A gravity power generation and energy storage system based on linear motor and deep learning multi-task model

Abstract

The application provides a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, which comprises a front load-bearing cage and a rear load-bearing cage, which are respectively slidably arranged in a front vertical track section and a rear vertical track section. The front linear motor is drivingly connected with the front load-bearing cage, the rear linear motor is drivingly connected with the rear load-bearing cage, and the battery module is connected with the two linear motors. The central controller of the energy storage control unit is responsible for the start and operation control of the system, including the preheating, acceleration, steering, deceleration and other stages. And a deep learning based multi-task module is introduced, the central controller dynamically adjusts the driving force of the linear motor, prevents the cage from tilting or deviating from the track, avoids misstarting, and monitors and adjusts the posture of the cage in real time, ensures that it remains stable during movement, thereby improves the safety and stability of the system. The purpose is to improve the efficiency, accuracy and safety of the system.

Description

Technical Field

[0001] This invention relates to the field of gravity energy storage technology, and in particular provides a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model. Background Technology

[0002] Most existing gravity energy storage experimental systems are based on lifting mechanical structures, using traditional rotary motors combined with gears, belts, or hydraulic systems to achieve the vertical lifting of the mass block. These systems often have complex structural designs, including multiple mechanical conversion stages, such as gearboxes and pulley systems, which work together to convert rotational motion into linear motion. This multi-step energy conversion process results in significant energy losses, impacting the overall energy efficiency of the system. Furthermore, the response speed and real-time control of the model are greatly limited due to mechanical delays and system inertia. In addition, the mechanical transmission system involves many complex mechanical components, requiring extensive maintenance and affecting the long-term sustainability of the system. Summary of the Invention

[0003] To achieve the above objectives and overcome the aforementioned problems, this invention proposes a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model. The system includes a three-dimensional frame, a car unit, a weight transfer unit, an image acquisition unit, an image processing unit, and an energy storage control unit. The three-dimensional frame has multiple three-dimensional tracks spaced apart along its width, each track including a front vertical track segment, a horizontal track segment, and a rear vertical track segment.

[0004] The car unit consists of a front load-bearing car that slides within the front vertical track section and a rear load-bearing car that slides within the rear vertical track section. A front linear motor is connected to the front load-bearing car drive, and a rear linear motor is connected to the rear load-bearing car drive. The battery module is connected to both linear motors.

[0005] The heavy block conveying unit has a conveyor belt that slides inside a three-dimensional track. The heavy blocks include multiple blocks that are evenly distributed along the length of the conveyor belt. The conveying drive mechanism is connected to the conveyor belt drive.

[0006] An image acquisition unit, located above the conveyor belt track, includes an image acquisition module to ensure that the image acquisition module can acquire images of the track and is connected to the image acquisition unit.

[0007] The image processing unit, connected to the central controller, includes a target detection module, an attitude detection module, and a track wear detection module.

[0008] The control process of the energy storage control unit and central controller includes the image preprocessing stage, the startup stage, the attitude detection stage, and the operation stage.

[0009] Image preprocessing stage: This includes image acquisition, using traditional computer vision algorithms to filter out track masks, using the Darknet backbone network to extract image features, and using a target detection head to perform real-time detection of the track. After detecting quality blocks, the startup stage begins.

[0010] Start-up phase: Before startup, the system automatically warms up and gradually accelerates the front linear motor and the rear linear motor to the running speed based on sensor data and preset parameters;

[0011] Image processing stage: The Darknet backbone network is used to extract image features, and a multi-task head is used to detect whether there are defective blocks on the track and the attitude data of the car, to determine whether there is any abnormality in the car's movement, and the results are returned to the central controller.

[0012] Operation phase: including acceleration, turning, descent and deceleration phases, the system adjusts the load and speed according to energy demand.

[0013] Furthermore, the image processing unit first acquires the image through the image acquisition device, then obtains the edge information in the entire image through the edge detection algorithm, and then obtains the straight line fitted by the orbital boundary in the image through the Hough line transform, and identifies the middle area of ​​the straight line as the mask.

[0014] Image features are extracted using Darknet, then processed through a feature fusion network, and finally trained by an object detection head to detect target blocks. The loss function for the training process is shown in equation (1):

[0015] L = L loc +L conf +L cls +L structure (1)

[0016] L loc It is the localization loss, used to measure the difference between the predicted bounding box's position and size and the true bounding box; L conf It is the confidence loss, used to measure the difference between the predicted probability that the bounding box contains an object and the actual probability; L cls It is the classification loss, used to measure the difference between the predicted class and the true class, L. structure It is skeleton loss, which is the key skeleton information for measuring the pose of a block.

[0017] Furthermore, L loc Calculate according to formula (2):

[0018]

[0019] Where λ_coord is the weighting coefficient, emphasizing the importance of positioning error; S2 is the summation of all grid cells; Sum the predicted bounding box number B for each grid cell; The indicator function is 1 when the i-th grid cell and the j-th bounding box are responsible for predicting an object, and 0 otherwise; True bounding box center coordinates With the predicted bounding box center coordinates x i The mean square error between them; The true bounding box center coordinates y i Coordinates of the predicted bounding box center The mean square error between them; Actual bounding box width With the predicted bounding box width The mean square error between them; True bounding box height With predicted bounding box height The mean square error between them.

[0020] Furthermore, L conf Calculate according to formula (3):

[0021]

[0022] Where c i : Confidence of the true bounding box (1 if the box is responsible for predicting an object, 0 otherwise); Predict the confidence level of the bounding box; The weighting coefficient is an indicator function that is 1 when the i-th grid cell and the j-th bounding box are not responsible for predicting any objects, and 0 otherwise.

[0023] Furthermore, L cls Calculate according to formula (4):

[0024]

[0025] P is the probability of the model predicting that a target belongs to class c. By weighting and summing the three loss functions, we can obtain the loss function for target detection.

[0026] Furthermore, for the pose detection task, in addition to the basic target detection loss function, a new loss function is also involved, as shown in equation (4):

[0027]

[0028] L structure It is the skeleton loss of the model, used to determine the pose of the mass blocks. and These represent the actual distance and the predicted distance between point k and point I, respectively.

[0029] Furthermore, the energy storage control unit adjusts its operating parameters based on real-time monitoring data of load changes, energy demand, and environmental conditions, and sets the operation according to energy demand to adjust the energy storage release rate to meet demand fluctuations.

[0030] Furthermore, the energy storage control unit includes a preprocessing module to process the image, reducing computational load and lowering costs. The energy storage control unit is equipped with an anti-false start module, which uses a target detection algorithm to detect objects and only initiates the start-up phase when a target mass block is detected, preventing false starts. The energy storage control unit is designed to maximize energy capture and storage efficiency, automatically switching to energy-saving mode during low-load periods. It also features refined energy feedback control logic to ensure maximum energy recovery and reuse at any stage of operation.

[0031] Furthermore, the energy storage control unit is equipped with a fault detection module, configured to diagnose the status of key components in real time, automatically identify potential faults and issue warnings, and automatically alarm in cases of overload, mechanical jamming, etc. The energy storage control unit also includes a car status alarm module; when abnormal changes occur in the car's attitude, the system will issue a warning to prevent accidents. Additionally, the energy storage control unit is equipped with a track defect detection module; when damage or defects are found on the track, the system will issue a warning, automatically shut down, reduce losses, and prevent accidents. Finally, the energy storage control unit also includes an emergency response module, configured to automatically initiate an emergency shutdown procedure when abnormal operation or performance degradation is detected, and includes an emergency stop button and an automatic fault shutdown function.

[0032] Furthermore, the front linear motor and the rear linear motor reach their optimal acceleration state in 0.2s, then move at a constant speed, enter low-speed operation when 500mm away from the target position, and start maximum progressive braking to stop operation when reaching the target position.

[0033] Furthermore, the front and rear loaded cars are each equipped with a height sensor. The central controller is connected to the height sensor signal and is configured to receive and control the linear motor to operate based on the car height detected by the height sensor, thereby performing motion control of the front and rear loaded cars.

[0034] Furthermore, the front track section is equipped with a front travel sensor to detect the up and down travel of the front loaded car, and the rear track section is equipped with a rear travel sensor to detect the up and down travel of the rear loaded car. The central controller is connected to the height sensor signal and is configured to receive and control the linear motor to work based on the car height detected by the height sensor, thereby performing motion control of the front and rear loaded cars.

[0035] Furthermore, the front load-bearing car is equipped with rollers that roll in cooperation with the front vertical track, and the rear load-bearing car is equipped with rollers that roll in cooperation with the rear vertical track. Each roller is connected to the car via a wheel frame. The conveyor belt is equipped with rollers that cooperate with the front vertical track section, the horizontal track section, and the rear vertical track section; alternatively, the front vertical track section, the horizontal track section, and the rear vertical track section are equipped with rollers that cooperate with the conveyor belt. The linear motor includes a motor stator and a motor mover that slide in cooperation. The motor stator is arranged parallel to the front and rear vertical tracks, and the motor mover is fixedly installed on the outer circumferential side of the car.

[0036] The system also includes a brake regeneration unit connected to the front and rear loaded cars. The brake regeneration unit includes a mounting base, a pulley, a reducer, a generator, and a brake. The mounting base is fixedly installed above the front and rear vertical tracks. The generator's motor shaft is connected to the pulley's axle via the reducer. The movable end of the flexible rope wound around the pulley extends vertically downwards and connects to the loaded car. The brake is connected to the pulley's axle for braking. The transmission drive mechanism includes an electromagnetic push-pull device located inside the car. This device includes an electromagnet, a guide rail, and a polarity control circuit. When the weight moves to a designated height on the vertical track, the electromagnetic push-pull device activates, and the electromagnet switches to repulsive polarity, pushing the weight out of the car. When the weight moves to the mirror-side endpoint via the conveyor belt, the electromagnetic push-pull device on the other side activates, and the electromagnet switches to attractive polarity, pulling the weight into the mirror-side car.

[0037] Furthermore, the conveying drive mechanism also includes an electric drive wheel device disposed at the horizontal guide rail section, the front vertical rail section, and the rear vertical rail section. The electric drive wheel device includes a conveying motor and a conveying wheel. The conveying motor is connected to the conveying wheel through a reduction transmission mechanism. The transmission belt is frictionally driven with the conveying wheel. The conveying motor is configured to drive the conveying wheel to rotate, thereby driving the conveyor belt to move along the three-dimensional track to carry the heavy block into or out of the car.

[0038] Compared with existing technologies, the technical advantages of the gravity energy storage system based on a linear motor provided by this invention are at least reflected in the following aspects:

[0039] 1. By directly connecting the linear motor to the loaded car, the traditional intermediate conversion mechanisms such as gears and belts are eliminated, and electrical energy is directly converted into linear power. This simplifies the structure and significantly improves energy conversion efficiency and system response speed. Furthermore, it integrates high-precision sensors to achieve real-time monitoring and adjustment of the position and speed of the load, ensuring precise operation and improving the efficiency and accuracy of the gravity energy storage system.

[0040] 2. By using regenerative braking technology, the kinetic energy of the heavy object during its descent is recovered and stored, reducing energy waste and improving the overall energy efficiency of the system. At the same time, the use of environmentally friendly battery modules reduces the impact on the environment, reduces energy consumption, reduces carbon emissions, and promotes the development of energy conservation and environmental protection.

[0041] 3. By utilizing deep learning technology, the safety of the device is improved, energy waste can be effectively reduced, reasonable safety warnings can be made, and the reliability of the system can be enhanced;

[0042] 4. The modular design allows each system component to be operated and maintained independently, reducing maintenance complexity and cost, improving the long-term sustainability of the system, and making it suitable for practical application scenarios such as terminal shipments and bulk cargo storage. It improves the efficiency of bulk cargo storage and shipment processes. The system's high efficiency and precise control capabilities enhance operational efficiency, reduce the intensity of manual operations, and have significant social and economic benefits. Attached Figure Description

[0043] The accompanying drawings, which form part of this specification, illustrate embodiments of the invention and, together with the specification, serve to explain the principles of the invention. The invention will become more clearly understood from the following detailed description, referring to the accompanying drawings, in which:

[0044] Figure 1 This is a schematic diagram of a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, according to an embodiment of the present invention.

[0045] Figure 2 This is a structural schematic diagram of the front-load-bearing car provided according to an embodiment of the present invention; (disassembled state)

[0046] Figure 3 This is a schematic diagram of the electromagnetic push-pull device provided according to an embodiment of the present invention; (disassembled state)

[0047] Figure 4 This is a schematic diagram of the structure of the braking regeneration unit provided according to an embodiment of the present invention;

[0048] Figure 5 This is a circuit system schematic diagram of a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, according to an embodiment of the present invention.

[0049] Figure 6 This is a system control main interface for a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, provided according to an embodiment of the present invention.

[0050] Figure 7This is an operation monitoring interface for a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, provided according to an embodiment of the present invention.

[0051] Figure 8 This is a general monitoring interface for a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, provided according to an embodiment of the present invention.

[0052] Figure 9 This is a fault alarm interface for a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, provided according to an embodiment of the present invention.

[0053] Figure 10 This is a flowchart of a multi-task convolutional neural network provided according to an embodiment of the present invention.

[0054] Explanation of reference numerals in the attached diagram:

[0055] 11-Three-dimensional frame, 12-Three-dimensional track, 121-Front vertical track segment, 122-Horizontal track segment, 123-Rear vertical track segment;

[0056] 21-Front load-bearing car, 22-Rear load-bearing car, 23-Linear motor, 24-Roller, 25-Wheel frame;

[0057] 31-Conveyor belt, 32-Weight block, 33-Electromagnet, 34-Guide rail;

[0058] 41-Rope pulley, 42-Reducer, 43-Generator, 44-Brake;

[0059] 51-Central controller, 52-Battery module.

[0060] It should be understood that the dimensions of the various parts shown in the accompanying drawings are not drawn to actual scale. Furthermore, the same or similar reference numerals denote the same or similar components. Detailed Implementation

[0061] Traditional gravity energy storage experimental models are complex in structure and suffer from problems such as poor energy efficiency, low control precision, poor sustainability, and complex maintenance. This invention proposes a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model. It involves a novel linear motor model system that improves system performance and experimental accuracy during gravity energy storage experiments. It belongs to the field of gravity energy storage hardware systems and is particularly suitable for port shipments and bulk cargo storage scenarios.

[0062] The provided system is a gravity power generation and energy storage system based on linear motors and a deep learning multi-task model. A three-dimensional frame is provided with multiple three-dimensional tracks at intervals. Image acquisition devices are mounted on the tracks. The front linear motor of the car unit is vertically arranged at the front of the three-dimensional frame and driven by the adjacent front-loaded car. The rear linear motor is vertically arranged at the rear of the three-dimensional frame and driven by the adjacent rear-loaded car. The conveyor belt of the weight transfer unit slides within the tracks. Multiple weights are evenly distributed along the length of the conveyor belt. The transfer drive mechanism drives the conveyor belt forward to drive the front weights into the front-loaded car and the rear weights out of the rear-loaded car, or drives the conveyor belt backward to drive the front weights out of the front-loaded car and the rear weights into the rear-loaded car. The central controller of the energy storage control unit is connected to the front linear motors, the rear linear motors, and the transfer drive mechanism. The battery module is configured to store the electrical energy generated by the linear motors and supply it to the system.

[0063] The specific algorithm flow of the image processing unit is as follows: Figure 10 As shown:

[0064] First, an image is acquired using an image acquisition device. Then, an edge detection algorithm is used to obtain the edge information of the entire image. Finally, the Hough linear transform is used to obtain the straight line fitted to the orbital boundary in the image. The middle region of the straight line is identified as the mask.

[0065] Image features are extracted using Darknet, then processed through a feature fusion network, and finally trained by an object detection head to detect target blocks. The loss function for the training process is shown in equation (1):

[0066] L = L loc +L conf +L cls +L structure (1)

[0067] L loc It is the localization loss, used to measure the difference between the predicted bounding box's position and size and the true bounding box. conf It is the confidence loss, used to measure the difference between the predicted probability that the bounding box contains an object and the actual probability. cls It is the classification loss, used to measure the difference between the predicted class and the true class, L. structure This is the skeleton loss, which measures the key skeleton information of the block's pose. This function can be used to train a multi-task model, as shown in equation (2):

[0068]

[0069] Where λ_coord is the weighting coefficient, emphasizing the importance of positioning error. S2 is the number of grid cells, summed over all grid cells. Sum the predicted bounding box number B for each grid cell. The indicator function is 1 when the i-th grid cell and the j-th bounding box are responsible for predicting an object, and 0 otherwise. True bounding box center coordinates With the predicted bounding box center coordinates x i The mean square error between them. The true bounding box center coordinates y i Coordinates of the predicted bounding box center The mean square error between them. Actual bounding box width With the predicted bounding box width The mean square error between them. True bounding box height With predicted bounding box height The mean square error between them. L conf As shown in equation (3):

[0070]

[0071] Where c i : Confidence of the true bounding box (1 if the box is responsible for predicting an object, 0 otherwise). Predict the confidence level of the bounding box. Weight coefficients, an indicator function, are 1 when the i-th grid cell and the j-th bounding box are not responsible for predicting any objects, and 0 otherwise. L cls As shown in equation (4):

[0072]

[0073] P is the probability of the model predicting that a target belongs to class c. By weighting and summing the three loss functions, we can obtain the loss function for target detection.

[0074] For the pose detection task, in addition to the basic target detection loss function, a new loss function is also involved, as shown in Equation (5).

[0075]

[0076] L structure It is the skeleton loss of the model, used to determine the pose of the mass blocks. and These represent the actual distance and the predicted distance between point k and point I, respectively.

[0077] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. The descriptions of the exemplary embodiments are merely illustrative and are in no way intended to limit the invention or its application or use. The invention can be implemented in many different forms and is not limited to the embodiments described herein. In the present invention, when a particular device is described as being located between a first device and a second device, an intermediary device may or may not be present between the particular device and the first or second device.

[0078] Example 1:

[0079] A gravity power generation and energy storage system based on linear motors and a deep learning multi-task model includes a three-dimensional frame 11 with multiple three-dimensional tracks 12 spaced apart along its width. Each track 12 includes a front vertical track section 121, a horizontal track section 122, and a rear vertical track section 123. A car unit is also included, with a front loaded car 21 sliding within the front vertical track section 121 and a rear loaded car 22 sliding within the rear vertical track section 123. A front linear motor 23 is connected to both the front and rear loaded cars 21, and a battery module 52 is connected to both linear motors 23. A weight conveying unit is also included, with a conveyor belt 31 sliding within the three-dimensional tracks. Multiple weights 32 are evenly distributed along the length of the conveyor belt 31, and a conveyor drive mechanism is connected to the conveyor belt 31.

[0080] The energy storage control unit and the central controller's control process includes a pneumatic phase and an operation phase: Start-up phase: Before startup, the system automatically preheats and gradually accelerates the front linear motor 23 and the rear linear motor 23 to the operating speed based on sensor data and preset parameters; Operation phase: Includes acceleration, turning, descent, and deceleration phases, during which the system adjusts the load and speed according to energy demand.

[0081] Modular design allows each system component to be operated and maintained independently, reducing maintenance complexity and cost, improving the long-term sustainability of the system, and making it suitable for practical application scenarios such as terminal shipments and bulk cargo storage. It improves the efficiency of bulk cargo storage and shipment processes, and the system's high efficiency and precise control capabilities enhance operational efficiency, reduce the intensity of manual operations, and have significant social and economic benefits.

[0082] During implementation, the front linear motor 23 and the rear linear motor 23 reach their optimal acceleration state in 0.2s, then move at a constant speed. When they are 500mm away from the target position, they enter low-speed operation and start maximum progressive braking to stop when they reach the target position.

[0083] like Figures 6 to 9As shown, during implementation, the energy storage control unit adjusts its operating parameters based on real-time monitoring data of load changes, energy demand, and environmental conditions, and adjusts the energy storage release rate according to energy demand settings to meet demand fluctuations.

[0084] In some preferred embodiments, the energy storage control unit is configured to maximize energy capture and storage efficiency, automatically switch to energy-saving mode during low-load periods, and has refined energy feedback control logic to ensure that energy recovery and reuse are maximized at any stage of operation.

[0085] In some preferred embodiments, the energy storage control unit is further provided with a fault detection module, which is configured to diagnose the status of key components in real time, automatically identify potential faults and issue early warnings.

[0086] In some preferred embodiments, the energy storage control unit is further provided with an emergency response module, which is configured to automatically initiate an emergency shutdown procedure when abnormal operation or performance degradation is detected, and is equipped with an emergency stop button and an automatic shutdown function for faults.

[0087] Example 2:

[0088] like Figures 1 to 5 As shown, the present invention provides a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model, including a three-dimensional frame, a car unit, a weight transfer unit, and an energy storage control unit.

[0089] The three-dimensional frame includes multiple vertical support beams and horizontal support beams. The three-dimensional frame 11 is provided with multiple three-dimensional tracks 12 at intervals along the width direction. The three-dimensional track 12 includes a front vertical track section 121, a horizontal track section 122, and a rear vertical track section 123. The front vertical track section 121 and the rear vertical track section 123 are respectively arranged on the front and rear sides of the three-dimensional frame 11. The horizontal track section 122 is arranged longitudinally on the top of the three-dimensional frame 11. The front and rear ends of the horizontal track section are respectively connected to the upper ends of the front vertical track section 121 and the rear vertical track section 123.

[0090] During implementation, the three-dimensional frame 11 consists of a robust matrix structure composed of multiple vertical and horizontal support beams, providing basic support and stability for the entire system and ensuring that other components can operate safely and efficiently within it.

[0091] The three-dimensional track 12 consists of horizontal and vertical tracks equipped with efficient rolling elements. It provides a movement path for the loaded car and horizontal conveyor belt, reducing friction and energy loss. The track system ensures that the load can move smoothly and accurately within the system. The vertical track, in conjunction with the linear motor 23, provides additional stability and safety, preventing lateral swaying and ensuring precise vertical positioning of the load.

[0092] The car unit includes a front load-bearing car 21, a rear load-bearing car 22, a front linear motor 23, and a rear linear motor 24. The front load-bearing car 21 slides within a front vertical track section 121, and the rear load-bearing car 22 slides within a rear vertical track section 123. The front linear motor 23 is vertically arranged on the front side of the three-dimensional frame 11 and is driven and connected to the adjacent front load-bearing car 21. The rear linear motor 23 is vertically arranged on the rear side of the three-dimensional frame 11 and is driven and connected to the adjacent rear load-bearing car 22. The load-bearing cars are used to carry heavy objects. The cars are equipped with high-precision sensors and move via efficient rolling elements. The load-bearing cars carry and transport heavy objects to various positions within the system, realizing the storage and release of heavy objects.

[0093] The heavy block conveying unit includes a conveyor belt 31, heavy blocks 32, and a conveying drive mechanism. The conveyor belt 31 is slidably mounted on a horizontal track section 122, with its front end extending downward along the front vertical track section 121 and its rear end extending downward along the rear vertical track section 123. The heavy blocks 32 include multiple blocks and are evenly distributed along the length of the conveyor belt 31. The conveying drive mechanism is driven to the conveyor belt 31 and is configured to drive the conveyor belt 31 forward to drive the front heavy blocks 32 to slide into the front loaded car 21 and the rear heavy blocks 32 to slide out of the rear loaded car 22, or to drive the conveyor belt 31 backward to drive the front heavy blocks 32 to slide out of the front loaded car 21 and the rear heavy blocks 32 to slide into the rear loaded car 22.

[0094] The energy storage control unit includes a central controller 51 and a battery module 52. The central controller is connected to the front linear motor 23, the rear linear motor 23 and the transmission drive mechanism. The battery module 52 is configured to store the electrical energy generated by the linear motor 23 and supply it to the system.

[0095] The system motor is a linear motor selected to meet the system load requirements, with motor specifications matched to the mass of the weight and the system's operating speed. The linear motor 23 includes a slidingly fitted stator and a mover. The stator is arranged parallel to the front and rear vertical tracks, while the mover is fixedly mounted on the outer circumference of the car. The linear motor 23 drives the vertical and horizontal movement of the weight. It directly converts electrical energy into linear power, driving the car's ascent and descent, as well as its horizontal movement. The linear motor's efficient energy conversion and precise control are the core of the system, ensuring efficient energy storage and release.

[0096] The battery energy storage unit, composed of multiple lithium iron phosphate battery modules and equipped with a battery management system (BMS), stores the electrical energy generated by the linear motor and regenerative braking system for system use. The battery energy storage unit provides reliable energy storage and supply, ensuring the system's energy needs are met under different operating conditions. The battery modules are environmentally friendly lithium iron phosphate batteries, reducing environmental impact, energy consumption, and carbon emissions, thus promoting energy conservation and environmental protection.

[0097] The present invention provides a gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model. By directly connecting the linear motor to the load-bearing car, the traditional intermediate conversion mechanisms such as gears and belts are eliminated, and electrical energy is directly converted into linear power. This simplifies the structure and significantly improves energy conversion efficiency and system response speed. Furthermore, it integrates high-precision sensors to achieve real-time monitoring and adjustment of the position and speed of the load, ensuring precise operation and improving the efficiency and accuracy of the gravity energy storage experimental system.

[0098] The linear motor, track system, heavy-duty car, and battery energy storage unit are modularly designed to ensure that each module can operate independently, facilitating maintenance and possible upgrades.

[0099] Example 3:

[0100] like Figure 1 and Figure 4 As shown, based on Embodiment 1, the system is optimized by adding a regenerative braking unit and implementing regenerative braking technology to convert the kinetic energy of the car during descent into electrical energy, which is then stored in a lithium iron phosphate battery.

[0101] Specifically, the system also includes a brake regeneration unit that is brake-connected to the front loaded car 21 and the rear loaded car 22. The brake regeneration unit includes a mounting base plate, a rope pulley 41, a reducer 42, a generator 43, and a brake 44. The mounting base plate is fixedly installed directly above the front vertical track and the rear vertical track. The motor shaft of the generator 43 is connected to the axle of the rope pulley 41 through the reducer 42. The movable end of the flexible rope fixedly wound on the rope pulley 41 extends vertically downward and is connected to the loaded car. The brake 44 is brake-connected to the axle of the rope pulley 41.

[0102] Regenerative braking technology recovers and stores the kinetic energy of heavy objects during descent, reducing energy waste and improving the overall energy efficiency of the system. At the same time, the use of environmentally friendly battery modules reduces the impact on the environment, reduces energy consumption, reduces carbon emissions, and promotes the development of energy conservation and environmental protection.

[0103] Example 4:

[0104] like Figure 1 and Figure 3As shown, the conveying drive mechanism includes an electromagnetic push-pull device installed inside the car. The electromagnetic push-pull device includes an electromagnet 33, a guide rail 34, and a polarity control circuit. When the weight 32 moves to a specified height on the vertical rail, the electromagnetic push-pull device is activated, and the electromagnet 33 switches to the repulsive polarity, pushing the weight 32 out of the car. When the weight 32 moves to the end position on the mirror side via the conveyor belt 31, the electromagnetic push-pull device on the other side of the car is activated, and the electromagnet 33 switches to the attractive polarity, pulling the weight 32 into the car on the mirror side.

[0105] An electromagnetic push-pull device is installed inside the car to facilitate the transition of heavy objects from vertical to horizontal movement and to pull them from the conveyor belt into the mirror-side car. The push-pull mechanism consists of an electromagnet, a polarity control circuit, and a guide rail. When the heavy object moves to a designated height on the vertical rail, the electromagnetic push-pull device activates, the electromagnet switches to repulsive polarity, and pushes the heavy object out of the car and onto the conveyor belt. When the heavy object moves to the mirror-side endpoint via the conveyor belt, the electromagnetic push-pull device on the other side of the car activates, the electromagnet switches to attractive polarity, and pulls the heavy object into the mirror-side car.

[0106] Example 5:

[0107] like Figure 1 As shown, the transmission drive mechanism further includes an electric drive wheel device disposed at the horizontal guide rail section, the front vertical track section 121, and the rear vertical track section 123. The electric drive wheel device includes a transmission motor and a transmission wheel. The transmission motor is connected to the transmission wheel through a reduction transmission mechanism. The transmission belt is frictionally driven with the transmission wheel. The transmission motor is configured to drive the transmission wheel to rotate, thereby driving the transmission belt 31 to move along the three-dimensional track 12 to drive the weight 32 into or out of the car.

[0108] Furthermore, the conveyor belt 31 is a chain, the weights 32 are fixedly connected at equal intervals to different chain plates of the chain, the chain slides in the middle of the track, the weights 32 slide in the sides of the track, and the conveyor wheel is a sprocket that works with the chain.

[0109] Furthermore, the conveyor belt 31 is a synchronous belt, the weights 32 are fixedly connected to the synchronous belt at equal intervals, the synchronous belt is in sliding engagement with the middle of the track, the weights 32 are in sliding engagement with both sides of the track, and the conveyor wheel is a synchronous belt pulley that engages with the synchronous belt.

[0110] Example 6:

[0111] like Figures 1 to 4As shown, the sensor system consists of various sensors, including Hall effect sensors, position sensors, and speed sensors, installed in key locations. It monitors the status of various parts of the system in real time, including the position and speed of the load, and the motor status. The sensor system provides accurate feedback data to ensure the safe and efficient operation of the system. The system integrates sensors to monitor the position and speed of the car and the load, adjusting the motor output in real time to meet requirements.

[0112] During implementation, the front load-bearing car 21 and the rear load-bearing car 22 are respectively equipped with height sensors. The central controller 51 is connected to the height sensor signal and is configured to receive and control the linear motor 23 to work based on the car height detected by the height sensor, so as to perform motion control of the front load-bearing car 21 and the rear load-bearing car 22.

[0113] The front track section is equipped with a front travel sensor to detect the up and down travel of the front loaded car 21, and the rear track section is equipped with a rear travel sensor to detect the up and down travel of the rear loaded car 22. The central controller 51 is connected to the height sensor signal and is configured to receive and control the linear motor 23 to work based on the car height detected by the height sensor, so as to perform motion control of the front loaded car 21 and the rear loaded car 22.

[0114] like Figure 2 As shown, the front load-bearing car 21 is equipped with rollers 24 that roll in cooperation with the front vertical track, and the rear load-bearing car 22 is equipped with rollers 24 that roll in cooperation with the rear vertical track. Each roller 24 is connected to the car via a wheel frame 25.

[0115] The conveyor belt 31 is provided with rollers 24 that cooperate with the front vertical track section 121, the horizontal track section 122 and the rear vertical track section 123, or the front vertical track section 121, the horizontal track section 122 and the rear vertical track section 123 are provided with rollers 24 that cooperate with the conveyor belt 31.

[0116] Example 7:

[0117] like Figures 1 to 4 As shown, this invention provides a gravity energy storage system based on a linear motor and a deep learning multi-task model, including a three-dimensional frame, a car unit, a weight transfer unit, an image acquisition unit, an image processing unit, and an energy storage control unit. It monitors the status of each part of the system in real time, including the position and speed of the weight, and the motor status. The sensor system provides accurate feedback data to ensure the safe and efficient operation of the system. Sensors are integrated into the system to monitor the position and speed of the car and the weight, and the motor output is adjusted in real time to ensure demand is met.

[0118] During implementation, the front load-bearing car 21 and the rear load-bearing car 22 are respectively equipped with height sensors. The central controller 51 is connected to the height sensor signal and is configured to receive and control the linear motor 23 to work based on the car height detected by the height sensor, so as to perform motion control of the front load-bearing car 21 and the rear load-bearing car 22.

[0119] During implementation, when the mass block undergoes abnormal pose changes, the attitude detection module detects the anomaly and issues an early warning signal, effectively preventing accidents and demonstrating significant social and economic benefits.

[0120] Example 8:

[0121] like Figure 1 As shown, the transmission drive mechanism further includes an electric drive wheel device disposed at the horizontal guide rail section, the front vertical track section 121, and the rear vertical track section 123. The electric drive wheel device includes a transmission motor and a transmission wheel. The transmission motor is connected to the transmission wheel through a reduction transmission mechanism. The transmission belt is frictionally driven with the transmission wheel. The transmission motor is configured to drive the transmission wheel to rotate, thereby driving the transmission belt 31 to move along the three-dimensional track 12 to drive the weight 32 into or out of the car.

[0122] Furthermore, during the implementation process, if foreign objects or damage appear on the conveyor belt, the conveyor belt will stop and a warning signal will be issued. This effectively avoids accidents and has significant social and economic benefits.

[0123] This invention not only improves the efficiency and accuracy of gravity energy storage experimental systems, but also reduces energy consumption and carbon emissions through its application in practical scenarios such as port shipments and bulk cargo storage, thus promoting the development of energy conservation and environmental protection. Simultaneously, the system's high efficiency and precise control capabilities enhance operational efficiency and reduce manual labor intensity, resulting in significant social and economic benefits.

[0124] The embodiments of this disclosure have now been described in detail. To avoid obscuring the concept of this disclosure, some details known in the art have not been described.

[0125] Those skilled in the art will fully understand how to implement the technical solutions disclosed herein based on the above description. Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and not for limiting the scope of the invention. Those skilled in the art should understand that modifications can be made to the above embodiments or equivalent substitutions can be made to some technical features without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A gravity-powered power generation and energy storage system based on a linear motor and a deep learning multi-task model, characterized in that, include: The three-dimensional frame (11) has multiple three-dimensional tracks (12) spaced apart along the width direction. The three-dimensional tracks (12) include a front vertical track segment (121), a horizontal track segment (122), and a rear vertical track segment (123). The car unit has a front load-bearing car (21) that slides in the front vertical track section (121) and a rear load-bearing car (22) that slides in the rear vertical track section (123). The front linear motor is driven by the front load-bearing car (21) and the rear linear motor is driven by the rear load-bearing car (22). The battery module (52) is connected to the two linear motors. The heavy block conveying unit has a conveyor belt (31) sliding inside a three-dimensional track. The heavy blocks (32) include multiple blocks and are evenly distributed along the length of the conveyor belt (31). The conveying drive mechanism is connected to the conveyor belt (31) in a drive connection. An image acquisition unit is placed above the conveyor belt track. It includes an image acquisition module to ensure that the image acquisition module can acquire images of the track and is connected to the image acquisition unit. The image processing unit, connected to the central controller, includes a target detection module, an attitude detection module, and a track wear detection module; and The control process of the energy storage control unit and the central controller includes the image preprocessing stage, the startup stage, the attitude detection stage, and the operation stage. Image preprocessing stage: This includes image acquisition, using traditional computer vision algorithms to filter out the track mask, using the Darknet backbone network to extract image features, and using a target detection head to detect the track in real time. After detecting the mass block, the startup stage is initiated. Start-up phase: Before startup, the system automatically preheats and gradually accelerates the two linear motors to the operating speed based on sensor data and preset parameters; Attitude detection stage: The Darknet backbone network is used to extract image features, and a multi-task head is used to detect whether there are defective blocks on the track and the attitude data of the car, to determine whether the car movement is abnormal, and the results are returned to the central controller. Operation phase: including acceleration, turning, descent and deceleration phases, the system adjusts the load and speed according to energy demand.

2. The linear motor and deep learning multi-task model based gravity power generation and energy storage system according to claim 1, characterized in that, The image processing unit first acquires the image through the image acquisition device, then obtains the edge information in the entire image through the edge detection algorithm, and then obtains the straight line fitted by the orbit boundary in the image through the Hough linear transformation, and identifies the middle area of ​​the straight line as the mask.

3. The gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model according to claim 1 or 2, characterized in that, Image features are extracted using Darknet, then processed through a feature fusion network and trained by an object detection head to detect target blocks. The loss function for the training process is shown in equation (1): （1）； It is the localization loss, which measures the difference between the predicted bounding box's position and size and the true bounding box; It is the confidence loss, which measures the difference between the predicted probability that the bounding box contains an object and the actual probability. It is the classification loss, used to measure the difference between the predicted class and the true class. It is skeleton loss, which is the key skeleton information for measuring the pose of the block; Calculated according to formula (2): （2）； in S² is the summation over all grid cells, where S² is the number of grid cells. : Sum the predicted bounding box number B for each grid cell; : Indicator function, which is 1 when the i-th grid cell and the j-th bounding box are responsible for predicting an object, and 0 otherwise; : Coordinates of the center of the true bounding box Coordinates of the predicted bounding box center The mean square error between them; : Coordinates of the center of the true bounding box Coordinates of the predicted bounding box center The mean square error between them; : actual bounding box width With the predicted bounding box width The mean square error between them; True bounding box height With predicted bounding box height The mean square error between them.

4. The gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model according to claim 3, characterized in that, Calculated according to formula (3): （3）； in : Confidence of the ground truth bounding box. If the ground truth bounding box is responsible for predicting an object, it is 1; otherwise, it is 0. : Confidence level of the predicted bounding box; : Weight coefficient, indicator function, is 1 when the i-th grid cell and the j-th bounding box are not responsible for predicting any object, and 0 otherwise.

5. The gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model according to claim 3, characterized in that, As shown in equation (5): (5)； is the skeleton loss of the model, respectively represent the real distance and the predicted distance between the k points and the I points.

6. The linear motor and deep learning multi-task model based gravity power generation and energy storage system according to claim 1 or 2, characterized in that, The energy storage control unit adjusts its operating parameters based on real-time monitoring data of load changes, energy demand, and environmental conditions. It sets the operation according to energy demand to adjust the energy release rate to meet demand fluctuations. The energy storage control unit is equipped with functions to maximize energy capture and storage efficiency. During low-load periods, it automatically switches to energy-saving mode and has refined energy feedback control logic to ensure that energy recovery and reuse are maximized at any operating stage.

7. The linear motor and deep learning multi-task model based gravity power generation and energy storage system according to claim 1, wherein, The front load-bearing car (21) and the rear load-bearing car (22) are respectively equipped with height sensors. The central controller (51) is connected to the height sensor signal and is configured to receive and control the linear motor to work according to the car height detected by the height sensor, so as to perform motion control of the front load-bearing car (21) and the rear load-bearing car (22). The front track section is equipped with a front travel sensor to detect the up and down travel of the front loaded car (21), and the rear track section is equipped with a rear travel sensor to detect the up and down travel of the rear loaded car (22). The central controller (51) is connected to the height sensor signal and is configured to receive and control the linear motor to work according to the car height detected by the height sensor, so as to perform motion control of the front loaded car (21) and the rear loaded car (22).

8. The gravity power generation and energy storage system based on a linear motor and a deep learning multi-task model according to claim 7, characterized in that, The system also includes a brake regeneration unit that is braked and connected to the front load car (21) and the rear load car (22). The brake regeneration unit includes a mounting base plate, a rope wheel (41), a reducer (42), a generator (43), and a brake (44). The mounting base plate is fixedly installed directly above the front vertical track and the rear vertical track. The motor shaft of the generator (43) is connected to the wheel axle of the rope wheel (41) through the reducer (42). The movable end of the flexible rope fixedly wound on the rope wheel (41) extends vertically downward and is connected to the load car. The brake (44) is braked and connected to the wheel axle of the rope wheel (41).

9. The linear motor and deep learning multi-task model based gravity power generation and energy storage system according to claim 8, characterized in that, The transmission drive mechanism includes an electromagnetic push-pull device installed inside the car. The electromagnetic push-pull device includes an electromagnet (33), a guide rail (34), and a polarity control circuit. When the weight (32) moves to a specified height on the vertical rail, the electromagnetic push-pull device is activated, and the electromagnet (33) switches to the repulsive polarity to push the weight (32) out of the car. When the weight (32) moves to the end position on the mirror side via the conveyor belt (31), the electromagnetic push-pull device on the other side of the car is activated, and the electromagnet (33) switches to the attractive polarity to pull the weight (32) into the car on the mirror side.

Images