Shared electric bicycle overload detection method, detection system and computing device

Abstract

The invention discloses a shared electric bicycle overload detection method and system and computing equipment, and belongs to the technical field of electric digital data processing.The detection method comprises the following steps that driving data of a shared electric bicycle are obtained, and the driving data comprise current, voltage, gradient and speed; obtaining the current weight of the shared electric bicycle according to the driving data; and obtaining an overload condition according to the current weight and a first threshold value. The overload condition is detected through the current, the voltage, the gradient, the speed and other riding data of the shared electric bicycle, the detection mode is simple and effective, the situation that a weight sensor is installed in an existing shared electric bicycle is avoided, and the transformation cost is saved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric digital data processing, and particularly relates to a detection method, a detection system and a computing device for overloading of shared electric bicycles. Background Art

[0002] Shared electric vehicles (Shared ev) are a new type of transportation. Shared electric bicycles have entered cities large and small, bringing convenience to travelers and solving the problem of the last mile. Electric bicycles have brought traffic convenience and have become an important means of transportation for travel.

[0003] Shared electric bicycles are usually only for one person to ride. However, in the actual operation process, there are still some users carrying two passengers, resulting in overloading of the electric bicycle. Under overloading, it is easy to cause damage to the frame or electric drive mechanism of the electric bicycle, posing a safety hazard to travel. In traditional detection, by installing a gravity sensor on the electric bicycle, the load is detected, and whether there is overloading is judged according to the load situation; this detection method requires modification of the electric bicycle, and the existing electric bicycles still cannot achieve overloading detection. Summary of the Invention

[0004] In view of the above technical problems existing in the prior art, the present invention provides a detection method, a detection system and a computing device for overloading of shared electric bicycles, and detects the overloading situation during the user's riding process.

[0005] The first aspect of the present invention discloses a detection method for overloading of shared electric bicycles, including the following steps: obtaining the driving data of the shared electric bicycle, where the driving data includes current, voltage, slope and speed; obtaining the current weight of the shared electric bicycle according to the driving data; obtaining the overloading situation according to the current weight and a first threshold.

[0006] Preferably, the method for calculating the current weight includes:

[0007]

[0008] where m represents the current weight, g represents the acceleration due to gravity, μ is the rolling resistance coefficient, ρ is the air density, C d is the air resistance coefficient, A represents the frontal area, v represents the driving speed, and θ represents the slope.

[0009] Preferably, the method for calculating the load is:

[0010] Δm = m - m0

[0011] where Δm represents the load, m0 represents the vehicle self-weight, and m represents the current weight.

[0012] Preferably, according to the load and historical data, the overloading situation is obtained.

[0013] Preferably, if the difference between the load and the average load is greater than the first threshold, it is considered that there is an overloading situation.

[0014] Preferably, if the product of the load and the weight is greater than the first threshold, it is considered that there is an overloading situation.

[0015] The calculation method of the weight is as follows:

[0016]

[0017] W(t) represents the weight at time t, where t peak is the center point of the high-frequency period in the historical data, and d route is the distance between the current path and the historical path.

[0018] Preferably, it is judged whether the load, the difference between the load and the average load, or the product of the load and the weight is greater than the first threshold;

[0019] If not, execute step 302: Mark it as normal and continuously collect driving data;

[0020] If so, execute step 303: Judge whether the current time period is in the historical high-load period;

[0021] If it is in the historical high-load period, execute step 304: Judge whether the slope is greater than the third threshold;

[0022] If it is greater than the third threshold, execute step 302;

[0023] If it is less than or equal to the third threshold, execute step 306;

[0024] If the historical high-load period has not been processed, execute step 305: Judge whether the acceleration is greater than the fourth threshold;

[0025] If it is greater than the fourth threshold, execute step 302;

[0026] If it is less than or equal to the fourth threshold, execute step 306;

[0027] Step 306: Judge whether the confidence level is greater than the fifth threshold;

[0028] If it is greater than the fifth threshold, confirm overloading;

[0029] If it is less than or equal to the fifth threshold, it is considered that there is an abnormality in the vehicle's hardware sensor, and an alarm message is sent to the management personnel.

[0030] Preferably, the calculation method of the confidence level is as follows:

[0031]

[0032] Among them, Con represents the confidence level, Δm represents the load, σ represents the standard deviation of the historical load, and D t is the time decay factor between the current time and the most recent overloading time.

[0033] The second aspect of the present invention discloses a detection system for implementing the above detection method. The detection system includes a collection module, a calculation module, and a detection module.

[0034] The collection module is used to collect the driving data of the shared electric bicycle.

[0035] The calculation module is used to calculate the current weight of the shared electric bicycle according to the driving data.

[0036] The detection module is used to obtain the overloading situation according to the current weight and the first threshold.

[0037] The third aspect of the present invention provides a computing device, including a memory that stores code. When the code is executed, the above detection method is implemented.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows: By using the riding data such as the current, voltage, slope, and speed of the shared electric bicycle, the overloading situation is detected. The detection method is simple and effective, avoiding the installation of weight sensors in existing shared electric bicycles and saving the transformation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is the flowchart of the detection method for overloading of the shared electric bicycle of the present invention;

[0040] Figure 2 is the flowchart of the third overloading detection method;

[0041] Figure 3 is the logical block diagram of the detection system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] The following further describes the present invention in detail with reference to the accompanying drawings:

[0044] Overview: Shared electric bicycles generally refer to bicycles or electric bicycles put on the market in the form of rental; shared electric bicycles are usually two-wheeled vehicles, equipped with batteries and motors, and driven by batteries and motors. Electronic fence: A shared bicycle or electric bicycle is parked in the specified area, which is a closed area surrounded by coordinates. The user side refers to the terminal application used by the user who uses the shared electric bicycle. The ground area corresponding to the electronic fence is called a parking zone or a parking spot. The shared electric bicycle relies on being within the parking spot.

[0045] After riding to the destination, the user of the vehicle returns the electric bicycle to the designated location and then completes the return. The return can be completed in multiple ways such as judging the parking position coordinates, Bluetooth ground pins, intelligent footrests, RFID landmarks, photo return, camera return, etc.

[0046] The first aspect of the present invention provides a method for detecting overloading of shared electric bicycles, as Figure 1 shown, including the following steps:

[0047] Step 101: Obtain the driving data of the shared electric bicycle.

[0048] The driving data includes data such as current, voltage, slope, speed, time, and path.

[0049] Step 102: Obtain the current weight of the shared electric bicycle according to the driving data.

[0050] Step 103: Obtain the overloading value according to the current weight and the first threshold.

[0051] For example, if the current weight is greater than the first threshold, it can be determined as overloading.

[0052] By using the riding data such as current, voltage, slope, and speed of the shared electric bicycle to detect the overloading situation, the detection method is simple and effective, avoiding the installation of weight sensors in existing shared electric bicycles and saving the transformation cost.

[0053] In step 102, the method for calculating the current weight includes:

[0054] Step 301: Calculate the current weight according to the relationship between the resistance, power, and current of the shared electric bicycle.

[0055] The resistance model is:

[0056] F roll =μ·m·g (1)

[0057] F air =0.5·ρ·C d ·A·v 2 (2)

[0058] F grade= m·g·sinθ (3)

[0059] F total = F roll + F air + F grade (4)

[0060] Among them, F roll represents the rolling resistance, m represents the current weight, g represents the acceleration due to gravity, μ is the rolling resistance coefficient, F air represents the air resistance, ρ is the air density, C d is the air resistance coefficient, A represents the frontal area, v represents the driving speed, F grade represents the gradient resistance, θ represents the gradient, F total represents the total resistance.

[0061] The power and current models are expressed as:

[0062] P mech = F total ·v (5)

[0063]

[0064] P mech represents the mechanical power, P ele represents the total power, η1 represents the motor efficiency, U represents the driving voltage of the motor, and I represents the driving current of the motor.

[0065] Based on Formulas 1 - 6, the following formulas can be derived:

[0066]

[0067] Among them, Δm represents the load, and m0 represents the vehicle self - weight.

[0068] Specifically, the value range of the rolling resistance coefficient μ is: 0.015 - 0.025, C d A has a value range of 0.4 - 0.6, the value of the air density ρ is 1.225 KG / M 3 , the value range of the motor efficiency η1 is 75 - 85%, the vehicle self - weight range is 50 - 60 KG. However, the values of these parameters can be adjusted according to the actual environment and vehicle parameters. The rolling resistance coefficient can be measured, the air resistance coefficient takes a typical value, the air density takes a typical value, the motor efficiency: can be measured or given by the manufacturer; the angle and gradient are collected and calculated through a six - axis sensor; the speed can be collected and calculated through the rotation of the phase wires; the current can be collected through the controller.

[0069] In step 103, the following judgment method can be adopted:

[0070] The first type of overload detection: The detected load can be compared with the user's average load. If the difference between the load and the average load is greater than the first threshold, it is considered that there is an overload situation.

[0071] The second type of overload detection method: The overload detection can be carried out by combining the riding time and path: The product of the load Δm and the weight w(t) is compared with the first threshold: If Δm·w(t) is greater than the first threshold, it is considered that there is an overload.

[0072] Among them, the weight calculation formula is expressed as:

[0073]

[0074] W(t) represents the weight at time t, where t peak is the center point of the high-frequency period in the historical data, and d route is the distance between the current path and the historical path. The distance between the two paths can be calculated based on the dynamic time warping (DTW) algorithm. t peak reflects the time correlation used to adjust the weight according to the difference between the current time and the user's peak time, and d route allocates weights through the path difference. This dynamic adjustment can flexibly adjust the weights of different factors according to the changes in time and path, improving the accuracy of the model's judgment of overload. In user behavior analysis, the impact of different time periods and different paths on the load may be different. For example, users may be more likely to overload during peak hours, and a specific path (such as a route with a large slope) may also affect the load judgment. By dynamically adjusting the weights, these changes can be better captured and misjudgments can be reduced.

[0075] Such as Figure 2 , the third type of overload detection method adopts the following steps:

[0076] Step 301: Judge whether the load, the difference between the load and the average load, or the product of the load Δm and the weight w(t) is greater than the first threshold.

[0077] If not, execute Step 302: Mark it as normal and continuously collect driving data.

[0078] If so, execute Step 303: Judge whether the current time period is in the historical high-load period.

[0079] For example, in the historical data, if the number of overloads in the time period from 20:00 to 21:00 is greater than the second threshold, then this time period is considered a high-load period.

[0080] If it is in the historical high-load period, execute Step 304: Judge whether the slope is greater than the third threshold.

[0081] If it is greater than the third threshold, step 302 is executed. When the slope is too large, the motor does a lot of work, which may cause the detected value of the current data to deviate.

[0082] If it is less than or equal to the third threshold, step 306 is executed.

[0083] If there is no processing of the historical high-load period, step 305 is executed: Determine whether the acceleration is greater than the fourth threshold.

[0084] If it is greater than the fourth threshold, step 302 is executed. When the acceleration is too large, the motor does a lot of work, which may cause the detected value of the current data to deviate.

[0085] If it is less than or equal to the fourth threshold, step 306 is executed.

[0086] Step 306: Determine whether the confidence level is greater than the fifth threshold.

[0087] If it is greater than the fifth threshold, step 307 is executed: Confirm overloading.

[0088] If it is less than or equal to the fifth threshold, step 308 is executed: It is considered that there is an abnormality in the vehicle's hardware sensor, and an alarm message is sent to the management personnel.

[0089] Through the historical high-frequency time period, slope, acceleration, and confidence level, the detection results are screened and corrected to improve the accuracy of detection and avoid false alarms.

[0090] Overloading can also be set as: the load, the difference between the load and the average load, or the product of the load Δm and the weight w(t) is greater than the first threshold, the slope is less than or equal to the third threshold, the acceleration is less than or equal to the fourth threshold, and the confidence level is greater than the fifth threshold.

[0091] Optionally, random / regular sampling detection is performed during the driving of the shared electric bicycle, or real-time detection can also be performed. During a trip, when the number or duration of overloading exceeds the sixth threshold, an alarm message is sent to the user or operator.

[0092] Among them, the calculation method of the confidence level is:

[0093]

[0094] Among them, Con represents the confidence level, Δm represents the load, σ represents the historical load standard deviation, and D t is the time decay factor between the current time and the nearest overloading time.

[0095] Through the above calculation method, an overloading detection model can be established. In the present invention, the various parameters of the overloading detection model can also be automatically adjusted according to historical data, such as adjusting corresponding threshold values and other parameters:

[0096]

[0097] Among them, θ new is the updated model parameter, θ old is the historical model parameter, η is the learning rate (value range: 0.001 - 0.1), N is the amount of new data samples, is the gradient of the loss function with respect to the parameter, L is the loss function, new input features (load, acceleration, path, slope, etc.), new label data (manual verification results, sensor values).

[0098] The second aspect of the present invention provides a detection system for implementing the above detection method, as Figure 3 shown, including a collection module 1, a calculation module 2, and a detection module 3,

[0099] The collection module 1 is used to collect the driving data of the shared electric bicycle;

[0100] The calculation module 2 is used to calculate the current weight of the shared electric bicycle according to the driving data;

[0101] The detection module 3 is used to determine whether it is overloaded according to the current weight and the first threshold.

[0102] In some processes described in the present invention, a plurality of operations appear in a specific order, but it should be clearly understood that these operations can be executed not in the order in which they appear in this text or in parallel. The operation numbers such as 101, 102, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations can be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this text are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0103] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject.

[0104] In the present invention, terms such as "including" or "having" are intended to indicate the presence of features, numbers, steps, actions, components, parts, or combinations thereof disclosed in this specification, and do not exclude the possibility of the presence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0105] A third aspect of the present invention provides a computing device, which includes a memory and a processor. The memory stores code for implementing the above detection method. When the code is executed by the processor, the above detection method is implemented.

[0106] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A detection method for overloading of shared electric bicycles, characterized in that, It includes the following steps: Obtain the driving data of the shared electric bicycle, where the driving data includes current, voltage, slope, and speed; Obtain the current weight of the shared electric bicycle according to the driving data; Obtain the overloading situation according to the current weight and the first threshold.

2. The detection method according to claim 1, wherein The method for calculating the current weight includes: Where, m represents the current weight, g represents the acceleration due to gravity, μ is the rolling resistance coefficient, ρ is the air density, C d is the air resistance coefficient, A represents the frontal area, v represents the driving speed, and θ represents the slope.

3. The detection method according to claim 1 or 2, characterized in that The calculation method of the load is: Δm = m - m0 where Δm represents the load, m0 represents the vehicle self-weight, and m represents the current weight.

4. The detection method according to claim 3, wherein Obtain the overloading situation according to the load and historical data.

5. The detection method according to claim 4, characterized in that If the difference between the load and the historical average load is greater than the first threshold, there is an overloading situation.

6. The detection method according to claim 4, wherein If the product of the load and the weight is greater than the first threshold, there is an overloading situation. The calculation method of the weight is: W(t) represents the weight at time t, where t peak is the center point of the high-frequency period in the historical data, and d route is the distance between the current path and the historical path.

7. The detection method according to claim 4, wherein Judge whether the load, the difference between the load and the average load, or the product of the load and the weight is greater than the first threshold; If not, execute step 302: Mark it as normal and continuously collect the driving data; If so, execute step 303: Judge whether the current time period is in the historical high-load period; If it is in the historical high-load period, execute step 304: Judge whether the slope is greater than the third threshold; If it is greater than the third threshold, execute step 302; If it is less than or equal to the third threshold, execute step 306; If the historical high-load period has not been processed, execute step 305: Judge whether the acceleration is greater than the fourth threshold; If it is greater than the fourth threshold, execute step 302; If it is less than or equal to the fourth threshold, execute step 306; Step 306: Judge whether the confidence level is greater than the fifth threshold; If it is greater than the fifth threshold, there is overloading.

8. The detection method according to claim 7, wherein If it is less than or equal to the fifth threshold, there is an abnormality in the vehicle's hardware sensor; The calculation method of the confidence level is: Wherein, Con represents confidence, Δm represents load, σ represents historical load standard deviation, and D t is the time decay factor between the current time and the most recent overload time.

9. A detection system, characterized in that, For implementing the detection method according to any one of claims 1-8, the detection system includes an acquisition module, a calculation module, and a detection module. The acquisition module is used to acquire the driving data of the shared electric bicycle; The calculation module is used to calculate the current weight of the shared electric bicycle according to the driving data; The detection module is used to obtain the overloading situation according to the current weight and the first threshold.

10. A computing device, characterized in that, It includes a memory, and the memory stores code, and when the code is executed, the detection method according to any one of claims 1-8 is implemented.

Images