Short-circuit diagnosis method, device and electronic equipment for LED load

Abstract

The application provides a LED load short circuit diagnosis method, device and electronic equipment, relates to the fault diagnosis technical field of vehicle lighting load, and comprises the following steps: judging whether the current on time of the LED load reaches a preset steady state time length, wherein the preset steady state time length is used to represent a preset time value of reaching a steady state of the current vehicle; if not, determining a predicted current value at the current time based on the on time, the whole vehicle storage battery voltage and the current environment temperature, wherein the predicted current value is a predicted normal working current value of the LED load at the current time; judging whether the actual current value of the LED load is greater than a target current value, wherein the target current value is determined by the predicted current value and a first safety coefficient in the case that the on time does not reach the preset steady state time length; if yes, performing an alarm record of the short circuit fault of the current vehicle, solving the misjudgment alarm problem of the diagnosis program, and ensuring the reliability of the vehicle lamp load.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology for vehicle lighting loads, and in particular to a short-circuit diagnosis method, apparatus and electronic device for LED loads. Background Technology

[0002] In recent years, LED loads have gradually replaced traditional halogen lamps in the automotive field. The automotive lighting installation standard GB4785 stipulates that external loads of vehicles, such as turn signals, need to have fault diagnosis functions.

[0003] However, LED loads are difficult to diagnose effectively, and often misjudge excessive current during the initial startup phase, causing the diagnostic program to mistakenly alarm as a short circuit, thus affecting the normal use of vehicle lighting equipment. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a short-circuit diagnosis method for LED loads, solve the problem of false alarms in diagnostic programs, and ensure the reliability of vehicle lighting loads.

[0005] In a first aspect, an embodiment provides a short-circuit diagnosis method for an LED load, the method comprising:

[0006] Determine whether the current on-time of the LED load has reached the preset steady-state duration, wherein the preset steady-state duration is used to characterize the preset time value for the current vehicle to reach a steady state;

[0007] If not, the predicted current value at the current moment is determined based on the connection time, the vehicle battery voltage and the current ambient temperature, wherein the predicted current value is the predicted normal operating current value of the LED load at the current moment.

[0008] Determine whether the actual current value of the LED load is greater than the target current value, wherein, if the turn-on time has not reached the preset steady-state duration, the target current value is determined by the predicted current value and the first safety factor.

[0009] If so, then record the alarm for the current vehicle's short circuit fault.

[0010] In an optional implementation, the step of determining the predicted current value at the current moment based on the connection time, the vehicle battery voltage, and the current ambient temperature includes:

[0011] The variable matrix is ​​determined based on the connection time, vehicle battery voltage, and current ambient temperature.

[0012] The variable matrix is ​​input into the prediction model, and the predicted current value at the current moment is output.

[0013] In an optional implementation, the method further includes:

[0014] If the current on-time of the LED load reaches the preset steady-state duration, it is determined whether the actual current value of the LED load is greater than the target current value. In the case that the on-time reaches the preset steady-state duration, the target current value is determined by the steady-state current value of the LED load at the current moment and the second safety factor.

[0015] If the value is greater than the specified value, an alarm record for the current vehicle's short circuit fault will be generated.

[0016] In an optional implementation, before determining whether the current on-time of the LED load has reached a preset steady-state duration, the method includes:

[0017] In response to the operation command for the LED load, control the LED load to operate.

[0018] In an optional implementation, before determining whether the current on-time of the LED load has reached a preset steady-state duration, the method includes:

[0019] If the turn-on time reaches the sampling period, the step of determining whether the current turn-on time of the LED load has reached the preset steady-state duration is triggered.

[0020] In an optional implementation, the method further includes:

[0021] If the alarm record appears in a consecutive preset number of sampling periods, a vehicle alarm operation is executed.

[0022] In an optional implementation, the prediction model is trained using a long short-term neural network.

[0023] Secondly, an embodiment provides a short-circuit diagnostic device for an LED load, the device comprising:

[0024] The first judgment module determines whether the current on-time of the LED load has reached the preset steady-state duration, wherein the preset steady-state duration is used to characterize the preset time value for the current vehicle to reach a steady state.

[0025] If the target is not reached, the module determines the predicted current value at the current moment based on the connection time, the vehicle battery voltage, and the current ambient temperature. The predicted current value is the predicted normal operating current value of the LED load at the current moment.

[0026] The second judgment module determines whether the actual current value of the LED load is greater than the target current value. In the case that the turn-on time has not reached the preset steady-state duration, the target current value is determined by the predicted current value and the first safety factor.

[0027] If so, the recording module will record the alarm for the current vehicle's short circuit fault.

[0028] Thirdly, an embodiment provides an electronic device including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method described in any of the foregoing embodiments.

[0029] Fourthly, an embodiment provides a machine-readable storage medium storing machine-executable instructions, which, when invoked and executed by a processor, cause the processor to perform the steps of the method described in any of the foregoing embodiments.

[0030] This invention provides a short-circuit diagnosis method, apparatus, and electronic device for LED loads. By employing a corresponding short-circuit diagnosis strategy for LED loads whose turn-on time does not meet a preset steady-state duration, the normal operating current of such LED loads is predicted. A target current value is determined based on the predicted current value and a first safety factor used to avoid erroneous operation. If the actual current value of the LED load is greater than the target current value, a short-circuit fault is recorded for subsequent alarm purposes. This invention avoids false alarms when diagnosing short circuits in LED loads that have just started up and do not meet the preset steady-state duration.

[0031] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0032] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0033] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0034] Figure 1This is a schematic diagram of the structure of an LED load diagnostic device provided in an embodiment of the present invention;

[0035] Figure 2 A flowchart of a short-circuit diagnosis method for an LED load provided in an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of a long short-term neural network provided in an embodiment of the present invention;

[0037] Figure 4 A flowchart of another short-circuit diagnosis method for LED load provided in an embodiment of the present invention;

[0038] Figure 5 A functional block diagram of a short-circuit diagnostic device for an LED load provided in an embodiment of the present invention;

[0039] Figure 6 This is a schematic diagram of the hardware architecture of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Traditional halogen lamps can be considered equivalent to resistors, with linear current changes. However, LED loads, due to the characteristics of LEDs, generally require a built-in DC / DC step-up / step-down converter driver module. Depending on the starting voltage, this driver module is further divided into boost, bulk, and boost-bulk modules. Because of the addition of these boost / step-down modules, the inductors and capacitors within them cause a very large starting current, while the steady-state current is very small, making effective diagnosis difficult. This often leads to false alarms due to excessive current during the initial startup phase, causing diagnostic programs to mistakenly identify a short circuit.

[0042] Based on this, the present invention provides a short-circuit diagnosis method for LED loads, which performs diagnostic monitoring before and after the steady state of the lamp, solves the problem of false alarms in the diagnostic program, and ensures the reliability of vehicle lamp loads.

[0043] Figure 1This is a diagnostic circuit for an LED load. The high-side driver chip receives control signals from the SOC processor to determine the on / off state of its internal MOSFETs, thereby controlling the on / off state of the vehicle battery and LEDs. The high-side driver chip itself has an output current detection function, which can output the current at the LED load terminal as a constant current source according to a specific ratio. s =k0I load The SOC obtains the current at the LED load terminal by dividing the voltage across the sampling resistor by the resistance value and k0. k0 is obtained from the datasheet of the high-side driver chip.

[0044] To facilitate understanding of this embodiment, a short-circuit diagnosis method for LED loads disclosed in this embodiment of the invention will be described in detail first. This method can be applied to the vehicle body domain controller.

[0045] Figure 2 This is a flowchart of a short-circuit diagnosis method for an LED load provided in an embodiment of the present invention.

[0046] Reference Figure 2 The method steps may include:

[0047] Step S102: Determine whether the current on-time of the LED load has reached the preset steady-state duration.

[0048] The preset steady-state duration is used to characterize the preset time value for the current vehicle to reach a steady state. This steady-state duration can be preset when the LED load leaves the factory. Embodiments of the present invention employ different short-circuit diagnostic methods for LED loads that meet or do not meet the preset steady-state duration.

[0049] Step S104: If the condition is not met, determine the predicted current value at the current moment based on the connection time, the vehicle battery voltage, and the current ambient temperature.

[0050] The predicted current value is the predicted normal operating current of the LED load at the current moment. It should be noted that this predicted current value is a dynamic variable, changing in real time based on three parameters: the on-time, the vehicle battery voltage, and the current ambient temperature. If the on-time does not meet the steady-state duration, the normal operating current of the LED load may differ at different times.

[0051] Step S106: Determine whether the actual current value of the LED load is greater than the target current value.

[0052] In cases where the on-time has not reached the preset steady-state duration, the target current value is determined jointly by the predicted current value and a first safety factor. As an optional embodiment, the target current value can be obtained by multiplying the predicted current value by the first safety factor. It should be noted that when the LED load has just started up, its actual operating current may be relatively high. To minimize false alarms, the first safety factor can be set to 2, thus ensuring diagnosis of short circuits while avoiding false alarms.

[0053] Step S108: If yes, then record the alarm for the current vehicle's short circuit fault.

[0054] It is understandable that if the actual current value of the LED load is less than the target current value, it will continue to work normally.

[0055] In a preferred embodiment of practical application, a corresponding short-circuit diagnosis strategy is adopted for LED loads whose turn-on time does not meet the preset steady-state duration. The normal operating current of such LED loads is predicted, and a target current value is determined based on this predicted current value and a first safety factor used to avoid misoperation. If the actual current value of the LED load is greater than the target current value, a short-circuit fault is recorded in the vehicle for subsequent alarm purposes. This embodiment of the invention avoids false alarms for short-circuit diagnosis of LED loads that have just started up and do not meet the preset steady-state duration.

[0056] In some embodiments, based on step S104 above, the normal operating current value can be predicted to diagnose short-circuit conditions in LED loads that do not meet the preset steady-state duration. As an example, step S104 above may further include the following steps:

[0057] Step 1.1) Determine the variable matrix based on the connection time, vehicle battery voltage and current ambient temperature.

[0058] The connection time, vehicle battery voltage, and current ambient temperature are used as three parameters in the variable matrix.

[0059] Step 1.2) Input the variable matrix into the prediction model and output the predicted current value at the current time.

[0060] Specifically, a neural network algorithm is integrated into the SOC chip of the vehicle domain controller to filter overcurrent problems during the startup phase. The algorithm used is the LSTM (Long Short-Term Memory) neural network algorithm. This prediction model is trained using a Long Short-Term Memory neural network.

[0061] It should be noted that the current of the LED load is related to the enabled time (on-time) M, the current ambient temperature T, and the vehicle battery voltage V. A set of input variables is constructed as a 1*3 matrix x. t =[M t T t V t ];

[0062] f t =σ(W fx ·x t +W fh h t-1 +b f )

[0063] i t =σ(W ix x t +W ih h t-1 +b i )

[0064]

[0065] o t =σ(W ox x i +W oh h t-1 +b0)

[0066] h t =o t ·tanh(c t )

[0067] Where σ is the sigmoid function;

[0068]

[0069] The tanh function is the hyperbolic tangent function;

[0070]

[0071] Among them, such as Figure 3 As shown, f t This refers to the forget gate, whose purpose is to control which information is lost or retained; t This represents the input gate, which controls which input information is sent to the memory cells; O t This represents the output gate. The function of the output gate is to control what information the memory cell outputs before entering the next self-loop iteration; x t c represents the input at time t; t h represents the state of the memory cell at time t. tLet t represent the output current at time t, W represent the weight matrix corresponding to the above three parameters, and b represent the offset between the actual current value and the predicted current value.

[0072] In addition, the weight matrix and offset of each LED load sample can be obtained through calibration. The calibration method is as follows: M t The step size is the actual AD sampling period, and the total duration is the maximum time it takes for the LED load to reach steady state from startup, denoted as T. s T t The step size is 5℃, and the ambient temperature range is -40℃ to 85℃ (automotive industry standard). t The step size is 0.5V, and the range is 9V-16V (passenger car industry standard). The actual value of the LED load current is recorded simultaneously. Based on the above data, the initial calibration weight matrix and initial calibration offset at the factory can be calculated. Subsequent error training is then performed, meaning that the initial calibration value is corrected based on the actual recorded load values ​​during use to correct for individual differences in LED products.

[0073] For example, in practical applications, as vehicles are used continuously, the actual current value, ambient temperature, battery voltage, and connection time of the historical LED load before reaching the preset steady state can be used as training samples to input into the prediction model, thereby calibrating and updating the weight matrix and offset in the neural network design.

[0074] In some embodiments, short-circuit faults in LED loads that meet a preset steady-state duration can also be diagnosed to achieve comprehensive reliability of the LED load. As an example, the above steps may further include the following steps:

[0075] Step 2.1): If the current on-time of the LED load reaches the preset steady-state duration, then determine whether the actual current value of the LED load is greater than the target current value.

[0076] Specifically, when the connection time reaches the preset steady-state duration, the target current value is determined jointly by the steady-state current value of the LED load at the current moment and the second safety factor. It should be noted that this steady-state current value is preset at the factory and is similar to the rated current during steady-state operation. The second safety factor serves the same purpose as the first safety factor: to prevent false alarms. The second safety factor can be the same as the first safety factor, i.e., a factor of 2.

[0077] Step 2.2): If the value is greater than the specified value, then an alarm record for the short circuit fault of the current vehicle is generated.

[0078] Step 2.3): If it is not greater than, then it works normally.

[0079] In some embodiments, fault diagnosis of the LED load can be achieved by triggering a specific timing. As an example, before step S102, the method includes:

[0080] Step 3.1): Respond to the operation command for the LED load and control the LED load to operate.

[0081] Specifically, when the user operates and controls the LED load, the system diagnoses whether the LED load is faulty and triggers the execution of subsequent steps; or when the user controls the diagnosis of the LED load's status, the system triggers the execution of subsequent steps.

[0082] In some embodiments, fault diagnosis of the LED load can be performed according to a preset sampling period. As an example, before step S102, the method further includes:

[0083] Step 3.2): If the turn-on time reaches the sampling period, then trigger the step of determining whether the current turn-on time of the LED load has reached the preset steady-state duration.

[0084] As can be seen from the aforementioned embodiments, the sampling period can be 5 milliseconds, that is, every 5 milliseconds of the connection time, a subsequent fault diagnosis step is triggered.

[0085] In some embodiments, an alarm may be triggered when the number of alarm records exceeds a threshold, in order to more effectively avoid erroneous operations. As an example, before step S102, the method further includes:

[0086] Step 4.1): If the alarm record appears in a consecutive preset number of sampling periods, then execute the vehicle alarm operation.

[0087] The preset number can be set according to the requirements for alarm accuracy and reliability, and / or vehicle safety requirements. For example, if the requirement for alarm reliability is higher, i.e., to minimize false alarms, the preset number can be set to a relatively large value; if the requirement for vehicle safety is higher, the preset number can be set to a relatively small value. In practical applications, both false alarms and vehicle safety requirements can be comprehensively considered to achieve the desired preset number. As an example, the preset number can be three. For instance, as described in the aforementioned embodiment, if the alarm record appears in three consecutive 5-millisecond sampling cycles, a vehicle alarm operation will be executed.

[0088] As an optional embodiment, this invention can also be used to diagnose open-circuit faults in LED loads:

[0089] When the actual current value of the load is less than 50% of the minimum operating current (steady-state current under this condition) under the corresponding conditions, the LED load can be considered to be open circuit.

[0090] Figure 4 A flowchart of another short-circuit diagnosis method for LED loads provided in an embodiment of the present invention.

[0091] Reference Figure 4 First, the LED load receives a lighting command; then it determines whether the LED load's on-time is greater than a preset time Ts, which is a preset steady-state time. In some embodiments, the diagnostic strategy for the LED load can be selected by setting this preset time.

[0092] If yes, determine whether the actual current value is greater than twice the steady-state current value under the current battery voltage and ambient temperature conditions; if yes, determine that a short circuit fault alarm record fault code DTC has occurred; if no, then work normally.

[0093] If not, the actual current of the current LED load is detected, and the on-time, vehicle battery voltage, and ambient temperature are input into the LSTM neural network to obtain the predicted current value; then it is determined whether the actual current value is greater than twice the predicted current value; if so, a short circuit fault alarm is detected and a fault code DTC is recorded; if not, normal operation is maintained.

[0094] The embodiments of the present invention can perform corresponding short-circuit diagnosis and control on LED loads before and after the steady-state duration of the connection time. Specifically, for LED loads that are started up, the predicted current value of the short circuit is dynamically set through a prediction algorithm to perform dynamic diagnosis. At the same time, a safety factor is adopted to avoid false alarm operations and ensure the reliability of LED load applications.

[0095] like Figure 5 As shown, this embodiment of the invention also provides a short-circuit diagnostic device 200 for LED loads, the device comprising:

[0096] The first judgment module 201 determines whether the current on-time of the LED load has reached the preset steady-state duration, wherein the preset steady-state duration is used to characterize the preset time value for the current vehicle to reach a steady state.

[0097] If the target is not reached, the module 202 determines the predicted current value at the current moment based on the connection time, the vehicle battery voltage, and the current ambient temperature. The predicted current value is the predicted normal operating current value of the LED load at the current moment.

[0098] The second judgment module 203 determines whether the actual current value of the LED load is greater than the target current value. In the case that the turn-on time has not reached the preset steady-state duration, the target current value is determined by the predicted current value and the first safety factor.

[0099] If so, the recording module 204 will record the alarm for the short circuit fault of the current vehicle.

[0100] In some embodiments, the determining module 202 is further configured to determine a variable matrix based on the connection time, the vehicle battery voltage, and the current ambient temperature; input the variable matrix into the prediction model; and output the predicted current value at the current moment.

[0101] In some embodiments, the second determination module 203 is further configured to, if the current on-time of the LED load reaches a preset steady-state duration, determine whether the actual current value of the LED load is greater than a target current value, wherein, if the on-time reaches the preset steady-state duration, the target current value is determined jointly by the steady-state current value of the LED load at the current moment and a second safety factor. If it is greater, then an alarm record for a short-circuit fault in the current vehicle is generated.

[0102] In some embodiments, the device further includes a trigger module, which, before the first judgment module 201 determines whether the current on-time of the LED load has reached a preset steady-state duration, is specifically used to respond to an operation command for the LED load and control the LED load to work.

[0103] In some embodiments, before the first judgment module 201 determines whether the current on-time of the LED load has reached the preset steady-state duration, the triggering module is further specifically configured to, if the on-time reaches the sampling period, trigger the first judgment module 201 to determine whether the current on-time of the LED load has reached the preset steady-state duration.

[0104] In some embodiments, the device further includes an alarm module, specifically configured to perform a vehicle alarm operation if the alarm record occurs in a consecutive preset number of sampling periods.

[0105] In some embodiments, the prediction model is trained using a long short-term neural network.

[0106] Figure 6 This is a schematic diagram of the hardware architecture of the electronic device 300 provided in an embodiment of the present invention. See also... Figure 6As shown, the electronic device 300 includes a machine-readable storage medium 301 and a processor 302, and may also include a non-volatile storage medium 303, a communication interface 304, and a bus 305; wherein the machine-readable storage medium 301, the processor 302, the non-volatile storage medium 303, and the communication interface 304 communicate with each other through the bus 305. The processor 302 can execute the method described in the above embodiments by reading and executing the machine-executable instructions in the machine-readable storage medium 301.

[0107] The machine-readable storage medium mentioned in this article can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, etc. For example, machine-readable storage media can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0108] Non-volatile media can be non-volatile memory, flash memory, storage drives (such as hard disk drives), any type of storage disk (such as optical discs, DVDs, etc.), or similar non-volatile storage media, or combinations thereof.

[0109] It is understood that the specific operation methods of each functional module in this embodiment can be referred to the detailed description of the corresponding steps in the above method embodiment, and will not be repeated here.

[0110] The computer-readable storage medium provided in the embodiments of the present invention stores a computer program. When the computer program code is executed, it can implement the method described in any of the above embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0111] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0112] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0113] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0114] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the scope of the technology disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention.

Claims

1. A short-circuit diagnosis method for an LED load, characterized by, The method comprises: determining whether the current on-time of the LED load reaches a preset steady state time length, wherein the preset steady state time length is used to represent a preset time value for the current vehicle to reach a steady state; if not, determining a predicted current value at the current time based on the on-time, the battery voltage of the whole vehicle and the current ambient temperature, wherein the predicted current value is a predicted normal working current value of the LED load at the current time; determining whether the actual current value of the LED load is greater than a target current value, wherein the target current value is determined by the predicted current value and a first safety factor in the case that the on-time does not reach the preset steady state time length; if yes, performing an alarm record of a short circuit fault of the current vehicle; the step of determining the predicted current value at the current time based on the on-time, the battery voltage of the whole vehicle and the current ambient temperature comprises: determining a variable matrix according to the on-time, the battery voltage of the whole vehicle and the current ambient temperature; inputting the variable matrix into a prediction model and outputting the predicted current value at the current time.

2. The method of claim 1, wherein, The method further comprises: if the current on-time of the LED load reaches the preset steady state time length, determining whether the actual current value of the LED load is greater than a target current value, wherein the target current value is determined by a steady state current value of the LED load at the current time and a second safety factor in the case that the on-time reaches the preset steady state time length; if yes, performing an alarm record of a short circuit fault of the current vehicle.

3. The method of claim 1, wherein, Before the step of determining whether the current on-time of the LED load reaches the preset steady state time length, the method comprises: controlling the LED load to work in response to an operation instruction for the LED load.

4. The method of claim 1, wherein, Before the step of determining whether the current on-time of the LED load reaches the preset steady state time length, the method comprises: if the on-time reaches a sampling period, triggering the step of determining whether the current on-time of the LED load reaches the preset steady state time length.

5. The method according to claim 1 or 4, characterized in that, The method further comprises: if the alarm record appears in a continuous preset number of sampling periods, performing a vehicle alarm operation.

6. The method of claim 1, wherein, The prediction model is trained by a long short-term neural network.

7. An LED load short-circuit diagnosis device characterized by comprising: The device comprises: a first determining module for determining whether the current on-time of the LED load reaches a preset steady state time length, wherein the preset steady state time length is used to represent a preset time value for the current vehicle to reach a steady state; a determining module for determining a predicted current value at the current time based on the on-time, the battery voltage of the whole vehicle and the current ambient temperature if the on-time does not reach the preset steady state time length, wherein the predicted current value is a predicted normal working current value of the LED load at the current time; a second determining module for determining whether the actual current value of the LED load is greater than a target current value, wherein the target current value is determined by the predicted current value and a first safety factor in the case that the on-time does not reach the preset steady state time length; a recording module for performing an alarm record of a short circuit fault of the current vehicle if the actual current value of the LED load is greater than the target current value. The determining module is further configured to determine a variable matrix according to the switch-on time, the battery voltage and the current ambient temperature; input the variable matrix into a prediction model, and output a predicted current value at the current time.

8. An electronic device comprising a memory, a processor, the memory having stored therein a computer program executable on the processor, characterized in that, The processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 6.

9. A machine-readable storage medium, characterized in that, The machine readable storage medium stores machine executable instructions, which, when invoked and executed by the processor, cause the processor to implement the steps of the method of any one of claims 1 to 6.

Images