Excavator weighing method, device, equipment and medium

Abstract

The embodiment of the invention provides an excavator weighing method and device, equipment and a medium. The method comprises the steps that firstly, when it is determined that the excavator enters the rotation action, a pressure stability control strategy is adopted to control a hydraulic system of the excavator, so that a weighing measurement window with stable pressure is formed in the rotation action; acquiring pressure data in the weighing measurement window; and finally, the pressure data, the dynamic operation data and the equipment parameters are input into the trained weighing model, and the material weight corresponding to the excavator is obtained. Through the method, the material weighing precision of the excavator is improved.

Description

Technical Field

[0001] This application relates to the field of engineering machinery technology, and in particular to a weighing method, device, equipment and medium for excavators. Background Technology

[0002] Tracked excavators are core excavation and loading equipment in mining, earthmoving, and construction sites, and their operational efficiency and accuracy directly impact project progress and costs. In practice, after operators excavate and load materials using the bucket, they must ensure the material weight remains within the limits set by road transport regulations. Traditional operating methods rely on operator experience or weighing on a weighbridge after excavation, requiring repeated trial loading and adjustments to the bucket load, thus extending the loading cycle. Weighbridge weighing, on the other hand, requires additional waiting time and cannot provide real-time weight information. Therefore, there is an urgent need for a system that can proactively create stable measurement conditions during dynamic operations to improve operational efficiency and accuracy, meeting the high demands of engineering scenarios.

[0003] In existing technologies, hydraulic system pressure and angle sensors are typically used to collect data, and the load weight is calculated using a mechanical model. The core idea is to derive the material weight based on parameters such as boom cylinder pressure and boom and stick angles when the bucket is raised to a specific height, combined with excavator structural mechanics formulas.

[0004] However, existing weighing technologies are unable to cope with the dynamic complexity and machine model differences in actual operations, resulting in weighing accuracy and efficiency failing to meet engineering requirements. Summary of the Invention

[0005] This application provides a weighing method, apparatus, equipment, and medium for excavators to address the problem in the prior art that it is difficult to cope with the dynamic complexity and model differences in actual operations, resulting in weighing accuracy and efficiency failing to meet engineering requirements.

[0006] In a first aspect, embodiments of this application provide a method for weighing an excavator, including:

[0007] When the excavator enters the slewing motion, a pressure stabilization control strategy is adopted to control the hydraulic system of the excavator in order to form a pressure-stable weighing measurement window during the slewing motion.

[0008] Acquire pressure data within the weighing measurement window;

[0009] The pressure data, dynamic operation data, and equipment parameters are input into the trained weighing model to obtain the material weight corresponding to the excavator. The dynamic operation data is the operation data of the excavator before it enters the slewing action.

[0010] In one possible implementation, the use of a pressure stabilization control strategy to control the excavator's hydraulic system to create a pressure-stabilized weighing measurement window during the slewing motion includes:

[0011] Obtain the current pressure value of the target hydraulic actuator in the hydraulic system, and determine the current pressure value as the pressure reference value;

[0012] Based on the deviation between the pressure reference value and the hydraulic pressure value collected in real time during the rotation process, the sliding surface of the sliding mode variable structure control algorithm is constructed.

[0013] A control quantity is generated based on the sliding surface, and the control quantity is applied to the control loop corresponding to the target hydraulic actuator to suppress hydraulic pressure fluctuations caused during the rotation process;

[0014] When the amplitude of the hydraulic pressure fluctuation is less than a preset threshold and continues to meet a preset time condition, a weighing measurement window for pressure stabilization is determined.

[0015] In one possible implementation, the sliding surface of the sliding mode variable structure control algorithm is designed as follows:

[0016]

[0017]

[0018] in, The pressure reference value is... The hydraulic pressure value is... is a preset positive control parameter, and s is the sliding surface;

[0019] The process of generating the control quantity is as follows:

[0020]

[0021]

[0022] in, For equivalent control items, To switch gain parameters, For boundary layer thickness parameters, It is a saturation function.

[0023] In one possible implementation, acquiring pressure data within the weighing measurement window includes:

[0024] Within the weighing measurement window, the pressure signal of the boom cylinder of the excavator is collected;

[0025] The pressure signal is subjected to amplitude limiting filtering and low-pass filtering in sequence to obtain the pressure data, which includes at least the pressure mean, pressure standard deviation and displacement.

[0026] In one possible implementation, inputting the pressure data, dynamic operation data, and equipment parameters into a trained weighing model to obtain the material weight corresponding to the excavator includes:

[0027] The pressure data, the dynamic operation data, and the equipment parameters are fused to obtain a fused feature vector.

[0028] The feature vector is input into the trained weighing model, and the estimated weight of the material and the material type identification result are output.

[0029] Based on the material type identification result, a material compensation strategy is executed on the estimated material weight to obtain the material weight corresponding to the excavator.

[0030] The material compensation strategy is as follows: when the material type is a spillable material type, spillage compensation is performed; when the material type is an adhesive material type, adhesion residue compensation is performed.

[0031] In one possible implementation, the training process of the weighing model includes:

[0032] Historical operation data from various models of excavators is collected, including pressure data, equipment parameters, dynamic operation data, and the corresponding types and weights of real materials.

[0033] Using the historical operation data as training samples and the type and weight of the real materials as sample labels, the initial model based on the Transformer neural network architecture is trained to obtain the trained weighing model.

[0034] In one possible implementation, the process of determining that the excavator has entered the slewing motion includes:

[0035] The control signals of the excavator's bucket angle, boom angle, and swing control handle are acquired in real time.

[0036] When the bucket angle is detected to be greater than a first preset threshold, the boom angle is detected to be greater than a second preset threshold, and the control signal of the slewing control handle is in a non-neutral state, it is determined that the excavator has entered the slewing action.

[0037] Secondly, embodiments of this application provide an excavator weighing device, comprising:

[0038] The control module is used to control the hydraulic system of the excavator using a pressure stabilization control strategy when it is determined that the excavator has entered the slewing action, so as to form a pressure-stabilized weighing measurement window during the slewing action.

[0039] The acquisition module is used to acquire pressure data within the weighing measurement window;

[0040] The processing module is used to input the pressure data, dynamic operation data and equipment parameters into the trained weighing model to obtain the material weight corresponding to the excavator. The dynamic operation data is the operation data of the excavator before entering the slewing action.

[0041] In one possible implementation, the control module is specifically used for:

[0042] Obtain the current pressure value of the target hydraulic actuator in the hydraulic system, and determine the current pressure value as the pressure reference value;

[0043] Based on the deviation between the pressure reference value and the hydraulic pressure value collected in real time during the rotation process, the sliding surface of the sliding mode variable structure control algorithm is constructed.

[0044] A control quantity is generated based on the sliding surface, and the control quantity is applied to the control loop corresponding to the target hydraulic actuator to suppress hydraulic pressure fluctuations caused during the rotation process;

[0045] When the amplitude of the hydraulic pressure fluctuation is less than a preset threshold and continues to meet a preset time condition, a weighing measurement window for pressure stabilization is determined.

[0046] In one possible implementation, the sliding surface of the sliding mode variable structure control algorithm is designed as follows:

[0047]

[0048]

[0049] in, The pressure reference value is... The hydraulic pressure value is... is a preset positive control parameter, and s is the sliding surface;

[0050] The process of generating the control quantity is as follows:

[0051]

[0052]

[0053] in, For equivalent control items, To switch gain parameters, For boundary layer thickness parameters, It is a saturation function.

[0054] In one possible implementation, the acquisition module is specifically used for:

[0055] Within the weighing measurement window, the pressure signal of the boom cylinder of the excavator is collected;

[0056] The pressure signal is subjected to amplitude limiting filtering and low-pass filtering in sequence to obtain the pressure data, which includes at least the pressure mean, pressure standard deviation and displacement.

[0057] In one possible implementation, the processing module is specifically used for:

[0058] The pressure data, the dynamic operation data, and the equipment parameters are fused to obtain a fused feature vector.

[0059] The feature vector is input into the trained weighing model, and the estimated weight of the material and the material type identification result are output.

[0060] Based on the material type identification result, a material compensation strategy is executed on the estimated material weight to obtain the material weight corresponding to the excavator.

[0061] The material compensation strategy is as follows: when the material type is a spillable material type, spillage compensation is performed; when the material type is an adhesive material type, adhesion residue compensation is performed.

[0062] In one possible implementation, the processing module is specifically used for:

[0063] Historical operation data from various models of excavators is collected, including pressure data, equipment parameters, dynamic operation data, and the corresponding types and weights of real materials.

[0064] Using the historical operation data as training samples and the type and weight of the real materials as sample labels, the initial model based on the Transformer neural network architecture is trained to obtain the trained weighing model.

[0065] In one possible implementation, the excavator weighing device further includes a determining module for:

[0066] The control signals of the excavator's bucket angle, boom angle, and swing control handle are acquired in real time.

[0067] When the bucket angle is detected to be greater than a first preset threshold, the boom angle is detected to be greater than a second preset threshold, and the control signal of the slewing control handle is in a non-neutral state, it is determined that the excavator has entered the slewing action.

[0068] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0069] The memory stores computer-executed instructions;

[0070] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0071] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0072] The excavator weighing method, device, equipment, and medium provided in this application embodiment address the issue that, while the working conditions are more controllable during the slewing phase compared to the digging and lifting phases, the hydraulic pressure is still susceptible to fluctuations due to inertia and coupled motion. Therefore, a pressure stabilization control strategy is first introduced when the excavator enters the slewing phase to actively control the hydraulic system, constraining the hydraulic pressure within a preset fluctuation range during slewing. This artificially creates a short-term pressure stability state under dynamic working conditions, forming a suitable weighing measurement window for weighing calculation. Subsequently, pressure data is acquired within this weighing measurement window. Since hydraulic pressure fluctuations are effectively suppressed at this time, the collected pressure data more accurately reflects the material's weight. The static or quasi-static effect of material load on the hydraulic system improves the reliability of basic measurement data. Finally, the pressure data, dynamic operation data generated by the excavator before entering the slewing action, and equipment parameters representing differences between different machine models are input into the trained weighing model. Through the comprehensive modeling and reasoning of the dynamic load formation process, stable bearing state, and individual differences of the equipment, the corresponding material weight is output. Thus, without relying on additional static weighing conditions, a high-precision estimate of the excavator's material weight is achieved, effectively reducing the impact of hydraulic fluctuations, dynamic changes in operation, and differences in machine models on the weighing results. Overall, this significantly improves the accuracy and applicability of excavator material weighing. Attached Figure Description

[0073] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0074] Figure 1aA schematic diagram of the hardware layout of an excavator provided in an embodiment of this application;

[0075] Figure 1b A schematic diagram of the software layout of an excavator provided in an embodiment of this application;

[0076] Figure 2 A schematic flowchart of the excavator weighing method provided in this application embodiment;

[0077] Figure 3 Flowchart of the excavator weighing method provided in the embodiments of this application Figure 2 ;

[0078] Figure 4 Simplified model schematic diagrams of various mechanical devices in an excavator provided in the embodiments of this application;

[0079] Figure 5 This is a schematic diagram of the structure of the excavator weighing device provided in the embodiments of this application;

[0080] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0081] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0082] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0083] Tracked excavators are core excavation and loading equipment in mining, earthmoving, and construction sites, and their operational efficiency and accuracy directly impact project progress and costs. In practice, after operators excavate and load materials using the bucket, they must ensure the material weight remains within the limits set by road transport regulations (such as overload restrictions). However, traditional operating methods rely on operator experience or weighing on a weighbridge after excavation, resulting in significant efficiency bottlenecks: operators need to repeatedly test loads and adjust bucket capacity, extending the loading cycle; weighbridge weighing requires additional waiting time and cannot provide real-time weight information. Furthermore, during dynamic operations (such as excavation, lifting, and rotation), the hydraulic system pressure fluctuates drastically due to sudden load changes, mechanical inertia, and differences in operator actions, leading to frequent fluctuations in weight values ​​calculated based on instantaneous pressure, resulting in low reliability. Simultaneously, the physical properties of different materials (such as sand, clay, and gravel) vary significantly, and existing systems lack the ability to identify and compensate for these material characteristics, further exacerbating weighing errors. Furthermore, due to differences in hydraulic system characteristics and structural parameters, different models or levels of wear of excavators require recalibration of the weighing algorithm for each machine, which severely restricts the promotion of the technology. Therefore, there is an urgent need for an intelligent weighing system that can proactively create stable measurement conditions during dynamic operations, adapt to different machine models, and take into account material characteristics, in order to improve operational efficiency and accuracy and meet the high requirements of engineering scenarios.

[0084] In existing technologies, hydraulic system pressure and angle sensors are typically used to collect data, and the load weight is calculated using a mechanical model. The core idea is to derive the material weight based on parameters such as boom cylinder pressure and boom and stick angles when the bucket is raised to a specific height, combined with excavator structural mechanics formulas.

[0085] However, in the existing weighing methods, the hydraulic system experiences severe pressure fluctuations during excavation, lifting, and rotation due to sudden load changes, hydraulic shocks, and differences in operator movements. As a result, the weight values ​​calculated based on instantaneous pressure fluctuate frequently, failing to provide stable and reliable measurement results.

[0086] Based on this, this application proposes a weighing method for excavators. Starting from the problems of existing technology, the inventors first identified that the core reason for the poor dynamic accuracy is that the hydraulic pressure fluctuations cannot be effectively suppressed. Based on the above understanding, the inventors further realized that compared with the excavation and lifting stages, the slewing action has the characteristics of relatively simple working conditions, concentrated control degrees of freedom, and controllable hydraulic load changes in the work cycle, and has the feasibility of actively suppressing pressure fluctuations and constructing stable measurement conditions through control means. Therefore, when identifying when an excavator enters a slewing motion, a pressure stabilization control strategy is introduced to actively adjust the hydraulic system. Pressure feedback control suppresses hydraulic pressure fluctuations caused by inertia and structural coupling during slewing, artificially creating a short-term pressure stability interval—the weighing measurement window—during dynamic operation. After this window is established, pressure data is collected. This data is then combined with dynamic operation data generated before the excavator enters slewing and equipment parameters reflecting differences between different models, serving as unified input features to a trained weighing model for comprehensive reasoning. This allows the model to both characterize the current load state using pressure information from the stable phase and reflect material formation characteristics during dynamic operation, while also adaptively correcting for differences in the hydraulic structures of different excavators. This technical solution transforms the traditional passive weighing method, which relies on occasional stable conditions, into a weighing method that actively creates stable measurement conditions and performs multi-source information fusion reasoning through control measures. This effectively reduces the impact of hydraulic pressure fluctuations, dynamic changes in operation, and equipment differences on weighing accuracy, significantly improving the material weighing accuracy and engineering applicability of excavators in actual dynamic operation scenarios.

[0087] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0088] Figure 1a This is a schematic diagram of the hardware layout of the excavator provided in the embodiments of this application; as shown below. Figure 1a As shown, the hardware includes a digital hydraulic cylinder 10, a rotation angle sensor 20, an inertial measurement unit (IMU) 30, an auxiliary controller 40, and a main controller 50.

[0089] The digital cylinder 10 integrates high-precision displacement and pressure sensors, serving as the core execution and sensing component for acquiring key physical quantities for weighing in this application. The displacement sensor collects the telescopic displacement of the boom cylinder in real time, indirectly characterizing the attitude changes of the boom, stick, and other working mechanisms, providing a foundation for determining the bucket loading status, the pre-slewing operation stage, and constructing dynamic operation data. The pressure sensor collects the hydraulic pressure within the cylinder cavity in real time. This pressure directly reflects the force exerted by the material load on the hydraulic system and is the primary data source for subsequently forming a pressure-stable weighing measurement window and extracting stable pressure characteristics. Furthermore, the digital cylinder, as a hydraulic actuator, implements closed-loop adjustment of the pressure stabilization control strategy under the control of the auxiliary controller, making it a key execution unit for actively suppressing pressure fluctuations.

[0090] The slewing angle sensor 20 is used to detect the change in the slewing angle of the upper vehicle relative to the lower vehicle in real time. Its output signal is used to determine whether the excavator has entered the slewing action and the start and end time of the slewing action. Through the slewing angle or angular velocity information, the system can accurately identify the switching node from the loading stage to the slewing stage in the work cycle, thereby triggering the intervention of the pressure stabilization control strategy and providing a reliable basis for the time segmentation of dynamic work data, avoiding the impact on weighing accuracy due to misjudgment of the work status.

[0091] The inertial measurement unit 30 is used to acquire the excavator's attitude and motion information during operation. Its output includes at least acceleration and attitude angle information. The attitude data acquired by the IMU can, on the one hand, help determine whether the excavator's attitude changes during rotation are within the weighable range, avoiding additional inertial interference caused by drastic changes in the overall machine attitude; on the other hand, IMU data can serve as an important component of dynamic operation data, reflecting the inertial characteristics during rotation and operation, providing the weighing model with kinematic information complementary to hydraulic pressure, thereby improving the model's adaptability to dynamic working conditions.

[0092] The auxiliary controller 40's primary function is to temporarily take over control of the target hydraulic actuator circuit related to weighing when it detects that the excavator has entered a slewing motion and meets the weighing conditions. Based on the real-time pressure signal fed back from the digital cylinder 10, the auxiliary controller constructs a pressure stabilization control strategy, such as sliding mode variable structure control, to suppress pressure fluctuations caused by the slewing motion by adjusting the control quantity of the hydraulic actuators, thereby actively forming a pressure-stable weighing measurement window under dynamic operating conditions. Simultaneously, the auxiliary controller maintains communication and coordination with the main controller to ensure a smooth exit from control after weighing is completed, guaranteeing the safety and continuity of the entire machine's operation.

[0093] The main controller 50 is the excavator's original control unit, responsible for executing the operator's control commands and completing the excavator's routine operation control. On one hand, the main controller provides the auxiliary controller with data such as slewing control commands, operational status information, and equipment parameters, serving as crucial evidence for determining when to initiate slewing and constructing model input characteristics. On the other hand, it works collaboratively with the auxiliary controller during its intervention to avoid control conflicts and restores full control of the hydraulic system after the auxiliary controller withdraws. Through the coordinated operation of the main and auxiliary controllers, the weighing process is embedded into the excavator's normal operating procedures, achieving high-precision dynamic weighing without affecting the operator's work habits.

[0094] Figure 1b This is a schematic diagram of the software layout of an excavator provided in an embodiment of this application; as shown below. Figure 1b As shown, the main control software is first deployed in the Huaxing VCU (Vehicle Control Unit). This main control software is the original control logic of the excavator, responsible for receiving input from the operating handle, executing the coordinated control of the engine ECM, managing the routine actions of the hydraulic actuators, and scheduling the overall machine operation status. The main control software periodically collects and manages basic operating data from the swing angle sensor, each digital cylinder (boom, stick, bucket), and the vehicle's IMU via the vehicle bus (such as the CAN bus, with a data transmission rate of 250 kbps). At the same time, it provides information such as swing command status, operation stage status, and equipment parameters, providing the necessary software interface and data source for the dynamic weighing function.

[0095] Secondly, the auxiliary control and weighing core algorithm software is deployed in the Goufeng ACU (Auxiliary Control Unit). This software operates as a functional module independent of the main control logic, integrating a work phase identification module, a pressure stabilization control module, and a weighing model inference module. Logically, the ACU receives real-time data from the VCU regarding the slewing motion command status, displacement and pressure data of the working mechanism, and IMU attitude information via a bus. When it detects that the excavator has entered a slewing motion and meets the weighing conditions, it triggers the pressure stabilization control subroutine. This subroutine constructs a pressure feedback control algorithm (such as sliding mode variable structure control) at the software level, generates control commands, and applies them to the target hydraulic circuit via a collaborative interface with the VCU. This suppresses hydraulic pressure fluctuations during slewing, forming a pressure-stable weighing measurement window. Simultaneously, the ACU software filters the pressure signal and, in conjunction with the dynamic work data and equipment parameters before slewing, calls a pre-trained weighing model to calculate the material weight.

[0096] Furthermore, the human-machine interface and display software is deployed on the HMI display screen. The HMI software obtains weighing results, system status information, and necessary prompts through a communication interface with the VCU or ACU, and presents them to the operator in a visual manner. For example, it displays the current loaded weight, cumulative load, weighing completion prompts, or system error prompts. This software only handles information display and simple interaction functions and does not directly participate in weighing calculations and control decisions, thus ensuring the independence and security of the core weighing algorithm.

[0097] In addition, the power management-related software logic is deployed in the E-power power module and its associated control unit to provide stable power supply to weighing-related components such as ACU, sensors, and HMI. At the software level, it works in conjunction with the power-on, power-off, and fault management strategies of the whole machine to ensure the reliable operation of the weighing system under different working conditions.

[0098] By employing the aforementioned software deployment method, this application modularly deploys dynamic weighing-related software functions within an independent auxiliary control unit without altering the original VCU main control software architecture. These functions then collaborate with the main control system, sensor system, and human-machine interface system via standard communication interfaces, achieving low-intrusion integration of the dynamic weighing function. This software deployment not only facilitates independent upgrades and maintenance of the weighing algorithm but also effectively avoids interference with the original machine control logic, ensuring the stability, scalability, and engineering feasibility of the excavator's dynamic weighing function at the system level.

[0099] It should be noted that the aforementioned main controller 50 and auxiliary controller 40 can be independent control units in terms of hardware implementation, or they can be integrated into the same control hardware depending on the integration level of the overall electronic and electrical architecture. In one possible implementation, the main controller 50 and auxiliary controller 40 are jointly deployed in the same physical controller, implemented as different software functional modules or logical partitions. The main control software corresponding to the main controller is used to execute the excavator's conventional overall machine control functions, while the auxiliary control and weighing algorithm software corresponding to the auxiliary controller is used to realize functions such as operation stage identification, pressure stabilization control, and weighing model reasoning. In another possible implementation, the main controller 50 and auxiliary controller 40 are deployed in different physical control units and communicate and coordinate through the vehicle bus. Regardless of the implementation method, it does not affect the technical effect of this application, which is to form a pressure-stable weighing measurement window and complete dynamic weighing during the slewing operation stage by working together with the main control function and the auxiliary control function. The description of the main controller, auxiliary controller, and their corresponding software modules in this application is intended to illustrate the system from the perspective of functional division and does not constitute a limitation on the specific hardware integration form.

[0100] Figure 2A flowchart illustrating the excavator weighing method provided in this application embodiment is shown below; Figure 2 As shown, the method includes:

[0101] S201. When it is determined that the excavator has entered the slewing motion, a pressure stabilization control strategy is adopted to control the hydraulic system of the excavator in order to form a pressure-stable weighing measurement window during the slewing motion.

[0102] In one possible approach, the excavator's bucket angle, boom angle, and control signals of the swing control handle are first acquired in real time; then, when the bucket angle is detected to be greater than a first preset threshold, the boom angle is detected to be greater than a second preset threshold, and the control signal of the swing control handle is in a non-neutral state, the excavator is determined to enter the swing action.

[0103] It should be noted that since the bucket angle and boom angle exceeding preset thresholds indicate that the bucket has completed material loading and been raised to a safe height, while the non-neutral signal of the swing handle directly reflects the operator's intention to swing. By combining multiple conditions for judgment, false triggering of weighing control can be avoided under conditions of insufficient loading or non-swing, thereby improving the accuracy of weighing timing judgment. Furthermore, the bucket angle and boom angle can be calculated from the displacement signal of the digital cylinder combined with the geometric relationship of the excavator mechanism; the specific calculation process is detailed in [details omitted]. Figure 4 As explained in the text, the control signal for the rotary operating handle is acquired by the main controller.

[0104] It should be understood that after the excavator enters the swing motion, the core controller switches from the "human-controlled operation segment" to the "auxiliary control segment." During this stage, an independent auxiliary controller takes over control of the swing control valve. This involves using a pressure stabilization control strategy to control the target hydraulic actuator in the hydraulic system, suppressing hydraulic pressure fluctuations during swing. Because the swing phase, compared to the digging and lifting phases, has relatively simple working conditions and is more controllable, this strategy can proactively establish a relatively stable pressure time interval under dynamic operating conditions, serving as a weighing measurement window.

[0105] Understandably, by dividing the excavator's operating cycle into a "human-controlled operating segment" and an "auxiliary control segment," and proactively adopting a pressure stabilization strategy based on sliding mode control when a slewing intention is detected, a stable and reliable dynamic weighing measurement window is created, thereby solving the problem of poor dynamic weighing accuracy caused by hydraulic pressure fluctuations.

[0106] S202. Obtain pressure data within the weighing measurement window.

[0107] In one feasible approach, the pressure signal of the excavator's boom cylinder is first acquired within the weighing measurement window; then, the pressure signal is sequentially subjected to amplitude limiting filtering and low-pass filtering to obtain pressure data.

[0108] The pressure data should include at least the mean pressure, the standard deviation of pressure, and the displacement.

[0109] It should be understood that, as a key actuator that directly bears the weight of the material, the pressure changes in the boom cylinder can effectively reflect the effect of the material load on the hydraulic system. Therefore, within the weighing measurement window, the system collects the pressure signal of the boom cylinder in real time through pressure sensors installed on the boom cylinder.

[0110] Furthermore, since transient interference and measurement noise may still exist in the hydraulic system under actual working conditions, the system sequentially performs amplitude limiting filtering and low-pass filtering on the acquired pressure signal. The amplitude limiting filter, a nonlinear filtering method, is mainly used to remove sudden outliers or spike noise from the signal. It suppresses sudden interference by limiting the maximum variation between adjacent sampling points. By comparing the difference between the current sampled value and the filtered output value from the previous moment, if the difference exceeds a set threshold (amplitude limit), the current sampled value is considered abnormal, and the value from the previous moment is used instead of the current value; otherwise, the current sampled value is used. The IIR (Infinite Impulse Response Lowpass Filter) is a linear time-invariant system used to eliminate high-frequency noise components, thereby retaining effective pressure information related to material load.

[0111] After the above processing, pressure data for weighing calculation is obtained. This pressure data includes at least the mean pressure, the standard deviation of pressure, and the corresponding cylinder displacement information. The mean pressure characterizes the average load level during the steady-state phase, the standard deviation of pressure reflects the degree of stability, and the displacement information describes the influence of the cylinder posture on the relationship between pressure and load.

[0112] Understandably, by acquiring and processing the pressure signal of the boom cylinder only within the stable weighing measurement window, the obtained pressure data can accurately and stably reflect the effect of material load on the hydraulic system, thereby effectively reducing the impact of transient shocks, hydraulic oscillations, and measurement noise on the weighing results during dynamic operations.

[0113] S203. Input the pressure data, dynamic operation data and equipment parameters into the trained weighing model to obtain the material weight corresponding to the excavator.

[0114] Among them, dynamic operation data refers to the operation data of the excavator before it enters the slewing action.

[0115] It should be understood that by jointly modeling the pressure information during the stable phase, the dynamic operation process information, and the equipment difference information, the weighing model can comprehensively depict the load formation and bearing state, thereby improving the robustness of weighing; at the same time, the introduction of a compensation mechanism based on material type effectively corrects the systematic errors caused by the physical properties of different materials.

[0116] The excavator weighing method provided in this application, since the working conditions are more controllable during the slewing phase compared to the digging and lifting phases, but the hydraulic pressure is still easily affected by inertia and coupled motion, causing fluctuations, firstly, a pressure stabilization control strategy is introduced when the excavator enters the slewing motion. This actively controls the hydraulic system, constraining the hydraulic pressure within a preset fluctuation range during slewing, thereby artificially constructing a short-term pressure stability state under dynamic working conditions, forming a weighing measurement window suitable for weighing calculation. Subsequently, pressure data is acquired within this weighing measurement window. Since hydraulic pressure fluctuations are effectively suppressed at this time, the collected pressure data can more accurately reflect the effect of material load on the hydraulic system. The static or quasi-static effect generated by the pressure system improves the reliability of the basic measurement data. Finally, the pressure data, dynamic operation data generated by the excavator before entering the slewing action, and equipment parameters representing differences between different machine models are input into the trained weighing model. Through the comprehensive modeling and reasoning of the dynamic load formation process, stable bearing state, and individual differences of the equipment, the corresponding material weight is output. Thus, without relying on additional static weighing conditions, a high-precision estimate of the excavator's material weight can be achieved, effectively reducing the impact of hydraulic fluctuations, dynamic changes in operation, and differences in machine models on the weighing results. Overall, this significantly improves the accuracy and applicability of excavator material weighing.

[0117] In one feasible approach, the process of obtaining the material weight corresponding to the excavator includes:

[0118] First, pressure data, dynamic operation data, and equipment parameters are fused to obtain a fused feature vector. Then, the feature vector is input into the trained weighing model to output the material weight estimate and material type identification result. Finally, based on the material type identification result, a material compensation strategy is executed on the material weight estimate to obtain the material weight corresponding to the excavator.

[0119] The material compensation strategy is as follows: when the material type is easily spilled, spillage compensation is performed; when the material type is easily adhered, adhesion residue compensation is performed.

[0120] It should be understood that although the base weight value obtained at a single stable moment or within a stable range can reflect the effect of the material on the hydraulic system under the current load condition, in actual operation, different materials will produce systematic errors during rotation or unloading due to differences in their physical properties (such as spillage and adhesion). Therefore, it is necessary to introduce a dynamic compensation mechanism based on material type on the basis of the base weight.

[0121] In specific implementation, the system first fuses the pressure data obtained in step S202, the dynamic operation data generated by the excavator before entering the slewing action, and the equipment parameters to construct a unified feature vector. Then, the feature vector is input into the trained weighing model for inference. This weighing model is a pre-trained multi-task learning model, using a Transformer-Encoder as the backbone network to model the temporal data of the manually controlled operation segment, and capturing long-range dependencies in the dynamic operation process through a self-attention mechanism. The multi-task learning model has multiple output heads, where the main task output head outputs the basic weight estimate, and the auxiliary task output head outputs the probability distribution results of the material type. After obtaining the material type identification result, the system executes the corresponding material compensation strategy based on the material type. When the identified material type is sand or gravel, or other easily spilled materials, the system does not directly... Instead of using the final weight, a decay model is constructed to compensate for the weight drop over time or during rotation, dynamically adjusting the base weight. This decay model can be expressed as:

[0122]

[0123] or

[0124] The attenuation coefficient k or λ is adaptively calculated by the weighing model based on dynamic characteristics such as material type probability, bucket filling degree, lifting angle, and slewing angular velocity. This is achieved at the moment the slewing unloading is completed. Corresponding weight Determined as the final effective weight And used for display and recording.

[0125] When the identified material type is easily adhered, such as clay or wet soil, the system implements an adhesion residue compensation strategy. During a loading / unloading cycle, when the system detects the completion of the unloading action, it records the tare weight of the bucket at that moment. and the pre-stored empty bucket tare weight Compare and calculate the amount of adhesive residue in this operation cycle. After the next excavation is completed and the foundation weight is obtained. Then, the system automatically performs compensation calculations. To eliminate the influence of adhesion residue on the weighing results, the system continuously records the changes in residue under different material conditions and adaptively optimizes the adhesion compensation parameters.

[0126] The pressure data includes the average pressure, standard deviation of pressure, and cylinder displacement extracted within the weighing measurement window, used to characterize the stable load-bearing state; the dynamic operation data includes the characteristics of the digging resistance curve and the area of ​​the pressure envelope formed during the digging and lifting stages, used to depict the material formation process; the equipment parameters include at least the equipment model identification and working hours, used to reflect the hydraulic and structural differences between different models.

[0127] Furthermore, the weighing model incorporates equipment identity features as embedding vectors during training and inference, enabling the model to learn the mapping relationship between different equipment parameters, dynamic process features, and actual weight during the training phase. Thus, during the inference phase, only the corresponding equipment parameters need to be input to complete adaptive weighing of different excavator models, achieving calibration-free model expansion.

[0128] For example, in a loading operation, the system obtains the basic weight during the slewing phase. The model measures 5.2 tons and identifies the material type as sand and gravel. Based on the current bucket fill level and slewing rate, it calculates an attenuation coefficient to compensate for weight spillage, ultimately achieving the desired result at the unloading point. The weight was 5.0 tons; in another operation, the system identified the material as wet soil, detected adhering residue in the bucket after unloading, and automatically deducted the corresponding residue in the next weighing, thus obtaining a weighing result closer to the true value.

[0129] Understandably, by introducing a dynamic compensation mechanism based on material type on top of basic weight measurement, and combining dynamic operation data with equipment parameters for multi-task model inference, this embodiment can effectively eliminate systematic errors in weighing results caused by differences in the physical properties of different materials and the differences in the operation process. In particular, through dynamic attenuation compensation for easily spilled materials and residual compensation for easily adherent materials, the weighing result is transformed from a single-moment measurement to a comprehensive evaluation of the entire operation process, thereby significantly improving the weighing accuracy and stability of excavators under actual dynamic working conditions. At the same time, with the help of a machine type adaptive mechanism driven by equipment identity characteristics, the system can achieve high-precision weighing without separate calibration for different excavators, enhancing the versatility and engineering application value of this method under multiple machine types and working conditions.

[0130] Figure 3 Flowchart of the excavator weighing method provided in the embodiments of this application Figure 2 ;like Figure 3 As shown, in this embodiment... Figure 2Based on the embodiments, a detailed description is provided of the method for forming a pressure-stable weighing measurement window, which includes:

[0131] S301. Obtain the current pressure value of the target hydraulic actuator in the hydraulic system and determine the current pressure value as the pressure reference value.

[0132] It should be understood that this embodiment is used to establish a pressure control reference after triggering the entry into the auxiliary control stage, so as to achieve stable pressure control with the initial load state as the target during the slewing process. Specifically, when the system enters the auxiliary control stage according to the operation stage identification result, the auxiliary controller 40 intervenes in the slewing control and takes over the handle signal output. At this time, the slewing control valve command is no longer directly based on the operator's handle opening, but is generated by the program set value output by the auxiliary controller 40, thereby avoiding drastic fluctuations in boom cylinder pressure caused by the operator performing other working device actions during the slewing period. Subsequently, the auxiliary controller 40 reads the current pressure value of the target hydraulic actuator in the hydraulic system in real time and determines this pressure value as the pressure reference value. .in, Characterizes the load-bearing state at the start of the auxiliary control phase, and subsequent control maintains it. Converging and stabilizing at The target is the vicinity. For ease of description, the system state variables of the auxiliary control section are established. ,in For rotation angle, For rotational angular velocity, The boom cylinder pressure is given; the control input u is the slewing control valve command; the external disturbance d represents the external load disturbance caused by load changes, hydraulic coupling, inertial impact, etc. The system can be represented by the state equation. Provide an abstract description.

[0133] Understandably, by locking the pressure reference value at the beginning of the auxiliary control section, the control objective changes from following the handle or transient pressure changes to maintaining a stable load state, providing a clear benchmark for the error definition and control convergence of the subsequent sliding mode variable structure control. At the same time, by cooperating with the controller to take over the handle output, pressure disturbances introduced by the operator's additional actions can be avoided, making it easier to form a stable pressure range during the rotation phase, thus laying the foundation for establishing a usable weighing measurement window.

[0134] S302. Based on the deviation between the pressure reference value and the hydraulic pressure value collected in real time during the rotation process, the sliding surface of the sliding mode variable structure control algorithm is constructed.

[0135] In one feasible approach, the sliding surface of the sliding mode variable structure control algorithm is designed as follows:

[0136]

[0137]

[0138] in, This is a pressure reference value. This is the hydraulic pressure value. is a preset positive control parameter, and s is the sliding surface.

[0139] In this embodiment, step S302 transforms the pressure stabilization control problem into an error-sliding surface constraint problem that can be handled by sliding mode control, thereby improving robustness to disturbances. Specifically, the controller collects the boom cylinder pressure in real time during the slewing process. and the pressure reference value determined by S301. The pressure error e is calculated. To ensure both rapid convergence of the pressure error and suppression of steady-state residuals, a sliding mode surface is further constructed to adjust the error convergence speed and dynamic response. Furthermore, considering the external load disturbance d during rotation, such as the additional torque generated by the material in the bucket under rotational inertia and pressure shocks caused by hydraulic circuit coupling, this embodiment further employs sliding mode variable structure control based on a disturbance observer: the controller estimates the disturbance term Dd through the disturbance observer, and uses the disturbance estimation result to correct the equivalent control term, thereby reducing the gain required for the switching term and minimizing chattering risk, thus improving pressure stability performance without sacrificing robustness.

[0140] It should be understood that by transforming the control objective from direct pressure regulation to forcing the system state to converge toward and move toward the sliding surface through the above process, the pressure error is theoretically guaranteed to have good convergence even in the presence of disturbances. At the same time, the introduction of a disturbance observer to estimate and feedforward compensate for external disturbances can reduce the impact of unknown disturbances on pressure fluctuations, improve control robustness, and reduce chattering caused by sliding mode switching, making it easier to achieve the stable conditions required to form the weighing measurement window.

[0141] S303. Generate a control quantity based on the sliding surface and apply the control quantity to the control loop corresponding to the target hydraulic actuator to suppress hydraulic pressure fluctuations caused during the rotation process.

[0142] In one feasible approach, the process of generating the control quantity is as follows:

[0143]

[0144]

[0145] in, For equivalent control items, To switch gain parameters, For boundary layer thickness parameters, It is a saturation function.

[0146] It should be understood that in this embodiment, the equivalent control term is used to maintain ideal closed-loop dynamics, allowing the system to operate along the expected trajectory without disturbance; the switching control term is used to suppress disturbances and ensure that the system state always converges to the sliding surface, and a saturation function is used to reduce high-frequency switching chattering caused by the traditional sign function. Furthermore, since this embodiment adopts a sliding mode control structure based on a disturbance observer, the equivalent control term can be compensated in conjunction with the disturbance observer output to maintain the rationality and stability of the control input even when disturbances change. The controller ultimately outputs the generated control quantity to the rotary control valve control loop, thereby indirectly affecting the evolution of the system state during the rotary process, thus affecting the pressure... Controlled and stable at Nearby. Meanwhile, to ensure safety and operability, the controller takes over the handle signal output in the auxiliary control section, preventing the operator from controlling the working device to avoid introducing additional pressure disturbances; in case of dangerous working conditions, the release condition can be triggered by simultaneously pulling the left and right handles inward, causing the controller to exit the auxiliary control section and resume manual control.

[0147] Understandably, by employing a sliding mode variable structure control algorithm with equivalent control and switching control, and replacing the ideal sign function with a saturation function, chattering can be significantly reduced while maintaining strong robustness. Combined with the estimation and compensation of external load disturbances by the disturbance observer, the ability to suppress disturbances such as inertial impact, load sway, and hydraulic coupling can be further improved, thereby controlling the boom cylinder pressure fluctuation within a smaller range during slewing. At the same time, by taking over the handle through the auxiliary control section and providing a quick release mechanism, pressure fluctuations introduced by human operation are reduced, while ensuring operational safety and system availability.

[0148] S304. When the amplitude of hydraulic pressure fluctuation is less than the preset threshold and the preset time condition is met continuously, a weighing measurement window with stable pressure is determined.

[0149] It should be understood that in this embodiment, the pressure is used to determine whether it has reached the data quality requirements for weighing and to determine the weighing measurement window accordingly. Specifically, during the execution of auxiliary slewing smooth control, the controller continuously monitors the fluctuation range of the boom cylinder pressure (e.g., the difference between the maximum and minimum values, or the short-time standard deviation can be used to characterize the fluctuation range) and compares it with a preset threshold. When the pressure fluctuation range is detected to be less than the preset threshold and is maintained continuously for more than a preset time length, it is determined that the pressure has entered a stable state, and this time interval is determined to form a stable pressure weighing measurement window.

[0150] Understandably, by applying dual conditions to determine the magnitude and duration of pressure fluctuations, the weighing data collection can be limited to a range where the pressure is sufficiently stable and the stable duration is sufficiently long. This excludes transient fluctuations caused by rotational inertial shocks and external disturbances from the weighing calculation, significantly improving the reliability of subsequent pressure feature extraction and weighing model inference input.

[0151] Figure 4 This is a simplified model diagram of the various mechanical devices in the excavator provided in the embodiments of this application; such as Figure 4 As shown, the boom angle With boom cylinder The relationship can be represented as:

[0152]

[0153] pole angle With boom cylinder The relationship can be represented as:

[0154]

[0155] Bucket angle With bucket cylinder The relationship can be represented as:

[0156]

[0157]

[0158] Figure 5 This is a schematic diagram of the structure of the excavator weighing device provided in the embodiments of this application; as shown. Figure 5 As shown, the device includes:

[0159] The control module 501 is used to control the hydraulic system of the excavator by adopting a pressure stabilization control strategy when it is determined that the excavator has entered the slewing action, so as to form a pressure-stable weighing measurement window during the slewing action.

[0160] The acquisition module 502 is used to acquire pressure data within the weighing measurement window;

[0161] The processing module 503 is used to input pressure data, dynamic operation data and equipment parameters into the trained weighing model to obtain the material weight corresponding to the excavator. The dynamic operation data is the operation data of the excavator before entering the slewing action.

[0162] In one possible implementation, the control module 501 is specifically used for:

[0163] Obtain the current pressure value of the target hydraulic actuator in the hydraulic system, and determine the current pressure value as the pressure reference value;

[0164] Based on the deviation between the pressure reference value and the hydraulic pressure value collected in real time during the rotation process, the sliding surface of the sliding mode variable structure control algorithm is constructed.

[0165] The control quantity is generated based on the sliding surface and applied to the control loop corresponding to the target hydraulic actuator to suppress hydraulic pressure fluctuations caused during the rotation process;

[0166] When the amplitude of hydraulic pressure fluctuation is less than a preset threshold and the preset time condition is met continuously, a weighing measurement window with stable pressure is determined.

[0167] In one possible implementation, the sliding surface of the sliding mode variable structure control algorithm is designed as follows:

[0168]

[0169]

[0170] in, This is a pressure reference value. This is the hydraulic pressure value. is a preset positive control parameter, and s is the sliding surface;

[0171] The process of generating the control quantity is as follows:

[0172]

[0173]

[0174] in, For equivalent control items, To switch gain parameters, For boundary layer thickness parameters, It is a saturation function.

[0175] In one possible implementation, the acquisition module 502 is specifically used for:

[0176] Within the weighing measurement window, the pressure signal of the excavator's boom cylinder is collected;

[0177] The pressure signal is subjected to amplitude limiting filtering and low-pass filtering in sequence to obtain pressure data. The pressure data includes at least the pressure mean, pressure standard deviation, and displacement.

[0178] In one possible implementation, the processing module 503 is specifically used for:

[0179] The pressure data, dynamic operation data, and equipment parameters are fused to obtain the fused feature vector.

[0180] The feature vector is input into the trained weighing model, and the output is the material weight estimate and the material type identification result;

[0181] Based on the material type identification results, a material compensation strategy is executed on the estimated material weight to obtain the material weight corresponding to the excavator.

[0182] The material compensation strategy is as follows: when the material type is easily spilled, spillage compensation is performed; when the material type is easily adhered, adhesion residue compensation is performed.

[0183] In one possible implementation, the processing module 503 is specifically used for:

[0184] Historical operation data is collected from various models of excavators. This historical operation data includes pressure data, equipment parameters, dynamic operation data, and the corresponding types and weights of real materials.

[0185] Using historical operational data as training samples and the type and weight of real materials as sample labels, the initial model based on the Transformer neural network architecture is trained to obtain a trained weighing model.

[0186] In one possible implementation, the excavator weighing device further includes a determining module for:

[0187] The system acquires control signals for the excavator's bucket angle, boom angle, and swing control handle in real time.

[0188] When the bucket angle is detected to be greater than the first preset threshold, the boom angle is detected to be greater than the second preset threshold, and the control signal of the slewing control handle is in a non-neutral state, the excavator is determined to enter the slewing action.

[0189] The excavator weighing device provided in this application embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0190] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0191] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0192] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0193] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0194] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0195] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0196] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0197] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0198] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0199] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0200] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0201] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0202] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0203] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0204] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for weighing an excavator, characterized in that, include: When the excavator enters the slewing motion, a pressure stabilization control strategy is adopted to control the hydraulic system of the excavator in order to form a pressure-stable weighing measurement window during the slewing motion. Acquire pressure data within the weighing measurement window; The pressure data, dynamic operation data, and equipment parameters are input into the trained weighing model to obtain the material weight corresponding to the excavator. The dynamic operation data is the operation data of the excavator before it enters the slewing action.

2. The method according to claim 1, characterized in that, The method of employing a pressure stabilization control strategy to control the hydraulic system of the excavator to form a pressure-stabilized weighing measurement window during the slewing motion includes: Obtain the current pressure value of the target hydraulic actuator in the hydraulic system, and determine the current pressure value as the pressure reference value; Based on the deviation between the pressure reference value and the hydraulic pressure value collected in real time during the rotation process, the sliding surface of the sliding mode variable structure control algorithm is constructed. A control quantity is generated based on the sliding surface, and the control quantity is applied to the control loop corresponding to the target hydraulic actuator to suppress hydraulic pressure fluctuations caused during the rotation process; When the amplitude of the hydraulic pressure fluctuation is less than a preset threshold and continues to meet a preset time condition, a weighing measurement window for pressure stabilization is determined.

3. The method according to claim 2, characterized in that, The sliding surface of the sliding mode variable structure control algorithm is designed as follows: in, The pressure reference value is... The hydraulic pressure value is... is a preset positive control parameter, and s is the sliding surface; The process of generating the control quantity is as follows: in, For equivalent control items, To switch gain parameters, For boundary layer thickness parameters, It is a saturation function.

4. The method according to claim 1, characterized in that, The step of acquiring pressure data within the weighing measurement window includes: Within the weighing measurement window, the pressure signal of the boom cylinder of the excavator is collected; The pressure signal is subjected to amplitude limiting filtering and low-pass filtering in sequence to obtain the pressure data, which includes at least the pressure mean, pressure standard deviation and displacement.

5. The method according to claim 1, characterized in that, The step of inputting the pressure data, dynamic operation data, and equipment parameters into the trained weighing model to obtain the material weight corresponding to the excavator includes: The pressure data, the dynamic operation data, and the equipment parameters are fused to obtain a fused feature vector. The feature vector is input into the trained weighing model, and the estimated weight of the material and the material type identification result are output. Based on the material type identification result, a material compensation strategy is executed on the estimated material weight to obtain the material weight corresponding to the excavator. The material compensation strategy is as follows: when the material type is a spillable material type, spillage compensation is performed; when the material type is an adhesive material type, adhesion residue compensation is performed.

6. The method according to claim 5, characterized in that, The training process of the weighing model includes: Historical operation data from various models of excavators is collected, including pressure data, equipment parameters, dynamic operation data, and the corresponding types and weights of real materials. Using the historical operation data as training samples and the type and weight of the real materials as sample labels, the initial model based on the Transformer neural network architecture is trained to obtain the trained weighing model.

7. The method according to claim 1, characterized in that, The process of determining when the excavator enters the slewing motion includes: The control signals of the excavator's bucket angle, boom angle, and swing control handle are acquired in real time. When the bucket angle is detected to be greater than a first preset threshold, the boom angle is detected to be greater than a second preset threshold, and the control signal of the slewing control handle is in a non-neutral state, it is determined that the excavator has entered the slewing action.

8. A weighing device for an excavator, characterized in that, include: The control module is used to control the hydraulic system of the excavator using a pressure stabilization control strategy when it is determined that the excavator has entered the slewing action, so as to form a pressure-stabilized weighing measurement window during the slewing action. The acquisition module is used to acquire pressure data within the weighing measurement window; The processing module is used to input the pressure data, dynamic operation data and equipment parameters into the trained weighing model to obtain the material weight corresponding to the excavator. The dynamic operation data is the operation data of the excavator before entering the slewing action.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images