Three-in-one test method and system for electric scooter

Abstract

The invention provides a three-in-one test method and system for an electric scooter, and relates to the technical field of scooter testing, and the method comprises the steps: obtaining initial target test data of a target core part, carrying out the preprocessing of the target test data, and obtaining a first stability index of the target core part; performing compensation adjustment on the first stability index to generate a second stability index; linkage test data of the associated parts are obtained, and a cooperative influence index is generated according to the linkage test data; adjusting a second stability index according to the collaborative influence index to generate a target stability index; inputting the target stability index into a target test evaluation model, and determining whether a target core component corresponding to the electric scooter is abnormal or not; the three-in-one test efficiency and accuracy of the electric scooter are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of scooter testing technology, specifically a three-in-one testing method and system for electric scooters. Background Technology

[0002] With the surge in demand for short-distance travel, electric scooters, with their convenience and flexibility, have become an important tool for urban commuting and short-distance transportation, and their market share continues to climb. However, the safety performance of electric scooters is directly related to the personal safety of users, and the stability and reliability of their core components are key to ensuring product quality.

[0003] Existing technologies for testing electric scooters often involve testing different tasks separately. For example, tests on the brakes, throttle, and lights of an electric scooter are usually conducted separately, which is inefficient when dealing with large batches of products. Furthermore, the testing environment for electric scooters is often limited to production warehouses, which is too monotonous and does not reflect the actual riding performance of electric scooters in different environments, leading to decreased testing accuracy. Therefore, this paper provides a three-in-one testing method and system for electric scooters. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, the purpose of this invention is to provide a three-in-one testing method and system for electric scooters.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a three-in-one testing method for electric scooters, the method comprising: Obtain initial target test data for the target core component, preprocess the target test data, and obtain the first stability index of the target core component; The first stability index is adjusted to generate the second stability index; Obtain the linkage test data of related components, and generate a synergistic impact index based on the linkage test data; The second stability index is adjusted based on the synergistic influence index to generate a target stability index; the target stability index is then input into the target test and evaluation model to determine whether there are any abnormalities in the target core components corresponding to the electric scooter.

[0006] Furthermore, the process of obtaining initial target test data includes: The electric scooter undergoes model verification, and initial target test data is collected for the corresponding core components of the verified electric scooter using a data acquisition unit or an external data acquisition device.

[0007] Furthermore, the process of preprocessing the initial target test data to obtain the first stability index includes: The initial target test data is input into the data preprocessing model, and then the preprocessed standard initial target test data is output; based on the initial target test data, the corresponding first stability index is obtained.

[0008] Furthermore, the process of compensating for the first stability index includes: Obtain the corresponding test environment number, match the number with the number in the environment database to obtain the corresponding test environment; input the test task corresponding to the electric scooter into the test environment, and compensate and adjust the first stability index.

[0009] Furthermore, a target stability index is generated based on the synergistic impact index, the first stability index, and the second stability index.

[0010] Furthermore, the process of generating the target test evaluation model includes: Obtain the first stability index, second stability index, and synergistic impact index for several historical data collection periods, and group and label them as follows: It is a natural number; Will The first stability index, second stability index, synergistic effect index, and standard stability index of the historical data collection period were used as sample data, and Less than The natural numbers are used to obtain the mean of the sample data, which is denoted as the sample set; the first stability index, the second stability index, the synergistic influence index, and the standard stability index of the remaining historical collection periods are used as the test set; and a training sample set is formed based on the sample set and the test set. The training sample set is then input into the initial restoration model, and the initial restoration model after training is denoted as the target test evaluation model.

[0011] Furthermore, multiple loss functions at different levels are established for joint calculation to constrain the target testing and evaluation model learning from different perspectives.

[0012] A second aspect of the present invention also provides a three-in-one testing system for electric scooters, comprising: a data acquisition module, a data preprocessing module, an intelligent analysis module, and a data storage module; The data acquisition module is used to collect the initial target test data of the target core component of the electric scooter under test, as well as the linkage test data of the related components that work together with the target core component within a preset time period. The data preprocessing module is used to preprocess the initial target test data to obtain a first stability index of the target core component; to compensate and adjust the first stability index to generate a second stability index; to generate a synergistic impact index of the corresponding target core component working together based on the linkage test data; and to adjust the second stability index based on the synergistic impact index to generate a target stability index. The data intelligence analysis module constructs a target test and evaluation model, inputs the target stability index into the target test and evaluation model, and determines whether there are any abnormalities in the target core components corresponding to the electric scooter. The data storage module is used to store the corresponding test environment and the corresponding test results.

[0013] Compared with the prior art, the beneficial effects of the present invention are: 1. Through multi-dimensional test data processing and model training, accurate detection of core components of electric scooters was achieved. From acquiring initial target test data, to obtaining the first stability index through preprocessing, then compensating and adjusting for the test environment to generate the second stability index, and finally considering the synergistic influence of related components to obtain the target stability index, the entire process is progressive, comprehensively considering the performance of the core component itself, environmental factors, and the influence of collaborating components. Simultaneously, the target test evaluation model includes multiple extraction branches, capable of accurately extracting various feature data. After training and optimization using historical data, it can accurately determine whether core components are abnormal, significantly reducing the false positive rate. This provides a reliable basis for the quality inspection of core components of electric scooters, helping to detect potential faults in advance and ensuring the safety and stability of electric scooters during use.

[0014] 2. This application includes a model verification step to ensure the relevance of data collection, and data can be flexibly acquired through the data acquisition unit or external devices. Regarding the testing environment, the corresponding testing environment can be quickly invoked through number matching, facilitating testing of the task under test in different environments and enhancing the adaptability of the test. Furthermore, the data preprocessing model can quickly transform initial data into standard data, and the target test evaluation model, after being trained on samples, can efficiently evaluate the target stability index. The overall process is standardized and efficient, reducing tedious manual testing steps and saving testing time and labor costs. It can be widely applied to testing work in various scenarios such as electric scooter production and maintenance. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0016] Figure 1 This is a schematic diagram illustrating the steps of a three-in-one testing method for electric scooters.

[0017] Figure 2 This is a schematic diagram of a three-in-one testing system for electric scooters. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] This invention also provides a three-in-one testing method for electric scooters. This method can be applied to testing scenarios for electric scooters, especially for testing the brakes, throttle, and lights of electric scooters under different environmental conditions. To facilitate understanding of this embodiment, a detailed description of the three-in-one testing method for electric scooters disclosed in this invention will be provided first, such as... Figure 1 As shown, the method includes the following specific steps: S202, according to the test task of the electric scooter, obtain the initial target test data (brake voltage, throttle voltage, headlight sensitivity value and photosensitive voltage) of the corresponding target core components (brake, throttle, headlight) of the electric scooter, preprocess the target test data, and obtain the first stability index of the target core components. Optionally, in the embodiments of this application, the test tasks of the electric scooter include, but are not limited to, brake test, throttle test, headlight test or any other related test, that is, all test tasks in the entire process of testing the electric scooter.

[0021] It should be noted that the test tasks for the aforementioned electric scooters are selected based on actual needs. They can be standard test tasks directly from the manufacturer or customized test tasks based on user requirements. The specific selection of test tasks is not limited to test subjects of the same model of electric scooter. For example, different types of electric scooters, electric bicycles, and electric vehicles are also included, and this application does not limit this. In addition, there are various possibilities for the test time, test method, and test location of the test tasks, which are also unrestricted.

[0022] Furthermore, the target core components include, but are not limited to, vehicle brakes, throttle, and lights.

[0023] Optionally, in this embodiment of the application, the specific process of obtaining the initial target test data of the corresponding target core components (brakes, throttle, lights) of the electric scooter includes: The PID, MAC, DID, SN, LCDSN, OOB, AES128, software version, hardware version, and UUID of the electric scooter are verified, and then the initial target test data of the target core component of the electric scooter that has passed the verification are tested.

[0024] It should be noted that, in this embodiment, the aforementioned initial target test data includes, but is not limited to, brake voltage, throttle voltage, headlight sensitivity value, and photosensitive voltage.

[0025] The corresponding data acquisition unit collects the vehicle brake voltage, throttle voltage, vehicle light light sensitivity value, and photosensitive voltage within a preset time period; or the corresponding data is collected through an external data acquisition device, which is not limited in this application.

[0026] Optionally, in this embodiment of the application, the specific process of preprocessing the initial target test data to obtain the first stability index of the target core component includes: The initial target test data is input into the data preprocessing model, and then the preprocessed standard initial target test data is output. It should be noted that, in this embodiment, the above data preprocessing model includes, but is not limited to, algorithms such as missing value handling, outlier detection, and Z-score normalization.

[0027] Furthermore, in this embodiment, the first stability index includes the brake voltage stability index, the throttle voltage stability index, the headlight light sensitivity value stability index, and the photosensitive voltage stability index; the first stability index in other test tasks is not limited in this application.

[0028] Specifically, the aforementioned first stability index can be determined according to the following formula: ;in, Indicates the first stability index; This represents the stability coefficient, which is set by the actual testers. This is the corresponding initial target test data; This represents the average value of the initial target test data.

[0029] Furthermore, the first stability index The calculation formula is a universal formula that is applicable to the calculation of brake voltage stability index, throttle voltage stability index, headlight light sensitivity stability index, and photosensitive voltage stability index.

[0030] S204, preset the corresponding test environment, input the test task corresponding to the electric scooter into the test environment, compensate and adjust the first stability index (such as low temperature compensation for brake voltage fluctuation, high humidity correction for headlight current threshold), and generate the second stability index. It should be noted that the test task usually refers to the corresponding test process set by the tester according to their actual test needs, and the test task includes the test scenario triggering conditions required for the electric scooter under test. Specifically, in this embodiment, the test scenario triggering conditions may be based on the actual scene elements of the electric scooter. In this embodiment, when the test scenario triggering conditions are received, the test task is identified, and then the test environment that meets the test scenario triggering conditions is determined. It should be further noted that the test environment includes, but is not limited to, rainy days, sunny days, or humidity, temperature, etc.

[0031] Optionally, in this embodiment of the application, the above-mentioned test environment refers to environmental data collected by the data acquisition and recording system from various sites and corresponding environments. The environmental data is input into the simulation software to construct the corresponding test environment. The environmental data has characteristic data of the corresponding test environment. The environmental data can also be used as an evaluation index for constructing test cases. It should be noted that the test environment is recorded and stored in the environment library, and a corresponding test environment number is generated; the test environments in the environment library can be directly used for simulation testing of electric scooters; and the environment library contains a variety of venues and corresponding test cases.

[0032] Furthermore, in some embodiments, the data sources in the environment database also include actual traffic signs, temporary traffic obstacles, road vehicles, pedestrians, bicycles, and e-scooters, which interact with the e-scooter under test to test the impact of the e-scooter's braking, throttle, and light states under actual traffic conditions. It is necessary to simultaneously reference the e-scooter's PID, MAC, DID, SN, LCDSN, OOB, AES128, software version, hardware version, UUID, and the test task. In this case, test cases for e-scooters that meet the test task can be automatically determined and extracted directly.

[0033] Optionally, in this embodiment of the application, the specific process of inputting the test task corresponding to the electric scooter into the test environment and compensating for the first stability index includes: Optionally, in this embodiment of the application, the test task corresponding to the electric scooter is input into the test environment. It is necessary to obtain the number of the corresponding test environment in advance, and match the number with the number in the environment database to obtain the corresponding test environment. The method of obtaining the number of the corresponding test environment includes, but is not limited to, manual input.

[0034] Specifically, the test task corresponding to the electric scooter is input into the test environment, and the first stability index can be adjusted and compensated according to the following formula: ;in, This is represented as the second stability index; It is an environmental compensation factor.

[0035] It should be noted that, in this embodiment, the second stability index is the data after environmental compensation for the brake voltage stability index, throttle voltage stability index, headlight light sensitivity value stability index, and photosensitive voltage stability index; the environmental compensation factors include, but are not limited to, the influence of temperature, humidity, and the degree of slipperiness of the ground, which can be set by the tester by referring to a table, and are not limited in this application.

[0036] S206, Obtain linkage test data (such as controller response delay and power output ripple) of related components (controller, power module) that work in conjunction with the target core component within a preset time period, and generate a corresponding linkage impact index of the target core component working in conjunction with the target core component based on the linkage test data; Optionally, in the embodiments of this application, the aforementioned associated components include, but are not limited to, a controller module and a power module; It should be noted that the preset duration refers to the time period between the start and end of the collaborative operation of the target core components of the electric scooter; Furthermore, the coordinated operation of the target core components includes the coordination between the brakes and lights, and between the brakes and the throttle. For example, braking coordinates with the lights; most electric scooters automatically activate the brake lights when braking. The principle is that after the braking action is detected by sensors, the controller receives the signal and simultaneously activates the brake light circuit to alert pedestrians or vehicles behind. Some models may adjust the brake light brightness according to the braking force to improve driving safety. When the electric scooter is in motion (i.e., the throttle outputs an acceleration signal), if braking is triggered, the controller will prioritize the braking signal and immediately cut off the motor's power output (regardless of whether the throttle is still rotating), avoiding power conflicts or reduced braking efficiency caused by accelerating and braking simultaneously, and ensuring the stability of the deceleration process.

[0037] Optionally, in this embodiment of the application, the linkage test data within a corresponding preset time period is obtained through the controller; It should be noted that the linkage test data includes, but is not limited to, controller response delay and power output ripple; based on the linkage test data, a synergistic impact index for the coordinated operation of the corresponding target core components is generated.

[0038] S208, Adjust the second stability index according to the synergistic influence index to generate a target stability index; Input the target stability index into the target test and evaluation model to determine whether there is an anomaly in the target core component corresponding to the electric scooter; wherein, the target test and evaluation model is obtained by training an initial restoration model using the first stability index, the second stability index, and the synergistic influence index, and the initial restoration model includes a brake voltage extraction branch, a throttle voltage extraction branch, a photosensitivity value extraction branch, and a photosensitivity voltage extraction branch; The brake voltage extraction branch is used to extract the brake voltage feature data of the first stability index and the second stability index; The throttle voltage extraction branch is used to extract the throttle voltage feature data of the first stability index and the second stability index; The photosensitivity value extraction branch is used to extract the photosensitivity value feature data of the first stability index and the second stability index; The photosensitivity voltage extraction branch is used to extract the photosensitivity voltage feature data of the first stability index and the second stability index.

[0039] Optionally, in this embodiment, the aforementioned target testing and evaluation model refers to an optimized deep learning model capable of effectively obtaining a standard stability index from the first stability index, the second stability index, and the co-influence index. The deep learning model used in the target testing and evaluation model includes, but is not limited to, convolutional neural networks (CNN), generative adversarial networks (GAN), or self-supervised learning frameworks. Based on the selected deep learning model, an initial reconstruction model is constructed, and the initial reconstruction model is trained to obtain the target testing and evaluation model. By judging the relationship between the standard stability index and the target stability index, it is determined whether there is an anomaly in the target core component corresponding to the electric scooter.

[0040] This application selects a convolutional neural network as the basic model architecture to construct an initial reconstruction model. By training the initial reconstruction model, a target test evaluation model is obtained.

[0041] Based on this, the embodiments of this application use the deep prior information of a pre-trained large model. To make more reasonable use of the deep prior information, brake voltage extraction branch, throttle voltage extraction branch, photosensitive value extraction branch, and photosensitive voltage extraction branch are designed to estimate the initial target test data. Utilizing the relationship between the deep prior and the initial target test data, the co-influence index, the first stability index, and the second stability index, a first loss function and a second loss function are designed to train the initial restoration model, thereby obtaining the target test evaluation model. Specifically, the training process of the initial restoration model includes, but is not limited to:

[0042] S1, obtain the first stability index, the second stability index, and the synergistic influence index of several historical collection periods; The first stability index, second stability index, synergistic effect index, and standard stability index of several historical data collection periods are grouped and labeled, denoted as follows: It is a natural number; Will The first stability index, second stability index, synergistic effect index, and standard stability index of the historical data collection period were used as sample data, and Less than The natural numbers are used to obtain the mean of the sample data, which is denoted as the sample set; the first stability index, the second stability index, the synergistic influence index, and the standard stability index of the remaining historical collection periods are used as the test set; and a training sample set is formed based on the sample set and the test set. S2, input the training sample set into the initial restoration model, and the corresponding first stability index and second stability index are transmitted to the brake voltage extraction branch, throttle voltage extraction branch, photosensitive value extraction branch and photosensitive voltage extraction branch respectively, to obtain the corresponding brake voltage feature data, throttle voltage feature data, photosensitive value feature data and photosensitive voltage feature data respectively; It should be noted that after training, the standard stability index obtained from these four components should be consistent with the original target stability index during the actual use of the target test evaluation model.

[0043] S3, the components extracted from the brake voltage extraction branch, throttle voltage extraction branch, photosensitive value extraction branch and photosensitive voltage extraction branch are adjusted twice based on the synergistic influence index to generate the final standard stability index, and the initial restoration model after training is recorded as the target test evaluation model.

[0044] Furthermore, the aforementioned brake voltage extraction branch can be used to perform brake voltage extraction operations on the first stability index and the second stability index to obtain corresponding brake voltage feature data; the throttle voltage extraction branch can perform throttle voltage extraction operations on the first stability index and the second stability index to obtain corresponding throttle voltage feature data; the photosensitivity value extraction branch can perform photosensitivity value extraction operations on the first stability index and the second stability index to obtain corresponding photosensitivity value feature data; and the photosensitivity voltage extraction branch can perform photosensitivity voltage extraction operations on the first stability index and the second stability index to obtain corresponding photosensitivity voltage feature data.

[0045] Among them, the aforementioned brake voltage extraction branch, throttle voltage extraction branch, photosensitive value extraction branch, and photosensitive voltage extraction branch can all be composed of simple convolutional layers, Norm, and sigmoid activation functions; this allows for more flexible adaptation to different testing requirements and enhances the robustness and generalization ability of the target testing and evaluation model.

[0046] Specifically, adjustments can be made according to the following formula, based on the synergistic impact index, the first stability index, and the second stability index: ;in, It is a synergistic influence index, and is not equal to 0; The target stability index.

[0047] It should also be noted that, in the embodiments of this application, multiple loss functions at different levels can be established for joint calculation to constrain model learning from different perspectives, thereby enabling the finally trained model to have high accuracy. Specifically: S1, based on the first stability index, the second stability index, and the synergistic influence index, designs a first loss function to achieve this constraint. Furthermore, considering the need to avoid falling into degeneracy, a further approach can be adopted... The function, i.e., the gradient stopping operation, is expressed by the following formula: ;in, Represents the first loss function; S2, based on the corresponding initial target test data and the second stability exponent, and considering the gradient consistency loss, a second loss function is designed to implement this constraint, as shown in the following formula: ;in, This represents the second loss function; This is the corresponding initial target test data.

[0048] Based on the first loss function and the second loss function, the target loss function is determined as follows: .

[0049] Furthermore, when the target loss function meets the preset loss value output condition, the initial restoration model is successfully trained. The preset loss value output condition here refers to the value of the target loss function reaching or falling below a pre-set threshold or standard during the model training process. This usually means that the model training has converged and the model parameters can effectively process the input data and achieve the expected performance indicators, such as at least one of the following: loss function threshold, loss function change rate, validation set performance, number of iterations, or training time.

[0050] Optionally, in the embodiments of this application, the aforementioned target loss function refers to a set of functions used to quantify and guide the accuracy of judging the relationship between the standard stability index and the target stability index during model training, including but not limited to the first loss function and the second loss function, which work together to optimize the authenticity of the test results.

[0051] In one exemplary embodiment, rainy day, temperature Taking conditions such as slippery road surfaces as an example, firstly, the control system obtains the corresponding test environment from the environment library, and according to the corresponding test task, it gradually obtains the first stability index, the second stability index, the collaborative influence index, and the target stability index. The target stability index is then input into the target test evaluation model, and processed directly by the brake voltage extraction branch, the throttle voltage extraction branch, the photosensitive value extraction branch, and the photosensitive voltage extraction branch, and outputs the test results of the corresponding target core components.

[0052] In other words, in practical applications, the target test and evaluation model may retain only one of the above-mentioned brake voltage extraction branch, throttle voltage extraction branch, photosensitive value extraction branch, and photosensitive voltage extraction branch, and this application does not impose any restrictions on this.

[0053] Specifically, during the training phase of the initial restoration model, the brake voltage extraction branch, throttle voltage extraction branch, photosensitive value extraction branch, and photosensitive voltage extraction branch are used to establish interactive feedback with the target output branch. Through different paths and loss functions, the initial restoration model learns how to judge the target stability index without explicit supervision signals.

[0054] Therefore, in practical applications, the target test evaluation model includes optional branches for extracting brake voltage, throttle voltage, photosensitive value, and photosensitive voltage. This optimizes resource utilization, reduces computational latency, and makes the target restoration model more suitable for real-time processing or resource-constrained equipment.

[0055] In an exemplary embodiment, the test environment is set by retrieving the snowy test environment numbered "6" from the environment library. Its characteristic data are: temperature: -3℃; humidity: 85%; road surface slip coefficient: 0.8 (for icy and snowy roads); environmental compensation factor: 1.35 (due to the increased viscosity of the brake hydraulic fluid, changes in the throttle circuit resistance, and frost formation on the headlight lens affecting photosensitive sensitivity at low temperatures, targeted compensation is required). Simultaneously, snowy scene-related data is loaded into the environment library: pedestrian walking speed reduced by 20%, road surface friction reduced by 30%, and headlight transmittance reduced by 15%, among other interactive parameters. For device and model verification, the electric scooter under test is authenticated by reading its PID (product identification code), SN (serial number), hardware version (V2.3), and UUID (unique device identifier) ​​to confirm that the model supports low-temperature and slippery road surface testing (some lower-end models may not be compatible with snowy conditions). After successful verification, the data acquisition unit (built-in voltage sensor, photoresistor, and temperature probe) and external devices (road surface friction sensor and controller response timer) are activated.

[0056] Acquire initial target test data and calculate the first stability index; Data acquisition: in a standard indoor environment ( Under dry conditions, collect preset data. Key component data within minutes: Brake voltage: During multiple braking operations, the voltage fluctuation range is... (common (Group data) Throttle voltage: When the throttle is turned, the voltage changes from... (Stationary) Linear rise to (Full speed), recording Group data: Vehicle headlight sensitivity value: When the vehicle headlights are on, the ambient light value detected by the photoresistor is... (Base values ​​before snow simulation) Photosensitive voltage: The voltage output corresponding to the photosensitive value is Data preprocessing: Outlier removal is performed using a data preprocessing model (e.g., a sudden change in braking voltage). (If the sensor is determined to have poor contact and is discarded), and Z-score standardization is performed to obtain standard data. The first stability index (stability coefficient) is then calculated. (Set by testers): Brake voltage stability index: (average value) , → ); Throttle voltage stability index: (average value) , → ); Headlight sensitivity stability index: (average value) , → Photosensitive voltage stability index: (average value) , → ).

[0057] Environmental compensation generates a second stability index. The test task ("snowy weather brake-throttle-light coordination test") is input into the snowy weather test environment, based on the environmental compensation factor ( Adjust the first stability index; calculate the second stability index according to the formula. ; ; ; .

[0058] It should be noted that the compensated data reflects the impact of low temperatures in snowy weather on circuit stability and the damping of mechanical components. For example, the increase in the brake voltage stability index indicates that voltage fluctuations are more significant at low temperatures.

[0059] Calculate the synergistic impact index and collect preset data. Interlocking data of related components within minutes: Controller response delay: The average delay from the issuance of the brake signal to the activation of the brake lights is... (Standard environment is) (Due to low temperatures in snowy weather, circuit delays increase); power output ripple: battery in... The lower output voltage ripple factor is (Standard environment is) Based on the linkage data, and combined with the calculation of the collaborative relationship of core components: Weighting of brake and headlight coordination: (The headlights should illuminate simultaneously as a warning when braking); Brake and throttle coordination weights: (The throttle must be disconnected immediately when braking to avoid power conflict). Weighting of headlight and power supply coordination: (Power supply ripple affects the voltage stability of vehicle lights at low temperatures) .

[0060] Generate and evaluate the target stability index according to the target stability index calculation formula; ; ; .

[0061] The target stability index is input into the trained target test evaluation model, and the model then... Extraction branch processing: Brake voltage branch: Extract brake voltage fluctuation characteristics in snowy weather and determine whether it exceeds a threshold (the threshold is...). ); Throttle voltage branch: Analysis of the linearity deviation of the throttle at low temperatures; Photosensitive value branch: Evaluates the photosensitive adjustment capability of vehicle lights under strong light reflection in snowy weather; Photosensitive voltage branch: Verify whether the headlight voltage is excessively affected by power supply ripple; Model output: Target stability index ( ) > Standard stability index ( The results showed that the core components were normal in the snowy environment.

[0062] like Figure 2 As shown, a three-in-one testing system for electric scooters includes: a data acquisition module, a data preprocessing module, an intelligent analysis module, and a data storage module; The data acquisition module is used for the initial target test data of the core component of the electric scooter under test, as well as the linkage test data of the related components that work together with the core component within a preset time period. The data preprocessing module is used to preprocess the initial target test data to obtain the first stability index of the target core component; input the test task corresponding to the electric scooter into the test environment, compensate and adjust the first stability index to generate the second stability index; generate the synergistic impact index of the corresponding target core component working together based on the linkage test data; adjust the second stability index based on the synergistic impact index to generate the target stability index.

[0063] The data intelligence analysis module is used to input the target stability index into the target test and evaluation model to determine whether there are any abnormalities in the target core components of the electric scooter. The data storage module is used to store the corresponding test environment and the corresponding test results.

[0064] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0065] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0066] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the 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 to cause one or more electronic devices to execute all or part of the steps of the methods described in the various embodiments of this application.

[0067] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed application can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0069] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0070] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0071] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A three-in-one testing method for electric scooters, characterized in that, The method includes: Obtain initial target test data for the target core component, preprocess the target test data, and obtain the first stability index of the target core component; The first stability index is adjusted to generate the second stability index; Obtain the linkage test data of related components, and generate a synergistic impact index based on the linkage test data; The second stability index is adjusted based on the synergistic influence index to generate a target stability index; the target stability index is then input into the target test and evaluation model to determine whether there are any abnormalities in the target core components corresponding to the electric scooter.

2. The method according to claim 1, characterized in that, The process of obtaining initial target test data based on the test task of the electric scooter includes: The electric scooter undergoes model verification, and initial target test data is collected for the corresponding core components of the verified electric scooter using a data acquisition unit or an external data acquisition device.

3. The method according to claim 2, characterized in that, The process of preprocessing the initial target test data to obtain the first stability index includes: The initial target test data is input into the data preprocessing model, and then the preprocessed standard initial target test data is output; based on the initial target test data, the corresponding first stability index is obtained.

4. The method according to claim 3, characterized in that, The process of compensating for the first stability index includes: Obtain the corresponding test environment number, match the number with the number in the environment database to obtain the corresponding test environment; input the test task corresponding to the electric scooter into the test environment, and compensate and adjust the first stability index.

5. The method according to claim 4, characterized in that, The target stability index is generated based on the synergistic impact index, the first stability index, and the second stability index.

6. The method according to claim 5, characterized in that, The process of generating the target test evaluation model includes: Obtain the first stability index, second stability index, and synergistic impact index for several historical data collection periods, and group and label them as follows: It is a natural number; Will The first stability index, second stability index, synergistic effect index, and standard stability index of the historical data collection period were used as sample data, and Less than The natural numbers are used to obtain the mean of the sample data, which is denoted as the sample set; the first stability index, the second stability index, the synergistic influence index, and the standard stability index of the remaining historical collection periods are used as the test set; and a training sample set is formed based on the sample set and the test set. The training sample set is then input into the initial restoration model, and the initial restoration model after training is denoted as the target test evaluation model.

7. The method according to claim 6, characterized in that, Multiple loss functions at different levels are established and jointly calculated to constrain the target testing and evaluation model learning from different perspectives.

8. A three-in-one testing system for electric scooters, implementing the method described in any one of claims 1 to 7, characterized in that, include: Data acquisition module, data preprocessing module, intelligent analysis module, and data storage module; The data acquisition module is used to collect the initial target test data of the target core component of the electric scooter under test, as well as the linkage test data of the related components that work together with the target core component within a preset time period. The data preprocessing module is used to preprocess the initial target test data to obtain the first stability index of the target core component; The first stability index is compensated and adjusted to generate a second stability index; based on the linkage test data, a synergistic impact index for the coordinated operation of the corresponding target core components is generated; the second stability index is adjusted based on the synergistic impact index to generate a target stability index. The data intelligence analysis module constructs a target test and evaluation model, inputs the target stability index into the target test and evaluation model, and determines whether there are any abnormalities in the target core components corresponding to the electric scooter. The data storage module is used to store the corresponding test environment and the corresponding test results.

Images