Power rail fault early warning system, method, device and equipment and vehicle
By deploying a prediction model between the ECU and the server, and uploading the power rail operating parameters using the T-BOX gateway, the problem of low efficiency and accuracy of power rail fault warning in the ECU is solved, efficient and accurate fault warning is achieved, and the power supply is reduced Rail failure probability.
Patent Information
- Application Number
- CN202411202545.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-06
AI Technical Summary
In the prior art, the power rail fault warning in the ECU is low and has poor accuracy, and it is impossible to deal with abnormal power rails in a timely manner, affecting the safety of the vehicle's driving.
By deploying a prediction model between the ECU and the server, uploading the power rail operating parameters using the T-BOX gateway, analyzing and processing based on the first prediction model and the second prediction model, the power rail fault warning information is determined, and the efficiency and accuracy of the fault warning are improved. .
It realizes efficient determination of power rail fault warning information under any connection state, improves the efficiency and accuracy of ECU power rail fault warning, and reduces the probability of power rail fault failure.
Smart Images

Figure CN119087022A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a power rail fault early warning system, method, device, equipment and vehicle. Background Art
[0002] With the rapid development of automobile intelligence, there are more and more electronic control units (ECUs) on vehicles, and the functions of each ECU are becoming more and more complex, which in turn increases the risk of ECU failure. Therefore, the functional safety of ECUs has become increasingly important in vehicle design, and attention should be paid to the functional safety of each ECU. Among them, the power rail, which ensures the normal operation of the ECU, is particularly important. However, as the functions of the ECU become more and more complex, the design of the power rail is becoming more and more bloated, and the operating status of the power rail will directly affect whether the ECU is stable and reliable during operation.
[0003] In the related art, patent CN 219339386 U detects the power supply status of the power rail through a power rail monitoring unit, and issues power rail fault information when the power supply status of the power rail is abnormal. Then, the control unit executes a fault response according to the power rail fault information to promptly discover the failure of the power rail in the electrical device. This method only issues fault information to execute a fault response when the power supply status of the power rail is abnormal. The lag time for responding to the abnormal situation of the power rail is long, and the abnormal situation of the power rail cannot be handled in time, affecting the driving safety of the vehicle. In another related art, patent CN 117068189 A supplies power to other modules of the controller through the output voltage of the power management module, and monitors whether these output voltages are working properly. Then, the intelligent driving peripheral device data is received by the peripheral device data receiving module and sent to the automatic driving chip, and the data transmission is debugged through the Ethernet data interaction module. This method involves data interaction between multiple modules in the intelligent driving domain controller, and the function realized is only to diagnose whether the power supply fails. Such multiple modules further increase the complexity of the domain controller, making the domain controller more prone to abnormal problems. Therefore, currently determining the operating status of the power rail in the ECU and providing early warning of power rail failures is inefficient and inaccurate. Summary of the invention
[0004] The present application provides a power rail fault warning system, method, device, equipment and vehicle. The purpose of the present application is to at least solve the technical problems in the related art of determining the operating status of the power rail in the ECU and warning of the power rail fault with low efficiency and poor accuracy.
[0005] In order to achieve the above purpose, the technical solution adopted in this application is as follows:
[0006] According to a first aspect provided by the present application, a power rail fault warning system is provided, the power rail fault warning system comprising: an electronic controller ECU, a telematics processor T-BOX gateway and a server; the ECU comprises a power rail, a first prediction model is deployed on the ECU, the ECU is used to obtain operating parameters of the power rail, and analyze and process the operating parameters of the power rail based on the first prediction model, and determine fault warning information of the power rail within a preset time after the current moment, and the fault warning information is used to indicate whether the voltage of the power rail is abnormal; the T-BOX gateway is used to upload the operating parameters of the power rail to the server; a second prediction model is deployed on the server, and the server is used to analyze and process the operating parameters of the power rail based on the second prediction model, and determine the fault warning information of the power rail within a preset time after the current moment.
[0007] According to the above technical means, since the ECU and the server are connected through the T-BOX gateway, and the network will affect the connection status between the ECU and the server. Therefore, the operating parameters of the power rail can be analyzed and processed through the first prediction model deployed locally on the ECU and / or the second prediction model deployed on the server, so as to determine the fault warning information of the power rail. In this way, the fault warning information of the power rail can be determined by the first prediction model deployed locally on the ECU and / or the second prediction model deployed on the server, respectively, to know whether the voltage of the power rail will be abnormal within a preset time after the current moment. In this way, the operating status of the power rail in the ECU can be efficiently determined, and the efficiency and accuracy of warning of power rail failures can be improved.
[0008] In one possible implementation, the power rail includes: a system basis chip (SBC) and a DC-DC converter (DC-DC) circuit, the ECU corresponds to a target safety level, the ECU includes a microcontroller unit (MCU), and the configuration parameters of the MCU and the configuration parameters of the SBC both meet the target safety level.
[0009] According to the above technical means, by deploying SBC on ECU, the number of DC-DC circuits deployed can be reduced, and SBC itself can provide functional safety related measures to ensure the safety of power lines. In this way, the number of components deployed on ECU can be reduced, thereby reducing the probability of power rail failure. In addition, by determining the corresponding safety levels of MCU, SBC and ECU, the probability of power rail failure can be reduced by using high-quality and high-safety devices.
[0010] In a possible implementation, the MCU further includes a detection circuit, and the detection circuit is used to detect a power supply circuit included in the MCU to determine whether the MCU is abnormal.
[0011] According to the above technical means, the detection circuit included in the MCU can further perform a self-check operation on the power circuit included in the MCU to determine whether there is an abnormality in the power circuit included in the MCU, thereby further ensuring the stability of the MCU and reducing the probability of MCU failure.
[0012] According to a second aspect provided by the present application, a power rail fault warning method is provided, the method comprising: obtaining operating parameters of a power rail in an electronic controller ECU; analyzing and processing the operating parameters of the power rail based on a prediction model corresponding to a connection state between the ECU and a server, and determining fault warning information of the power rail within a preset time after a current moment, wherein the fault warning information is used to indicate whether the voltage of the power rail is abnormal, and the prediction model comprises at least one of the following: a first prediction model deployed on the ECU and a second prediction model deployed on the server, and when the connection state between the ECU and the server is different, the corresponding prediction model is different.
[0013] According to the above technical means, since the ECU and the server are connected through a network, and the network will affect the connection status between the ECU and the server. Therefore, according to the connection status between the ECU and the server, the operating parameters of the power rail can be analyzed and processed through the first prediction model deployed locally on the ECU and / or the second prediction model deployed on the server, so as to determine the fault warning information of the power rail. In this way, no matter what the connection status between the ECU and the server is, the fault warning information of the power rail can be determined by the prediction model, and it is known whether the voltage of the power rail will be abnormal within a preset time after the current moment. In this way, the operating status of the power rail in the ECU can be efficiently determined, and the efficiency and accuracy of warning of power rail failures can be improved.
[0014] In a possible implementation, the prediction model corresponding to the connection status between the ECU and the server is used to analyze and process the operating parameters of the power rail to determine the fault warning information of the power rail within a preset time after the current moment, including: when the ECU is disconnected from the server, based on the first prediction model, the operating parameters of the power rail are analyzed and processed to determine the fault warning information of the power rail, and the operating parameters include at least one of the following: operating time and operating voltage; or, when the ECU is connected to the server, based on the first prediction model and / or the second prediction model, the operating parameters of the power rail are analyzed and processed to determine the fault warning information of the power rail, and the operating parameters include at least one of the following: operating time, operating voltage, ambient temperature, ambient humidity, altitude, collision parameters, and operating frequency.
[0015] According to the above technical means, when the ECU is disconnected from the server, a small amount of operating parameters can be analyzed and processed based on the first prediction model deployed locally on the ECU to determine the fault warning information of the power rail. In this case, there is no need to transmit operating parameters between the ECU and the server, there is no delay in data transmission, and the fault warning information of the power rail can be determined in a timely manner. When the ECU is connected to the server, a large number of operating parameters can be further analyzed and processed based on the second prediction model deployed on the server to determine the fault warning information of the power rail. In this case, since the server has a strong data processing capability, more accurate fault warning information can be determined based on a large number of operating parameters. In this way, under the influence of the network, the fault warning information of the power rail can be determined in any case through different operating parameters and corresponding prediction models, thereby improving the efficiency and accuracy of warning of power rail faults.
[0016] In a possible implementation, when the ECU is connected to the server, based on the first prediction model and the second prediction model, the operating parameters of the power rail are analyzed and processed to determine the fault warning information of the power rail within a preset time after the current moment, including: when the ECU is connected to the server, based on the first prediction model, the operating parameters of the power rail are analyzed and processed to determine the first fault warning information of the power rail; the operating parameters of the power rail are sent to the server so that the server determines the second fault warning information of the power rail based on the second prediction model; the second fault warning information sent by the server is received; based on the first fault warning information and the second fault warning information, the fault warning information of the power rail within a preset time after the current moment is determined.
[0017] According to the above technical means, when the ECU is connected to the server, the first fault warning information of the power rail can be determined based on the first prediction model deployed locally on the ECU, and the second fault warning information of the power rail can be determined based on the second prediction model deployed on the server. In this way, by combining the two fault warning information determined by the two prediction models, the characteristics of the first prediction model deployed locally on the ECU that there is no data transmission delay, and the characteristics of the second prediction model deployed on the server that has strong data processing capabilities can be comprehensively considered, thereby further improving the accuracy of the fault warning information.
[0018] In a possible implementation, the power rail includes multiple power lines, and the operating voltage includes the operating voltage of each power line in the multiple power lines collected at each first time interval. The above method also includes: when it is determined that the operating voltage of the target power line exceeds the preset interval for a consecutive preset number of time points, disconnecting the target power line, where the target power line is any power line in the multiple power lines; when the time for disconnecting the target power line reaches a second time, closing the target power line.
[0019] According to the above technical means, for any power line among the multiple power lines included in the power rail, when it is determined that the operating voltage of the power line exceeds the preset range for a consecutive preset number of time points, it can be considered that there is an abnormality in the voltage of the power line, and the target power line is disconnected. By judging the voltage at a consecutive preset number of time points, it is possible to prevent the voltage at a certain time point from changing due to voltage fluctuations, thereby reducing the probability of misjudgment. In addition, combined with the operation of reclosing the power line, the operating voltage of the power line can be further judged, thereby further avoiding misjudgment and disconnecting the power line, affecting the operation of the circuit, and improving the accuracy of determining whether there is an abnormality in the voltage of the power line.
[0020] In a possible implementation, after closing the target power line when the target power line is disconnected for a second time period, the method further includes: disconnecting the target power line when it is determined that the operating voltage of the target power line exceeds a preset range at any time point within a third time period; or keeping the target power line closed when it is determined that the voltage of the target power line is within the preset range at each time point within the third time period.
[0021] According to the above technical means, after the power line is closed again, the operating voltage of the power line can be further judged to further determine whether the voltage of the power line is abnormal and determine the connectivity of the power line. This avoids misjudgment that causes the power line to be disconnected for a long time, affecting the operation of the circuit, and can improve the accuracy of determining whether the voltage of the power line is abnormal.
[0022] In a possible implementation manner, the method further includes: when the number of consecutive disconnections of the target power line reaches a preset number, keeping the target power line disconnected before the ECU is powered on again.
[0023] According to the above technical means, when the power line is disconnected for multiple consecutive times, it can be considered that the voltage of the power line is indeed abnormal and the power line cannot operate normally. Therefore, the power line needs to be disconnected before powering on again to avoid more serious abnormalities in the power line, thereby ensuring the stability of the entire ECU.
[0024] According to a third aspect provided by the present application, a power rail fault warning device is provided, the power rail fault warning device comprising: an acquisition module and a processing module; the acquisition module is used to acquire the operating parameters of the power rail in the electronic controller ECU; the processing module is used to analyze and process the operating parameters of the power rail based on a prediction model corresponding to the connection status of the ECU and the server, and determine the fault warning information of the power rail within a preset time after the current moment, the fault warning information is used to indicate whether the voltage of the power rail is abnormal, and the prediction model comprises at least one of the following: a first prediction model deployed on the ECU, a second prediction model deployed on the server, and when the connection status of the ECU and the server is different, the corresponding prediction model is different.
[0025] In one possible implementation, the processing module is specifically used to analyze and process the operating parameters of the power rail based on the first prediction model to determine the fault warning information of the power rail when the ECU is disconnected from the server, and the operating parameters include at least one of the following: operating time and operating voltage; or, the processing module is specifically used to analyze and process the operating parameters of the power rail based on the first prediction model and / or the second prediction model to determine the fault warning information of the power rail when the ECU is connected to the server, and the operating parameters include at least one of the following: operating time, operating voltage, ambient temperature, ambient humidity, altitude, collision parameters, and operating frequency.
[0026] In a possible implementation, the power rail fault warning device further includes: a transmission module; a processing module, specifically used to analyze and process the operating parameters of the power rail based on the first prediction model to determine the first fault warning information of the power rail when the ECU is connected to the server; the transmission module is used to send the operating parameters of the power rail to the server, so that the server determines the second fault warning information of the power rail based on the second prediction model; the transmission module is also used to receive the second fault warning information sent by the server; the processing module is specifically used to determine the fault warning information of the power rail within a preset time after the current moment based on the first fault warning information and the second fault warning information.
[0027] In a possible implementation, the power rail includes multiple power lines, the operating voltage includes the operating voltage of each of the multiple power lines collected at each first time interval, and the processing module is further used to disconnect the target power line when it is determined that the operating voltage of the target power line exceeds a preset interval for a consecutive preset number of time points, and the target power line is any power line among the multiple power lines; the processing module is also used to close the target power line when the time for disconnecting the target power line reaches a second time.
[0028] In one possible implementation, the processing module is further used to disconnect the target power circuit when it is determined that the operating voltage of the target power circuit exceeds a preset range at any time point within the third time period; or, the processing module is further used to keep the target power circuit closed when it is determined that the voltage of the target power circuit is within the preset range at each time point within the third time period.
[0029] In a possible implementation manner, the processing module is further configured to keep disconnecting the target power line before the ECU is powered on again when the number of consecutive disconnections of the target power line reaches a preset number.
[0030] According to the fourth aspect provided by the present application, an electronic device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.
[0031] According to the fifth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device executes the method in the above-mentioned first aspect and any possible implementation method thereof.
[0032] According to the sixth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.
[0033] According to a seventh aspect provided by the present application, a vehicle is provided, the vehicle comprising a power rail failure warning device as in the second aspect, the vehicle being used to implement a method as in the first aspect and any possible implementation manner thereof.
[0034] Therefore, the above technical features of the present application have the following beneficial effects:
[0035] (1) Since the ECU and the server are connected via a network, the network will affect the connection status between the ECU and the server. Therefore, according to the connection status between the ECU and the server, the operating parameters of the power rail can be analyzed and processed through the first prediction model deployed locally on the ECU and / or the second prediction model deployed on the server, so as to determine the fault warning information of the power rail. In this way, no matter what the connection status between the ECU and the server is, the fault warning information of the power rail can be determined through the prediction model, and it can be known whether the voltage of the power rail will be abnormal within a preset time after the current moment. In this way, the operating status of the power rail in the ECU can be efficiently determined, and the efficiency and accuracy of warning of power rail failures can be improved.
[0036] (2) When the ECU is disconnected from the server, a small number of operating parameters can be analyzed and processed based on the first prediction model deployed locally on the ECU to determine the fault warning information of the power rail. In this case, there is no need to transmit operating parameters between the ECU and the server, there is no delay in data transmission, and the fault warning information of the power rail can be determined in a timely manner. When the ECU is connected to the server, a large number of operating parameters can be further analyzed and processed based on the second prediction model deployed on the server to determine the fault warning information of the power rail. In this case, since the server has a strong data processing capability, more accurate fault warning information can be determined based on a large number of operating parameters. In this way, under the influence of the network, the fault warning information of the power rail can be determined in any case through different operating parameters and corresponding prediction models, thereby improving the efficiency and accuracy of warning of power rail faults.
[0037] (3) When the ECU is connected to the server, the first fault warning information of the power rail can be determined based on the first prediction model deployed locally on the ECU, and the second fault warning information of the power rail can be determined based on the second prediction model deployed on the server. In this way, by combining the two fault warning information determined by the two prediction models, the characteristics of the first prediction model deployed locally on the ECU that there is no data transmission delay and the characteristics of the second prediction model deployed on the server that has strong data processing capabilities can be comprehensively considered, thereby further improving the accuracy of the fault warning information.
[0038] (4) For any power line among the multiple power lines included in the power rail, when it is determined that the operating voltage of the power line exceeds the preset range for a consecutive number of time points, it can be considered that there is an abnormality in the voltage of the power line, and the target power line is disconnected. By judging the voltage at a consecutive number of preset time points, it is possible to prevent the voltage at a certain time point from changing due to voltage fluctuations, thereby reducing the probability of misjudgment. In addition, combined with the operation of reclosing the power line, the operating voltage of the power line can be further judged, thereby further avoiding misjudgment and disconnecting the power line, which affects the operation of the circuit, and can improve the accuracy of determining whether there is an abnormality in the voltage of the power line.
[0039] (5) After the power line is closed again, the operating voltage of the power line can be further determined to further determine whether the voltage of the power line is abnormal and determine the connectivity of the power line. This avoids misjudgment that causes the power line to be disconnected for a long time, affecting the operation of the circuit, and can improve the accuracy of determining whether the voltage of the power line is abnormal.
[0040] (6) When the power line is disconnected for multiple times in succession, it can be considered that the voltage of the power line is indeed abnormal and the power line cannot operate normally. Therefore, the power line needs to be disconnected before powering on again to avoid more serious abnormalities in the power line, thereby ensuring the stability of the entire ECU.
[0041] It should be noted that the technical effects brought about by any implementation method in the second to seventh aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.
[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.
[0044] Figure 1 is a structural schematic diagram of a power rail fault early warning system according to an exemplary embodiment;
[0045] Figure 2 is a flow chart of a power rail fault early warning method according to an exemplary embodiment;
[0046] Figure 3 is a flow chart of another power rail fault early warning method according to an exemplary embodiment;
[0047] Figure 4 is a flow chart of another power rail fault early warning method according to an exemplary embodiment;
[0048] Figure 5 is a flow chart of another power rail fault early warning method according to an exemplary embodiment;
[0049] Figure 6 is a block diagram of a power rail fault early warning device according to an exemplary embodiment;
[0050] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0051] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.
[0053] At present, it is proposed to decompose the functional safety of the whole vehicle system into each ECU, emphasizing the functional safety of each ECU itself. When designing an ECU, it is necessary to consider the schematic design, the layout of the printed circuit board (PCB), the software architecture design, etc. Among them, the power supply design, which is the basis for ensuring the normal operation of the ECU, is particularly important. The quality of the ECU's power supply circuit design will directly affect whether the ECU is stable and reliable during operation. Of course, the stability of ECU operation is also inseparable from the support of software. How to design the software's monitoring strategy for the power supply circuit, thereby improving the stability of ECU operation, and real-time monitoring and detection of early warning fault information, has become the main design idea of ECU.
[0054] The power rail fault warning method provided in the embodiment of the present application can be applied to a power rail fault warning system. Figure 1 FIG. 1 shows a schematic diagram of the structure of a power rail fault warning system. Figure 1 As shown, the power rail fault warning system 10 includes: an ECU 11 and a server 12 , the ECU 11 includes: a power rail 111 and an MCU 112 , and the power rail 111 includes: an SBC 1111 and a DC-DC circuit 1112 .
[0055] A first prediction model is deployed on ECU11, and ECU11 is used to obtain the operating parameters of the power rail 111, and analyze and process the operating parameters of the power rail 111 based on the first prediction model, and determine the fault warning information of the power rail 111 within a preset time after the current moment. The fault warning information is used to indicate whether the voltage of the power rail 111 is abnormal.
[0056] The power rail fault warning system 10 further includes a telematics BOX (T-BOX) gateway 13, and the T-BOX gateway is used to upload the operating parameters of the power rail 111 to the server 12. The operating parameters of the power rail 111 are uploaded to the server 12 via the T-BOX gateway 13 for special communication between the ECU 11 and the server 12.
[0057] A second prediction model is deployed on the server 12, and the server 12 is used to analyze and process the operating parameters of the power rail 111 based on the second prediction model, and determine the fault warning information of the power rail 111 within a preset time after the current moment.
[0058] Specifically, ECU11 can obtain the operating parameters of the local power rail 111, and analyze and process the operating parameters of the power rail 111 based on the prediction model corresponding to the connection status of ECU11 and the server 12, and determine the fault warning information of the power rail 111 within a preset time after the current moment. The fault warning information is used to indicate whether the voltage of the power rail 111 is abnormal. The prediction model includes at least one of the following: a first prediction model deployed on ECU11 and a second prediction model deployed on the server 12. When the connection status between ECU11 and the server 12 is different, the corresponding prediction model is different.
[0059] In some embodiments, the first prediction model is specifically deployed in MCU112, and MCU112 can specifically collect the operating parameters of SBC1111 and DC-DC circuit 1112 included in power rail 111 based on analog to digital converter (ADC) sampling, and perform data storage and data processing on the operating parameters. Then the operating parameters are input into the first prediction model, and fault warning information is output. It should be noted that the first prediction model can be obtained by model training in advance through empirical data.
[0060] In some embodiments, the power rail 111 includes: a system basis chip SBC and a DC-DC circuit, the ECU corresponds to a target safety level, the ECU includes a microcontroller unit MCU, and the configuration parameters of the MCU and the configuration parameters of the SBC both meet the target safety level.
[0061] In some embodiments, the MCU further includes a detection circuit, and the detection circuit is used to detect a power supply circuit included in the MCU to determine whether the MCU is abnormal.
[0062] For ease of understanding, the power rail fault warning method provided by the present application is specifically introduced below with reference to the accompanying drawings.
[0063] Figure 2 is a flow chart of a power rail fault early warning method according to an exemplary embodiment. Figure 2 As shown, the method includes the following S201-S202:
[0064] S201. Obtain operating parameters of a power rail in an ECU.
[0065] Optionally, the operating parameters of the power rail may be collected by the MCU in the ECU, and data storage and data processing of the operating parameters may be performed.
[0066] Optionally, when obtaining the operating parameters of the power rail in the ECU, some power rail parameter collection designs can be added so that the MCU can collect the operating parameters of the SBC and DC-DC circuits in real time and obtain the working status of the power rail.
[0067] Specifically, the SBC and DC-DC circuits can be linked to the AD analog quantity acquisition pins of the MCU through a voltage divider circuit, thereby realizing the function of the MCU collecting the operating parameters of the SBC and DC-DC circuits. And for each power supply line included in the SBC and DC-DC circuits, at least one set of return pins needs to be linked to the AD analog quantity acquisition pins of the MCU to collect the operating parameters of the power supply line (such as output voltage). If there is a redundant design requirement, the same power supply line can have two sets of return pins linked to the AD analog quantity acquisition pins of the MCU.
[0068] In some embodiments, the power rail includes: a system basis chip SBC and a DC-DC circuit, the ECU corresponds to a target safety level, the ECU includes a microcontroller unit MCU, and the configuration parameters of the MCU and the configuration parameters of the SBC both meet the target safety level.
[0069] Specifically, the operating parameters of the SBC and the DC-DC circuit may be collected through the MCU. For example, the SBC may be a chip of the FS26 model, or a chip of the FS45 model, or a chip of the FS65 model, etc.
[0070] Optionally, when designing an ECU with automotive safety integrity level (ASIL) requirements, according to the different functional safety levels (ASIL-A\B\C\D), when designing the ECU power supply circuit, you can use an SBC of the corresponding level that matches the MCU. Then, the DC-DC circuit is used to assist in achieving the full power supply voltage requirements of the ECU.
[0071] Based on this, SBC can replace a large number of DC-DC circuits, which can greatly reduce the number of components used in the power supply circuit (i.e. the number of DC-DC circuits), thereby reducing the risk points that may cause failures and reducing the possibility of power supply circuit failure.
[0072] Optionally, since the power rail includes SBC, some functional safety related measures can be simplified. Since the functional safety related measures provided by the SBC chip itself can ensure that the power system reaches the corresponding ASIL level, common measures include: output voltage over-voltage and under-voltage monitoring, SBC watchdog, monitoring of the MCU's fault collection and control unit (FCCU), and fault mode output after triggering fail-safe. Therefore, based on this, the register parameters of the SBC can be configured based on the power supply requirements to achieve the corresponding fault warning function.
[0073] Optionally, you can also consider redundantly monitoring the SBC through the MCU alone, for example: independently collect and monitor the input voltage and output voltage of the SBC, enable the operation of the independent watchdog monitoring software inside the MCU, and regularly perform the built-in self test (BIST) function on the SBC. The BIST self-test function can determine whether the SBC functions normally and whether the data is reliable.
[0074] In this way, by adding redundant measures, the operating trend of the SBC can be monitored in real time. When a fault occurs, the status trend of the power line in the SBC before and after the fault can be obtained, the failure risk of the SBC can be predicted in advance, and the early warning function can be realized.
[0075] Optionally, the operating parameters of the power rail in the ECU can be obtained once every first time interval (e.g., 50ms, 100ms), and the obtained operating parameters can be stored in an independent array. Furthermore, when the accumulated stored data reaches an upper limit (e.g., 1000 groups, 2000 groups of data), the oldest data is removed and the new data is stored, and this rule is repeated recursively.
[0076] Optionally, for the auxiliary DC-DC circuit, the MCU can monitor the over / under voltage of the power supply circuit included in the DC-DC circuit, and the voltage of the power supply circuit included in the DC-DC circuit can be periodically collected through the ADC of the MCU. When the power supply circuit is over / under voltage, abnormal control (such as disconnecting the power supply circuit) and corresponding recovery strategies (such as closing the power supply circuit) are triggered. In this way, in the process of monitoring the DC-DC circuit, the change trend data of the operating parameters of the DC-DC circuit can be obtained.
[0077] In the embodiment of the present application, by deploying SBC on ECU, the number of DC-DC circuits deployed can be reduced, and SBC itself can provide functional safety related measures to ensure the safety of the power supply line. In this way, the number of components deployed on ECU can be reduced, thereby reducing the probability of power rail failure. In addition, by determining the corresponding safety levels of MCU, SBC and ECU, the probability of power rail failure can be reduced by using high-quality and high-safety devices.
[0078] S202: Analyze and process the operating parameters of the power rail based on the prediction model corresponding to the connection status between the ECU and the server, and determine the fault warning information of the power rail within a preset time after the current moment.
[0079] Among them, the fault warning information is used to indicate whether the voltage of the power rail is abnormal. The prediction model includes at least one of the following: a first prediction model deployed on the ECU and a second prediction model deployed on the server. When the connection status between the ECU and the server is different, the corresponding prediction model is different.
[0080] Optionally, the fault warning information is also used to indicate a power line where a power rail fault is predicted to occur, and the time when the fault occurs.
[0081] It should be noted that, considering that the connection between ECU and server requires a network, if only a prediction model is deployed on the server in the cloud, due to the delay in data transmission and whether the connection between ECU and server is abnormal (for example, network disconnection and inability to transmit operating parameters), the prediction model in the server will reduce the timeliness of operating parameter analysis and processing, miss the best processing opportunity, and cause the obtained fault warning information to be biased.
[0082] Therefore, this application deploys a large machine learning model (i.e., the second prediction model) in the server, which is mainly responsible for data training and long-term prediction, and at the same time deploys a small prediction model (i.e., the first prediction model) locally in the ECU, which is mainly responsible for short-term processing of operating parameters. The two prediction models can work together to improve the accuracy and timeliness of determining fault warning information.
[0083] Optionally, the MCU local to the ECU can use a multi-core controller to deploy a first prediction model locally on the ECU without affecting normal functions. The first prediction model is a small-scale model (small machine learning model) that does not require data learning and model training as much as possible, or data learning and model training can be completed in advance (for example, deployed locally on the ECU after pre-training on other devices), and there is no need to re-perform data learning and model training during the operation of the ECU.
[0084] Exemplarily, the first prediction model may be: a multivariable linear regression algorithm, a ridge regression algorithm, a multicollinearity algorithm, etc. These models require a small amount of training data, are fast and simple to model, and meet the local performance conditions of the ECU.
[0085] Optionally, the large machine learning model (i.e., the second prediction model) deployed on the server can select a more powerful and complex model to achieve long-term data training, prediction, iteration, and experience accumulation because it does not have the various performance limitations of the ECU itself. Therefore, in the process of determining the fault warning information through the second prediction model, the model can be continuously trained, and based on the determined fault warning information, the second prediction model can iteratively learn data to improve the performance of the second prediction model and the accuracy of the prediction results.
[0086] Exemplarily, the second prediction model can be: support vector machine (SVM) classification algorithm, Bayesian classification algorithm, decision tree algorithm, artificial neural network, etc. These models improve the generalization ability of the learning machine by seeking the minimum structured risk, and minimize the empirical risk and confidence range.
[0087] In the embodiment of the present application, since the ECU and the server are connected via a network, the network will affect the connection status between the ECU and the server. Therefore, according to the connection status between the ECU and the server, the operating parameters of the power rail can be analyzed and processed by the first prediction model deployed locally on the ECU and / or the second prediction model deployed on the server, so as to determine the fault warning information of the power rail. In this way, no matter what the connection status between the ECU and the server is, the fault warning information of the power rail can be determined by the prediction model, and it is known whether the voltage of the power rail will be abnormal within a preset time after the current moment. In this way, the operating status of the power rail in the ECU can be efficiently determined, and the efficiency and accuracy of warning of power rail failures can be improved.
[0088] In some embodiments, Figure 3 As shown, in a power rail fault warning method provided in an embodiment of the present application, the above step S202 may specifically include S301 or S302:
[0089] S301 . When the ECU is disconnected from the server, based on a first prediction model, analyze and process operating parameters of the power rail to determine fault warning information of the power rail.
[0090] The operating parameters include at least one of the following: operating time and operating voltage. The operating time and operating voltage are the parameters that are most directly related to the operating state of the power supply line.
[0091] Optionally, when the ECU is disconnected from the server, the ECU cannot send the operating parameters of the power rail to the server. Therefore, the operating parameters of the power rail can be analyzed and processed by the locally deployed first prediction model to determine the fault warning information of the power rail.
[0092] It should be noted that due to the low data processing capability of the ECU, the first prediction model deployed locally is a small-scale model. Therefore, when analyzing and processing the operating parameters of the power rail through the first prediction model deployed locally by the ECU, the fault warning information of the power rail can be determined only by the operating time and operating voltage.
[0093] S302: When the ECU is connected to the server, based on the first prediction model and / or the second prediction model, analyze and process the operating parameters of the power rail to determine fault warning information of the power rail.
[0094] The operating parameters include at least one of the following: operating time, operating voltage, ambient temperature, ambient humidity, altitude, collision parameters, and operating frequency.
[0095] Optionally, when the ECU is connected to the server, the ECU can send the operating parameters of the power rail to the server. Therefore, the operating parameters of the power rail can be analyzed and processed by the second prediction model deployed on the server to determine the fault warning information of the power rail.
[0096] It should be noted that since the server has strong data processing capabilities, the second prediction model deployed on the server is a large-scale machine learning model. Therefore, by analyzing and processing the operating parameters of the power rail through the second prediction model deployed on the server, a large number of related parameters can be analyzed and processed, and the influence of various parameters can be comprehensively considered to more accurately determine the fault warning information of the power rail.
[0097] In an embodiment of the present application, when the ECU is disconnected from the server, a small amount of operating parameters can be analyzed and processed based on the first prediction model deployed locally on the ECU to determine the fault warning information of the power rail. In this case, there is no need to transmit operating parameters between the ECU and the server, there is no delay in data transmission, and the fault warning information of the power rail can be determined in a timely manner. When the ECU is connected to the server, a large number of operating parameters can be further analyzed and processed based on the second prediction model deployed on the server to determine the fault warning information of the power rail. In this case, since the server has a strong data processing capability, more accurate fault warning information can be determined based on a large number of operating parameters. In this way, under the influence of the network, the fault warning information of the power rail can be determined in any case through different operating parameters and corresponding prediction models, thereby improving the efficiency and accuracy of warning of power rail faults.
[0098] In some embodiments, Figure 4 As shown, in a power rail fault warning method provided in an embodiment of the present application, the above step S302 may specifically include S401-S404:
[0099] S401 : When the ECU is connected to the server, based on a first prediction model, analyze and process operating parameters of the power rail to determine first fault warning information of the power rail.
[0100] Optionally, the acquired operating parameters of the power rail may be input into the first prediction model for analysis and processing at certain intervals (e.g., 10 seconds, 20 seconds), to analyze the changing trend of the operating parameters, estimate the time point when the risk of failure may occur, and determine the fault warning information.
[0101] Optionally, when the estimated time point at which the risk of failure may occur exceeds a reasonable time range (determined based on experience and models), it can be considered that the power rail currently does not have a risk of failure. Otherwise, preventive measures can be taken in advance for power lines with a risk of failure. For example, report the fault warning information to the server, and the backend staff will decide how to handle the fault; or, before the time point at which the risk of failure occurs, the corresponding power line can be shut down in advance to prevent other failure risks.
[0102] S402: Send the operating parameters of the power rail to the server, so that the server determines second fault warning information of the power rail based on the second prediction model.
[0103] Optionally, the operating parameters of the source track within a certain time period (eg, 50 seconds, 60 seconds) stored locally in the ECU may be sent to the server.
[0104] Optionally, since the operating parameters of the power rail are obtained every 50ms, the operating parameters of the source rail within a certain period of time (such as 50 seconds, 60 seconds) still include a large amount of data information. Therefore, the ECU can be set to transmit the operating parameters to the server through the T-BOX once per second.
[0105] Optionally, multiple (e.g., 20) operating parameters acquired per second may be preprocessed to determine the root mean square (or average) of the multiple operating parameters acquired per second, and the root mean square (or average) of the multiple operating parameters acquired per second may be sent to the server. This can solve the problem of large data volume and high load of data transmitted to the server, while retaining the characteristic that the operating parameters change all the time, and provide reliable training samples and prediction data for the second prediction model in the server.
[0106] Optionally, after receiving the operating parameters of the power rail, the server may train a second prediction model, and predict second fault warning information of the power rail based on the operating parameters of the power rail.
[0107] Optionally, the second prediction model in the server needs to be trained based on a large amount of data to obtain a prediction model with a stable convergence state, thereby providing effective and reliable prediction results. At the same time, the training samples can be continuously enriched based on the received real-time operating parameters to further iterate the training of the second prediction model.
[0108] It should be noted that a large amount of data may be operating parameters for a duration of 5000 hours (or 6000 hours), which duration may be determined based on the characteristics of the three failure stages in the characteristic curve of failure rate and time (ie, the bathtub curve).
[0109] S403: Receive second fault warning information sent by the server.
[0110] S404: Determine the fault warning information of the power rail within a preset time period after the current moment based on the first fault warning information and the second fault warning information.
[0111] Optionally, the time when the power rail failure is predicted to occur can be determined based on the first fault warning information indicating the predicted time when the power rail failure occurs, and the second fault warning information indicating the predicted time when the power rail failure occurs, by comprehensively considering the accuracy of the first prediction model and the accuracy of the second prediction model, to determine a more accurate time when the power rail failure occurs, thereby determining more accurate fault warning information.
[0112] Exemplarily, the accuracy of the first prediction model is 90%, the accuracy of the second prediction model is 95%, the first fault warning information indicates that the predicted time of the power rail failure is 30 minutes later, and the second fault warning information indicates that the predicted time of the power rail failure is 25 minutes later. Then, based on these parameters, as well as the coefficient corresponding to the accuracy of the first prediction model (for example, 0.6) and the coefficient corresponding to the accuracy of the second prediction model (for example, 0.4), it can be determined that the time of the power rail failure is 28 minutes.
[0113] In the embodiment of the present application, when the ECU is connected to the server, the first fault warning information of the power rail can be determined based on the first prediction model deployed locally on the ECU, and the second fault warning information of the power rail can be determined based on the second prediction model deployed on the server. In this way, by combining the two fault warning information determined by the two prediction models, the characteristics of the first prediction model deployed locally on the ECU that there is no data transmission delay, and the characteristics of the second prediction model deployed on the server that has strong data processing capabilities can be comprehensively considered, thereby further improving the accuracy of the fault warning information.
[0114] In some embodiments, when the ECU is powered on, the SBC needs to be initialized first, and parameters are written to the function registers corresponding to the SBC according to the functional safety requirements and fault safety requirements to configure the SBC to take safety actions after triggering over / under voltage (for example, disconnecting the power circuit).
[0115] It should be noted that the over-voltage and under-voltage thresholds of some SBC models (such as the FS26 model) are configured in the one-time programmable (OTP) area, which is written by the chip factory and does not require software configuration.
[0116] Optionally, you also need to configure the upper threshold of the SBC fault counter (e.g., 3 times, 5 times, etc.), and the fail-safe action is to pull down the voltage of the RSTB pin and the FS0B pin. You can also configure the delay time of the FS1B pin (e.g., 500ms, 1s), that is, after the FS0B pin performs the voltage pull-down action, the voltage of the FS1B pin is pulled down after a delay of 500ms.
[0117] Optionally, you can also configure the SBC watchdog parameters, set the dog feeding cycle (e.g. 1024ms), and the dog feeding window period ratio (e.g. 50%). You can also configure the upper threshold of the watchdog fault counter (i.e. the upper limit of abnormal dog feeding times, e.g. 4 times, 5 times), and the corresponding fail-safe action is to lower the voltage of the RSTB pin and the FS0B pin, and configure the upper threshold of the watchdog refresh counter.
[0118] Optionally, you can also configure the effective level of the FCCU, and the corresponding fail-safe action is to pull down the voltage of the RSTB pin and the FS0B pin. And configure the over / under voltage fail-safe action of the SBC to pull down the voltage of the RSTB pin and the FS0B pin. And configure the MUX pin output source of the SBC, and cyclically switch the output source in the periodic task for the ADC of the MCU to periodically collect data and monitor the output voltage status of the SBC.
[0119] It should be noted that the fail-safe action is an action that needs to be performed to handle the fault when a power rail fails, and is used to resolve the fault in the power rail and ensure the stability of the power rail.
[0120] In some embodiments, the power rail includes a plurality of power lines, and the operating voltage includes the operating voltage of each of the plurality of power lines collected at each first time interval, such as Figure 5 As shown, a power rail fault warning method provided in an embodiment of the present application may further include S501-S505:
[0121] S501: When it is determined that the operating voltage of the target power line exceeds a preset range at a preset number of consecutive time points, disconnect the target power line.
[0122] The target power line is any power line among the multiple power lines.
[0123] Optionally, it is possible to determine whether the operating voltage corresponding to each of the multiple power lines included in the power rail reaches a preset over / under voltage threshold (i.e., exceeds a preset interval), so that when the operating voltage corresponding to the power line exceeds the preset interval, the power line needs to be disconnected to ensure the stability of the power rail.
[0124] Optionally, it is possible to determine whether the operating voltage of the power supply line exceeds a preset range once every certain time interval. Therefore, it is also possible to determine whether the operating voltage of the power supply line exceeds the preset range by determining whether the corresponding operating voltage of the power supply line exceeds the preset range for multiple consecutive times (for example, 3 times).
[0125] It should be noted that disconnecting the power line can be accomplished by turning off (pulling low) the enable control pin of the power line.
[0126] S502: When the target power line is disconnected for a second period of time, close the target power line.
[0127] It should be noted that, in some cases, the operating voltage of the power line is recoverable when it exceeds the preset range, that is, the operating voltage of the power line can return to the preset range after exceeding the preset range for a short period of time. Therefore, in order to eliminate the situation of automatic fault recovery, the power line can be closed again after a second time interval (for example, 30 seconds), and the operating voltage of the power line can be re-tested.
[0128] In an embodiment of the present application, for any power line among the multiple power lines included in the power rail, when it is determined that the operating voltage of the power line exceeds the preset interval for a consecutive number of time points, it can be considered that there is an abnormality in the voltage of the power line, and the target power line is disconnected. By judging the voltage at a consecutive number of preset time points, it is possible to prevent the voltage at a certain time point from changing due to voltage fluctuations, thereby reducing the probability of misjudgment. In addition, combined with the operation of reclosing the power line, the operating voltage of the power line can be further judged, thereby further avoiding misjudgment and disconnecting the power line, affecting the operation of the circuit, and improving the accuracy of determining whether there is an abnormality in the voltage of the power line.
[0129] S503: When it is determined that the operating voltage of the target power line exceeds a preset range at any time point within the third time period, disconnect the target power line.
[0130] Optionally, when the power line is reclosed and the operating voltage of the power line is re-tested, if, during multiple tests within the third time period, it is determined at any time point that the operating voltage of the power line exceeds the preset range again, the power line needs to be disconnected again.
[0131] S504: When it is determined that the voltage of the target power circuit belongs to the preset range at each time point within the third time period, keep the target power circuit closed.
[0132] Optionally, if during multiple detections within the third time period, it is determined that the voltage of the power line belongs to the preset range, it is considered that the fault is automatically recovered, there is no fault in the power line, and the power line can be kept running.
[0133] In the embodiment of the present application, after the power line is closed again, the operating voltage of the power line can be further determined to further determine whether the voltage of the power line is abnormal and determine the connectivity of the power line. This avoids misjudgment that causes the power line to be disconnected for a long time, affecting the operation of the circuit, and can improve the accuracy of determining whether the voltage of the power line is abnormal.
[0134] S505: When the number of times the target power line is disconnected continuously reaches a preset number, the target power line is kept disconnected before the ECU is powered on again.
[0135] Optionally, if the operating voltage of the power line is determined to be beyond the preset range for multiple times in a row and the power line is disconnected multiple times, the fault of the power line is considered to be a fault that cannot be automatically recovered and needs to be handled by staff. Therefore, the power line can be disconnected for a long time to keep the target power line disconnected before the ECU is powered on again.
[0136] In the embodiment of the present application, when the power line is disconnected for multiple consecutive times, it can be considered that the voltage of the power line is indeed abnormal and the power line cannot operate normally. Therefore, the power line needs to be disconnected before powering on again to avoid more serious abnormalities in the power line, thereby ensuring the stability of the entire ECU.
[0137] In some embodiments, the MCU further includes a detection circuit, which is used to detect a power line included in the MCU. The above method further includes: performing a self-test operation on the power line included in the MCU at every fourth time interval by the detection circuit to determine whether the MCU is abnormal.
[0138] Optionally, the self-check function can be periodically turned on to determine whether the MCU is abnormal. The self-check function can be turned on for a period of 1 to 24 hours, or a self-check can be performed every 3 (5) driving cycles (i.e., the MCU is powered on 3 times in a row and a self-check is performed).
[0139] In the embodiment of the present application, the detection circuit included in the MCU can be further used to periodically perform self-checking operations on the power supply circuit included in the MCU to determine whether the power supply circuit included in the MCU itself is abnormal, thereby further ensuring the stability of the MCU and reducing the probability of MCU failure.
[0140] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the power rail fault warning device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.
[0141] The embodiment of the present application can exemplarily divide the functional modules of the power rail fault warning device or the electronic device according to the above method. For example, the power rail fault warning device or the electronic device may include various functional modules corresponding to the various functional divisions, or two or more functions may be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.
[0142] Figure 6 is a block diagram of a power rail fault warning device according to an exemplary embodiment. Figure 6 The power rail fault warning device 600 includes: an acquisition module 601, a processing module 602 and a transmission module 603.
[0143] The acquisition module 601 is used to acquire the operating parameters of the power rail in the electronic controller ECU; the processing module 602 is used to analyze and process the operating parameters of the power rail based on the prediction model corresponding to the connection status of the ECU and the server, and determine the fault warning information of the power rail within a preset time after the current moment. The fault warning information is used to indicate whether the voltage of the power rail is abnormal. The prediction model includes at least one of the following: a first prediction model deployed on the ECU and a second prediction model deployed on the server. When the connection status of the ECU and the server is different, the corresponding prediction model is different.
[0144] In one possible implementation, the processing module 602 is specifically used to analyze and process the operating parameters of the power rail based on the first prediction model to determine the fault warning information of the power rail when the ECU is disconnected from the server, and the operating parameters include at least one of the following: operating time and operating voltage; or, the processing module 602 is specifically used to analyze and process the operating parameters of the power rail based on the first prediction model and / or the second prediction model to determine the fault warning information of the power rail when the ECU is connected to the server, and the operating parameters include at least one of the following: operating time, operating voltage, ambient temperature, ambient humidity, altitude, collision parameters, and operating frequency.
[0145] In one possible implementation, the processing module 602 is specifically used to analyze and process the operating parameters of the power rail based on the first prediction model to determine the first fault warning information of the power rail when the ECU is connected to the server; the transmission module 603 is used to send the operating parameters of the power rail to the server, so that the server determines the second fault warning information of the power rail based on the second prediction model; the transmission module 603 is also used to receive the second fault warning information sent by the server; the processing module 602 is specifically used to determine the fault warning information of the power rail within a preset time after the current moment based on the first fault warning information and the second fault warning information.
[0146] In one possible implementation, the power rail includes multiple power lines, the operating voltage includes the operating voltage of each of the multiple power lines collected at each first time interval, and the processing module 602 is further used to disconnect the target power line when it is determined that the operating voltage of the target power line exceeds a preset interval for a consecutive preset number of time points, and the target power line is any power line among the multiple power lines; the processing module 602 is also used to close the target power line when the time for disconnecting the target power line reaches a second time.
[0147] In one possible implementation, the processing module 602 is further used to disconnect the target power line when it is determined that the operating voltage of the target power line exceeds a preset range at any time point within the third time period; or, the processing module 602 is further used to keep the target power line closed when it is determined that the voltage of the target power line is within the preset range at each time point within the third time period.
[0148] In a possible implementation manner, the processing module 602 is further configured to keep disconnecting the target power line before the ECU is powered on again when the number of consecutive disconnections of the target power line reaches a preset number.
[0149] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0150] Figure 7 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 includes but is not limited to: a processor 701 and a memory 702 .
[0151] The memory 702 is used to store executable instructions of the processor 701. It can be understood that the processor 701 is configured to execute instructions to implement the power rail fault early warning method in the above embodiment.
[0152] It should be noted that those skilled in the art can understand that Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Figure 7 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.
[0153] The processor 701 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 702, and calling data stored in the memory 702, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 701 may include one or more processing units. Optionally, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.
[0154] The memory 702 may be used to store software programs and various data. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a processing module, etc.), etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0155] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 702 including instructions, and the above instructions can be executed by a processor 701 of an electronic device 700 to implement the power rail fault early warning method in the above embodiment.
[0156] In actual implementation, Figure 6 The functions of the acquisition module 601, the processing module 602 and the transmission module 603 in Figure 7 The processor 701 in the embodiment calls the computer program stored in the memory 702. The specific execution process can refer to the description of the power rail fault early warning method in the above embodiment, which will not be repeated here.
[0157] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0158] In an exemplary embodiment, the embodiment of the present application further provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 701 of the electronic device 700 to implement the power rail fault early warning method in the above embodiment.
[0159] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned power rail fault warning method embodiment are implemented, and the same technical effect as the above-mentioned power rail fault warning method can be achieved. To avoid repetition, it will not be repeated here.
[0160] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0161] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0162] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0164] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.
[0165] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A power rail fault early warning system, It is characterized in that The power rail fault warning system includes: an electronic controller ECU, a telematics processor T-BOX gateway and a server; The ECU includes a power rail, and a first prediction model is deployed on the ECU. The ECU is used to obtain operating parameters of the power rail, and analyze and process the operating parameters of the power rail based on the first prediction model to determine fault warning information of the power rail within a preset time after a current moment, and the fault warning information is used to indicate whether the voltage of the power rail is abnormal; The T-BOX gateway is used to upload the operating parameters of the power rail to the server; A second prediction model is deployed on the server, and the server is used to analyze and process the operating parameters of the power rail based on the second prediction model to determine fault warning information of the power rail within a preset time after a current moment.
2. The power rail fault early warning system according to claim 1, It is characterized in that The power rail includes: a system basis chip SBC and a direct current-to-direct current DC-DC circuit. The ECU corresponds to a target safety level. The ECU includes a microcontroller unit MCU. Configuration parameters of the MCU and configuration parameters of the SBC both meet the target safety level.
3. The power rail fault early warning system according to claim 1 or 2, It is characterized in that The MCU further includes a detection circuit, and the detection circuit is used to detect a power supply circuit included in the MCU to determine whether the MCU is abnormal.
4. A power rail fault early warning method, It is characterized in that The method comprises: Get the operating parameters of the power rail in the electronic controller ECU; Based on the prediction model corresponding to the connection status of the ECU and the server, the operating parameters of the power rail are analyzed and processed to determine the fault warning information of the power rail within a preset time after the current moment, and the fault warning information is used to indicate whether the voltage of the power rail is abnormal. The prediction model includes at least one of the following: a first prediction model deployed on the ECU and a second prediction model deployed on the server. When the connection status of the ECU and the server is different, the corresponding prediction model is different.
5. The method according to claim 4, It is characterized in that The prediction model corresponding to the connection state between the ECU and the server is used to analyze and process the operating parameters of the power rail to determine the fault warning information of the power rail within a preset time after the current moment, including: When the ECU is disconnected from the server, based on the first prediction model, analyzing and processing the operating parameters of the power rail to determine the fault warning information of the power rail, the operating parameters including at least one of the following: operating time and operating voltage; Alternatively, when the ECU is connected to the server, based on the first prediction model and / or the second prediction model, the operating parameters of the power rail are analyzed and processed to determine the fault warning information of the power rail, and the operating parameters include at least one of the following: the operating time, the operating voltage, ambient temperature, ambient humidity, altitude, collision parameters, and operating frequency.
6. The method according to claim 5, It is characterized in that When the ECU is connected to the server, based on the first prediction model and the second prediction model, the operating parameters of the power rail are analyzed and processed to determine the fault warning information of the power rail within a preset time after the current moment, including: When the ECU is connected to the server, based on the first prediction model, analyzing and processing the operating parameters of the power rail to determine first fault warning information of the power rail; sending the operating parameters of the power rail to the server, so that the server determines second fault warning information of the power rail based on the second prediction model; receiving the second fault warning information sent by the server; Based on the first fault warning information and the second fault warning information, fault warning information of the power rail within a preset time period after a current moment is determined.
7. The method according to any one of claims 4 to 6, It is characterized in that The power rail includes a plurality of power lines, the operating voltage includes the operating voltage of each of the plurality of power lines collected at intervals of a first time length, and the method further includes: When it is determined that the operating voltage of the target power line exceeds a preset range at a preset number of consecutive time points, disconnecting the target power line, wherein the target power line is any power line among the multiple power lines; When the time duration for which the target power line is opened reaches a second time duration, the target power line is closed.
8. The method according to claim 7, It is characterized in that In the case where the duration of disconnecting the target power line reaches a second duration, after closing the target power line, the method further includes: If it is determined at any time point within the third time period that the operating voltage of the target power line exceeds the preset interval, disconnecting the target power line; Alternatively, when it is determined that the voltage of the target power circuit belongs to the preset interval at each time point within the third time period, the target power circuit is kept closed.
9. The method according to claim 8, It is characterized in that The method further comprises: When the number of times the target power line is disconnected continuously reaches a preset number, the target power line is kept disconnected before the ECU is powered on again.
10. A power rail fault warning device, It is characterized in that The power rail fault early warning device comprises: an acquisition module and a processing module; The acquisition module is used to acquire the operating parameters of the power rail in the electronic controller ECU; The processing module is used to analyze and process the operating parameters of the power rail based on the prediction model corresponding to the connection status of the ECU and the server, and determine the fault warning information of the power rail within a preset time after the current moment, wherein the fault warning information is used to indicate whether the voltage of the power rail is abnormal. The prediction model includes at least one of the following: a first prediction model deployed on the ECU and a second prediction model deployed on the server. When the connection status of the ECU and the server is different, the corresponding prediction model is different.
11. An electronic device, It is characterized in that include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method as claimed in any one of claims 4 to 9.
12. A vehicle, It is characterized in that The vehicle comprises the power rail failure warning device according to claim 10, and the vehicle is used to implement the method according to any one of claims 4-9.
Citation Information
Patent Citations
Intelligent driving area controller
CN117068189A
