Intelligent parameter adjustment method, adjustment device and intelligent electric power-assisted bicycle

Abstract

The embodiment of the present invention relates to the technical field of intelligent electric power-assisted vehicles, and specifically to an intelligent parameter adjustment method, an adjustment device, and an intelligent electric power-assisted vehicle. The present invention first obtains torque data, road condition data, angle data, and speed data, determines the pre-riding period of the intelligent electric power-assisted vehicle according to the angle data, and obtains user data in the pre-riding period identification; then determines the current riding mode of the intelligent electric power-assisted vehicle according to the torque data, road condition data, and speed data; obtains parameter influence values ​​through a parameter influence model; and finally adjusts the riding parameters of the current riding mode according to the parameter influence values. Thus, intelligent parameter adjustment of the intelligent electric power-assisted vehicle is realized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of data information processing, and specifically to an intelligent parameter adjustment method, an adjustment device and an intelligent electric assisted vehicle. Background Art

[0002] An intelligent electric power-assisted bicycle refers to a mechatronic vehicle that uses a battery as an auxiliary energy source and is installed on the basis of a bicycle, and then equipped with a motor, a motor management unit, a battery, a throttle, a brake handle and other operating components and a display instrument system. Electric power-assisted bicycles are becoming more and more intelligent with the development, and various personalized adjustment settings make power-assisted bicycles more intelligent. In "CN107351969B-A method for adjusting the adaptive power assistance of an electric power-assisted bicycle" (hereinafter referred to as Patent Document 1), the following steps are disclosed: A. Setting the target power of the hub motor's electrical output power; B. Obtaining the average power output of manpower to complete a cycle; C. Obtaining the target power; D. Controlling the working voltage of the hub motor. Adjusting the adaptive power assistance of the power-assisted bicycle. Patent Document 1 has the following defects:

[0003] (1) Patent Document 1 mechanically adjusts the electric assisted bicycle based on the power output of the hub motor, which is unable to take into account the rider's driving habits and road condition data. Its power assist adaptive adjustment is not intelligent enough and does not meet the rider's personalized riding needs.

[0004] (2) During the assisted riding process, there are multiple stages such as the assisted starting stage, the secondary starting stage, and the process control stage. Patent Document 1 only uses a complete cycle of riding power and uses a unified target power for riding. It is impossible to make targeted parameter adjustments corresponding to the assistance in each stage. In different stages of riding, it is easy to cause excessive or insufficient assistance, which makes the rider easily fatigued and may even cause safety accidents. Summary of the invention

[0005] In view of the above problems, the embodiments of the present invention provide an intelligent parameter adjustment method, an adjustment device and an intelligent electric power-assisted bicycle, which are used to solve the problem that the prior art mechanically adjusts the electric power-assisted bicycle based on the power output power of the hub motor, is unable to take into account the rider's driving habits and road condition data, and its power-assisted adaptive adjustment is not intelligent enough and does not meet the rider's personalized riding needs.

[0006] According to one aspect of an embodiment of the present invention, there is provided an intelligent parameter adjustment method, which is applied to an intelligent electric power-assisted vehicle, and the method comprises:

[0007] Obtain the torque data, road condition data, angle data, and speed data of the smart electric assisted bicycle in real time;

[0008] Determine the pre-riding period of the intelligent electric-assisted bicycle according to the angle data, and identify and obtain user data during the pre-riding period;

[0009] Determine the current riding mode of the smart electric-assisted bicycle according to the torque data, road condition data, and speed data;

[0010] Input torque data, user data, and road condition data into a parameter impact model to obtain parameter impact values;

[0011] The riding parameters of the current riding mode are adjusted according to the parameter influence values.

[0012] In some optional embodiments, the intelligent electric assisted vehicle is integrated with a gyroscope, a road surface roughness measuring instrument, a torque sensor, and a wheel rotation counter, and the real-time acquisition of road condition data, torque data, angle data, and speed data specifically includes:

[0013] The road condition data is obtained through the gyroscope and the road surface flatness measuring instrument; the torque data is obtained through the torque sensor; the angle data is obtained through the wheel revolution counter; and the speed data is obtained through the speed sensor.

[0014] In some optional embodiments, determining the pre-riding period of the intelligent electric-assisted vehicle according to the angle data specifically includes:

[0015] The angle data continuously increases from 0 after the smart electric-assisted vehicle is started. When the angle data is less than or equal to the preset starting angle, the smart electric-assisted vehicle is in a pre-riding cycle.

[0016] In some optional embodiments, identifying and acquiring user data in the pre-riding period specifically includes:

[0017] In the pre-riding period, the torque data is continuously obtained, a torque change curve is drawn, and the continuous torque data is averaged to obtain the average torque data;

[0018] The torque change curve and the average torque data are compared with each user data in the preset user riding characteristic table to obtain the user data.

[0019] In some optional embodiments, determining the current riding mode of the intelligent electric-assisted vehicle according to the torque data, the road condition data, and the speed data specifically includes:

[0020] When the road condition data is within the preset road condition range, the speed data is within the starting speed range and the torque data is greater than the maximum value of the preset torque range, the current riding mode is the starting mode;

[0021] When the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the starting speed range and the torque data is within the preset torque range, the current riding mode is the stable mode;

[0022] When the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the starting speed range, and the torque data change range exceeds the preset torque range, the current riding mode is the speed change mode;

[0023] When the road condition data is within the slope increasing range, the current riding mode is climbing mode;

[0024] When the road condition data is within the slope descending range, the current riding mode is downhill mode.

[0025] In some optional embodiments, the parameter influence model is a BP neural network model, and the step of inputting the torque data, the user data, and the road condition data into the parameter influence model to obtain the parameter influence value includes:

[0026] Input the torque data, user data, and road condition data into the three input units of the input layer of the parameter influence model respectively;

[0027] The hidden layer and output layer of the parameter impact model use Leaky ReLU activation function to calculate and output parameter impact values;

[0028] The BP neural network model is obtained by training through the following steps:

[0029] Setting the error function ,in is the target value of the parameter influence value, is the calculated value of the parameter influence value;

[0030] The user database of the smart electric assisted bicycle is recorded As training samples, is the torque data, For user data, Traffic data; is the difference between the initial parameter and the historical average parameter impact value;

[0031] Through the gradient descent algorithm, the weights from the hidden layer to the output layer and from the input layer to the hidden layer are updated to obtain the parameter influence model.

[0032] In some optional embodiments, adjusting the riding parameters of the current riding mode according to the parameter influence value specifically includes:

[0033] In the starting mode, the actual starting acceleration is obtained by calculating the product of the parameter influence value and the initial starting acceleration;

[0034] In the stable mode, the actual power assist ratio is obtained by calculating the product of the parameter influence value and the initial power assist ratio;

[0035] In the variable speed mode, the actual process acceleration is obtained by calculating the product of the parameter influence value and the initial process acceleration;

[0036] In the climbing mode, the actual climbing power ratio is obtained by calculating the product of the parameter influence value and the initial climbing power ratio;

[0037] In the downhill mode, the actual downhill assist ratio is obtained by calculating the product of the parameter influence value and the initial downhill assist ratio.

[0038] In some optional embodiments, after adjusting the riding parameters of the current riding mode according to the parameter influence value, further adjusting the riding parameters for a second time in the following manner includes:

[0039] Receive adjustment instructions through the control panel or lever of the smart electric bicycle, and adjust the riding parameters according to the adjustment instructions;

[0040] Or receive adjustment instructions through the terminal APP or background server, and adjust the riding parameters through the adjustment instructions;

[0041] Among them, the priority of receiving adjustment instructions through the control panel or lever of the smart electric assisted bicycle and the priority of receiving adjustment instructions through the terminal APP or background server are both higher than adjusting the actual riding parameters through the parameter influence model.

[0042] According to another aspect of an embodiment of the present invention, there is provided an intelligent parameter adjustment device, the device comprising:

[0043] The data acquisition module is used to acquire the torque data, road condition data, angle data, and speed data of the smart electric assisted bicycle in real time, and determine the pre-riding period of the smart electric assisted bicycle according to the angle data, and identify and acquire user data in the pre-riding period

[0044] A riding mode determination module, used to determine the current riding mode of the smart electric-assisted vehicle according to the torque data, road condition data, and speed data;

[0045] A parameter influence value calculation module is used to input torque data, user data, and road condition data into a parameter influence model to obtain a parameter influence value;

[0046] The parameter adjustment module is used to adjust the riding parameters of the current riding mode according to the parameter influence value.

[0047] According to another aspect of an embodiment of the present invention, there is provided an intelligent electric assisted vehicle, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;

[0048] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations such as the above-mentioned intelligent parameter adjustment method.

[0049] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention first obtains torque data, road condition data, angle data, and speed data, determines the pre-riding period of the intelligent electric-assisted bicycle according to the angle data, and identifies and obtains user data in the pre-riding period; then determines the current riding mode of the intelligent electric-assisted bicycle according to the torque data, road condition data, and speed data; obtains parameter influence values ​​through a parameter influence model; and finally adjusts the riding parameters of the current riding mode according to the parameter influence values. Thus, intelligent parameter adjustment of the intelligent electric-assisted bicycle is realized.

[0050] The present invention provides an "intelligent brain" for riding parameter adjustment through a parameter influence model. The parameter influence model can comprehensively consider the torque data, user data, and road condition data that affect power-assisted riding, thereby inputting the customized needs of the rider; at the same time, the parameter influence model has self-learning capabilities and can iterate its own weight parameters according to historical riding data. Through the continuous self-improvement of the parameter influence model, the output parameter influence value can be made more scientific and accurate, further improving the riding experience. At the same time, the scheme of the present invention can realize parameter adjustment of each state of the intelligent electric power-assisted vehicle, so that different parameters can be adjusted in each stage of power-assisted riding, thereby improving the comfort of power-assisted riding, which can not only effectively reduce the fatigue due to power-assisted riding, but also improve the overall riding safety.

[0051] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0053] Figure 1 A schematic diagram of the process of the intelligent parameter adjustment method provided by the present invention is shown;

[0054] Figure 2A schematic diagram of a process for identifying and acquiring user data in a pre-riding period provided by the present invention is shown;

[0055] Figure 3 A schematic diagram of a process of inputting torque data, user data, and road condition data into a parameter influence model to obtain parameter influence values ​​is shown in the present invention;

[0056] Figure 4 The structure diagram of the intelligent parameter adjustment device provided by the present invention is shown;

[0057] Figure 5 The schematic diagram of the structure of the intelligent electric power-assisted bicycle provided by the present invention is shown. DETAILED DESCRIPTION

[0058] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0059] Embodiment 1:

[0060] Figure 1 The flowchart of the first embodiment of the intelligent parameter adjustment method of the present invention is shown, which is applied to an intelligent electric power-assisted vehicle. The method includes:

[0061] 110, real-time acquisition of the torque data, road condition data, angle data, and speed data of the smart electric-assisted bicycle; in step 110, the smart electric-assisted bicycle is integrated with a gyroscope, a road surface roughness meter, a torque sensor, and a wheel rotation counter, and real-time acquisition of road condition data, torque data, angle data, and speed data is performed, specifically including: acquiring road condition data through a gyroscope and a road surface roughness meter, wherein the road condition data may be a riding slope value, and the road condition data may be obtained by detecting the angle between the smart electric-assisted bicycle and the horizontal road surface or detecting the height difference between the front wheel and the rear wheel through a gyroscope. The torque data is acquired through a torque sensor, which is disposed on the pedal or crank of the smart electric-assisted bicycle and is used to detect the magnitude of the force applied by the rider, and its unit is Nm. The angle data is acquired through a wheel rotation counter, and the angle data is actually the rotation angle of the wheel. When the wheel rotates one circle, its angle is 360°. The speed data can be obtained by calculating the speed sensor, or it can be calculated based on the angle data, wheel circumference, and timer. That is, within time t1, the angle data of the smart electric assisted bicycle is 360°, and the speed data is equal to the vehicle circumference divided by time t1.

[0062] 120, determine the pre-riding period of the smart electric-assisted vehicle according to the angle data, and identify and obtain user data during the pre-riding period; in step 120, determine the pre-riding period of the smart electric-assisted vehicle according to the angle data, specifically including: the angle data increases continuously from 0 after the smart electric-assisted vehicle is started, and when the angle data is less than or equal to the preset starting angle, the smart electric-assisted vehicle is in the pre-riding period. Identifying and obtaining user data during the pre-riding period specifically includes: in the pre-riding period, continuously obtain torque data, draw a torque change curve, and average the continuous torque data to obtain torque average data; traverse and compare the torque change curve and the torque average data with each user data in the preset user riding feature table to obtain user data.

[0063] Among them, user data may include any one or more of weight data, physical energy data allocation data, and user riding habits. The unit of weight data is kg. The physical energy data allocation data is the ratio of the user's current physical energy data to the total energy. The user's riding habits are the riding habit coefficient values. In this electric power-assisted bicycle, the standard riding habit coefficient value is 1. The parameter ratio can be set according to the user's habits. If the current user is used to riding faster and starting faster, the riding habit coefficient value can be set to 1.5; that is, the speed can be increased to 1.5 times the standard mode in the starting acceleration, process acceleration, and the power ratio of various riding modes. When the user is an elderly person or a child, the riding habit coefficient value can be set to 0.5 for corresponding parameter adjustment. Through this adaptive adjustment, the actual needs of various users can be met, and the intelligence and universality of electric power-assisted bicycles can be improved.

[0064] 130, determine the current riding mode of the smart electric assisted vehicle according to the torque data, the road condition data, and the speed data; in step 130, determine the current riding mode of the smart electric assisted vehicle according to the torque data and the road condition data, specifically including: when the road condition data is within the preset road condition range, the speed data is within the preset starting speed range and the torque data is greater than the maximum value of the preset torque range, then the current riding mode is the starting mode; when the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the preset starting speed range and the torque data is within the preset torque range, then the current riding mode is the stable mode; when the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the preset starting speed range and the torque data change range is outside the preset torque range, then the current riding mode is the variable speed mode; when the road condition data is within the slope rising range, the current riding mode is the climbing mode; when the road condition data is within the slope descending range, the current riding mode is the downhill mode.

[0065] 140, input the torque data, user data, and road condition data into the parameter influence model to obtain the parameter influence value; in step 140, the parameter influence model is a BP neural network model, and the torque data, user data, and road condition data are input into the parameter influence model to obtain the parameter influence value, including: inputting the torque data, user data, and road condition data into three input units of the input layer of the parameter influence model respectively; the hidden layer and the output layer of the parameter influence model use the Leaky ReLU activation function to calculate and output the parameter influence value.

[0066] The parameter impact value can be a calculated ratio, which is used to adjust the parameters of different riding modes under different torque data, user data, and road condition data. When the riding conditions are good and the user intends to ride faster, the parameters of different modes can be adjusted through the parameter impact value to increase the speed or speed change to meet the user's needs, and vice versa.

[0067] 150, adjusting the riding parameters of the current riding mode according to the parameter influence value. In step 150, the riding parameters of the current riding mode are adjusted according to the parameter influence value, specifically including: in the starting mode, the actual starting acceleration is obtained by calculating the product of the parameter influence value and the initial starting acceleration; in the stable mode, the actual power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial power-assistance ratio; in the speed change mode, the actual process acceleration is obtained by calculating the product of the parameter influence value and the initial process acceleration; in the climbing mode, the actual climbing power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial climbing power-assistance ratio; in the downhill mode, the actual downhill power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial downhill power-assistance ratio.

[0068] Among them, the riding parameters can be initial starting acceleration, initial power ratio, initial process acceleration, initial climbing power ratio, and initial downhill power ratio. In this step, the initial starting acceleration, initial power ratio, initial process acceleration, initial climbing power ratio, and initial downhill power ratio are all calculated according to the standard power parameters of the smart electric power-assisted bicycle or the average of historical users when the power-assisted bicycle leaves the factory, and written into the on-board memory of each smart electric power-assisted bicycle. When calculating the riding parameters, the initial starting acceleration, initial power ratio, initial process acceleration, initial climbing power ratio, and initial downhill power ratio of the on-board memory can be read through the on-board controller, and the actual starting acceleration, actual power ratio, actual process acceleration, actual climbing power ratio, and actual downhill power ratio can be used to adjust the current riding mode through the above riding parameters to adapt to different road conditions of different users, thereby improving the experience of power-assisted riding.

[0069] The present invention first obtains torque data, road condition data, and angle data, determines the pre-riding period of the intelligent electric power-assisted vehicle according to the angle data, and identifies and obtains user data during the pre-riding period; then determines the current riding mode of the intelligent electric power-assisted vehicle according to the torque data, road condition data, and angle data; obtains parameter influence values ​​through a parameter influence model; and finally adjusts the riding parameters of the current riding mode according to the parameter influence values. Thus, intelligent parameter adjustment of the intelligent electric power-assisted vehicle is realized.

[0070] The present invention provides an "intelligent brain" for riding parameter adjustment through a parameter influence model. The parameter influence model can comprehensively consider the torque data, user data, and road condition data that affect power-assisted riding, thereby inputting the customized needs of the rider; at the same time, the parameter influence model has self-learning capabilities and can iterate its own weight parameters according to historical riding data. Through the continuous self-improvement of the parameter influence model, the output parameter influence value can be made more scientific and accurate, further improving the riding experience. At the same time, the scheme of the present invention can realize parameter adjustment of each state of the intelligent electric power-assisted vehicle, so that different parameters can be adjusted in each stage of power-assisted riding, thereby improving the comfort of power-assisted riding, which can not only effectively reduce the fatigue due to power-assisted riding, but also improve the overall riding safety.

[0071] In some optional embodiments, the smart electric power-assisted vehicle is integrated with a gyroscope, a road surface roughness meter, a torque sensor, and a wheel rotation counter to obtain road condition data, torque data, angle data, and speed data in real time, specifically including: obtaining road condition data through a gyroscope and a road surface roughness meter; obtaining torque data through a torque sensor; and obtaining angle data through a wheel rotation counter. In this embodiment, the road condition data can be any one or more of riding slope data, road surface roughness data, and riding congestion ahead. The angle data is the rotation angle of the wheel. For example, according to the user portrait setting in the user data, when the pedal is rotated to 180°-360°, the smart electric power-assisted vehicle recognizes the start intention and immediately starts the power-assisted mode. The start angle can be detected by detecting the vehicle's travel distance based on the speed detector or obtained through a vehicle lap detector or a wheel rotation counter. The torque sensor can be set on two different coupling shafts of the smart electric power-assisted vehicle to detect the magnitude of the force generated by the rider's riding pedal. The speed data can be obtained by calculating the speed sensor, or it can be calculated based on the angle data, wheel circumference, and timer. That is, within time t1, the angle data of the smart electric assisted bicycle is 360°, and the speed data is equal to the vehicle circumference divided by time t1.

[0072] In some optional embodiments, the pre-riding cycle of the smart electric-assisted vehicle is determined based on the angle data, specifically including: the angle data increases continuously from 0 after the smart electric-assisted vehicle is started, and when the angle data is less than or equal to the preset starting angle, the smart electric-assisted vehicle is in the pre-riding cycle. In this embodiment, when the smart electric-assisted vehicle is started, the angle speed increases from 0, and the pre-riding cycle is defined according to the number of rotations, such as the pedal rotation to 180°-360° is the pre-riding cycle. The specific data can be set according to the user's preset data.

[0073] In some optional embodiments, see Figure 2 , in the pre-riding period, identify and obtain user data, including:

[0074] 210, in the pre-riding period, continuously obtain torque data, draw a torque change curve, and average the continuous torque data to obtain torque average data; in step 210, in the pre-riding period, obtain multiple torque data through the torque sensor, and establish a coordinate system based on the torque data, the horizontal axis is time or angle data, and the vertical axis is the torque measurement value; connect the coordinate points of adjacent torque data to form a torque change curve. And calculate the average value of all torque data in the pre-riding period to obtain the torque average data.

[0075] 220, compare the torque change curve and the average torque data with each user data in the preset user riding feature table to obtain user data. In step 220, multiple user data are preset in the smart electric power-assisted vehicle, and the user data includes the torque change trend range value and the average torque size range value in the pre-riding cycle, i.e., the startup phase. By querying and judging whether the torque change curve and the average torque data fall into the torque change trend range value and the average torque size range value of any user at the same time, the target user of the current riding can be queried, and the user data can be obtained according to the pre-stored information of the target user. In a specific example, the torque data of user 1 in the pre-riding cycle is 70Nm, 80Nm, 70Nm, 80Nm, the average torque data is 75Nm, and the torque change curve is characterized by fluctuations along the average value. By querying the user database of the smart electric power-assisted vehicle, it can be judged that the target user with the average torque data of 75Nm and the torque change curve characteristic of fluctuations along the average value is found, thereby obtaining the target user data.

[0076] In addition, in order to more accurately query the target user, a pressure sensor can be set at the seat cushion position to obtain the weight of the current user, thereby assisting in determining the target user and improving the accuracy of the determination.

[0077] In some optional embodiments, determining the current riding mode of the smart electric-assisted vehicle according to the torque data, the road condition data, and the speed data specifically includes:

[0078] When the road condition data is within the preset road condition range, the speed data is within the preset starting speed range, and the torque data is greater than the maximum value of the preset torque range, the current riding mode is the starting mode;

[0079] When the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the preset starting speed range and the torque data is within the preset torque range, the current riding mode is the stable mode;

[0080] When the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the preset starting speed range, and the torque data change range is outside the preset torque range, the current riding mode is the speed change mode;

[0081] When the road condition data is within the slope increasing range, the current riding mode is climbing mode;

[0082] When the road condition data is within the slope descending range, the current riding mode is downhill mode.

[0083] In this embodiment, the speed data is the current riding speed value of the smart electric power-assisted vehicle, and the standard setting value of the preset starting speed interval is 0km / h-15km / h. The preset starting speed interval can be set according to user data or user portrait. The road condition data can be a riding slope value. When the riding slope value is between -5°-5°, the riding slope value can be regarded as being within the preset road condition range value. When the riding slope value is greater than 5°, it is a climbing mode, and less than -5° is a downhill section. The angular preset torque range value can be 5 Nm-10 Nm to avoid small sudden changes in speed and change the riding mode. Under different riding modes, its motor working mode and auxiliary riding mode are different. When the speed data is in the preset starting speed interval and the torque data is increasing, it is considered that the current smart electric power-assisted vehicle is in the starting mode; when the speed data is greater than the preset starting speed interval and the torque data fluctuates in the preset range value, it is considered to be in the stable mode, and when the speed data is greater than the torque data change, and the change amplitude exceeds the preset torque range value, it is considered to be in the speed change mode.

[0084] In some optional embodiments, the parameter influence model is a BP neural network model, such as Figure 3 As shown, the torque data, user data, and road condition data are input into the parameter influence model to obtain the parameter influence value, which specifically includes:

[0085] 310, the torque data, user data, and road condition data are respectively input into three input units of the input layer of the parameter influence model; in step 310, three input units are set in the input layer of the parameter influence model, and after the torque data, user data, and road condition data are obtained, they are respectively input into the three input units.

[0086] 320, the hidden layer and output layer of the parameter influence model use the Leaky ReLU activation function to calculate and output the parameter influence value; in step 320, the hidden layer uses the Leaky ReLU activation function, and performs weighted calculations on the torque data, user data, and road condition data in the input layer through the activation function to obtain intermediate calculation values. After the intermediate calculation value of the hidden layer is output to the output layer, the Leaky ReLU activation function of the output layer is used to perform cumulative weighted calculations to obtain the parameter influence value.

[0087] Among them, the BP neural network model is trained and obtained through the following steps:

[0088] Setting the error function ,in is the target value of the parameter influence value, is the calculated value of the parameter influence value;

[0089] The user database of the smart electric assisted bicycle is recorded As training samples, is the torque data, For user data, Traffic data; is the difference between the initial parameter and the historical average parameter impact value;

[0090] Through the gradient descent algorithm, the weights from the hidden layer to the output layer and from the input layer to the hidden layer are updated to obtain the parameter influence model.

[0091] In this embodiment, the patent adopts a BP neural network model, which includes 3 layers of neural networks.

[0092] The first layer is the input layer, which has 3 units, namely torque data, user data, and road condition data. The hidden layer has 7 units, and the output layer is the parameter influence value.

[0093] Hidden layer units The calculation expression is:

[0094]

[0095] in , is the hidden layer unit; , , is the input layer unit; , , is the weight from the input layer to the hidden layer; the threshold , The weight of , .

[0096] Hidden layer units Output :

[0097]

[0098] in, , , is the output after the hidden layer is activated. The activation function of the hidden layer uses the LeakyReLU function, where the coefficient .

[0099] Hidden layer output To the output layer unit The calculation expression is:

[0100]

[0101] in , , is the weight from the hidden layer to the output layer, the threshold , The weight of .

[0102] Output layer units Output :

[0103]

[0104] in, is the output after the output layer is activated, that is, the parameter influence value. The activation function of the hidden layer uses the LeakyReLU function, where the coefficient The output of both the hidden layer and the output layer uses the Leaky ReLU activation function.

[0105] In this embodiment, the torque data is the data unit Nm collected by the sensor in real time or periodically; the user data can be the weight data unit kg or the user's current physical data to total physical data ratio or the user's riding habit coefficient value; the road condition data can be the riding slope data unit in angle units. For torque data , user data , traffic data Calculate and according to the output of the hidden layer , through the output layer unit Output to hidden layer Perform weighted statistical calculations and finally obtain is the output after the output layer is activated, i.e., the parameter influence value. The parameter influence model is a BP neural network model. During model training, each parameter of the model is calculated and iterated through historical data.

[0106] The present invention provides an "intelligent brain" for riding parameter adjustment through a parameter influence model. The parameter influence model can comprehensively consider the torque data, user data, and road condition data that affect power-assisted riding, thereby inputting the customized needs of the rider; at the same time, the parameter influence model has self-learning capabilities and can iterate its own weight parameters according to historical riding data. Through the continuous self-improvement of the parameter influence model, the output parameter influence value can be made more scientific and accurate, further improving the riding experience. At the same time, the scheme of the present invention can realize parameter adjustment of each state of the intelligent electric power-assisted vehicle, so that different parameters can be adjusted in each stage of power-assisted riding, thereby improving the comfort of power-assisted riding, which can not only effectively reduce the fatigue due to power-assisted riding, but also improve the overall riding safety.

[0107] In one implementation of the above embodiment, the weight parameters of the hidden layer and the output layer are obtained by reverse deduction from the known input and output results. The BP neural network model is obtained by training through the following steps: setting the error function ,in is the target value of the parameter influence value, is the calculated value of the parameter influence value; the user database of the smart electric assisted vehicle records As training samples, is the torque data, For user data, Traffic data; is the difference between the initial parameter and the historical average parameter influence value. The weights from the hidden layer to the output layer and from the input layer to the hidden layer are updated through the gradient descent algorithm to obtain the BP neural network model.

[0108] The weights from the hidden layer to the output layer and from the input layer to the hidden layer are updated using the gradient descent method:

[0109]

[0110]

[0111] in, is the learning rate, which is 0.5 here.

[0112] In this embodiment, the BP neural network model is trained before delivery to complete the initial parameters of the model. After delivery, the parameters can be continuously updated according to user needs to achieve continuous optimization of the BP neural network model and improve the applicability of the model.

[0113] In some optional embodiments, adjusting the riding parameters of the current riding mode according to the parameter influence value specifically includes:

[0114] In the starting mode, the actual starting acceleration is obtained by calculating the product of the parameter influence value and the initial starting acceleration; the starting mode is to accelerate from a speed of 0 to a stable speed mode, in which the motor is mainly driven; after the torque sensor is triggered, the motor works, and the drive output set by the motor is used to achieve a stable speed through the initial starting acceleration. In the starting mode, the initial starting acceleration of the start can be adjusted according to the characteristics and conditions such as torque data, user data, and road condition data to achieve the best starting effect. Specifically, the parameter influence value is inferred by the parameter influence model based on the torque data, user data, and road condition data, and the initial starting acceleration is weighted calculated by the parameter influence value to obtain a better actual starting acceleration. In an example, when the user wants to accelerate, the torque parameter increases by 1 times, and the parameter influence value is obtained by calculation as 1.2, and the initial starting acceleration is 5km / h². By calculating 5km / h²*1.2=6 km / h², 6 km / h² is the actual starting acceleration.

[0115] In the stable mode, the actual power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial power-assistance ratio; in the stable mode, the human drive and motor drive of the smart electric power-assist vehicle are in a certain proportion. After real-time monitoring of torque data, user data and road condition data, the stable mode can be adjusted according to the real-time situation to achieve the best riding effect. Specifically, the parameter influence value is inferred through the parameter influence model based on the torque data, user data and road condition data, and the initial power-assistance ratio is weightedly calculated by the parameter influence value to obtain a better actual power-assistance ratio. For example, the parameter influence value is calculated to be 2, the initial power-assistance ratio is 1 / 2, and 1 / 2*2=1, where 1 is the actual power-assistance ratio.

[0116] In the speed change mode, the actual process acceleration is obtained by calculating the product of the parameter influence value and the initial process acceleration; in the speed change mode, the smart electric assisted vehicle changes from one speed to another. In this mode, the motor is mainly driven during the speed change process; after the torque sensor is triggered, the motor works, and the drive output set by the motor is used to achieve a stable speed through the initial process acceleration. In the speed change mode, the initial process acceleration can be adjusted according to the characteristics and conditions such as torque data, user data, and road condition data to achieve the best starting effect. Specifically, the parameter influence value is inferred through the parameter influence model based on the torque data, user data, and road condition data, and the initial process acceleration is weighted calculated through the parameter influence value to obtain a better actual process acceleration. For example, the parameter influence value is calculated to be 1.2, the initial starting acceleration is -2km / h², and -2km / h²*1.2=-2.4 km / h², -2.4 km / h² is the actual starting acceleration, indicating that the current speed is gradually slowing down at an acceleration of 2.4 km / h².

[0117] In the climbing mode, the actual climbing power ratio is obtained by calculating the product of the parameter influence value and the initial climbing power ratio; in the climbing mode, the human drive and motor drive of the smart electric power-assisted vehicle are in a certain proportion. After real-time monitoring of torque data, user data and road condition data, the climbing mode can be adjusted according to the real-time situation to achieve the best riding effect. Specifically, based on the torque data, user data, and road condition data, the parameter influence value is inferred through the parameter influence model, and the initial climbing power ratio is weighted calculated through the parameter influence value to obtain a better actual power ratio.

[0118] In downhill mode, the actual downhill power-assist ratio is obtained by calculating the product of the parameter influence value and the initial downhill power-assist ratio. In downhill mode, the human drive and motor drive of the smart electric power-assist vehicle are in a certain proportion. After real-time monitoring of torque data, user data and road condition data, the downhill mode can be adjusted according to the real-time situation to achieve the best riding effect. Specifically, based on the torque data, user data and road condition data, the parameter influence value is inferred through the parameter influence model, and the initial downhill power-assist ratio is weighted calculated through the parameter influence value to obtain a better actual power-assist ratio.

[0119] In the present invention, by controlling the acceleration in the starting mode and the speed change mode, the set speed can be reached faster or slower to adapt to different users and road conditions and improve the riding experience. The power ratio can be adjusted in the stable mode, climbing mode, and downhill mode, and adaptive adjustment can be made according to the actual riding environment and user needs to improve the safety and convenience of riding and further improve the riding experience.

[0120] In some optional embodiments, after adjusting the riding parameters of the current riding mode according to the parameter influence value, the riding parameters are also adjusted for the second time in the following manners: receiving the adjustment instruction through the control panel or lever of the smart electric power-assisted vehicle, and adjusting the riding parameters through the adjustment instruction; or receiving the adjustment instruction through the terminal APP or the background server, and adjusting the riding parameters through the adjustment instruction; wherein, the priority of receiving the adjustment instruction through the control panel or lever of the smart electric power-assisted vehicle and the priority of receiving the adjustment instruction through the terminal APP or the background server are higher than adjusting the actual riding parameters through the parameter influence model. The adjustment is adjusted to manual mode through the control panel or lever of the smart electric power-assisted vehicle, the adjustment is adjusted to semi-intelligent mode through the terminal APP or the background server, and the actual riding parameters are adjusted to intelligent mode through the parameter influence model. The present invention can realize personalized adjustment of power assistance through three modes. At the same time, the present invention also sets: in the current riding mode, the priority of manual mode and semi-intelligent mode is higher than the priority of intelligent mode; so in a riding mode cycle, the manual mode or semi-intelligent mode is executed, and the intelligent mode adjustment is no longer performed. After the current riding mode is switched to the field riding mode, the intelligent mode will be automatically executed and the parameters of the current riding mode will be corrected.

[0121] In some optional embodiments, in the current riding mode, any one or more of the tertiary adjustment parameters of the speed limit percentage and the maximum power are obtained according to the user data, and the actual riding parameters are adjusted in real time according to the tertiary adjustment parameters. In this embodiment, the speed limit percentage is the maximum speed set according to the user portrait; for example, the maximum speed can be set for adults, and the maximum speed can be set for the elderly and children at 60%. The maximum power is to limit the output power of the smart electric power-assisted vehicle, and different output powers can be set according to the user portrait. In this embodiment, through the secondary adjustment parameters, the working indicators of the smart electric power-assisted vehicle can be controlled at a fixed value to ensure the driving safety of the smart electric power-assisted vehicle.

[0122] Embodiment 2:

[0123] Figure 4 An embodiment of an intelligent parameter adjustment device of the present invention is shown, and the device specifically comprises:

[0124] The data acquisition module 410 is used to execute step 110 and step 120 in Example 1. The data acquisition module 410 specifically also includes: real-time acquisition of road condition data, torque data, angle data, and speed data, specifically including: acquiring road condition data through a gyroscope and a road surface roughness meter; acquiring torque data through a torque sensor; and acquiring angle data through a wheel rotation counter. Determining the pre-riding period of the smart electric-assisted vehicle based on the angle data specifically includes: the angle data continuously increases from 0 after the smart electric-assisted vehicle is started, and when the angle data is less than or equal to the preset starting angle, the smart electric-assisted vehicle is in the pre-riding period. Identifying and acquiring user data in the pre-riding period specifically includes: in the pre-riding period, continuously acquiring torque data, drawing a torque change curve, and averaging the continuous torque data to obtain torque average data; traversing and comparing the torque change curve and the torque average data with each user data in the preset user riding feature table to acquire user data.

[0125] The riding mode judgment module 420 is used to execute step 130 in Example 1; the riding mode judgment module 420 is specifically used for: when the road condition data is within the preset road condition range value, the speed data is equal to the preset speed interval and the torque data is greater than the preset torque range value, the current riding mode is the starting mode; when the road condition data is within the preset road condition range value, the speed data is greater than the preset speed interval and the torque data is within the preset torque range value, the current riding mode is the stable mode; when the road condition data is within the preset road condition range value, the speed data is greater than the preset speed interval and the torque data change amplitude exceeds the preset torque range value, the current riding mode is the speed change mode; when the road condition data is within the slope rising range, the current riding mode is the climbing mode; when the road condition data is within the slope descending range, the current riding mode is the downhill mode

[0126] The parameter influence value calculation module 430 is used to execute step 140 in Example 1; the parameter influence value calculation module 430 is specifically used to: input the torque data, user data, and road condition data into the three input units of the input layer of the parameter influence model respectively; the hidden layer and output layer of the parameter influence model use the Leaky ReLU activation function to calculate and output the parameter influence value.

[0127] The parameter adjustment module 440 is used to execute step 150 in embodiment 1. The parameter adjustment module 440 is specifically used to obtain the actual starting acceleration by calculating the product of the parameter influence value and the initial starting acceleration in the starting mode; obtain the actual power-assistance ratio by calculating the product of the parameter influence value and the initial power-assistance ratio in the stable mode; obtain the actual process acceleration by calculating the product of the parameter influence value and the initial process acceleration in the speed change mode; obtain the actual climbing power-assistance ratio by calculating the product of the parameter influence value and the initial climbing power-assistance ratio in the climbing mode; and obtain the actual downhill power-assistance ratio by calculating the product of the parameter influence value and the initial downhill power-assistance ratio in the downhill mode.

[0128] The present invention provides an intelligent brain for riding parameter adjustment through a parameter influence model. The parameter influence model can comprehensively consider the torque data, user data, and road condition data that affect power-assisted riding, thereby inputting the customized needs of the rider; at the same time, the parameter influence model has self-learning ability and can iterate its own weight parameters according to historical riding data. Through the continuous self-improvement of the parameter influence model, the output parameter influence value can be made more scientific and accurate, further improving the riding experience. At the same time, the scheme of the present invention can realize parameter adjustment of each state of the intelligent electric power-assisted vehicle, so that different parameters can be adjusted in each stage of power-assisted riding, thereby improving the comfort of power-assisted riding, which can not only effectively reduce the fatigue due to power-assisted riding, but also improve the overall riding safety.

[0129] Embodiment 3:

[0130] Figure 5 The schematic diagram of the structure of an embodiment of the intelligent electric power-assisted vehicle of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the intelligent electric power-assisted vehicle.

[0131] like Figure 5 As shown, the intelligent electric assisted vehicle may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530, and a communication bus 540.

[0132] The processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The communication interface 520 is used to communicate with other devices such as a client or other server network elements. The processor 510 is used to execute the program 550, which can specifically execute the relevant steps in the above-mentioned embodiment of the intelligent parameter adjustment method.

[0133] Specifically, the program 550 may include program code including computer-executable instructions.

[0134] The processor 510 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the smart electric assisted vehicle may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0135] The memory 530 is used to store the program 550. The memory 530 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0136] Program 550 can be specifically called by processor 510 to enable the smart electric assisted vehicle to perform the following operations:

[0137] 110, real-time acquisition of torque data, road condition data, and angle data of the smart electric assisted bicycle;

[0138] 120, determining a pre-riding period of the intelligent electric-assisted bicycle according to the angle data, and identifying and acquiring user data during the pre-riding period;

[0139] 130, determining a current riding mode of the smart electric-assisted bicycle according to the torque data, the road condition data, and the angle data;

[0140] 140, inputting the torque data, user data, and road condition data into a parameter influence model to obtain a parameter influence value;

[0141] 150, adjusting the riding parameters of the current riding mode according to the parameter influence value.

[0142] The present invention first obtains torque data, road condition data, and angle data, determines the pre-riding period of the intelligent electric power-assisted vehicle according to the angle data, and identifies and obtains user data during the pre-riding period; then determines the current riding mode of the intelligent electric power-assisted vehicle according to the torque data, road condition data, and angle data; obtains the parameter influence value through the parameter influence model; and finally adjusts the riding parameters of the current riding mode according to the parameter influence value. Thus, intelligent parameter adjustment of the intelligent electric power-assisted vehicle is realized.

[0143] The present invention provides an "intelligent brain" for riding parameter adjustment through a parameter influence model. The parameter influence model can comprehensively consider the torque data, user data, and road condition data that affect power-assisted riding, thereby inputting the customized needs of the rider; at the same time, the parameter influence model has self-learning capabilities and can iterate its own weight parameters according to historical riding data. Through the continuous self-improvement of the parameter influence model, the output parameter influence value can be made more scientific and accurate, further improving the riding experience. At the same time, the scheme of the present invention can realize parameter adjustment of each state of the intelligent electric power-assisted vehicle, so that different parameters can be adjusted in each stage of power-assisted riding, thereby improving the comfort of power-assisted riding, which can not only effectively reduce the fatigue due to power-assisted riding, but also improve the overall riding safety.

[0144] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system or other device. In addition, the embodiments of the present invention are not directed to any particular programming language.

[0145] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. Similarly, in order to simplify the present invention and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself is a separate embodiment of the present invention.

[0146] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0147] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim that lists a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. An intelligent parameter adjustment method, characterized in that: Applied to an intelligent electric power-assisted vehicle, the method comprises: Obtain the torque data, road condition data, angle data, and speed data of the smart electric assisted bicycle in real time; Determine the pre-riding period of the intelligent electric-assisted bicycle according to the angle data, and identify and obtain user data during the pre-riding period; Determine the current riding mode of the smart electric-assisted bicycle according to the torque data, road condition data, and speed data; Input torque data, user data, and road condition data into a parameter impact model to obtain parameter impact values; adjusting the riding parameters of the current riding mode according to the parameter influence value; Among them, the riding parameters of the current riding mode are adjusted according to the parameter influence value, specifically including: in the starting mode, the actual starting acceleration is obtained by calculating the product of the parameter influence value and the initial starting acceleration; in the stable mode, the actual power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial power-assistance ratio; in the speed change mode, the actual process acceleration is obtained by calculating the product of the parameter influence value and the initial process acceleration; in the climbing mode, the actual climbing power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial climbing power-assistance ratio; in the downhill mode, the actual downhill power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial downhill power-assistance ratio.

2. The intelligent parameter adjustment method according to claim 1, characterized in that: The intelligent electric assisted vehicle is integrated with a gyroscope, a road surface roughness measuring instrument, a torque sensor, and a wheel rotation counter. The real-time acquisition of road condition data, torque data, angle data, and speed data specifically includes: The road condition data is obtained through the gyroscope and the road surface flatness measuring instrument; the torque data is obtained through the torque sensor; the angle data is obtained through the wheel revolution counter; and the speed data is obtained through the speed sensor.

3. The intelligent parameter adjustment method according to claim 2, characterized in that: Determining the pre-riding period of the intelligent electric-assisted vehicle according to the angle data specifically includes: The angle data continuously increases from 0 after the smart electric-assisted vehicle is started. When the angle data is less than or equal to the preset starting angle, the smart electric-assisted vehicle is in a pre-riding cycle.

4. The intelligent parameter adjustment method according to claim 3, characterized in that: Identify and obtain user data during the pre-riding period, including: In the pre-riding period, the torque data is continuously obtained, a torque change curve is drawn, and the continuous torque data is averaged to obtain the average torque data; The torque change curve and the average torque data are compared with each user data in the preset user riding characteristic table to obtain the user data.

5. The intelligent parameter adjustment method according to claim 1, characterized in that: Determining the current riding mode of the smart electric-assisted vehicle according to the torque data, the road condition data, and the speed data specifically includes: When the road condition data is within the preset road condition range, the speed data is within the preset starting speed range, and the torque data is greater than the maximum value of the preset torque range, the current riding mode is the starting mode; When the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the preset starting speed range and the torque data is within the preset torque range, the current riding mode is the stable mode; When the road condition data is within the preset road condition range, the speed data is greater than the maximum value of the preset starting speed range, and the torque data change range is outside the preset torque range, the current riding mode is the speed change mode; When the road condition data is within the slope increasing range, the current riding mode is climbing mode; When the road condition data is within the slope descending range, the current riding mode is downhill mode.

6. The intelligent parameter adjustment method according to claim 5, characterized in that: The parameter influence model is a BP neural network model. The moment data, user data, and road condition data are input into the parameter influence model to obtain the parameter influence value, including: Input the torque data, user data, and road condition data into the three input units of the input layer of the parameter influence model respectively; The hidden layer and output layer of the parameter impact model use Leaky ReLU activation function to calculate and output parameter impact values; The BP neural network model is obtained by training through the following steps: Setting the error function ,in is the target value of the parameter influence value, is the calculated value of the parameter influence value; The user database of the smart electric assisted bicycle is recorded As training samples, is the torque data, For user data, For road condition data; is the difference between the initial parameter and the historical average parameter impact value, where the target value of the parameter impact value is equal to the difference between the initial parameter and the historical average parameter impact value; Through the gradient descent algorithm, the weights from the hidden layer to the output layer and from the input layer to the hidden layer are updated to obtain the parameter influence model.

7. The intelligent parameter adjustment method according to claim 1, characterized in that: After adjusting the riding parameters of the current riding mode according to the parameter influence value, further adjusting the riding parameters for a second time in the following manner includes: Receive adjustment instructions through the control panel or lever of the smart electric bicycle, and adjust the riding parameters through the adjustment instructions; Or receive adjustment instructions through the terminal APP or background server, and adjust the riding parameters according to the adjustment instructions; Among them, the priority of receiving adjustment instructions through the control panel or lever of the smart electric assisted bicycle and the priority of receiving adjustment instructions through the terminal APP or background server are both higher than adjusting the actual riding parameters through the parameter influence model.

8. An intelligent parameter adjustment device, characterized in that: The device comprises: The data acquisition module is used to acquire the torque data, road condition data, angle data, and speed data of the smart electric assisted bicycle in real time, and determine the pre-riding period of the smart electric assisted bicycle according to the angle data, and identify and acquire user data in the pre-riding period A riding mode determination module, used to determine the current riding mode of the smart electric-assisted vehicle according to the torque data, road condition data, and speed data; A parameter influence value calculation module is used to input torque data, user data, and road condition data into a parameter influence model to obtain a parameter influence value; A parameter adjustment module is used to adjust the riding parameters of the current riding mode according to the parameter influence value, wherein the riding parameters of the current riding mode are adjusted according to the parameter influence value, specifically including: in the starting mode, the actual starting acceleration is obtained by calculating the product of the parameter influence value and the initial starting acceleration; in the stable mode, the actual power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial power-assistance ratio; in the speed change mode, the actual process acceleration is obtained by calculating the product of the parameter influence value and the initial process acceleration; in the climbing mode, the actual climbing power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial climbing power-assistance ratio; in the downhill mode, the actual downhill power-assistance ratio is obtained by calculating the product of the parameter influence value and the initial downhill power-assistance ratio.

9. An intelligent electric power-assisted vehicle, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the intelligent parameter adjustment method as described in any one of claims 1-7.

Images