Intelligent control system of loading machine

Abstract

The invention discloses an intelligent control system of a loading machine, and relates to the technical field of engineering machinery intellectualization, the intelligent control system comprises a sensor module, a central controller and an actuator module, the sensor module, the central controller and the actuator module are in closed loop operation, and automatic, collaborative and optimal control of the operation process of the loading machine is realized. According to the intelligent control system of the loading machine, various sensors such as a millimeter wave radar, a laser radar and a camera in the sensor module are fused to perceive the environment, the vehicle state and the intention of a driver, and the central controller dynamically adjusts control parameters such as an engine rotating speed threshold value and a hydraulic system pressure threshold value based on a self-adaptive algorithm; subsystems such as a power transmission system and a hydraulic working system are always in the optimal working state, the problems of efficiency fluctuation and energy waste caused by the fact that a traditional loader depends on experience of a driver are solved, and maximization of working efficiency and minimization of fuel consumption under complex working conditions are achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent construction machinery, and in particular to an intelligent control system for a loader. Background Technology

[0002] Loaders are heavy-duty engineering machines widely used in construction, mining, ports and other places. Their core components include a power system, hydraulic transmission device, working device and walking system. Their main function is to load, transport, unload and level bulk materials through the front bucket. They can efficiently handle materials such as soil, sand, gravel and coal, and are an indispensable key equipment in modern earthwork construction.

[0003] Traditional loaders generally employ a control mode that combines mechanical hydraulic transmission with manual operation. Their operating efficiency and energy consumption heavily depend on the driver's experience and skill level, leading to problems such as unstable work quality and energy waste caused by human factors. Therefore, an intelligent control system for loaders is proposed. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides the following technical solution: an intelligent control system for a loader, comprising: a sensor module for collecting environmental information, vehicle status information and driver operation intention information of the loader; The central controller is communicatively connected to the sensor module, receives and fuses multi-source information collected by the sensor module, and generates cooperative instructions based on an adaptive algorithm to control the various subsystems of the loader. The actuator module is communicatively connected to the central controller, receives the coordinated control commands, and drives the actions of various subsystems of the loader. The sensor module, central controller, and actuator module operate in a closed loop, enabling automated, coordinated, and optimized control of the loader's operation process.

[0005] Preferably, the sensor module includes millimeter-wave radar, lidar, and camera for sensing environmental information; multiple of the following: inertial measurement unit, pressure sensor, angle sensor, and speed sensor for sensing vehicle status information; and joystick displacement sensor and accelerator pedal opening sensor for sensing the driver's operating intention.

[0006] Preferably, the adaptive control algorithm used by the central controller needs to dynamically adjust the control parameters based on the real-time collected operating condition information, including material resistance and ground slope, and the control parameters include engine speed threshold and hydraulic system pressure threshold.

[0007] Preferably, the loader's subsystems include a power transmission system, a hydraulic working system, a steering system, and a braking system. The power transmission system provides the loader with power output and transmission adapted to different working conditions. The hydraulic working system provides the hydraulic power required for the lifting, digging, and unloading actions of the working device. The steering system enables precise control of the vehicle's direction of travel according to control commands. The braking system provides different braking torques according to working conditions to ensure driving safety.

[0008] Preferably, the central controller, based on the planned work trajectory and real-time working conditions, coordinates with the actuator module to control the power transmission system to provide the optimal traction force matching the current working conditions, controls the hydraulic working system to output lifting and digging forces adapted to the material characteristics, controls the steering system to achieve a precise steering angle consistent with the travel path, and controls the braking system to provide appropriate braking torque according to the work requirements, so that each subsystem works together to complete the automated work task.

[0009] Preferably, it also includes a human-machine interface connected to the central controller, used to display operation guidance information, system status information and fault warning information to the driver, and to receive advanced target instructions from the driver.

[0010] Preferably, the human-machine interface provides automated operation guidance for the driver. The driver only needs to set the target material pile position and unloading position for the V-shaped shovel loading operation, and the central controller can automatically plan and execute the complete shovel loading, transportation and unloading cycle path control.

[0011] Preferably, it also includes a data communication module connected to the central controller, used to upload the data collected by the sensor module and system status data to the cloud platform. The cloud platform constructs a digital twin model corresponding to the loader, and performs predictive analysis on the performance degradation trend and remaining component life of the loader based on historical and real-time data, and generates maintenance suggestions or optimized control strategies and sends them to the central controller.

[0012] Preferably, the digital twin model is based on machine learning algorithms, analyzes the operating data of key components to predict their potential failure risks and performance degradation inflection points, receives real-time working data uploaded by the loader, and performs simulation operation in virtual space. At the same time, the optimized control parameters verified by the simulation are sent to the central controller for closed-loop optimization control of the physical loader.

[0013] In summary, the present invention provides an intelligent control system for a loader, which has the following beneficial effects: 1. The intelligent control system of this loader uses multiple sensors, such as millimeter-wave radar, lidar, and cameras, in the sensor module to perceive the environment, vehicle status, and driver intentions. The central controller dynamically adjusts control parameters such as engine speed threshold and hydraulic system pressure threshold based on adaptive algorithms, so that the power transmission system, hydraulic working system and other subsystems are always in the optimal working state. This solves the problems of efficiency fluctuation and energy waste caused by the reliance on driver experience in traditional loaders, and maximizes the working efficiency and minimizes fuel consumption under complex working conditions.

[0014] 2. The intelligent control system of this loader, with its central controller, coordinates the power transmission system, hydraulic working system, steering system and braking system through the actuator module according to the planned working trajectory, so that each subsystem works as a whole. This coordinated control not only reduces the operating skill requirements for new drivers, enabling them to be competent in complex operations after short-term training, but also avoids human operation errors through precise automated control, thereby improving the safety of operation.

[0015] 3. The intelligent control system of this loader uploads real-time data to the cloud platform through the data communication module to build a digital twin model corresponding to the physical loader. This model analyzes the operating data of key components based on machine learning algorithms, predicts potential failure risks and performance degradation inflection points, and realizes the transformation from post-maintenance to predictive maintenance. At the same time, the optimized control parameters verified by simulation are sent to the central controller to form a closed-loop optimized control. This not only extends the service life of the equipment and reduces maintenance costs, but also minimizes unexpected downtime and ensures the equipment's uptime and operational continuity. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0017] The specific embodiments of the present invention will now be described in further detail with reference to the accompanying drawings. Example

[0018] Please see Figure 1 An intelligent control system for a loader includes: a sensor module for collecting environmental information, vehicle status information and driver operation intention information of the loader; The central controller communicates with the sensor modules, receives and fuses multi-source information collected by the sensor modules, and generates coordinated instructions based on adaptive algorithms to control the various subsystems of the loader. The actuator module communicates with the central controller, receives coordinated control commands, and drives the actions of various subsystems of the loader. The sensor module, central controller, and actuator module operate in a closed loop to achieve automated, coordinated, and optimized control of the loader's operation process.

[0019] The sensor module includes millimeter-wave radar, lidar, and cameras for sensing environmental information; multiple inertial measurement units, pressure sensors, angle sensors, and speed sensors for sensing vehicle status information; and joystick displacement sensors and accelerator pedal opening sensors for sensing driver operating intentions.

[0020] In the sensor module, environmental information perception achieves multi-dimensional perception fusion through the collaborative combination of millimeter-wave radar, lidar, and cameras: millimeter-wave radar utilizes the time difference between the emission and reflection of high-frequency electromagnetic waves in the 24GHz-77GHz band to penetrate rain, fog, and dust and detect the distance, speed, and angle information of obstacles within a range of 50-200 meters in real time. Its all-weather working characteristics can compensate for the performance degradation of visual sensors in low light or severe weather conditions; lidar emits 905nm-1550nm laser pulses through omnidirectional rotation to construct a three-dimensional point cloud model within 200 meters around the loader, accurately identifying the shape of material piles, slope angles, and small obstacles, while providing high-resolution spatial data for path planning; the camera adopts a wide-angle and narrow-angle binocular vision system. The wide-angle lens covers a 120° field of view to achieve global monitoring of the operation scene, while the narrow-angle lens focuses on the area 5 meters in front of the bucket to identify material characteristics such as particle size distribution and humidity prediction. Combined with deep learning algorithms, it analyzes the semantic information of personnel, vehicles, and marking lines in the image. By fusing dynamic target tracking from millimeter-wave radar, static structural modeling from lidar, and semantic feature extraction from cameras into multimodal data, a comprehensive perception result is generated that includes obstacle categories, motion trajectories, spatial occupancy, and environmental semantics. This improves the accuracy of environmental recognition for loaders under complex working conditions while reducing response latency.

[0021] The adaptive control algorithm used by the central controller needs to dynamically adjust the control parameters based on the real-time collected operating condition information, including material resistance and ground slope, and the control parameters include engine speed threshold and hydraulic system pressure threshold.

[0022] The adaptive control algorithm relies on real-time acquired operating condition information. Its inputs are material resistance signals and vehicle pitch angle signals from sensors, and its outputs are dynamically adjusted speed threshold parameters and hydraulic electromagnetic proportional valve pressure setting thresholds. This allows the controller to automatically change the engine's power output characteristics and the hydraulic system's force distribution according to the weight of the loaded material and the angle of travel on the slope, thereby achieving the optimal match between power and economy.

[0023] The loader's subsystems include a power transmission system, a hydraulic working system, a steering system, and a braking system. The power transmission system provides the loader with power output and transmission to adapt to different working conditions; the hydraulic working system provides the hydraulic power required for the lifting, digging, and unloading actions of the working device; the steering system is used to achieve precise control of the vehicle's driving direction according to control commands; and the braking system provides different braking torques according to working conditions to ensure driving safety.

[0024] The power transmission system mainly includes a diesel engine, a hydraulic torque converter, a power shift gearbox, and front and rear drive axles, and its function is to efficiently transmit power to the wheels; the hydraulic working system mainly includes a variable displacement hydraulic pump, an electro-hydraulic proportional multi-way valve, a lifting cylinder, and a bucket tilting cylinder, and its function is to provide precise hydraulic power for loading and lifting operations; the steering system mainly includes a steering hydraulic pump, a fully hydraulic steering gear, and a steering cylinder, and its function is to change the vehicle's direction of travel in response to control commands; the braking system mainly includes a service brake and a parking brake, and its function is to provide necessary deceleration and stopping braking force.

[0025] Based on the planned work trajectory and real-time working conditions, the central controller coordinates with the actuator module to control the power transmission system to provide the best traction force matching the current working conditions, controls the hydraulic working system to output lifting and digging forces adapted to the material characteristics, controls the steering system to achieve a precise steering angle that matches the travel path, and controls the braking system to provide appropriate braking torque according to the work requirements, so that each subsystem can work together to complete the automated work task.

[0026] The central controller's collaborative control function primarily involves the path planning module generating the optimal operating trajectory. The control signal distribution module then sends commands to the electronic control units (ECUs) of each subsystem via the CAN bus: commands to the ECU of the powertrain system to control the engine and transmission to output the optimal traction force matching the current load; commands to the solenoid valve group of the hydraulic system to precisely control the output force of the lifting and bucket-turning cylinders to adapt to the loose or viscous characteristics of the material; commands to the electro-hydraulic servo controller of the steering system to achieve a precise steering angle that perfectly matches the preset trajectory; and simultaneously, commands to the ECU of the braking system to provide just the right braking torque when retracting the shovel or positioning, ensuring vehicle stability. Example

[0027] Please see Figure 1 It also includes a human-machine interface that connects to the central controller to display work guidance information, system status information, and fault warning information to the driver, and to receive advanced target instructions from the driver.

[0028] The human-machine interface is an integrated intelligent display terminal in the cab. Its hardware is a high-brightness LCD touch screen. The terminal is connected to the central controller through the vehicle network. Its software interface is designed to graphically display system status information to the driver, including the optimal loading path guide line, real-time engine speed and fuel consumption, hydraulic system temperature and pressure, etc. At the same time, it receives advanced target commands such as target point coordinates input by the driver through the touch screen.

[0029] The human-machine interface provides automated operation guidance for the driver. The driver only needs to set the target material pile position and unloading position for the V-shaped loading operation, and the central controller can automatically plan and execute the complete loading, transportation and unloading cycle path control.

[0030] The automated operation guidance function of the human-machine interface is specifically implemented by its built-in task planning software module: After the driver sets the outline of the material pile and the coordinates of the unloading point for the V-shaped shovel loading operation on the touch screen, the module sends the task instructions to the central controller. The global path planner of the central controller then automatically generates a complete loop path including shovel loading, transportation, unloading and empty return, and automatically executes the path by controlling each subsystem. The driver does not need to operate the steering wheel, accelerator or working device handle, but only needs to monitor. Example

[0031] Please see Figure 1 It also includes a data communication module, which connects to the central controller and is used to upload data collected by the sensor module and system status data to the cloud platform. The cloud platform builds a digital twin model corresponding to the loader and performs predictive analysis on the performance degradation trend and remaining life of components of the loader based on historical and real-time data, and generates maintenance suggestions or optimized control strategies and sends them to the central controller.

[0032] The data communication module is an on-board telematics processor with built-in 4G / 5G cellular communication and GPS positioning modules. This module collects sensor and status data from the central controller through the on-board gateway and continuously uploads it to the cloud platform server. The digital twin modeling engine on the cloud platform uses this historical and real-time data to build a virtual model that corresponds to the physical loader at a 1:1 scale. It also uses big data analysis algorithms to predictive analyze the trend of engine performance degradation and the remaining life of hydraulic pumps, and finally sends the generated maintenance alarms or control parameter optimization packages to the on-board controller.

[0033] The digital twin model is based on machine learning algorithms. It analyzes the operating data of key components to predict their potential failure risks and performance degradation inflection points. It receives real-time working data uploaded by the loader and performs simulation operation in virtual space. At the same time, it sends the optimized control parameters verified by the simulation to the central controller for closed-loop optimization control of the physical loader.

[0034] The digital twin model is a predictive maintenance agent based on machine learning algorithms. It continuously receives real-time time-series data such as vibration, temperature, and pressure uploaded by the loader, and uses a trained LSTM deep learning neural network to analyze this data to predict potential failure risk points and performance degradation inflection points of key components such as gearbox bearings. At the same time, it simulates and runs new control strategies in virtual space and sends the optimized control parameters verified by the simulation to the central controller, thus forming a data-driven optimization closed loop to continuously improve the performance of the physical equipment.

[0035] In operation, millimeter-wave radar actively detects the distance and speed of dynamic obstacles within 200 meters, lidar scans to generate a high-precision 3D point cloud model of the surrounding environment, stereo cameras capture visual images and identify material characteristics and semantic information through deep learning algorithms, while the inertial measurement unit monitors the vehicle's attitude angle and acceleration in real time. Pressure and angle sensors collect hydraulic system pressure values ​​and boom / bucket hinge angles, respectively, while joystick displacement and throttle pedal opening sensors analyze the driver's operating intentions. All multi-source heterogeneous data is transmitted to the central controller via the vehicle's Ethernet, where a multimodal data fusion algorithm performs spatiotemporal alignment and feature extraction to generate a unified perception of the environment, vehicle, and driver. The adaptive control algorithm module in the central controller's core dynamically optimizes control parameters based on real-time operating conditions and generates coordinated commands. These instructions are sent to the actuator module via the CAN bus: the powertrain's electronic control unit adjusts the engine speed and gearbox gear according to the instructions to output optimal traction; the electro-hydraulic proportional valve of the hydraulic system receives the instructions and precisely controls the extension and retraction speed and output force of the lifting and bucket cylinders; the steering system's electro-hydraulic servo controller drives the steering cylinder to achieve precise steering based on the path tracking algorithm; and the braking system's electronic control unit applies appropriate braking torque at specific stages of the work cycle. The entire process constitutes a local closed-loop control. At the same time, the on-board remote information processor uploads the processed data to the cloud platform via the 4G / 5G module. The digital twin model on the cloud platform analyzes historical and real-time data, predicts the failure risk of key components, and simulates and verifies new control strategies. Finally, the optimized parameter package is sent to the on-board central controller to form a global optimization closed loop.

[0036] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent control system for a loader characterized by, include: The sensor module is used to collect environmental information, vehicle status information, and driver operation intention information of the loader; The central controller is communicatively connected to the sensor module, receives and fuses multi-source information collected by the sensor module, and generates cooperative instructions based on an adaptive algorithm to control the various subsystems of the loader. The actuator module is communicatively connected to the central controller, receives the coordinated control commands, and drives the actions of various subsystems of the loader. The sensor module, central controller, and actuator module operate in a closed loop, enabling automated, coordinated, and optimized control of the loader's operation process.

2. The intelligent control system for a loader of claim 1, wherein: The sensor module includes millimeter-wave radar, lidar, and camera for sensing environmental information; multiple inertial measurement units, pressure sensors, angle sensors, and speed sensors for sensing vehicle status information; and joystick displacement sensors and accelerator pedal opening sensors for sensing the driver's operating intentions.

3. The intelligent control system for a loader as set forth in claim 1, wherein: The adaptive control algorithm used by the central controller needs to dynamically adjust the control parameters based on the real-time collected operating condition information, including material resistance and ground slope, and the control parameters include engine speed threshold and hydraulic system pressure threshold.

4. The intelligent control system for a loader of claim 1, wherein: The loader's subsystems include a power transmission system, a hydraulic working system, a steering system, and a braking system. The power transmission system provides the loader with power output and transmission to adapt to different working conditions. The hydraulic working system provides the hydraulic power required for the lifting, digging, and unloading actions of the working device. The steering system is used to achieve precise control of the vehicle's driving direction according to control commands. The braking system provides different braking torques according to working conditions to ensure driving safety.

5. The intelligent control system for a loader as set forth in claim 4, wherein: The central controller, based on the planned work trajectory and real-time working conditions, coordinates with the actuator module to control the power transmission system to provide the optimal traction force matching the current working conditions, controls the hydraulic working system to output lifting and digging forces adapted to the material characteristics, controls the steering system to achieve a precise steering angle consistent with the travel path, and controls the braking system to provide appropriate braking torque according to the work requirements, so that each subsystem can work together to complete the automated work task.

6. The intelligent control system for a loader of claim 1, wherein: It also includes a human-machine interface connected to the central controller, used to display operation guidance information, system status information and fault warning information to the driver, and to receive advanced target instructions from the driver.

7. The intelligent control system for a loader as set forth in claim 6, wherein: The human-machine interface provides automated operation guidance for the driver. The driver only needs to set the target material pile position and unloading position for the V-shaped loading operation, and the central controller can automatically plan and execute the complete loading, transportation and unloading cycle path control.

8. The intelligent control system for a loader of claim 1, wherein: It also includes a data communication module connected to the central controller, used to upload the data collected by the sensor module and system status data to the cloud platform. The cloud platform constructs a digital twin model corresponding to the loader, and performs predictive analysis on the performance degradation trend and remaining component life of the loader based on historical and real-time data, and generates maintenance suggestions or optimized control strategies and sends them to the central controller.

9. The intelligent control system for a loader of claim 8, wherein: The digital twin model is based on machine learning algorithms. It analyzes the operating data of key components to predict their potential failure risks and performance degradation inflection points. It receives real-time working data uploaded by the loader and performs simulation operation in virtual space. At the same time, it sends the optimized control parameters verified by the simulation to the central controller for closed-loop optimization control of the physical loader.

Images