Vehicle fault diagnosis and prediction using automatic data segmentation and trend analysis

Abstract

A controller processes data from one or more sensors of a vehicle subsystem. The processing includes smoothing the data and calculating an average of the data. The controller identifies a transition point in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating a trend. The controller selects a segment of the processed data after the transition point, detects a trend in the segment using regression, and extrapolates the detected trend to reach a predetermined fault threshold. The controller predicts failure of the subsystem based on a slope of the extrapolated trend and provides an indication of the prediction based on the slope to schedule service to the subsystem.

Description

[0001] introduction

[0002] The information provided in this section is intended to generally introduce the background of the present disclosure. To the extent described in this section, the work of the presently named inventors, and aspects of the description that may not qualify as prior art at the time of filing, are neither explicitly nor implicitly admitted to be prior art against the present disclosure. Technical Field

[0003] The present disclosure relates generally to vehicle fault diagnosis and prediction systems, and more particularly, to vehicle fault diagnosis and prediction using automatic data segmentation and trend analysis. Background Art

[0004] The vehicle health management system includes a diagnostic system, a prognostic system, and / or a fault mitigation system. The diagnostic system typically includes an on-board diagnostic module that indicates system-level faults to the vehicle owner using an indicator on the vehicle dashboard. The diagnostic system also includes advanced diagnostics, which service personnel use to perform detailed fault analysis to find the root cause of the problem, down to the component level. The on-board diagnostic module typically compares the signal level of a signal from a vehicle subsystem to a predetermined threshold and determines whether the subsystem is faulty based on the comparison result. Service personnel typically use advanced diagnostics, which can analyze signals from multiple components of a subsystem and other related subsystems, and can determine the root cause of the problem, down to the component level.

[0005] Predictive systems can predict which component in a vehicle is likely to fail in the near future. Predictive systems predict failures before they occur. Predictive systems can help vehicle owners schedule repairs before a component fails. That way, when a component fails, the owner will not be left helpless. However, some failures occur suddenly and cannot be predicted. Fault mitigation systems determine vehicle operations to mitigate the effects of the fault. For example, some faults are minor and can be mitigated to allow the vehicle to be driven for a period of time until the fault is corrected by a service vehicle. Summary of the invention

[0006] A system includes a plurality of sensors associated with a plurality of subsystems of a vehicle and a controller configured to communicate with the plurality of subsystems of the vehicle. The controller is configured to process data received from one or more sensors of one of the vehicle subsystems. The processing includes smoothing the data and calculating an average of the data. The controller is configured to identify a transition point in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend, or at which the moving average is greater than the average by a predetermined amount indicating a downward trend. The controller is configured to select a segment of the processed data after the transition point; detect a trend in the segment of the processed data after the transition point using regression, wherein the trend includes an upward trend or a downward trend; and extrapolate the detected trend to reach a predetermined fault threshold. The controller is configured to predict a failure of one of the subsystems based on a slope of the extrapolated trend, and provide an indication of the prediction based on the slope of the extrapolated trend to schedule service of one of the subsystems.

[0007] In other features, the controller is further configured to use the detected trends to accurately diagnose a fault in one of the subsystems, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of a component in one of the subsystems before the component in one of the subsystems fails.

[0008] In other features, the controller is also configured to detect a second trend in second data collected from one or more sensors of one of the subsystems after service; and evaluate the service based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

[0009] In other features, the received data includes first and second data for first and second parameters, respectively, of one of the subsystems. The controller is further configured to determine whether to generate an alarm regarding a condition of the one of the subsystems based on whether the first data for the first parameter has crossed a first threshold; and to detect a trend using the second data for the second parameter. The second parameter is different from the first parameter.

[0010] In another feature, the controller is configured to provide an indication of the prediction in response to a slope of the extrapolated trend being greater than a first predetermined threshold.

[0011] In other features, the controller is configured to estimate an operational life of one of the subsystems based on a slope of the extrapolated trend; and provide the predicted indication based on the estimate.

[0012] In another feature, the controller is configured to select a type of regression depending on a type of parameter of one of the subsystems for which data is received.

[0013] In another feature, the controller is configured to detect trends by excluding data prior to a transition point.

[0014] In other features, the controller is located in a computing device remote from the vehicle, and the computing device includes a mobile device, a service tool, or a server in the cloud.

[0015] In other features, a system includes a processor and a memory storing instructions that, when executed by the processor, configure the processor to process data received from a sensor of a vehicle subsystem, wherein the processing includes smoothing the data and calculating an average of the data. The instructions configure the processor to identify a transition point in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend, or at which the moving average is greater than the average by a predetermined amount indicating a downward trend. The instructions configure the processor to select a segment of the processed data after the transition point; detect a trend in the segment using regression, wherein the trend includes an upward trend or a downward trend; and extrapolate the detected trend to reach a predetermined fault threshold. The instructions configure the processor to predict a failure of the subsystem based on a slope of the extrapolated trend; and provide an indication of the prediction based on the slope of the extrapolated trend to schedule service to the subsystem.

[0016] In other features, the instructions further configure the processor to accurately diagnose faults in the subsystem, modify control parameters of the vehicle to improve vehicle safety, and / or use detected trends to extend the life of subsystem components before the components fail.

[0017] In other features, the instructions further configure the processor to detect a second trend in second data collected from one or more sensors of the subsystem after the service; and evaluate the service based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

[0018] In other features, the received data includes first and second data for first and second parameters, respectively, of the subsystem. The instructions further configure the processor to determine whether to generate an alert regarding a condition of the subsystem based on whether the first data for the first parameter has exceeded a first threshold; and to detect a trend using the second data for the second parameter. The second parameter is different from the first parameter.

[0019] In another feature, the instructions further configure the processor to provide an indication of a prediction in response to a slope of the extrapolated trend being greater than a first predetermined threshold.

[0020] In other features, the instructions further configure the processor to estimate an operational life of the subsystem based on a slope of the extrapolated trend; and provide an indication of a prognosis based on the estimate.

[0021] In another feature, the instructions further configure the processor to select the regression type depending on a parameter type of the subsystem for which the data is received.

[0022] In another feature, the instructions further configure the processor to detect the trend by excluding data prior to a transition point.

[0023] In another feature, a computing device includes the system of claim 10. The computing device is remote from the vehicle and includes a mobile device, a service tool, or a server in the cloud.

[0024] In other features, a method includes processing data received from a sensor of a vehicle subsystem, wherein the processing includes smoothing the data and calculating an average of the data. The method includes identifying a transition point in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend, or at which the moving average is greater than the average by a predetermined amount indicating a downward trend. The method includes selecting a segment of the processed data after the transition point; detecting a trend in the segment using regression, wherein the trend includes an upward trend or a downward trend; and extrapolating the detected trend to reach a predetermined fault threshold. The method includes predicting a failure of the subsystem based on a slope of the extrapolated trend; and providing an indication of the prediction based on the slope of the extrapolated trend to schedule service to the subsystem. The method includes using the detected trend to accurately diagnose a fault in the subsystem, modify a control parameter of the vehicle to improve vehicle safety, and / or extend the life of a component of the subsystem before the component fails.

[0025] In other features, the method also includes detecting a second trend in second data collected from one or more sensors of the subsystem after the service; and evaluating the service based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

[0026] The present invention provides the following technical solutions:

[0027] 1. A system comprising:

[0028] a plurality of sensors associated with a plurality of subsystems of the vehicle; and

[0029] a controller configured to communicate with the plurality of subsystems of the vehicle and further configured to:

[0030] processing data received from one or more sensors of one of the subsystems of the vehicle, wherein the processing includes smoothing the data and calculating an average of the data;

[0031] identifying transition points in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend or the moving average is greater than the average by a predetermined amount indicating a downward trend;

[0032] selecting a segment of the processed data after the transition point;

[0033] detecting a trend of the processed data in a segment after the transition point using regression, wherein the trend comprises an upward trend or a downward trend;

[0034] Extrapolating detected trends to reach a predetermined failure threshold;

[0035] predicting a failure of said one of said subsystems based on a slope of the extrapolated trend; and

[0036] An indication of a prediction is provided based on the slope of the extrapolated trend to serve the one of the subsystems in scheduling.

[0037] A system according to technical solution 1, wherein the controller is also configured to use the detected trends to accurately diagnose a fault in one of the subsystems, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of the component before the component of one of the subsystems fails.

[0038] According to the system of technical solution 1, the controller is further configured to:

[0039] detecting a second trend in second data collected from one or more sensors of one of the subsystems after the servicing; and

[0040] The service is evaluated based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

[0041] The system according to technical solution 1, wherein the received data includes first and second data for first and second parameters of the one of the subsystems, respectively, and wherein the controller is further configured to:

[0042] determining whether to generate an alert regarding a condition of said one of said subsystems based on whether first data for said first parameter has crossed a first threshold; and

[0043] detecting a trend using second data for the second parameter,

[0044] The second parameter is different from the first parameter.

[0045] A system according to technical solution 1, wherein the controller is configured to provide an indication of the prediction in response to a slope of the extrapolated trend being greater than a first predetermined threshold.

[0046] According to the system of technical solution 1, the controller is configured to:

[0047] estimating an operational life of one of the subsystems based on a slope of the extrapolated trend; and

[0048] An indication of the prediction is provided based on the estimate.

[0049] A system according to technical solution 1, wherein the controller is configured to select a type of regression depending on a parameter type of one of the subsystems for which data is received.

[0050] A system according to technical solution 1, wherein the controller is configured to detect the trend by excluding data before the transition point.

[0051] A system according to technical solution 1, wherein the controller is located in a computing device remote from the vehicle, and wherein the computing device includes a mobile device, a service tool, or a server in the cloud.

[0052] A system comprising:

[0053] Processor; and

[0054] A memory storing instructions that, when executed by a processor, configure the processor to:

[0055] processing data received from sensors of vehicle subsystems, wherein the processing includes smoothing the data and calculating an average of the data;

[0056] identifying transition points in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend or a moving average is greater than the average by a predetermined amount indicating a downward trend;

[0057] Selecting a segment of the processed data after the transition point;

[0058] detecting a trend in the segment using regression, wherein the trend comprises an upward trend or a downward trend;

[0059] Extrapolating detected trends to reach a predetermined failure threshold;

[0060] predicting failure of the subsystem based on the slope of the extrapolated trend; and

[0061] An indication of the prediction is provided based on the extrapolated trend slope to schedule service for the subsystem.

[0062] A system according to technical solution 10, wherein the instructions further configure the processor to use the detected trends to accurately diagnose faults in the subsystem, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of components of the subsystem before they fail.

[0063] According to the system of technical solution 10, the instruction further causes the processor to:

[0064] detecting a second trend in second data collected from one or more sensors of the subsystem after the servicing; and

[0065] The service is evaluated based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

[0066] A system according to technical solution 10, wherein the received data includes first and second data for first and second parameters of the subsystem, respectively, and wherein the instructions further configure the processor to:

[0067] determining whether to generate an alert regarding a condition of the subsystem based on whether first data for the first parameter has crossed a first threshold; and

[0068] detecting a trend using second data for the second parameter,

[0069] The second parameter is different from the first parameter.

[0070] A system according to technical solution 10, wherein the instructions further configure the processor to provide an indication of the prediction in response to a slope of the extrapolated trend being greater than a first predetermined threshold.

[0071] According to the system of technical solution 10, the instruction further configures the processor to:

[0072] estimating an operational life of the subsystem based on a slope of the extrapolated trend; and

[0073] An indication of the prediction is provided based on the estimate.

[0074] A system according to technical solution 10, wherein the instructions further configure the processor to select the type of regression depending on the type of parameters of the subsystem for which data is received.

[0075] A system according to technical solution 10, wherein the instructions further configure the processor to detect the trend by excluding data before the transition point.

[0076] A computing device comprising the system according to Technical Solution 10, wherein the computing device is remote from the vehicle and comprises a mobile device, a service tool, or a server in the cloud.

[0077] A method comprising:

[0078] processing data received from sensors of vehicle subsystems, wherein the processing includes smoothing the data and calculating an average of the data;

[0079] identifying transition points in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend or greater than the average by a predetermined amount indicating a downward trend;

[0080] selecting a segment of the processed data after a transition point;

[0081] detecting a trend in the segment using regression, wherein the trend comprises an upward trend or a downward trend;

[0082] Extrapolating detected trends to reach a predetermined failure threshold;

[0083] Predict subsystem failure based on the slope of the extrapolated trend;

[0084] providing an indication of the forecast based on a slope of the extrapolated trend to schedule service to the subsystem; and

[0085] The detected trends are used to accurately diagnose faults in the subsystem, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of the components of the subsystem before the components fail.

[0086] The method according to technical solution 19 further includes:

[0087] detecting a second trend in second data collected from one or more sensors of the subsystem after servicing; and

[0088] The service is evaluated based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

[0089] Further areas of applicability of the present disclosure will become apparent from the detailed description, claims and drawings.The detailed description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] The present disclosure will be more fully understood from the detailed description and accompanying drawings, in which:

[0091] Figures 1A-1C An example of a vehicle fault diagnosis and prediction system using automatic data segmentation and trend analysis according to the present disclosure is shown;

[0092] Figure 2A and 2B shows normalized data from vehicle subsystems plotted with respect to time to illustrate fault diagnosis and prediction performed using automatic data segmentation and trend analysis in accordance with the present disclosure;

[0093] Figure 2C An example of using normalized data from a subsystem plotted with respect to time to verify a repair performed on a vehicle subsystem in accordance with the present disclosure is shown;

[0094] Figure 3A and 3B A method of fault diagnosis and prediction using automatic data segmentation and trend analysis according to the present disclosure is shown; and

[0095] Figure 3C A method for verifying a repair performed on a vehicle subsystem according to the present disclosure is shown.

[0096] In the drawings, reference numerals may be repeated to identify similar and / or identical elements. DETAILED DESCRIPTION

[0097] Diagnostic and prognostic systems typically generate an alert if the fault signature exceeds a predefined threshold. These systems will fail to generate an alert if the fault signature does not exceed the predefined threshold. Often, the fault signature may not exceed the predefined threshold when the monitored subsystem degrades rapidly or when data is not collected from the subsystem prior to the imminent failure / repair. For example, if the processing is performed on a server in the cloud rather than on the vehicle, the most recent data may not be available for analysis due to communication failures. Using historical data for fault diagnosis also presents other challenges. For example, historical data cannot be used to accurately assess and verify repairs, which can be problematic when the repair involves an OEM part with a warranty claim.

[0098] To address the above problems, the present disclosure provides an improved fault diagnosis and prediction system that uses automatic data segmentation and trend analysis methods for situations including rapid subsystem degradation or lack of data. The system automatically segments the data and determines the point at which the data changes from normal to abnormal (i.e., indicating a problem). The system uses the data after the change point to determine the trend. The system extrapolates the trend to predict failures and other fault characteristics.

[0099] Specifically, the system of the present disclosure uses a moving average to smooth the collected data before performing trend analysis. The system uses a data segmentation method to determine change points. The system uses regression to detect trends. The system uses extrapolation to confirm the severity of the trend. The system uses the detected trends and other fault characteristics to perform fault isolation. The system can also verify repairs. Therefore, the system of the present disclosure is more robust than existing fault diagnosis and prediction systems for vehicles, and significantly improves existing fault diagnosis and prediction systems for vehicles. These and other features of the present disclosure are described in detail below.

[0100] Figures 1A-1C An example of a system 100 for vehicle fault diagnosis and prediction using automatic data segmentation and trending according to the present disclosure is shown. Figure 1A , system 100 includes a controller 102 that communicates with a plurality of subsystems 104-1, 104-2, ..., and 104-N (collectively referred to as subsystems 104) of a vehicle. For example, subsystems 104 may include an engine subsystem, a transmission subsystem, an exhaust subsystem, a brake subsystem, a suspension subsystem, a battery subsystem, an HVAC subsystem, a navigation subsystem, an autonomous subsystem, and the like.

[0101] Figure 1B As shown, in general, each subsystem 104 can broadly include one or more sensors 120, one or more actuators 122, and a processor 124. The processor 124 receives data from the one or more sensors 120 and controls the one or more actuators 122. The processor 124 can also receive data from one or more of the other subsystems 104 and can control at least one of the sensor 120 and the actuator 124 based on the data.

[0102] exist Figure 1A In the embodiment of the present invention, the controller 102 also communicates with the vehicle's infotainment subsystem 106 and the communication subsystem 108. For example, the infotainment subsystem 106 can be used to provide audio, visual and / or tactile alerts to one or more occupants of the vehicle. For example, the communication subsystem 108 includes one or more transceivers that can communicate with the vehicle's Figure 1CThe distributed communication system 110 shown communicates with the vehicle. For example, the distributed communication system 110 may include a cellular network, a WiFi network, a satellite network, and / or the Internet. Therefore, the controller 102 can communicate with a server 112 in the cloud via the vehicle's communication subsystem 108 and via the distributed communication system 110. Figure 1C shown) communication.

[0103] Figure 1C The communication subsystem 108 is shown to also communicate with a service tool 114 used by a service technician to test and troubleshoot the subsystem 104. The service tool 114 can access the vehicle's subsystem 104 through the communication subsystem 108. In some examples, the service tool 114 can also be directly attached to the vehicle's CAN bus (described below) and obtain data, such as diagnostic test codes and other test results stored in the controller 102. The communication subsystem 108 can also communicate with a mobile device 116, such as a cellular phone. For example, the mobile device 116 can typically only access the vehicle's infotainment subsystem 106 via a Bluetooth interface. The mobile device 116 can also access other safety subsystems and on-board diagnostics of the vehicle via a dongle (not shown). The service tool 114 and the mobile device 116 can also communicate with the server 112 via the distributed communication system 110. Therefore, the fault diagnosis and prediction system of the present disclosure can also be implemented at least in part in the server 112, the service tool 114, and / or the mobile device 116.

[0104] The controller 102, the subsystem 104, the infotainment subsystem 106, and the communication subsystem 108 are interconnected through a control area network (CAN bus) in the vehicle and communicate with each other via the CAN bus. The controller 102 is configured to execute Figures 3A-3C The method shown. Figures 3A-3C The method shown may also be performed by the server 112, the service tool 114, and / or the mobile device 116 after the required data is transmitted thereto. Figures 2A-3C The operation of the controller 102 is described in detail. Throughout this disclosure, the battery subsystem including the battery and the starter is used only as an illustrative example to describe the various operations of the fault diagnosis and prediction system of the present disclosure. The teachings of the present disclosure can be applied to any subsystem of a vehicle.

[0105] Figure 2A and 2B An example of fault diagnosis and prognosis of a battery subsystem (eg, one of the subsystems 104 ) using automated data segmentation and trend analysis (eg, by the controller 102 ) according to the present disclosure is shown. Figure 2C An example of a verification repair according to the present disclosure is shown. As an example only, Figures 2A-2CA graph of normalized data collected from one or more sensors of a battery subsystem (eg, sensor 120 ) is shown plotted against time on the X-axis.

[0106] exist Figure 2A In the present invention, typically, the entire data set collected over a relatively long period of time (e.g., many days) is used for curve fitting, which is used to detect faults. Fitted curve 200 is usually obtained using the entire data set collected over a relatively long period of time. However, using the entire data set for curve fitting cannot accurately predict faults. When fitted curve 200 is extrapolated, extrapolated curve 202 cannot reach fault threshold 204, and therefore cannot successfully detect faults.

[0107] On the contrary, Figure 2B In the example, a segment 205 of a data set selected according to the present disclosure (hereinafter referred to as Figure 3A and 3B Detailed illustration and explanation) can more accurately indicate the fault trend. Figure 2A , the fitting curve 206 is obtained by curve fitting the data from the selected segment 205 of the data set. When the fitting curve 206 is extrapolated, the extrapolated curve 208 can reach the failure threshold 204, and thus the failure can be successfully predicted. In addition, using the extrapolated curve 208, the remaining life L of the failed component (i.e., the duration between points 210 and 212) can also be predicted, as explained in detail below.

[0108] Additionally, after a repair is performed at 212, a sudden reversal in the trend as seen at 214, followed by a data value below the baseline 216, can verify that the repair was successful and necessary. In contrast, a slow reversal in the trend would indicate that the repair was unsuccessful and / or unnecessary (e.g., a different component needs to be repaired / replaced instead). Figure 2C As shown, if the data collected after a repair is within the empirically determined upper and lower fault thresholds 204, 203 (ie, within a normal range), the data may indicate that the repair was successful and necessary. The method by which the controller 102 performs these operations is described in detail below.

[0109] Figure 3A and 3B A method 300 of vehicle fault diagnosis and prediction using automatic data segmentation and trending according to the present disclosure is shown. Figure 3C A method 370 for verifying a repair according to the present disclosure is shown. Likewise, in the following description, the battery subsystem is used for example only; and the following teachings may be applied to any subsystem 104. Additionally, the term control in the following description refers to the controller 102.

[0110] exist Figure 3AIn 302, when the vehicle is started, control collects current start data from sensors associated with the battery subsystem. For example, the start data may include battery resistance, starter resistance, start time, battery open circuit voltage, and battery charge resistance. In general, control collects current values ​​of one or more parameters of a subsystem (e.g., one of the subsystems 104) of the vehicle using one or more sensors of the subsystem (e.g., sensor 120).

[0111] At 304 , control retrieves historical startup data (typically, historical data of parameters) from memory and aggregates all data. For example, the memory may be located in the subsystem, in another subsystem of the vehicle, in the controller 102 , or in a server 112 in the cloud.

[0112] At 306, control determines whether the start time or charging resistance is greater than a predetermined threshold based on the current start data (typically, the current value of one of the parameters). Alternatively, depending on the type of parameter, control may instead determine whether the current value of the parameter is less than a predetermined threshold. Essentially, control determines whether the current value of the parameter crosses an upper limit or a lower limit.

[0113] If the current start time or charging resistance is not greater than a predetermined threshold (typically, if the current value of the parameter has not yet crossed an upper or lower limit), then at 322, control determines whether the subsystem is operating normally, and control does not generate an alarm. Since starting is not an ongoing operation (i.e., starting is not repeatedly performed during normal operation of the vehicle), control ends. In the case of another subsystem, if control can continue to monitor the operation of the subsystem, control can return to 302 and continue to collect parameter data for the subsystem instead of ending.

[0114] At 307 , control determines whether the cranking ratio is greater than or less than a threshold. If the cranking ratio is greater than or less than the threshold, control generates a battery / starter alarm at 308 . If the cranking ratio is not greater than or less than the threshold, control continues at 308 to use a trend analysis method.

[0115] If the current start time or charging resistance is greater than a predetermined threshold (typically, if the current value of the parameter has crossed an upper or lower limit), then at 309, control is performed as described below with reference to Figure 3B The control detects the change point of the battery resistance and the starter resistance (or the starting ratio, which is the ratio of the battery resistance to the starter resistance), as shown in the following reference Figure 3B Note that at 306 , control may use one set of parameters for the subsystem (eg, start time and charging resistance) and may use another (ie, different) set of parameters (eg, start ratio) to perform trend analysis as described below.

[0116] At 310, control uses curve fitting and regression to determine trends in a selected segment of the data for the data from the change point to the current point (i.e., the time point when the current data was collected at 302). For example, linear or any other type of regression (e.g., polynomial or exponential regression, or machine learning based regression, such as Gaussian regression) may be selected depending on the parameter being observed.

[0117] At 312, control extrapolates the trend until the trend reaches a predetermined fault threshold (eg, fault threshold 204). Control also estimates the remaining life L of components of the subsystem (eg, the battery and starter in the case of a battery subsystem) (described above with reference to Figure 2A Description), after which components of the subsystem will fail.

[0118] At 314, control determines whether the estimated life of the battery (estimated based on the battery resistance) is less than a threshold (e.g., 3 days) and whether the start ratio is trending upward (i.e., the slope of the general trend). If the estimated life of the battery is less than the threshold and if the start ratio is trending upward, then at 316, control generates an alert for the battery. For example, control notifies the occupant via the infotainment subsystem 106 that the battery will fail within the estimated life and that service for the battery should be scheduled. Again, since starting is not an ongoing operation, control ends. In the case of another subsystem, if control can continue to monitor the operation of the subsystem, control can return to 302 and continue to collect parameter data for the subsystem instead of ending.

[0119] If the estimated life of the battery is not less than a threshold, and if the start ratio is not trending upward, then at 318, control determines whether the estimated life of the starter (estimated based on the starter resistance) is less than a threshold (e.g., 3 days), and the start ratio is trending downward (i.e., the slope of the general trend), and the start time is greater than a threshold.

[0120] If the estimated life of the starter is not less than the threshold, and if the start ratio is not trending downward, and if the start time is not greater than the threshold, control does not generate an alarm for the starter at 322. Again, since starting is not an ongoing operation, control ends. In the case of another subsystem, if control can continue to monitor the operation of the subsystem, control can return to 302 and continue to collect parameter data for the subsystem instead of ending.

[0121] If the estimated life of the starter is less than the threshold, and if the start ratio is trending downward, and if the start time is greater than the threshold, control generates an alert for the starter at 320. For example, control notifies the occupant via the infotainment subsystem 106 that the starter will fail within the estimated life and that maintenance of the starter should be scheduled. Again, since starting is not an ongoing operation, control ends. In the case of another subsystem, if control can continue to monitor the operation of the subsystem, control can return to 302 and continue to collect parameter data for the subsystem instead of ending.

[0122] Figure 3B The data segmentation step 309 of method 300 is shown in more detail. At 350, control smoothes the historical data using a moving average or other smoothing algorithm. For example, Figure 2B , a moving average curve is shown at 360. At 352, control calculates the average of the smoothed (ie, averaged) historical data. For example, Figure 2B , the average is shown at 362.

[0123] At 354, control identifies a change point (or transition point) 364 in the data at which the moving average is less than the average by a predetermined amount. Subsequent data that is later in time than the change point 364 represents an upward trend in the data set. Alternatively, in another example, depending on the subsystem and the parameters of the subsystem being observed, the change point 364 may be where the moving average is greater than the average by a predetermined amount, and subsequent data that is later in time than the change point 364 may represent a downward trend in the data set. After 354, control returns to Figure 3A Step 310 of method 300 is shown.

[0124] Therefore, the method 300 detects trends based on the failure data after the change point 364 and does not use the healthy history data before the change point 364. Therefore, unlike trends determined based on the entire data set (i.e., including healthy and failure data), trends determined based only on the failure data (i.e., excluding healthy data) may correctly predict failures when extrapolated.

[0125] Note that the trend information can be used for many other purposes. For example, the controller 102 can use the detected trends to accurately diagnose faults in the subsystem 104. The controller 102 can modify the control parameters of the vehicle (e.g., parameters of the autonomous subsystems) to improve vehicle safety. Using the detected trends, the life of the components of the subsystem 104 can also be extended before the components fail (e.g., by limiting the use of the components, switching to spares if available, etc.).

[0126] Figure 3CA method 370 for verifying a repair in accordance with the present disclosure is shown. The method 370 may be performed after a repair recommended by the method 300 (e.g., at 316 or 320) is performed on the subsystem. At 372, control collects data from one or more sensors associated with the subsystem. For example, control collects startup data from sensors associated with the battery subsystem. Generally, control collects one or more parameters of a subsystem (e.g., one of the subsystems 104) of the vehicle using one or more sensors of the subsystem (e.g., sensor 120). Control compares the data collected after the repair to upper and lower fault thresholds (e.g., Figure 2C The threshold values ​​204, 203 are compared.

[0127] At 374 , control determines whether the data is within upper and lower fault thresholds (ie, within a normal range). In some examples, control may use the same thresholds used to determine fault data (eg, Figure 2C The threshold values ​​204, 203 shown in FIG. 204 and 203 are different threshold values ​​to determine health data (e.g., Figure 2C If the data is within the upper and lower fault thresholds, control determines the repair is successful and necessary at 376. If the data is not within the upper and lower fault thresholds, control determines the repair is unsuccessful at 378 (i.e., the wrong part was replaced and the faulty part is still to be replaced, or the replaced part is defective or has failed).

[0128] Other methods may be used to assess or verify repairs. For example, Figure 2C As shown, after a repair is performed at 212, a sudden reversal of the trend (i.e., the slope of the trend is greater than a threshold), as seen at 214, followed by a data value below the baseline 216, may verify that the repair was successful and necessary. In contrast, a slow or gradual reversal of the trend (i.e., the slope of the trend is less than a threshold) would indicate that the repair was unsuccessful and / or unnecessary (e.g., a different component needs to be repaired / replaced).

[0129] The foregoing description is merely illustrative in nature and is not intended to limit the present disclosure, its application or use. The broad teachings of the present disclosure can be implemented in many forms. Therefore, although the present disclosure includes specific examples, the true scope of the present disclosure should not be so limited, because other modifications will become apparent after studying the drawings, the specification and the appended claims. It should be understood that one or more steps in the method can be performed in a different order (or simultaneously) without changing the principles of the present disclosure. In addition, although each embodiment is described above as having certain features, any one or more of those features described with respect to any embodiment of the present disclosure can be implemented in any other embodiment and / or combined with the features of any other embodiment, even if the combination is not explicitly described. In other words, the described embodiments are not mutually exclusive, and the replacement of one or more embodiments with each other is still within the scope of the present disclosure.

[0130] Various terms are used to describe the spatial and functional relationships between elements (e.g., between modules, circuit elements, semiconductor layers, etc.), including "connected," "engaged," "coupled," "adjacent," "immediately adjacent," "on," "above," "above," "below," and "disposed." Unless explicitly described as "direct," when describing the relationship between a first and a second element in the above disclosure, the relationship may be a direct relationship with no other intervening elements between the first and second elements, but may also be an indirect relationship with one or more intervening elements (spatially or functionally) between the first and second elements. As used herein, the phrase "at least one of A, B, and C" should be interpreted as using a non-exclusive logical "or" to represent a logical "or," and should not be interpreted as "at least one of A, at least one of B, and at least one of C."

[0131] In a diagram, the direction of the arrow generally indicates the flow of information (such as data or instructions) that the diagram is concerned with. For example, when element A and element B exchange various information, but the information transmitted from element A to element B is relevant to the diagram, the arrow may point from element A to element B. This one-way arrow does not mean that no other information is transmitted from element B to element A. In addition, for information sent from element A to element B, element B may send a request for the information or a receipt confirmation to element A.

[0132] In this application, including the following definitions, the term "module" or the term "controller" may be replaced by the term "circuit". The term "module" or the term "controller" may refer to, be or include: an application-specific integrated circuit (ASIC); a digital, analog or mixed analog / digital discrete circuit; a digital, analog or mixed analog / digital integrated circuit; a combinational logic circuit; a field programmable gate array (FPGA); a processor circuit (shared, dedicated or group) that executes code; a memory circuit (shared, dedicated or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system on a chip.

[0133] A module or controller may include one or more interface circuits. In some examples, the interface circuit may include a wired or wireless interface to a local area network (LAN), the Internet, a wide area network (WAN), or a combination thereof. As described above, the term code may include software, firmware, and / or microcode, and may refer to programs, routines, functions, classes, data structures, and / or objects.

[0134] The term memory is a subset of the term computer-readable medium. The term computer-readable medium as used herein does not include transient electrical or electromagnetic signals propagated through a medium (e.g., a carrier wave); therefore, the term computer-readable medium may be considered to be tangible and non-transitory. Non-limiting examples of non-transitory tangible computer-readable media are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or shielded read-only memory circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tapes or hard drives), and optical storage media (such as compact disks, DVDs, or Blu-ray disks).

[0135] The devices and methods described in this application may be implemented in part or in whole by a special-purpose computer created by configuring a general-purpose computer to perform one or more specific functions contained in a computer program. The functional blocks, flow chart components and other elements described above serve as software specifications that can be translated into computer programs by the routine work of a skilled technician or programmer.

[0136] The computer program includes processor executable instructions stored on at least one non-transitory tangible computer readable medium. The computer program may also include or rely on stored data. The computer program may include a basic input / output system (BIOS) that interacts with the hardware of the special-purpose computer, device drivers that interact with specific devices of the special-purpose computer, one or more operating systems, user applications, background services, background applications, etc.

[0137] A computer program may include: (i) descriptive text to be parsed, such as HTML (Hypertext Markup Language), XML (Extensible Markup Language), or JSON (JavaScript Object Notation) (ii) assembly code, (iii) object code generated by a compiler from source code, (iv) source code executed by an interpreter, (v) source code compiled and executed by a just-in-time compiler, etc. By way of example only, source code may be written using syntax from the following languages: C, C++, C#, Objective C, Swift, Haskell, Go, SQL, R, Lisp, Java, Fortran, Perl, Pascal, Curl, OCaml, Javascript®, HTML5 (Hypertext Markup Language 5th Revision), Ada, ASP (Active Server Pages), PHP (PHP: Hypertext Preprocessor), Scala, Eiffel, Smalltalk, Erlang, Ruby, Flash®, Visual Basic®, Lua, MATLAB, SIMULINK, and Python®.

Claims

1. A system, include: a plurality of sensors associated with various subsystems of the vehicle; and a controller configured to communicate with the plurality of subsystems of the vehicle and further configured to: processing data received from one or more sensors of one of the subsystems of the vehicle, wherein the processing includes smoothing the data and calculating an average of the data; identifying transition points in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend or the moving average is greater than the average by a predetermined amount indicating a downward trend; selecting a segment of the processed data after the transition point; detecting a trend of the processed data in a segment after the transition point using regression, wherein the trend comprises an upward trend or a downward trend; Extrapolating detected trends to reach a predetermined failure threshold; predicting a failure of said one of said subsystems based on a slope of the extrapolated trend; and An indication of a prediction is provided based on the slope of the extrapolated trend to serve the one of the subsystems in scheduling.

2. The system according to claim 1, in, The controller is also configured to use the detected trends to accurately diagnose a fault in one of the subsystems, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of a component in one of the subsystems before the component fails.

3. The system according to claim 1, in, The controller is also configured to: detecting a second trend in second data collected from one or more sensors of one of the subsystems after the servicing; and The service is evaluated based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

4. The system according to claim 1, in, The received data comprises first and second data for first and second parameters, respectively, of the one of the subsystems, and wherein the controller is further configured to: determining whether to generate an alert regarding a condition of the one of the subsystems based on whether first data for the first parameter has crossed a first threshold; and detecting a trend using second data for the second parameter, The second parameter is different from the first parameter.

5. The system according to claim 1, in, The controller is configured to provide an indication of the prediction in response to a slope of the extrapolated trend being greater than a first predetermined threshold.

6. The system according to claim 1, in, The controller is configured to: estimating an operational life of one of the subsystems based on a slope of the extrapolated trend; and An indication of the prediction is provided based on the estimate.

7. The system according to claim 1, in, The controller is configured to select a type of regression depending on a type of parameter of one of the subsystems for which data is received.

8. The system according to claim 1, in, The controller is configured to detect the trend by excluding data before the transition point.

9. The system according to claim 1, in, The controller is located in a computing device remote from the vehicle, and wherein the computing device comprises a mobile device, a service tool, or a server in the cloud.

10. A system, include: processor; and A memory storing instructions that, when executed by a processor, configure the processor to: processing data received from sensors of vehicle subsystems, wherein the processing includes smoothing the data and calculating an average of the data; identifying transition points in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend or a moving average is greater than the average by a predetermined amount indicating a downward trend; Selecting a segment of the processed data after the transition point; detecting a trend in the segment using regression, wherein the trend comprises an upward trend or a downward trend; Extrapolating detected trends to reach a predetermined failure threshold; predicting failure of the subsystem based on the slope of the extrapolated trend; and An indication of the prediction is provided based on the extrapolated trend slope to schedule service for the subsystem.

11. The system according to claim 10, in, The instructions further configure the processor to use the detected trends to accurately diagnose faults in the subsystem, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of components of the subsystem before they fail.

12. The system according to claim 10, in, The instructions further cause the processor to: detecting a second trend in second data collected from one or more sensors of the subsystem after the servicing; and The service is evaluated based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

13. The system according to claim 10, in, The received data includes first and second data for first and second parameters, respectively, of the subsystem, and wherein the instructions further configure the processor to: determining whether to generate an alert regarding a condition of the subsystem based on whether first data for the first parameter has crossed a first threshold; and detecting a trend using second data for the second parameter, The second parameter is different from the first parameter.

14. The system according to claim 10, in, The instructions further configure the processor to provide an indication of the prediction in response to a slope of the extrapolated trend being greater than a first predetermined threshold.

15. The system according to claim 10, in, The instructions further configure the processor to: estimating an operational life of the subsystem based on a slope of the extrapolated trend; and An indication of the prediction is provided based on the estimate.

16. The system according to claim 10, in, The instructions further configure the processor to select a type of regression depending on a type of parameter of the subsystem for which data is received.

17. The system according to claim 10, in, The instructions further configure the processor to detect the trend by excluding data before the transition point.

18. A computing device comprising the system according to claim 10, in, The computing device is remote from the vehicle and includes a mobile device, a service tool, or a server in the cloud.

19. A method, include: processing data received from sensors of vehicle subsystems, wherein the processing includes smoothing the data and calculating an average of the data; identifying transition points in the processed data at which a moving average of the data is less than the average by a predetermined amount indicating an upward trend or greater than the average by a predetermined amount indicating a downward trend; selecting a segment of the processed data after a transition point; detecting a trend in the segment using regression, wherein the trend comprises an upward trend or a downward trend; Extrapolating detected trends to reach a predetermined failure threshold; Predict subsystem failure based on the slope of the extrapolated trend; providing an indication of the forecast based on a slope of the extrapolated trend to schedule service to the subsystem; and The detected trends are used to accurately diagnose faults in the subsystem, modify control parameters of the vehicle to improve vehicle safety, and / or extend the life of the components of the subsystem before the components fail.

20. The method according to claim 19, further comprising: include: detecting a second trend in second data collected from one or more sensors of the subsystem after servicing; and The service is evaluated based on at least one of whether a second slope of the second trend is greater than a second threshold and whether the second data is within a predetermined range.

Images