A method and system for diagnosing short circuits in LED lamp beads for new energy vehicles

Abstract

This invention relates to the field of vehicle fault diagnosis technology, and in particular to a method and system for diagnosing short circuits in LED beads of new energy vehicles. The method includes the following steps: acquiring reference electrical characteristic parameters of each independently controlled LED unit under a preset fault-free operating state; acquiring real-time electrical characteristic parameters of each independently controlled LED unit during the execution of the dynamic lighting sequence of the turn signal; comparing the real-time electrical characteristic parameters of each independently controlled LED unit with the corresponding reference electrical characteristic parameters to obtain a comparison result; by monitoring the electrical characteristic parameters of the LED units in real time and comparing them with the reference parameters, faults caused by short circuits in a few LED beads can be detected in a timely manner, and when the turn signal is associated with an advanced driver assistance system, a warning message is sent to the system, thereby reducing safety risks.

Description

Technical Field

[0001] This invention relates to the field of vehicle fault diagnosis technology, and in particular to a method and system for diagnosing short circuits in LED lamp beads for new energy vehicles. Background Technology

[0002] The dynamic sequential LED turn signal system of new energy vehicles consists of multiple timing-controlled LED units. These units constantly face environmental challenges such as vibration and temperature / humidity variations, which can easily cause individual LEDs to short-circuit due to internal defects or packaging flaws. This short circuit reduces the equivalent resistance of the faulty unit. If the drive system fails to accurately compensate for or detect this minute change in electrical characteristics, the faulty unit will exhibit decreased brightness, partial blackouts, or deviations in its on / off timing compared to the normal units. This results in visual inconsistencies, dark spots, or rhythmic irregularities (such as breaks or uneven speeds) in the dynamic sequential effect. However, such subtle defects are difficult to detect when the driver is focused on driving or in bright daylight, and are easily mistaken for aging or contamination of the lights.

[0003] However, modern new energy vehicles generally integrate Advanced Driver Assistance Systems (ADAS), such as automatic lane change assist. Their existing turn signal status confirmation mechanisms (such as monitoring the overall circuit status, total current / voltage, or simple camera judgment) are often unable to effectively identify subtle distortions in this dynamic flow effect. The system may still determine that the turn signal is working normally and continue to execute the automatic lane change command even when the integrity and clarity of the dynamic turn signal are compromised. In this case, the vehicle is actually maneuvering with a turn signal that may be misread or delayed by other road users (for example, an inconsistent flow effect makes it difficult for drivers behind to accurately predict the lane change trajectory or timing). This undoubtedly increases the risk of potential conflicts with other vehicles during automatic lane changes, or forces other drivers to take more sudden evasive actions, posing a threat to traffic safety. If such faults are not diagnosed and repaired in a timely manner, they not only continue to affect driving safety but also make it difficult for maintenance personnel to quickly and accurately locate the root cause of the abnormal dynamic effect using conventional testing methods—that is, which LEDs in which LED unit are short-circuited—leading to increased repair time and costs.

[0004] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a short-circuit diagnosis method and system for LED lamp beads in new energy vehicles.

[0006] In a first aspect, the present invention provides a method for diagnosing short circuits in LED lamp beads of new energy vehicles, applicable to turn signals with multiple independently controllable LED units, the method comprising the following steps:

[0007] Obtain the reference electrical characteristic parameters of each independently controlled LED unit turn signal under a preset fault-free operating state;

[0008] During the execution of the dynamic lighting sequence of the LED unit turn lights, the real-time electrical characteristic parameters of each independently controlled LED unit turn light are acquired in real time.

[0009] The comparison results are obtained by comparing the real-time electrical characteristic parameters of each independently controlled LED unit turn signal with the corresponding reference electrical characteristic parameters;

[0010] Based on the comparison results, it is determined whether the deviation of the real-time electrical characteristic parameters from the reference electrical characteristic parameters exceeds a preset fault determination threshold, so as to determine whether the independently controlled LED unit turn signal has experienced a target fault caused by a short circuit of a few LED beads.

[0011] When it is determined that the target fault has occurred in the independently controlled LED unit turn signal, and the illumination of the LED unit turn signal is associated with the operation decision of the advanced driver assistance system, a warning message is sent to the advanced driver assistance system.

[0012] Preferably, the step of sending a warning message to the advanced driver assistance system when it is determined that the independently controlled LED unit turn signal has experienced the target fault, and the illumination of the LED unit turn signal is associated with the operation decision of the advanced driver assistance system, includes:

[0013] Obtain fault severity information that characterizes the severity of the target fault, and obtain operational risk information that characterizes the current operational decision risk level of the advanced driver assistance system;

[0014] Based on the severity information of the fault and the operational risk information, the differentiated content of the warning information is determined, and the differentiated content is used to enable the advanced driver assistance system to perform risk assessment and behavior adjustment;

[0015] Based on the determined differentiated content, the warning information is generated and sent to the advanced driver assistance system.

[0016] Preferably, the step of determining the differentiated content of the warning information based on the fault severity information and the operational risk information, wherein the differentiated content is used to enable the advanced driver assistance system to perform risk assessment and behavior adjustment, includes:

[0017] The severity information of the fault is converted into a first decision factor, and the operational risk information is converted into a second decision factor.

[0018] A preset fusion strategy is applied to the first decision factor and the second decision factor to generate a fused decision basis;

[0019] Based on the fused decision criteria, the differentiated content of the early warning information is determined.

[0020] Preferably, the fusion strategy incorporates specific processing logic for situations where the indication directions of the first decision factor and the second decision factor are inconsistent or potentially conflicting.

[0021] Preferably, the step of applying a preset fusion strategy to the first decision factor and the second decision factor to generate a fused decision basis includes:

[0022] Acquire vehicle operating condition information and on-board system information status;

[0023] Based on the vehicle operating condition information and the vehicle system information status, an effectiveness evaluation is performed to determine whether the decision effectiveness of the preset fusion strategy used to generate a fused decision basis from the first decision factor and the second decision factor meets the preset effectiveness requirements under the current conditions.

[0024] If not satisfied, the operating parameters or internal processing logic of the preset fusion strategy are adjusted according to the vehicle operating condition information, the vehicle system information status, and the preset strategy adjustment rules to obtain the adjusted fusion strategy.

[0025] Based on the results of the performance evaluation, the adjusted fusion strategy or the original preset fusion strategy is selected and applied to the first decision factor and the second decision factor to generate the fused decision basis.

[0026] Preferably, the step of adjusting the operating parameters or internal processing logic of the preset fusion strategy based on the vehicle operating condition information, the vehicle system information status, and preset strategy adjustment rules to obtain the adjusted fusion strategy includes:

[0027] Based on the vehicle operating condition information, the vehicle system information status, and the preset strategy adjustment rules, the operating parameters or internal processing logic of the preset fusion strategy are adjusted to obtain the initial adjusted fusion strategy.

[0028] Obtain verification input for verifying the initial adjusted fusion strategy, wherein the verification input is adapted to the current vehicle operating condition information and the vehicle system information status;

[0029] The verification input is applied to the initial adjusted fusion strategy and a reference strategy respectively to obtain the adjusted strategy output of the initial adjusted fusion strategy and the reference output of the reference strategy. The reference strategy is the preset fusion strategy or the preset baseline security strategy before adjustment.

[0030] Based on the preset evaluation rules, the performance of the initial adjusted fusion strategy is evaluated based on the adjustment strategy output, the reference output, and the expected output corresponding to the verification input.

[0031] Based on the performance, either the initial adjusted fusion strategy or the reference strategy is selected as the adjusted fusion strategy.

[0032] Preferably, the step of evaluating the performance of the initial adjusted fusion strategy based on the adjusted strategy output, the reference output, and the expected output corresponding to the verification input, according to preset evaluation rules, includes:

[0033] The verification input, the adjustment strategy output, the reference output, and the expected output corresponding to the verification input are associated with preset risk scenarios that characterize the new energy vehicle under specific LED unit turn signal indication and advanced driver assistance system operation states.

[0034] Based on the associated risk scenarios, the decision risk of the decisions corresponding to the adjustment strategy output, the reference output, and the expected output under the risk scenarios is assessed, and the decision risk assessment results corresponding to each output are obtained.

[0035] Based on the preset evaluation rules and the decision risk assessment results corresponding to each output, the performance of the initial adjusted fusion strategy is evaluated.

[0036] Preferably, the step of assessing the decision risk of the decisions corresponding to the adjustment strategy output, the reference output, and the expected output under the risk scenario based on the associated risk scenario includes:

[0037] For the decisions corresponding to the adjustment strategy output, the reference output, and the expected output, respectively, obtain the characteristic parameters of the decisions under the associated risk scenarios;

[0038] Based on the preset risk measurement standards, the characteristic parameters are matched with the preset risk levels or risk scoring tables to determine the corresponding safety impact or probability of functional failure.

[0039] Preferably, the step of applying a preset fusion strategy to the first decision factor and the second decision factor to generate a fused decision basis further includes:

[0040] The first decision factor and the second decision factor are respectively fuzzified to obtain the fuzzy membership degree μ_D1 of the first decision factor and the fuzzy membership degree μ_D2 of the second decision factor.

[0041] Based on the fuzzy membership degree μ_D1 of the first decision factor, the fuzzy membership degree μ_D2 of the second decision factor, and the preset fuzzy rule set R, fuzzy inference is performed to obtain multiple fuzzy output sets μ_F_k_out.

[0042] The multiple fuzzy output sets μ_F_k_out are aggregated to obtain a total fuzzy output set μ_F_total, wherein the aggregation process is implemented using the S-norm operator;

[0043] The total fuzzy output set μ_F_total is defuzzified to generate the fused decision basis F.

[0044] Secondly, a short-circuit diagnostic system for LED lamp beads in new energy vehicles is provided, applicable to turn signals with multiple independently controllable LED units. This system includes:

[0045] The parameter acquisition module is used to acquire the reference electrical characteristic parameters of each independently controlled LED unit turn light under the preset fault-free working state.

[0046] The real-time parameter acquisition module is used to acquire the real-time electrical characteristic parameters of each independently controlled LED unit turn light during the execution of the dynamic lighting sequence of the LED unit turn light.

[0047] The parameter comparison module is used to compare the real-time electrical characteristic parameters of each independently controlled LED unit turn signal with the corresponding reference electrical characteristic parameters to obtain the comparison result.

[0048] The fault determination module is used to determine, based on the comparison result, whether the deviation of the real-time electrical characteristic parameters from the reference electrical characteristic parameters exceeds a preset fault determination threshold, so as to determine whether the independently controlled LED unit turn signal has experienced a target fault caused by a short circuit of a few LED beads.

[0049] The warning information sending module is used to send warning information to the advanced driver assistance system when it is determined that the independently controlled LED unit turn signal has the target fault, and the illumination of the LED unit turn signal is associated with the operation decision of the advanced driver assistance system.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] By monitoring the real-time electrical characteristic parameters of each independently controlled LED unit that makes up the dynamic flowing effect turn signal with fine granularity and comparing them with the reference parameters under fault-free conditions, it is possible to accurately diagnose unit-level hidden faults caused by short circuits of a few LED beads that are difficult to identify by traditional methods. When the turn signal is associated with the operation decision of the advanced driver assistance system, it can promptly send a warning message to the advanced driver assistance system indicating that the light effect may be impaired, thereby reducing safety risks. It has the advantage of being able to diagnose LED bead short circuit faults in the LED light group in a timely manner and reduce safety risks. Attached Figure Description

[0052] Figure 1 This is a flowchart of the method of the present invention.

[0053] Figure 2 This is a system structure diagram of the present invention.

[0054] In the diagram: 201, Parameter Acquisition Module; 202, Real-time Parameter Acquisition Module; 203, Parameter Comparison Module; 204, Fault Judgment Module; 205, Early Warning Information Sending Module. Detailed Implementation

[0055] Embodiments of the present invention are described in detail below, examples of which 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 are only used to explain the present invention, and should not be construed as limiting the present invention.

[0056] 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 one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0057] For example, suppose a new energy vehicle is driving on a highway, and its advanced driver assistance system (ADAS) activates its automatic lane change assist function. The system instructs the vehicle to illuminate the turn signals with a dynamic flowing effect, signaling its intention to change lanes to surrounding vehicles. At this moment, a small number of LEDs in an independently controlled LED unit within the turn signal assembly short-circuit, causing a decrease in the unit's equivalent resistance. Although the drive circuit attempts to maintain normal operation, a slight deviation in the brightness or timing of this unit within the dynamic illumination sequence creates a barely noticeable dark spot or discontinuity in the flowing light band. The driver, focused on the road ahead, fails to notice this subtle anomaly. The on-board diagnostic system may only monitor the total current of the entire turn signal circuit. Because the number of short-circuited LEDs is small, the change in total current does not exceed a preset threshold, and the system determines that the turn signal is working normally. The ADAS receives the signal that the turn signal is illuminated and continues the automatic lane change operation accordingly. However, drivers of vehicles behind may fail to accurately and promptly understand the lane change signal due to the distortion of the turn signal's dynamic light effect, increasing potential traffic risks.

[0058] In this regard, this application makes the following... Figure 1 The method shown is a short-circuit diagnosis method for LED lamp beads in new energy vehicles, applied to turn signals with multiple independently controllable LED units. The method includes the following steps:

[0059] Obtain the reference electrical characteristic parameters of each independently controlled LED unit turn signal under a preset fault-free operating state;

[0060] During the execution of the dynamic lighting sequence of the LED unit turn lights, the real-time electrical characteristic parameters of each independently controlled LED unit turn light are acquired in real time.

[0061] The real-time electrical characteristic parameters of each independently controlled LED unit turn signal are compared with the corresponding reference electrical characteristic parameters to obtain the comparison results;

[0062] Based on the comparison results, it is determined whether the deviation of the real-time electrical characteristic parameters from the reference electrical characteristic parameters exceeds a preset fault judgment threshold, so as to determine whether the independently controlled LED unit turn signal has experienced a target fault caused by a short circuit of a few lamp beads.

[0063] When a target malfunction is detected in the independently controlled LED unit turn signal, and the illumination of the LED unit turn signal is related to the operation decision of the advanced driver assistance system, a warning message is sent to the advanced driver assistance system.

[0064] In this context, an independently controlled LED unit refers to the smallest set of LEDs that constitute the dynamic flowing effect turn signals and can be controlled by a separate drive circuit to turn on or off. This can be achieved using a single LED, a series connection, or a parallel connection of LED beads. Electrical characteristic parameters are physical quantities that characterize the electrical properties of an LED unit, and can be implemented using parameters such as current, voltage, resistance, and power. The preset fault judgment threshold is the boundary value used to determine whether a deviation of real-time electrical characteristic parameters from the reference parameter constitutes a fault; it is mainly used to distinguish between normal fluctuations and abnormal changes caused by faults. A target fault caused by a short circuit in a few LED beads refers to a fault mode in which a short circuit occurs in some LED beads within the LED unit, causing a change in the overall electrical characteristics of the unit, but not yet leading to complete unit failure or a current change amplitude insufficient to be identified by traditional macroscopic monitoring methods. This is mainly used to identify this type of highly concealed fault that affects the continuity of dynamic lighting effects. The connection between turn signal illumination and the operational decisions of advanced driver assistance systems (ADAS) in new energy vehicles means that before performing certain operations, the ADAS will issue a command to illuminate the turn signals, using the turn signal illumination status as an input or prerequisite in its decision-making or execution process. This is primarily to ensure that the vehicle can convey its intentions to the outside world through light signals when performing assisted driving functions. Warning information sent to the ADAS includes information about whether the dynamic display effect of the turn signals may no longer meet expectations (e.g., inconsistent flow, uneven brightness, abnormal timing). This is mainly to remind the ADAS that the effectiveness of the current turn signal may be reduced, thereby affecting its decisions based on the signal.

[0065] Specifically, this method first establishes a diagnostic benchmark by acquiring the baseline electrical characteristic parameters of each independently controlled LED unit under a preset fault-free operating state. These baseline parameters reflect the electrical characteristics of the LED unit under normal conditions. Subsequently, during the dynamic lighting sequence of the turn signals, the system acquires the real-time electrical characteristic parameters of each independently controlled LED unit. These real-time parameters reflect the actual electrical performance of the LED unit under the current operating state. Next, the real-time acquired electrical characteristic parameters are compared with the corresponding baseline electrical characteristic parameters to obtain the degree of deviation. Based on the comparison results, it is determined whether the deviation of the real-time electrical characteristic parameters from the baseline electrical characteristic parameters exceeds a preset fault judgment threshold. If the deviation exceeds the threshold, it is determined that the independently controlled LED unit has experienced a target fault caused by a short circuit of a few LEDs. This judgment based on unit-level parameter deviation can identify minute changes that are difficult to capture by traditional methods. Finally, when it is determined that the independently controlled LED unit has experienced a target fault, and the lighting of the turn signals is associated with the operation decision of the advanced driver assistance system of the new energy vehicle, the system will send a warning message to the advanced driver assistance system. This warning message explicitly indicates that the integrity or clarity of the turn signal's dynamic lighting effect may have been compromised, thus reminding the advanced driver assistance system (ADAS) to consider potential distortion of the light signal when making decisions and avoid performing operations based on erroneous information. The entire process, through refined monitoring, benchmark-based comparison and judgment, and integration with the ADAS, achieves effective diagnosis and risk avoidance of hidden faults.

[0066] As a preferred embodiment, the solution of this application is implemented as follows: A diagnostic function is integrated into the turn signal control module of a new energy vehicle. This module contains multiple LED driver circuits, each controlling an independent LED unit. Before the vehicle leaves the factory or during initial use, the current value of each LED unit is measured under standard voltage, and these current values ​​are stored in the memory of the control module as reference electrical characteristic parameters. During vehicle operation, when the turn signal is activated to perform dynamic sequential illumination, the control module monitors the actual operating current of each illuminated LED unit in real time through a current sampling circuit, using this as a real-time electrical characteristic parameter. The microprocessor within the control module compares the real-time current value with the stored corresponding reference current value and calculates the current deviation percentage. A fault judgment threshold is preset, for example, a current deviation exceeding 5%. If the real-time current of a certain LED unit deviates from its reference current by more than 5%, it is determined that the unit has experienced a short circuit fault in a few LED beads. Simultaneously, the vehicle's advanced driver assistance system sends an illumination command to the turn signal control module before executing an automatic lane change. When the turn signal control module detects a fault and receives an activation command from the Advanced Driver Assistance System (ADAS), it sends a specific fault message to the ADAS via the vehicle's CAN bus. This message contains a fault code indicating a potential abnormality in the dynamic lighting effect of the left (or right) front turn signal. Upon receiving this message, the ADAS can adjust or cancel the current automatic lane change operation based on its internal logic.

[0067] As one embodiment of the present invention, when it is determined that a target fault has occurred in the independently controlled LED unit, and the illumination of the LED unit's turn signal is associated with the operation decision of the advanced driver assistance system, the step of sending a warning message to the advanced driver assistance system includes:

[0068] Obtain fault severity information that characterizes the severity of the target fault, and obtain operational risk information that characterizes the risk level of the current operational decision of the advanced driver assistance system;

[0069] Based on fault severity information and operational risk information, differentiated content of warning information is determined. This differentiated content enables advanced driver assistance systems to perform risk assessments and behavior adjustments.

[0070] Based on the identified differentiated content, a warning message is generated and sent to the advanced driver assistance system.

[0071] The severity information refers to the degree to which a target fault affects the dynamic luminous efficacy of the turn signals. This can be achieved using quantitative indicators, such as the number of faulty LED units, their position in the dynamic sequence, or the percentage of their impact on the overall current or brightness. Operational risk information can be assessed based on factors such as the vehicle's current speed, surrounding traffic conditions, and the specific functions performed by the advanced driver assistance system. Differentiated warning information refers to the specific content of the warning information adjusted based on the severity and operational risk information. This can include different warning levels, different text descriptions, or different intensities of visual or auditory cues.

[0072] The method works by first acquiring fault severity information—quantifying the actual impact of the fault on the turn signal's visual effect—when a target fault occurs in an independently controlled LED unit and meets the conditions associated with an Advanced Driver Assistance System (ADAS). Simultaneously, it acquires operational risk information assessing the urgency of the current ADAS operation's requirement for clear turn signal signals. Then, based on these two types of information, a pre-defined logic or algorithm determines the specific content of the warning message. This process considers both the "supply-side" impact of the fault and the "demand-side" risk of ADAS operation, making the warning information more targeted. Finally, the warning message is generated and sent based on the determined differentiated content. This approach, combined with basic fault diagnosis and judgment, allows the entire system to upgrade from simple fault detection and general warnings to intelligent warnings based on fault impact and usage scenarios. This enables the ADAS to receive more accurate risk alerts and adjust its behavior accordingly.

[0073] As one embodiment of the present invention, the step of determining differentiated content of warning information based on fault severity information and operational risk information, wherein the differentiated content is used to enable the advanced driver assistance system to perform risk assessment and behavior adjustment, includes:

[0074] The severity of the fault is converted into the first decision factor, and the operational risk information is converted into the second decision factor.

[0075] A preset fusion strategy is applied to the first decision factor and the second decision factor to generate a fused decision basis. The fusion strategy has built-in specific processing logic for situations where the indication direction of the first decision factor and the second decision factor is inconsistent or potentially conflicting.

[0076] Based on the integrated decision-making criteria, the differentiated content of the early warning information is determined.

[0077] Specifically, fault severity information and operational risk information are converted into a first decision factor and a second decision factor. These decision factors are quantified or standardized representations of the original information. This conversion allows different types of information to be processed within a unified framework. Furthermore, this application applies a pre-defined fusion strategy to the first and second decision factors to generate a fused decision basis. This fusion strategy is an algorithm or model used to comprehensively process multiple input information and produce an output result. It can be a rule-based system, a computational method based on a mathematical model, or a model trained using machine learning. The key to this fusion strategy lies in its built-in specific processing logic for situations where the indications of the first and second decision factors are inconsistent or potentially conflicting. This processing logic aims to identify and resolve contradictions between input information. For example, when the fault severity is low but the operational risk is extremely high, this logic ensures that the final fused decision basis fully reflects the potential danger brought by the high operational risk, rather than being diluted by the lower fault severity. This specific processing logic can be embodied in specific rules, weight allocation mechanisms, nonlinear mapping relationships, or decision tree branches within the fusion strategy. The decision-making basis after fusion is the result of comprehensively considering the two types of information and handling potential conflicts. It can be a single value, a risk level, a vector, or a more complex structure, used to guide the generation of subsequent early warning information.

[0078] Specifically, firstly, the severity information from the fault diagnosis module and the operational risk information from the advanced driver assistance system (ADAS) are transformed into a first decision factor and a second decision factor. This transformation process unifies the raw, potentially varied information into numerical or symbolic representations that are easy to calculate and compare. Subsequently, these two decision factors are input into a pre-defined fusion strategy. This fusion strategy is not simply a linear combination of the two factors, but includes specially designed processing logic to identify and resolve decision-making dilemmas that may arise when the severity of the fault and the direction of operational risk indications are inconsistent. For example, in certain high-risk driving scenarios, even if the severity level of a short-circuit fault in an LED bulb is not high, the fusion strategy may, based on a pre-defined safety priority principle, assign a higher weight to operational risk or trigger specific high-risk response rules, thereby generating a fusion decision basis reflecting the current high-risk state. Finally, based on this optimized fusion decision basis, the system can determine the differentiated content of the warning information. This differentiation is reflected in the urgency of the warning, the prompting method, and the level of detail provided to the ADAS. This approach, combined with basic fault diagnosis and early warning transmission schemes, forms a more intelligent and secure early warning decision-making mechanism, which can significantly improve the reliability and safety of the system, especially in scenarios where advanced driver assistance systems rely on turn signal signals for operation.

[0079] As one embodiment of the present invention, the step of applying a preset fusion strategy to the first decision factor and the second decision factor to generate a fused decision basis includes:

[0080] Acquire vehicle operating condition information and on-board system information status;

[0081] Based on vehicle operating condition information and on-board system information status, an effectiveness assessment is performed to determine whether the decision effectiveness of the preset fusion strategy used to generate a fused decision basis from the first and second decision factors meets the preset effectiveness requirements under the current conditions.

[0082] If not, the operating parameters or internal processing logic of the preset fusion strategy are adjusted based on the vehicle operating condition information, the status of the on-board system information, and the preset strategy adjustment rules to obtain the adjusted fusion strategy.

[0083] Based on the results of the performance evaluation, the adjusted fusion strategy or the original preset fusion strategy is selected and applied to the first and second decision factors to generate the fused decision basis.

[0084] Among these, vehicle operating condition information refers to data characterizing the current driving state of the vehicle, which may include information such as vehicle speed, acceleration, steering angle, braking status, ambient light, weather conditions, and road type. Vehicle system information status refers to data characterizing the current operating state of various systems within the vehicle, which may include information such as the operating mode of advanced driver assistance systems, sensor status, communication status, power status, and diagnostic system status. Performance evaluation is the process of evaluating the performance of a preset fusion strategy under the current vehicle operating conditions and vehicle system information status, which can be achieved using rule-based evaluation, model-based evaluation, or historical data-based evaluation. Preset performance requirements refer to the minimum standard or expected level set for the decision-making performance of the fusion strategy, which may be expressed as indicators such as decision accuracy, response time, and safety score. Preset strategy adjustment rules refer to the set of rules used to guide how to modify the preset fusion strategy based on the performance evaluation results, vehicle operating condition information, and vehicle system information status, which can be implemented using lookup tables, decision trees, expert systems, or machine learning models. An adjusted fusion strategy refers to a new fusion strategy obtained after adjustments. This can involve modifying the operating parameters of the original preset fusion strategy or altering its internal processing logic. Operating parameters are configurable values ​​that affect the output of the fusion strategy, and may include weights, thresholds, gain coefficients, etc., for different decision factors. Internal processing logic refers to the core algorithms or rules within the fusion strategy used to process input factors, perform fusion calculations, and resolve conflicts; it may include fuzzy inference rules, neural network structures, decision tree branching logic, etc.

[0085] The technical solution of this application aims to address the problem that preset fusion strategies may not always guarantee optimal decision-making performance under different vehicle operating conditions and on-board system states. By introducing an adaptive adjustment mechanism, the reliability and security of fusion decision-making are ensured. First, vehicle operating condition information and on-board system information status are acquired. This is the basis for performance evaluation and strategy adjustment. Different operating conditions and system states have a significant impact on the performance of the fusion strategy. For example, the tolerance for turn signal malfunctions should be higher under high-speed driving or inclement weather conditions. Second, based on this information, a performance evaluation is performed to determine whether the decision-making performance of the current preset fusion strategy meets the preset requirements. The performance evaluation considers factors such as the accuracy, response speed, and security of the fusion strategy under the current conditions. If the performance does not meet the requirements, strategy adjustment is necessary. Then, based on vehicle operating condition information, onboard system information status, and preset strategy adjustment rules, the preset fusion strategy is adjusted to obtain the adjusted fusion strategy. Adjustments may include modifying the fusion strategy's operating parameters, such as adjusting the weights of different decision factors, or modifying its internal processing logic, such as changing the conflict resolution mechanism. The adjusted fusion strategy also needs to have built-in or inherited processing logic for decision factor conflicts to ensure reasonable decisions are made under any circumstances. Finally, based on the performance evaluation results, either the adjusted fusion strategy or the original preset fusion strategy is selected for application. If the adjusted strategy improves decision-making efficiency, it is applied; otherwise, the original strategy continues to be used. This selection mechanism ensures that the fusion strategy is always in its optimal state, thereby improving the safety and reliability of the advanced driver assistance system. This adaptive adjustment mechanism, combined with the steps in the diagnostic method of obtaining fault severity information and operational risk information and converting them into decision factors, ensures that the final generated warning information not only reflects the fault and risk itself but is also optimized according to the vehicle's real-time status, guaranteeing the timeliness, accuracy, and relevance of the warnings. This more effectively assists the advanced driver assistance system in risk assessment and behavior adjustment.

[0086] As one embodiment of the present invention, the steps of adjusting the operating parameters or internal processing logic of a preset fusion strategy based on vehicle operating condition information, on-board system information status, and preset strategy adjustment rules to obtain the adjusted fusion strategy include:

[0087] Based on vehicle operating condition information, on-board system information status, and preset strategy adjustment rules, the operating parameters or internal processing logic of the preset fusion strategy are adjusted to obtain the initial adjusted fusion strategy.

[0088] Obtain the verification input for verifying the initial adjusted fusion strategy. The verification input is adapted to the current vehicle operating condition information and the status of the on-board system information.

[0089] The verification input is applied to the initial adjusted fusion strategy and the reference strategy respectively to obtain the adjusted strategy output of the initial adjusted fusion strategy and the reference output of the reference strategy. The reference strategy is the preset fusion strategy or the preset baseline security strategy before adjustment.

[0090] Based on the preset evaluation rules, the performance of the fusion strategy after the initial adjustment is evaluated based on the adjusted strategy output, the reference output, and the expected output corresponding to the verification input.

[0091] Based on performance, select one of the initial adjusted fusion strategy or the reference strategy as the adjusted fusion strategy.

[0092] The initial adjusted fusion strategy refers to the strategy version obtained after preliminary modifications to the preset fusion strategy according to preset strategy adjustment rules. This version requires further verification to determine its applicability. Verification input refers to a set of simulated or collected data used to input into the fusion strategy to be evaluated to test its output behavior under specific conditions. This data can be generated by simulation tools, filtered from historical operating data, or constructed based on the current real-time state. The reference strategy refers to the benchmark strategy used for comparative evaluation with the initial adjusted fusion strategy. It can be implemented using the preset fusion strategy before adjustment or a preset baseline security strategy with a known safety margin. Preset evaluation rules refer to the standards and methods used to quantitatively evaluate the performance of the fusion strategy. These can be implemented using error functions, risk scoring standards, performance index thresholds, or evaluation criteria defined based on expert experience. Performance refers to the quantitative result or level obtained after evaluating the initial adjusted fusion strategy according to the preset evaluation rules. This result reflects the degree of matching between the strategy's output and expected output under verification input and its superiority or inferiority relative to the reference strategy.

[0093] Specifically, after initially adjusting the fusion strategy based on vehicle operating condition information and on-board system information status to obtain the initial adjusted strategy, the method does not directly adopt this strategy. Instead, it first obtains a verification input adapted to the current state. Next, this verification input is simultaneously applied to both the initial adjusted fusion strategy and a reference strategy used as a comparison benchmark, and their outputs are obtained respectively. By comparing these two outputs with the expected output corresponding to the verification input, and according to preset evaluation rules, the performance of the initial adjusted fusion strategy can be objectively evaluated. Finally, based on this performance evaluation result, the method selects the strategy with better performance (which could be the initial adjusted fusion strategy or the reference strategy) as the final adjusted fusion strategy. This verification and selection process, combined with the aforementioned steps of performance evaluation and initial adjustment based on vehicle operating condition information and on-board system information status, forms a more complete strategy adaptive mechanism.

[0094] As one embodiment of the present invention, the step of evaluating the performance of the fusion strategy after initial adjustment based on the adjusted strategy output, the reference output, and the expected output corresponding to the verification input, according to preset evaluation rules, includes:

[0095] The verification input, adjustment strategy output, reference output, and expected output corresponding to the verification input are associated with preset risk scenarios that characterize new energy vehicles under specific LED unit turn signal indication and advanced driver assistance system operation states.

[0096] Based on the associated risk scenarios, the decision risk of the decisions corresponding to the adjustment strategy output, reference output and expected output are assessed in the risk scenarios, and the decision risk assessment results corresponding to each output are obtained.

[0097] Based on the preset evaluation rules and the decision risk assessment results corresponding to each output, the performance of the fusion strategy after the initial adjustment is evaluated.

[0098] Among these, the pre-defined evaluation rules refer to the standards and methods used to assess the performance of the strategy, which can be implemented using standards based on risk level classification or methods based on safety indicator scoring. The pre-defined risk scenarios, characterizing new energy vehicles under specific turn signal indications and advanced driver assistance system operating states, refer to the specific driving situations used to evaluate the strategy's performance, which can be implemented using scenario libraries or scenario description templates. Decision risk refers to the negative consequences that the decision corresponding to the strategy output may bring under specific risk scenarios. The decision risk assessment result refers to the result obtained after measuring the decision risk, which can be expressed in the form of risk score, risk level, safety margin, etc.

[0099] First, the validation input, adjusted strategy output, reference output, and expected output corresponding to the validation input are associated with preset risk scenarios. This step places the abstract strategy output in a specific driving context, and by associating it with risk scenarios, the potential risks that different strategy choices may bring can be understood. Second, based on the associated risk scenarios, the decision risk of the decisions corresponding to the adjusted strategy output, reference output, and expected output in the risk scenarios is evaluated, obtaining the decision risk assessment results for each output. Finally, according to preset evaluation rules and combined with the decision risk assessment results corresponding to each output, the performance of the fused strategy after the initial adjustment is evaluated. This evaluation method not only considers the performance of the strategy in a specific scenario, but also its adaptability under different risk levels, thus comprehensively evaluating the effectiveness of the strategy. This method places the strategy output in specific risk scenarios for consideration, and by quantifying the decision risk of different strategies in these scenarios, it provides a more reliable evaluation dimension than simple output comparison. This risk-based evaluation method is consistent with the goal of optimizing the decision basis by adjusting the strategy in the pre-planning, ensuring that the adjustment not only improves a certain performance indicator, but more importantly, improves the reliability of decision-making in critical safety scenarios, thereby solving the problem raised in the introduction.

[0100] As one embodiment of the present invention, the step of assessing the decision risk of decisions corresponding to the adjustment strategy output, reference output, and expected output under the risk scenario based on the associated risk scenario includes:

[0101] For each decision corresponding to the adjustment strategy output, reference output, and expected output, obtain the characteristic parameters of the decision under the associated risk scenario.

[0102] Based on the preset risk measurement standards, the characteristic parameters are matched with the preset risk level or risk scoring table to determine the corresponding safety impact or probability of functional failure.

[0103] In this context, the characteristic parameters of a decision under associated risk scenarios refer to the quantitative or qualitative attributes exhibited by the decision behavior or outcome corresponding to the adjusted strategy output, reference output, and expected output, respectively, under a specific risk scenario, and can be used to assess its potential risks. These parameters may include, but are not limited to, dynamic behavioral indicators such as the safety distance, rate of change of velocity, acceleration, path deviation, and response time caused by the decision, or system state information on which the decision depends or generates, such as the confidence level of sensor data, the error range of the control system, and the response delay of the actuator. These characteristic parameters can be obtained through real-time monitoring and data acquisition of the decision execution process. A pre-established risk measurement standard refers to a set of pre-established rules, models, or mapping relationships used to quantify decision risks. This standard defines how to assess the potential safety impact or functional failure probability of a decision under a specific risk scenario based on the acquired decision characteristic parameters. Risk measurement standards can be established based on expert experience, historical data analysis, simulation, or machine learning models, with the aim of providing an objective and repeatable basis for risk assessment. A predefined risk level or risk scoring table refers to a predefined table or set used to map decision-making characteristic parameters or intermediate results quantified by risk metrics (such as risk scores) to specific risk levels (e.g., low, medium, high risk) or direct safety impacts or functional failure probability values. This table establishes a correlation between characteristic parameters and risk consequences, making risk assessment results interpretable and actionable. Risk level or risk scoring tables can be implemented using multi-dimensional lookup tables, piecewise functions, or rule-based reasoning systems.

[0104] When assessing the risks of different decisions (adjustment strategy output, reference output, and expected output) in specific risk scenarios, this solution does not first directly calculate the risk probability. Instead, it obtains the characteristic parameters of the specific behaviors or states exhibited by these decisions in the current risk scenario. These characteristic parameters are a direct reflection of the decision-making behavior. For example, in an automatic lane-changing scenario, adjusting the strategy may lead to a larger lateral distance, the reference strategy may lead to a smaller lateral distance, and the expected output represents the ideal safe distance. Obtaining these specific distance values, speeds, accelerations, and other parameters is the foundation for quantifying risk. Subsequently, the solution uses preset risk measurement standards to match these specific characteristic parameters with preset risk levels or risk scoring tables. This matching process is crucial for transforming specific behavioral parameters into abstract risk assessment results. The risk level or risk scoring table predefines the risk level or probability value corresponding to different parameter ranges or combinations. By searching or calculating, characteristic parameters such as "lateral distance less than 0.5 meters" can be matched to a "high risk" level or a result such as "functional failure probability is 80%". This approach, based on matching risk levels or risk scoring tables with feature parameters, makes the risk quantification process more concrete and operational, avoiding the difficulties of directly performing probabilistic modeling on complex scenarios. By linking specific decision-making behavior characteristics with preset risk consequences, this solution can more precisely assess the potential risks of different strategies, providing data support for selecting safer strategies. This helps solve the problem of accurately assessing risks and issuing effective warnings when light fixtures malfunction and ADAS-related operations occur.

[0105] As one embodiment of the present invention, the step of applying a preset fusion strategy to the first decision factor and the second decision factor to generate a fused decision basis further includes:

[0106] The first decision factor and the second decision factor are respectively fuzzified to obtain the fuzzy membership degree μ_D1 of the first decision factor and the fuzzy membership degree μ_D2 of the second decision factor. The fuzzy membership degree is determined by a preset membership function.

[0107] Based on the fuzzy membership degree μ_D1 of the first decision factor, the fuzzy membership degree μ_D2 of the second decision factor, and the preset fuzzy rule set R, fuzzy inference is performed to obtain multiple fuzzy output sets μ_F_k_out. The fuzzy rule set R has built-in specific processing logic for situations where the indication direction between the first and second decision factors is inconsistent or there is a potential conflict. The activation intensity α_k of each rule is determined by the T-norm operator. The fuzzy output set μ_F_k_out is obtained by truncating the corresponding output membership function μ_L_k by the activation intensity α_k.

[0108] Multiple fuzzy output sets μ_F_k_out are aggregated to obtain a total fuzzy output set μ_F_total. The aggregation process is implemented using the S-norm operator.

[0109] The total fuzzy output set μ_F_total is defuzzified to generate the fused decision basis F.

[0110] Fuzzification refers to the process of converting precise input values ​​into fuzzy sets, which can be achieved by defining the universe of discourse of the input variables and the corresponding fuzzy sets.

[0111] Fuzzy membership degree refers to the degree to which an element belongs to a certain fuzzy set, and it can be represented by a value between 0 and 1.

[0112] The preset membership function is a function that defines how input or output variables are mapped to their corresponding fuzzy sets. It can be implemented using triangular membership functions, trapezoidal membership functions, or Gaussian membership functions.

[0113] The preset fuzzy rule set R refers to a set of rules in the form of IF-THEN, which describes the relationship between the input fuzzy set and the output fuzzy set. It can be constructed using expert experience or machine learning methods.

[0114] Fuzzy inference refers to the process of deriving a fuzzy output set based on the fuzzy membership degree and fuzzy rule set of the input. It can be implemented using inference methods such as Mamdan or Sugeno.

[0115] The fuzzy output set μ_F_k_out refers to the fuzzy result obtained by reasoning from a single fuzzy rule, which can be achieved by truncating or scaling the output membership function.

[0116] The activation strength α_k refers to the truth value of the antecedent part of a single fuzzy rule, which can be calculated using the T-norm operator.

[0117] The T-norm operator is a mathematical function used to calculate the intersection (logical AND) of two or more fuzzy membership degrees. It can be implemented by methods such as taking the minimum value (min) or multiplying (product).

[0118] Truncation refers to the operation of restricting the shape of the output membership function to a height determined by the activation intensity, which can be achieved by taking the minimum value (min).

[0119] The output membership function μ_L_k refers to the membership function of the output variable corresponding to the consequent of a single fuzzy rule, which can be implemented using a predefined fuzzy set membership function.

[0120] Aggregation processing refers to the process of merging the fuzzy output sets obtained from multiple fuzzy rules into a single fuzzy output set, which can be calculated using the S-norm operator.

[0121] The S-norm operator is a mathematical function used to calculate the union (logical OR) of two or more fuzzy membership degrees. It can be implemented by methods such as taking the maximum value (max) or probabilistic sum.

[0122] The total fuzzy output set μ_F_total refers to the fuzzy set representing the comprehensive result of all rules obtained after aggregation processing. It can be achieved by performing a union operation on all fuzzy output sets.

[0123] Defuzzification refers to the process of converting the total fuzzy output set into a precise numerical value to obtain the final decision basis. It can be achieved by methods such as the centroid method, the bisector method, and the mean of maximum membership method.

[0124] The fused decision basis F refers to the precise value obtained after fuzzy logic processing, which is used to guide subsequent operations. It can be represented by the result of defuzzification processing.

[0125] This application provides a fusion strategy based on fuzzy logic to resolve potential conflicts between the first and second decision factors, thereby generating a more reliable fusion decision basis. This scheme achieves this goal through a series of steps. First, the first and second decision factors are fuzzified to obtain fuzzy membership degrees μ_D1 and μ_D2. Fuzzification transforms precise numerical values ​​into fuzzy concepts, enabling the system to handle uncertainty and fuzziness. By determining the fuzzy membership degrees through a preset membership function, different decision factors can be mapped to different fuzzy sets, thus providing a foundation for subsequent fuzzy inference. Second, based on the fuzzy membership degrees μ_D1 and μ_D2 and a preset fuzzy rule set R, fuzzy inference is performed to obtain multiple fuzzy output sets μ_F_k_out. The fuzzy rule set R contains specific processing logic for decision factor conflicts, which is the core of this scheme. Through predefined rules, the system can select appropriate processing methods according to different conflict situations, thereby avoiding decision errors. The activation strength α_k of each rule is determined by the T-norm operator, ensuring the effectiveness of the rules. The fuzzy output set μ_F_k_out is obtained by truncating the corresponding output membership function μ_L_k based on the activation intensity α_k, achieving precise control over the rule output. Then, multiple fuzzy output sets μ_F_k_out are aggregated to obtain a total fuzzy output set μ_F_total. This aggregation is implemented using the S-norm operator, which comprehensively considers different rule outputs to obtain a global fuzzy output. Finally, the total fuzzy output set μ_F_total is defuzzified to generate the fused decision basis F. Defuzzification transforms the fuzzy output into precise numerical values, providing directly usable decision basis for advanced driver assistance systems. This fuzzy logic fusion strategy can be applied as a specific fusion strategy within a framework that evaluates performance based on vehicle operating conditions and onboard system status, dynamically adjusting the fusion strategy. This enables the framework to handle conflicts between decision factors, improving the robustness and adaptability of the overall decision-making process.

[0126] like Figure 2 The system shown is a short-circuit diagnostic system for LED lamp beads in new energy vehicles, applied to turn signals with multiple independently controllable LED units. The system includes:

[0127] The parameter acquisition module 201 is used to acquire the reference electrical characteristic parameters of each independently controlled LED unit turn signal under a preset fault-free working state.

[0128] The real-time parameter acquisition module 202 is used to acquire the real-time electrical characteristic parameters of each independently controlled LED unit turn light during the execution of the dynamic lighting sequence of the LED unit turn light.

[0129] The parameter comparison module 203 is used to compare the real-time electrical characteristic parameters of each independently controlled LED unit turn signal with the corresponding reference electrical characteristic parameters to obtain the comparison result.

[0130] The fault determination module 204 is used to determine, based on the comparison results, whether the deviation of the real-time electrical characteristic parameters from the reference electrical characteristic parameters exceeds a preset fault determination threshold, so as to determine whether the independently controlled LED unit turn signal has a target fault caused by a short circuit of a few lamp beads.

[0131] The warning information sending module 205 is used to send a warning information to the advanced driver assistance system when it is determined that the independently controlled LED unit turn signal has a target fault and the illumination of the LED unit turn signal is related to the operation decision of the advanced driver assistance system.

[0132] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention.

Claims

1. A method for diagnosing short circuits in LED lamp beads of new energy vehicles, applied to turn signals with multiple independently controllable LED units, characterized in that, The method includes the following steps: Obtain the reference electrical characteristic parameters of each independently controlled LED unit turn signal under a preset fault-free operating state; During the execution of the dynamic lighting sequence of the LED unit turn lights, the real-time electrical characteristic parameters of each independently controlled LED unit turn light are acquired in real time. The comparison results are obtained by comparing the real-time electrical characteristic parameters of each independently controlled LED unit turn signal with the corresponding reference electrical characteristic parameters; Based on the comparison results, it is determined whether the deviation of the real-time electrical characteristic parameters from the reference electrical characteristic parameters exceeds a preset fault determination threshold, so as to determine whether the independently controlled LED unit turn signal has experienced a target fault caused by a short circuit of a few LED beads. When it is determined that the independently controlled LED unit turn signal has the target fault, and the illumination of the LED unit turn signal is related to the operation decision of the advanced driver assistance system, a warning message is sent to the advanced driver assistance system. When it is determined that the independently controlled LED unit turn signal has experienced the target fault, and the illumination of the LED unit turn signal is associated with the operation decision of the advanced driver assistance system, the step of sending a warning message to the advanced driver assistance system includes: Obtain fault severity information that characterizes the severity of the target fault, and obtain operational risk information that characterizes the current operational decision risk level of the advanced driver assistance system; Based on the severity information of the fault and the operational risk information, the differentiated content of the warning information is determined, and the differentiated content is used to enable the advanced driver assistance system to perform risk assessment and behavior adjustment; Based on the determined differentiated content, the warning information is generated and sent to the advanced driver assistance system; The step of determining the differentiated content of the warning information based on the fault severity information and the operational risk information, wherein the differentiated content is used to enable the advanced driver assistance system to perform risk assessment and behavior adjustment, includes: The severity information of the fault is converted into a first decision factor, and the operational risk information is converted into a second decision factor. A preset fusion strategy is applied to the first decision factor and the second decision factor to generate a fused decision basis. The fusion strategy has built-in specific processing logic for situations where the indication direction of the first decision factor and the second decision factor is inconsistent or potentially conflicting. Based on the fused decision criteria, the differentiated content of the early warning information is determined.

2. The method for diagnosing short circuits in LED beads for new energy vehicles according to claim 1, characterized in that, The step of applying a preset fusion strategy to the first decision factor and the second decision factor to generate a fused decision basis includes: Acquire vehicle operating condition information and on-board system information status; Based on the vehicle operating condition information and the vehicle system information status, an effectiveness evaluation is performed to determine whether the decision effectiveness of the preset fusion strategy used to generate a fused decision basis from the first decision factor and the second decision factor meets the preset effectiveness requirements under the current conditions. If not satisfied, the operating parameters or internal processing logic of the preset fusion strategy are adjusted according to the vehicle operating condition information, the vehicle system information status, and the preset strategy adjustment rules to obtain the adjusted fusion strategy. Based on the results of the performance evaluation, the adjusted fusion strategy or the original preset fusion strategy is selected and applied to the first decision factor and the second decision factor to generate the fused decision basis.

3. The method for diagnosing short circuits in LED beads for new energy vehicles according to claim 2, characterized in that, The step of adjusting the operating parameters or internal processing logic of the preset fusion strategy based on the vehicle operating condition information, the vehicle system information status, and preset strategy adjustment rules to obtain the adjusted fusion strategy includes: Based on the vehicle operating condition information, the vehicle system information status, and the preset strategy adjustment rules, the operating parameters or internal processing logic of the preset fusion strategy are adjusted to obtain the initial adjusted fusion strategy. Obtain verification input for verifying the initial adjusted fusion strategy, wherein the verification input is adapted to the current vehicle operating condition information and the vehicle system information status; The verification input is applied to the initial adjusted fusion strategy and a reference strategy respectively to obtain the adjusted strategy output of the initial adjusted fusion strategy and the reference output of the reference strategy. The reference strategy is the preset fusion strategy or the preset baseline security strategy before adjustment. Based on the preset evaluation rules, the performance of the initial adjusted fusion strategy is evaluated based on the adjustment strategy output, the reference output, and the expected output corresponding to the verification input. Based on the performance, either the initial adjusted fusion strategy or the reference strategy is selected as the adjusted fusion strategy.

4. The method for diagnosing short circuits in LED beads for new energy vehicles according to claim 3, characterized in that, The step of evaluating the performance of the initial adjusted fusion strategy based on the preset evaluation rules, the adjustment strategy output, the reference output, and the expected output corresponding to the verification input includes: The verification input, the adjustment strategy output, the reference output, and the expected output corresponding to the verification input are associated with preset risk scenarios that characterize the new energy vehicle under specific LED unit turn signal indication and advanced driver assistance system operation states. Based on the associated risk scenarios, the decision risk of the decisions corresponding to the adjustment strategy output, the reference output, and the expected output under the risk scenarios is assessed, and the decision risk assessment results corresponding to each output are obtained. Based on the preset evaluation rules and the decision risk assessment results corresponding to each output, the performance of the initial adjusted fusion strategy is evaluated.

5. A short-circuit diagnosis method for LED beads in new energy vehicles according to claim 4, characterized in that, The step of assessing the decision risk of the decisions corresponding to the adjustment strategy output, the reference output, and the expected output under the risk scenario based on the associated risk scenario includes: For the decisions corresponding to the adjustment strategy output, the reference output, and the expected output, respectively, obtain the characteristic parameters of the decisions under the associated risk scenarios; Based on the preset risk measurement standards, the characteristic parameters are matched with the preset risk levels or risk scoring tables to determine the corresponding safety impact or probability of functional failure.

6. A short-circuit diagnosis method for LED lamp beads in new energy vehicles according to claim 2, characterized in that, The step of applying a preset fusion strategy to the first decision factor and the second decision factor to generate a fused decision basis further includes: The first decision factor and the second decision factor are respectively fuzzified to obtain the fuzzy membership degree μ_D1 of the first decision factor and the fuzzy membership degree μ_D2 of the second decision factor. Based on the fuzzy membership degree μ_D1 of the first decision factor, the fuzzy membership degree μ_D2 of the second decision factor, and the preset fuzzy rule set R, fuzzy inference is performed to obtain multiple fuzzy output sets μ_F_k_out. The multiple fuzzy output sets μ_F_k_out are aggregated to obtain a total fuzzy output set μ_F_total, wherein the aggregation process is implemented using the S-norm operator; The total fuzzy output set μ_F_total is defuzzified to generate the fused decision basis F.

7. A short-circuit diagnostic system for LED lamp beads in new energy vehicles, applied to turn signals with multiple independently controllable LED units, for executing a short-circuit diagnostic method for LED lamp beads in new energy vehicles as described in any one of claims 1-6, characterized in that, The system includes: The parameter acquisition module is used to acquire the reference electrical characteristic parameters of each independently controlled LED unit turn light under the preset fault-free working state. The real-time parameter acquisition module is used to acquire the real-time electrical characteristic parameters of each independently controlled LED unit turn light during the execution of the dynamic lighting sequence of the LED unit turn light. The parameter comparison module is used to compare the real-time electrical characteristic parameters of each independently controlled LED unit turn signal with the corresponding reference electrical characteristic parameters to obtain the comparison result. The fault determination module is used to determine, based on the comparison result, whether the deviation of the real-time electrical characteristic parameters from the reference electrical characteristic parameters exceeds a preset fault determination threshold, so as to determine whether the independently controlled LED unit turn signal has experienced a target fault caused by a short circuit of a few LED beads. The warning information sending module is used to send a warning information to the advanced driver assistance system when it is determined that the independently controlled LED unit turn signal has the target fault and the illumination of the LED unit turn signal is associated with the operation decision of the advanced driver assistance system.

Images