and the location will be recorded (such as the starter current sensor).

[0102] Standardization and Correlation Processing: Engine speed (0-6000rpm) was standardized to 0.2 (1200 / 6000), and battery voltage (12-14.5V) was standardized to 0.04 ((11.6-12) / (14.5-12)). At the same time, a correlation model of "battery SOC-starter current-ambient temperature" was established to clarify the coupling relationship between starter current demand and voltage decay when SOC is 70% at low temperature.

[0103] Step 3: Calculate the dynamic protection threshold for the whole vehicle.

[0104] Model Input and Triggering Logic: Input the preprocessed standardized parameters into the fuzzy neural network model (computation delay 40ms), triggering three types of threshold adjustment logic: Power domain condition triggering: Engine speed 1200rpm (initial cold start), battery SOC 70%, starter motor requires instantaneous high current, the model increases the starter circuit overcurrent threshold from the conventional 180A to 250A (corresponding to...) Figure 3 The circuit exhibits a "temperature rise - threshold rise" trend, but its current tolerance does not decrease at low temperatures, requiring adaptation to high current demands. Electrical load triggering: Air conditioner (level 4 load) + seat heater (level 3 load) operating under high load; the model adjusts the overcurrent thresholds for the two circuits from 15A and 10A to 20A and 14A respectively (corresponding to...). Figure 3 (Logic for increasing load - increasing threshold). Low-voltage triggering: When the battery voltage is low (11.6V), the model lowers the undervoltage threshold of the low-voltage auxiliary circuit from 11.5V to 11.2V (to avoid false triggering of undervoltage protection), and at the same time lowers the overcurrent threshold of non-critical circuits (such as audio and ambient lighting) from 20A to 17.6A (to reduce ineffective energy consumption and adapt to the battery power supply capacity at low temperatures).

[0105] Vehicle model adaptation calibration: Input the basic parameters of the compact car (wheelbase 2650mm, conductor cross-sectional area 1.5mm², etc.), and the model will automatically calibrate the threshold calculation coefficients without the need to develop separate protection logic (solving the problem of poor platform compatibility in traditional solutions).

[0106] Step 4: Threshold update and hierarchical protection execution.

[0107] Threshold synchronization: The central processing unit synchronizes the calculated dynamic thresholds (starter 250A, air conditioning 20A, seat heating 14A, undervoltage 11.2V, audio 17.6A) to the power domain controller and body domain controller via the CAN bus, overriding the original fixed thresholds.

[0108] Real-time monitoring and protection actions: The instantaneous current of the starter is 220A (not exceeding the 250A threshold), which does not trigger the protection and successfully completes the cold start (solving the problem of false triggering and start failure in related technologies). The battery voltage is 11.6V (above the 11.2V undervoltage threshold), and no protection action is taken; if the voltage subsequently drops to 11.3V (reaching 93% of the threshold), a Level 1 warning will be triggered (corresponding to...). Figure 4 (Level 1 warning logic): The vehicle instrument panel displays "Battery power is low", and the smart cockpit voice prompts "It is recommended to turn off unnecessary electrical appliances" to avoid electrical system failure due to undervoltage. The air conditioning and seat heating currents are 18A and 12A respectively (both within the adjusted threshold). The system runs continuously, while the power supply distribution is optimized through a load adjustment algorithm (to avoid exceeding the total current limit).

[0109] Step 5: Data storage and model iterative optimization.

[0110] Vehicle-mounted storage: All parameters of this operating condition (collected data, preprocessing results, threshold adjustment records, and protection actions) are stored via the vehicle-mounted T-BOX, with a storage period of 6 months.

[0111] Cloud upload and optimization: After the vehicle has traveled 500 kilometers, the cold start condition data is automatically uploaded to the cloud server. The cloud uses the GBDT algorithm to optimize the weight coefficient of "ambient temperature - starter threshold" in the fuzzy neural network (for scenarios in low-temperature areas in the north). Subsequently, the optimized model is pushed to the vehicle via OTA to improve the accuracy of threshold calculation for subsequent cold start conditions.

[0112] For example, in the case of a dual operating condition of high temperature and low battery, the current parameters obtained are: ambient temperature: 42℃, circuit temperature: 70℃, battery SOC: 18%, and air conditioner running at full load (level 5). Trigger commands are generated based on the current parameters, and there are conflicts between the trigger commands, as shown in Table 1.

[0113] Table 1

[0114] Based on the weights and reference thresholds mentioned above, a weighted calculation is performed to obtain T=(0.55×26A)+(0.45×19A)=14.3+8.55=22.85A. The final output overcurrent threshold for the air conditioning circuit is set to 22.85A, which ensures both high-temperature heat dissipation requirements and prevents excessive power consumption under low power conditions.

[0115] According to the electrical system management method proposed in this application, vehicle parameters can be input into a pre-built protection threshold decision model. The protection decision threshold model outputs a target protection threshold that matches the current actual state of the vehicle. This enables the determination of the target protection threshold based on the current actual state of the vehicle, achieving a match between the target protection threshold and the actual state. Furthermore, the electrical system can be managed based on the current operating parameters of electrical circuits and appliances and the target protection threshold. This improves the accuracy of electrical system protection under different states, avoids false triggering or insufficient protection when fixed thresholds change operating conditions, thereby improving the operational reliability of the electrical system and ensuring its safe operation.

[0116] Next, the electrical system management device according to the embodiments of this application is described with reference to the accompanying drawings.

[0117] Figure 6 This is a block diagram of an electrical system management device according to an embodiment of this application.

[0118] like Figure 6 As shown, the electrical system management device 10 includes: an acquisition module 100, an input module 200, and a management module 300.

[0119] The acquisition module 100 is used to acquire vehicle parameters, including operating parameters and electrical parameters; the input module 200 is used to preprocess the vehicle parameters and input the preprocessed target vehicle parameters into a pre-built protection threshold decision model, which outputs the target protection thresholds for the vehicle's electrical circuits and appliances; the management module 300 is used to acquire the current operating parameters of the electrical circuits and appliances and manage the electrical system based on the current operating parameters and the target protection thresholds.

[0120] It should be noted that the foregoing explanation of the embodiment of the electrical system management method also applies to the electrical system management device of this embodiment, and will not be repeated here.

[0121] According to the electrical system management device proposed in the embodiments of this application, vehicle parameters can be input into a pre-built protection threshold decision model. The protection decision threshold model outputs a target protection threshold that matches the current actual state of the vehicle. This enables the determination of the target protection threshold based on the current actual state of the vehicle, achieving a match between the target protection threshold and the actual state. Furthermore, the electrical system is managed based on the current operating parameters of the electrical circuits and appliances and the target protection threshold. This improves the accuracy of electrical system protection under different states, avoids false triggering or insufficient protection when fixed thresholds change operating conditions, thereby improving the operational reliability of the electrical system and ensuring its safe operation.

[0122] Figure 7 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 701, the processor 702, and the computer program stored on the memory 701 and executable on the processor 702.

[0123] When the processor 702 executes the program, it implements the electrical system management method provided in the above embodiments.

[0124] Furthermore, the vehicle also includes: Communication interface 703 is used for communication between memory 701 and processor 702.

[0125] The memory 701 is used to store computer programs that can run on the processor 702.

[0126] The memory 701 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0127] If the memory 701, processor 702, and communication interface 703 are implemented independently, then the communication interface 703, memory 701, and processor 702 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0128] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.

[0129] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0130] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the above-described electrical system management method.

[0131] This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the above-described electrical system management method.

[0132] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0133] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0134] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0135] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0136] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. An electrical system management method, characterized in that, Includes the following steps: Obtain vehicle parameters, including operating parameters and electrical parameters; The vehicle parameters are preprocessed, and the preprocessed target vehicle parameters are input into a pre-built protection threshold decision model. The protection threshold decision model outputs the target protection thresholds for the vehicle's electrical circuits and electrical appliances. Obtain the current operating parameters of the electrical circuit and the electrical appliances, and manage the electrical system based on the current operating parameters and the target protection threshold.

2. The electrical system management method according to claim 1, characterized in that, The operating parameters include at least one of the following: engine speed, motor speed, battery SOC, high-voltage battery SOH, coolant temperature, engine oil temperature, vehicle speed, braking status, steering angle, ambient temperature, interior temperature, light intensity, number of in-vehicle screens open, and audio volume level.

3. The electrical system management method according to claim 1, characterized in that, The electrical parameters include at least one of the following: current, voltage, circuit temperature, wire resistance of each electrical circuit, and operating status and load level of each electrical appliance.

4. The electrical system management method according to claim 1, characterized in that, The protection threshold decision model is a fuzzy neural network model, which includes a fuzzification layer, an inference layer, and a defuzzification layer.

5. The electrical system management method according to claim 4, characterized in that, The fuzzification layer is used to calculate the membership degree of the target vehicle parameters on each fuzzy set; The inference layer is used to match at least one target rule from a preset fuzzy rule base based on the target vehicle parameters, extract the target vehicle parameters and reference threshold contained in each target rule, and select the minimum value of the membership degree corresponding to the target vehicle parameters as the activation intensity of the corresponding target rule. The deblurring layer is used to take the activation intensity of each target rule as the weight of the corresponding rule, and calculates the target protection threshold of the electrical circuit and the appliance based on the weight of each target rule and the reference threshold.

6. The electrical system management method according to claim 5, characterized in that, Before managing the electrical system based on the current operating parameters and the target protection threshold, the method further includes: When a conflict is detected between the reference threshold corresponding to the target rule, the target protection threshold is corrected. The electrical system is managed based on the revised target protection threshold and the current operating parameters.

7. The electrical system management method according to claim 6, characterized in that, The modification of the target protection threshold includes: Identify the category of each of the target rules; The safety weight of the corresponding target rule is determined based on the category and / or the vehicle parameters, and the corrected target protection threshold is calculated by weighting the safety weight of each target rule with a reference threshold.

8. The electrical system management method according to claim 1, characterized in that, Managing the electrical system based on the current operating parameters and the target protection threshold includes: The corresponding protection level is determined based on the current operating parameters and the target protection threshold. The corresponding management strategy is determined based on the protection level, and the electrical system is managed according to the management strategy.

9. The electrical system management method according to claim 8, characterized in that, The step of determining the corresponding protection level based on the current operating parameters and the target protection threshold includes: Calculate the ratio between the current operating parameters and the target protection threshold; The protection level is determined based on the ratio.

10. The electrical system management method according to claim 9, characterized in that, Determining the protection level based on the ratio includes: Obtain the first correspondence between the ratio and the protection level; The corresponding protection level is determined based on the ratio and the first correspondence.

11. The electrical system management method according to claim 8, characterized in that, The step of determining the corresponding management strategy based on the protection level includes: Obtain the second correspondence between protection levels and management policies; The corresponding management strategy is determined based on the protection level and the second correspondence.

12. An electrical system management device, characterized in that, include: The acquisition module is used to acquire vehicle parameters, wherein the vehicle parameters include operating parameters and electrical parameters; The output module is used to preprocess the vehicle parameters and input the preprocessed target vehicle parameters into a pre-built protection threshold decision model. The protection threshold decision model outputs the target protection thresholds for the vehicle's electrical circuits and electrical appliances. The management module is used to obtain the current operating parameters of the electrical circuit and the electrical appliances, and manage the electrical system according to the current operating parameters and the target protection threshold.

13. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the electrical system management method as described in any one of claims 1-11.

Images