Intelligent energy-saving electric wheelchair balance system

Abstract

The invention relates to the technical field of intelligent control, and discloses an intelligent energy-saving electric wheelchair balance system which comprises a driving layer, a control layer, a data layer and a display layer. By arranging a balance judgment module in the data layer, the balance stability value of the electric wheelchair can be obtained on the basis of a built balance prediction model, balance stability judgment is carried out, and therefore intelligent control over the electric wheelchair is carried out; the trained neural network model is integrated into the calculation of intelligent control, so that the nonlinear and multi-modal data modeling capability of the neural network can be brought into full play, and a complex data relationship can be effectively captured; according to a parallel computing processing mechanism, the computing efficiency is improved, and an intelligent control result is obtained through a deep learning technology, so that the pertinence and effectiveness of intelligent balance control of the electric wheelchair are improved; and data are fully utilized, and a complex data relationship is captured through a deep learning technology, so that the effectiveness and the accuracy of intelligent balance control of the electric wheelchair are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and more specifically to an intelligent energy-saving electric wheelchair balancing system. Background Art

[0002] With the aggravation of the problem of population aging, more and more people with limited mobility need to use electric wheelchairs as a means of transportation; the wheelchairs available on the market are basically divided into three grades: low, medium and high. The low grade is an ordinary push wheelchair, the medium grade is an electric wheelchair, and the high-end wheelchair has various special functions, some are specially used for climbing stairs, and some can be transformed into a lying position; generally speaking, the current finished electric wheelchairs are not perfect enough, the price is still too expensive, and more intelligent functions are not reflected.

[0003] The public document with publication number CN116300900A discloses an automatic slope obstacle avoidance and speed control system and method for an electric wheelchair, including: a drive module, an automatic obstacle avoidance module, a self-balancing controller module, a speed sensor module, a heart rate detection module, an alarm module, a deceleration module and a central processing module; the drive module, the automatic obstacle avoidance module, the self-balancing controller module, the speed sensor module, the heart rate detection module, the alarm module and the deceleration module are all electrically connected to the central processing module; the passenger can be reminded to avoid sections of the road where the electric wheelchair cannot climb in advance, and the speed after 2 seconds is estimated by measuring the acceleration and real-time speed, and the speed is reduced in advance before the upper limit of the wheelchair climbing speed is reached. The distance to the obstacle is measured by an ultrasonic sensor and an infrared sensor, and automatic obstacle avoidance is achieved through a fuzzy control algorithm. The slope stability of the wheelchair is achieved through the self-balancing control module.

[0004] However, these methods still need to be improved in terms of energy consumption, stability and intelligence. Traditional electric wheelchairs may lose balance and cause users to fall when traveling on uneven ground, which poses certain safety risks. Keeping the electric wheelchair balanced is the key to ensuring its safety. At the same time, as the use time of traditional electric wheelchairs increases, the balance control ability of the electric wheelchair system will gradually decrease. Therefore, it is necessary to monitor the balance control performance of the electric wheelchair in a timely manner and take corresponding repair measures to ensure the control performance of the electric wheelchair and improve the intelligence of the management of the balance control performance of the electric wheelchair. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent energy-saving electric wheelchair balancing system to solve the problems existing in the above-mentioned background technology.

[0006] The present invention provides the following technical solutions: an intelligent energy-saving electric wheelchair balancing system, comprising a driving layer, a control layer, a data layer and a display layer; The driving layer is used to drive the electric wheelchair to operate and run according to corresponding control instructions; The control layer is used to send corresponding control instructions to the drive layer and perform intelligent control on the electric wheelchair; The data layer is used to collect and analyze the data of the electric wheelchair, including: Basic data acquisition module: used to collect the basic data of the electric wheelchair and transmit it to the data preprocessing module for preprocessing operations; Data preprocessing module: used to receive data from the basic data acquisition module and the control data acquisition module, perform preprocessing operations on the data, and obtain data that can be directly used; Balance judgment module: used to receive the data preprocessed by the data preprocessing module, obtain the balance stability value of the electric wheelchair based on the constructed balance prediction model, and make a balance stability judgment, and send corresponding control instructions to the control layer based on the judgment result; Control data acquisition module: used to collect control data from the control layer and transmit it to the data preprocessing module for preprocessing; Influencing factor acquisition module: used to obtain the influencing factors that affect the balance performance of the electric wheelchair, the influencing factors include control compensation factors and energy contribution factors, and transmit them to the comprehensive balance performance analysis module; Comprehensive balance performance analysis module: used to analyze the comprehensive balance performance of the electric wheelchair and obtain the comprehensive balance performance index; Performance judgment module: used to judge the comprehensive balance performance index of the electric wheelchair, and send a warning instruction to the display layer according to the judgment result, and transmit the data to the display layer at the same time; The display layer is used to visualize the analysis results of the data layer and perform intelligent early warning.

[0007] Preferably, the control layer includes a PID control module and a wheelchair main body control module; the PID control module is used to intelligently control the electric wheelchair parameter data using a PID controller; the wheelchair main body control module is used to intelligently control the electric wheelchair entity; The data preprocessing module includes a basic data preprocessing unit and a control data preprocessing unit. The basic data preprocessing unit is used to preprocess the basic data and then transmit it to the balance determination module; the control data preprocessing unit is used to preprocess the control data and then transmit it to the influence factor acquisition module.

[0008] Preferably, the basic data includes the weight, real-time speed, force condition, tilt angle, motor power, output torque, acceleration and angular velocity of the electric wheelchair; The control data includes actual control data, predetermined control data, control time and control energy consumption; the actual control data is the actual control value of the electric wheelchair, that is, the actual value reached after the driving layer operates and runs the electric wheelchair according to the control instructions; the predetermined control data is the predetermined control value of the electric wheelchair, that is, the control value of the electric wheelchair by the control layer; the control value includes speed control value, motor power control value and output torque control value; the control time is the time required to complete the control of the electric wheelchair; the control energy consumption is the energy consumption generated when controlling the electric wheelchair.

[0009] Preferably, the PID controller is composed of a proportional unit, an integral unit and a differential unit. The PID control calculates the control deviation according to the given input value and the actual output value. The formula is expressed as: , where e(t) is the control deviation at time t, r(t) is the given input value at time t, and y(t) is the actual input value at time t; The control algorithm expression of PID controller is: , where u(t) is the control output, k p is the proportionality coefficient, T I and T D are the integral time constant and the differential time constant respectively.

[0010] Preferably, the equilibrium prediction model is constructed as follows: Take the basic data as analysis data, collect d groups of analysis data in advance, d is an integer greater than 1, and convert the analysis data and the corresponding equilibrium stability value into a corresponding set of characteristic vectors; each group of analysis data is each group of basic data, and the basic data at the ath moment is taken as the ath group of basic data; The equilibrium stability value corresponding to the analysis data can be calculated by the equilibrium stability value calculation formula, d groups of analysis data are collected, and each group of feature vectors is used as the input of the equilibrium prediction model, the equilibrium prediction model uses a group of predicted equilibrium stability values ​​corresponding to each group of analysis data as output, and uses the actual equilibrium stability value corresponding to each group of analysis data as the prediction target, and the actual equilibrium stability value is the equilibrium stability value corresponding to the analysis data collected in advance; minimizing the sum of the prediction errors of all analysis data is used as the training target; The prediction error is expressed as: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, θ p is the predicted equilibrium stability value corresponding to the pth group of analysis data, μ p The actual equilibrium stability value corresponding to the pth group of analysis data is used to train the equilibrium prediction model until the sum of the prediction errors reaches convergence and the training is stopped.

[0011] Preferably, the equilibrium stability value calculation formula is expressed as: , where PW t is the equilibrium stability value at the tth moment, LJ wt is the stable torque at the tth moment, LJ ft is the overturning moment at the tth moment; the stabilizing moment is the moment that keeps the object balanced, and the overturning moment is the moment that causes the object to overturn.

[0012] Preferably, the specific process of the balance stability determination module performing balance stability determination is: When the predicted balance stability value is greater than or equal to 0, the result is determined to be balanced, and no control instructions are sent to the control layer; When the predicted balance stability value is less than 0, the judgment result is unbalanced. At this time, a control instruction is sent to the control layer. If the electric wheelchair is in motion, only the PID control instruction is sent. At this time, the electric wheelchair parameter data is intelligently controlled. If the electric wheelchair is in a non-motion state, the PID control instruction and the main control instruction are sent, and the wheelchair entity is intelligently controlled at the same time.

[0013] Preferably, the calculation formula of the control compensation factor is expressed as: Among them, BK is the control compensation factor, Yk it The control value for the i-th type of basic data at the t-th time is preset, Sk it is the actual control value of the i-th type of basic data at the t-th moment, n is the total number of basic data categories, U is the total moment, i=1, 2, 3, …, n, t=1, 2, 3, …, U; The calculation formula of the energy contribution factor is expressed as: , where NG is the energy contribution factor, nh j is the energy consumption generated by the jth control, TC j is the duration of the jth control, J is the total number of controls, j=1, 2, 3, …, J.

[0014] Preferably, the calculation formula of the comprehensive balance performance index in the comprehensive balance performance analysis module is: , where ZH is the comprehensive balance performance index, vit is the number of successful controls in the control times, and J is the total control times.

[0015] Preferably, the specific manner in which the performance determination module determines the comprehensive balance performance index of the electric wheelchair is: When the comprehensive balance performance index ZH satisfies ZH≥YU, it is determined that no warning is needed and no warning information is sent to the display layer; When the comprehensive balance performance index ZH satisfies ZH<YU, it is determined that an early warning is required, and an early warning message is sent to the display layer; The YU is a safety threshold.

[0016] Technical effects and advantages of the present invention: (1) The present invention is provided with a balance judgment module, which is conducive to obtaining the balance stability value of the electric wheelchair based on the constructed balance prediction model and performing balance stability judgment, thereby intelligently controlling the electric wheelchair; integrating the trained neural network model into the calculation of intelligent control can give full play to the nonlinear and multimodal data modeling capabilities of the neural network and effectively capture complex data relationships; based on the parallel computing processing mechanism, the computing efficiency is improved, and the intelligent control results are obtained through deep learning technology, thereby improving the pertinence and effectiveness of the intelligent balance control of the electric wheelchair; making full use of data and capturing complex data relationships through deep learning technology, effectively improving the effectiveness and accuracy of the intelligent balance control of the electric wheelchair.

[0017] (2) The present invention is provided with an influencing factor acquisition module and a comprehensive balance performance analysis module, which is beneficial to obtaining the control compensation factor and energy contribution factor that affect the balance performance of the electric wheelchair, and then combining the analysis to obtain the comprehensive balance performance index; by obtaining the control compensation factor and the energy contribution factor, the comprehensive balance performance index is obtained, and the balance control performance analysis is performed in combination with the key influencing factors that affect the balance performance of the electric wheelchair, thereby improving the accuracy of the analysis of the balance control performance of the electric wheelchair, enhancing the intelligent level of the management of the balance control performance of the electric wheelchair, being able to monitor the balance control performance of the electric wheelchair in a timely manner and take corresponding measures in a timely manner, thereby reducing the risk of user use. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a structural diagram of the intelligent energy-saving electric wheelchair balancing system of the present invention.

[0019] Figure 2 This is a data layer structure diagram of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The intelligent energy-saving electric wheelchair balancing system involved in the present invention is not limited to the various structures recorded in the following embodiments. All other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0021] like Figure 1 As shown, the present invention provides an intelligent energy-saving electric wheelchair balancing system, including a driving layer, a control layer, a data layer and a display layer; The driving layer is used to drive the electric wheelchair to operate and run according to corresponding control instructions; The control layer is used to send corresponding control instructions to the drive layer and perform intelligent control on the electric wheelchair; the control layer includes a PID control module and a wheelchair body control module; the PID control module is used to perform intelligent control on the electric wheelchair parameter data using a PID controller; the wheelchair body control module is used to perform intelligent control on the electric wheelchair entity; the parameter data includes data parameters such as the posture, speed and motor parameters of the electric wheelchair; the electric wheelchair entity is a control component on the electric wheelchair, such as the electric wheelchair auxiliary wheelchair retraction and extension, footboard retraction and extension, and other electric wheelchair entity component parts that can be intelligently controlled; The data layer is used to collect and analyze the data of the electric wheelchair; The display layer is used to visualize the analysis results of the data layer and perform intelligent early warning.

[0022] In this embodiment, it should be specifically explained that the PID controller is a linear controller with a simple structure, which is composed of a proportional unit, an integral unit and a differential unit. The PID control calculates the control deviation according to the given input value and the actual output value. The formula is expressed as: , where e(t) is the control deviation at time t, r(t) is the given input value at time t, and y(t) is the actual input value at time t; the control deviation is subjected to proportional, integral and differential operations, and the results are summed to obtain the control output. In the continuous time domain, the control algorithm expression of the PID controller is: , where u(t) is the control output, k p is the proportionality coefficient, T I and T D are the integral time constant and the differential time constant respectively; The P in the PID controller is the proportional correction link, which is used to reflect the deviation signal exponentially. The controller immediately reduces the deviation when it occurs; I is the integral correction link, which is used to eliminate the static deviation of the system. The strength of its control effect is determined by the integral time constant; D is the differential correction link, which is used to reflect the rate of change of the deviation signal. The correction signal can be introduced in advance to prevent the deviation from becoming too large, which helps to reduce the adjustment time.

[0023] like Figure 2 As shown, the data layer includes a basic data acquisition module, a data preprocessing module, a balance determination module, a control data acquisition module, an influencing factor acquisition module, a comprehensive balance performance analysis module and a performance determination module; The basic data acquisition module is used to collect basic data of the electric wheelchair and transmit it to the data preprocessing module for preprocessing operations; the basic data includes but is not limited to the weight, real-time speed, force condition, tilt angle, motor power, output torque, acceleration and angular velocity of the electric wheelchair and other electric wheelchair operation status data; The data preprocessing module is used to receive data from the basic data acquisition module and the control data acquisition module, and perform preprocessing operations on the data to obtain data that can be directly used; the data preprocessing module includes a basic data preprocessing unit and a control data preprocessing unit, the basic data preprocessing unit is used to preprocess the basic data and then transmit it to the balance determination module; the control data preprocessing unit is used to preprocess the control data and then transmit it to the influence factor acquisition module; the preprocessing operations include but are not limited to cleaning, noise reduction and normalization of the data; The balance stability determination module is used to receive the data preprocessed by the data preprocessing module, obtain the balance stability value of the electric wheelchair based on the constructed balance prediction model, perform balance stability determination, and send corresponding control instructions to the control layer based on the determination result; The control data acquisition module is used to collect control data of the control layer and transmit it to the data preprocessing module for preprocessing; the control data includes actual control data, predetermined control data, control time, control energy consumption and other data reflecting the balance control situation; the actual control data is the actual control value of the electric wheelchair, that is, the actual value reached after the driving layer operates and runs the electric wheelchair according to the control instruction; the predetermined control data is the predetermined control value of the electric wheelchair, that is, the control value of the electric wheelchair by the control layer; the control value includes the control value of various basic data such as speed control value, motor power control value and output torque control value; the control time is the time required to complete the control of the electric wheelchair; the control energy consumption is the energy consumption generated when the electric wheelchair is controlled; The influencing factor acquisition module is used to acquire influencing factors that affect the balance performance of the electric wheelchair, wherein the influencing factors include control compensation factors and energy contribution factors, and transmit them to the comprehensive balance performance analysis module; The comprehensive balance performance analysis module is used to analyze the comprehensive balance performance of the electric wheelchair to obtain a comprehensive balance performance index; the comprehensive balance performance is the ability of the electric wheelchair to balance. The higher the comprehensive balance performance index, the better the ability of the electric wheelchair to balance, the lower the possibility of a loss of balance, and the higher the user safety factor; The performance determination module is used to determine the comprehensive balance performance index of the electric wheelchair, and send a warning instruction to the display layer according to the determination result, and transmit data to the display layer at the same time.

[0024] In this embodiment, it should be specifically explained that the equilibrium prediction model is constructed in the following manner: The basic data is used as analysis data, d groups of analysis data are collected in advance, d is an integer greater than 1, and the analysis data and the corresponding balance stability value are converted into a corresponding set of feature vectors; each group of analysis data is each group of basic data, and the basic data at the a-th moment is used as the a-th group of basic data. Each group of basic data includes all data types, and the real-time speed, tilt angle, motor power and output torque of the electric wheelchair are all data types; The equilibrium stability value corresponding to the analysis data can be calculated by the equilibrium stability value calculation formula. D groups of analysis data are collected. Under the conditions of each group of analysis data, the influence of different basic data on the equilibrium state is comprehensively analyzed; The equilibrium stability value calculation formula is expressed as: , where PW t is the equilibrium stability value at the tth moment, LJ wt is the stable torque at the tth moment, LJ ft is the overturning moment at the tth moment; the stabilizing moment is the moment that keeps the object balanced, and the overturning moment is the moment that causes the object to overturn; Each set of feature vectors is used as the input of the equilibrium prediction model. The equilibrium prediction model uses a set of predicted equilibrium stability values ​​corresponding to each set of analysis data as output, and uses the actual equilibrium stability values ​​corresponding to each set of analysis data as the prediction target. The actual equilibrium stability values ​​are the equilibrium stability values ​​corresponding to the analysis data collected in advance. The training target is to minimize the sum of the prediction errors of all analysis data. The formula of the prediction error is expressed as follows: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, θ p is the predicted equilibrium stability value corresponding to the pth group of analysis data, μ p The actual equilibrium stability value corresponding to the p-th group of analysis data is used to train the equilibrium prediction model until the sum of the prediction errors reaches convergence and the training is stopped; The balance prediction model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function is mapped into nonlinearity, allowing the network to learn more complex patterns and features.

[0025] In this embodiment, it should be specifically explained that the specific process of the balance stability determination module performing the balance stability determination is as follows: When the predicted balance stability value is greater than or equal to 0, the judgment result is balance, and no control command is sent to the control layer at this time, because when the predicted balance stability value is greater than 0, the stabilizing moment is greater than the overturning moment, indicating that the electric wheelchair will not overturn, that is, the electric wheelchair maintains balance and will not roll over; When the predicted balance stability value is less than 0, the judgment result is unbalanced. At this time, a control instruction is sent to the control layer. If the electric wheelchair is in motion, only the PID control instruction is sent. At this time, the electric wheelchair parameter data is intelligently controlled to increase the stabilizing torque to achieve the balance of the electric wheelchair. If the electric wheelchair is in a non-motion state, the PID control instruction and the main control instruction are sent, and the wheelchair entity is intelligently controlled at the same time, such as lowering the training wheels to enhance the stability of the electric wheelchair.

[0026] In this embodiment, it should be specifically explained that the calculation formula of the control compensation factor is expressed as: , where BK is the control compensation factor, Yk it The control value for the i-th type of basic data at the t-th time is preset, Sk it is the actual control value of the i-th type of basic data at the t-th moment, n is the total number of basic data categories, U is the total moment, i=1, 2, 3, …, n, t=1, 2, 3, …, U; The larger the control compensation factor is, the larger the value required for control compensation of the electric wheelchair is, indicating that the loss of the electric wheelchair in the control process is greater, that is, the worse the balance control ability of the electric wheelchair is, and the worse the comprehensive balance performance is; The calculation formula of the energy contribution factor is expressed as: , where NG is the energy contribution factor, nh j is the energy consumption generated by the jth control, TC j is the duration of the jth control, J is the total number of controls, j=1, 2, 3, ..., J; an uninterrupted control instruction received by the control layer is one control number. For example, if the control layer receives a control instruction at time t and does not receive a control instruction until time t+q, then the period from time t to time t+q is one control, and the duration of the control is q; The larger the energy contribution factor is, the greater the value of energy contribution required for the electric wheelchair is, which means that the electric wheelchair requires more energy consumption during balance control, that is, more energy is consumed for balance control of the electric wheelchair, the worse the energy utilization rate is, reflecting the worse overall balance performance.

[0027] In this embodiment, it should be specifically explained that the calculation formula of the comprehensive balance performance index in the comprehensive balance performance analysis module is: , where ZH is the comprehensive balance performance index, vit is the number of successful controls in the control times, and J is the total number of controls; the number of successful controls is the number of times the electric wheelchair does not tip over or roll over after the electric wheelchair is controlled.

[0028] In this embodiment, it should be specifically explained that the specific manner in which the performance determination module determines the comprehensive balance performance index of the electric wheelchair is: When the comprehensive balance performance index ZH satisfies ZH≥YU, it is determined that no warning is required, and no warning information is sent to the display layer; at this time, the comprehensive balance performance index reaches the preset safety threshold, that is, the balance performance of the electric wheelchair can meet the balance requirements, the comprehensive balance performance is good, and the electric wheelchair can be accurately and stably controlled to maintain balance during the balance control of the electric wheelchair, so there is no need to maintain the balance control system of the electric wheelchair and perform fault inspection and repair; When the comprehensive balance performance index ZH satisfies ZH<YU, it is determined that an early warning is required, and an early warning message is sent to the display layer; at this time, the comprehensive balance performance index does not reach the preset safety threshold, that is, the balance performance of the electric wheelchair cannot meet the balance requirements, and the comprehensive balance performance is poor. In the process of balancing the electric wheelchair, the control is not in place, which leads to the inability of the electric wheelchair to maintain balance. Therefore, maintenance and fault inspection and repair are required to ensure the normal use of the balance control system of the electric wheelchair, ensure user safety, and reduce risks; Among them, the YU is a safety threshold, satisfying YU≥95%. The specific value of YU can be set by technical personnel in this field according to the model of the electric wheelchair and the age and needs of the user. This implementation does not make any specific limitation on the specific value of the safety threshold.

[0029] In this embodiment, it should be specifically explained that the difference between this embodiment and the prior art lies in that this embodiment is equipped with a balance determination module, an influencing factor acquisition module and a comprehensive balance performance analysis module. The balance stability value of the electric wheelchair is obtained based on the constructed balance prediction model, and a balance stability determination is performed, so as to intelligently control the electric wheelchair, obtain the control compensation factor and energy contribution factor affecting the balance performance of the electric wheelchair, and then obtain the comprehensive balance performance index by combining the analysis; the trained neural network model is integrated into the calculation of intelligent control, which can give full play to the nonlinear and multimodal data modeling capabilities of the neural network and effectively capture complex data relationships; based on the parallel computing processing mechanism, the computing efficiency is improved, And through deep learning technology, intelligent control results are obtained, thereby improving the pertinence and effectiveness of intelligent balance control of electric wheelchairs; make full use of data and capture complex data relationships through deep learning technology to effectively improve the effectiveness and accuracy of intelligent balance control of electric wheelchairs; at the same time, by obtaining control compensation factors and energy contribution factors, a comprehensive balance performance index is obtained, and the balance control performance analysis is carried out in combination with key influencing factors affecting the balance performance of electric wheelchairs, thereby improving the accuracy of the analysis of the balance control performance of electric wheelchairs, enhancing the intelligence level of the management of the balance control performance of electric wheelchairs, being able to monitor the balance control performance of electric wheelchairs in a timely manner and take corresponding measures in a timely manner, thereby reducing the risk of user use.

[0030] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0031] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent energy-saving electric wheelchair balancing system, characterized in that: Including driver layer, control layer, data layer and display layer; The driving layer is used to drive the electric wheelchair to operate and run according to corresponding control instructions; The control layer is used to send corresponding control instructions to the drive layer and perform intelligent control on the electric wheelchair; The data layer is used to collect and analyze the data of the electric wheelchair, including: Basic data acquisition module: used to collect the basic data of the electric wheelchair and transmit it to the data preprocessing module for preprocessing operations; Data preprocessing module: used to receive data from the basic data acquisition module and the control data acquisition module, perform preprocessing operations on the data, and obtain data that can be directly used; Balance judgment module: used to receive the data preprocessed by the data preprocessing module, obtain the balance stability value of the electric wheelchair based on the constructed balance prediction model, and make a balance stability judgment, and send corresponding control instructions to the control layer based on the judgment result; Control data acquisition module: used to collect control data from the control layer and transmit it to the data preprocessing module for preprocessing; Influencing factor acquisition module: used to obtain the influencing factors that affect the balance performance of the electric wheelchair, the influencing factors include control compensation factors and energy contribution factors, and transmit them to the comprehensive balance performance analysis module; Comprehensive balance performance analysis module: used to analyze the comprehensive balance performance of the electric wheelchair and obtain the comprehensive balance performance index; Performance determination module: used to determine the comprehensive balance performance index of the electric wheelchair, and send a warning instruction to the display layer according to the determination result, and transmit the data to the display layer at the same time; The display layer is used to visualize the analysis results of the data layer and perform intelligent early warning.

2. The intelligent energy-saving electric wheelchair balancing system according to claim 1, characterized in that: The control layer includes a PID control module and a wheelchair main body control module; the PID control module is used to intelligently control the electric wheelchair parameter data using a PID controller; the wheelchair main body control module is used to intelligently control the electric wheelchair entity; The data preprocessing module includes a basic data preprocessing unit and a control data preprocessing unit, wherein the basic data preprocessing unit is used to preprocess the basic data and then transmit it to the balance determination module; The control data preprocessing unit is used to preprocess the control data and then transmit it to the influence factor acquisition module.

3. The intelligent energy-saving electric wheelchair balancing system according to claim 2, characterized in that: The basic data includes the weight, real-time speed, force, tilt angle, motor power, output torque, acceleration and angular velocity of the electric wheelchair; The control data includes actual control data, predetermined control data, control time and control energy consumption; the actual control data is the actual control value of the electric wheelchair, that is, the actual value reached after the driving layer operates and runs the electric wheelchair according to the control instructions; the predetermined control data is the predetermined control value of the electric wheelchair, that is, the control value of the electric wheelchair by the control layer; the control value includes speed control value, motor power control value and output torque control value; the control time is the time required to complete the control of the electric wheelchair; the control energy consumption is the energy consumption generated when controlling the electric wheelchair.

4. The intelligent energy-saving electric wheelchair balancing system according to claim 3, characterized in that: The PID controller is composed of a proportional unit, an integral unit and a differential unit. The PID control calculates the control deviation according to the given input value and the actual output value. The formula is expressed as: Among them, e(t) is the control deviation at time t, r(t) is the given input value at time t, and y(t) is the actual input value at time t; The control algorithm expression of PID controller is: , where u(t) is the control output, k p is the proportionality coefficient, T I and T D are the integral time constant and the differential time constant respectively.

5. The intelligent energy-saving electric wheelchair balancing system according to claim 4, characterized in that: The equilibrium prediction model is constructed as follows: Take the basic data as analysis data, collect d groups of analysis data in advance, d is an integer greater than 1, and convert the analysis data and the corresponding equilibrium stability value into a corresponding set of characteristic vectors; each group of analysis data is each group of basic data, and the basic data at the ath moment is taken as the ath group of basic data; The equilibrium stability value corresponding to the analysis data can be calculated by the equilibrium stability value calculation formula, d groups of analysis data are collected, and each group of feature vectors is used as the input of the equilibrium prediction model, the equilibrium prediction model uses a group of predicted equilibrium stability values ​​corresponding to each group of analysis data as output, and uses the actual equilibrium stability value corresponding to each group of analysis data as the prediction target, and the actual equilibrium stability value is the equilibrium stability value corresponding to the analysis data collected in advance; minimizing the sum of the prediction errors of all analysis data is used as the training target; The prediction error is expressed as: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, θ p is the predicted equilibrium stability value corresponding to the pth group of analysis data, μ p The actual equilibrium stability value corresponding to the pth group of analysis data is used to train the equilibrium prediction model until the sum of the prediction errors reaches convergence and the training is stopped.

6. The intelligent energy-saving electric wheelchair balancing system according to claim 5, characterized in that: The equilibrium stability value calculation formula is expressed as: , where PW t is the equilibrium stability value at the tth moment, LJ wt is the stable torque at the tth moment, LJ ft is the overturning moment at the tth moment; the stabilizing moment is the moment that keeps the object balanced, and the overturning moment is the moment that causes the object to overturn.

7. The intelligent energy-saving electric wheelchair balancing system according to claim 6, characterized in that: The specific process of the balance stability determination module performing balance stability determination is as follows: When the predicted balance stability value is greater than or equal to 0, the result is determined to be balanced, and no control command is sent to the control layer at this time; When the predicted balance stability value is less than 0, the judgment result is unbalanced. At this time, a control instruction is sent to the control layer. If the electric wheelchair is in motion, only the PID control instruction is sent. At this time, the electric wheelchair parameter data is intelligently controlled. If the electric wheelchair is in a non-motion state, the PID control instruction and the main control instruction are sent, and the wheelchair entity is intelligently controlled at the same time.

8. The intelligent energy-saving electric wheelchair balancing system according to claim 7, characterized in that: The calculation formula of the control compensation factor is expressed as: , where BK is the control compensation factor, Yk it The control value for the i-th type of basic data at the t-th time is preset, Sk it is the actual control value of the i-th category basic data at the t-th moment, n is the total number of basic data categories, U is the total moment, i=1, 2, 3, …, n, t=1, 2, 3, …, U; The calculation formula of the energy contribution factor is expressed as: , where NG is the energy contribution factor, nh j is the energy consumption generated by the jth control, TC j is the duration of the jth control, J is the total number of controls, j=1, 2, 3, …, J.

9. The intelligent energy-saving electric wheelchair balancing system according to claim 8, characterized in that: The calculation formula of the comprehensive balance performance index in the comprehensive balance performance analysis module is: , where ZH is the comprehensive balance performance index, vit is the number of successful controls in the control times, and J is the total control times.

10. The intelligent energy-saving electric wheelchair balancing system according to claim 9, characterized in that: The specific method in which the performance determination module determines the comprehensive balance performance index of the electric wheelchair is: When the comprehensive balance performance index ZH satisfies ZH≥YU, it is determined that no warning is needed and no warning information is sent to the display layer; When the comprehensive balance performance index ZH satisfies ZH<YU, it is determined that an early warning is required, and an early warning message is sent to the display layer; The YU is a safety threshold.

Images