Method and system for identifying overcrowded riding based on force cell sensor and related equipment

Abstract

The invention provides a method, system and related equipment for identifying overcrowded riding based on a force transducer, and the method comprises the steps: carrying out the load analysis of a key bearing part of a vehicle, and obtaining a plurality of target positions; force measurement sensors are arranged at the multiple target positions, and a multi-point force measurement monitoring network is formed; stress change data of all point positions are continuously obtained through the multi-point force measurement monitoring network; inputting the stress change data of each point location into a trained overcrowded riding identification model; performing comprehensive analysis of multi-source fusion on the stress change data of each point location through the overcrowded riding identification model to obtain a judgment result of whether overcrowded riding occurs or not; and if the judgment result is overcrowding, controlling a vehicle central controller to execute a preset overcrowding control strategy. According to the method, the multi-point-position force measurement monitoring network is constructed on the vehicle based on the key bearing parts, and then the stress data is collected based on the multi-point network and is subjected to multi-source analysis by using the model, so that the judgment precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shared vehicles, and in particular, to a method, a system and related devices for identifying overloading riding based on a force measuring sensor. Background Art

[0002] With the gradual development of the sharing economy, shared vehicles have become a powerful tool for solving people's travel problems. Overloading of shared vehicles will increase the instability of the vehicles and bring serious safety hazards. Therefore, how to identify vehicle overloading has become a technical problem to be solved in the prior art.

[0003] In the prior art, for vehicle overloading, there are technical solutions for detecting the number of riders by visual recognition or simply setting a pressure sensor directly under the seat. For the visual recognition solution, since a camera needs to be used and the camera is very prone to being damaged artificially, the recognition effect is affected. For the solution of directly setting a pressure sensor under the seat, there are technical problems such as low accuracy and high false alarm rate.

[0004] Therefore, the prior art still needs to be improved and developed. Summary of the Invention

[0005] The present invention provides a method, a system and related devices for identifying overloading riding based on a force measuring sensor. The main purpose of the present invention is to solve the technical problems mentioned in the background art existing in the prior art.

[0006] The first aspect of the present invention provides a method for identifying overloading riding based on a force measuring sensor, including:

[0007] Performing a load analysis on the key load-bearing parts of the vehicle to obtain a plurality of target positions;

[0008] Setting force measuring sensors at the plurality of target positions to form a multi-point force measuring monitoring network;

[0009] Continuously obtaining the force change data of each point through the multi-point force measuring monitoring network;

[0010] Inputting the force change data of each point into a trained overloading riding recognition model;

[0011] Performing a comprehensive analysis of multi-source fusion on the force change data of each point through the overloading riding recognition model to obtain a determination result of whether there is overloading;

[0012] If the determination result is overloading, controlling the vehicle central control to execute a preset overloading control strategy.

[0013] In some alternative embodiments of the first aspect of the present invention, the load analysis of the key load-bearing parts of the vehicle to obtain a plurality of target positions includes:

[0014] Performing a static load simulation on the key load-bearing parts of the vehicle in a static state to obtain a set of preliminary screening positions;

[0015] Performing a dynamic load simulation on the set of preliminary screening positions under different driving conditions to obtain the dynamic load change data of each preliminary screening position in the set of preliminary screening positions;

[0016] Performing a key index analysis on the dynamic load change data of each preliminary screening position in the set of preliminary screening positions to obtain the data stability evaluation results of each preliminary screening position in the set of preliminary screening positions;

[0017] Obtaining a plurality of target positions from the set of preliminary screening positions based on the data stability evaluation results.

[0018] In some alternative embodiments of the first aspect of the present invention, the performing a key index analysis on the dynamic load change data of each preliminary screening position in the set of preliminary screening positions to obtain the data stability evaluation results of each preliminary screening position in the set of preliminary screening positions includes:

[0019] Obtaining the dynamic load change curves of each preliminary screening position in the set of preliminary screening positions;

[0020] Obtaining the average fluctuation amplitude, average fluctuation frequency, and average fluctuation duration of each preliminary screening position from the dynamic load change curves of each preliminary screening position;

[0021] Performing a weighted operation on the average fluctuation amplitude, average fluctuation frequency, and average fluctuation duration of each preliminary screening position to obtain the data stability index of each preliminary screening position;

[0022] Sorting each preliminary screening position from small to large based on the data stability index to obtain the data stability evaluation results of each preliminary screening position.

[0023] In some alternative embodiments of the first aspect of the present invention, the performing a comprehensive analysis and judgment of multi-source fusion on the force change data of each point through the overcrowding riding recognition model to obtain a judgment result of whether there is overcrowding includes:

[0024] Comparing the force change data of each point with a preset threshold set to obtain an average difference, wherein the threshold set is set based on the point position, vehicle design parameters, and load limit parameters;

[0025] Determine the numerical range in which the average difference lies, and obtain the first confidence value for overloading judgment based on the numerical range;

[0026] Analyze the numerical distribution of the force change data at each of the points to obtain the dispersion degree of the force change data at each of the points;

[0027] Obtain the second confidence value for overloading judgment based on the dispersion degree of the force change data at each of the points;

[0028] Obtain the vehicle speed change-related data collected by other vehicle sensors, and analyze the acceleration characteristics and angular velocity characteristics of the vehicle speed change-related data to obtain the third confidence value for overloading judgment;

[0029] Perform a weighted average operation on the first confidence value, the second confidence value, and the third confidence value to obtain an overloading confidence index;

[0030] Compare the overloading confidence index with a preset confidence threshold to obtain a judgment result on whether there is overloading.

[0031] In some alternative embodiments of the first aspect of the present invention, the analyzing the numerical distribution of the force change data at each of the points to obtain the dispersion degree of the force change data at each of the points includes:

[0032] Group the force change data at each of the points based on the vehicle position area where they are located;

[0033] For each group of the force change data, calculate the average value of the force change data;

[0034] For each group of the force change data, calculate the standard deviation of the force change data from the average value;

[0035] Obtain the standard deviation corresponding to each group of the force change data and perform an average operation to obtain the dispersion degree of the force change data at each of the points.

[0036] In some alternative embodiments of the first aspect of the present invention, the obtaining the vehicle speed change-related data collected by other vehicle sensors, and analyzing the acceleration characteristics and angular velocity characteristics of the vehicle speed change-related data to obtain the third confidence value for overloading judgment includes:

[0037] Analyze the acceleration characteristics of the vehicle speed change-related data to obtain the first overloading matching degree of the acceleration-related statistical indicators;

[0038] Analyze the angular velocity characteristics of the vehicle speed change-related data to obtain the second overloading matching degree of the angular velocity-related statistical indicators;

[0039] Perform an average operation on the first overcrowding matching degree and the second overcrowding matching degree to obtain a third confidence value for overcrowding judgment.

[0040] In some alternative embodiments of the first aspect of the present invention, the if the determination result is overcrowding, then controlling the vehicle central control to execute a preset overcrowding control strategy includes:

[0041] If the determination result is overcrowding, then control the vehicle central control to repeatedly play the alarm voice of the preset statement, and after the number of times of playing the alarm voice reaches the preset number of times, send a power-off command to the vehicle power supply system.

[0042] The second aspect of the present invention provides a system for identifying overcrowded riding based on a force sensor, and the system for identifying overcrowded riding based on a force sensor includes:

[0043] An installation position acquisition module for performing load analysis on key load-bearing parts of the vehicle to obtain multiple target positions;

[0044] A force measurement network construction module for setting force sensors at multiple said target positions to form a multi-point force measurement monitoring network:

[0045] A force data acquisition module for continuously acquiring the force change data of each point through the multi-point force measurement monitoring network;

[0046] A data input module for inputting the force change data of each said point into a trained overcrowded riding identification model;

[0047] A data analysis module for performing a comprehensive analysis of multi-source fusion on the force change data of each said point through the overcrowded riding identification model to obtain a determination result of whether there is overcrowding;

[0048] An overcrowding control module for, if the determination result is overcrowding, controlling the vehicle central control to execute a preset overcrowding control strategy.

[0049] The third aspect of the present invention provides a device for identifying overcrowded riding based on a force sensor, and the device for identifying overcrowded riding based on a force sensor includes: a memory and at least one processor, instructions are stored in the memory, and the memory and the at least one processor are interconnected by a line;

[0050] The at least one processor calls the instructions in the memory so that the device for identifying overcrowded riding based on a force sensor executes the method for identifying overcrowded riding based on a force sensor according to any one of the above-mentioned first aspects of the present invention.

[0051] In a fourth aspect of the present invention, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the method for identifying overloaded riding based on a force sensor as described in any one of the first aspects of the present invention above.

[0052] Beneficial effects: The present invention provides a method, a system and related devices for identifying overloaded riding based on a force sensor. The method includes performing a load analysis on key load-bearing parts of a vehicle to obtain multiple target positions; setting force sensors at the multiple target positions to form a multi-point force measurement monitoring network: continuously obtaining the force change data of each point through the multi-point force measurement monitoring network; inputting the force change data of each point into a trained overloaded riding identification model; performing a comprehensive analysis of multi-source fusion on the force change data of each point through the overloaded riding identification model to obtain a determination result of whether it is overloaded; if the determination result is overloaded, controlling the vehicle central control to execute a preset overloaded control strategy. By constructing a multi-point force measurement monitoring network on the vehicle based on key load-bearing parts, and then performing multi-source analysis on the force data collected by the multi-point network using a model, the present invention improves the judgment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of an embodiment of a method for identifying overloaded riding based on a force sensor according to the present invention;

[0054] Figure 2 It is a schematic diagram of an embodiment of a system for identifying overloaded riding based on a force sensor according to the present invention;

[0055] Figure 3 It is a schematic diagram of an embodiment of a device for identifying overloaded riding based on a force sensor according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0056] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order different from that shown or described herein. In addition, the terms "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0057] For ease of understanding, the specific process of the embodiments of the present invention will be described below. Please refer to Figure 1 , the first aspect of the present invention provides a method for identifying overloaded cycling based on a force sensor, including:

[0058] S100. Analyze the load of the key load-bearing parts of the vehicle to obtain multiple target positions; in the present invention, the force sensor should be installed at the key load-bearing parts of the vehicle, such as below the frame crossbeam, at the connection between the seat and the frame, etc., to ensure that the gravity distribution of the vehicle can be comprehensively and evenly sensed.

[0059] In some optional embodiments of step S100 of the present invention, the analyzing the load of the key load-bearing parts of the vehicle to obtain multiple target positions includes:

[0060] Simulate the static load of the key load-bearing parts of the vehicle in a static state to obtain a set of preliminary screening positions; in this step, when the vehicle is in a stationary state, a load simulating the human body mass is placed on the seat of the vehicle, and then the force conditions of the key load-bearing parts are measured. Based on the magnitude of the force on the key load-bearing parts, the preliminary screening positions are selected. The purpose of this step is to delete the positions with small forces, so that the forces measured at the obtained set of preliminary screening positions can be better read and the changes can be observed.

[0061] Simulate the dynamic load of the set of preliminary screening positions under different driving conditions to obtain the dynamic load change data of each of the preliminary screening positions in the set of preliminary screening positions; in the present invention, the simulated human body mass during dynamic load simulation is different from that during static load simulation. The different driving conditions can specifically be simulated under different driving road environments. The purpose of simulating the dynamic load of the set of preliminary screening positions is to further obtain points with more stable data from the set of preliminary screening positions. If there are large fluctuations in the data at the data stable points, it can better reflect the situation of carrying passengers.

[0062] A key indicator analysis is performed on the dynamic load change data of each of the primary screening positions in the primary screening position set to obtain a data stability evaluation result of each of the primary screening positions in the primary screening position set; the key indicators here include but are not limited to fluctuation amplitude, fluctuation frequency and fluctuation duration, that is, in the present invention, this step may specifically include: obtaining the dynamic load change curve of each of the primary screening positions in the primary screening position set; from the dynamic load change curve of each of the primary screening positions, obtaining the average fluctuation amplitude, average fluctuation frequency and average fluctuation duration of each of the primary screening positions; performing weight calculation on the average fluctuation amplitude, average fluctuation frequency and average fluctuation duration of each of the primary screening positions to obtain a data stability index of each of the primary screening positions; sorting each of the primary screening positions from small to large based on the data stability index to obtain a data stability evaluation result of each of the primary screening positions.

[0063] Based on the data stability evaluation result, multiple target positions are obtained from the preliminary screening position set. In the present invention, this step is to obtain the target position with more stable dynamic load change data from the preliminary screening position set. The more stable the position data is, the more accurate the subsequent analysis results will be.

[0064] S200. Force sensors are set at multiple target positions to form a multi-point force measurement monitoring network; in the present invention, multiple force sensors are reasonably configured according to the specific structure and size of the vehicle to form a multi-point monitoring network. Generally speaking, at least one sensor needs to be installed on the front and rear sides of the vehicle to capture gravity changes in different directions. For large vehicles or specially designed vehicles, more sensors may need to be added to improve recognition accuracy. The sensor can be installed in a fixed manner to ensure a close fit with the vehicle structure and reduce measurement errors caused by vibration or looseness. Pay attention to the direction and angle of the sensor during installation to ensure that the measurement direction is consistent with the direction of gravity.

[0065] In the present invention, the force sensor contains a high-precision strain gauge or piezoelectric element as a sensing element, which produces deformation when subjected to pressure and converts it into an electrical signal output. The sensor housing is made of high-strength, corrosion-resistant material and has waterproof and dustproof functions. In addition, the sensor is also integrated with a signal processing circuit and a communication interface (such as a MODBUS interface) to convert the original signal into a digital signal and transmit it to the data processing center. The principle of use of the gravity sensor: Based on Hooke's Law, when an object is subjected to an external force, its deformation is proportional to the external force. The gravity sensor uses this principle to indirectly reflect the gravitational impact of the number of riders on the vehicle by measuring the slight deformation of the vehicle's load-bearing components.

[0066] S300. Continuously obtain the force change data of each point through the multi-point force measurement monitoring network; in the present invention, the force change data of each point mainly includes data during vehicle starting, acceleration, stable, and deceleration phases. Before the force change data is input into the model, the collected data can also be preprocessed first. The data preprocessing includes the following methods: 1. Filtering method: Use digital filtering techniques (such as low-pass filtering, median filtering, etc.) to preprocess the collected gravity data to eliminate noise and interference signals. The low-pass filter can filter out high-frequency noise, while the median filter can effectively suppress random pulse noise. 2. Abnormal data identification: Identify abnormal data by setting reasonable thresholds (such as maximum / minimum gravity values, gravity change rates, etc.). Abnormal data may be caused by sensor failures, external impacts, or extreme riding conditions. For the identified abnormal data, the system should exclude it or perform special processing. 3. Data retention: The data after filtering and abnormal data exclusion will be retained and used for subsequent data analysis. These data should be able to truly reflect the gravity changes during the riding process.

[0067] S400. Input the force change data of each point into the trained overloaded riding recognition model; in the present invention, the overloaded riding recognition model mainly has the following functions: Gravity data change law analysis: Establish an identification model by analyzing the change laws of gravity data under different riding numbers. When riding alone, the gravity data shows a relatively stable distribution characteristic; when riding with multiple people, there will be obvious gravity increase and uneven distribution phenomena. In addition, the influence of single-person obesity on gravity data also needs to be considered, and the differences between obesity and multi-person riding are distinguished by comparing historical data and statistical analysis. 2. Feature extraction and pattern recognition: Extract key features (such as gravity peaks, gravity distribution patterns, etc.) from the preprocessed data, and use machine learning or deep learning algorithms to construct an identification model. The model learns the gravity data features under different riding numbers through training to achieve accurate identification of the number of riders. 3. Exclude misjudgment of single-person obesity: To exclude misjudgment of single-person obesity, the system can adopt the following methods: One is to set reasonable thresholds by combining vehicle design parameters (such as maximum load) and the weight limit of the rider; the second is to judge whether it is a misjudgment caused by obesity by continuously monitoring the change trend and stability of gravity data; the third is to make a comprehensive judgment by combining other sensor data (such as accelerometers, gyroscopes, etc.).

[0068] S500. Perform a comprehensive analysis of multi-source fusion on the force change data of each point through the overloaded riding recognition model to obtain a determination result of whether it is overloaded; in the present invention, the comprehensive analysis of multi-source fusion means that in addition to using force sensors to obtain force data, it will also rely on data collected by other sensors (such as speedometers and gyroscopes, etc.) for auxiliary analysis.

[0069] In some alternative embodiments of the first aspect of the present invention, the comprehensive analysis and judgment of multi-source fusion of the force change data at each of the points by the overloading riding identification model to obtain a judgment result of whether there is overloading includes:

[0070] S501. Compare the force change data at each of the points with a preset threshold set to obtain an average difference, where the threshold set is set based on the point position, vehicle design parameters, and load limit parameters; determine the numerical interval where the average difference is located, and obtain a first confidence value for overloading judgment based on the numerical interval; in the present invention, the purpose of this step is to obtain the over-standard situation of the force at each of the points, and obtain a first confidence value for overloading judgment based on the over-standard situation of the force at each point. The larger the average difference, the larger the first confidence value corresponding to its numerical interval, that is, the more likely the vehicle is overloaded. In the model of the present invention, a mapping table between different numerical intervals and the first confidence value is preset.

[0071] S502. Analyze the numerical distribution of the force change data at each of the points to obtain the dispersion degree of the force change data at each of the points; obtain a second confidence value for overloading judgment based on the dispersion degree of the force change data at each of the points; in the present invention, in addition to analyzing the average difference of the force change data at the points, the numerical distribution of the force change data will also be analyzed. Generally speaking, the area covered on the vehicle seat is different for single-person riding and multi-person riding. Therefore, each of the points can be grouped in advance according to the position, and then the dispersion degree of the numerical values is judged for each group. If there are multiple groups of position data with dispersion and the numerical values are larger than those when there is no one riding at each of the points, then it is possible that there is multi-person riding. In the present invention, the second confidence value for overloading judgment obtained based on the dispersion degree is also obtained through a preset dispersion degree / second confidence value mapping table.

[0072] More specifically, in the present invention, the numerical distribution analysis of the force change data at each of the points to obtain the dispersion degree of the force change data at each of the points includes: grouping the force change data at each of the points based on the vehicle position area where they are located; for each group of the force change data, calculating the average value of the force change data; for each group of the force change data, calculating the standard deviation of the force change data from the average value; obtaining the standard deviation corresponding to each group of the force change data and performing an average operation to obtain the dispersion degree of the force change data at each of the points. In the present invention, if the force change data at each of the points in a certain vehicle position area is very dispersed (there are large fluctuations in human body movement and road condition change data during the bicycle ride), it proves that someone is sitting in that vehicle position area. By judging whether there are people sitting in multiple position areas, it is possible to determine whether there is overloading during the ride.

[0073] S504. Obtain the vehicle speed change-related data collected by other vehicle sensors, and perform acceleration feature and angular velocity feature analysis on the vehicle speed change-related data to obtain the third confidence value for overloading judgment; specifically, when performing acceleration feature analysis, statistical quantities such as the mean value, variance, and peak value of the acceleration data can be calculated. When overloaded, the mean value of the acceleration may decrease, the variance will increase, and the frequency and amplitude of the peak value will also be different. For example, when riding normally, the acceleration peak mainly appears at the moment when the rider pedals forcefully. After overloading, due to the increased load, a greater pedaling force is required, and the peak amplitude will increase, and a large negative peak will also appear when braking; analyze the characteristics of the angular velocity data such as the period, amplitude, and change rate. Overloading will change the center of gravity of the bicycle, resulting in an obvious difference in the change law of the angular velocity compared with normal riding. For example, when riding in a straight line, the fluctuation amplitude of the angular velocity of the overloaded bicycle will increase, and the period will become shorter; when turning, the change rate of the angular velocity will be faster, and after the turn, it will take longer for the vehicle body to regain balance.

[0074] In an alternative embodiment of the present invention, the obtaining of the vehicle speed change-related data collected by other vehicle sensors and the analysis of the acceleration characteristics and angular velocity characteristics of the vehicle speed change-related data to obtain a third confidence value for overloading determination include: analyzing the acceleration characteristics of the vehicle speed change-related data to obtain a first overloading matching degree of the acceleration-related statistical indicators; analyzing the angular velocity characteristics of the vehicle speed change-related data to obtain a second overloading matching degree of the angular velocity-related statistical indicators; performing an averaging operation on the first overloading matching degree and the second overloading matching degree to obtain a third confidence value for overloading determination. In the process of comparing the real-time collected acceleration and angular velocity characteristics with the characteristics of the normal riding model and the overloaded riding model, if the characteristics of the real-time data are closer to the overloaded riding model, such as the acceleration mean decreasing significantly, the variance increasing greatly, the angular velocity fluctuation amplitude and change rate increasing significantly, etc., the matching degree is the matching degree of the changes in these indicators of the vehicle speed change-related data with the corresponding indicators during overloaded riding.

[0075] S505. Perform a weighted average operation on the first confidence value, the second confidence value, and the third confidence value to obtain an overloading confidence index; compare the overloading confidence index with a preset confidence threshold to obtain a determination result of whether there is overloading. In the present invention, by obtaining confidence values from multiple aspects to determine vehicle overloading, the accuracy of overloading determination is further improved.

[0076] S600. If the determination result is overloading, control the vehicle central control to execute a preset overloading control strategy. In some alternative embodiments of step S600 of the present invention, the if the determination result is overloading, control the vehicle central control to execute a preset overloading control strategy includes: if the determination result is overloading, control the vehicle central control to repeatedly play a preset alarm voice statement, and after the number of times of playing the alarm voice reaches a preset number of times, send a power-off instruction to the vehicle power supply system. Specifically, in the present invention, once it is determined that there is overloading (riding with multiple people), the central control system immediately triggers an alarm mechanism, plays a voice reminder "It is prohibited to carry passengers while driving, the system will power off soon", and after playing the voice a certain number of times, sends a power-off instruction to the vehicle through the communication module. When single-person riding is restored, the central control system restores power supply and plays a prompt tone of "Power supply restored, have a pleasant ride".

[0077] The method for identifying overloaded riding based on a force sensor in the present invention builds a force measurement network by using force sensors at key load-bearing parts of the vehicle, which has high sensitivity and high precision, can accurately sense the weight change on the vehicle, and can automatically judge the number of riders in combination with a data processing unit and algorithm analysis, and quickly respond to execute management measures to improve management efficiency. The system can adopt a wireless communication method, without complex wiring and is easy to install; at the same time, the device supports long-term standby, reducing the operation and maintenance cost and the complexity of maintenance work. Generally speaking, the method for identifying overloaded riding based on a force sensor in the present invention has the following beneficial effects: improving the safety and stability of the vehicle and reducing safety accidents caused by multiple riders. Reducing the vehicle repair and maintenance cost and extending the service life of the vehicle. Improving the management efficiency of transportation tools such as shared electric vehicles and bicycles and promoting the standardization of urban traffic order.

[0078] See Figure 2 , the second aspect of the present invention provides a system for identifying overloaded riding based on a force sensor, and the system for identifying overloaded riding based on a force sensor includes:

[0079] An installation position acquisition module 10, configured to perform load analysis on key load-bearing parts of the vehicle to obtain a plurality of target positions;

[0080] A force measurement network building module 20, configured to set force sensors at the plurality of target positions to form a multi-point force measurement monitoring network;

[0081] A force data acquisition module 30, configured to continuously acquire force change data of each point through the multi-point force measurement monitoring network;

[0082] A data input module 40, configured to input the force change data of each point into a trained overloaded riding identification model;

[0083] A data analysis module 50, configured to perform comprehensive analysis of multi-source fusion on the force change data of each point through the overloaded riding identification model to obtain a determination result of whether it is overloaded;

[0084] An overloaded control module 60, configured to control the vehicle central control to execute a preset overloaded control strategy if the determination result is overloaded.

[0085] In some optional embodiments of the second aspect of the present invention, the installation position acquisition module includes:

[0086] A static load simulation unit, configured to perform static load simulation on key load-bearing parts of the vehicle in a static state to obtain a set of initially screened positions;

[0087] A dynamic load simulation unit for simulating dynamic loads under different driving conditions for the set of preliminary screening positions, and obtaining dynamic load change data for each of the preliminary screening positions in the set of preliminary screening positions;

[0088] A key index analysis unit for performing key index analysis on the dynamic load change data of each of the preliminary screening positions in the set of preliminary screening positions, and obtaining a data stability evaluation result for each of the preliminary screening positions in the set of preliminary screening positions;

[0089] A position determination unit for obtaining a plurality of target positions from the set of preliminary screening positions based on the data stability evaluation result.

[0090] In some alternative embodiments of the second aspect of the present invention, the key index analysis unit includes:

[0091] A load curve acquisition subunit for acquiring the dynamic load change curves of each of the preliminary screening positions in the set of preliminary screening positions;

[0092] A curve data analysis subunit for obtaining the average fluctuation amplitude, average fluctuation frequency, and average fluctuation duration of each of the preliminary screening positions from the dynamic load change curves of each of the preliminary screening positions;

[0093] A stability index acquisition subunit for performing a weighted operation on the average fluctuation amplitude, average fluctuation frequency, and average fluctuation duration of each of the preliminary screening positions to obtain a data stability index for each of the preliminary screening positions;

[0094] A sorting subunit for sorting each of the preliminary screening positions from small to large based on the data stability index to obtain a data stability evaluation result for each of the preliminary screening positions.

[0095] In some alternative embodiments of the second aspect of the present invention, the data analysis module includes:

[0096] A difference calculation unit for comparing the force change data of each of the points with a preset threshold set to obtain an average difference, wherein the threshold set is set based on point position, vehicle design parameters, and load limit parameters;

[0097] A first confidence value acquisition unit for determining the numerical interval in which the average difference is located, and obtaining a first confidence value for overloading judgment based on the numerical interval;

[0098] A numerical distribution analysis unit for performing numerical distribution analysis on the force change data of each of the points to obtain the dispersion degree of the force change data of each of the points;

[0099] The first confidence value acquisition unit is configured to obtain a second confidence value for overcrowding judgment based on the dispersion degree of the force change data of each of the points;

[0100] The third confidence value acquisition unit is configured to acquire vehicle speed change related data collected by other vehicle sensors, and perform acceleration feature and angular velocity feature analysis on the vehicle speed change related data to obtain a third confidence value for overcrowding judgment;

[0101] The summation unit is configured to perform a weighted average operation on the first confidence value, the second confidence value, and the third confidence value to obtain an overcrowding confidence index;

[0102] The confidence comparison unit is configured to compare the overcrowding confidence index with a preset confidence threshold to obtain a judgment result on whether there is overcrowding.

[0103] In some optional embodiments of the second aspect of the present invention, the numerical distribution analysis unit includes:

[0104] The data grouping subunit is configured to group the force change data of each of the points based on the vehicle position area where it is located;

[0105] The average operation subunit is configured to, for each group of the force change data, calculate the average value of the force change data;

[0106] The standard deviation calculation subunit is configured to, for each group of the force change data, calculate the standard deviation between the force change data and the data average value;

[0107] The dispersion degree acquisition subunit is configured to acquire the standard deviation corresponding to each group of the force change data and perform an average operation to obtain the dispersion degree of the force change data of each of the points.

[0108] In some optional embodiments of the second aspect of the present invention, the third confidence value acquisition unit includes:

[0109] The first overcrowding matching degree acquisition unit is configured to perform acceleration feature analysis on the vehicle speed change related data to obtain a first overcrowding matching degree of acceleration related statistical indicators;

[0110] The second overcrowding matching degree acquisition unit is configured to perform angular velocity feature analysis on the vehicle speed change related data to obtain a second overcrowding matching degree of angular velocity related statistical indicators;

[0111] The third confidence value acquisition subunit is configured to perform an average operation on the first overcrowding matching degree and the second overcrowding matching degree to obtain a third confidence value for overcrowding judgment.

[0112] In some alternative embodiments of the second aspect of the present invention, the overcrowding control module includes:

[0113] A voice alarm and power-off control unit, configured to, if the determination result is overcrowding, control the vehicle central control to repeatedly play a preset alarm voice statement, and after the number of times of playing the alarm voice reaches a preset number of times, send a power-off instruction to the vehicle power supply system.

[0114] Figure 3 FIG. 7 is a schematic structural diagram of a device for identifying overcrowded riding based on a force sensor according to an embodiment of the present invention. The device for identifying overcrowded riding based on a force sensor may vary greatly due to different configurations or performances, and may include one or more processors 70 (central processing units, CPUs) (for example, one or more processors) and a memory 80, and one or more storage media 90 (for example, one or more mass storage devices) for storing application programs or data. Among them, the memory and the storage media may be transient storage or persistent storage. The programs stored in the storage media may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the device for identifying overcrowded riding based on a force sensor. Further, the processor may be configured to communicate with the storage media and execute a series of instruction operations in the storage media on the device for identifying overcrowded riding based on a force sensor.

[0115] The device for identifying overcrowded riding based on a force sensor of the present invention may further include one or more power supplies 100, one or more wired or wireless network interfaces 110, one or more input / output interfaces 120, and / or one or more operating systems, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art can understand that Figure 3 The shown structural diagram of the device for identifying overcrowded riding based on a force sensor does not limit the device for identifying overcrowded riding based on a force sensor, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0116] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium, and when the instructions are run on a computer, the computer is caused to execute the steps of the method for identifying overcrowded riding based on a force sensor.

[0117] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system or systems and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0119] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A method for identifying overriding riding based on a force sensor, characterized in that: include: Perform load analysis on key load-bearing parts of the vehicle to obtain multiple target positions; Setting force sensors at a plurality of the target positions to form a multi-point force monitoring network; Continuously acquiring force change data of each point through the multi-point force measurement monitoring network; Inputting the force change data of each of the points into a trained overcrowded riding recognition model; The overcrowded riding identification model is used to perform a comprehensive analysis of the force change data at each of the points through multi-source fusion to obtain a determination result of whether the vehicle is overcrowded; If the determination result is overcrowding, the vehicle central control is controlled to execute a preset overcrowding control strategy.

2. The method for identifying overriding riders based on a force sensor according to claim 1, characterized in that: The load analysis of the key load-bearing parts of the vehicle is performed to obtain multiple target positions including: Perform static load simulation on key load-bearing parts of the vehicle in a static state to obtain a set of preliminary screening positions; Performing dynamic load simulation under different driving conditions on the primary screening position set to obtain dynamic load change data of each primary screening position in the primary screening position set; Performing key indicator analysis on the dynamic load change data of each of the primary screening positions in the primary screening position set to obtain a data stability evaluation result of each of the primary screening positions in the primary screening position set; A plurality of target positions are obtained from the preliminary screening position set based on the data stability evaluation result.

3. The method for identifying overriding riding based on a force sensor according to claim 2, characterized in that: The step of performing key indicator analysis on the dynamic load change data of each of the primary screening positions in the primary screening position set to obtain a data stability evaluation result of each of the primary screening positions in the primary screening position set includes: Obtaining a dynamic load variation curve of each of the primary screening positions in the primary screening position set; From the dynamic load change curve of each of the primary screening positions, obtain the average fluctuation amplitude, average fluctuation frequency and average fluctuation duration of each of the primary screening positions; Performing weight calculation on the average fluctuation amplitude, the average fluctuation frequency and the average fluctuation duration of each of the primary screening positions to obtain a data stability index of each of the primary screening positions; The various preliminary screening positions are sorted from small to large based on the data stability index to obtain data stability evaluation results for the various preliminary screening positions.

4. The method for identifying overriding riders based on a force sensor according to claim 2, characterized in that: The method of performing a comprehensive analysis and judgment of the force change data of each point by multi-source fusion through the overcrowded riding identification model to obtain a judgment result of whether the vehicle is overcrowded includes: Comparing the force change data of each of the points with a preset threshold set to obtain an average difference, wherein the threshold set is set based on the point position, vehicle design parameters and load limit parameters; Determine a numerical interval in which the average difference value is located, and obtain a first confidence value for overcrowding judgment based on the numerical interval; Analyzing the numerical distribution of the force change data at each of the points to obtain the dispersion of the force change data at each of the points; Obtaining a second confidence value for overcrowding judgment based on the dispersion of the force change data at each of the points; Acquire vehicle speed change related data collected by other vehicle sensors, and perform acceleration characteristic and angular velocity characteristic analysis on the vehicle speed change related data to obtain a third confidence value for overcrowding judgment; Performing a weighted average operation on the first confidence value, the second confidence value, and the third confidence value to obtain an overcrowding confidence index; The overcrowding confidence index is compared with a preset confidence threshold to obtain a judgment result of whether there is overcrowding.

5. The method for identifying overriding riding based on a force sensor according to claim 4, characterized in that: The numerical distribution analysis of the force change data at each of the points to obtain the dispersion of the force change data at each of the points includes: Grouping the force change data of each point based on the vehicle location area; For each group of the force change data, obtaining a data average of the force change data; For each set of the force change data, calculating the standard deviation between the force change data and the data average value; The standard deviation corresponding to each group of the force change data is obtained and averaged to obtain the dispersion of the force change data at each point.

6. The method for identifying overriding riders based on a force sensor according to claim 4, characterized in that: The acquiring of vehicle speed change related data collected by other vehicle sensors, and performing acceleration characteristic and angular velocity characteristic analysis on the vehicle speed change related data to obtain a third confidence value for overcrowding judgment includes: Performing acceleration characteristic analysis on the vehicle speed change related data to obtain a first overcrowding matching degree of acceleration related statistical indicators; Performing angular velocity characteristic analysis on the vehicle speed change related data to obtain a second overcrowding matching degree of angular velocity related statistical indicators; An average operation is performed on the first overcrowding matching degree and the second overcrowding matching degree to obtain a third confidence value of overcrowding judgment.

7. The method for identifying overriding riding based on a force sensor according to claim 1, characterized in that: If the determination result is overcrowding, controlling the vehicle central control to execute a preset overcrowding control strategy includes: If the determination result is overcrowding, the vehicle central control is controlled to repeatedly play the alarm voice of the preset sentence, and after the alarm voice is played a preset number of times, a power-off command is issued to the vehicle power supply system.

8. A system for identifying overriding riders based on force sensors, characterized in that: The system for identifying overriding riding based on a force sensor comprises: Install a position acquisition module to perform load analysis on key load-bearing parts of the vehicle and obtain multiple target positions; A force measurement network building module is used to set force measurement sensors at multiple target positions to form a multi-point force measurement monitoring network; A force data acquisition module, used to continuously acquire force change data of each point through the multi-point force measurement monitoring network; A data input module, used for inputting the force change data of each of the points into a trained overcrowded riding recognition model; A data analysis module, used for performing a comprehensive analysis of the force change data of each of the points by multi-source fusion through the overcrowded riding identification model to obtain a determination result of whether the vehicle is overcrowded; The overcrowding control module is used to control the vehicle central control to execute a preset overcrowding control strategy if the determination result is overcrowding.

9. A device for identifying overriding riders based on a force sensor, characterized in that: The device for identifying overriding riders based on a force sensor comprises: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via a line; The at least one processor calls the instructions in the memory to enable the device for identifying excess riders riding based on a force sensor to perform the method for identifying excess riders riding based on a force sensor according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying excess riders based on a force sensor as described in any one of claims 1 to 7 is implemented.

Images