Adaptive driving in vehicle energy consumption prediction

Abstract

A system for in-drive updating of an adaptive driving of a vehicle on a route comprises a controller adapted to obtain, via an energy consumption predictor, a pre-drive energy consumption prediction of the route. An in-drive updating module is selectively executable by the controller at a point in time during the route at which a completed portion of the route has been traversed while a remaining portion remains untraversed. The controller is adapted to obtain actual energy consumptions of road segments in the completed portion of the route. The controller is adapted to obtain at least one correction factor based on a comparison of the actual energy consumptions of the road segments in the completed portion of the route and the pre-drive energy consumption prediction. The pre-drive energy consumption prediction of the remaining portion of the route is adjusted based on the correction factor.

Description

Technical Field

[0001] This disclosure generally relates to updating the predicted amount of energy consumed by a vehicle. More specifically, this disclosure relates to systems and methods for adaptive in-drive updating of predicted energy consumption for vehicles traveling on a route. Background Technology

[0002] In electric vehicles, predicting the amount of energy a vehicle will consume along a specific route is valuable for users planning their trips. Furthermore, predicting energy consumption during a trip can help alleviate range anxiety. However, due to various factors, the prediction of the amount of energy a vehicle consumes (before the trip) may be inaccurate. Summary of the Invention

[0003] This paper discloses a system for adaptive in-driving updates for vehicles traveling on a route. The system includes a controller adapted to obtain a pre-driving energy consumption prediction of the route via an energy consumption predictor. The controller has a processor and tangible non-transitory memory. The in-driving update module can be selectively executed by the controller at a point in time during the route, where the completed portion of the route has been traversed, while the remaining portion remains untraversed. The route is divided into multiple segments. Execution of the in-driving update module causes the controller to obtain the actual energy consumption of the segments in the completed portion of the route. The controller is adapted to obtain at least one correction factor based on a comparison between the actual energy consumption of the segments in the completed portion of the route and the pre-driving energy consumption prediction. The pre-driving energy consumption prediction of the remaining portion of the route is adjusted based on the correction factor. The in-driving update introduced by the system improves prediction accuracy and provides better trip optimization for the driver.

[0004] In some embodiments, adjusting the pre-driving energy consumption prediction includes multiplying the pre-driving energy consumption prediction of the remaining segment by at least one correction factor. In some embodiments, adjusting the pre-driving energy consumption prediction may include adding at least one correction factor to the pre-driving energy consumption prediction of the remaining segment. The in-driving update module may incorporate a machine learning model to adjust the pre-driving energy consumption prediction.

[0005] The correction factor can be based in part on the sum of actual energy consumption in the road segment and the sum of predicted pre-driving energy consumption in the road segment. The correction factor can also be based in part on the damping coefficient. Furthermore, the correction factor can be based in part on the corresponding weighting factor of the road segment, which is between zero and one, including endpoint values. The correction factor (Mi) applied to the i-th road segment at the beginning of the remainder can be obtained as follows: , where d is the damping coefficient, w_j is the corresponding weighting factor, a_j is the actual energy consumption in one of the completed road segments, and p_j is the predicted pre-driving energy consumption in one of the completed road segments.

[0006] In some embodiments, the controller is programmed to update the pre-driving energy consumption prediction for future segments in the remaining portion of the route based on the similarity between characteristic features in future segments and characteristic features in past segments in the completed portion. Characteristic features may include vehicle speed and the geographical classification of the route.

[0007] In some embodiments, the energy consumption predictor incorporates multiple modules, and the controller is programmed to sequentially update the multiple modules. The multiple modules may include a speed prediction module, a driving consumption prediction module, and an HVAC consumption prediction module.

[0008] This paper discloses a method for updating in-drive information for a vehicle traveling on a route divided into multiple segments, the vehicle having a controller with a processor and tangible non-transitory memory. The method includes obtaining pre-driving energy consumption predictions for segments of the route via an energy consumption predictor. An in-drive update module is executed via the controller at a point in time during the route, where the completed portion of the route has been traversed, while the remaining portion remains untraversed. The method includes obtaining the actual energy consumption of the segments in the completed portion of the route. The method includes obtaining at least one correction factor via the controller based on a comparison of the actual energy consumption of the segments in the completed portion of the route and the pre-driving energy consumption predictions. The pre-driving energy consumption predictions for the segments in the remaining portion of the route are adjusted based on the at least one correction factor.

[0009] This disclosure includes the following solutions.

[0010] Option 1. A system for updating in adaptive driving, for a vehicle traveling on a route, the system comprising:

[0011] A controller adapted to obtain a pre-driving energy consumption prediction of the route via an energy consumption predictor, the controller having a processor and tangible non-transitory memory;

[0012] A driving update module, which can be selectively executed by the controller at a point in time during the route, where the completed portion of the route has been traversed while the remaining portion remains untraversed, the route being divided into multiple segments, the execution of the driving update module causing the controller to:

[0013] Obtain the actual energy consumption of the road segment in the completed portion of the route;

[0014] At least one correction factor is obtained by comparing the actual energy consumption and the predicted pre-driving energy consumption of a segment of the completed section of the route; and

[0015] The pre-driving energy consumption prediction for the remaining sections of the route is adjusted based on the at least one correction factor.

[0016] Option 2. The system according to Option 1, wherein the driving update module incorporates a machine learning model to adjust the pre-driving energy consumption prediction.

[0017] Option 3. The system according to Option 1, wherein:

[0018] Adjusting the pre-driving energy consumption prediction includes multiplying the at least one correction factor by the pre-driving energy consumption prediction of the remaining road segments; and

[0019] The at least one correction factor is based in part on the sum of actual energy consumption in the road segment and the sum of predicted pre-driving energy consumption in the road segment.

[0020] Option 4. The system according to Option 3, wherein the at least one correction factor is partially based on the damping coefficient.

[0021] Option 5. The system according to Option 3, wherein the at least one correction factor is partially based on a corresponding weighting factor of the road segment, the corresponding weighting factor being between zero and one, including endpoint values.

[0022] Solution 6. The system according to Solution 5, wherein the at least one correction factor (Mi) is applied at the i-th segment at the beginning of the remaining portion and obtained as follows: , where d is the damping coefficient, w_j is the corresponding weighting factor, a_j is the actual energy consumption in one segment of the completed section, and p_j is the predicted pre-driving energy consumption in one segment of the completed section.

[0023] Option 7. The system according to Option 1, wherein adjusting the pre-driving energy consumption prediction includes adding the at least one correction factor to the pre-driving energy consumption prediction of the road segment in the remaining portion.

[0024] Option 8. The system according to Option 1, wherein the controller is programmed to update the pre-driving energy consumption prediction in the future segments of the remaining portion of the route based on the similarity between characteristic features in the future segments and characteristic features in the past segments of the completed portion.

[0025] Option 9. The system according to Option 8, wherein the characteristic feature is the speed of the vehicle.

[0026] Option 10. The system according to Option 8, wherein the characteristic feature is the geographical classification of the route.

[0027] Option 11. The system according to Option 1, wherein the energy consumption predictor combines multiple modules, and the controller is programmed to sequentially update the multiple modules.

[0028] Option 12. The system according to Option 11, wherein the plurality of modules includes a speed prediction module, a driving consumption prediction module, and an HVAC consumption prediction module.

[0029] Option 13. A method for updating in adaptive driving, for a vehicle traveling on a route divided into multiple segments, the vehicle having a controller with a processor and tangible non-transitory memory, the method comprising:

[0030] Pre-driving energy consumption predictions for road segments within the route are obtained via an energy consumption predictor;

[0031] The driving update module is executed via the controller at a point in time during the route, at which the completed portion of the route has been traversed while the remaining portion remains untraversed;

[0032] Obtain the actual energy consumption of the completed section of the route;

[0033] At least one correction factor is obtained via the controller based on a comparison of the actual energy consumption and the predicted pre-driving energy consumption for a segment of the completed portion of the route; and

[0034] The pre-driving energy consumption prediction for the remaining sections of the route is adjusted based on the at least one correction factor.

[0035] Option 14. The method according to Option 13, further comprising:

[0036] The machine learning model is incorporated into the driving update module to adjust the pre-driving energy consumption prediction.

[0037] Option 15. The method according to Option 13, wherein adjusting the pre-driving energy consumption prediction includes:

[0038] Multiply the at least one correction factor by the pre-driving energy consumption prediction for the remaining road segments; and

[0039] The at least one correction factor is obtained in part based on the sum of actual energy consumption in the road segment and the sum of predicted pre-driving energy consumption in the road segment.

[0040] Option 16. The method according to Option 13, wherein adjusting the pre-driving energy consumption prediction includes:

[0041] The at least one correction factor is added to the pre-driving energy consumption prediction of the remaining road segments.

[0042] Option 17. The method according to Option 13, characterized in that it further comprises:

[0043] The pre-driving energy consumption prediction for the future segments of the remaining portion of the route is updated based on the similarity of the characteristics of the future segments with those of the past segments in the completed portion.

[0044] Option 18. A system for updating in adaptive driving for a vehicle traveling on a route, the system comprising:

[0045] A controller adapted to obtain a pre-driving energy consumption prediction of the route via an energy consumption predictor, the controller having a processor and tangible non-transitory memory;

[0046] A driving update module, which can be selectively executed by the controller at a point in time during the route, where the completed portion of the route has been traversed while the remaining portion remains untraversed, the route being divided into multiple segments, wherein the execution of the driving update module causes the controller to:

[0047] Obtain the actual energy consumption of the completed section of the route;

[0048] At least one correction factor is obtained based on the damping coefficient, the corresponding weighting factor of the road segment, the sum of actual energy consumption in the road segment, and the sum of predicted pre-driving energy consumption in the completed section of the route; and

[0049] The pre-driving energy consumption prediction for the remaining sections of the route is adjusted based on the at least one correction factor.

[0050] Option 19. The system according to Option 18, wherein the driving update module incorporates a machine learning model to adjust the pre-driving energy consumption prediction.

[0051] Option 20. The system according to Option 18, wherein the controller is programmed to update the pre-driving energy consumption prediction in the future segments of the remaining portion of the route based on the similarity between characteristic features in the future segments and characteristic features in the past segments of the completed portion.

[0052] The foregoing features and advantages, as well as other features and advantages, of this disclosure will become apparent from the following detailed description of the best mode for carrying out this disclosure, taken in conjunction with the accompanying drawings. Attached Figure Description

[0053] Figure 1 This is a partial schematic diagram of the system used for updating adaptive driving to predict vehicle energy consumption.

[0054] Figure 2 This is an explanation of the reason. Figure 1 A partial schematic diagram of the vehicle's route;

[0055] Figure 3 It is used for Figure 1 A flowchart of an example method for updating vehicle energy consumption prediction in adaptive driving; and

[0056] Figure 4 This is an explanation Figure 1 A graph showing example tracks of the vehicle's pre-driving predicted speed, actual speed, and updated predicted speed.

[0057] Representative embodiments of this disclosure are illustrated by way of non-limiting example in the accompanying drawings and are described in further detail below. However, it should be understood that the novel aspects of this disclosure are not limited to the specific forms illustrated in the drawings listed above. Rather, this disclosure will cover modifications, equivalents, combinations, sub-combinations, permutations, groupings, and alternatives that fall within the scope of this disclosure, as defined by the appended claims, for example. Detailed Implementation

[0058] Referring to the accompanying drawings, where the same reference numerals refer to the same parts, Figure 1 The adaptive driving update system 10 (hereinafter referred to as the "System") for vehicle 12 is illustrated schematically. Vehicle 12 may include, but is not limited to, passenger cars, SUVs, light trucks, heavy-duty vehicles, minivans, buses, transport vehicles, bicycles, mobile robots, agricultural implements (e.g., tractors), sports-related equipment (e.g., golf carts), boats, airplanes, and trains. Vehicle 12 may be an electric vehicle, which may be fully electric or hybrid / partially electric. It should be understood that vehicle 12 may take many different forms and have additional components.

[0059] refer to Figure 1System 10 includes a controller C having at least one processor P and at least one memory M (or a non-transitory tangible computer-readable storage medium) on which data for execution (see below) can be recorded. Figure 3 The instructions of method 100 (described). System 10 (executed via method 100) enables the updating of the predicted energy consumption of vehicle 12 traveling on the route during driving. Figure 2 Example route 14 is shown, starting at point 16 and ending at destination 18. Controller C can access and selectively execute energy consumption predictor 20 and driving update module 22, as shown. Figure 1 As shown.

[0060] Given a specific route, vehicle 12 can present a prediction of energy consumption to the user. Before driving, route 14 can be planned, segmented, and characterized based on static and real-time features. These features are used to predict the energy consumed to complete route 14. The planned route, along with other factors such as distance, altitude, real-time traffic, weather, and driver characteristics, are fed into energy consumption predictor 20 (which can be a physical model, a machine learning model, or other types of model) to obtain predicted fuel or energy consumption.

[0061] System 10 provides an architecture for updating forecasts in a robust and accurate manner. (Reference) Figure 2 The driving update module 22 is executed at time point T, when the completed portion 24 has been traversed by vehicle 12, while the remaining portion 26 has not yet been driven. In other words, the driving update module 22 is run in real time while vehicle 12 remains on route 14.

[0062] Figure 1 The controller C can be a component of other controllers of vehicle 12, or a separate module operatively connected to them. For example, controller C can be an electronic control unit (ECU) of vehicle 12. Memory M can store a set of controller executable instructions, and processor P can execute the set of controller executable instructions stored in memory M.

[0063] refer to Figure 2 Route 14 can be divided into multiple distinct segments 30. In the example shown, segments 30 include a first segment 32, a second segment 34, a third segment 36, a fourth segment 38, and a fifth segment 40. During the collection and processing phase, each individual segment 30 can consist of multiple smaller segments or sub-segments. In one embodiment, each segment 30 can be approximately 4 kilometers long. The dimensions of the segments 30 can vary.

[0064] refer to Figure 1Pre-driving route planning can be input via a communication interface 42 accessible to the user or operator of vehicle 12. For example, a route planner can generate candidate routes and send them to a predictor to obtain their predicted consumption, which helps in selecting an energy-efficient route. Communication interface 42 may include a touchscreen or other I / O device and may be integrated into the infotainment unit of vehicle 12. In some embodiments, route planning can be input via a mobile application 44 communicating with controller C. For example, mobile application 44 may be physically connected (e.g., wired) to controller C as part of the vehicle's infotainment unit. Mobile application 44 may be embedded in a smart device belonging to a user of vehicle 12 and may be plugged into or otherwise linked to vehicle 12. The circuitry and components of mobile application 44 (“apps”) available to those skilled in the art may be employed. Communication interface 42 may also be used for vehicle-to-vehicle (V2V) communication and / or vehicle-to-everything (V2X) communication.

[0065] The in-driving update module 22 and / or energy consumption predictor 20 may be stored in the vehicle 12. In some embodiments, the in-driving update module 22 and / or energy consumption predictor 20 may be stored in a remotely located or "off-vehicle" cloud computing service, referred to herein as cloud unit 46, which interfaces with controller C and / or a mobile application. Cloud unit 46 may include one or more servers hosted on the Internet to store, manage, and process data maintained by an organization such as a research institution or company. The in-driving update module 22 may be updated via remote update.

[0066] refer to Figure 1 The controller C can be configured to communicate with the cloud unit 46 via the wireless network 48. Figure 1 The wireless network 48 can be a short-range network or a long-range network. The wireless network 48 can be a communication bus, which can take the form of a Serial Controller Area Network (CAN bus). The wireless network 48 can be combined with Bluetooth™ connectivity, a wireless local area network (LAN) using wireless distribution methods to link multiple devices, a wireless metropolitan area network (MAN) connecting several wireless LANs, or a wireless wide area network (WAN). Other types of connections can also be used.

[0067] Now for reference Figure 3 The following is an example flowchart of method 100. Method 100 can be implemented as stored in... Figure 1Computer-readable code or instructions that are executed on and partially by the controller C. Method 100 is not necessarily applied in the specific order described herein and can be executed dynamically. Furthermore, it should be understood that some steps can be omitted. As used herein, the terms "dynamic" and "dynamically" describe steps or processes executed in real time and are characterized by monitoring or otherwise determining the state of parameters during or between iterations of an execution routine and updating the state of parameters periodically or periodically.

[0068] Method 100 is initiated or triggered when vehicle 12 begins traveling on route 14. According to... Figure 3 In box 102, method 100 includes determining whether vehicle 12 continues to travel on route 14. If so, then method 100 proceeds to... Figure 3 In box 104, controller C is programmed to obtain the actual energy consumption for segment 30 in the completion portion 24 of route 14. Controller C also retrieves pre-driving energy consumption predictions for segment 30 in the completion portion 24 of route 14 from energy consumption predictor 20.

[0069] Advance to Figure 3 In block 106, controller C is programmed to acquire at least one correction factor (hereinafter "at least one") based on a comparison of the pre-driving energy consumption prediction for past segment 30 (i.e., the completed portion 24 of route 14) and the actual energy consumption of the same segment (acquired in block 104). Individual correction factors may be acquired for each of the future segments 30 (i.e., the remainder 26 of route 14).

[0070] Adjusting the pre-driving energy consumption forecast may include multiplying a correction factor by the pre-driving energy consumption forecast for segment 30 in the remaining portion 26, for example, by multiplying the future pre-driving forecast by the ratio between past actual consumption (the sum of actual energy consumption of segment 30 in the completed portion 24) and past pre-driving forecasts (the sum of pre-driving energy consumption forecasts in the completed portion 24).

[0071] The correction factor can be based in part on the damping coefficient (d). In this paper, the correction factor (applied to the i-th segment at the beginning of the remaining part 26) is obtained as follows: Where d is the damping coefficient and a_j is the actual energy consumption in a single road segment j. To complete the sum of actual energy consumption in section 30 of part 24, and p_j is the predicted pre-driving energy consumption in a single section j, To complete the sum of the predicted pre-driving energy consumption for section 30 of part 24. The damping or "forgotten" factor can be constrained or calibrated based on the application at hand.

[0072] The correction factor can be based in part on the corresponding weighting factor used for segment 30. The corresponding weighting factor is between zero and one, includes endpoint values, and can be customized to add a larger weight to the most recent past segments and a smaller weight to older past segments. The correction factor (Mi) applied to the i-th segment at the beginning of the remaining portion 26 can be obtained as follows: Mi = , where w_j is the corresponding weighting factor.

[0073] Adjusting the pre-driving energy consumption prediction may include adding a correction factor to the pre-driving energy consumption prediction for segment 30 in the remaining portion 26. In this document, the correction factor is obtained as the average difference between the actual energy consumption and the pre-driving predicted energy consumption for each segment.

[0074] In some embodiments, the driving update module 22 incorporates a machine learning model, such as a machine learning adaptive predictor, to adjust the pre-driving predicted energy consumption or obtain a correction factor. While the method is described herein as providing a correction factor, it should be understood that the driving update module 22 may directly output an adaptive prediction without involving an explicit correction factor. The machine learning model may include, but is not limited to, neural networks, simple linear regression models, support vector regression models, and other types of machine learning models available to those skilled in the art. For example, the machine learning model may be a feedforward artificial neural network having an input layer, one or more hidden layers, and an output layer. Each layer consists of corresponding nodes configured to perform an affine transformation of the linear sum of the inputs. The corresponding nodes are independent and characterized by a unique set of weights. In some embodiments, the driving update module 22 may incorporate a machine learning model (e.g., a neural network) trained to predict the actual energy consumption in segment X using the following inputs: (1) characteristics of segment 1 to segment (X-1), (2) the actual energy consumption of segment 1 to segment (X-1); and (3) characteristics of segment X.

[0075] Advance to Figure 3 In box 108, method 100 includes adjusting the pre-driving energy consumption prediction for the remainder 26 of route 14 based on one or more correction factors obtained in box 106. As described above, the adjustment can be multiplicative, additive, extrapolated, or a machine learning-based algorithm. After the adjustment in box 108, method 100 loops back to box 102 to determine whether vehicle 12 continues on route 14. If route 14 has been completed, then method 100 ends (as indicated by line 103). If vehicle 12 remains on route 14, then the process is repeated in box 104.

[0076] Method 100 can be applied to monolithic and modular architectures. In some embodiments, the energy consumption predictor 20 is characterized by a modular architecture with multiple modules that operate sequentially or in series to obtain predicted energy consumption. (Reference) Figure 1 For example, the energy consumption predictor 20 may include a speed prediction module 50, a driving energy consumption module 52, and an HVAC (heating, ventilation, and air conditioning) energy consumption module 54. Multiple modules receive input information such as route data, weather data, and traffic data via a feature extractor 56. The speed prediction module 50 models driving style to predict the speed of vehicle 12, which is output to the driving energy consumption module 52. The driving energy consumption module 52 is adapted to predict the driving energy, or primary energy, consumed to move vehicle 12. The HVAC energy consumption module 54 is adapted to predict the secondary energy consumed by the HVAC units of vehicle 12. The outputs of the driving energy consumption module 52 and the HVAC energy consumption module 54 are totaled or added in a total energy consumption module 58 to predict the pre-driving energy consumption in each of the segments 30 of a specific route plan.

[0077] In this type of modular architecture, updates (to the pre-driving energy consumption prediction) are performed sequentially. In the architecture described above, updates can be performed as follows: Controller C is adapted to first compare the predicted HVAC consumption and predicted speed with past measurements of HVAC consumption and speed, respectively. Next, the future HVAC consumption and future speed predictions are updated. Controller C is adapted to recalculate past consumption predictions (in box 52) using the measured speed. Finally, the recalculated consumption predictions are compared with the measured consumption, and the future consumption predictions are also updated accordingly based on the updated speed (from above).

[0078] In some embodiments, method 100 includes updating predictions based on route similarity or characteristic features. For each future road segment, controller C may be programmed to find the most similar road segment in the past or one or more road segments with the closest characteristic feature values. In other words, controller C is programmed to update the pre-driving energy consumption predictions in future road segments (e.g., fourth road segment 38) in the remaining portion 26 of route 14 based on the similarity between the characteristic features in the future road segment and the characteristic features in past road segments (e.g., second road segment 34) in the completed portion 24. Characteristic features may be the geographical classification of road segment 30 (e.g., urban, highway, mountainous). For example, if first road segment 32, second road segment 34, third road segment 36, fourth road segment 38, and fifth road segment 40 are classified as highway, urban, mountainous, urban, and highway, respectively, then the prediction in the future urban road segment (fourth road segment 38) will be adjusted based on the prediction and actual consumption in the past urban road segment (second road segment 34) (see arrow 60). The forecasts for future highway segments (segment 5, 40) can be adjusted based on forecasts and actual consumption from past highway segments (segment 1, 32) (see arrow 62).

[0079] The characteristic feature can be the speed of vehicle 12. Figure 4 An illustrative example of similarity-based speed prediction is shown. (Reference) Figure 4 The example graph is shown, where speed is on the vertical axis 202 and distance traveled along the route is on the horizontal axis 204. The route described in this article includes at least the first segment 206, the second segment 208, and the third segment 210. Reference Figure 4 At the current time 215, the completed portion 212 has been traversed by vehicle 12, while the remaining portion 214 has not yet been driven. Traces 216A, 216B, and 216C show the corresponding pre-driving speed predictions for the first road segment 206, the second road segment 208, and the third road segment 210. Traces 218A and 218B show the actual speeds along the first road segment 206 and the second road segment 208, respectively. (Reference) Figure 4 The future speed prediction in the third segment 210 is adapted from the first segment 206, where the initial speed predictions are similar. Trace 220 shows the modified or updated pre-driving speed prediction for the third segment 210.

[0080] In summary, system 10 (executed via method 100) combines predefined route prediction with a robust method of acquiring in-driving updates. Figure 1The controller C includes computer-readable media (also known as processor-readable media), including non-transitory (e.g., tangible) media that participate in providing data (e.g., instructions) that can be read by a computer (e.g., by the computer's processor). Such media can take many forms, including but not limited to non-volatile and volatile media. Non-volatile media can include, for example, optical discs or magnetic disks and other permanent storage. Volatile media can include, for example, dynamic random access memory (DRAM), which can constitute main memory. Such instructions can be transmitted via one or more transmission media, including coaxial cables, copper wires, and optical fibers, including lines containing a system bus coupled to the computer processor. Some forms of computer-readable media include, for example, floppy disks, floppy disks, hard disks, magnetic tape, other magnetic media, CD-ROMs, DVDs, other optical media, physical media with perforated patterns, RAM, PROMs, EPROMs, FLASH-EEPROMs, other memory chips or cassette tapes, or other media that can be read by a computer.

[0081] The lookup tables, databases, data repositories, or other data repositories described herein can include various mechanisms for storing, accessing, and retrieving various types of data, including hierarchical databases, a set of files in a file-based rechargeable energy storage system, application databases in proprietary formats, relational database energy management systems (RDBMS), etc. Each such data repository can be included within a computing device employing a computer operating system such as those described above, and can be accessed via a network in one or more of various ways. File systems can be accessed from the computer operating the rechargeable energy storage system and can include files stored in various formats. RDBMS can employ Structured Query Language (SQL), in addition to languages ​​used for creating, storing, editing, and executing stored procedures, such as PL / SQL mentioned above.

[0082] Figure 3The flowcharts illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each box in a flowchart or block diagram may represent a code module, code segment, or code portion containing one or more executable instructions for implementing one or more specified logical functions. It will also be noted that each box in the block diagrams and / or flowchart illustrations, and combinations of boxes in the block diagrams and / or flowchart illustrations, may be implemented by a dedicated hardware-based rechargeable energy storage system that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions. These computer program instructions may also be stored in a computer-readable medium that can instruct a controller or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of art including instructions that implement the functions / actions specified in the flowchart and / or block diagram boxes.

[0083] Numerical values ​​of parameters (e.g., quantities or conditions) in this specification, including the appended claims, should in each relevant case be understood to be modified by the term “about,” regardless of whether “about” actually appears before the numerical value. “About” indicates that the numerical value allows for some slight imprecision (approaching the accuracy of the value in some way; approximately or reasonably close to the value; nearly). If the imprecision provided by “about” is not otherwise understood in this common sense in the art, then “about” as used herein at least indicates variations that may arise from common methods of measuring and using such parameters. Furthermore, the disclosure of ranges includes disclosing every value throughout the range and further subdivided ranges. Each value within the range and the endpoints of the range are disclosed herein as separate embodiments.

[0084] Detailed description and accompanying drawings are provided to support and describe this disclosure, but the scope of this disclosure is defined only by the claims. While the best mode and some other embodiments for carrying out the claimed disclosure have been described in detail, various alternative designs and embodiments exist to practice the disclosure as defined in the appended claims. Furthermore, features of the embodiments shown in the drawings or the various embodiments mentioned in this specification are not necessarily to be construed as independent embodiments. Rather, each of the features described in one of the examples of embodiments may be combined with one or more other desired features from other embodiments to result in other embodiments not described in words or with reference to the drawings. Therefore, such other embodiments fall within the framework of the appended claims.

Claims

1. A system for updating in adaptive driving, for a vehicle traveling on a route, the system comprising: A controller adapted to obtain a pre-driving energy consumption prediction of the route via an energy consumption predictor, the controller having a processor and tangible non-transitory memory; A driving update module, which can be selectively executed by the controller at a point in time during the route, where the completed portion of the route has been traversed while the remaining portion remains untraversed, the route being divided into multiple segments, the execution of the driving update module causing the controller to: Obtain the actual energy consumption of the road segment in the completed portion of the route; At least one correction factor is obtained by comparing the actual energy consumption of the road segment in the completed portion of the route with the predicted pre-driving energy consumption. and The pre-driving energy consumption prediction for the remaining portion of the route is adjusted based on the at least one correction factor. Adjusting the pre-driving energy consumption prediction includes multiplying the at least one correction factor by the pre-driving energy consumption prediction of the remaining road segments; and The at least one correction factor is based in part on the sum of actual energy consumption in the road segment and the sum of predicted pre-driving energy consumption in the road segment; The at least one correction factor is partially based on a corresponding weighting factor for the road segment, the corresponding weighting factor being between zero and one, including endpoint values; The at least one correction factor Mi is applied to the i-th segment at the beginning of the remaining portion and obtained as follows: , where d is the damping coefficient, w_j is the corresponding weighting factor, a_j is the actual energy consumption in one segment of the completed section, and p_j is the predicted pre-driving energy consumption in one segment of the completed section.

2. The system according to claim 1, wherein, The driving update module incorporates a machine learning model to adjust the pre-driving energy consumption prediction.

3. The system according to claim 1, wherein, The at least one correction factor is based in part on the damping coefficient.

4. The system according to claim 1, wherein, Adjusting the pre-driving energy consumption prediction includes adding the at least one correction factor to the pre-driving energy consumption prediction of the remaining road segments.

5. The system according to claim 1, wherein, The controller is programmed to update the pre-driving energy consumption prediction for future segments in the remaining portion of the route based on the similarity between characteristic features in future segments and characteristic features in past segments in the completed portion.

6. The system according to claim 5, wherein, The characteristic feature is the vehicle's speed.

7. The system according to claim 5, wherein, The characteristic feature is the geographical classification of the route.

8. The system according to claim 1, wherein, The energy consumption predictor combines multiple modules, and the controller is programmed to update the multiple modules sequentially.

9. The system according to claim 8, wherein, The multiple modules include a speed prediction module, a driving consumption prediction module, and an HVAC consumption prediction module.

10. A method for updating in adaptive driving, for a vehicle traveling on a route divided into multiple segments, the vehicle having a controller with a processor and tangible non-transitory memory, the method comprising: Pre-driving energy consumption predictions for road segments within the route are obtained via an energy consumption predictor; The driving update module is executed via the controller at a point in time during the route, at which the completed portion of the route has been traversed while the remaining portion remains untraversed; Obtain the actual energy consumption of the completed section of the route; At least one correction factor is obtained via the controller based on a comparison between the actual energy consumption and the predicted pre-driving energy consumption of a segment in the completed portion of the route. and The pre-driving energy consumption prediction for the remaining portion of the route is adjusted based on the at least one correction factor. The adjustment of the pre-driving energy consumption prediction includes: Multiply the at least one correction factor by the pre-driving energy consumption prediction for the remaining road segments; and The at least one correction factor is obtained in part based on the sum of actual energy consumption in the road segment and the sum of predicted pre-driving energy consumption in the road segment; The at least one correction factor is partially based on a corresponding weighting factor for the road segment, the corresponding weighting factor being between zero and one, including endpoint values; The at least one correction factor Mi is applied to the i-th segment at the beginning of the remaining portion and obtained as follows: , where d is the damping coefficient, w_j is the corresponding weighting factor, a_j is the actual energy consumption in one segment of the completed section, and p_j is the predicted pre-driving energy consumption in one segment of the completed section.

11. The method of claim 10, further comprising: The machine learning model is incorporated into the driving update module to adjust the pre-driving energy consumption prediction.

12. The method according to claim 10, wherein, Adjusting the pre-driving energy consumption prediction includes: The at least one correction factor is added to the pre-driving energy consumption prediction of the remaining road segments.

13. The method according to claim 10, characterized in that... Also includes: The pre-driving energy consumption prediction for the future segments of the remaining portion of the route is updated based on the similarity of the characteristics of the future segments with those of the past segments in the completed portion.

Images