Control method, system and equipment of vehicle active suspension and medium

Abstract

The invention provides a control method, system and device for a vehicle active suspension and a medium, and the method comprises the steps: obtaining a plurality of control targets, and obtaining the vehicle state data of a target vehicle in the current driving process of the target vehicle; inputting the vehicle state data into a state prediction model for state prediction to obtain predicted state data output by the state prediction model and space-time state features corresponding to the vehicle state data; according to the space-time state characteristics, performing priority distribution on all the control targets to obtain a control priority of each control target; and controlling the active suspension of the target vehicle according to the predicted state data and the control priority of each control target. According to the method, the control effect of the vehicle active suspension can be effectively improved, and user experience is improved. The invention relates to the technical field of vehicles.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a control method, system, device and medium for an active vehicle suspension. Background Technology

[0002] With the development of vehicle technology, active suspension control has received much attention from relevant personnel because it can balance the comfort and handling stability of the vehicle during driving.

[0003] Currently, related technologies typically rely on PID control or rule-based control strategies to control active suspension. However, this approach is ineffective when faced with complex and varied road conditions and vehicle dynamic responses, making it difficult to balance vehicle comfort and handling stability during driving, resulting in an unsatisfactory user experience.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0005] The purpose of this invention is to at least partially solve one of the technical problems existing in the related art.

[0006] The main objective of this application is to provide a control method, system, device, and medium for vehicle active suspension, wherein the method can effectively improve the control effect of vehicle active suspension and enhance user experience.

[0007] To achieve the above objectives, one aspect of this application proposes a control method for an active vehicle suspension, comprising: Acquire several control targets, and acquire vehicle status data of the target vehicles during their current driving process; The vehicle state data is input into the state prediction model for state prediction, and the predicted state data and spatiotemporal state features corresponding to the vehicle state data are obtained from the output of the state prediction model. Based on the spatiotemporal state characteristics, priority is assigned to all the control targets to obtain the control priority of each control target; The active suspension of the target vehicle is controlled based on the predicted state data and the control priority of each control target.

[0008] In addition, the vehicle active suspension control method according to the above embodiments of this application may also have the following additional technical features: In some embodiments, obtaining vehicle status data of the target vehicle includes: Acquire raw sensor data collected by several sensors of the target vehicle; Outlier removal is performed on the original sensing data to obtain intermediate sensing data; The intermediate sensor data is standardized to obtain the vehicle status data.

[0009] In some embodiments, the method further includes: Fault detection is performed on the first target sensor to obtain the fault detection result. The first target sensor is any one of all sensors in the target vehicle. If the fault detection result is that the first target sensor is faulty, then the raw sensing data of several second target sensors are acquired. The second target sensors are the sensors that are associated with the first target sensor among all the sensors of the target vehicle. Based on the raw sensor data of all the second target sensors, interpolation compensation is performed to obtain the raw sensing data of the first target sensor.

[0010] In some embodiments, the step of inputting the vehicle state data into a state prediction model for state prediction, and obtaining the predicted state data output by the state prediction model and the spatiotemporal state features corresponding to the vehicle state data, includes: Obtain historical state sequences that are adjacent to the vehicle state data; Spatial features are extracted from the vehicle state data to obtain spatial state features; The predicted state data is obtained by performing temporal state prediction on the spatial state features and the historical state sequence. Based on the predicted state data, feature fusion is performed on the spatial state features to obtain the spatiotemporal state features.

[0011] In some embodiments, the step of prioritizing all the control objectives based on the spatiotemporal state characteristics to obtain the control priority of each control objective includes: Obtain the priority strategy table, which records several driving conditions and a priority array corresponding to each driving condition; The spatiotemporal state characteristics are analyzed to obtain the target operating condition, which is used to characterize the driving condition of the target vehicle in the current driving process. Based on the target operating condition, the priority strategy table is matched to obtain a target array; the target array is the priority array corresponding to the driving conditions that match the target operating condition among all the priority arrays; Based on the target array, determine the control priority of each control target.

[0012] In some embodiments, controlling the active suspension of the target vehicle based on the predicted state data and the control priority of each control target includes: Based on the predicted state data, obtain the intermediate control strategy for each of the control targets; Based on the control priority of each control objective, all the intermediate control strategies are fused to determine the target control strategy for the target vehicle during the current driving process; The active suspension of the target vehicle is controlled according to the target control strategy.

[0013] In some embodiments, the method further includes: Obtain vehicle response data of the target vehicle, wherein the vehicle response data is used to characterize the vehicle state data of the target vehicle's active suspension after the target control strategy is executed; Based on the predicted state data, a state loss analysis is performed on the predicted state data to obtain the state loss value; Based on the state loss value, the parameters of the state prediction model are updated to obtain the updated state prediction model.

[0014] To achieve the above objectives, another aspect of this application proposes a control system for an active vehicle suspension, comprising: The first processing unit is used to acquire several control targets and acquire vehicle status data of the target vehicle during the current driving process of the target vehicle. The second processing unit is used to input the vehicle state data into the state prediction model for state prediction, and obtain the predicted state data output by the state prediction model and the spatiotemporal state features corresponding to the vehicle state data. The third processing unit is used to assign priority to all the control targets according to the spatiotemporal state characteristics, and obtain the control priority of each control target; The fourth processing unit is used to control the active suspension of the target vehicle based on the predicted state data and the control priority of each control target.

[0015] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned auxiliary control method.

[0016] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned auxiliary control method.

[0017] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program stored in a computer-readable storage medium. The processor of an electronic device reads the computer program from the computer-readable storage medium and executes the computer program, causing the electronic device to perform the method described above.

[0018] The embodiments of this application include at least the following beneficial effects: This application provides a method, system, device, and medium for controlling an active suspension system for a vehicle. The method includes acquiring several control targets and obtaining vehicle state data of the target vehicle during its current driving process; inputting the vehicle state data into a state prediction model for state prediction, obtaining predicted state data output by the state prediction model and spatiotemporal state features corresponding to the vehicle state data; prioritizing all the control targets according to the spatiotemporal state features to obtain a control priority for each control target; and controlling the active suspension of the target vehicle according to the predicted state data and the control priority of each control target. This method prioritizes the vehicle based on the spatiotemporal state features output by the current state prediction model and controls the suspension of the target vehicle based on the predicted state data of the target vehicle in future time periods and the control priority of each control target. It can effectively improve the performance of active suspension control when facing complex and varied road surface excitations and vehicle dynamic responses, thereby enhancing the user experience. Attached Figure Description

[0019] Figure 1 This is a flowchart of a vehicle active suspension control method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating how to acquire vehicle status data, as provided in an embodiment of this application. Figure 3 This is an optional flowchart of a vehicle active suspension control method provided in an embodiment of this application; Figure 4 This is a detailed flowchart of step S120 provided in an embodiment of this application; Figure 5 This is a simplified network framework diagram of a state prediction model provided in an embodiment of this application; Figure 6 This is a detailed flowchart of step S130 provided in an embodiment of this application; Figure 7 This is a detailed flowchart of step S140 provided in an embodiment of this application; Figure 8This is another optional flowchart of a vehicle active suspension control method provided in the embodiments of this application; Figure 9 This is a schematic diagram of the structure of a vehicle active suspension control system provided in an embodiment of this application; Figure 10 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] This application will be further described in detail below. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this application; they are merely examples of apparatuses / devices and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0021] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0022] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0024] Currently, related technologies typically rely on PID control or rule-based control strategies to control active suspension. However, this approach is ineffective when faced with complex and varied road conditions and vehicle dynamic responses. In particular, it lacks control precision under nonlinear and time-varying conditions, making it difficult to balance vehicle comfort and handling stability during driving, resulting in an unsatisfactory user experience.

[0025] Furthermore, some related technologies rely on precise mathematical models to control active suspension. However, in practical applications, due to numerous uncertainties during vehicle operation (such as random road disturbances, vehicle load changes, and aging of vehicle parts), this approach suffers from lag in the control response of the active suspension, poor adaptability to various driving scenarios, and consequently, poor control performance of the vehicle's active suspension, resulting in an unsatisfactory user experience.

[0026] It should be noted that the aforementioned related technologies are only used to assist in understanding the technical solutions of this application and do not mean that they belong to the publicly disclosed prior art.

[0027] In view of this, this application provides a method, system, device and medium for controlling an active vehicle suspension. The method prioritizes the spatiotemporal state features output by the current state prediction model and controls the suspension of the target vehicle based on the predicted state data of the target vehicle in the future time period and the control priority of each control target. This can effectively improve the effect of active suspension control when facing complex and changing road excitations and vehicle dynamic responses, so as to better balance the comfort and handling stability of the vehicle during driving and improve the user experience.

[0028] Furthermore, this method uses a model to predict future state data and controls the suspension of the target vehicle based on this data. This allows for more timely control of the vehicle's active suspension, effectively improving the adaptability of the vehicle's suspension control in various driving scenarios, thereby enhancing the control effect of the vehicle's active suspension and improving the user experience.

[0029] The method provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited thereto; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application implementing the method, but is not limited to the above forms.

[0030] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0031] Figure 1 This is an optional flowchart of a vehicle active suspension control method provided in an embodiment of this application. Figure 1 The method may include, but is not limited to, steps S110 to S140.

[0032] Step S110: Obtain several control targets and acquire the vehicle status data of the target vehicle during the current driving process of the target vehicle; In this embodiment, the active suspension can be the vehicle's active suspension system. The control objective can be the comfort, handling stability, ride smoothness, etc., of the target vehicle during the current driving process. For ease of understanding, this embodiment uses two control objectives, namely comfort and handling stability, as an example. The vehicle status data can be the real-time status data of the target vehicle during the current driving process, specifically including the target vehicle's speed information, acceleration information, vehicle height information, and wheel speed information of each wheel.

[0033] Reference Figure 2 In some embodiments, obtaining the vehicle status data of the target vehicle includes: Step S210: Obtain the raw sensing data collected by several sensors of the target vehicle; Step S220: Remove outliers from the original sensing data to obtain intermediate sensing data; Step S230: Standardize the intermediate sensor data to obtain the vehicle status data.

[0034] In this embodiment, raw sensing data collected by various sensors of the target vehicle can be acquired. This raw sensing data can be vehicle wheel speed collected by wheel speed sensors, vehicle acceleration collected by acceleration sensors, suspension extension / retraction speed data collected by suspension sensors, etc. For ease of understanding, this embodiment takes one piece of raw sensing data as an example; the case where the number of raw sensing data is greater than or equal to two can be easily deduced. Specifically, outlier removal can be performed by removing outliers from the raw sensing data, such as removing outliers from the vehicle acceleration at various time points, thereby obtaining raw sensing data (i.e., intermediate sensing data) after outlier removal.

[0035] It is understandable that there are already various ways to implement outlier removal. For example, the three sigma (3σ) principle can be used to process each specific data in the original sensor data. This application does not impose any restrictions on the specific method of outlier removal. Standardization processing can be performed by applying Kalman filtering to the intermediate sensor data and then standardizing the intermediate sensor data after Kalman filtering. There are already various standardization methods, such as min-max scaling and Z-score standardization, which will not be elaborated on here.

[0036] Reference Figure 3 In some embodiments, the method further includes: Step S310: Perform fault detection on the first target sensor and obtain the fault detection result. The first target sensor is any one of all sensors in the target vehicle. Step S320: If the fault detection result is that the first target sensor is faulty, then acquire the original sensing data of several second target sensors, wherein the second target sensors are the sensors of the target vehicle that are associated with the first target sensor. Step S330: Based on the original sensor data of all the second target sensors, perform interpolation compensation processing to obtain the original sensing data of the first target sensor.

[0037] In this embodiment, the first target sensor can be any one of all sensors related to active suspension control in the target vehicle. Fault detection can be performed to detect whether the first target sensor has malfunctioned. There are various methods for specific sensor fault detection. For example, it can determine whether the first target sensor has normal data output and generate a fault detection result indicating that the first target sensor is malfunctioning when the first target sensor does not have normal data output; or, it can generate a fault detection result indicating that the first target sensor is normal when the first target sensor has normal data output, in which case the process can return to step S310.

[0038] Understandably, when the fault detection result indicates a fault in the first target sensor, raw sensing data from several second target sensors can be acquired. These second target sensors can be any of the other sensors associated with the first target sensor among all sensors related to active suspension control. For example, if the faulty first target sensor is a speed sensor, its corresponding second target sensor can be a wheel speed sensor used to collect vehicle wheel speeds. The raw sensing data from the first target sensor can be obtained by interpolation based on the vehicle wheel speeds collected by the second target sensors and the circumference of each vehicle, to obtain an estimated vehicle speed. This estimated vehicle speed is then used as the raw sensing data of the faulty speed sensor.

[0039] It should be noted that, in this embodiment of the application, the original sensor data of the faulty first target sensor is interpolated and compensated using the original sensor data of the second target sensor. This ensures that the target vehicle can collect as comprehensive a vehicle status data as possible, so that the execution logic of subsequent steps is not interrupted, thereby improving the robustness of the vehicle's active suspension control.

[0040] Step S120: Input the vehicle state data into the state prediction model to perform state prediction, and obtain the predicted state data output by the state prediction model and the spatiotemporal state features corresponding to the vehicle state data. In this embodiment, the state prediction model can be a hybrid model of convolutional neural network-long short-term memory network (CNN-LSTM). Step S120 can be to input vehicle state data into the current state prediction model, and use the current state prediction model to predict the state of the vehicle at the current moment, thereby obtaining the predicted state data of the target vehicle at future moments, as well as the spatiotemporal state characteristics of the target vehicle at the current moment.

[0041] Reference Figure 4 and Figure 5In some embodiments, step S120, inputting the vehicle state data into a state prediction model for state prediction to obtain predicted state data output by the state prediction model and spatiotemporal state features corresponding to the vehicle state data, includes: Step S410: Obtain the historical state sequence adjacent to the vehicle state data; Step S420: Extract spatial features from the vehicle state data to obtain spatial state features; Step S430: Perform time-series state prediction on the spatial state features and the historical state sequence to obtain the predicted state data; Step S440: Based on the predicted state data, perform feature fusion on the spatial state features to obtain the spatiotemporal state features.

[0042] In this embodiment, the historical state sequence can be a set of historical vehicle state data or historical spatial state features that are adjacent to the vehicle state data on the time axis. Taking the historical state sequence as a set of historical wheel state data as an example, if the current vehicle state data of the target vehicle is the vehicle state data at time point t, then the historical state sequence can be the vehicle state data before time point t, such as the vehicle state data at time point t-1 or the vehicle state data at time point t-2. The content of the historical state sequence as a set of historical spatial states is similar to the content of the aforementioned historical state sequence as a set of historical wheel state data, and can be easily deduced by analogy.

[0043] It is understandable that spatial feature extraction can be achieved by using the CNN feature extraction subnetwork in the state prediction model to extract deep spatial features (such as the complex patterns of the target vehicle's speed and attitude) from the data of various sensors in the vehicle state data, thereby obtaining spatial state features. Temporal state prediction can be achieved by inputting the spatial state features and historical state sequences into the LSTM prediction subnetwork in the state prediction model. The LSTM prediction subnetwork learns the temporal dynamics of the target vehicle during driving and predicts the state of the target vehicle at future times (i.e., predicted state data) based on the learned temporal dynamics. This state can specifically be the vehicle state data of the target vehicle at future times or the spatial state features of the target vehicle at future times.

[0044] It is worth mentioning that feature fusion can be the fusion of predicted state data and spatial state features. There are various specific fusion methods, such as concatenation, element-wise addition, element-wise multiplication, and attention-based feature fusion, to obtain spatiotemporal state features, which are used to indicate the environment and vehicle state of the target vehicle.

[0045] Step S130: Based on the spatiotemporal state characteristics, prioritize all the control targets to obtain the control priority of each control target; In this embodiment of the application, priority allocation can be based on spatiotemporal state characteristics, assigning a control priority to each control objective (such as comfort or operational stability) to obtain the control priority of each control objective.

[0046] Reference Figure 6 In some embodiments, step S130, prioritizing all control targets according to the spatiotemporal state characteristics to obtain the control priority of each control target, includes: Step S610: Obtain a priority strategy table, which records several driving conditions and a priority array corresponding to each driving condition. Step S620: Perform state analysis on the spatiotemporal state features to obtain the target operating condition, which is used to characterize the driving condition of the target vehicle in the current driving process; Step S630: According to the target working condition, perform working condition matching on the priority strategy table to obtain a target array; the target array is the priority array corresponding to the driving working condition that matches the target working condition among all the priority arrays; Step S640: Determine the control priority of each control target based on the target array.

[0047] In this embodiment, the priority strategy table records several driving conditions and a priority array for each driving condition. The priority array records the control priority of each control objective in the corresponding driving condition. Specifically, for ease of understanding, this embodiment takes an example where the priority strategy table includes two driving conditions: smooth cruise and turning / lane changing, and the control objectives include comfort and handling stability. In the smooth cruise driving condition, the control priority of the comfort control objective may be greater than the control priority of the handling stability control objective; and in the turning / lane changing driving condition, the control priority of the comfort control objective may be less than the control priority of the handling stability control objective.

[0048] Understandably, in practical applications, the number of driving conditions and control objectives is often greater than or equal to two. For example, driving conditions may include braking / acceleration and bumpy / rough conditions; control objectives may include ride comfort, etc. For any given driving condition, the control priority of each control objective can be deduced by analogy with the aforementioned examples and actual needs. For instance, for the braking / acceleration driving condition, the control priority of ride comfort might be greater than that of comfort, and the control priority of comfort might be greater than that of handling stability.

[0049] It should be noted that state analysis can involve inputting the spatiotemporal state features output by the state prediction model into an output layer for condition classification and prediction. This output layer can specifically include several fully connected layers and activation function layers (such as a Softmax activation function layer) to obtain the driving condition of the target vehicle during the current driving process, denoted as the target condition. Condition matching can be based on the target condition, matching each driving condition in the priority strategy table, and determining the priority array of the target condition based on the driving conditions that successfully match the target condition, denoted as the target array; then, based on the records in the target array, the control priority of each control objective is determined.

[0050] Step S140: Control the active suspension of the target vehicle according to the predicted state data and the control priority of each control target.

[0051] In this embodiment, the suspension height, shape, damping and other parameters of the active suspension of the target vehicle can be adjusted and controlled according to the predicted state data of the target vehicle at a future time and the control priority of each control target, so as to achieve a balance between the comfort and handling stability of the vehicle during driving, and improve the control effect of the vehicle's dynamic suspension and the user experience.

[0052] Reference Figure 7 In some embodiments, step S140, controlling the active suspension of the target vehicle based on the predicted state data and the control priority of each control target, includes: Step S710: Obtain the intermediate control strategy for each control target based on the predicted state data; Step S720: Based on the control priority of each control target, perform strategy fusion on all the intermediate control strategies to determine the target control strategy of the target vehicle in the current driving process; Step S730: Control the active suspension of the target vehicle according to the target control strategy.

[0053] In this embodiment, a corresponding control algorithm can be assigned to each control objective, and the predicted state data can be input into each control algorithm for calculation to obtain the intermediate control strategy for each control objective. For example, taking comfort and handling stability as examples, the control algorithm corresponding to handling stability can be a groundhook control algorithm, which aims to control the relative speed of the vehicle body relative to the ground, thereby improving vehicle handling stability; while the control algorithm corresponding to comfort can be a skyhook control algorithm, which aims to suppress the absolute vertical speed of the vehicle, thereby improving vehicle comfort.

[0054] Understandably, for the intermediate control strategy of the control objective of handling stability, the suspension extension / retraction speed data and vehicle acceleration data of the target vehicle at future time can be obtained based on the predicted state data; then the suspension extension / retraction speed data and vehicle acceleration data at the future time can be determined as the input data of the floor control algorithm and calculated, thereby determining the intermediate control strategy of the control objective of handling stability.

[0055] The intermediate control strategy for achieving the control objective of comfort can be based on predicted state data to obtain vehicle speed and acceleration data for the target vehicle at future moments; then, the vehicle speed and acceleration data at these future moments are used as input data for the ceiling control algorithm and calculated to determine the intermediate control strategy for achieving the control objective of comfort.

[0056] It should be noted that strategy fusion can be based on the control priority of each control objective, dynamically assigning a dynamic weight to the intermediate control strategies for each control objective, with the dynamic weight of each intermediate control strategy being positively correlated with the control priority of the corresponding control objective; and then, based on the dynamic weight of each intermediate control strategy, weighted fusion of all intermediate control strategies is performed to obtain the target control strategy; finally, the target control strategy is executed by controlling the active suspension of the target vehicle to achieve active suspension control of the target vehicle. For example, in this embodiment, taking the control priority of comfort as a control objective as greater than the control priority of handling stability as a control objective, the target control strategy can be expressed as:

[0057] in, For target control strategy; An intermediate control strategy for achieving the control objective of comfort; For intermediate control strategy The dynamic weight can have a specific value of 0.7; An intermediate control strategy for manipulating stability as the control objective; For intermediate control strategy The dynamic weight can be 0.3.

[0058] Reference Figure 8 In some embodiments, the method further includes: Step S810: Obtain vehicle response data of the target vehicle, wherein the vehicle response data is used to characterize the vehicle state data of the active suspension of the target vehicle after the target control strategy is executed; Step S820: Based on the predicted state data, perform state loss analysis on the predicted state data to obtain the state loss value; Step S830: Update the parameters of the state prediction model according to the state loss value to obtain the updated state prediction model.

[0059] In this embodiment, after the active suspension of the target vehicle executes the target control strategy, corresponding vehicle data can be acquired. The degree of difference between the actual vehicle response data and the predicted state data output by the model is analyzed. Specifically, a loss function is used to calculate the loss value corresponding to the predicted state data and the vehicle response data, denoted as the state loss value. Various loss functions are commonly used, such as 0-1 loss function, squared loss function, absolute loss function, logarithmic loss function, and cross-entropy loss function, which will not be elaborated upon here. In this embodiment, any one of these loss functions can be selected to determine the training loss value, such as the squared loss function. Based on the calculated state loss value, the parameters of the current state prediction model are updated using a backpropagation algorithm to obtain an updated predicted state model, which is then used in the next active suspension control process.

[0060] Please see Figure 9 This application also provides a control system for a vehicle active suspension, which can implement the above-described vehicle active suspension control method. The system includes: The first processing unit 901 is used to acquire a number of control targets and acquire vehicle status data of the target vehicle during the current driving process of the target vehicle. The second processing unit 902 is used to input the vehicle state data into the state prediction model to perform state prediction, and obtain the predicted state data output by the state prediction model and the spatiotemporal state features corresponding to the vehicle state data. The third processing unit 903 is used to assign priority to all the control targets according to the spatiotemporal state characteristics, and obtain the control priority of each control target; The fourth processing unit 904 is used to control the active suspension of the target vehicle according to the predicted state data and the control priority of each control target.

[0061] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0062] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0063] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0064] Please see Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 1001 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 1002 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called and executed by the processor 1001. Input / output interface 1003 is used to implement information input and output; The communication interface 1004 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 1005 transmits information between various components of the device (e.g., processor 1001, memory 1002, input / output interface 1003, and communication interface 1004); The processor 1001, memory 1002, input / output interface 1003 and communication interface 1004 are connected to each other within the device via bus 1005.

[0065] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0066] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0067] This application also discloses a computer program product or computer program, which includes computer instructions stored in the aforementioned computer-readable storage medium; the processor of the aforementioned electronic device can read the computer instructions from the aforementioned computer-readable storage medium, and the processor executes the computer instructions, causing the electronic device to perform the aforementioned method embodiment.

[0068] It is understood that the content of the above method embodiments is applicable to this computer program product or computer program embodiment. The specific functions implemented by this computer program product or computer program embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0069] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0070] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0071] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0072] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0073] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0074] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application 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 this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, 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.

[0075] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0077] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0079] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A control method of a vehicle active suspension, characterized by, The method comprises the following steps: obtaining a plurality of control targets and obtaining vehicle state data of the target vehicle in the current driving process of the target vehicle; inputting the vehicle state data into a state prediction model for state prediction to obtain predicted state data output by the state prediction model and space-time state features corresponding to the vehicle state data; according to the space-time state features, assigning priorities to all the control targets to obtain a control priority of each control target; controlling the active suspension of the target vehicle according to the predicted state data and the control priority of each control target.

2. The method of claim 1, wherein, The method further comprises the following steps: obtaining vehicle state data of the target vehicle, comprising: obtaining original sensor data collected by a plurality of sensors of the target vehicle; performing outlier rejection on the original sensor data to obtain intermediate sensor data; 3. The method of claim 2, wherein, performing standardization processing on the intermediate sensor data to obtain the vehicle state data. The method further comprises the following steps: performing fault detection on a first target sensor to obtain a fault detection result, the first target sensor being any one of all sensors of the target vehicle; if the fault detection result indicates that the first target sensor is faulty, obtaining original sensor data of a plurality of second target sensors, the second target sensors being sensors of the target vehicle that are associated with the first target sensor; 4. The method of claim 1, wherein, performing interpolation compensation processing on the original sensor data of all the second target sensors to obtain the original sensor data of the first target sensor. The method further comprises the following steps: obtaining a historical state sequence adjacent to the vehicle state data; performing spatial feature extraction on the vehicle state data to obtain spatial state features; performing time series state prediction on the spatial state features and the historical state sequence to obtain the predicted state data; 5. The method of claim 1, wherein, performing feature fusion on the spatial state features according to the predicted state data to obtain the space-time state features. The method further comprises the following steps: obtaining a priority strategy table, the priority strategy table recording a plurality of driving conditions and a priority array corresponding to each driving condition; performing state analysis on the space-time state features to obtain a target condition, the target condition being used to represent a driving condition of the target vehicle in the current driving process; performing condition matching on the priority strategy table according to the target condition to obtain a target array, the target array being a priority array corresponding to a driving condition matching the target condition in all the priority arrays; 6. The method of any one of claims 1, wherein, determining the control priority of each control target according to the target array. The method further comprises the following steps: According to the predicted state data, an intermediate control strategy of each control target is obtained; According to the control priority of each control target, the intermediate control strategies are fused to determine a target control strategy of the target vehicle in the current driving process; According to the target control strategy, the active suspension of the target vehicle is controlled.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: Obtaining vehicle response data of the target vehicle, the vehicle response data being used to represent vehicle state data of the active suspension of the target vehicle after the target control strategy is executed; According to the predicted state data, state loss analysis is performed on the predicted state data to obtain a state loss value; According to the state loss value, parameter updating is performed on the state prediction model to obtain an updated state prediction model.

8. A control system for a vehicle active suspension, characterised in that, Comprise: A first processing unit is configured to obtain a plurality of control targets and obtain vehicle state data of a target vehicle in a current driving process of the target vehicle; A second processing unit is configured to input the vehicle state data into a state prediction model for state prediction to obtain predicted state data output by the state prediction model and space-time state features corresponding to the vehicle state data; A third processing unit is configured to assign a priority to all the control targets according to the space-time state features to obtain a control priority of each control target; A fourth processing unit is configured to control an active suspension of the target vehicle according to the predicted state data and the control priority of each control target.

9. An electronic device, comprising: Comprise: At least one processor; At least one memory configured to store at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. The computer program is executed by the processor to implement the method of any one of claims 1 to 7.

Images