A power-assisted method and device for assisting in climbing a tower

Abstract

The application discloses a power assisting method and device for assisting tower climbing, and the method comprises the following steps: S101, collecting lower limb muscle deformation signals and foot bottom pressure distribution signals of a target object; predicting a climbing intention of the target object through the lower limb muscle deformation signals; judging a climbing stage of the target object through the foot bottom pressure signals; S102, generating an initial desired joint trajectory according to the climbing intention and the climbing stage; setting initial joint stiffness damping parameters according to the initial desired joint trajectory; real-time sensing environmental information around the tower, and dynamically adjusting the desired joint trajectory and the joint stiffness damping coefficient; S103, inputting the joint stiffness damping coefficient into a dielectric elastic soft body; the dielectric elastic soft body simulates muscle activation of the target object, and drives each joint in the soft body to output an assisting torque to the target object. The technical scheme of the embodiment of the application ensures efficient and safe tower climbing operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of iron tower climbing assistance, in particular to a power assisting method and device for assisting iron tower climbing. BACKGROUND

[0002] With the rapid development of power, communication and other infrastructure, the demand for iron tower climbing operations is increasing. Iron tower climbing is a high-risk and high-intensity task, and the operating personnel need to complete high-altitude operations in a complex environment, which puts high requirements on physical strength and safety.

[0003] The traditional climbing method mainly relies on manpower. The operating personnel not only need to overcome their own gravity, but also need to deal with the complexity of the iron tower structure (such as uneven cross arm spacing, rusted areas, etc.), resulting in high physical consumption, low operation efficiency, and high safety risks. In recent years, lower limb exoskeleton assisting devices have gradually been introduced into iron tower climbing operations as an auxiliary tool. Such devices provide additional assistance to operating personnel through mechanical structures, reducing the physical burden during climbing.

[0004] However, existing lower limb exoskeleton assisting devices use motors or hydraulic drives, which are stiff and have delayed responses, and cannot simulate the compliance characteristics of human muscles, resulting in uncoordinated climbing movements and increased user physical consumption. Moreover, due to the lack of active sensing capabilities for iron tower structures (such as rust, cracks) and environmental risks, it is difficult to achieve safe path planning. SUMMARY

[0005] Embodiments of the present application aim to at least solve one of the deficiencies in the above-mentioned technology. By sensing the climbing intention of the operating personnel and the environment of the iron tower climbing, the efficiency and safety of the iron tower climbing operation are ensured.

[0006] In a first aspect, the present application provides a power assisting method for assisting iron tower climbing, comprising:

[0007] S101, collecting lower limb muscle deformation signals and plantar pressure distribution signals of a target object; predicting the climbing intention of the target object through the lower limb muscle deformation signals; determining the climbing stage of the target object through the plantar pressure signals;

[0008] S102, generating an initial desired joint trajectory according to the climbing intention and the climbing stage; setting initial joint stiffness and damping parameters according to the initial desired joint trajectory; real-time sensing of environmental information around the iron tower, dynamic adjustment of the desired joint trajectory and joint stiffness and damping coefficients;

[0009] S103, inputting the joint stiffness and damping coefficients into a dielectric elastomer soft body; the dielectric elastomer soft body simulates the muscle activation of the target object and drives each joint in the soft body to output an assisting torque to the target object.

[0010] Further, S101 specifically includes:

[0011] S201, acquiring in real time through a flexible electronic skin array, capturing lower limb muscle deformation signals of quadriceps and calf muscles of the target object; extracting intrinsic mode function features of the lower limb muscle deformation signals by performing CEEMDAN signal decomposition on the lower limb muscle deformation signals;

[0012] S202, inputting the intrinsic mode function into a preset time-dynamics model, the output of the time-dynamics model being an estimated result of muscle activation; obtaining muscle activation information according to the estimated result of muscle activation;

[0013] S203, acquiring pressure distribution information through a plantar pressure sensor; inputting the muscle activation information and the pressure distribution information into a preset dual-channel LSTM neural network, the output of the dual-channel LSTM neural network being a climbing intention and a climbing stage of the target object.

[0014] Further, S102 specifically includes:

[0015] S301: formulating an initial climbing strategy according to the climbing intention and the climbing stage; inputting the initial climbing strategy into a double-layer optimization model, the upper layer of the model aiming to generate an initial desired joint trajectory according to the initial climbing strategy, and the lower layer of the model aiming to initialize joint stiffness damping coefficients according to the initial desired joint trajectory;

[0016] S302: establishing a biomimetic compound eye vision network and a pulse neural network; acquiring multispectral image information of the tower through the biomimetic compound eye vision network; identifying structural hidden danger information of the tower through the pulse neural network;

[0017] S303, according to the multispectral image information of the tower and the structural hidden danger information of the tower, real-time correcting the climbing strategy, and inputting the corrected climbing strategy into the double-layer optimization model to dynamically adjust the desired joint trajectory and the joint stiffness damping coefficients.

[0018] Further, S303 specifically includes:

[0019] S401, according to the structural hidden danger information of the tower, adjusting the adhesion between the target object and the tower to generate a new climbing strategy;

[0020] S402, identifying whether the new climbing strategy has a structural resonance risk through the surface acoustic wave sensor; if not, the new climbing strategy is taken as the current climbing strategy; if yes, a tactile feedback and transcranial electrical stimulation are triggered to modify the new climbing strategy, and the modified climbing strategy is taken as the current climbing strategy.

[0021] S403, inputting the current climbing strategy into the double-layer optimization model to dynamically adjust the expected joint trajectory and the joint stiffness damping coefficient.

[0022] Further, the judgment condition of the structural resonance risk is that the resonance frequency offset Δf is detected through the surface acoustic wave sensor, and when Δf>5%, the structural resonance risk exists.

[0023] Further, the method further comprises:

[0024] The climbing strategy is divided into a real-time control sub-group and a path optimization sub-group through the bee colony optimization algorithm, and different motion modes are set for different target objects;

[0025] The real-time control sub-group is used for optimizing the assist torque of the target object, and the path optimization sub-group is used for optimizing the joint trajectory of the target object.

[0026] Further, the method further comprises:

[0027] The motion mode of different target objects is adapted through a transfer learning method, and a reward function balances the action relationship among the work efficiency, work safety and work energy consumption;

[0028] The reward function is defined as:

[0029] R=w1×efficiency+w2×safety-w3×energy consumption

[0030] Wherein, w1, w2 and w3 are dynamic weight coefficients.

[0031] In a second aspect, the application provides an assistive device for assisting tower climbing, comprising:

[0032] The acquisition module is used for acquiring the lower limb muscle deformation signal and the foot pressure distribution signal of the target object; the climbing intention of the target object is predicted through the lower limb muscle deformation signal; and the climbing stage of the target object is judged through the foot pressure signal.

[0033] The generation module is used for generating an initial expected joint trajectory according to the climbing intention and the climbing stage; setting an initial joint stiffness damping parameter according to the initial expected joint trajectory; and dynamically adjusting the expected joint trajectory and the joint stiffness damping coefficient by real-time sensing the environmental information around the tower.

[0034] An assisting module is configured to input the joint stiffness damping coefficient into a dielectric elastomer soft body, and the dielectric elastomer soft body simulates muscle activation of the target object and drives each joint in the soft body to output an assisting torque to the target object.

[0035] In a third aspect, an electronic device is provided, and the electronic device comprises:

[0036] at least one processor; and

[0037] a memory connected with the at least one processor; wherein

[0038] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the assisting method for tower climbing.

[0039] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores computer instructions for enabling a processor to execute the assisting method for tower climbing when the processor executes the computer instructions.

[0040] Compared with the prior art, the present application has the following beneficial effects:

[0041] In the embodiment of the present application, the climbing intention and the climbing stage of the target object are analyzed by collecting the lower limb muscle deformation signal and the foot pressure distribution signal, and the initial desired joint trajectory and the initial joint stiffness damping parameter are generated. The desired joint trajectory and the joint stiffness damping coefficient are dynamically adjusted according to the environmental information around the tower. Finally, the dielectric elastomer soft body is used to drive each joint in the soft body to output an assisting torque to the target object, so as to realize the soft assisting force for the target object and ensure the safety and efficiency of the work. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only preferred embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 A flowchart of an assisting method for tower climbing provided by the first embodiment of the present application is shown in the figure.

[0044] Figure 2 A structural diagram of an assisting device for tower climbing provided by the second embodiment of the present application is shown in the figure.

[0045] Figure 3 The structural schematic diagram of the electronic device provided for the third embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0047] Embodiment one

[0048] Figure 1 The flowchart of the power assisting method for assisting tower climbing provided for the first embodiment of the present application. The embodiment can be applicable to the case of completing high-altitude operation in a complex environment. The method can be executed by the power assisting device for assisting tower climbing provided for the second embodiment of the present application. The device can be implemented in the software and / or hardware manner.

[0049] As Figure 1 shown, the method specifically includes:

[0050] S101, collecting lower limb muscle deformation signals and plantar pressure distribution signals of a target object; predicting a climbing intention of the target object through the lower limb muscle deformation signals; and judging a climbing stage of the target object through the plantar pressure signals.

[0051] It should be noted that the target object refers to an operator performing tower climbing high-altitude operation. Before climbing, the target object needs to wear the power assisting device for assisting tower climbing. The power assisting device for assisting tower climbing is an innovative lower limb exoskeleton assisting device. The lower limb muscle deformation signals of the target object can be collected through surface electromyography sensors. The plantar pressure signals of the target object can be collected through plantar pressure sensors. The climbing intention includes intentions such as not climbing, climbing upward, and climbing downward. The climbing stage includes stages such as preparing to climb, climbing, and ending climbing.

[0052] It can be understood that the power assisting device for assisting tower climbing can be internally arranged with various physiological signal collecting elements such as surface electromyography sensors and plantar pressure sensors to collect multiple modal physiological signals of the target object. For example, a temperature sensor is arranged to collect the body temperature of the target object.

[0053] In a specific application scenario, for example, an operator needs to overhaul an old power transmission tower with a height of 60 meters. The cross arm of the tower is rusted at multiple places, and some bolts are loose. The operator needs to wear the power assisting device for assisting tower climbing in the second embodiment of the present application to perform the climbing task.

[0054] During the wearing process of the device, the operator stands beside the specially designed wearing auxiliary frame and first aligns the leg part of the auxiliary iron tower climbing assisting device with the lower limbs; by adjusting the belt, the hip joint, knee joint and ankle joint parts are ensured to be closely and comfortably fitted; the belt has elasticity and adjustability and can adapt to different body types; then, the waist support part is fixed to be stably and closely fitted to the waist to provide overall support, and the whole wearing process takes about 3 minutes.

[0055] After the wearing of the device is completed, the operator starts the power supply of the device, and sets the initial parameters of the device through the handheld control terminal; according to the body parameters of the operator, such as height 175cm and weight 75kg, the basic size and adaptive parameters of the exoskeleton are set; at the same time, the surface electromyography sensor and the plantar pressure sensor are calibrated to ensure accurate data acquisition, for example, the surface electromyography sensor needs to be closely attached to the surface of the quadriceps femoris muscle, hamstrings and other key muscle groups, and the signal conduction is enhanced by applying special conductive gel.

[0056] Further, S101 specifically includes:

[0057] S201, real-time acquisition is performed through the flexible electronic skin array to capture lower limb muscle deformation signals of the quadriceps femoris muscle and the calf muscle of the target object; and intrinsic mode function features of the lower limb muscle deformation signals are extracted through CEEMDAN signal decomposition on the lower limb muscle deformation signals.

[0058] The flexible electronic skin array is made of graphene / liquid metal composite material, and the muscle contraction strength is quantified through resistance strain and capacitance coupling dual-mode sensing.

[0059] Since the surface electromyography sensor is susceptible to electromagnetic interference, sweat or vibration environment when performing motion intention recognition, the intention recognition error is large; therefore, the embodiment of the present application adopts the mode of integrating the surface electromyography sensor in the flexible electronic skin array to realize the detection of muscle electrical signals. At the same time, the wearability and flexibility of the flexible electronic skin make it better fit the skin, improve the accuracy and comfort of the surface electromyography signal detection.

[0060] Specifically, the operator approaches the iron tower ladder stand and prepares to start climbing. At this time, the surface electromyography sensor collects the initial contraction signals of the quadriceps femoris muscle and the calf muscle, and extracts the key intrinsic mode function features through CEEMDAN algorithm decomposition.

[0061] CEEMDAN is a signal decomposition method based on adaptive noise control, in the extraction process of each intrinsic mode function IMF, an adaptive noise related to the current IMF is added. This adaptive noise is obtained by calculating the weighted sum of the residual of the previous IMF and the current noise. With the gradual extraction of IMF, the influence of noise will gradually decrease, thus avoiding the problem of noise residue. At the same time, in the extraction process of each IMF, the algorithm will adaptively adjust the amplitude and frequency of the noise according to the current residual, ensuring the convergence of the algorithm.

[0062] Any signal is composed of several intrinsic mode functions IMF, at any time, a signal can contain several intrinsic mode functions, if the intrinsic mode functions overlap with each other, a composite signal is formed.

[0063] S202, input the intrinsic mode function into the preset time-dynamics model, and the output of the time-dynamics model is the estimated result of muscle activation; obtain muscle activation information according to the estimated result of muscle activation.

[0064] Among them, the muscle activation can stably reflect the muscle contraction; the muscle activation information includes: the average absolute value, the root mean square value and the integral absolute value of the muscle activation, etc.; the average absolute value (MAV) refers to the average value of the absolute value of the muscle activation; the root mean square value (RMS) refers to the square average value of the muscle activation; the integral absolute value (IAV) refers to the integral value of the absolute value of the muscle activation.

[0065] In the embodiment of the application, the relationship between the intrinsic mode function characteristics and the muscle activation is established through a large number of model training. When the intrinsic mode function characteristics are input into the model, the model solves the intrinsic mode function characteristics, estimates the muscle activation, and calculates the average absolute value, the root mean square value and the integral absolute value of the muscle activation according to the muscle activation.

[0066] S203, collect pressure distribution information through a plantar pressure sensor; input the muscle activation information and the pressure distribution information into a preset double-channel LSTM neural network, and the output of the double-channel LSTM neural network is the climbing intention and the climbing stage of the target object.

[0067] Specifically, the first channel of the double-channel LSTM neural network processes the muscle activation information to predict the climbing intention of the target object, and the second channel analyzes the center trajectory of the plantar pressure to determine the climbing stage of the target object. Through a large number of model training, the relationship between the muscle activation information and the climbing intention is established, and the relationship between the pressure distribution information and the climbing stage is established. The attention mechanism is introduced into the double-channel LSTM neural network, and the motion intention of the operator is determined by fusing the muscle activation information and the pressure distribution information.

[0068] S102, generating an initial desired joint trajectory according to the climbing intention and the climbing stage; setting initial joint stiffness damping parameters according to the initial desired joint trajectory; perceiving environmental information around the tower in real time, and dynamically adjusting the desired joint trajectory and the joint stiffness damping coefficient.

[0069] The environmental information around the tower includes multispectral image information and structural hidden danger information of the tower, etc. The joint stiffness damping coefficient includes a stiffness coefficient and a damping coefficient, etc. The stiffness coefficient is the relationship between force and displacement, and the damping coefficient is the relationship between force and velocity.

[0070] Further, S102 specifically includes:

[0071] S301: formulating an initial climbing strategy according to the climbing intention and the climbing stage; inputting the initial climbing strategy into a double-layer optimization model, the upper layer of the model aiming to generate an initial desired joint trajectory according to the initial climbing strategy, and the lower layer of the model aiming to set initial joint stiffness damping coefficients according to the initial desired joint trajectory.

[0072] Preferably, through cloud collaboration technology, the edge end is responsible for collecting muscle activation information and pressure distribution information in real time, and performing real-time impedance control, and the cloud deploys a double-channel LSTM neural network and a double-layer optimization model to formulate a climbing strategy and optimize the global climbing path.

[0073] The climbing strategy includes a climbing path, etc. Through the double-layer optimization model, the exoskeleton gently assists the worker to lift the leg and take the first step of climbing. The upper layer of the model adopts a model predictive control algorithm MPC, and the lower layer of the model adopts a particle swarm algorithm. The MPC algorithm can determine the optimal control input at the current time by solving a finite-time optimization problem, and then apply the first value of the control input to the system, and repeat the above process at the next sampling time, and continuously roll optimization. The particle swarm algorithm uses the sharing of information of individuals in the group to make the movement of the whole group evolve from disorder to order in the problem solving space, so as to obtain a feasible solution of the problem.

[0074] S302: establishing a bionic compound eye vision network and a pulse neural network; acquiring multispectral image information of the tower through the bionic compound eye vision network; and identifying structural hidden danger information of the tower through the pulse neural network.

[0075] Specifically, the bionic compound eye vision network is used to acquire multispectral images of the tower, the pulse neural network is used to identify structural corrosion, cracks and bolt loosening hidden dangers, and the risk level is labeled; and then the perception of the climbing surrounding environment is completed.

[0076] In the power-assisted device for assisting in climbing the iron tower, elements such as laser radar and camera for environmental perception are arranged, forming a bionic compound eye vision network and a pulse neural network. For example, when the worker climbs to about 10 meters and encounters a region with a large distance between cross arms. The laser radar scans the surrounding environment in real time, and the point cloud data is quickly identified as the edge of the tower cross arm structure through the improved RANSAC algorithm. The camera can cover a 360° panoramic field of view, support ultraviolet light tower oxidation feature recognition and infrared temperature difference detection; the pulse neural network processes multispectral data in real time through space-time pulse coding, and outputs the risk area coordinates and confidence.

[0077] The RANSAC algorithm is an algorithm used in computer vision, which can calculate the mathematical model parameters of the data according to a sample data set containing abnormal data, and obtain effective sample data. The pulse neural network SNN is a deep learning algorithm, and has strong biological basis support, which can process biological stimuli by simulating the working principle of biological neurons, explain the intelligent behavior of the brain, and interface with the biological nervous system.

[0078] S303, according to the multispectral image information of the iron tower and the structure hidden danger information of the iron tower, real-time correction of the climbing strategy, and input the corrected climbing strategy to the double-layer optimization model, dynamically adjust the expected joint trajectory and joint stiffness damping coefficient.

[0079] Specifically, a safe climbing path is generated using cubic spline interpolation. In this process, the body posture of the worker changes, and the surface electromyogram signal and plantar pressure data also change. These changes are continuously and accurately perceived through a multi-modal data fusion algorithm, and the dynamic adaptive control algorithm adjusts the joint stiffness damping parameters in a timely manner. For example, when the worker needs to turn sideways to bypass an obstacle, the hip joint and knee joint of the exoskeleton dynamically adjust the stiffness and damping according to the algorithm instructions, provide appropriate assistance and support, and ensure smooth and safe movement. At the same time, the hardware acceleration module ensures fast operation of the algorithm, 1kHz actuator current loop control makes the magneto-rheological actuator respond quickly, 100Hz impedance parameter adjustment ensures comfortable joint movement, and 10Hz path planning update adjusts the climbing path according to real-time environmental changes.

[0080] Further, S303 specifically includes:

[0081] S401, according to the structure hidden danger information of the iron tower, adjust the adhesion between the target object and the iron tower, generate a new climbing strategy.

[0082] S402, identifying whether the new climbing strategy has a structural resonance risk through the surface acoustic wave sensor; if not, the new climbing strategy is taken as the current climbing strategy; if yes, triggering the tactile feedback and transcranial electrical stimulation to modify the new climbing strategy, and taking the modified climbing strategy as the current climbing strategy.

[0083] S403, inputting the current climbing strategy into the double-layer optimization model to dynamically adjust the expected joint trajectory and the joint stiffness damping coefficient.

[0084] Wherein, the judgment condition of the structural resonance risk is that the resonance frequency offset Δf is detected through the surface acoustic wave sensor, and when Δf>5%, a three-level alarm is triggered, and the structural resonance risk exists. The adhesion strength of the magnetorheological fluid can be controlled through the current, and the adjustable range of the adhesion force is 50-500N; and the surface acoustic wave sensor can detect the resonance frequency offset Δf of the tower cross arm.

[0085] According to the structural hidden danger information of the tower, the adhesion force between the target object and the tower is adjusted. For example, when the user crosses the rusty cross arm, the knee part of the device: according to the path curvature, the electric field strength is dynamically adjusted (2kV→4kV), the shrinkage rate is smoothly transitioned from 20% to 45%, and the assist torque is increased from 50N·m to 120N·m, simulating the natural muscle power curve; the foot part of the device: the current of the magnetorheological fluid is increased from 0.5A to 1.5A, and the adhesion force is increased from 100N to 300N, preventing the foot from slipping on the rusty surface.

[0086] When there is a structural resonance risk, the tactile feedback and transcranial electrical stimulation are triggered. For example, the surface acoustic wave sensor detects that the resonance frequency offset Δf of a cross arm is 6%(baseline frequency 1kHz→940Hz), and it is determined that there is a structural instability risk. The tactile feedback array triggers 80Hz high-frequency vibration at the foot, the transcranial electrical stimulation (tES) applies 1.5mA current to stimulate the user's motor cortex; the current of the foot part of the device is suddenly increased to 2A, and the adhesion force is locked at 500N to provide rigid support; at the same time, the driving part of the device is reversely contracted, and outputs 150N·m torque to assist the user to move sideways to escape the dangerous area.

[0087] In the embodiment of the application, the foot stability is enhanced through the magnetorheological adhesion-locking dual-state switching mechanism, and the human-machine collaborative risk avoidance is realized by triggering the tactile feedback and transcranial electrical stimulation.

[0088] Further, in order to set different motion modes for different target objects, the climbing strategy can be divided into a real-time control sub-group and a path optimization sub-group through a bee colony optimization algorithm to set corresponding motion modes for the target objects; wherein, the real-time control sub-group is used to optimize the assist torque of the target object, and the path optimization sub-group is used to optimize the joint trajectory of the target object.

[0089] Further, in order to balance the action efficiency, action safety and action energy consumption, the motion mode of different target objects is adapted through a transfer learning method in a meta reinforcement learning framework, and a reward function is defined as:

[0090] R = w1 x efficiency + w2 x safety - w3 x energy consumption

[0091] wherein w1, w2 and w3 are dynamic weight coefficients.

[0092] In S103, the joint stiffness damping coefficient is input into the dielectric elastomer, the dielectric elastomer simulates the muscle activation of the target object, and drives each joint in the soft body to output the assist torque to the target object.

[0093] Optionally, based on the output of the dielectric elastomer, the mechanical vibration energy is converted into electrical energy by using the friction nanometer generator synchronously.

[0094] Optionally, the dielectric elastomer adopts a laminated structure, the voltage response rate is <10 ms, and the output density reaches 30 N / cm 2 ; the friction nanometer generator is embedded in the joint hinge and the foot bottom contact surface, and the output power satisfies the following formula:

[0095] P TENG =k·f 1.2 ·A 0.8

[0096] wherein f is the vibration frequency, A is the amplitude, and k is the material coupling coefficient.

[0097] Optionally, the working voltage of the dielectric elastomer is 0.5-5kV, and the relationship between the deformation rate ε and the electric field strength E satisfies:

[0098] ε = λ·E 2 + μ·E

[0099] wherein λ and μ are material nonlinear coefficients.

[0100] Further, during the climbing process, an energy self-consistent model can also be set. For example, the friction nanometer generator (TENG) at the knee joint hinge converts the impact vibration (frequency 20 Hz, amplitude 2 mm) into electrical energy, and the single-step recovery energy is 0.15J, which is stored in the super capacitor. After unloading the device, the deformation rate (threshold <5%) of the driving unit and the state of the magnetorheological fluid (viscosity error <3%) are automatically detected, and a maintenance report is generated.

[0101] The embodiment of the application extracts the eigenmode function features in the signal, analyzes the muscle activation information of the operation personnel, and simultaneously collects the plantar pressure distribution information of the operation personnel through the plantar pressure sensor; high-precision recognition of the user's movement intention is realized, and potential risks such as rust and cracks of the tower structure are actively detected, so as to ensure the safety of the climbing path; through the magneto-rheological adhesion-locking mechanism, the foot support force can be dynamically adjusted to adapt to the needs of different climbing stages, and the stability and adaptability of the system are greatly enhanced; through real-time adjustment of the climbing strategy, closed-loop control of the entire climbing process is formed, and efficient and safe operation is ensured.

[0102] Embodiment two

[0103] Figure 2 A structural schematic diagram of a power-assisted device for assisting tower climbing is provided for the second embodiment of the application. Figure 2 As shown in the figure, the device specifically includes:

[0104] The acquisition module 100 is used for collecting the lower limb muscle deformation signal and the plantar pressure distribution signal of the target object; the climbing intention of the target object is predicted through the lower limb muscle deformation signal; and the climbing stage of the target object is judged through the plantar pressure signal.

[0105] The generation module 200 is used for generating an initial desired joint trajectory according to the climbing intention and the climbing stage; setting initial joint stiffness damping parameters according to the initial desired joint trajectory; and dynamically adjusting the desired joint trajectory and the joint stiffness damping coefficient by real-time sensing of the environmental information around the tower.

[0106] The power-assisted module 300 is used for inputting the joint stiffness damping coefficient into the dielectric elastomer soft body; the dielectric elastomer soft body simulates the muscle activation of the target object, and drives each joint in the soft body to output a power torque to the target object.

[0107] Optionally, the device can be provided with multiple sensing units, such as a flexible electronic skin array, a bionic compound eye vision system, and a nine-axis inertial measurement unit (IMU), etc.

[0108] Optionally, the device can be provided with multiple bionic driving units, such as hip, knee, and ankle joints integrated with dielectric elastomer driving units and triboelectric nanogenerators (TENG), and a magnesium alloy hollow structure with topological optimization for the support skeleton, etc.

[0109] Optionally, the device can be provided with a decision control unit, such as an edge-mounted FPGA and real-time operating system (RTOS), a cloud-connected quantum annealing coprocessor, etc.

[0110] Optionally, the device can be provided with a safety protection unit, such as an integrated magneto-rheological adhesion foot pad, a surface acoustic wave sensor, and a tactile feedback array, etc.

[0111] In the embodiment of the present application, the acquisition module is used to acquire multiple modal signals of the target object, and analyze the climbing intention and the climbing stage; the generation model is used to dynamically adjust the expected joint trajectory and the joint stiffness damping coefficient; and the power assisting module is used to provide soft power assistance to the target object, thereby providing a more intelligent and safe solution for high-altitude operation.

[0112] Embodiment three

[0113] Figure 3 is a structural schematic diagram of an electronic device for implementing the power assisting method for assisting tower climbing. The electronic device is intended to represent various forms of digital computers, such as a laptop computer, a desktop computer, a workstation, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.), and other similar computing devices. The components shown herein, their connections, and relationships, and their functions, are merely examples and are not intended to limit the implementation of the present application described herein and / or claimed.

[0114] As shown in Figure 3 , the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] The plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, a loudspeaker, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunications networks.

[0116] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, and the like. The processor 11 performs various methods and processes described above, such as the power-assisted tower climbing method.

[0117] In some embodiments, the power-assisted tower climbing method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the power-assisted tower climbing method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the power-assisted tower climbing method by any other suitable means, such as by means of firmware.

[0118] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0119] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0120] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0122] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business expansion in traditional physical host and VPS service.

[0124] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted, using the steps. For example, each step described in the present application can be executed in parallel, can be executed sequentially, or can be executed in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0125] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for assisting in climbing iron towers, characterized in that, include: S101, Collect the lower limb muscle deformation signal and foot pressure distribution signal of the target object; predict the climbing intention of the target object through the lower limb muscle deformation signal; The climbing stage of the target object is determined by the foot pressure distribution signal. S102, Generate an initial expected joint trajectory based on the climbing intention and the climbing stage; Set initial joint stiffness and damping parameters based on the initial expected joint trajectory; Real-time perception of environmental information around the tower, and dynamic adjustment of desired joint trajectory and joint stiffness damping coefficient; S103, input the joint stiffness damping coefficient into the dielectric elastic software; The dielectric elastic soft body simulates the muscle activation level of the target object and drives each joint in the soft body to output assist torque to the target object; S102 specifically includes: S301: Based on the climbing intention and the climbing stage, formulate an initial climbing strategy; input the initial climbing strategy into a two-layer optimization model, the upper layer of the model aims to generate an initial expected joint trajectory based on the initial climbing strategy, and the lower layer of the model aims to set the initial joint stiffness damping coefficient based on the initial expected joint trajectory. S302: Establish a biomimetic compound eye visual network and a spiking neural network; acquire multispectral image information of the iron tower through the biomimetic compound eye visual network; identify structural hazard information of the iron tower through the spiking neural network; S303, based on the multispectral image information of the tower and the structural hazard information of the tower, the climbing strategy is corrected in real time, and the corrected climbing strategy is input into the dual-layer optimization model to dynamically adjust the desired joint trajectory and joint stiffness damping coefficient.

2. The method according to claim 1, characterized in that, S101 specifically includes: S201, real-time acquisition is performed using a flexible electronic skin array to capture the lower limb muscle deformation signals of the quadriceps femoris and calf muscles of the target object; the intrinsic mode function features of the lower limb muscle deformation signals are extracted by performing CEEMDAN signal decomposition on the lower limb muscle deformation signals. S202, the intrinsic mode function is input into a preset time-kinetic model, and the output of the time-kinetic model is the predicted result of muscle activation; based on the predicted result of muscle activation, muscle activation information is obtained; S203, pressure distribution information is collected through a plantar pressure sensor; the muscle activation information and the pressure distribution information are input into a preset dual-channel LSTM neural network, and the output of the dual-channel LSTM neural network is the climbing intention and climbing stage of the target object.

3. The method according to claim 1, characterized in that, S303 specifically includes: S401, Based on the structural hazard information of the iron tower, adjust the adhesion force between the target object and the iron tower to generate a new climbing strategy; S402, using a surface acoustic wave sensor, identify whether the new climbing strategy has a risk of structural resonance; if not, use the new climbing strategy as the current climbing strategy; if so, trigger tactile feedback and transcranial electrical stimulation to modify the new climbing strategy, and use the modified climbing strategy as the current climbing strategy. S403, input the current climbing strategy into the dual-layer optimization model to dynamically adjust the desired joint trajectory and joint stiffness damping coefficient.

4. The method according to claim 3, characterized in that, The criterion for determining the structural resonance risk is: detecting the resonance frequency shift using a surface acoustic wave sensor. ,when At that time, there is a risk of structural resonance.

5. The method according to claim 3, characterized in that, Also includes: The climbing strategy is divided into a real-time control subgroup and a path optimization subgroup using a bee colony optimization algorithm, and different movement modes are set for different target objects. The real-time control subgroup is used to optimize the assist torque of the target object, and the path optimization subgroup is used to optimize the joint trajectory of the target object.

6. The method according to claim 5, characterized in that, Also includes: The transfer learning method is used to adapt to the motion patterns of different target objects, and the reward function balances the relationship between work efficiency, work safety and work energy consumption. The reward function is defined as follows: ； in, , , These are dynamic weighting coefficients.

7. A power-assisted device for climbing iron towers, characterized in that, The apparatus is configured to implement the method according to any one of claims 1-6, the apparatus comprising: The acquisition module is used to acquire lower limb muscle deformation signals and plantar pressure distribution signals of the target object; predict the target object's climbing intention through lower limb muscle deformation signals; and determine the target object's climbing stage through plantar pressure distribution signals. The generation module is used to generate an initial expected joint trajectory based on the climbing intention and the climbing stage; set initial joint stiffness and damping parameters based on the initial expected joint trajectory; and dynamically adjust the expected joint trajectory and joint stiffness and damping coefficient by sensing the environmental information around the tower in real time. The assist module is used to input the joint stiffness damping coefficient into the dielectric elastic software; the dielectric elastic software simulates the muscle activation of the target object and drives each joint in the software to output assist torque to the target object; The generation module is specifically used for: S301: Based on the climbing intention and the climbing stage, formulate an initial climbing strategy; input the initial climbing strategy into a two-layer optimization model, the upper layer of the model aims to generate an initial expected joint trajectory based on the initial climbing strategy, and the lower layer of the model aims to set the initial joint stiffness damping coefficient based on the initial expected joint trajectory. S302: Establish a biomimetic compound eye visual network and a spiking neural network; acquire multispectral image information of the iron tower through the biomimetic compound eye visual network; identify structural hazard information of the iron tower through the spiking neural network; S303, based on the multispectral image information of the tower and the structural hazard information of the tower, the climbing strategy is corrected in real time, and the corrected climbing strategy is input into the dual-layer optimization model to dynamically adjust the desired joint trajectory and joint stiffness damping coefficient.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the steps of the assistive method for climbing the iron tower as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the steps of the assistive tower climbing method according to any one of claims 1-6.

Images