System for predicting remaining useful life
By deploying compilers and sensors in vehicle components, combining operating modes and statistics, the problem of difficulty in accurately predicting the remaining service life of vehicles in the prior art is solved, and accurate life prediction of all components is achieved, reducing maintenance cost.
Patent Information
- Application Number
- CN202411013562.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-07-28
- Filing Date
- 2024-07-26
- Publication Date
- 2025-02-14
AI Technical Summary
The prior art is difficult to accurately predict the remaining service life of vehicle components, especially those that are not in communication with the ECU.
Using a system and method, the system includes a compiler and a sensor connected to it, and by analyzing the operating mode and actual use of the vehicle, combining statistical data from the dealer network, the predictive reliability and actual reliability of the components are calculated, and then Determine the remaining service life of the component.
Accurate residual service life predictions for all vehicle components, including those not connected to the ECU, are achieved, reducing unnecessary component replacement and maintenance costs.
Smart Images
Figure CN119442445A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to systems and methods for predicting the remaining useful life (RUL) of automotive components. Background Art
[0002] The remaining useful life (RUL) of a vehicle component is the amount of time the component can continue to operate effectively without repair or replacement. Accurately determining the RUL of a vehicle component significantly eliminates unnecessary expenses due to premature replacement of components. Such premature replacement of vehicle components occurs due to predetermined schedules issued by vehicle manufacturers, which do not take into account the actual degree of use of the vehicle.
[0003] Conventional predictive tools for determining the RUL of automotive components utilize on-board diagnostics (OBD) or performance-based predictive models. OBD involves electronic communication between various vehicle components and an electronic control unit (ECU). However, some vehicle components are not communicatively connected to the ECU.
[0004] Performance-based prediction models infer RUL estimates based on performance metrics.Such performance-based models are inaccurate proxies for the actual degree of usage of specific vehicle components and, therefore, can be unreliable.
[0005] What is needed are systems and methods for determining the RUL of vehicle components that are based on actual usage of the vehicle in operating modes that affect the vehicle components of interest. What is needed are systems and methods for estimating the RUL of substantially all vehicle components, regardless of whether the vehicle components are communicatively connected to an ECU. Summary of the invention
[0006] Described herein are embodiments of systems and methods for determining the remaining useful life (RUL) of vehicle components included in and / or on a vehicle. The system may include a compiler and a dealer network communicatively connected to the compiler. In an embodiment, the system may further include one or more sensors positioned in and / or on the vehicle components. The (one or more) sensors may be communicatively connected to the compiler. The compiler determines the predicted reliability of the vehicle component, determines the actual reliability of the vehicle component, divides the predicted reliability by the actual reliability to determine the predicted useful operating time Tx, and deducts the total operating time T from the predicted useful operating time Tx to determine the RUL. The system described herein may be utilized in conjunction with conventional trucks, hybrid vehicles, and electric vehicles, but is not limited thereto. The system described herein may also be used in conjunction with other electromechanical devices. BRIEF DESCRIPTION OF THE DRAWINGS
[0007] Figure 1 is a schematic diagram representing a system for predicting the RUL of a vehicle component as described herein.
[0008] Figure 2 is an annotated flow chart depicting the logic for outputting a RUL value for a particular vehicle component according to the systems and methods described herein.
[0009] Figure 3 is a chart depicting examples of different operating modes in a conventional truck, in a hybrid vehicle, and in an electric vehicle.
[0010] Figure 4 is a schematic diagram showing a stand-alone version of a prediction system for determining the RUL of a vehicle component.
[0011] Figure 5 is a schematic diagram showing an onboard version of a prediction system for determining the RUL of a vehicle component. DETAILED DESCRIPTION
[0012] The following disclosure relates to embodiments of systems and methods for determining the remaining useful life ("RUL") of vehicle components included in and / or on a vehicle. The systems and methods described herein can be used to determine the RUL of virtually any vehicle component in any type of vehicle (e.g., conventional vehicles, hybrid vehicles, electric vehicles).
[0013] For the purpose of clearly describing the components, features, and method steps discussed throughout this disclosure, some frequently used symbols and terms will now be defined. "T" used throughout this disclosure refers to the total time that a vehicle component is in operation. As used throughout this disclosure, T means the operating time from the moment a vehicle leaves an assembly line to the moment of a predicted estimate.
[0014] "A", "B", "C", "D", etc. may be used to represent a particular operating mode of a vehicle, whether (but not limited to) a conventional truck 300, a hybrid vehicle 301, or an electric vehicle 302. When the system of the present disclosure is implemented in a conventional truck, the operating mode may be selected from the group 303 consisting of start, idle, run, and stop.
[0015] In an embodiment, when the system of the present disclosure is implemented in a conventional truck at idle, "A", "B", "C", and "D" may be used to variously represent (304) that the vehicle is warming up, the vehicle is operating under normal conditions, the vehicle is performing stationary regenerative braking, or the vehicle is desorbing at increased engine speed and exhaust temperature.
[0016] In an embodiment, when the system of the present disclosure is implemented in a conventional truck that is in operation, "A", "B", and "C" may be used to variously indicate (305) that the vehicle is warming up, the vehicle is operating under normal conditions, or the vehicle is performing regenerative braking.
[0017] In an embodiment, a system according to the present disclosure may be implemented in a hybrid vehicle. In such an embodiment, "A", "B", and "C" may be used to variously indicate (306) that the vehicle is starting, the vehicle is idling, the vehicle is running, and the vehicle has stopped.
[0018] In an embodiment, when the system of the present disclosure is implemented in a running hybrid vehicle, operating modes "A", "B", "C", and "D" may be used to variously represent (307) whether the vehicle is operating solely using electric power, the vehicle is operating in an electric assist mode, the battery is charging, or the vehicle is performing regenerative braking.
[0019] In an embodiment, when the system of the present disclosure is implemented in an electric vehicle, operating modes "A", "B", "C", and "D" may be used to variously indicate (308) that the vehicle is starting, the vehicle is running, and the vehicle has stopped.
[0020] In an embodiment, when the system of the present disclosure is implemented in a running electric vehicle, "A", "B", etc. may be used to variously represent (309) different driving modes, such as but not limited to normal efficiency or high efficiency.
[0021] In an embodiment, when the system of the present disclosure is implemented in a running electric vehicle, "A", "B", "C", etc. may be used to represent (310) different braking modes, such as but not limited to creep, roll, or hold.
[0022] In an embodiment, when the system of the present disclosure is implemented in a running electric vehicle, "A" and "B" can be used to indicate whether the battery is being charged. According to such an embodiment, "A" can be used to indicate that the battery is being charged, and "B" can be used to indicate that the battery is not being charged.
[0023] In an embodiment, when the system of the present disclosure is implemented in a running electric vehicle, "A", "B", etc. may be used to variously indicate whether the vehicle is performing regenerative braking.
[0024] As used throughout this disclosure, the numbers "1" and "0" associated with a particular operating mode shall indicate whether, for a given operating mode (i.e., "A," "B," etc.), a particular vehicle component is affected; in other words, whether a particular vehicle component is operating in the operating mode.
[0025] As used throughout this disclosure, “T A ”, “T B ”, “T C ", etc. shall represent the total time that the vehicle has been operating in a particular operating mode (e.g., start mode, idle mode, etc.). As used throughout this disclosure, T A , T B , T C Etc. refers to the total time the vehicle has been operating in a particular operating mode, from the time the vehicle leaves the assembly line to the moment of the predicted estimate.
[0026] As used throughout this disclosure, "N" shall represent the total number of vehicles in operation as delivered from the dealer network.
[0027] As used throughout this disclosure, "M" shall represent the total number of vehicles in which a particular component has failed, as communicated from the dealer network.
[0028] As used throughout this disclosure, "P(Tx)" shall mean the predicted reliability of a particular automotive component at a predicted operating time (Tx).
[0029] As used throughout this disclosure, “M TH ” shall represent the threshold number of failures for a particular component.
[0030] As used throughout this disclosure, "RUL" refers to the remaining useful life of a particular automotive component.
[0031] The systems and methods described herein may be used to determine the RUL of vehicle components that are communicatively connected to an ECU. The systems and methods described herein may be used to determine the RUL of vehicle components that are not communicatively connected to an ECU. Components within the latter group may include, but are not limited to, wheel bearings, connecting rods in a vehicle suspension, drive shafts, and components of a powertrain (e.g., an engine, transmission, differential, and axles).
[0032] The systems and methods described herein may include a compiler 101 that may be communicatively connected to the ECU. In such embodiments, the ECU may transmit data to the compiler 101 in substantially real time regarding the amount of time the vehicle 100 has been in each operating mode. The compiler 101 may be programmed to determine, for each vehicle component 102, whether the component is operational when the vehicle 100 is in each operating mode.
[0033] In another embodiment, the systems and methods described herein may include a compiler 101 that receives actual data about the amount of time the vehicle component 102 has been in operation from sensors positioned in and / or on the vehicle component 102, and the actual data about the amount of time the vehicle component 102 has been in operation is compared with the predicted total useful life of the vehicle component 102 to determine the RUL.
[0034] The systems and methods described herein allow for the definition and prediction of RUL using statistical data from the dealer network 104 and Controller Area Network (CAN) messages regarding actual operating times transmitted by the CAN bus 103 to the compiler 101. The systems and methods for determining RUL as described herein do not require the use of on-board diagnostics (OBD).
[0035] The systems and methods described herein may utilize statistics provided by the dealer network 104, 400, 500 to determine the optimal vehicle component for a given vehicle. TH ) based on acceptable threshold limits for the number of failures. Based on those threshold limits, the systems and methods described herein can be used to determine the predicted reliability (ie, total useful life; P(Tx)) for a given vehicle component.
[0036] The systems and methods described herein can utilize information about the vehicle in various operating modes (T A , T B , T C etc.), and in particular, data 401, 501 of the actual operating time of vehicle components when determining the total actual operating time (T) of the vehicle components.
[0037] By comparing the total actual operating time (T) of a vehicle component to a predicted reliability based on statistical data provided by a dealer network, the systems and methods described herein may be used to determine the RUL 402, 502. Specifically, the RUL of a vehicle component may be determined by subtracting the total time (T) that the vehicle component has been in operation from the predicted useful life (Tx) of the component.
[0038] Embodiments of the systems and methods described herein may include a CAN bus 103. In embodiments, one or more sensors located in and / or on components 102 throughout the vehicle 100 may be communicatively connected via the CAN bus to the compiler 101. The CAN bus may facilitate the transmission of electronic messages (i.e., CAN messages) from the sensor(s) to the compiler 101.
[0039] An embodiment may include an external computerized device 104 that is communicatively connected to a compiler 101 located within a vehicle 100. In this embodiment, the external computerized device may be connected to a database that includes historical statistical data regarding vehicle component failures. Such data may include the number of vehicles in operation (N), the number of failures of a particular vehicle component (M), and the historical failure rate of a particular vehicle component, which data may be used as an acceptable number of failures (M). TH ) maximum or threshold limit.
[0040] Embodiments may utilize methods such as Figure 1 The RUL of a vehicle component may be estimated using a model such as the model depicted in . In an embodiment, the RUL may be determined by calculating the predicted reliability P(Tx) of the vehicle component (Calculation 6), taking the negative natural logarithm of P(Tx) (Calculation 7), dividing this value by the actual failure rate Λ of the component at the total operating time T (Calculation 8) to obtain the useful life of the component (Tx), and subtracting the total operating time T from Tx to obtain the RUL (Calculation 9).
[0041] The actual failure rate Λ of a component can be determined using the following model, which can be applied to each applicable operating mode 303, 304, 305, 306, 307, 308, 309, 310. A (or T B , T C The percentage of time that the vehicle is in a particular operating mode is calculated by dividing the total time in a particular operating mode A (B, C, etc.) by the total time T that the vehicle is in operation (Calculation 2). In certain operating modes, the vehicle component under consideration may not be operational, and therefore, the amount of time the vehicle is in this operating mode will not affect this calculation. Then, the percentage of time that the vehicle is in a particular operating mode is calculated by dividing T by the total time T that the vehicle is in operation (Calculation 2). A , T B , T C =A, B, C, and C are added together to determine the percentage of the total operating time T that the component worked. The resulting value can then be multiplied (Calculation 3) by the percentage of vehicles in which the component worked properly (i.e., NM / N; Calculation 1). Then, in Calculation 4, the negative natural logarithm of the product of Calculation 3 can be taken. The result of Calculation 4 can then be divided by the total time T (Calculation 5) to determine the actual failure rate Λ of the component at the total time T (Calculation 6).
[0042] In an embodiment, the compiler 101 can be programmed to determine the amount of time a particular component 102 has been in operation based on data from the ECU indicating the total time in each operating mode, and information (for each vehicle component) programmed into the compiler 101 regarding whether the component is operating in each operating mode.
[0043] In another embodiment, sensors located on or near components 102 may be utilized to collect data regarding the amount of time a particular component 102 has been in operation. These sensors may be communicatively connected to compiler 101.
[0044] In an embodiment, the number of vehicles in operation (N), the number of failures of a particular component (M), and an acceptable threshold number of failures (M) as determined based on historical statistics provided by the dealer network 104. TH ) data may be transmitted from the vehicle dealer network 104 to the compiler 101 .
[0045] In an embodiment, the compiler may include a computer program that can be installed to an ECU located within a vehicle. According to such an embodiment, the compiler 101 may be added to an existing ECU in a vehicle as a software update. In another embodiment, the compiler may be contained within a separate computerized device located within the vehicle.
[0046] Although described herein are systems and methods for determining the RUL of vehicle components, the systems and methods can be readily used to determine the RUL of any number of other machines and equipment. The systems and methods described herein can be used to determine the RUL of aircraft components and locomotive components, as well as the RUL of components of electric fans, washers and dryers, and other electromechanical equipment. Example 1
[0047] The following is an illustrative example of how the systems or methods described herein may be applied in a conventional truck to determine the RUL of a wheel bearing.
[0048] For the purposes of this example, the total operating time of the vehicle will be 15,000 hours; that is, T = 15,000 hours. There are 5,000 trucks in operation (N = 5,000). From the dealer network, we know that the predicted number of trucks that will have a failed part is 10 (M TH =10). The component has actually failed 6 times (M=6).
[0049] The truck is in start-up mode for 750 hours (T A ), idling time up to 3,000 hours (T B ), running for 5,250 hours (T C ) and stopped for 6,000 hours (T D ).
[0050] refer to Figure 2, about calculation 1: (NM) / M; 5,000-6 / 5,000=4,994 / 5,000=0.9988.
[0051] About calculation 2: T A / T=750 / 15,000=0.05 T B / T=3,000 / 15,000=0.2 T C / T=5,250 / 15,000=0.35 T D / T=6,000 / 15,000=0.4
[0052] About Calculation 3(T D Work not involving wheel bearings): Calculate 1×(T A +T B +T C +0) 0.9988×(0.05+0.2+0.35) 0.9988×0.6=0.59928
[0053] About calculation 4: -ln[P(T)] -ln[0.59928]=0.00120072
[0054] About calculation 5: -ln[P(T)] / T=0.00120072 / 15,000=0.000000080048
[0055] Regarding calculation 6: (NM TH ) / N=(5,000-10) / 5,000=4,990 / 5,000=0.998
[0056] About calculation 7: -ln[P(Tx)] -ln[0.998]=0.00200200
[0057] About calculation 8: Result of calculation 7 / result of calculation 5 = 0.00200200 / 8.0048×10 -8 =25,009.994
[0058] About calculation 9: T x–T=25,009.994–15,000=10,009.994
[0059] Thus, the vehicle component has approximately 10,000 hours of service life remaining. Example 2
[0060] The following is an illustrative example of how the systems or methods described herein may be applied in an electric vehicle to determine the RUL of a battery.
[0061] For the purposes of this example, the total operating time of the vehicles will be 4,000 hours; that is, T = 4,000 hours. There are 7,000 vehicles in operation (N = 7,000). From the dealer network, we know that the predicted number of vehicles that will have a failed component is 15 (M TH = 15). There are 10 instances (M = 10) where the component has actually failed.
[0062] The vehicle is in start-up mode for 700 hours (T A ), running for 1,800 hours (T B ) and stopped for 1,500 hours (T C ).
[0063] refer to Figure 2 , about calculation 1: (NM) / M; 7,000-10 / 7,000=4,994 / 5,000=0.9986.
[0064] About calculation 2: T A / T=700 / 4,000=0.175 T B / T=1,800 / 4,000=0.45 T C / T=1,500 / 4,000=0.375
[0065] About calculation 3: Calculate 1×(T A +T B +T C +0) 0.9986×(0.175+0.45+0.375) 0.9986×1=0.9986
[0066] About calculation 4: -ln[P(T)] -ln[0.9986]=0.0014
[0067] About calculation 5: -ln[P(T)] / T=0.0014 / 4,000=3.5×10 -7
[0068] Regarding calculation 6: (NM TH ) / N=(7,000-15) / 7,000=6,985 / 7,000=0.9979
[0069] About calculation 7: -ln[P(Tx)] -ln[0.9979]=0.00210220809
[0070] About calculation 8: Result of calculation 7 / result of calculation 5 = .00210220809 / 3.5 x 10 -7 =6006.31
[0071] About calculation 9: T x –T=6,006.31–4,000=2,006.31
[0072] Thus, the vehicle component has approximately 2,006 hours of useful life remaining.
Claims
1. A system for determining a remaining useful life RUL of a vehicle component included in and / or on a vehicle, comprising: Compiler; as well as a dealer network communicatively connected to the compiler; Wherein the compiler determines a predicted reliability of the vehicle component, determines an actual reliability of the vehicle component, divides the predicted reliability by the actual reliability to determine a predicted useful operating time Tx, and subtracts a total operating time T from the predicted useful operating time Tx to determine the RUL.
2. The system of claim 1, further comprising one or more sensors positioned in and / or on the vehicle component, wherein: The one or more sensors are communicatively coupled to the compiler.
3. The system of claim 2, wherein: The one or more sensors are communicatively coupled to the compiler via a controller area network.
4. The system of claim 1, wherein: The compiler comprises a computer program installable to an electronic control unit located within the vehicle.
5. The system of claim 1, wherein: The compiler is contained within a stand-alone computerized device.
6. The system of claim 5, wherein: The compiler is located within the vehicle.
7. The system of claim 1, wherein: The vehicle is a conventional truck.
8. The system of claim 1, wherein: The vehicle is a hybrid vehicle.
9. The system of claim 1, wherein: The vehicle is an electric vehicle.
10. The system of claim 7, wherein: The operating modes include start, idle, run and stop.
11. The system of claim 8, wherein the operating modes include start, idle, run, and stop.
12. The system of claim 9, wherein: The operation modes include start, run and stop.
13. A system for determining a remaining useful life (RUL) of a component of an electromechanical device, comprising: Compiler; as well as an external network, the external network being communicatively connected to the compiler; Wherein, the compiler determines a predicted reliability of the component, determines an actual reliability of the component, divides the predicted reliability by the actual reliability to determine a predicted useful operating time Tx, and subtracts a total operating time T from the predicted useful operating time Tx to determine the RUL.
14. The system of claim 13, further comprising one or more sensors positioned in and / or on the component, wherein: The one or more sensors are communicatively coupled to the compiler.
15. The system of claim 14, wherein: The compiler determines the reliability of the prediction of the component by: obtaining data (N) identifying a number of electromechanical devices in operation from the external network; Obtain the acceptable maximum number (M) of failures of the component identified from the external network. TH ) data; Subtract M from N TH , and then dividing the value by N to provide a P(Tx) value; Calculating the negative natural logarithm of P(Tx) to determine the reliability of the forecast; And wherein, the compiler determines the actual reliability of the component by: obtaining data from the one or more sensors indicating a total time that the component of the electromechanical device has been in one or more operating modes in each operating mode of operation; dividing the total time that the electromechanical device has been in the operating mode in which the component is operating by the total time T that the electromechanical device has been in operation to obtain a percentage of the total time T that the component is operating; subtracting the number of electromechanical devices (M) in which the component has actually failed from the total number of electromechanical devices (N), and then dividing the resulting value by the total number of electromechanical devices (N); multiplying the percentage of time that the electromechanical device is in the operating mode in which the component is on by the quotient of (NM) / N to determine P(T); Calculate the negative natural logarithm of P(T) and divide the value by the total time T to obtain the actual reliability Λ.