Control method and apparatus, vehicle, and computer-readable storage medium

Abstract

The present disclosure relates to a control method and apparatus, a vehicle, and a computer-readable storage medium, relating to the technical field of vehicle control. The control method comprises: according to dynamic parameters of an engineering machinery vehicle at a first time point, using a machine learning model to determine a predicted value of an operational accuracy deviation of the engineering machinery vehicle at a next time point of the first time point; according to the predicted value of the operational accuracy deviation, determining an allocated power of each system among a plurality of systems of the engineering machinery vehicle; and according to the allocated powers, controlling the engineering machinery vehicle to operate within a future time period starting from the first time point.

Description

Control methods, devices, vehicles, and computer-readable storage media

[0001] Cross-references to related applications

[0002] This application is based on and claims priority to CN application No. 202511735402.0, filed on November 24, 2025, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to the field of vehicle control technology, and in particular to a control method, control device, vehicle, computer-readable storage medium, and computer program product. Background Technology

[0004] The power distribution scheme among the various systems of construction machinery vehicles determines their operating efficiency, energy utilization, and operational precision. Taking agricultural machinery vehicles as an example, the PTO (Power Take Off) system undertakes the core function of driving implements and other operating mechanisms. The driving system is responsible for ensuring the stable movement of the agricultural machinery vehicle, and the degree of coordination between the two affects the efficiency and quality of agricultural operations.

[0005] In related technologies, the power distribution between the PTO system and the driving system is determined solely based on power demand. Summary of the Invention

[0006] According to some embodiments of this disclosure, a control method is provided, comprising: determining, using a machine learning model, a predicted value of the operational accuracy deviation of the construction machinery vehicle at a next time point based on the dynamic parameters of the construction machinery vehicle at a first time point; determining the allocated power of each of the multiple systems of the construction machinery vehicle based on the predicted value of the operational accuracy deviation; and controlling the construction machinery vehicle to perform operations in a future time period starting from the first time point based on the allocated power.

[0007] In some embodiments, the allocation ratio of each system is determined based on the risk level corresponding to the predicted value; the allocation power is determined based on the allocation ratio and the output power of the construction machinery vehicle.

[0008] In some embodiments, the multiple systems include a driving system and a power output system for outputting power to the working mechanism of the construction machinery vehicle. A risk level is determined based on the prediction accuracy risk value corresponding to the predicted value. Based on the risk level, a first allocation ratio for the driving system and a second allocation ratio for the power output system are determined.

[0009] In some embodiments, the first allocation ratio is positively correlated with the risk level, and the second allocation ratio is negatively correlated with the risk level.

[0010] In some embodiments, a control strategy for the working mechanism of the construction machinery vehicle is determined based on the risk level; and the construction machinery vehicle is controlled to perform operations according to the control strategy based on the allocated power.

[0011] In some embodiments, the risk level includes a first risk level and a second risk level, the first risk level is greater than the second risk level, and the prediction accuracy risk value corresponding to the second risk level is greater than a first deviation threshold. In response to the risk level being the first risk level, the auxiliary working mechanism of the construction machinery vehicle is used to compensate for the working accuracy deviation of the construction machinery vehicle; in response to the risk level being the second risk level, the working parameters of the working mechanism are adjusted.

[0012] In some embodiments, a power supply strategy is selected based on the relationship between the allocated power and the required power, wherein the required power is determined based on the dynamic parameters of each system; and the engineering machinery vehicle is controlled to operate in the future time period according to the power supply strategy.

[0013] In some embodiments, the dynamic parameters include the driving speed of the construction machinery vehicle; in response to a first distribution power of the driving system being less than a first demand power of the driving system and a second distribution power of the power output system being greater than the second demand power of the power output system, the first distribution power is determined as the target power of the driving system and the second demand power is determined as the target power of the power output system; the driving speed of the construction machinery vehicle is adjusted to reduce the first demand power of the driving system such that the reduced first demand power is not greater than the first distribution power.

[0014] In some embodiments, the dynamic parameters include the rotational speed of the power output system; in response to the second distribution power of the power output system being less than the second demand power of the power output system and the first distribution power of the driving system being greater than the first demand power of the driving system, the first demand power is determined as the target power of the driving system, and the second distribution power is determined as the target power of the power output system; the rotational speed of the power output system is adjusted to reduce the second demand power of the power output system such that the reduced second demand power is not greater than the second distribution power.

[0015] In some embodiments, in response to the first allocated power of the driving system being less than the first demand power of the driving system and the second allocated power of the power output system being less than the second demand power of the power output system, the allocated power of each system is determined as the first target power of each system; the engine speed and motor output power of the construction machinery vehicle are adjusted to increase the output power of the construction machinery vehicle; in response to the adjusted engine speed reaching a speed threshold, it is determined whether to use a power supply device to power the construction machinery vehicle based on the relationship between the first target power and the demand power corresponding to the increased output power.

[0016] In some embodiments, in response to a first target power corresponding to the increased output power being less than the required power, a second target power is provided to each system using a power supply device, such that the sum of the first target power and the second target power meets the required power.

[0017] In some embodiments, the supplementary power output by the power supply device is determined based on the power difference between the first target power and the required power; the supplementary power allocation ratio in each system is determined based on the power level corresponding to the power information of the power supply device; the second target power is determined based on the supplementary allocation ratio and the supplementary power; and the power supply device is used to supply power to each system according to the second target power.

[0018] In some embodiments, the power supply device is controlled to stop supplying power in response to at least one of the following conditions: the power difference is less than a difference threshold; the power supply device's power information is less than a power threshold; the power supply device's temperature information is greater than a temperature threshold; and the operational accuracy deviation of the engineering machinery vehicle is less than a first deviation threshold.

[0019] In some embodiments, for the same power difference, the supplementary power is positively correlated with the power level.

[0020] In some embodiments, the power level includes a first power level and a second power level, the first power level is greater than the second power level, and the power information corresponding to the second power level is greater than the power threshold. In response to the power level being the first power level, a supplementary allocation ratio is determined according to the type of the working mechanism of the construction machinery vehicle; in response to the power level being the second power level, the supplementary allocation ratio is the same for each system.

[0021] In some embodiments, the future time period includes a first time period and a second time period adjacent to the first time period. During the first time period, the construction machinery vehicle is controlled to operate according to the allocated power. The actual value of the operation accuracy deviation of the construction machinery vehicle at the second time point is obtained as a reference deviation, and the second time point is the end of the first time period. It is determined whether the allocated power needs to be updated based on whether the reference deviation is greater than a first deviation threshold. In response to the need to adjust the allocated power, the allocated power is adjusted according to the reference deviation to obtain the adjusted power. During the second time period, the construction machinery vehicle is controlled to operate according to the adjusted power.

[0022] In some embodiments, during a sub-time period of the second time period, the engineering machinery vehicle is controlled to operate according to the adjusted power; based on the dynamic parameters of the engineering machinery vehicle at the end of the sub-time period, a predicted value of the operation accuracy deviation of the engineering machinery vehicle at the next time point at the end of the sub-time period is determined; in response to the predicted value being greater than a first deviation threshold, the adjusted power is updated; the above steps are repeated until the predicted value of the operation accuracy deviation at the next time point at the end of the sub-time period is not greater than the first deviation threshold.

[0023] In some embodiments, the machine learning model is trained by: collecting the actual value of the operational accuracy deviation of the engineering machinery vehicle at the sample time point and the dynamic parameters at the previous time point to form a training dataset for the machine learning model; using the dynamic parameters at the previous time point as the input of the machine learning model, using the actual value as the target output of the machine learning model, and using minimizing the first difference between the actual value and the predicted value of the operational accuracy deviation output by the machine learning model as the training objective to train the machine learning model.

[0024] In some embodiments, training a machine learning model includes: determining an actual accuracy risk value for a sample time point based on the actual value and a second deviation threshold; determining a predicted accuracy risk value for a sample time point based on the predicted value and a second deviation threshold; and retraining the machine learning model in response to a first difference being greater than a first difference threshold or a second difference between the actual accuracy risk value and the predicted accuracy risk value being greater than a second difference threshold, until the first difference is less than the first difference threshold and the second difference is less than the second difference threshold.

[0025] According to some other embodiments of this disclosure, a control device is provided, comprising: a first determining unit, configured to determine, based on the dynamic parameters of the construction machinery vehicle at a first time point and using a machine learning model, a predicted value of the operational accuracy deviation of the construction machinery vehicle at a next time point after the first time point; a second determining unit, configured to determine the allocated power of each of the multiple systems of the construction machinery vehicle based on the predicted value of the operational accuracy deviation; and a control unit, configured to control the construction machinery vehicle to perform operations in a future time period starting from the first time point based on the allocated power.

[0026] In some embodiments, the second determining unit determines the allocation ratio of each system based on the risk level corresponding to the predicted value; and determines the allocation power based on the allocation ratio and the output power of the construction machinery vehicle.

[0027] In some embodiments, the multiple systems include a driving system and a power output system for outputting power to the working mechanism of the construction machinery vehicle. The second determining unit determines a risk level based on the prediction accuracy risk value corresponding to the predicted value; and determines a first allocation ratio for the driving system and a second allocation ratio for the power output system based on the risk level.

[0028] In some embodiments, the first allocation ratio is positively correlated with the risk level, and the second allocation ratio is negatively correlated with the risk level.

[0029] In some embodiments, the control unit determines the control strategy of the working mechanism of the construction machinery vehicle according to the risk level; and controls the construction machinery vehicle to perform operations according to the allocated power and the control strategy.

[0030] In some embodiments, the risk level includes a first risk level and a second risk level, the first risk level is greater than the second risk level, and the prediction accuracy risk value corresponding to the second risk level is greater than a first deviation threshold. In response to the risk level being the first risk level, the control unit uses the auxiliary working mechanism of the construction machinery vehicle to compensate for the working accuracy deviation of the construction machinery vehicle; in response to the risk level being the second risk level, it adjusts the working parameters of the working mechanism.

[0031] In some embodiments, the control unit selects a power supply strategy based on the relationship between the allocated power and the required power, wherein the required power is determined based on the dynamic parameters of each system; and controls the construction machinery vehicle to operate in the future time period according to the power supply strategy.

[0032] In some embodiments, the dynamic parameters include the driving speed of the construction machinery vehicle. In response to the first distribution power of the driving system being less than the first demand power of the driving system and the second distribution power of the power output system being greater than the second demand power of the power output system, the control unit determines the first distribution power as the target power of the driving system and the second demand power as the target power of the power output system; and adjusts the driving speed of the construction machinery vehicle to reduce the first demand power of the driving system so that the reduced first demand power is not greater than the first distribution power.

[0033] In some embodiments, the dynamic parameters include the rotational speed of the power output system. In response to the second distribution power of the power output system being less than the second demand power of the power output system and the first distribution power of the driving system being greater than the first demand power of the driving system, the control unit determines the first demand power as the target power of the driving system and the second distribution power as the target power of the power output system; and adjusts the rotational speed of the power output system to reduce the second demand power of the power output system so that the reduced second demand power is not greater than the second distribution power.

[0034] In some embodiments, the control unit, in response to the first allocated power of the driving system being less than the first demand power of the driving system and the second allocated power of the power output system being less than the second demand power of the power output system, determines the allocated power of each system as the first target power of each system; adjusts the engine speed and motor output power of the construction machinery vehicle to increase the output power of the construction machinery vehicle; and in response to the adjusted engine speed reaching a speed threshold, determines whether to use the power supply device to power the construction machinery vehicle based on the relationship between the first target power and the demand power corresponding to the increased output power.

[0035] In some embodiments, in response to a first target power corresponding to the increased output power being less than the required power, the control unit provides a second target power to each system using a power supply device, such that the sum of the first target power and the second target power meets the required power.

[0036] In some embodiments, the control unit determines the supplementary power output by the power supply device based on the power difference between the first target power and the required power; determines the supplementary power allocation ratio in each system based on the power level corresponding to the power information of the power supply device; determines the second target power based on the supplementary allocation ratio and the supplementary power; and supplies power to each system according to the second target power using the power supply device.

[0037] In some embodiments, the control unit controls the power supply device to stop supplying power in response to at least one of the following conditions: the power difference is less than a difference threshold; the power supply device's power information is less than a power threshold; the power supply device's temperature information is greater than a temperature threshold; the operational accuracy deviation of the construction machinery vehicle is less than a first deviation threshold.

[0038] In some embodiments, for the same power difference, the supplementary power is positively correlated with the power level.

[0039] In some embodiments, the power level includes a first power level and a second power level, the first power level is greater than the second power level, and the power information corresponding to the second power level is greater than the power threshold. When the power level is the first power level, the control unit determines the supplementary allocation ratio according to the type of the working mechanism of the construction machinery vehicle; when the power level is the second power level, the supplementary allocation ratio is the same for each system.

[0040] In some embodiments, the future time period includes a first time period and a second time period adjacent to the first time period. During the first time period, the control unit controls the construction machinery vehicle to operate according to the allocated power. The control unit obtains the actual value of the operation accuracy deviation of the construction machinery vehicle at the second time point as a reference deviation, and the second time point is the end of the first time period. The control unit determines whether the allocated power needs to be updated based on whether the reference deviation is greater than a first deviation threshold. In response to the need to adjust the allocated power, the control unit adjusts the allocated power according to the reference deviation to obtain the adjusted power. During the second time period, the control unit controls the construction machinery vehicle to operate according to the adjusted power.

[0041] In some embodiments, the control unit controls the construction machinery vehicle to operate at an adjusted power during a sub-time period of the second time period; determines a predicted value of the operation accuracy deviation of the construction machinery vehicle at the end of the sub-time period based on the dynamic parameters of the construction machinery vehicle at the end of the sub-time period; updates the adjusted power in response to the predicted value being greater than a first deviation threshold; and repeats the above steps until the predicted value of the operation accuracy deviation at the next time point after the end of the sub-time period is not greater than the first deviation threshold.

[0042] In some embodiments, the machine learning model is trained by: collecting the actual value of the operational accuracy deviation of the engineering machinery vehicle at the sample time point and the dynamic parameters at the previous time point to form a training dataset for the machine learning model; using the dynamic parameters at the previous time point as the input of the machine learning model, using the actual value as the target output of the machine learning model, and using minimizing the first difference between the actual value and the predicted value of the operational accuracy deviation output by the machine learning model as the training objective to train the machine learning model.

[0043] In some embodiments, training a machine learning model includes: determining an actual accuracy risk value for a sample time point based on the actual value and a second deviation threshold; determining a predicted accuracy risk value for a sample time point based on the predicted value and a second deviation threshold; and retraining the machine learning model in response to a first difference being greater than a first difference threshold or a second difference between the actual accuracy risk value and the predicted accuracy risk value being greater than a second difference threshold, until the first difference is less than the first difference threshold and the second difference is less than the second difference threshold.

[0044] According to further embodiments of the present disclosure, a control device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the control method of any of the above embodiments based on instructions stored in the memory device.

[0045] According to further embodiments of this disclosure, an engineering machinery vehicle is provided, including the control device of any of the above embodiments.

[0046] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the control method of any of the above embodiments.

[0047] According to further embodiments of this disclosure, a computer program product is also provided, including instructions that, when executed by a processor, cause the processor to perform the control method according to any of the foregoing embodiments. Attached Figure Description

[0048] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this application, illustrate exemplary embodiments of this disclosure and are used to explain this disclosure, but do not constitute an undue limitation of this disclosure. In the drawings:

[0049] Figure 1 shows a flowchart of some embodiments of the control method of this disclosure;

[0050] Figure 2 shows schematic diagrams of some embodiments of the control device of this disclosure;

[0051] Figure 3 shows flowcharts of some other embodiments of the control method of this disclosure;

[0052] Figure 4 shows flowcharts of some further embodiments of the control method of this disclosure;

[0053] Figure 5 shows a block diagram of some embodiments of the control device of this disclosure;

[0054] Figure 6 shows a block diagram of some other embodiments of the control device of this disclosure;

[0055] Figure 7 shows a block diagram of some further embodiments of the control device of this disclosure;

[0056] Figure 8 shows a block diagram of some embodiments of the vehicle disclosed herein. Detailed Implementation

[0057] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0058] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0059] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0060] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0061] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0062] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0063] The inventors of this disclosure have discovered the following problems in the above-mentioned related technologies: the decision-making basis for power distribution is too singular, resulting in low operating accuracy of construction machinery vehicles and poor operating stability of construction machinery vehicles.

[0064] As mentioned earlier, agricultural machinery vehicles, as core equipment in agricultural production, have their PTO (Power Take-Off) and driving systems' power distribution schemes significantly impacting the efficiency and quality of agricultural operations. The power matching between the PTO and driving systems typically employs an independent distribution mode, relying on a fixed power allocation ratio. However, different operational scenarios (such as sowing, tillage, and transportation) place vastly different demands on the rotational speed and driving speed of the power output shaft in the PTO system. This fixed allocation method is difficult to apply to complex operational scenarios, resulting in agricultural machinery vehicles failing to fully utilize their power efficiency in actual agricultural production environments, often leading to problems such as power imbalance and insufficient operational continuity.

[0065] To improve power distribution schemes, the power ratio between the PTO system and the driving system can be dynamically adjusted. However, dynamic distribution schemes typically determine the power allocation based solely on the power demands of the PTO and driving systems, neglecting the impact of power changes on operational accuracy and failing to incorporate operational accuracy into the power distribution scheme.

[0066] In agricultural operations, operational precision affects crop growth and final harvest. For example, row spacing deviations in sowing and tillage depth fluctuations in tillage can affect crop growth space and root development, thus impacting yield and quality. Furthermore, sudden load changes in the PTO (Power Transfer) system triggering power distribution adjustments can lead to fluctuations in travel speed, resulting in uneven row spacing in sowing and deviations in tillage depth—all indicating operational precision anomalies. This dynamic allocation scheme cannot correct for these precision anomalies, leading to low operational precision and poor operational stability of agricultural machinery in complex operating scenarios.

[0067] To address at least one of the aforementioned problems, this disclosure provides a control method capable of dynamically predicting operational accuracy deviations based on the dynamic parameters of engineering machinery vehicles, and adaptively determining the vehicle's power distribution scheme based on the predicted operational accuracy deviations. This approach rationally determines the power distribution for each system while ensuring the vehicle's operational accuracy, thereby improving the stability of vehicle operation.

[0068] For example, the technical solution of this disclosure can be implemented through the following embodiments.

[0069] Figure 1 shows a flowchart of some embodiments of the control method of this disclosure.

[0070] As shown in Figure 1, in step 110, based on the dynamic parameters of the construction machinery vehicle at the first time point, a machine learning model is used to determine the predicted value of the operational accuracy deviation of the construction machinery vehicle at the next time point. For example, the dynamic parameters include the construction machinery vehicle's travel speed, travel acceleration, travel resistance, load torque of the PTO system, and vibration acceleration of the PTO shaft. Among these dynamic parameters, travel speed is a key parameter affecting the operational accuracy of the construction machinery vehicle; travel acceleration reflects the degree of fluctuation in travel speed; and the load torque of the PTO system reflects the load intensity of the agricultural implement operation.

[0071] For example, driving resistance can be the sum of rolling resistance, air resistance, gradient resistance, and acceleration resistance. Driving resistance can be calculated according to automotive theory by collecting parameters such as driving speed, driving acceleration, and gradient, and measuring or querying parameters such as the total mass, frontal area, drag coefficient, and rolling resistance coefficient of the construction machinery vehicle.

[0072] In step 120, the power allocation for each of the multiple systems in the construction machinery vehicle is determined based on the predicted value of the operational accuracy deviation. For example, taking an agricultural machinery vehicle (e.g., a tractor) as an example, the multiple systems include a running system and a PTO (Power Transfer Tolerance) system. The PTO system is used to output power to the working mechanism of the agricultural machinery vehicle.

[0073] In step 130, the construction machinery vehicle is controlled to operate within a future time period starting from the first time point, based on the allocated power.

[0074] In the above embodiments, the operational accuracy deviation is dynamically predicted based on the dynamic parameters of the engineering machinery vehicle, and the power distribution scheme of the vehicle is adaptively determined based on the predicted value of the operational accuracy deviation. In this way, the power distribution of each system is reasonably determined, while ensuring the operational accuracy of the vehicle, thereby improving the stability of vehicle operation.

[0075] The training process of the machine learning model in step 110 above is illustrated below through some examples.

[0076] In some embodiments, the machine learning model is trained as follows: The actual values ​​of the operational accuracy deviation of the construction machinery vehicle at a sample time point and the dynamic parameters at the previous time point are collected to form a training dataset for the machine learning model; the dynamic parameters at the previous time point are used as the input to the machine learning model, the actual values ​​are used as the target output of the machine learning model, and the training objective is to minimize the first difference between the actual values ​​and the predicted value of the operational accuracy deviation output by the machine learning model. For example, the machine learning model can be built based on a random forest regression algorithm, using historical data of the construction machinery vehicle to train the model parameters and construct a nonlinear mapping relationship between the dynamic parameters and the operational accuracy deviation.

[0077] In this way, by collecting historical data on operational accuracy deviation at sample time points and using this historical data to build a machine learning model, the mapping relationship between dynamic parameters and operational accuracy deviation can be reflected. This allows for subsequent power distribution based on operational accuracy deviation, ensuring vehicle operational accuracy and thus improving vehicle operational stability.

[0078] For example, historical data includes the actual value of the vehicle's operational accuracy deviation at the sample time point and the dynamic parameters at the previous time point. These parameters can be collected through the multi-dimensional sensing layer in the control device shown in Figure 2.

[0079] Figure 2 shows schematic diagrams of some embodiments of the control device of this disclosure.

[0080] As shown in Figure 2, the control device 2 includes a hardware architecture consisting of a multi-dimensional perception layer 210, a control decision layer 220, and an execution layer 230. The multi-dimensional perception layer 210 includes a PTO torque sensor 211, a PTO vibration acceleration sensor 212, and operation accuracy sensors (e.g., a row spacing laser rangefinder 215 and a tillage depth ultrasonic sensor 216). The control decision layer 220 is centered around a VCU (Vehicle Controller Unit) 221. The execution layer 230 includes an engine ECU (Electronic Control Unit) 231, a motor controller 232, and a working mechanism controller 233.

[0081] For example, the multi-dimensional perception layer 210 can collect information such as the status of the vehicle's power system, the load characteristics of the PTO system, and the operating accuracy of the construction machinery vehicle, providing data support for subsequent power distribution and vehicle control.

[0082] For example, the multi-dimensional perception layer 210 includes multiple dedicated sensors and data acquisition devices. The PTO torque sensor 211 collects load torque data from the PTO system, and the PTO vibration acceleration sensor 212 captures sudden load changes (e.g., load changes when a seeder jams or a rotary tiller encounters hard soil) by monitoring the vibration acceleration of the PTO shaft. The vehicle-mounted GPS (Global Positioning System) 213 acquires vehicle driving information such as speed, acceleration, and displacement. The vehicle-wide CAN (Controller Area Network) bus 214 aggregates vehicle power parameters such as engine speed, speed, and battery SOC (State of Charge). The vehicle-wide CAN bus 214 collects driving speed data at a lower sampling frequency than the vehicle-mounted GPS 213, therefore, the driving speed data collected by the vehicle-mounted GPS 213 is often used. When an external vehicle-mounted GPS 213 cannot be connected, the driving speed data collected by the vehicle-wide CAN bus 214 is used as a substitute. Different types of sensors are required depending on the operating scenario. For example, in the sowing condition, a row spacing laser rangefinder 215 can be selected, and in the rotary tillage condition, an ultrasonic tillage depth sensor 216 can be selected to collect data on the deviation of operational accuracy such as row spacing and tillage depth.

[0083] The following example, shown in Figure 3, illustrates the process of model training based on the collected data and the process of predicting job accuracy deviation using the trained machine learning model.

[0084] Figure 3 shows flowcharts of some other embodiments of the control method of this disclosure.

[0085] Referring to Figure 3, in step 310, as described above, data collection is performed. Data can be collected under various agricultural operating conditions to ensure that the machine learning model can adapt to complex operating scenarios. Operating conditions include sowing, rotary tillage, harvesting, and transportation, and soil conditions include farmland soil textures such as clay, sandy soil, and loam. Input features T are collected at continuous time points. pto a pto The sample data are v, a, and F, which are used to form the input feature vector X = [T]. pto a pto v, a, F, η type ]. Among them, T pto For the load torque of the PTO system, a pto Let v be the vibration acceleration of the PTO shaft, v be the travel speed of the construction machinery vehicle, a be the travel acceleration of the construction machinery vehicle, and F be the vibration acceleration of the PTO shaft. 阻 For driving resistance, η typeThis is a task type parameter used to differentiate the varying accuracy requirements of different task scenarios. The driver selects the task type manually based on the current task scenario, and the system determines the task type parameters accordingly. For example, for seeding tasks, η... type =1; for rotary tillage, η type =2; for plowing operations, η type =3; for transportation operations, η type =4. The above distinction between job types can ensure that the model can adapt to the accuracy control requirements of different job scenarios.

[0086] For example, the actual row spacing deviation ΔL can also be collected using a farmland operation accuracy analyzer. real Deviation from actual tillage depth ΔD real The actual values ​​of the accuracy deviation of the operation are used to form the output feature vector, which is used to construct the training dataset.

[0087] In step 320, the collected sample data is preprocessed. For example, the sample data of the input features can be filtered, normalized, etc., and the job type coefficient η can be determined in combination with the job type. type The values ​​of are selected to form a standardized input feature vector.

[0088] In some embodiments, the actual accuracy risk value at a sample time point is determined based on the actual value and a second deviation threshold. For example, referring to Figure 3, in step 330, the actual value of the job accuracy deviation (e.g., ΔL) can be used as the basis for determining the risk value. real and ΔD real The comparison result between the actual accuracy and the second deviation threshold (i.e., the maximum allowable deviation value) indicates the actual accuracy risk value R. real .

[0089] For example, the second deviation threshold ΔL for row spacing deviation in sowing operations. max =2cm, the second deviation threshold ΔD for tillage depth deviation in rotary tillage operations max =3cm. Response to ΔL real >ΔL max or ΔD real >ΔD max Mark R real =0.8~1.0, indicating that an error has occurred. Response to ΔL real ∈[0.8ΔL max ΔL max ] or ΔD real ∈[0.8ΔD max ΔD max ], marked R real =0.5~0.8, indicating a risk of accuracy deviation. Response to ΔL real<0.8ΔL max or ΔD real <0.8ΔD max Mark R real <0.5 indicates that there is no risk of accuracy deviation.

[0090] In step 340, a model training framework is constructed using the random forest algorithm, with the following improvements. The goal of the random forest algorithm is to minimize the overall error of samples within the current node, while the improved random forest algorithm focuses the node splitting objective on the job accuracy deviation (ΔL, ΔD), allowing the model to prioritize learning the patterns of input parameters that affect this indicator (e.g., the driving speed of construction machinery vehicles), avoiding interference from irrelevant features, and ensuring that the difference between the predicted and actual values ​​of the final job accuracy deviation can be controlled within a threshold range to meet the high precision requirements of operations such as sowing and rotary tillage.

[0091] In some embodiments, a prediction accuracy risk value for a sample time point is determined based on the predicted value and a second deviation threshold; in response to a first difference greater than a first difference threshold or a second difference between the actual accuracy risk value and the predicted accuracy risk value greater than a second difference threshold, the machine learning model is retrained until the first difference is less than the first difference threshold and the second difference is less than the second difference threshold.

[0092] For example, setting the number of decision trees to 100 and the tree depth to 8 levels, and using MSE (Mean Squared Error) as the basis for node splitting, to minimize the predicted value of the job accuracy deviation (the predicted value of the row spacing deviation ΔL). pred Or the predicted value of tillage depth deviation ΔD pred The model is trained with the squared difference between the predicted value of the job accuracy deviation and the actual value of the deviation as the target. Furthermore, an L2 regularization term is introduced (e.g., the weight decay coefficient is set to 0.01). Through iterative training using 5-fold cross-validation on the training dataset, the predicted value of the job accuracy deviation output by the model is made to satisfy |ΔL... pred -ΔL real |≤0.2cm、|ΔD pred -ΔD real |≤0.3cm, to cover the allowable error range for high-precision agricultural operations.

[0093] Thus, by improving the algorithm, the accuracy of model predictions is enhanced. Furthermore, by introducing an L2 regularization term, the impact of outliers caused by complex agricultural operating environments on model parameters can be suppressed, preventing the overall prediction trend from shifting due to individual extreme samples. This strengthens the model's robustness to outliers and improves the output stability of the model under complex operating scenarios. Moreover, further verification using actual accuracy risk values ​​and predicted accuracy risk values ​​ensures the accuracy of the prediction results, thereby improving the reliability of model predictions.

[0094] In step 350, the machine learning model trained in step 340 is used to predict the job accuracy deviation in real time. During the actual operation of the construction machinery vehicle, the VCU will call the trained machine learning model to filter and normalize the real-time data collected by the multi-dimensional perception layer 210 according to the preprocessing process in step 320, and determine η based on the current job type. type This forms a standardized real-time input feature X for prediction. pred =[T pto_pre a pto_pre v pre a pre F pre η type ]. and X pred Input into the already trained machine learning model, via [ΔL] pred ,ΔD pred ,R pred ] = Model(X pred Output real-time prediction results, where Model(X) pred This represents a trained machine learning model. The computation cycle of a machine learning model can be consistent with the highest acquisition frequency of the input feature data. For example, a prediction calculation can be completed every 10ms to ensure real-time performance.

[0095] The following examples illustrate how to determine the allocated power for each system based on the predicted value of the operational accuracy deviation.

[0096] In some embodiments, the allocation ratio of each system is determined based on the risk level corresponding to the predicted value; the allocation power is determined based on the allocation ratio and the output power of the construction machinery vehicle. For example, it can be based on a trained machine learning model and the job type parameter η. type Determine the allocation ratio between the PTO system and the driving system.

[0097] In some embodiments, multiple systems include a driving system and a power output system for outputting power to the working mechanism of the construction machinery vehicle. A risk level is determined based on a prediction accuracy risk value corresponding to the predicted value. Based on the risk level, a first allocation ratio for the driving system and a second allocation ratio for the power output system are determined. For example, the first allocation ratio is positively correlated with the risk level, and the second allocation ratio is negatively correlated with the risk level.

[0098] In this way, the power distribution ratio between the driving system and the PTO system is dynamically adjusted according to the risk level. This ensures that the driving system's power is prioritized to stabilize the vehicle speed when the risk level is high, while allocating more power to the PTO system to improve work efficiency when the risk level is low. This achieves a balance between work accuracy and work efficiency under complex working conditions.

[0099] For example, the basic allocation ratio ω of the PTO system is set according to the demand characteristics and precision control targets of different operation types of construction machinery vehicles. pto0 The basic allocation ratio ω of the driving system drive0 Taking sowing as an example, the operation type coefficient is 1, ω pto0 Set to 0.5, ω drive0 Set to 0.5. Based on the prediction accuracy risk value R from the model output. pred (R pred The larger the value, the higher the risk of operational accuracy deviation. Adjustments are made based on the basic allocation ratio to determine the allocation ratio for each system.

[0100] For example, in R pred With a value <0.5, the risk level is lowest, indicating no risk of accuracy deviation, and the vehicle can operate normally. The power distribution ratio between the PTO system and the driving system is:

[0101] In formula (1), ω drive ω is the first allocation ratio used for the driving system. pto Let ω be the second allocation ratio used in the PTO system, and max(·) be a boundary constraint function used to limit the range of values ​​for the allocation ratio. For example, ω pto ∈[0.3, 0.7], ω drive ∈[0.3, 0.7]. By setting the boundary constraint function, the problem of insufficient power supply to another system due to excessive power allocation to a single system can be avoided.

[0102] The aforementioned power distribution method prioritizes ensuring the operational efficiency of the working mechanism by preferentially supplying the vehicle's engine output power to the PTO system to meet the load torque T of the PTO system. pto The demand.

[0103] For example, in R pred When the value is between 0.5 and 0.8, the risk level is higher than R. pred The risk level is <0.5, indicating a risk of excessive accuracy deviation. The power distribution ratio between the PTO system and the driving system is as follows:

[0104] Compared to R, the above power distribution method predIn cases where T < 0.5, the power supply to the PTO system is reduced. For example, only those satisfying T are retained. pto Reduce the power required for basic needs (e.g., from 100% full load to 80%) to prevent the PTO system from over-utilizing power and causing instability in the driving system. Also, increase the power supply to the driving system to suppress speed fluctuations Δv (e.g., suppress to ≤3%).

[0105] Speed ​​fluctuation refers to the deviation between the actual driving speed and the target driving speed. When the power supply can match the driving resistance, the driving speed is stable; when the power supply is insufficient or fluctuates, the driving speed will fluctuate accordingly. For example, the power system can receive signals from the speed sensor in real time. If the actual driving speed is detected to be lower than the target driving speed, the power supply to the driving system will be increased, and the power supply to the PTO system will be appropriately reduced; if the actual driving speed is higher than the target driving speed, the power supply to the driving system can be increased.

[0106] For example, in R pred With a value between 0.8 and 1.0, the risk level is the highest, indicating that accuracy deviations have occurred. The power distribution ratio between the PTO system and the driving system is:

[0107] In formula (3), min(·) is a boundary constraint function used to limit the range of priority weight values. For example, ω pto ∈[0.3, 0.7], ω drive ∈[0.3, 0.7].

[0108] The aforementioned power distribution method, by allocating more of the engine's output power to the driving system, can stabilize the driving speed of construction machinery vehicles (for example, controlling Δv to ≤2%), and can avoid further deviations in accuracy caused by speed fluctuations.

[0109] Based on the predicted value of the operational accuracy deviation in the above technical solution, the control strategy of the operating mechanism can also be determined. The following examples illustrate the process of determining the control strategy of the operating mechanism.

[0110] In some embodiments, a control strategy for the working mechanism of the construction machinery vehicle is determined based on the risk level; the construction machinery vehicle is controlled to perform operations according to the control strategy based on the allocated power. For example, the risk level includes a first risk level and a second risk level, where the first risk level is greater than the second risk level, and the prediction accuracy risk value corresponding to the second risk level is greater than a first deviation threshold. In response to the risk level being the first risk level, the auxiliary working mechanism of the construction machinery vehicle is used to compensate for the operational accuracy deviation of the construction machinery vehicle; in response to the risk level being the second risk level, the operating parameters of the working mechanism are adjusted.

[0111] For example, in R pred When the value is between 0.5 and 0.8, the risk level is the second risk level. The control strategy corresponding to the second risk level can be to adjust the operating parameters of the operating mechanism. Taking the sowing condition as an example, the rotation speed of the operating mechanism (e.g., the seed metering device) can be reduced by 5% proportionally to the vehicle speed to ensure that the seed dispensing volume matches the vehicle speed, thereby consolidating the precision control effect.

[0112] For example, in R pred When the value is between 0.8 and 1.0, the risk level is the first risk level. The control strategy corresponding to the first risk level can be to trigger the auxiliary operation mechanism. Taking the sowing condition as an example, the supplementary sowing motor can be started to supplement the seeds proportionally according to the row spacing deviation ΔL, so as to correct the existing operation accuracy deviation and shorten the recovery time of the operation accuracy deviation.

[0113] A supplementary seeding motor is an auxiliary seeding device used in high-precision agricultural seeding operations to correct row spacing deviations and solve problems of missed or insufficient seeding. It typically works in conjunction with the main seeding system. When a precision deviation is detected, the supplementary seeding motor can be activated to re-seed the areas where the precision deviation occurred.

[0114] For example, in seeding operations, when the row spacing measuring instrument detects ΔL real >0.8ΔL max In this case, the system sends a reseeding trigger signal to the control module of the reseeding motor and uploads the actual value of the operation accuracy deviation (e.g., ΔL). real =2.5cm). After receiving the reseeding trigger signal, the control module calculates the required reseeding amount and, combined with the reseeding amount Q and the seeding efficiency of the reseeding port (e.g., 5 seeds per revolution of the stepper motor), calculates the target speed n and working time t of the reseeding motor. Then, the control module sends a command to the drive module, and the reseeding motor starts at the corresponding speed, driving the small seed metering device to perform the sowing operation. During the reseeding process, the system can continuously monitor the row spacing deviation after reseeding, provide real-time feedback to the control module, and dynamically adjust the speed of the reseeding motor. The response to the detection system feedback ΔL real <0.8ΔL max If the amount of reseeding reaches the threshold, the control module sends a stop command, the reseeding motor stops, and the reseeding port closes.

[0115] In this way, different control strategies can be adaptively selected for the operating mechanism according to the risk level. This can quickly correct the operation accuracy deviation that has occurred in the case of high risk level by assisting the operating mechanism, and actively consolidate the control effect by optimizing the operation parameters in the case of medium and low risk level. This achieves precise control of operation accuracy deviation and improves the operation efficiency and stability of construction machinery vehicles under complex working conditions.

[0116] In the above embodiments, the allocation ratio between the driving system and the PTO system is dynamically adjusted according to the risk level, and corresponding control strategies for the working mechanism are adopted for different risk levels. In this way, driving stability can be prioritized and operational accuracy deviations can be compensated under high-risk conditions, while operational parameters can be optimized under medium- and low-risk conditions. This achieves synergy between power distribution and working mechanism control, improving the operational accuracy, stability, and efficiency of construction machinery vehicles under complex working conditions.

[0117] The following examples illustrate the process of adjusting the allocated power determined in step 120.

[0118] In some embodiments, the future time period includes a first time period and a second time period adjacent to the first time period. During the first time period, the construction machinery vehicle is controlled to operate according to the allocated power. The actual value of the operation accuracy deviation of the construction machinery vehicle at the second time point is obtained as a reference deviation, and the second time point is the end of the first time period. It is determined whether the allocated power needs to be updated based on whether the reference deviation is greater than a first deviation threshold. In response to the need to adjust the allocated power, the allocated power is adjusted according to the reference deviation to obtain the adjusted power. During the second time period, the construction machinery vehicle is controlled to operate according to the adjusted power.

[0119] For example, at the second time point, based on the operation accuracy deviation (e.g., row spacing deviation ΔL, tillage depth deviation ΔD) transmitted by the multi-dimensional sensing layer 210 received in real time by the VCU, and the operation accuracy deviation second deviation threshold (e.g., ΔL) max and ΔD max A comparison is made, and a tiered early warning mechanism is set up to proactively avoid the risk of accuracy deviation exceeding the limit. If the operational accuracy deviation ΔL or ΔD reaches 80% of the second deviation threshold (i.e., the first deviation threshold), a first-level early warning is triggered, prompting the system to enter accuracy risk prevention mode, and adjustments are made according to the control scheme described above when R is between 0.5 and 0.8. If the operational accuracy deviation ΔL or ΔD reaches the second deviation threshold, a second-level early warning is triggered, prompting the system to activate emergency accuracy correction mode, and adjustments are made according to the control scheme described above when R is between 0.8 and 1.0. If the operational accuracy deviation ΔL or ΔD is less than the first deviation threshold, there is no risk of accuracy deviation exceeding the limit, and the current control scheme is maintained without adjustment.

[0120] For example, based on the warning level and the risk level corresponding to the actual value of the operational accuracy deviation, the VCU adjusts the power distribution ratio between the driving system and the PTO system according to the aforementioned power adjustment scheme. By adjusting the power ratio between the PTO system and the driving system, further expansion of the accuracy deviation is suppressed. Furthermore, it outputs operational execution commands to control the control strategy of the operating mechanism (e.g., adjusting the speed of the seed metering device in seeding conditions, and adjusting the extension and retraction of the tillage depth cylinder in rotary tillage conditions to compensate for an operational accuracy deviation of ±0.5cm), thereby correcting the operational accuracy deviation.

[0121] In this way, the aforementioned precision deviation closed-loop correction mechanism constructs a full-process closed-loop control system of "perception-decision-execution-feedback" to monitor precision deviation in real time, dynamically output adjustment commands, verify correction effects, and continuously iterate and optimize, ensuring that the operation precision deviation quickly converges to below the first deviation threshold, thereby improving operation precision and thus improving the stability of construction machinery vehicle operation.

[0122] In some embodiments, during a sub-time period of the second time period, the engineering machinery vehicle is controlled to operate according to the adjusted power; based on the dynamic parameters of the engineering machinery vehicle at the end of the sub-time period, a predicted value of the operation accuracy deviation of the engineering machinery vehicle at the next time point at the end of the sub-time period is determined; in response to the predicted value being greater than a first deviation threshold, the adjusted power is updated; the above steps are repeated until the predicted value of the operation accuracy deviation at the next time point at the end of the sub-time period is not greater than the first deviation threshold.

[0123] For example, at the second time point, the execution layer 230 receives instructions and completes action adjustments. The multi-dimensional perception layer 210 collects relevant vehicle data (e.g., load torque of the PTO system, driving speed, and operational accuracy deviation of the construction machinery vehicle after updating the power allocation) during the second time period and sends the data back to the VCU. The VCU calls a machine learning model, substitutes the sent-back data into the model for calculation, and uses the predicted values ​​output by the model to verify the effect of the allocation ratio and the control strategy of the operating mechanism on the correction of operational accuracy deviation.

[0124] For example, if the VCU verification finds that the predicted value of the operational accuracy deviation of the construction machinery vehicle has not converged to below the first deviation threshold after updating the power allocation (i.e., the corresponding R...), pred If the deviation is still greater than 0.5, re-analyze the reasons why the operation accuracy deviation has not converged (e.g., unreasonable power distribution weight, insufficient adjustment range of the operating mechanism), readjust the power distribution ratio of the VCU, and execute the above decision-execution-feedback technical solution again until the operation accuracy deviation meets the standard.

[0125] For example, the machine learning model may not directly participate in the above correction process, but instead optimize its parameters based on the data generated by the correction. The VCU adjusts the allocation ratio according to the system-defined adjustment rules based on the operational accuracy deviation at the second time point, and stores the adjustment ratio. Key data from each correction process (such as the actual value of the operational accuracy deviation, the corresponding control commands, and the correction effect) are automatically stored in the cloud database for iterative updates to the machine learning model's parameters, thereby improving the model's adaptability to different working conditions and providing more accurate algorithmic support for accuracy control in subsequent similar operational scenarios.

[0126] In this way, by updating the early warning mechanism and allocation ratio, the expansion of operational accuracy deviation was suppressed. Furthermore, multiple iterative adjustments ensured that the operational accuracy deviation quickly converged below the threshold, improving the stability of construction machinery vehicle operations. Moreover, by feeding the corrected data back to the model to optimize the parameters of the machine learning model, the adaptive control of operational accuracy of construction machinery vehicles under complex working conditions was improved, thereby further enhancing the stability of vehicle operations.

[0127] The technical solution for determining the power distribution between the PTO system and the driving system, as well as the control strategy of the working mechanism, will be illustrated below using the control device shown in Figure 2 as an example.

[0128] As shown in Figure 2, the control decision layer 220 uses machine learning models to dynamically determine the allocation ratio and perform closed-loop correction based on the real-time data transmitted by the multi-dimensional perception layer 210, and finally outputs control commands to realize the prediction of the working status of the construction machinery vehicle and the dynamic adjustment of the power distribution strategy.

[0129] First, the control decision layer 220 receives data from the multi-dimensional perception layer 210, including the load torque of the PTO system, the vibration acceleration of the PTO shaft, the operational accuracy deviation, and the vehicle's power parameters, and preprocesses this data. Then, a machine learning model is used to determine the predicted value of the operational accuracy deviation to predict the accuracy risk value. Based on the risk level corresponding to the accuracy risk value, the power distribution ratio between the PTO system and the driving system is dynamically determined, and the ratio is adjusted using a closed-loop correction algorithm. Finally, the above calculation results are integrated to output control commands including engine power adjustment, motor-assisted power control, and collaborative correction of the operating mechanism, ensuring the coordinated implementation of power distribution and accuracy assurance. The core hardware of the control decision layer 220 is the VCU 221, in which the above algorithms are integrated and run.

[0130] The execution layer 230 includes the engine ECU 231, the motor controller 232, and the work actuator controller 233. By receiving control commands from the VCU 221, it adjusts the output power of the power source and the control strategy of the work mechanism to achieve coordinated correction of power distribution and work accuracy. After receiving the command, the engine ECU 231 can dynamically adjust the engine output power according to the demand, providing basic power support for the PTO system and the driving system.

[0131] The motor controller 232 (adapted for hybrid or electric motor models) can control the output power of the motor according to instructions, supplementing power when the engine power is insufficient, or flexibly adjusting the distribution ratio under load fluctuations to ensure the stability of power supply. For example, the motor controller 232 monitors the engine output power. When the engine output power is low and cannot meet the current operation requirements (e.g., heavy-load climbing or high-intensity operation), the motor controller 232 controls the output power of the ISG (Integrated Starter Generator) motor to work together with the engine to provide sufficient power.

[0132] The working mechanism controller 233 can actively correct the working accuracy by controlling the working mechanism. For example, it can control the rotation speed of the seeder's seed metering device to adapt to changes in travel speed, or adjust the tillage depth of the rotary tiller by adjusting the extension and retraction of the hydraulic cylinder to compensate for tillage depth deviations.

[0133] In the above embodiments, closed-loop dynamic control of vehicle power distribution and operational accuracy is achieved through the coordinated operation of a multi-dimensional perception layer, control decision layer, and execution layer. Machine learning models are used to predict risk levels and dynamically adjust the distribution ratio. Multiple controllers execute engine power regulation, motor auxiliary drive, and control of the working mechanism. This ensures the coordinated optimization of power distribution and operational accuracy, and enhances the system's adaptability through a closed-loop feedback mechanism, thereby improving the operational accuracy, stability, and efficiency of construction machinery vehicles under complex working conditions.

[0134] The following examples illustrate the control process of vehicle operation based on allocated power in step 130.

[0135] In some embodiments, a power supply strategy is selected based on the relationship between the allocated power and the required power, wherein the required power is determined based on the dynamic parameters of each system; and the engineering machinery vehicle is controlled to operate in the future time period according to the power supply strategy.

[0136] For example, according to the allocation ratio ω pto ω drive and the total available power P of the power source total (Ptotal =P engine +P motor P engine P is the engine's output power. motor (This refers to the auxiliary output power of the motor), which can be used to calculate the power distribution between the PTO system and the driving system. The calculation formula is as follows:

[0137] In formula (4), P drive_theo For the first power distribution of the driving system, P pto_theo This is the second power allocation for the PTO system.

[0138] For example, the target power of the system can be calculated based on the power requirements of the PTO system and the driving system. The initial power requirement P required to drive the construction machinery vehicle can be calculated based on its driving resistance and speed. drive_req The calculation formula is as follows: P drive_req =F×v (5)

[0139] In formula (5), F is the driving resistance of the engineering machinery vehicle (including soil resistance, traction resistance of the implement, air resistance, etc.), and v is the driving speed of the engineering machinery vehicle.

[0140] Based on the load torque and PTO shaft speed of the PTO system of the construction machinery vehicle, calculate the second required power P of the PTO system for driving the working mechanism (e.g., seeder, rotary tiller, harvester). pto_req The calculation formula is as follows:

[0141] In formula (6), T pto n is the load torque of the PTO system. pto This refers to the rotational speed of the PTO shaft in the PTO system. Based on the relationship between the allocated power and the required power, the power supply strategy described below is selected.

[0142] The following examples illustrate power supply strategies corresponding to different size relationships.

[0143] In some embodiments, in response to a first power allocation of the driving system being greater than a first power demand of the driving system and a second power allocation of the power output system being greater than a second power demand of the power output system, the first power demand is determined as the target power of the driving system, and the second power demand is determined as the target power of the driving system.

[0144] For example, in P pto_req ≤P pto_theo And P drive_req ≤P drive_theoIn this case, the total available power of the power source (i.e., the output power of the construction machinery vehicle) allocated to each system can meet the power demand. Therefore, the target power can be set as follows:

[0145] In formula (7), P pto_tar For the target power of the PTO system, P drive_tar This is the target power for the driving system.

[0146] In some embodiments, the dynamic parameters include the driving speed of the construction machinery vehicle; in response to a first distribution power of the driving system being less than a first demand power of the driving system and a second distribution power of the power output system being greater than the second demand power of the power output system, the first distribution power is determined as the target power of the driving system and the second demand power is determined as the target power of the power output system; the driving speed of the construction machinery vehicle is adjusted to reduce the first demand power of the driving system such that the reduced first demand power is not greater than the first distribution power.

[0147] For example, in P pto_req >P pto_theo And P drive_req ≤P drive_theo In this case, the first power demand of the driving system is less than the first allocated power; therefore, the first power demand of the driving system is the target power of the driving system. However, the second power demand of the PTO system exceeds the second allocated power. To prevent the PTO system from overloading and damaging the working mechanism, the target power of the PTO can be limited to the second allocated power, and the second power demand can be reduced by fine-tuning the PTO system's rotational speed. The calculation formula is as follows:

[0148] In formula (8), n pto_tar The target speed for the PTO system is determined based on the distributed power and power demand of the PTO system. The PTO system speed is then adjusted down to this target speed to achieve a match between the load and power supply of the PTO system.

[0149] This prevents the operating mechanism from being damaged due to overload, ensures the normal operation of the construction machinery and vehicles, and maintains the stability and safety of the system operation.

[0150] In some embodiments, the dynamic parameters include the rotational speed of the power output system; in response to the second distribution power of the power output system being less than the second demand power of the power output system and the first distribution power of the driving system being greater than the first demand power of the driving system, the first demand power is determined as the target power of the driving system, and the second distribution power is determined as the target power of the power output system; the rotational speed of the power output system is adjusted to reduce the second demand power of the power output system such that the reduced second demand power is not greater than the second distribution power.

[0151] For example, in P pto_req ≤P pto_theo And P drive_req >P drive_theo In this case, the second required power of the PTO system is less than the second allocated power; therefore, the second required power of the PTO system is the target power of the PTO system. However, the first required power of the driving system exceeds the first allocated power. To avoid operational accuracy deviations caused by driving speed fluctuations, the target power of the driving system can be limited to the first allocated power, and the first required power can be reduced by fine-tuning the driving speed. The calculation formula is as follows:

[0152] In formula (9), v tar The target travel speed is determined based on the power distribution and power requirements of the driving system. By adjusting the travel speed to this target speed, the stability and operational accuracy of the construction machinery vehicle are ensured.

[0153] This avoids the decrease in operational accuracy caused by fluctuations in vehicle speed, ensures the stability of vehicle operation, and achieves reasonable power distribution.

[0154] In some embodiments, in response to the first allocated power of the driving system being less than the first demand power of the driving system and the second allocated power of the power output system being less than the second demand power of the power output system, the allocated power of each system is determined as the first target power of each system; the engine speed and motor output power of the construction machinery vehicle are adjusted to increase the output power of the construction machinery vehicle; in response to the adjusted engine speed reaching a speed threshold, it is determined whether to use a power supply device to power the construction machinery vehicle based on the relationship between the first target power and the demand power corresponding to the increased output power.

[0155] For example, in P pto_req >P pto_theo And P drive_req >P drive_theo In this case, the second power demand of the PTO system and the first power demand of the driving system both exceed the allocated power corresponding to each system. The target power of each system can be set as the allocated power, and the power source power enhancement mechanism can be triggered.

[0156] For example, in a power source boosting mechanism, the engine speed can be increased to the upper limit of the high-efficiency operating range, and the motor can be controlled to output full power to meet the power difference between the allocated power and the required power. The calculation formula is as follows:

[0157] In formula (10), nengine_tar is the target engine speed, nengine_max_eff is the upper limit speed of the engine's high-efficiency operating range, and nengine_rated is the engine's rated speed. By activating the engine's high-efficiency range, power output is increased while energy consumption is reduced. The high-efficiency operating range is determined based on the engine's BSFC (Brake Specific Fuel Consumption) diagram. Furthermore, the ISG motor can be activated to compensate for the power delay during the engine's speed increase process. After the above power-boosting mechanism is triggered, the motor switches from auxiliary power supply to full-power output.

[0158] This not only compensates for the power difference but also avoids the problem of increased fuel consumption caused by the engine operating in the inefficient range, effectively controlling fuel consumption while ensuring operational power.

[0159] For example, when the electronic control system of a construction vehicle detects a need to increase engine speed, it sends a command to the ISG motor. The ISG motor operates as an electric motor, using battery power to generate rotational torque. This torque, connected to the engine crankshaft, directly assists the engine in increasing its speed. During this process, the ISG motor responds quickly, compensating for the power output delay during engine speed increase, enabling the engine to reach the required speed. The ISG motor can provide the engine with additional auxiliary torque and power. During the engine speed increase process, the ISG motor can also output auxiliary power to assist the engine in increasing its speed. This auxiliary power can be dynamically adjusted according to the engine's actual needs and the vehicle's driving conditions. When the engine requires greater torque to quickly increase its speed, the ISG motor will output greater auxiliary power to meet the engine's needs and ensure that the engine can smoothly reach the target speed.

[0160] After the power source boosting mechanism is triggered, the ISG motor switches from auxiliary power supply to full-power output. In auxiliary power supply mode, the ISG motor provides auxiliary power according to the engine's needs, helping the engine increase its speed. When the power source boosting mechanism is triggered, the vehicle requires a greater power supply, and the vehicle's electronic control system sends a command to the ISG motor again, requesting it to output at full power. Upon receiving the command, the ISG motor adjusts its control strategy, changing parameters such as current magnitude and phase to maximize the motor's torque output, thus achieving full-power output. If, in response to the triggering of the power source boosting mechanism, the allocated power corresponding to the increased total available power of the power source still does not meet the power demand, the power supply device is activated to provide supplementary power.

[0161] The following examples illustrate technical solutions for replenishing the system with power supply devices.

[0162] In some embodiments, in response to a first target power corresponding to the increased output power being less than the required power, a second target power is provided to each system using a power supply device, such that the sum of the first target power and the second target power meets the required power. For example, the power supply device includes a battery.

[0163] For example, based on the power difference between the first target power and the required power, the supplementary power output of the power supply device is determined; based on the power level corresponding to the power information of the power supply device, the supplementary power allocation ratio in each system is determined; based on the supplementary allocation ratio and the supplementary power, the second target power is determined; and the power supply device is used to supply power to each system according to the second target power.

[0164] For example, the VCU calculates the total available power and total required power of the power source after power enhancement, and determines whether to trigger battery replenishment. Based on the battery's SOC, it performs different levels of replenishment and outputs a battery replenishment command to the BMS (Battery Management System). In response to the BMS receiving the VCU command, it activates the battery's high-voltage output circuit and sets and controls the replenishment power output from the battery. The motor controller receives the VCU allocation command and distributes the battery's replenishment power to the PTO system or the driving system according to the corresponding replenishment allocation ratio. Furthermore, the operating mechanism can also be adjusted accordingly. For example, to prioritize replenishing the driving system, the seeder speed can be synchronously fine-tuned with the driving speed to avoid accuracy fluctuations.

[0165] In this way, when the allocated power cannot meet the required power, the battery is activated to provide supplementary power, and the supplementary power is reasonably allocated according to the remaining battery charge to ensure the normal operation of the vehicle. This also avoids over-discharge of the battery, thus solving the problem of insufficient power and protecting the battery's lifespan.

[0166] In some embodiments, for the same power difference, the supplementary power is positively correlated with the power level. For example, the power level includes a first power level and a second power level, where the first power level is greater than the second power level, and the power information corresponding to the second power level is greater than the power threshold. In response to the power level being the first power level, the supplementary allocation ratio is determined according to the type of the working mechanism of the construction machinery vehicle; in response to the power level being the second power level, the supplementary allocation ratio is the same for each system.

[0167] For example, when SOC ≥ 40%, the battery's capacity level is set to the first level. 80% of the power difference between the total required power and the total allocated power is set as the maximum supplementary power output from the battery. The supplementary power allocation ratio is determined based on the type of working mechanism of the construction machinery vehicle, prioritizing systems with a higher correlation to the operational accuracy deviation of the current work scenario. For example, in seeding operations, priority is given to supplementing the travel system to stabilize the travel speed and control row spacing. In rotary tillage operations, priority is given to supplementing the PTO system to ensure the required torque of the tillers, thereby restoring operational accuracy (e.g., tillage depth).

[0168] For example, the maximum duration of a single battery recharge can be set to 5 minutes. If the operational accuracy deviation has not converged below the first accuracy deviation after 5 minutes of battery recharge, the system switches to the regular recharge mode. In the regular recharge mode, the proportion of battery recharge power to power difference is reduced to 40%-60%, thereby extending the battery recharge cycle and preventing overheating or over-discharge caused by prolonged high-power output.

[0169] For example, when the SOC is between 25% and 40%, the battery's capacity level is classified as the second capacity level. The minimum of 50% of the power difference and 50% of the battery's rated power is determined as the supplementary power output from the battery. This supplementary power allocation is determined using a balanced distribution strategy, meaning the battery's supplementary power is evenly distributed between the PTO system and the driving system to prevent insufficient power from a single system from worsening operational accuracy. Furthermore, the SOC can be monitored in real time, and supplementary power supply from the battery is stopped when the SOC drops to 25%.

[0170] For example, when the SOC is less than 25%, the additional power supply channels from the battery to the PTO system and driving system should be cut off, and the battery should only supply power to low-voltage systems such as VCU and sensors. The current operation of the construction machinery vehicle should be ended or recharged as soon as possible.

[0171] For example, when recharging, the vehicle operation is paused, shutdown control is implemented, and the battery is charged via external charging equipment. Recharging is carried out when recharging is possible, subsequent operations require power assistance, and the work must be completed on the same day. If recharging is not possible or the operational accuracy cannot be guaranteed, the current operation of the construction machinery vehicle is terminated.

[0172] In this way, by allocating different proportions of supplementary power based on the remaining battery charge, the power replenishment becomes more precise, thereby improving the stability of vehicle operation.

[0173] In some embodiments, the power supply device is controlled to stop supplying power in response to at least one of the following conditions: the power difference is less than a difference threshold; the power supply device's power information is less than a power threshold; the power supply device's temperature information is greater than a temperature threshold; and the operational accuracy deviation of the engineering machinery vehicle is less than a first deviation threshold.

[0174] For example, the multi-dimensional sensing layer 210 collects battery status information (e.g., SOC, temperature), power allocation information, and operational accuracy deviation information in real time, and transmits this data back to the VCU to verify the battery's charging effect. During the battery charging process, the row spacing measuring instrument collects ΔL in real time. real and ΔD real When the operational accuracy deviation converges to below the first deviation threshold, or the power difference shrinks to the difference threshold (e.g., 5kW), recharging can be stopped. When the battery recharging time reaches its limit, i.e., the SOC drops to 25% or the battery temperature exceeds the temperature threshold, the VCU sends a stop command to the BMS, the BMS cuts off the high-voltage output, and battery recharging ends.

[0175] In the above embodiments, by determining the relationship between the allocated power and the required power, the corresponding power supply strategy is adaptively selected and switched. When the allocated power is sufficient, it is supplied precisely on demand; when the allocated power of a single system is insufficient, the speed of the PTO shaft or the vehicle speed is adjusted to match the demand; when the allocated power of each system is insufficient, the output power of the engine and motor is increased in a coordinated manner, and a graded battery replenishment strategy is activated when necessary. In this way, the adaptability and operating efficiency of the construction machinery vehicle in different operating scenarios are improved.

[0176] Figure 4 shows flowcharts of some further embodiments of the control method of this disclosure.

[0177] As shown in Figure 4, in step 410, the driver selects the job type through manual interaction based on the current work scenario. In step 415, the system sets the basic allocation ratio ω according to the job type. pto0 and ω drive0 In step 420, as described above, the risk level corresponding to the predicted value of the job accuracy deviation output by the machine learning model is determined. Based on the risk level, steps 425, 430, or 435 are executed to make corresponding adjustments based on the basic allocation ratio to determine the allocation ratio.

[0178] In step 425, R pred <0.5, at this point there is no risk of accuracy exceeding tolerance. Based on the basic distribution ratio, the power distribution of the PTO system is improved to ensure the operating efficiency of the working mechanism. This is achieved by prioritizing the supply of the vehicle's engine output power to the PTO system to meet the load torque T of the PTO system.pto The demand.

[0179] In step 430, R pred = 0.5~0.8, at which point there is a risk of accuracy deviation. Compared to R pred If the value is less than 0.5, the power supply to the PTO system should be reduced. For example, the basic allocation ratio should be determined as the allocation ratio for each system.

[0180] In step 435, R pred =0.8~1.0, indicating that the accuracy has exceeded the tolerance. The power distribution of the driving system can be increased based on the basic distribution ratio. By allocating more of the engine's output power to the driving system, the driving speed of the construction machinery vehicle can be stabilized, thus avoiding further accuracy deviations caused by speed fluctuations.

[0181] The process of determining the allocation ratio in steps 425, 430 or 435 can refer to the above formulas (1)-(3) and related descriptions.

[0182] In step 440, the allocated power is determined based on the determined allocation ratio. The relationship between the allocated power and the required power is then determined. Based on this relationship, steps 445, 450, 455, or 460 are executed to select the appropriate power supply strategy. The process of determining the allocated power and the required power can be found in formulas (4)-(6) and related descriptions.

[0183] In step 445, the power supply is sufficient. The total available power of the power source, when allocated to each system, meets the power demand; therefore, the target power for each system can be set to the power demand.

[0184] In step 450, the PTO system experiences insufficient power supply. The first power demand of the driving system is less than the first allocated power, therefore the first power demand of the driving system is the target power of the driving system. However, the second power demand of the PTO system exceeds the second allocated power. To prevent the PTO system from overloading and damaging the working mechanism, the target power of the PTO can be limited to the second allocated power, and the second power demand can be reduced by fine-tuning the rotational speed of the PTO shaft.

[0185] In step 455, the driving system has insufficient power supply. The second required power of the PTO system is less than the second allocated power, therefore the second required power of the PTO system is the target power of the PTO system. However, the first required power of the driving system exceeds the first allocated power. To avoid deviations in operational accuracy caused by fluctuations in driving speed, the target power of the driving system can be limited to the first allocated power, and the first required power can be reduced by fine-tuning the driving speed.

[0186] In step 460, by triggering the power source power enhancement mechanism, the engine speed is increased to the upper limit of the high-efficiency operating range, and the motor is controlled to output full power to meet the power difference between the allocated power and the required power. In response to triggering the power source power enhancement mechanism, if the allocated power corresponding to the increased total available power of the power source still does not meet the required power, step 465 is executed. The power supply scheme in steps 445-460 above can be referred to formulas (7)-(10) and related descriptions.

[0187] In step 465, the battery is started to replenish energy, and a graded energy replenishment strategy is determined according to the battery SOC, and steps 470, 475 or 480 are executed.

[0188] When SOC ≥ 40%, proceed to step 470. As previously mentioned, the battery's charge level is the first charge level. 80% of the power difference between the total required power and the total allocated power is set as the maximum supplementary power output from the battery. The supplementary power allocation ratio is determined based on the type of working mechanism of the construction machinery vehicle, prioritizing systems with a higher correlation to the operational accuracy deviation of the current work scenario. For example, in seeding operations, priority is given to supplementing the travel system to stabilize the travel speed and control row spacing. In rotary tillage operations, priority is given to supplementing the PTO system to ensure tillage torque, thereby restoring tillage depth accuracy.

[0189] When the SOC is between 25% and 40%, proceed to step 475. The battery's capacity level is the second capacity level. The minimum value between 50% of the power difference and 50% of the battery's rated power is determined as the supplementary power output from the battery. The supplementary power allocation is determined using a balanced allocation strategy, that is, the battery's supplementary power is evenly distributed between the PTO system and the driving system to avoid deterioration of operational accuracy due to insufficient power in a single system. Furthermore, the SOC can be monitored in real time, and in response to the SOC dropping to 25%, the use of the battery for supplementary power supply is stopped.

[0190] If the SOC is less than 25%, proceed to step 480. Disconnect the battery from the additional power supply channels to the PTO system and driving system, and only maintain the battery's power supply to low-voltage systems such as the VCU and sensors. Then, end the current operation of the construction machinery vehicle or start recharging as soon as possible.

[0191] In the above embodiments, the allocation ratio between the driving system and the PTO system is dynamically adjusted according to the risk level, and corresponding control strategies for the working mechanism are adopted for different risk levels, thereby improving the operating accuracy, stability, and efficiency of construction machinery vehicles under complex working conditions. Furthermore, by judging the relationship between the allocated power and the required power, the corresponding power supply strategy is adaptively selected and switched, enhancing the adaptability and operating efficiency of construction machinery vehicles under different working conditions.

[0192] Figure 5 shows a block diagram of some embodiments of the control device of this disclosure.

[0193] According to some other embodiments of this disclosure, a control device 5 is provided, comprising: a first determining unit 51, configured to determine, based on the dynamic parameters of the construction machinery vehicle at a first time point and using a machine learning model, a predicted value of the operational accuracy deviation of the construction machinery vehicle at the next time point after the first time point; a second determining unit 52, configured to determine the allocated power of each of the multiple systems of the construction machinery vehicle based on the predicted value of the operational accuracy deviation; and a control unit 53, configured to control the construction machinery vehicle to perform operations in a future time period starting from the first time point based on the allocated power.

[0194] For example, the first determining unit 51 and the second control unit 52 can be set in the control decision layer 220 shown in FIG2, and the control unit 53 can be set in the execution layer 230 shown in FIG2.

[0195] In some embodiments, the second determining unit 52 determines the allocation ratio of each system based on the risk level corresponding to the predicted value; and determines the allocation power based on the allocation ratio and the output power of the construction machinery vehicle.

[0196] In some embodiments, the multiple systems include a driving system and a power output system for outputting power to the working mechanism of the construction machinery vehicle. The second determining unit 52 determines a risk level based on the prediction accuracy risk value corresponding to the predicted value; and determines a first allocation ratio for the driving system and a second allocation ratio for the power output system based on the risk level.

[0197] In some embodiments, the first allocation ratio is positively correlated with the risk level, and the second allocation ratio is negatively correlated with the risk level.

[0198] In some embodiments, the control unit 53 determines the control strategy of the working mechanism of the construction machinery vehicle according to the risk level; and controls the construction machinery vehicle to perform operations according to the control strategy based on the allocated power.

[0199] In some embodiments, the risk level includes a first risk level and a second risk level, the first risk level is greater than the second risk level, and the prediction accuracy risk value corresponding to the second risk level is greater than the first deviation threshold. In response to the risk level being the first risk level, the control unit 53 uses the auxiliary working mechanism of the construction machinery vehicle to compensate for the working accuracy deviation of the construction machinery vehicle; in response to the risk level being the second risk level, it adjusts the working parameters of the working mechanism.

[0200] In some embodiments, the control unit 53 selects a power supply strategy based on the relationship between the allocated power and the required power, wherein the required power is determined based on the dynamic parameters of each system; and controls the construction machinery vehicle to operate in the future time period according to the power supply strategy.

[0201] In some embodiments, the dynamic parameters include the driving speed of the construction machinery vehicle. In response to the first distribution power of the driving system being less than the first demand power of the driving system and the second distribution power of the power output system being greater than the second demand power of the power output system, the control unit 53 determines the first distribution power as the target power of the driving system and the second demand power as the target power of the power output system; and adjusts the driving speed of the construction machinery vehicle to reduce the first demand power of the driving system so that the reduced first demand power is not greater than the first distribution power.

[0202] In some embodiments, the dynamic parameters include the rotational speed of the power output system. In response to the second distribution power of the power output system being less than the second demand power of the power output system and the first distribution power of the driving system being greater than the first demand power of the driving system, the control unit 53 determines the first demand power as the target power of the driving system and the second distribution power as the target power of the power output system; and adjusts the rotational speed of the power output system to reduce the second demand power of the power output system so that the reduced second demand power is not greater than the second distribution power.

[0203] In some embodiments, the control unit 53, in response to the first allocated power of the driving system being less than the first demand power of the driving system and the second allocated power of the power output system being less than the second demand power of the power output system, determines the allocated power of each system as the first target power of each system; adjusts the engine speed and motor output power of the construction machinery vehicle to increase the output power of the construction machinery vehicle; and in response to the adjusted engine speed reaching a speed threshold, determines whether to use the power supply device to power the construction machinery vehicle based on the relationship between the first target power and the demand power corresponding to the increased output power.

[0204] In some embodiments, the control unit 53, in response to a first target power corresponding to the increased output power being less than the required power, provides a second target power to each system using a power supply device, such that the sum of the first target power and the second target power meets the required power.

[0205] In some embodiments, the control unit 53 determines the supplementary power output by the power supply device based on the power difference between the first target power and the required power; determines the supplementary power allocation ratio in each system based on the power level corresponding to the power information of the power supply device; determines the second target power based on the supplementary allocation ratio and the supplementary power; and supplies power to each system according to the second target power using the power supply device.

[0206] In some embodiments, the control unit 53 controls the power supply device to stop supplying power in response to at least one of the following conditions: the power difference is less than a difference threshold; the power supply device's power information is less than a power threshold; the power supply device's temperature information is greater than a temperature threshold; the operational accuracy deviation of the construction machinery vehicle is less than a first deviation threshold.

[0207] In some embodiments, for the same power difference, the supplementary power is positively correlated with the power level.

[0208] In some embodiments, the power level includes a first power level and a second power level, the first power level is greater than the second power level, and the power information corresponding to the second power level is greater than the power threshold. In response to the power level being the first power level, the control unit 53 determines the supplementary allocation ratio according to the type of the working mechanism of the construction machinery vehicle; in response to the power level being the second power level, the supplementary allocation ratio is the same for each system.

[0209] In some embodiments, the future time period includes a first time period and a second time period adjacent to the first time period. During the first time period, the control unit 53 controls the construction machinery vehicle to operate according to the allocated power; obtains the actual value of the operation accuracy deviation of the construction machinery vehicle at the second time point as a reference deviation, and the second time point is the end of the first time period; determines whether the allocated power needs to be updated based on whether the reference deviation is greater than a first deviation threshold; in response to the need to adjust the allocated power, adjusts the allocated power according to the reference deviation to obtain the adjusted power; and during the second time period, controls the construction machinery vehicle to operate according to the adjusted power.

[0210] In some embodiments, the control unit 53 controls the construction machinery vehicle to operate at an adjusted power during a sub-time period of the second time period; determines a predicted value of the operation accuracy deviation of the construction machinery vehicle at the end of the sub-time period based on the dynamic parameters of the construction machinery vehicle at the end of the sub-time period; updates the adjusted power in response to the predicted value being greater than a first deviation threshold; and repeats the above steps until the predicted value of the operation accuracy deviation at the next time period after the end of the sub-time period is not greater than the first deviation threshold.

[0211] In some embodiments, the machine learning model is trained by: collecting the actual value of the operational accuracy deviation of the engineering machinery vehicle at the sample time point and the dynamic parameters at the previous time point to form a training dataset for the machine learning model; using the dynamic parameters at the previous time point as the input of the machine learning model, using the actual value as the target output of the machine learning model, and using minimizing the first difference between the actual value and the predicted value of the operational accuracy deviation output by the machine learning model as the training objective to train the machine learning model.

[0212] In some embodiments, training a machine learning model includes: determining an actual accuracy risk value for a sample time point based on the actual value and a second deviation threshold; determining a predicted accuracy risk value for a sample time point based on the predicted value and a second deviation threshold; and retraining the machine learning model in response to a first difference being greater than a first difference threshold or a second difference between the actual accuracy risk value and the predicted accuracy risk value being greater than a second difference threshold, until the first difference is less than the first difference threshold and the second difference is less than the second difference threshold.

[0213] In the above embodiments, the operational accuracy deviation is dynamically predicted based on the dynamic parameters of the engineering machinery vehicle, and the power distribution scheme of the vehicle is adaptively determined based on the predicted value of the operational accuracy deviation. In this way, the power distribution of each system is reasonably determined, while ensuring the operational accuracy of the vehicle, thereby improving the stability of vehicle operation.

[0214] Figure 6 shows a block diagram of some other embodiments of the control device of this disclosure.

[0215] As shown in FIG6, the control device 6 of this embodiment includes a memory 61 and a processor 62 coupled to the memory 61. The processor 62 is configured to execute the control method in any embodiment of this disclosure based on instructions stored in the memory 61.

[0216] The memory 61 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory stores, for example, the operating system, application programs, boot loader, database, and other programs.

[0217] Figure 7 shows a block diagram of some further embodiments of the control device of this disclosure.

[0218] As shown in FIG7, the control device 7 of this embodiment includes a memory 710 and a processor 720 coupled to the memory 710. The processor 720 is configured to execute the control method of any of the foregoing embodiments based on instructions stored in the memory 710.

[0219] The memory 710 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory may store, for example, the operating system, application programs, boot loader, and other programs.

[0220] The control device 7 may also include an input / output interface 730, a network interface 740, and a storage interface 750. These interfaces 730, 740, and 750, as well as the memory 710 and processor 720, can be connected via, for example, a bus 760. The input / output interface 730 provides a connection interface for input / output devices such as a monitor, mouse, keyboard, touchscreen, microphone, and speakers. The network interface 740 provides a connection interface for various networked devices. The storage interface 750 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0221] Figure 8 shows a block diagram of some embodiments of the vehicle disclosed herein.

[0222] As shown in Figure 8, the vehicle 8 in this embodiment includes the control device 81 of any of the above embodiments.

[0223] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0224] The control method, control device, and vehicle according to this disclosure have now been described in detail. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0225] The methods and systems of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the specific order described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0226] While specific embodiments of this disclosure have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and are not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure.

Claims

1. A control method, comprising: Based on the dynamic parameters of the construction machinery vehicle at the first time point, a machine learning model is used to determine the predicted value of the operational accuracy deviation of the construction machinery vehicle at the next time point after the first time point. Based on the predicted value of the operational accuracy deviation, determine the power allocation of each system in the multiple systems of the engineering machinery vehicle; Based on the allocated power, the engineering machinery vehicle is controlled to operate within a future time period starting from the first time point.

2. The control method according to claim 1, wherein, The step of determining the allocated power of each system among the multiple systems of the construction machinery vehicle based on the predicted value of the operational accuracy deviation includes: The allocation ratio for each system is determined based on the risk level corresponding to the predicted value; The allocated power is determined based on the allocation ratio and the output power of the engineering machinery vehicle.

3. The control method according to claim 2, wherein, The multiple systems include a driving system and a power output system for outputting power to the working mechanism of the engineering machinery vehicle. The step of determining the allocation ratio of each system based on the risk level corresponding to the predicted value includes: The risk level is determined based on the prediction accuracy risk value corresponding to the predicted value; Based on the risk level, a first allocation ratio for the driving system and a second allocation ratio for the power output system are determined.

4. The control method according to claim 3, wherein, The first allocation ratio is positively correlated with the risk level, and the second allocation ratio is negatively correlated with the risk level.

5. The control method according to any one of claims 2-4, wherein, The step of controlling the construction machinery vehicle to operate within a future time period starting from the first time point, based on the allocated power, includes: Based on the risk level, determine the control strategy for the operating mechanism of the engineering machinery vehicle; Based on the allocated power and in accordance with the control strategy, the engineering machinery vehicle is controlled to perform operations.

6. The control method according to claim 5, wherein, The risk levels include a first risk level and a second risk level, where the first risk level is greater than the second risk level, and the prediction accuracy risk value corresponding to the second risk level is greater than a first deviation threshold. The control strategy for determining the operating mechanism of the construction machinery vehicle based on the risk level includes: In response to the risk level being the first risk level, the auxiliary working mechanism of the construction machinery vehicle is used to compensate for the deviation in the working accuracy of the construction machinery vehicle. In response to the risk level being the second risk level, the operating parameters of the operating mechanism are adjusted.

7. The control method according to any one of claims 1-6, wherein, The step of controlling the construction machinery vehicle to operate within a future time period starting from the first time point, based on the allocated power, includes: Based on the relationship between the allocated power and the required power, a power supply strategy is selected, wherein the required power is determined according to the dynamic parameters of each system; According to the power supply strategy, the engineering machinery vehicle is controlled to operate during the future time period.

8. The control method according to claim 7, wherein, The dynamic parameters include the travel speed of the engineering machinery vehicle. The step of selecting a power supply strategy based on the relationship between the allocated power and the demanded power includes: In response to the first allocated power of the driving system being less than the first demand power of the driving system and the second allocated power of the power output system being greater than the second demand power of the power output system, the first allocated power is determined as the target power of the driving system, and the second demand power is determined as the target power of the power output system; The driving speed of the engineering machinery vehicle is adjusted to reduce the first required power of the driving system, so that the reduced first required power is not greater than the first allocated power.

9. The control method according to claim 7 or 8, wherein, The dynamic parameters include the rotational speed of the power output system. The step of selecting a power supply strategy based on the relationship between the allocated power and the demanded power includes: In response to the second power allocation of the power output system being less than the second demand power of the power output system and the first power allocation of the driving system being greater than the first demand power of the driving system, the first demand power is determined as the target power of the driving system, and the second power allocation is determined as the target power of the power output system; Adjust the rotational speed of the power output system to reduce the second required power of the power output system, so that the reduced second required power is not greater than the second allocated power.

10. The control method according to any one of claims 7-9, wherein, The step of selecting a power supply strategy based on the relationship between the allocated power and the demanded power includes: In response to the first allocated power of the driving system being less than the first demanded power of the driving system and the second allocated power of the power output system being less than the second demanded power of the power output system, the allocated power of each system is determined as the first target power of each system; Adjust the engine speed and motor output power of the construction machinery vehicle to increase the output power of the construction machinery vehicle; In response to the adjusted engine speed reaching the speed threshold, a determination is made on whether to use a power supply device to power the construction machinery vehicle based on the relationship between the first target power corresponding to the increased output power and the required power.

11. The control method according to claim 10, wherein, The step of determining whether to use a power supply device to power the construction machinery vehicle based on the relationship between the first target power corresponding to the improved output power and the required power includes: In response to the first target power corresponding to the increased output power being less than the required power, the power supply device provides a second target power to each system, such that the sum of the first target power and the second target power meets the required power.

12. The control method according to claim 11, wherein, The provision of the second target power to each of the systems using the power supply device includes: The supplementary power output by the power supply device is determined based on the power difference between the first target power and the required power. Based on the power level corresponding to the power information of the power supply device, the supplementary power allocation ratio in each system is determined; The second target power is determined based on the supplementary allocation ratio and the supplementary power; Using the power supply device, each system is powered according to the second target power.

13. The control method according to claim 12, wherein, The step of supplying power to each system using the power supply device according to the second target power includes: The power supply device is controlled to stop supplying power in response to at least one of the following conditions: The power difference is less than the difference threshold; The power supply device's power level is less than the power threshold. The temperature information of the power supply device is greater than the temperature threshold. The operational accuracy deviation of the engineering machinery vehicle is less than the first deviation threshold.

14. The control method according to claim 12 or 13, wherein, For the same power difference, the supplementary power is positively correlated with the power level.

15. The control method according to any one of claims 12-14, wherein, The battery level includes a first battery level and a second battery level, where the first battery level is greater than the second battery level, and the battery level corresponding to the second battery level is greater than a battery threshold. The step of determining the supplementary power allocation ratio in each system based on the power level corresponding to the power information of the power supply device includes: In response to the power level being the first power level, the supplementary allocation ratio is determined according to the type of the working mechanism of the engineering machinery vehicle; In response to the power level being the second power level, the supplementary allocation ratio for each system is the same.

16. The control method according to any one of claims 1-15, wherein, The future time period includes a first time period and a second time period adjacent to the first time period. The step of controlling the construction machinery vehicle to operate within a future time period starting from the first time point, based on the allocated power, includes: During the first time period, the engineering machinery vehicle is controlled to operate according to the allocated power. The actual value of the operational accuracy deviation of the engineering machinery vehicle at the second time point is obtained as a reference deviation, and the second time point is the end point of the first time period; Whether the allocated power needs to be updated is determined based on whether the reference deviation is greater than a first deviation threshold; In response to the need to adjust the allocated power, the allocated power is adjusted according to the reference deviation to obtain the adjusted power; During the second time period, the engineering machinery vehicle is controlled to operate according to the adjusted power.

17. The control method according to claim 16, wherein, The step of controlling the construction machinery vehicle to operate according to the adjusted power during the second time period includes: During the sub-time period of the second time period, the engineering machinery vehicle is controlled to operate according to the adjusted power. Based on the dynamic parameters of the engineering machinery vehicle at the end of the sub-time period, determine the predicted value of the operational accuracy deviation of the engineering machinery vehicle at the next time point at the end of the sub-time period. In response to the predicted value being greater than the first deviation threshold, the adjustment power is updated; Repeat the above steps until the predicted value of the job accuracy deviation at the next time point after the end of the sub-time period is not greater than the first deviation threshold.

18. The control method according to any one of claims 1-17, wherein, The machine learning model is trained using the following method: The actual values ​​of the operational accuracy deviation of the engineering machinery vehicle at the sample time point and the dynamic parameters of the previous time point are collected to form the training dataset of the machine learning model. The machine learning model is trained by using the dynamic parameters at the previous time point as input, the actual value as target output, and minimizing the first difference between the actual value and the predicted value of the job accuracy deviation output by the machine learning model as training objective.

19. The control method according to claim 18, wherein, Training the machine learning model includes: Based on the actual value and the second deviation threshold, the actual accuracy risk value of the sample time point is determined; Based on the predicted value and the second deviation threshold, the prediction accuracy risk value for the sample time point is determined; In response to a first difference greater than a first difference threshold or a second difference between the actual accuracy risk value and the predicted accuracy risk value greater than a second difference threshold, the machine learning model is retrained until the first difference is less than the first difference threshold and the second difference is less than the second difference threshold.

20. A control device, comprising: The first determining unit is used to determine the predicted value of the operation accuracy deviation of the construction machinery vehicle at the next time point at the first time point by using a machine learning model based on the dynamic parameters of the construction machinery vehicle at the first time point. The second determining unit is used to determine the allocated power of each of the multiple systems of the engineering machinery vehicle based on the predicted value of the operation accuracy deviation. The control unit is configured to control the construction machinery vehicle to operate within a future time period starting from the first time point, based on the allocated power.

21. A control device, comprising: Memory; and A processor coupled to the memory, the processor being configured to execute the control method of any one of claims 1-19 based on instructions stored in the memory.

22. An engineering machinery vehicle, comprising: The control device according to claim 20 or 21.

23. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the control method according to any one of claims 1-19.

24. A computer program product comprising instructions that, when executed by a processor, cause the processor to perform the control method according to any one of claims 1-19.

Images