An abnormality detection system for automobile windows

Abstract

The present invention relates to the field of data processing technology and discloses an abnormality detection system for automobile windows. The system obtains the tire internal volume of a target vehicle and collects, at a fixed time interval u, the following: current data and operating status of N window motors, tire pressure data and temperature data of M tires, and the damping coefficient of a suspension system; based on the tire internal volume and temperature data, the tire pressure data of each tire at a corresponding moment is uniformly dimensioned to obtain standard tire pressure data for each tire; based on the operating status of the window motor, the current data of the N window motors is screened to obtain first screened data and second screened data; based on the first screened data and the second screened data, a current prediction model is constructed; and within a second preset time period, the current data at each moment is subjected to abnormality detection based on the predicted current data output by the current prediction model to obtain an abnormality test result.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and more particularly to an abnormality detection system for automobile windows. Background Art

[0002] Existing automotive window lift management is based on motor drive. Specifically, a current parameter threshold is set. When the motor's real-time current parameter exceeds the threshold, it typically indicates that the window's movement is actively obstructed (for example, by a person or object, potentially causing a pinching problem). At this point, the window stops moving. This existing technology has the following issues: When the vehicle is jolted, the window also jolts, causing the motor's real-time parameters to change, resulting in the window's abnormal stoppage or lowering. Summary of the Invention

[0003] The present invention provides an abnormality detection system for automobile windows, which solves the technical problems raised in the background technology.

[0004] The present invention provides a vehicle window abnormality detection system, comprising:

[0005] The data acquisition module is used to collect data in a first preset time period. Get the target vehicle's tire volume and calculate it at fixed time intervals. Collect: current data and operating status of N window motors, tire pressure and temperature data of M tires, and the damping coefficient of the suspension system;

[0006] A dimension unification module is used to unify the tire pressure data of each tire at the corresponding moment based on the tire volume and temperature data to obtain the standard tire pressure data of each tire;

[0007] a data screening module, configured to screen the current data of the N window motors based on the operating status of the window motors to obtain first screened data and second screened data;

[0008] a model building module for building a current prediction model based on the first screening data and the second screening data; the output of the current prediction model represents predicted current data of the window motor in an operating state within a second preset time period; wherein the operating state includes a rising state and a falling state;

[0009] The abnormality detection module is used to perform abnormality detection on the current data at each moment within a second preset time period based on the predicted current data output by the current prediction model to obtain abnormality detection results; wherein the abnormality detection results include: normal current state and abnormal current state.

[0010] Furthermore, data is collected at fixed time intervals, including:

[0011] In a first preset time period, if it is determined that at least one of the N window motors is in operation at the i-th moment, current data of the window motor corresponding to the i-th moment, tire pressure data and temperature data of the M tires, and a damping coefficient of the suspension system are collected. , Is a positive integer.

[0012] Furthermore, unified dimensional processing includes:

[0013] Set dimensionless temperature ;

[0014] Based on the tire volume and the temperature data of the mth tire at the i-th moment, the tire pressure data of the mth tire at the i-th moment is converted to dimensionless temperature The standard tire pressure data is calculated as follows:

[0015] ;

[0016] in, represents the standard tire pressure data of the mth tire at the i-th moment, represents the tire pressure data of the mth tire at the i-th moment, represents dimensionless temperature, represents the temperature data of the mth tire at the i-th moment, Indicates the adjustment weight, Indicates the tire's internal volume. , represents the natural base, , Is a positive integer.

[0017] Furthermore, obtaining the first screening data and the second screening data includes:

[0018] The operating states include an ascending state, a descending state, and a standby state. According to the operating states of the N window motors at the i-th moment, the current data of the window motors with the same operating state are divided into the same type, and the current data of the ascending window, the current data of the descending window, and the current data of the standby window at the i-th moment are obtained. The current data of the ascending window is used as the first screening data, and the current data of the descending window is used as the second screening data.

[0019] Furthermore, the current prediction model includes a rising prediction unit and a falling prediction unit;

[0020] Obtain the Euclidean distance between each window motor and each tire in the target vehicle and construct training data. The training data includes: sample data and sample labels, as follows:

[0021] Initial sample data is constructed. Each element of the initial sample data is constructed based on the standard tire pressure data of M tires at the i-th moment and the i+1-th moment. For the m-th element m(n) in the initial sample data, its calculation and determination process is as follows:

[0022] Calculate the absolute value of the difference between the standard tire pressure data of the mth tire at the i-th moment and the i+1-th moment; multiply the absolute value by the Euclidean distance between the n-th window motor and the m-th tire to obtain the m-th element in the initial sample data;

[0023] Based on the damping coefficient of the suspension system at the i-th moment, the initial sample data is processed:

[0024] ;

[0025] in, represents the mth element in the standard sample data, represents the damping coefficient of the suspension system at the i-th moment, represents the damping coefficient weight;

[0026] The standard sample data is normalized and used as the sample data of the current prediction model, and the current data of the nth window motor at the i-th moment is normalized and used as the sample label.

[0027] Furthermore, the rising prediction unit includes: if the current data of the nth window motor at the i-th moment is the first screening data, then the rising prediction unit is trained based on the corresponding sample data and sample labels; wherein the rising prediction unit is constructed based on a one-dimensional convolutional neural network.

[0028] Furthermore, the descent prediction unit includes: if the current data of the nth window motor at the i-th moment is the second screening data, then the descent prediction unit is trained based on the corresponding sample data and sample labels; wherein the descent prediction unit is constructed based on a one-dimensional convolutional neural network.

[0029] Furthermore, the loss functions of the ascending prediction unit and the descending prediction unit are both mean square error loss functions.

[0030] Furthermore, an abnormality detection result is obtained, including: obtaining the current data and operating status of the nth window motor of the target vehicle at the kth moment within the second preset time period, the tire pressure data and temperature data of M tires, and the damping coefficient of the suspension system; if the operating status of the nth window motor is a rising state or a falling state, constructing an input sample at the kth moment; wherein, the input sample is constructed in the same manner as the sample data of the current prediction model; based on the operating status of the nth window motor, the input sample is input into the rising prediction unit or the falling prediction unit to obtain the predicted current data output by the current prediction model at the kth moment; if the absolute difference between the predicted current data and the current data of the nth window motor at the kth moment is ≤ the preset threshold, the current state is normal, otherwise the current state is abnormal.

[0031] The beneficial effect of this invention lies in the following: by comprehensively collecting multi-dimensional data such as window motor current, operating status, tire pressure and temperature, and suspension system damping coefficient, and utilizing unified dimensional processing and a current prediction model built using a one-dimensional convolutional neural network, it achieves accurate prediction and detection of abnormal window conditions. Compared with traditional single-threshold detection methods, this invention effectively overcomes the problem of misjudgment of current fluctuations caused by vehicle turbulence, significantly improving window operation safety and detection accuracy, thereby avoiding the risk of accidental stops or injuries caused by misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a module diagram of an abnormality detection system for automobile windows of the present invention. DETAILED DESCRIPTION

[0033] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0034] like Figure 1 As shown, a vehicle window abnormality detection system includes:

[0035] The data acquisition module is used to collect data in a first preset time period. Get the target vehicle's tire volume and calculate it at fixed time intervals. Collect: current data and operating status of N window motors, tire pressure and temperature data of M tires, and the damping coefficient of the suspension system;

[0036] A dimension unification module is used to unify the tire pressure data of each tire at the corresponding moment based on the tire volume and temperature data to obtain the standard tire pressure data of each tire;

[0037] a data screening module, configured to screen the current data of the N window motors based on the operating status of the window motors to obtain first screened data and second screened data;

[0038] a model building module for building a current prediction model based on the first screening data and the second screening data; the output of the current prediction model represents predicted current data of the window motor in an operating state within a second preset time period; wherein the operating state includes a rising state and a falling state;

[0039] The abnormality detection module is used to perform abnormality detection on the current data at each moment within a second preset time period based on the predicted current data output by the current prediction model to obtain abnormality detection results; wherein the abnormality detection results include: normal current state and abnormal current state.

[0040] It should be noted that the tire pressure data, temperature data, and the damping coefficient of the suspension system are all obtained based on the vehicle's existing sensors. When a car encounters a bump, it is first reflected in the car's tire pressure data. Secondly, it is filtered by the car's active suspension system and finally reflected in the window motor. Therefore, the car's tire pressure data, the temperature data in the car's tires, and the damping coefficient of the suspension system can be transmitted to the window motor with a nonlinear effect, thereby interfering with the window motor's current data. The interference of the current data is fitted through a neural network, and then the predicted current value at each moment can be directly obtained based on the data from the car's sensors. Based on the predicted current value as a standard, the current parameters at each moment are compared, and abnormal conditions are determined based on the threshold.

[0041] Comparative data between traditional threshold detection and the present invention:

[0042]

[0043] Specifically, the comparative data shows that the present invention does not cause abnormal stopping or lowering of windows during bumpy roads, and its response time to pressure application is significantly better than that of traditional threshold detection methods.

[0044] In one embodiment of the present invention, collecting data at fixed time intervals includes:

[0045] In a first preset time period, if it is determined that at least one of the N window motors is in operation at the i-th moment, current data of the window motor corresponding to the i-th moment, tire pressure data and temperature data of the M tires, and a damping coefficient of the suspension system are collected. , Is a positive integer.

[0046] Specifically, collecting data at fixed time intervals ensures data continuity and consistency, providing a reliable time-series data foundation for subsequent data processing and model building. On the other hand, by collecting data only when the window motor is in operation, it can ensure that the collected information is closely related to the actual operating status, avoiding the collection of idle data or noisy data.

[0047] In one embodiment of the present invention, the unified dimension processing includes:

[0048] Set dimensionless temperature ;

[0049] Based on the tire volume and the temperature data of the mth tire at the i-th moment, the tire pressure data of the mth tire at the i-th moment is converted to dimensionless temperature The standard tire pressure data is calculated as follows:

[0050] ;

[0051] in, represents the standard tire pressure data of the mth tire at the i-th moment, represents the tire pressure data of the mth tire at the i-th moment, represents dimensionless temperature, represents the temperature data of the mth tire at the i-th moment, Indicates the adjustment weight, Indicates the tire's internal volume. , represents the natural base, , Is a positive integer.

[0052] Specifically, tire pressure data is dimensionalized. This involves setting a standard temperature dimension and converting the raw tire pressure data based on the tire volume and the temperature data at the current moment to obtain standard tire pressure data under uniform temperature conditions. This is because tire pressure is significantly affected by temperature, and tire pressure data fluctuates significantly under different temperature environments. Directly using the raw data can lead to deviations in subsequent model training and anomaly detection. However, dimensionalizing the data eliminates the impact of temperature differences on tire pressure, ensuring data consistency and comparability. This provides more accurate and stable sample data for the current prediction model, further improving the system's accuracy in detecting abnormal window conditions.

[0053] In one embodiment of the present invention, obtaining the first screening data and the second screening data includes:

[0054] The operating states include an ascending state, a descending state, and a standby state. According to the operating states of the N window motors at the i-th moment, the current data of the window motors with the same operating state are divided into the same type, and the current data of the ascending window, the current data of the descending window, and the current data of the standby window at the i-th moment are obtained. The current data of the ascending window is used as the first screening data, and the current data of the descending window is used as the second screening data.

[0055] Specifically, the window motor operating states are categorized into rising, falling, and standby states. Based on the state of each motor at the i-th moment, the current data for the same state is grouped together. The rising current data is then used as the first filtered data, while the falling current data is used as the second filtered data. This is because the window motor's current characteristics vary significantly across different operating states. Separately extracting data for the rising and falling states helps build a more targeted current prediction model, improving the accuracy of anomaly detection. Furthermore, excluding the standby data reduces the impact of noise and irrelevant information on model training.

[0056] In one embodiment of the present invention, the current prediction model includes a rising prediction unit and a falling prediction unit;

[0057] Obtain the Euclidean distance between each window motor and each tire in the target vehicle and construct training data. The training data includes: sample data and sample labels, as follows:

[0058] The initial sample data is constructed based on the standard tire pressure data of M tires at the i-th moment and the i+1-th moment:

[0059] ;

[0060] in, Represents the mth element in the initial sample data, Indicates the The standard tire pressure data of the mth tire at the moment, represents the Euclidean distance between the nth window motor and the mth tire, , is a positive integer; the initial sample data is constructed in a vector structure, and the dimension of the initial sample data is M;

[0061] Based on the damping coefficient of the suspension system at the i-th moment, the initial sample data is processed:

[0062] ;

[0063] in, represents the mth element in the standard sample data, represents the damping coefficient of the suspension system at the i-th moment, represents the damping coefficient weight;

[0064] The standard sample data is normalized and used as the sample data of the current prediction model, and the current data of the nth window motor at the i-th moment is normalized and used as the sample label.

[0065] Specifically, the Euclidean distance between each window motor and each tire is obtained, and initial sample data is constructed based on the standard tire pressure data of M tires at time i and time i+1. The initial sample data is then adjusted based on the damping coefficient and its weight of the suspension system at time i to obtain standard sample data, which serves as the input to the current prediction model. The actual current data of the window motor at the corresponding time is used as sample labels to train the prediction units corresponding to the rising and falling states in the model.

[0066] In one embodiment of the present invention, a rise prediction unit includes: if the current data of the nth window motor at the i-th moment is the first screening data, then the rise prediction unit is trained based on the corresponding sample data and sample labels; wherein the rise prediction unit is constructed based on a one-dimensional convolutional neural network.

[0067] Specifically, when the current data for the nth window motor at the i-th moment falls within the first filtered data set (i.e., data corresponding to the rising state), a one-dimensional convolutional neural network is trained using the sample data and sample labels corresponding to this state to construct a prediction unit for predicting current changes during the rising state. One-dimensional convolutional neural networks have excellent local feature extraction capabilities for processing time series data and are capable of capturing the dynamic changes in current during the window's rising process.

[0068] In one embodiment of the present invention, a descent prediction unit includes: if the current data of the nth window motor at the i-th moment is the second screening data, then the descent prediction unit is trained based on the corresponding sample data and sample labels; wherein the descent prediction unit is constructed based on a one-dimensional convolutional neural network.

[0069] Specifically, when the window motor is in the lowering state, meaning its current data falls within the second filtered data, the system uses the corresponding sample data and sample labels to train a one-dimensional convolutional neural network to build a lowering prediction unit. The current variation characteristics of a window in the lowering process may differ from those in the upper state. By establishing a separate prediction unit for the lowering state, the accuracy of anomaly detection can be improved.

[0070] In one embodiment of the present invention, the loss functions of the ascending prediction unit and the descending prediction unit are both mean square error loss functions.

[0071] Specifically, both the rising and falling prediction units use mean squared error (MSE) as the loss function during training. MSE quantifies the difference between predicted current values and actual collected current data, enabling the model to more accurately correct erroneous predictions during training. Furthermore, the continuity and differentiability of MSE provide strong support for gradient-based optimization methods, contributing to the stable convergence of both the rising and falling prediction units, ultimately improving overall anomaly detection accuracy.

[0072] In one embodiment of the present invention, obtaining an abnormality detection result includes: obtaining the current data and operating status of the nth window motor of the target vehicle at the kth moment within a second preset time period, the tire pressure data and temperature data of M tires, and the damping coefficient of the suspension system; if the operating status of the nth window motor is a rising state or a falling state, constructing an input sample at the kth moment; wherein the input sample is constructed in the same manner as the sample data of the current prediction model; based on the operating status of the nth window motor, the input sample is input into the rising prediction unit or the falling prediction unit to obtain the predicted current data output by the current prediction model at the kth moment; if the absolute difference between the predicted current data and the current data of the nth window motor at the kth moment is ≤ a preset threshold, the current state is normal, otherwise the current state is abnormal.

[0073] Specifically, the trained current prediction model is used to predict the current of the window motor at the kth moment and compare it with the actual current data collected to determine whether the current state is normal. Specifically, when the nth window motor is detected to be in the rising or falling state, the input sample is constructed according to the same method as the model training, and then the input sample is input into the corresponding rising or falling prediction unit to obtain the predicted current data. The predicted current data is used to reflect the predicted current data of the window motor when it is rising or falling based on the bumpiness of the road surface at the kth moment. If the difference between the predicted current data and the actual current data exceeds the preset threshold, it means that the window may have received additional force, resulting in abnormal current of the window motor, and there is a risk of pinching people or objects.

[0074] The above describes the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. A vehicle window abnormality detection system, characterized in that: include: The data acquisition module is used to collect data in a first preset time period. Get the target vehicle's tire volume and calculate it at fixed time intervals. Collect: current data and operating status of N window motors, tire pressure and temperature data of M tires, and the damping coefficient of the suspension system; A dimension unification module is used to unify the tire pressure data of each tire at the corresponding moment based on the tire volume and temperature data to obtain the standard tire pressure data of each tire; a data screening module, configured to screen the current data of the N window motors based on the operating status of the window motors to obtain first screened data and second screened data; A model building module is used to build a current prediction model based on the first screening data and the second screening data; the output of the current prediction model represents the predicted current data of the window motor in the working state within the second preset time period; wherein the working state includes the rising state and the falling state; the current prediction model includes a rising prediction unit and a falling prediction unit; obtain the Euclidean distance between each window motor and each tire in the target vehicle, and build training data, the training data includes: sample data and sample labels, specifically as follows: build initial sample data, build initial sample data based on the standard tire pressure data of M tires at the i-th moment and the i+1-th moment For each element of the sample data, for the mth element m(n) in the initial sample data, the calculation and determination process is as follows: calculate the absolute value of the difference between the standard tire pressure data of the mth tire at the i-th moment and the i+1-th moment; multiply the absolute value by the Euclidean distance between the n-th window motor and the m-th tire to obtain the mth element in the initial sample data; process the initial sample data based on the damping coefficient of the suspension system at the i-th moment; use the standard sample data as the sample data of the current prediction model after normalization, and use the current data of the n-th window motor at the i-th moment as the sample label after normalization; An abnormality detection module is used to perform abnormality detection on the current data at each moment within a second preset time period based on the predicted current data output by the current prediction model to obtain an abnormality detection result; wherein the abnormality detection result includes: normal current state and abnormal current state, specifically including: obtaining the current data and operating state of the nth window motor at the kth moment of the target vehicle within the second preset time period, the tire pressure data and temperature data of M tires, and the damping coefficient of the suspension system; if the operating state of the nth window motor is a rising state or a falling state, constructing an input sample at the kth moment; wherein the input sample is constructed in the same manner as the sample data of the current prediction model; based on the operating state of the nth window motor, the input sample is input into the rising prediction unit or the falling prediction unit to obtain the predicted current data output by the current prediction model at the kth moment; if the absolute difference between the predicted current data and the current data of the nth window motor at the kth moment is ≤ a preset threshold, then the current state is normal, otherwise the current state is abnormal.

2. The abnormality detection system for automobile windows according to claim 1, characterized in that: Collect data at regular intervals, including: In a first preset time period, if it is determined that at least one of the N window motors is in operation at the i-th moment, current data of the window motor corresponding to the i-th moment, tire pressure data and temperature data of the M tires, and a damping coefficient of the suspension system are collected. , Is a positive integer.

3. The abnormality detection system for automobile windows according to claim 2, characterized in that: Unified dimensional processing, including: Set dimensionless temperature ; Based on the tire volume and the temperature data of the mth tire at the i-th moment, the tire pressure data of the mth tire at the i-th moment is converted to dimensionless temperature Standard tire pressure data below.

4. The abnormality detection system for automobile windows according to claim 3, characterized in that: Obtaining first screening data and second screening data includes: The operating states include an ascending state, a descending state, and a standby state. According to the operating states of the N window motors at the i-th moment, the current data of the window motors with the same operating state are divided into the same type, and the current data of the ascending window, the current data of the descending window, and the current data of the standby window at the i-th moment are obtained. The current data of the ascending window is used as the first screening data, and the current data of the descending window is used as the second screening data.

5. The abnormality detection system for automobile windows according to claim 4, characterized in that: The rise prediction unit includes: if the current data of the nth window motor at the i-th moment is the first screening data, then the rise prediction unit is trained based on the corresponding sample data and sample labels; wherein the rise prediction unit is constructed based on a one-dimensional convolutional neural network.

6. The abnormality detection system for automobile windows according to claim 5, characterized in that: The descent prediction unit includes: if the current data of the nth window motor at the i-th moment is the second screening data, then the descent prediction unit is trained based on the corresponding sample data and sample labels; wherein the descent prediction unit is constructed based on a one-dimensional convolutional neural network.

7. The abnormality detection system for automobile windows according to claim 6, characterized in that: The loss functions of the upward prediction unit and the downward prediction unit are both mean square error loss functions.

Images