A hybrid system switching jerk suppression method, device, equipment, medium and product

Abstract

The application discloses a hybrid system switching jerk suppression method, device, equipment, medium and product. The method comprises the following steps: under the current working condition, when the hybrid system switching request is detected, the switching parameters are collected through the sensor; the switching parameters comprise torque fluctuation, speed difference and longitudinal acceleration; the switching parameters are input into the target model to obtain the jerk level judgment result; the jerk level judgment result comprises smooth state, slight jerk, moderate jerk and severe jerk; the working condition information of the current working condition is obtained, and the jerk reason is determined according to the working condition information, the switching parameters and the jerk level judgment result; the torque compensation parameter is updated based on the jerk reason, and the next hybrid system switching is carried out based on the updated torque compensation parameter. Through the technical scheme of the application, the calibration cost can be reduced, the jerk suppression effect can be improved, and the continuous optimization of vehicle drivability can be realized.

Description

Technical Field

[0001] The present invention relates to the field of hybrid vehicle technology, and in particular to a method, apparatus, device, medium and product for suppressing switching jerks in a hybrid system. Background Technology

[0002] Hybrid vehicles require frequent power switching between the engine and the drive motor during operation (such as switching between pure electric mode and hybrid mode, and switching between engine start and stop). The smoothness of torque switching directly determines the vehicle's driving performance and ride experience, and is one of the core technical challenges in the field of hybrid vehicle control.

[0003] Currently, the calibration of torque compensation parameters for hybrid systems mainly relies on manual labor. Technicians need to conduct a large number of real vehicle tests under different road conditions and operating conditions, and determine the compensation coefficient MAP (map) through repeated adjustments, thereby suppressing switching jerks. However, manual calibration has many inherent defects and is difficult to meet actual driving needs: First, it does not cover all driving conditions. Manual testing cannot exhaust all complex driving scenarios (such as switching between different road conditions, different driving habits, and different ambient temperatures), resulting in poor adaptability of the calibrated compensation coefficient MAP, which is prone to jerking under uncovered conditions. Second, it has poor consistency. Different technicians have different calibration experience and debugging standards, resulting in inconsistent compensation effects for different vehicles and for the same vehicle at different calibration cycles, affecting product consistency. Third, it is difficult to optimize later. After manual calibration, the compensation coefficient MAP is fixed and cannot be dynamically adjusted according to changes in driving conditions and component aging (such as engine and motor performance degradation) during long-term vehicle use. As the usage time increases, the jerking problem will gradually become more prominent. Fourth, it has low calibration efficiency and high cost. Manual calibration requires a lot of time, manpower, and resources. According to statistics, traditional manual calibration requires the workload of dozens of people per day, and the calibration cost remains high.

[0004] Therefore, there is an urgent need for a hybrid system switching jerking suppression technology that can solve the defects of manual calibration, achieve online real-time self-learning, adapt to in-vehicle scenarios, and support long-term optimization. Summary of the Invention

[0005] This invention provides a method, apparatus, device, medium, and product for suppressing switching jerks in hybrid systems, which can reduce calibration costs, improve jerk suppression effects, and continuously optimize vehicle drivability.

[0006] According to one aspect of the present invention, a method for suppressing switching jerks in a hybrid system is provided, comprising: Under the current operating conditions, when a hybrid system switching request is detected, switching parameters are collected by sensors; the switching parameters include: torque fluctuation, speed difference, and longitudinal acceleration; The switching parameters are input into the target model to obtain the jerking level determination result; the jerking level determination result includes: smooth state, slight jerking, moderate jerking and severe jerking; Obtain the current operating condition information, and determine the cause of the jerking based on the operating condition information, the switching parameters, and the jerking level determination result; The torque compensation parameters are updated based on the cause of the jerking, and the next hybrid system switch is performed based on the updated torque compensation parameters.

[0007] According to another aspect of the present invention, a hybrid system switching jerking suppression device is provided, the device comprising: The data acquisition module is used to collect switching parameters through sensors when a hybrid system switching request is detected under the current operating conditions. The switching parameters include torque fluctuation, speed difference, and longitudinal acceleration. The input module is used to input the switching parameters into the target model to obtain the jerking level determination result; the jerking level determination result includes: smooth state, slight jerking, moderate jerking and severe jerking; The determination module is used to obtain the current working condition information and determine the cause of the jerking based on the working condition information, the switching parameters, and the jerking level determination result. The update module is used to update the torque compensation parameters based on the cause of the jerking, and to perform the next hybrid system switch based on the updated torque compensation parameters.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the hybrid system switching jerking suppression method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the hybrid system switching jerking suppression method according to any embodiment of the present invention.

[0010] According to another aspect of the present invention, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the hybrid system switching jerking suppression method described in any embodiment of the present invention.

[0011] This invention, under current operating conditions, when a hybrid system switching request is detected, collects switching parameters via sensors. These parameters include torque fluctuation, speed difference, and longitudinal acceleration. The switching parameters are input into a target model to obtain a jerking level determination result, which includes: smooth operation, slight jerking, moderate jerking, and severe jerking. The current operating condition information is obtained, and the cause of the jerking is determined based on this information, the switching parameters, and the jerking level determination result. The torque compensation parameters are updated based on the cause of the jerking, and the next hybrid system switch is performed based on the updated torque compensation parameters. This invention reduces calibration costs, improves jerking suppression, and continuously optimizes vehicle drivability.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of a method for suppressing switching jerks in a hybrid system according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a hybrid system switching jerking suppression device in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the hybrid system switching jerking suppression method of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and their derivatives, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0018] Example 1 While some existing technologies address jerking suppression in hybrid systems, most employ a fixed compensation coefficient (MAP) control method, which only suppresses jerking under specific operating conditions and cannot achieve adaptive optimization. A few solutions involving self-learning either utilize complex AI (Artificial Intelligence) models, requiring reliance on high-performance onboard computing platforms, resulting in high hardware costs and difficulty in engineering applications, or only achieve offline self-learning, failing to support online real-time optimization and OTA (Over-The-Air) upgrades, thus unable to meet the dynamic optimization needs of vehicles during long-term use. For example, some technologies use deep learning models for jerking prediction, but these models are massive (typically exceeding 50MB), consuming significant onboard computing resources and unsuitable for the onboard controllers of ordinary hybrid vehicles. Other technologies use simple parameter iteration methods for self-learning, but without combining AI models for intelligent recognition and optimization, resulting in low self-learning accuracy, slow convergence speed, and an inability to effectively address issues of incomplete operating condition coverage and poor consistency.

[0019] Figure 1 This is a flowchart of a hybrid system switching jerking suppression method according to an embodiment of the present invention. This embodiment is applicable to the case of hybrid system switching jerking suppression. The method can be executed by the hybrid system switching jerking suppression device in this embodiment of the present invention. The device can be implemented in software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps: S101. Under the current operating conditions, when a hybrid system switching request is detected, switching parameters are collected through sensors.

[0020] The technical solution of this invention is applied to hybrid vehicles, where the hybrid system can be a hybrid vehicle control system. For example, the switching request can be a power switching request between the engine and the drive motor (such as switching between pure electric mode and hybrid mode, or switching between engine start and stop).

[0021] Preferably, the sensors in the embodiments of the present invention may include motor and engine torque sensors, engine and motor speed sensors, vehicle body acceleration sensors, etc.

[0022] The switching parameters include torque fluctuation, speed difference, and longitudinal acceleration.

[0023] In the specific implementation process, when the vehicle controller detects a switching request (such as the battery SOC (State of Charge) being lower than the threshold or the accelerator pedal being pressed down by more than 50%), it automatically triggers the data acquisition operation. The data acquisition duration can be set from 50ms before the switch to 100ms after the switch to ensure complete capture of parameter changes during the switching process.

[0024] Specifically, the existing onboard sensors can be used to collect three types of core parameters (all of which are key data at the switching moment): (1) Torque fluctuation: collected by motor and engine torque sensors, with a sampling frequency of ≥10Hz, recording data 50ms before switching, during switching, and 50ms after switching, and calculating the maximum and minimum torque difference; (2) Speed ​​difference: collected by engine and motor speed sensors, calculating the absolute value of the speed difference between the two in real time, with a sampling frequency of ≥10Hz; (3) Longitudinal acceleration: collected by vehicle acceleration sensors, focusing on collecting the fluctuation value during the switching process as the core indicator for judging jerking, with a sampling frequency of ≥10Hz.

[0025] This step provides data support for AI recognition and self-learning, eliminating the need for additional sensors.

[0026] S102. Input the switching parameters into the target model to obtain the jerking level determination result.

[0027] In this embodiment, the target model can be a small AI model. Preferably, the target model can be a trained, improved MobileNet lightweight neural network, with model pruning and 8-bit quantization compression to strictly control the model size to ≤10M, which is suitable for the on-board controller of ordinary hybrid vehicles, such as HCU (Vehicle Control Unit) and VCU (Hybrid Control Unit).

[0028] The jerking level is determined by the following criteria: smooth, slight jerking, moderate jerking, and severe jerking.

[0029] In actual operation, the three types of parameters collected above are input into the deployed AI mini-model in real time, and the model outputs the stuttering status (smooth / slight / moderate / severe) within ≤50ms.

[0030] Specifically, the criteria for judging jerking can be set as follows: longitudinal acceleration fluctuation > 0.2g is a slight jerking, longitudinal acceleration fluctuation > 0.3g is a moderate jerking, and longitudinal acceleration fluctuation > 0.4g is a severe jerking. Combined with torque fluctuation > 30Nm and speed difference > 50r / min for auxiliary judgment, so as to avoid misjudgment.

[0031] S103. Obtain the current operating condition information and determine the cause of the jerking based on the operating condition information, switching parameters, and jerking level determination results.

[0032] For example, operating condition information could include vehicle speed, state of charge (SOC), and ambient temperature. The cause of jerking could be insufficient torque compensation or excessively rapid compensation.

[0033] Specifically, after the AI ​​model identifies the level of jerking, it automatically archives the relevant parameters, operating conditions (vehicle speed, SOC, ambient temperature), and jerking level data of this switch to the vehicle's local storage (with ≥100M of space reserved). At the same time, it automatically removes duplicates and selects valid jerking samples for subsequent MAP fine-tuning.

[0034] Specifically, the AI ​​model analyzes the causes of jerking based on valid jerking samples (such as insufficient torque compensation or excessive compensation) and outputs targeted adjustment instructions.

[0035] The above-mentioned steps of pause recognition and automatic sample labeling replace manual recognition and labeling, solving the problem of "poor consistency of manual labeling".

[0036] S104. Update the torque compensation parameters based on the cause of the jerking, and perform the next hybrid system switch based on the updated torque compensation parameters.

[0037] In this embodiment, the torque compensation parameter can refer to the torque compensation parameter MAP. It is known that the compensation coefficient MAP is typically a multi-dimensional lookup table, where each cell stores a compensation coefficient (such as torque compensation ratio, pressure compensation offset), with the operating parameters as the index axis: MAP[throttle opening][speed difference][oil temperature][driving mode] = compensation coefficient value.

[0038] In practice, during the initial deployment phase, a small amount of manually calibrated baseline MAP (accounting for only 20% of traditional working hours) is input as initial torque compensation parameters. After the hybrid system switch is completed (whether smooth or jerky), MAP fine-tuning is triggered, and the fine-tuned MAP is applied to the next switch.

[0039] This step is the core of self-learning, achieving "smoother and smoother operation".

[0040] This invention, under current operating conditions, when a hybrid system switching request is detected, collects switching parameters via sensors. These parameters include torque fluctuation, speed difference, and longitudinal acceleration. The switching parameters are input into a target model to obtain a jerking level determination result, which includes: smooth operation, slight jerking, moderate jerking, and severe jerking. The current operating condition information is obtained, and the cause of the jerking is determined based on this information, the switching parameters, and the jerking level determination result. The torque compensation parameters are updated based on the cause of the jerking, and the next hybrid system switch is performed based on the updated torque compensation parameters. This invention reduces calibration costs, improves jerking suppression, and continuously optimizes vehicle drivability.

[0041] Optionally, the target model is obtained by iteratively training a neural network model using a target parameter sample set. The target parameter sample set includes: parameter samples under different working conditions and jerking state samples corresponding to the parameter samples; the parameter samples in the target parameter sample set include: torque fluctuation samples, speed difference samples, and longitudinal acceleration samples.

[0042] In actual operation, no less than 100,000 sets of multi-scenario switching data were collected, covering three road conditions: urban congestion, highway cruising, and suburban roads; three environmental temperatures: -10℃, 25℃, and 40℃; and two states: new components and aging components. The data included more than 50,000 sets of jerking samples (longitudinal acceleration fluctuation > 0.2g is considered jerking) and 50,000 sets of smooth samples, forming the target parameter sample set.

[0043] Iteratively training a neural network model using a sample set of target parameters includes: Establish a neural network model.

[0044] In this embodiment, a lightweight model design was implemented: an improved MobileNet lightweight neural network was selected, and the model size was strictly controlled to be ≤10M through model pruning and 8-bit quantization compression, making it compatible with the on-board controller (HCU / VCU) of ordinary hybrid vehicles.

[0045] The parameter samples in the target parameter sample set are input into the neural network model to obtain the predicted stuttering state.

[0046] The predicted jerking state can be the jerking level judgment result predicted by the neural network model based on the parameter samples, such as smooth / slight / moderate / severe jerking.

[0047] In actual operation, three types of parameters, namely torque fluctuation, speed difference, and longitudinal acceleration, are used as inputs to obtain the predicted jerking state.

[0048] Based on the predicted stuttering states and the stuttering state samples corresponding to the parameter samples, the parameters of the neural network model are trained using the cross-entropy loss function.

[0049] Specifically, the sample labels (smooth / slight / moderate / severe stuttering) and the output predicted stuttering state are used for training with the cross-entropy loss function to ensure recognition accuracy ≥98% and response time ≤50ms.

[0050] Return to the operation of inputting parameter samples from the target parameter sample set into the neural network model to obtain the predicted stuttering state, until the target model is obtained.

[0051] Specifically, after the iterative training is completed, the trained model can be deployed to the vehicle controller (such as HCU / VCU) by software burning, occupying ≤10% of computing resources, without affecting the normal operation of other vehicle control systems (power, braking, etc.), thus solving the problem of "AI model cannot adapt to vehicle scenarios".

[0052] Optionally, update the torque compensation parameters based on the cause of the jerking, including: Once the target number of hybrid system switching cycles is detected, the torque compensation parameters are updated based on the cause of the jerking.

[0053] The target quantity can be set based on actual needs or empirical values. When this quantity is met, a torque compensation parameter update operation can be triggered. This embodiment does not limit the specific value of the target quantity and can be dynamically set and adjusted.

[0054] In actual operation, a MAP fine-tuning can be triggered every 10 hybrid system switches (whether smooth or jerky) with a reasonable frequency that does not affect real-time control.

[0055] In addition, you can set the adjustment range to ≤10% each time and set a reasonable range (such as torque compensation slope 20-100Nm / s) to avoid power fluctuations.

[0056] Optionally, after the next hybrid system switch based on the updated torque compensation parameters, the following may also be included: If the level of jerking decreases during the next hybrid system switch, the updated torque compensation parameters will be retained.

[0057] Specifically, the fine-tuned MAP is applied to the next handover, collecting parameters and identifying pauses. If the pause level decreases, the parameters are retained.

[0058] If the level of jerking increases during the next hybrid system switch, the torque compensation parameters will revert to the previous level.

[0059] Specifically, if the level of stuttering increases, it will revert to the previous parameter.

[0060] In this way, a closed loop of "fine-tuning-application-verification-iteration" can be formed.

[0061] Optionally, after determining the cause of the jerking based on the operating condition information, switching parameters, and jerking level judgment results, the following may also be included: The system collects operating condition information, switching parameters, and jerking level determination results to form a large dataset.

[0062] In practice, the vehicle controller can be set to periodically (e.g., once a week, or when there are ≥1000 samples) encrypt and upload effective stuttering samples and self-learning data to the cloud server via the 4G / 5G vehicle networking module to protect data security.

[0063] The target model is optimized based on a large dataset.

[0064] Specifically, samples from multiple vehicles are collected in the cloud to form a large dataset, which is then used to retrain and optimize the AI ​​model (to improve recognition accuracy). At the same time, the initial parameters of the MAP system and the fine-tuning logic are optimized.

[0065] Optionally, the next hybrid system switch can be based on the updated torque compensation parameters, including: The optimized target model and updated torque compensation parameters will be remotely pushed to the vehicle for upgrades in preparation for the next hybrid system switch.

[0066] Specifically, the cloud will push the optimized AI model and MAP parameters to the vehicle remotely via OTA, and the vehicle controller will automatically complete the upgrade (without user operation and without affecting vehicle use), thereby continuously improving the jerking suppression effect.

[0067] This operation can solve the problem of "difficulty in later optimization" and enable continuous technology upgrades.

[0068] In addition, to ensure stable system operation, the operating status of the AI ​​model (e.g., whether the recognition accuracy is ≥95%), sensor data collection (e.g., whether parameters change abruptly), and the rationality of MAP fine-tuning (e.g., whether jerking increases abnormally) can be monitored in real time. If an anomaly is detected, self-learning is immediately paused, switching to initial MAP control, recording the anomaly information and uploading it to the cloud for subsequent troubleshooting and optimization, ensuring driving safety.

[0069] The technical solution of this invention uses a lightweight in-vehicle AI mini-model to collect core parameters at the switching time of the hybrid system in real time, identify jerking states and automatically label samples, fine-tune the compensation coefficient MAP online based on the samples, and combine OTA upgrades to achieve continuous optimization of the AI ​​model and MAP parameters, forming a complete closed loop of "collection-identification-optimization-iteration-upgrade", ultimately achieving improved jerking suppression effect and reduced calibration cost.

[0070] Compared with the prior art, the technical solution of the embodiments of the present invention has the following beneficial effects: 1. Overcoming the inherent defects of manual driving performance calibration: Abandoning the traditional manual driving performance calibration mode, it adopts a vehicle-mounted lightweight AI small model to achieve full automation of jerking recognition, sample labeling, parameter fine-tuning, and iterative optimization without human intervention. This solves the pain points of incomplete coverage of driving performance calibration conditions, poor consistency, and difficulty in later optimization, reducing calibration costs and time while improving calibration efficiency.

[0071] 2. Improved jerking suppression: The lightweight AI model accurately identifies jerking and automatically labels valid samples. The compensation coefficient MAP is switched and iterated every 10 times, forming a closed loop of "collection-identification-optimization-iteration". It dynamically adapts to different working conditions and different component states, avoiding the limitations of fixed MAP. After self-learning, the jerking level is reduced, such as moderate jerking is reduced to slight jerking, and slight jerking is reduced to smoothness, improving the driving smoothness and riding experience of hybrid vehicles.

[0072] 3. High adaptability and low engineering cost: The lightweight AI model has a size of ≤10M, which can be directly embedded into the existing vehicle controller without the need for additional high-performance computing hardware and sensors. It occupies less vehicle computing resources, does not affect the normal operation of other vehicle systems, is easy to be engineered, reduces R&D and production costs, and is compatible with various ordinary hybrid vehicles.

[0073] 4. Achieve continuous evolution and smoother driving: Combined with OTA upgrade function, AI model and compensation coefficient MAP are optimized through cloud big data to achieve long-term improvement of vehicle driving performance. This solves the problem of difficult optimization in the later stage of existing technology. As the vehicle mileage increases and the sample accumulation increases, the jerking suppression effect gradually enhances, meeting the needs of users for long-term use.

[0074] 5. High system stability: A status monitoring and anomaly handling mechanism is set up to monitor the operation status of the AI ​​model, data acquisition, and parameter fine-tuning in real time, and handle abnormal situations in a timely manner to ensure system stability and reliability. At the same time, through compensation coefficient fine-tuning amplitude control and parameter range limitation, power fluctuations during optimization are avoided to ensure driving safety.

[0075] The technical solution of this invention deeply integrates "a lightweight in-vehicle AI model within 10M + online self-learning iteration + OTA continuous evolution" to form a complete closed-loop control, which can reduce calibration costs, improve jerking suppression effect, and continuously optimize vehicle drivability.

[0076] Example 2 Figure 2This is a schematic diagram of a hybrid system switching jerk suppression device according to an embodiment of the present invention. This embodiment is applicable to situations involving hybrid system switching jerk suppression. The device can be implemented using software and / or hardware, and can be integrated into any device that provides hybrid system switching jerk suppression functionality, such as… Figure 2 As shown, the hybrid system switching jerking suppression device specifically includes: a data acquisition module 201, an input module 202, a determination module 203, and an update module 204.

[0077] The acquisition module 201 is used to acquire switching parameters through sensors when a hybrid system switching request is detected under the current operating conditions; the switching parameters include: torque fluctuation, speed difference and longitudinal acceleration. Input module 202 is used to input the switching parameters into the target model to obtain the jerking level determination result; the jerking level determination result includes: smooth state, slight jerking, moderate jerking and severe jerking; The determination module 203 is used to obtain the current working condition information and determine the cause of the jerking based on the working condition information, the switching parameters and the jerking level determination result; The update module 204 is used to update the torque compensation parameters based on the cause of the jerking, and to perform the next hybrid system switch based on the updated torque compensation parameters.

[0078] Optionally, the target model is obtained by iteratively training a neural network model using a target parameter sample set, which includes: parameter samples under different operating conditions and jerking state samples corresponding to the parameter samples; the parameter samples in the target parameter sample set include: torque fluctuation samples, speed difference samples, and longitudinal acceleration samples. Iteratively training a neural network model using a sample set of target parameters includes: Establish a neural network model; The parameter samples in the target parameter sample set are input into the neural network model to obtain the predicted stuttering state; Based on the predicted stuttering state and the stuttering state samples corresponding to the parameter samples, the parameters of the neural network model are trained using the cross-entropy loss function; Return to the operation of inputting parameter samples from the target parameter sample set into the neural network model to obtain the predicted stuttering state, until the target model is obtained.

[0079] Optionally, the update module 204 is specifically used for: Once a hybrid system switching is detected after completing a target number of times, the torque compensation parameters are updated based on the cause of the jerking.

[0080] Optionally, the device is further specifically used for: If the level of jerking decreases during the next hybrid system switch, the updated torque compensation parameters will be retained. If the level of jerking increases during the next hybrid system switch, the torque compensation parameters will revert to the previous level.

[0081] Optionally, the device is further specifically used for: The operating condition information, the switching parameters, and the jerking level determination results are collected to form a large dataset; The target model is optimized based on the large dataset.

[0082] Optionally, the update module 204 is specifically used for: The optimized target model and updated torque compensation parameters will be remotely pushed to the vehicle for upgrades in preparation for the next hybrid system switch.

[0083] The above-mentioned products can perform the hybrid system switching jerking suppression method provided in any embodiment of the present invention, and have the corresponding functional modules and beneficial effects of the method.

[0084] Example 3 Figure 3 A schematic diagram of an electronic device 30 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0085] like Figure 3 As shown, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 or a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0086] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0087] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 31 performs the various methods and processes described above, such as the hybrid system switching jerk suppression method: Under the current operating conditions, when a hybrid system switching request is detected, switching parameters are collected by sensors; the switching parameters include: torque fluctuation, speed difference, and longitudinal acceleration; The switching parameters are input into the target model to obtain the jerking level determination result; the jerking level determination result includes: smooth state, slight jerking, moderate jerking and severe jerking; Obtain the current operating condition information, and determine the cause of the jerking based on the operating condition information, the switching parameters, and the jerking level determination result; The torque compensation parameters are updated based on the cause of the jerking, and the next hybrid system switch is performed based on the updated torque compensation parameters.

[0088] In some embodiments, the hybrid system handover jerking suppression method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the hybrid system handover jerking suppression method described above may be performed. Alternatively, in other embodiments, processor 31 may be configured to perform the hybrid system handover jerking suppression method by any other suitable means (e.g., by means of firmware).

[0089] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0090] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0091] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0092] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0093] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0094] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0095] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the hybrid system switching jerking suppression method of any embodiment of the present invention.

[0096] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0098] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A hybrid system switching jerk suppression method, characterized by, include: Under the current operating conditions, when a hybrid system switching request is detected, switching parameters are collected through sensors; The switching parameters include: torque fluctuation, speed difference, and longitudinal acceleration; The switching parameters are input into the target model to obtain the jerking level determination result; the jerking level determination result includes: smooth state, slight jerking, moderate jerking and severe jerking; Obtain the current operating condition information, and determine the cause of the jerking based on the operating condition information, the switching parameters, and the jerking level determination result; The torque compensation parameters are updated based on the cause of the jerking, and the next hybrid system switch is performed based on the updated torque compensation parameters.

2. The method of claim 1, wherein, The target model is obtained by iteratively training a neural network model using a target parameter sample set. The target parameter sample set includes: parameter samples under different working conditions and jerking state samples corresponding to the parameter samples; the parameter samples in the target parameter sample set include: torque fluctuation samples, speed difference samples, and longitudinal acceleration samples. Iteratively training a neural network model using a sample set of target parameters includes: Establish a neural network model; The parameter samples in the target parameter sample set are input into the neural network model to obtain the predicted stuttering state; Based on the predicted stuttering state and the stuttering state samples corresponding to the parameter samples, the parameters of the neural network model are trained using the cross-entropy loss function; Return to the operation of inputting parameter samples from the target parameter sample set into the neural network model to obtain the predicted stuttering state, until the target model is obtained.

3. The method of claim 1, wherein, The torque compensation parameters are updated based on the cause of the jerking, including: Once a hybrid system switching is detected after completing a target number of times, the torque compensation parameters are updated based on the cause of the jerking.

4. The method of claim 1, wherein, Following the next hybrid system switch based on the updated torque compensation parameters, the following will also be included: If the level of jerking decreases during the next hybrid system switch, the updated torque compensation parameters will be retained. If the level of jerking increases during the next hybrid system switch, the torque compensation parameters will revert to the previous level.

5. The method of claim 1, wherein, After determining the cause of the jerking based on the operating condition information, the switching parameters, and the jerking level determination result, the method further includes: The operating condition information, the switching parameters, and the jerking level determination results are collected to form a large dataset; The target model is optimized based on the large dataset.

6. The method of claim 5, wherein, The next hybrid system switch will be based on the updated torque compensation parameters, including: The optimized target model and updated torque compensation parameters will be remotely pushed to the vehicle for upgrades in preparation for the next hybrid system switch.

7. A hybrid system switching jerking suppression device, characterized in that, include: The data acquisition module is used to collect switching parameters through sensors when a hybrid system switching request is detected under the current operating conditions. The switching parameters include: torque fluctuation, speed difference, and longitudinal acceleration; The input module is used to input the switching parameters into the target model to obtain the jerking level determination result; the jerking level determination result includes: smooth state, slight jerking, moderate jerking and severe jerking; The determination module is used to obtain the current working condition information and determine the cause of the jerking based on the working condition information, the switching parameters, and the jerking level determination result. The update module is used to update the torque compensation parameters based on the cause of the jerking, and to perform the next hybrid system switch based on the updated torque compensation parameters.

8. An electronic device, comprising: The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the hybrid system switching jerking suppression method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the hybrid system switching jerking suppression method according to any one of claims 1-6.

10. A computer program product, characterised in that, It includes a computer program that, when executed by a processor, implements the hybrid system switching jerking suppression method according to any one of claims 1-6.

Images