Riding power estimation method and system

Abstract

The invention discloses a riding power estimation method and system, and the method comprises the steps: obtaining a wind direction and a riding course representing the windward riding or headwind riding of a user based on the wheel diameter of a bicycle, the pedaling frequency, the wind pressure representing the wind power, the riding speed and the gradient; obtaining kinetic energy increment and potential energy increment at the current moment based on the physiological information of the sports user, the weight of the bicycle, the riding speed and the gradient; based on a wind power response model between the pre-established input data and the resistance power output for overcoming the wind resistance, obtaining the resistance power at the current moment; and based on the bias, the resistance power, the kinetic energy increment and the potential energy increment, obtaining the riding power P at the current moment. The riding power of the exercise user is estimated, a power detection device does not need to be worn, and the use experience of the exercise user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sports health, and particularly to a method and system for estimating cycling power. Background Art

[0002] Power is an important output parameter of cycling and also an important reference index for measuring the strength of cycling ability. Generally, power detection requires an external power detection device (for example, a power meter) to obtain. However, a large number of users without wearing a power meter also have a need for this power index.

[0003] Therefore, there is an urgent need for a method that can obtain cycling power without wearing a power meter.

[0004] The above information disclosed in this background art is only used to increase the understanding of the background art of the present application. Therefore, it may include prior art that is not known to those of ordinary skill in the art. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method for estimating cycling power, which estimates the cycling power of a sports user based on the physiological information of the sports user himself, the weight of the bicycle, the cadence, the wind force, and the position information, without wearing a power detection device, and improves the use experience of the sports user.

[0006] To achieve the above invention purpose, the present invention is implemented by the following technical solutions: The present application relates to a method for estimating cycling power, including: Based on the bicycle wheel diameter L , the cadence cad , the wind pressure representing the wind force, the cycling speed ν and the slope slope , obtain the wind direction θ_wind representing whether the user is cycling against the wind or with the wind and the cycling heading heading ; Based on the physiological information of the sports user himself, the weight of the bicycle, the cycling speed and the slope, obtain the kinetic energy increment E and the potential energy increment Wg at the current moment; Based on the pre-established wind force response model between the input data and the resistance power output for overcoming the wind resistance P_wind , obtain the resistance power P_wind at the current moment; Based on the bias gain_θ , the resistance power P_wind , the kinetic energy increment E and the potential energy increment Wg , obtain the cycling power P at the current moment; Among them, the offset is determined according to the wind direction and the riding heading. gain_θ When facing the wind, the offset gain_θ is 1, and when against the wind, the offset gain_θ is -1. The input data includes the bicycle wheel diameter, the riding speed increment, the pedal frequency, the slope, the wind speed, the wind direction, and the riding heading. The wind speed is estimated from the wind pressure.

[0007] In some embodiments of the present application, obtaining the wind direction and the riding heading indicating that the user is riding against the wind or with the wind specifically includes: A first model between the pre-established first input data and the wind direction and the riding heading of riding against the wind or with the wind; Inputting the bicycle wheel diameter, the pedal frequency, the wind pressure, the riding speed, and the slope data into the first model to obtain the wind direction and the riding heading of riding against the wind or with the wind; Among them, the first input data includes the bicycle wheel diameter, the pedal frequency, the wind pressure, the riding speed, and the slope data.

[0008] In some embodiments of the present application, obtaining the kinetic energy increment at the current moment E and the potential energy increment Wg specifically includes: E = 1 / 2·(M_body + M_bake)·(ν t -ν t-1 ) 2 , ν t -ν t-1 ＞0； Wg = 1 / 4·(M_body + M_bake)·g·(ν t +ν t-1 ), slope t , slope t ＞0; Among them, M_body and M_bake are the weight of the user and the weight of the bicycle respectively, ν t is the riding speed at the current moment, ν t-1 is the riding speed at the previous moment, slope t is the slope at the current moment, slope t-1 is the slope at the previous moment, g is the acceleration due to gravity.

[0009] In some embodiments of the present application, the wind speed ν_windEstimated from the wind pressure, specifically: p_wind ; ; wherein, ρ is the atmospheric density.

[0010] In some embodiments of the present application, the wind force response model is specifically: ; wherein, IW is the link weight, B is the bias weight, LW is the output connection weight, and IW , B and LW are obtained by training with a neural network algorithm, relu(x) is the activation function, input represents the input data 。

[0011] In some embodiments of the present application, based on the bias gain_θ , resistance power P_wind , kinetic energy increment E and potential energy increment Wg , the riding power P at the current moment is obtained, specifically: P = E + Wg + gain_θ * P_wind。

[0012] The riding power estimation method provided by some embodiments of the present application has the following advantages and beneficial effects: (1) Based on the bicycle wheel diameter, cadence, wind pressure, position data, and headwind / tailwind riding conditions, riding power is estimated without wearing a power meter, meeting the user's power requirements without a power meter; (2) The hardware device cost required for this power estimation method is low, and it can provide richer riding feedback data for novice users.

[0013] The present application also relates to a riding power estimation system, including: A headwind / tailwind acquisition module; based on the bicycle wheel diameter, cadence, wind pressure representing wind force, riding speed, and slope data, it acquires the wind direction and riding course indicating whether the user is riding against the wind or with the wind; An increment acquisition module, which acquires the kinetic energy increment E and potential energy increment Wg at the current moment based on the physiological information of the moving user, the weight of the bicycle, riding speed, and slope; A resistance power acquisition module, which is based on the pre-established input data and the resistance power P_ windWind response model between, and obtain the resistance power at the current moment P_wind ; Ride power acquisition module, which is based on the bias gain_θ , resistance power P_wind , kinetic energy increment E and potential energy increment Wg , and obtain the ride power at the current moment P ; Among them, the bias is determined according to the wind direction and the riding course gain_θ , and the bias gain_θ is 1 when facing the wind and the bias gain_θ is -1 when against the wind. The input data includes the bicycle wheel diameter, the riding speed increment, the cadence, the slope, the wind speed, the wind direction and the riding course, and the wind speed is estimated from the wind pressure.

[0014] In some embodiments of the present application, the ride power estimation system is implemented on a cycle computer, and the following are provided on the cycle computer: A first barometer, which shields the wind and is used to detect the slope; A second barometer, which is used to detect the wind pressure; A navigation chip, which is used to detect the riding speed; Among them, the ride power P is displayed on the display screen of the cycle computer.

[0015] After reading the specific embodiments of the present invention in conjunction with the drawings, other features and advantages of the present invention will become clearer. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 is a flowchart of an embodiment of the ride power estimation method proposed in the present application; Figure 2 is a hardware block diagram of an embodiment of the ride power estimation system proposed in the present application; Figure 3 is a comparison diagram between the ride power estimated by the ride power estimation method proposed in the present application and the measured true ride power; Reference numerals: 100, ride power estimation system; 200, cycle computer. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0019] Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. In the description of the present invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0020] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0021] The terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise stated, the meaning of "plurality" is two or more.

[0022] To solve the problem that users need to wear power monitoring devices to obtain cycling power during cycling, some embodiments of the present application involve a cycling power estimation method, which is based on the physiological information of the exercising user himself, the weight of the bicycle, the cadence, the wind force, and the position information (such as including cycling speed and slope). Without wearing a power monitoring device, it can reliably and accurately estimate the cycling power, facilitate measuring the health status of the exercising user, and also provide rich cycling feedback data for novice users.

[0023] Some embodiments of the present application involve a cycling power estimation method.

[0024] This cycling power estimation method is implemented based on the cycling power estimation system 100. As follows, the cycling power estimation method will be described in conjunction with the cycling power estimation system 100.

[0025] Figure 1 A flowchart showing a cycling power estimation method is provided. Therefore, with reference to Figure 1 , the cycling power estimation method will be described in detail as follows.

[0026] S1: Based on data such as the bicycle wheel diameter, cadence, wind pressure representing wind force, cycling speed, and slope, obtain the wind direction and cycling heading indicating whether the user is cycling against the wind or with the wind.

[0027] The process of obtaining cycling against the wind or with the wind can be obtained through a headwind / tailwind acquisition module (not shown) in the cycling power estimation system 100.

[0028] The wheel diameter is an inherent parameter of the bicycle, and for the same bicycle, its wheel diameter is the same.

[0029] The cadence is the number of rotations of the pedals per minute, and for users using different pedals, there are differences in their cadences.

[0030] In some embodiments of the present application, the cadence sensor is used to obtain the cadence in real time cad .

[0031] The magnitude of the wind pressure can directly measure the magnitude of the wind force. There is a strong correlation between wind force and body energy consumption. In a windless environment, body energy consumption is related to the physiological information and speed of the exercising user. In a windy environment and at the same speed, the greater the wind force when cycling against the wind, the higher the body energy consumption, and when cycling with the wind, the greater the wind force, the lower the body energy consumption.

[0032] The cycling speed and slope data belong to position data. In some embodiments of the present application, referring to Figure 2 , the cycling power estimation system 100 is provided in the cycle computer 200, and the cycle computer 200 is internally provided with a first barometer (not shown) and a second barometer (not shown).

[0033] The first barometer shields the wind force and is mainly used to detect slope information; the second barometer is affected by the wind force and is mainly used to detect the wind pressure to measure the magnitude of the wind force.

[0034] In addition, a navigation chip (not shown) is also internally provided in the cycle computer 200, which is used not only for navigation and positioning but also for obtaining the cycling speed of the exercising user.

[0035] In order to obtain information about cycling against the wind or with the wind, in some embodiments of the present application, through a pre-established first model between the first input data and the wind direction and cycling heading, when the first input data is known, through this first model, the wind direction and cycling heading of the exercising user under the current input data can be obtained, and whether the current exercising user is cycling against the wind or with the wind can be determined through the wind direction and cycling heading.

[0036] Among them, the first input data includes bicycle wheel diameter, pedal frequency, wind pressure, riding speed, and slope data, and the first model can be a preset query table.

[0037] During testing, the first input data, wind direction, and riding heading are obtained to form the above query table.

[0038] During actual exercise, the wind direction at the current real-time moment can be obtained through the first input data obtained in real time. θ_wind and riding heading heading , and the headwind or upwind riding can be determined through the wind direction θ_wind and riding heading heading .

[0039] Specifically, at | |θ_wind - heading|>π / 2 , it indicates upwind riding, and at | |θ_wind - heading|<π / 2 , it indicates headwind riding.

[0040] S2: Based on the physiological information of the exercising user himself, the weight of the bicycle, the riding speed, and the slope, obtain the kinetic energy increment E and potential energy increment Wg at the current moment.

[0041] This process of obtaining the kinetic energy increment E and potential energy increment Wg can be implemented by an increment acquisition module (not shown) in the riding power estimation system 100.

[0042] During the riding process, the riding speed is obtained in real time by using a navigation chip ν , and the slope is obtained in real time by using a first barometer slope .

[0043] Using the physiological information of the exercising user himself (for example, weight M_body ), the weight of the bicycle M_bake , the riding speed ν and the slope slope , the following formula (1) is used to calculate the kinetic energy increment E and potential energy increment Wg .

[0044] (1).

[0045] Among them, ν t is the riding speed at the current moment, ν t-1 is the riding speed at the previous moment, slope t is the slope at the current moment, slope t-1 is the slope at the previous moment, gis the acceleration due to gravity.

[0046] It should be noted that the kinetic energy increment E and the potential energy increment Wg will only be calculated when there are increments in speed and slope.

[0047] S3: Based on the pre-established wind force response model between the input data and the resistance power output to overcome wind resistance P_wind obtain the resistance power at the current moment P_wind。

[0048] This estimation process of the riding power can be implemented by the resistance power acquisition module (not shown) in the riding power estimation system 100.

[0049] Since the wind pressure (wind pressure affects the wind force) and the wind direction have a greater impact on the riding power, in order to quantitatively feedback this response to the power value, a wind force response model is pre-established with the bicycle wheel diameter L, speed increment △ ν , pedal frequency cad , slope slope , wind speed ν_wind , wind direction θ_wind , riding heading heading as the input data and the power P_wind output to overcome wind resistance as the output.

[0050] In some embodiments of the present application, the wind speed ν_wind can be estimated from the wind pressure detected by the second barometer, as shown in formula (2) below.

[0051] (2).

[0052] Wherein, ρ is the atmospheric density.

[0053] In other embodiments, the wind speed ν_wind can also be obtained in other ways, such as using a speed sensor installed on the bicycle.

[0054] After establishing this wind force response model, when the speed increment △ ν , pedal frequency cad , slope slope , wind speed ν_wind , wind direction θ_wind , riding heading heading are obtained in real time, and then combined with the bicycle wheel diameter L , using this wind force response model, obtain the power P_wind output to overcome wind resistance.

[0055] When establishing the above wind force response model, it is necessary to consider the situation of riding against the wind or with the wind. When riding with the wind, there is a biasgain_θ is 1, and is offset when riding against the wind gain_θ is -1.

[0056] The wind force response model is shown in the following formula (3).

[0057] (3).

[0058] In some embodiments of the present application, a neural network learning algorithm is used to obtain the wind force response model.

[0059] In the above formula (3), IW is the link weight, B is the bias weight, LW is the output connection weight, relu(x) is the activation function, IW and B and LW Specifically, it can be obtained by training with an extreme learning machine.

[0060] Using the relu( ) function, the gradient descent speed is fast during training, and good convergence can be achieved with fewer iterations.

[0061] S4: Based on the bias gain_θ , the resistance power P_wind , the kinetic energy increment E and the potential energy increment Wg , obtain the riding power P at the current moment.

[0062] This riding power P can be obtained by the riding power acquisition module (not shown) in the riding power estimation system 100.

[0063] When riding against the wind, the bias gain_θ is 1, and when riding against the wind, the bias gain_θ is -1. When riding against the wind, the riding power of the moving user will increase, and when riding against the wind, the riding power of the moving user will decrease.

[0064] Based on the bias gain_θ , the resistance power P_wind , the kinetic energy increment E and the potential energy increment Wg , use formula (4) to obtain the riding power P at the current moment.

[0065] P = E + Wg + gain_θ * P_wind (4).

[0066] In some embodiments of the present application, the cycle computer 200 has a display screen (not shown), and the riding power can be displayed on the display screenP , or other data (e.g., cadence cad, riding speed ν, gradient slope , etc.), which is convenient for sports users to view.

[0067] In some embodiments of the present application, the cycle computer 200 can also be communicatively connected to a smart terminal (e.g., a mobile phone, a smart bracelet, etc.) to transmit the data on the cycle computer 200 (e.g., riding power P, cadence cad, riding speed ν ) to the smart terminal for display, meeting the flexible viewing needs of sports users.

[0068] Refer to Figure 3 , which gives a comparison graph between the riding power (i.e., the estimated value) estimated by using the riding power estimation method involved in the embodiments of the present application and the actually measured riding power (i.e., the true value).

[0069] The actually measured riding power can be obtained by a sports user wearing a power monitoring device (e.g., a power meter), refer to Figure 3 as shown by the dashed line in

[0070] The riding power obtained by using the riding power estimation method of the present application, refer to Figure 3 as shown by the solid line in

[0071] It can be seen from Figure 3 that the trend of the riding power estimated by using the above-mentioned riding power estimation method is basically the same as the trend of the actual riding power of the sports user, and the estimated riding power is basically approximate to the actual riding power.

[0072] The riding power estimated by this riding power estimation method has a high accuracy rate, and there is no need to wear a power monitoring device, reducing the cost investment.

[0073] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, for those of ordinary skill in the art, it is still possible to modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions required to be protected by the present invention.

Claims

1. A method for estimating cycling power, characterized in that, including: Based on the bicycle wheel diameter L , pedaling frequency cad , wind pressure representing wind force, riding speed ν and slope slope , obtain the wind direction representing whether the user is riding against the wind or with the wind θ_wind and riding heading heading ; Obtain the kinetic energy increment and potential energy increment at the current moment based on the physiological information of the exercising user himself / herself, the weight of the bicycle, the riding speed, and the slope E and the potential energy increment Wg ; Based on pre-established input data and the resistance power for overcoming wind resistance output P_wind between the wind force response models, obtain the resistance power at the current moment P_wind ; Based on offset gain_θ , resistance power P_wind , kinetic energy increment E and potential energy increment Wg , obtain the cycling power at the current moment P ; Among them, the offset is determined according to the wind direction and the riding heading gain_θ , and the offset is 1 when facing the wind gain_θ and the offset is -1 when against the wind. The input data includes the bicycle wheel diameter gain_θ , the riding speed increment, the pedaling frequency, the slope, the wind speed, the wind direction and the riding heading. The wind speed is estimated from the wind pressure L .

2. The cycling power estimation method according to claim 1, wherein Obtain the wind direction and riding heading that characterize the user riding against the wind or with the wind, specifically: The first model between the pre-established first input data and the wind direction and riding heading of riding against the wind or with the wind; Input the bicycle wheel diameter, cadence, wind pressure, riding speed and slope data into the first model to obtain the wind direction and riding heading of riding against the wind or with the wind; Among them, the first input data includes bicycle wheel diameter L , cadence, wind pressure, riding speed, and gradient data.

3. The riding power estimation method according to claim 1, characterized in that, Obtain the kinetic energy increment at the current moment E and the potential energy increment Wg , specifically as follows: E = 1 / 2·(M_body + M_bake)·(ν t -ν t-1 ) 2 ， ν t -ν t-1 ＞0； Wg = 1 / 4·(M_body + M_bake)·g·(ν t +ν t-1 )·(slope t ), slope t ＞0; Among them, M_body and M_bake are the user's weight and the weight of the bicycle respectively, ν t is the riding speed at the current moment, ν t-1 is the riding speed at the previous moment, slope t is the slope at the current moment, slope t-1 is the slope at the previous moment, g is the acceleration due to gravity.

4. The cycling power estimation method according to claim 1, wherein The wind speed ν_wind is estimated from the wind pressure p_wind specifically as follows: ； Among them, ρ is the atmospheric density.

5. The riding power estimation method according to claim 1, characterized in that, The wind force response model, specifically: ； Among them, IW is the link weight, B is the bias weight, LW is the output connection weight, and IW , B and LW are obtained by training with a neural network algorithm, relu(x) is the activation function, input represents the input data 。 6. The riding power estimation method according to claim 1, characterized in that Based on the bias gain_θ , the resistance power P_wind , the kinetic energy increment E and the potential energy increment Wg , obtain the riding power P at the current moment, specifically: P = E + Wg + gain_θ * P_wind.

7. A cycling power estimation system, characterized in that, including: Headwind / tailwind acquisition module; Based on the bicycle wheel diameter, cadence, wind pressure representing the wind force, riding speed and slope data, obtain the wind direction and riding heading that characterize the user riding against the wind or with the wind; An incremental acquisition module that obtains the kinetic energy increment at the current moment based on the physiological information of the exercising user himself, the weight of the bicycle, the riding speed, and the slope E and the potential energy increment Wg ; A resistance power acquisition module that obtains the resistance power at the current moment based on a pre-established wind force response model between the input data and the resistance power output for overcoming wind resistance P_wind ; P_wind ; Ride power acquisition module, which is based on bias gain_θ , resistance power P_wind , kinetic energy increment E and potential energy increment Wg , to obtain the ride power at the current moment P ; Among them, the offset is determined according to the wind direction and the riding course gain_θ , and the offset is 1 when facing the wind gain_θ and the offset is -1 when against the wind gain_θ . The input data includes the bicycle wheel diameter, the riding speed increment, the pedal frequency, the slope, the wind speed, the wind direction and the riding course, and the wind speed is estimated from the wind pressure.

8. The riding power estimation system according to claim 7, characterized in that, The riding power estimation system is implemented on the cycle computer, and the following are set on the cycle computer: The first barometer, which shields the wind force and is used to detect the slope; The second barometer, which is used to detect the wind pressure; The navigation chip, which is used to detect the riding speed; Among them, the riding power P is displayed on the display screen of the cycle computer.

Images