Sensor performance evaluation method, apparatus, electronic device, and medium

Abstract

The application discloses a kind of sensor performance evaluation method, device, electronic equipment and medium, the method includes: obtaining the first data actually collected and the second data simulatedly collected of sensor at each sampling time point;For each described sampling time point, configure multiple types of time windows, according to each described sampling time point in each time window of each described sampling time point The first feature and the second feature corresponding to each time window configured by the first data and the second data of each time window are respectively determined;According to the first feature and the second feature corresponding to each time window configured by each described sampling time point, determine the deviation value of each time window in the sensor sampling process;According to the deviation value corresponding to each time window, determine the performance score of the sensor.The method can be realized from the perspective of full sample evaluation, through the full amount, real sensor sampling data, the performance of sensor is monitored and evaluated comprehensively and accurately.

Description

Technical Field

[0001] This invention relates to the field of sensor technology, and in particular to a sensor performance evaluation method, apparatus, electronic device, and medium. Background Technology

[0002] With the rapid development of urban lifeline engineering and industrial internet ecosystem projects, various sensors are operating everywhere. These massive sensors collect various parameters in real time, upload them to the cloud, and perform data calculations for various businesses and models, providing a variety of monitoring and operational services for urban lifeline engineering. In this business scenario, all ecological applications of urban safety monitoring and operation must rely on sensor data to function effectively; therefore, it is necessary to ensure the authenticity and reliability of the data collected by the sensors. Currently, sensor quality inspection mainly relies on manual sampling and testing, which has many problems, such as insufficient sample size, cumbersome laboratory testing processes, and easy misinterpretation of results, making it impossible to accurately and comprehensively monitor and evaluate sensor performance. Summary of the Invention

[0003] Therefore, it is necessary to provide a sensor performance evaluation method, apparatus, electronic device, and medium that can comprehensively and accurately evaluate sensor performance in response to the above-mentioned technical problems.

[0004] A sensor performance evaluation method includes: acquiring first data actually collected by the sensor at each sampling time and second data simulated by the sensor;

[0005] Multiple types of time windows are configured for each sampling time. Based on the first data and the second data within each time window of each sampling time, a first feature and a second feature corresponding to each time window configured for each sampling time are determined respectively; wherein, the set width corresponding to each type of time window is different.

[0006] Based on the first feature and the second feature corresponding to each time window configured at each sampling time, the deviation value of each time window in the sensor sampling process is determined;

[0007] In the above scheme, when determining the deviation value of each time window during the sensor sampling process based on the first feature and the second feature corresponding to each time window configured for each sampling time, the method includes:

[0008] The deviation value corresponding to each time window is determined sequentially according to a set order; the set order is determined based on the width of each type of time window being sorted from largest to smallest.

[0009] In the above scheme, when determining the deviation value of each time window during the sensor sampling process based on the first feature and the second feature corresponding to each time window configured for each sampling time, the method includes:

[0010] The deviation value corresponding to the determined time window is compared with the preset deviation value corresponding to the type of the time window; wherein, the preset deviation value is preset for each type of time window;

[0011] If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value is retained;

[0012] If it is determined that the deviation value is greater than the preset deviation value, the deviation value corresponding to the time window is updated to the set value.

[0013] In the above scheme, determining the deviation value corresponding to each time window in a predetermined order includes:

[0014] The deviation value corresponding to the currently determined time window is compared with the preset deviation value corresponding to the type of time window; wherein, the preset deviation value is preset for each type of time window;

[0015] If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value corresponding to the next type of time window is determined according to the set order.

[0016] If the deviation value is determined to be greater than the preset deviation value, the calculation of deviation values ​​for other types of time windows located after the currently determined time window is stopped.

[0017] In the above scheme, when it is determined that the deviation value is greater than the preset deviation value, the method further includes:

[0018] The deviation values ​​corresponding to the currently determined time window and other types of time windows located after the currently determined time window are set as the set values.

[0019] In the above scheme, determining the deviation value of each time window during the sensor sampling process based on the first feature and the second feature corresponding to each time window configured for each sampling time includes:

[0020] Based on the first feature and the second feature corresponding to each time window configured at each sampling time, determine the vector spacing corresponding to each time window configured at each sampling time;

[0021] The vector spacing corresponding to the same type of time window in all the sampling times is summed to obtain the deviation value corresponding to each time window.

[0022] In the above scheme, determining the sensor performance based on the deviation value corresponding to each time window includes:

[0023] The deviation values ​​corresponding to each type of time window are summed to obtain the sensor performance evaluation score; wherein the evaluation score is negatively correlated with the sensor performance.

[0024] A sensor performance evaluation device, comprising:

[0025] The data acquisition module is used to acquire the first data actually collected by the sensor and the second data simulated at each sampling moment;

[0026] The first determining module is configured to configure multiple types of time windows for each sampling time, and to determine the first feature and the second feature corresponding to each time window configured for each sampling time based on the first data and the second data within each time window of each sampling time; wherein, the set width corresponding to each type of time window is different;

[0027] The second determining module is used to determine the deviation value of each time window in the sensor sampling process based on the first feature and the second feature corresponding to each time window configured at each sampling time.

[0028] The evaluation module is used to determine the performance score of the sensor based on the deviation value corresponding to each time window.

[0029] An electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described sensor performance evaluation method.

[0030] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described sensor performance evaluation method.

[0031] The aforementioned sensor performance evaluation methods, devices, electronic equipment, and media extract first and second features from actual and simulated data collected at different sampling times using different types of time windows. By utilizing the first and second features corresponding to each time window, the deviation values ​​of the first and second features in each time window are determined, thereby obtaining the sensor's performance score. This achieves comprehensive and accurate monitoring and evaluation of sensor performance from the perspective of full-sample evaluation, using full and real sensor sampling data. Attached Figure Description

[0032] Figure 1 This is a flowchart illustrating a sensor performance evaluation method in one embodiment;

[0033] Figure 2 This is a flowchart illustrating the process of determining the deviation value corresponding to a time window in one embodiment.

[0034] Figure 3 This is a flowchart illustrating the process of determining the deviation value corresponding to the time window in yet another embodiment;

[0035] Figure 4 This is a flowchart illustrating the process of determining the deviation value corresponding to the time window in yet another embodiment;

[0036] Figure 5 This is a structural block diagram of a sensor performance evaluation device in one embodiment. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0038] The implementation details of the technical solutions in the embodiments of this application are described in detail below.

[0039] In one embodiment, such as Figure 1 As shown, a sensor performance evaluation method is provided, which may include the following steps:

[0040] Step S101: Obtain the first data actually collected by the sensor at each sampling time and the second data simulated at each sampling time.

[0041] In this embodiment, there are two parts of the collected data. The first part of the data is the first data actually collected by the sensor at each sampling moment during actual operation. The second part of the data is the second data collected by the simulated sensor at each sampling moment under normal operating conditions. In other words, the second data is generated by simulation and is the theoretical value of the sensor's collected signal.

[0042] The following explanation uses a gas methane detection sensor as an example to illustrate how to acquire the second data simulated by the sensor.

[0043] When simulating sensor data acquisition, the first step is to obtain a report on the working principle of the methane gas detection sensor. The working principle of a methane gas detection sensor is typically based on a semiconductor gas sensor. The semiconductor material in the sensor reacts chemically with methane gas, causing a change in the semiconductor's resistance. This change in resistance is converted into a voltage signal output. The higher the methane gas concentration, the greater the resistance change; therefore, the output voltage signal is directly proportional to the methane concentration. Assuming the sensitivity of the methane gas detection sensor is S and the methane gas concentration is C, the sensor's output voltage signal can be expressed as V = S * C. This formula can be used to simulate the theoretical value of the signal acquired by the methane gas detection sensor under normal operating conditions.

[0044] In simulating sensor data acquisition, it is also necessary to design different operating environments for the sensor to simulate data acquisition under normal operating conditions of the gas methane detection sensor in different environments: The following are simulations of data acquisition by the gas methane detection sensor under different operating environments:

[0045] (1) Slow rise in gas leakage: Under this working environment, the concentration of methane gas will rise slowly. The response time of the gas methane detection sensor is relatively long. The response curve of the gas methane detection sensor can be simulated. It is assumed that the methane concentration increases by a fixed amount every certain period of time. Then, the corresponding voltage signal value can be calculated based on the response characteristics of the gas methane detection sensor.

[0046] (2) Rapid rise in gas leakage: Under this working environment, the concentration of methane gas will rise rapidly. The response time of the gas methane detection sensor is relatively short. The methane concentration can be simulated to rise rapidly to a high value, and then the corresponding voltage signal value can be calculated based on the response characteristics of the gas methane detection sensor.

[0047] (3) Unstable signal value: In this working environment, environmental factors such as temperature and humidity will cause fluctuations in the signal value output by the gas methane detection sensor. The fluctuation of the signal value can be calculated by simulating changes in environmental factors, such as periodic changes in temperature.

[0048] In practical applications, data can be collected by analog sensors using computer simulation software or mathematical simulation tools.

[0049] It should be noted that the first and second data obtained are time-series signal values. The first data can be represented as: T1: M1, T2: M2, ..., T m M m Where T1, T2, ..., T m Indicate the sampling times, M1, M2, ..., M mThis represents the first data point, which is the actual data collected by the sensor at time T1.

[0050] The obtained second data can be represented as: T1: m1, T2: m2, ..., T m :m m Where T1, T2, ..., T m Indicate the sampling times, m1, m2, ..., m m This represents the second data point, which is the sensor collecting m1 at time T1 during the simulation of sensor sampling.

[0051] Step S102: Configure multiple types of time windows for each sampling time. Based on the first data and the second data in each time window at each sampling time, determine the first feature and the second feature corresponding to each time window configured at each sampling time.

[0052] Here, different types of time windows are set, distinguished by their width. The time window types are: 1h, 2h, 4h, 8h, 12h, 24h, 2day, 4day, 1week, and 2week. A 1h time window is used to select data within one hour, a 2-day time window is used to select data within two days, and a 1-week time window is used to select data within one week. In practical applications, the time window type can be adjusted according to actual needs. This embodiment uses the 10 types of time windows listed above as examples for illustration.

[0053] In this embodiment, multiple types of time windows are configured for each sampling time, including the 10 types of time windows listed above.

[0054] After configuring a time window for each sampling moment, corresponding first and second data will fall into the time window. For example, assuming that one type of time window configured for T1 is a 1-hour time window, then the time window will take T1 as the starting moment and obtain the first and second data with a length of 1 hour before the current T1.

[0055] Next, the first and second data points falling within each time window configured for each sampling time need to be processed. In practical applications, the processing flow for the first and second data points within each time window is consistent; the difference lies in the number of data points processed. To more clearly illustrate the processing flow for the first and second data points within a time window, we will use one time window corresponding to a single sampling time as an example.

[0056] The first and second data falling into the time window are processed using feature functions. By processing the first data, the first feature of the first data within the time window can be calculated. By processing the second data, the second feature of the second data within the time window can be calculated.

[0057] In practical applications, multiple different feature functions can be used to extract data features, allowing for the extraction of different features from the first data point within a time window. These feature functions can include various statistical functions such as mean, variance, maximum, minimum, maximum slope, and minimum slope, used to extract the distribution and statistical characteristics of the data.

[0058] The following are the first features obtained at different sampling times within a 1-hour time window.

[0059] T1: f1_t1, f2_t1, ..., fn_t1

[0060] T2: f1_t2, f2_t2, ..., fn_t2

[0061] ...

[0062] T m f1_t m f2_t m , ...fn_t m

[0063] Where f1, f2, ..., fn refer to the values ​​calculated for each feature function. There are N feature functions in total. For example, f1 can correspond to the mean within the time window, and f2 can correspond to the variance within the time window; the subscripts t1, t2, ..., tn are used to represent the values ​​calculated for each feature function. m This corresponds to the sampling time. Therefore, within the 1-hour time window corresponding to sampling time T1, the first feature obtained is T1: f1_t1, f2_t1, ..., fn_t1. Within the 1-hour time window corresponding to sampling time T2, the first feature obtained is T2: f1_t1. m f2_t m , ...fn_t m .

[0064] The following are the second features obtained at different sampling times within a 1-hour time window:

[0065] T1: f1_t1_M, f2_t1_M,…fn_t1_M

[0066] T2: f1_t2_M, f2_t2_M,…fn_t2_M

[0067] ...

[0068] Tm f1_t m _M, f2_t m _M,…fn_t m _M

[0069] Where f1, f2, ..., fn refer to the values ​​calculated for each feature function. There are N feature functions in total. For example, f1 can correspond to the mean within the time window, and f2 can correspond to the variance within the time window; the subscripts t1, t2, ..., tn are used to represent the values ​​calculated for each feature function. m This corresponds to the sampling time. Therefore, within the 1-hour time window corresponding to the sampling time T1, the second feature obtained is f1_t1_M, f2_t1_M, ..., fn_t1_M. Within the 1-hour time window corresponding to the sampling time T2, the second feature obtained is T2: f1_t2_M, f2_t2_M, ..., fn_t2_M.

[0070] By processing each time window configured at each sampling time, we can obtain the first feature and the second feature corresponding to each time window configured at each sampling time. Here, the first feature refers to the distribution and statistical characteristics of the first data within the time window, and the second feature refers to the distribution and statistical characteristics of the second data within the time window.

[0071] In practical applications, feature functions can be user-defined functions (UDFs). Users write functions to extract data features and register these functions as UDFs, enabling them to extract data features during data processing. Besides statistical functions, UDFs can also include physical model functions, which may involve various physical laws, mathematical models, and related functions, such as linear models, nonlinear models, and differential equations.

[0072] In one implementation, the logic for processing data streams within a defined time window in the Flink computing framework can be utilized. This includes setting different types of time windows in the Flink computing framework, allowing the framework to acquire data of different sampling times with window lengths. Additionally, a UDF function can be set in the Flink computing framework to extract features from the first and second data during the data stream processing.

[0073] In this embodiment, multiple types of time windows are used to observe the changes of the first and second data within different time units, thereby enabling a more comprehensive analysis of the first and second data collected by the sensor.

[0074] In practical applications, after determining the first and second features, they can be stored in a time-series database. A time-series database is a database system specifically designed for storing and managing time-series data. It is designed to handle large-scale time-series data, such as sensor data. Time-series databases have efficient data storage and retrieval capabilities, can quickly process large amounts of time-series data, and provide flexible data analysis and query functions.

[0075] When storing the first and second features into the time series database, the "one item, one table" storage principle must be followed. "One item, one table" means creating a separate data table for each sensor to store its data. This storage principle allows each sensor's data to have its own independent storage space in the time series database, making it easier to manage and query.

[0076] After storing the first and second features in the time series database, the corresponding data can be quickly extracted from the time series database when subsequent data processing is performed using the first and second features corresponding to different time windows at different sampling times.

[0077] Step S103: Determine the deviation value of each time window during the sensor sampling process based on the first feature and the second feature corresponding to each time window configured at each sampling time.

[0078] Here, the first and second features within each time window configured according to each sampling time are compared, and the deviation value of each time window can be determined. Specifically, taking a 1-hour time window as an example, a 1-hour time window is configured at each sampling time. The first and second features within the 1-hour time window corresponding to each sampling time are then processed to determine the data deviation of the sensor throughout the sampling process in a 1-hour unit of time. This deviation value is used to evaluate the similarity between the first and second data of the sensor during the sampling process. This similarity is obtained by comparing the corresponding first and second features.

[0079] Based on this, the deviation values ​​of the 10 time windows listed above during the sensor sampling process can be obtained. Thus, by using the deviation values ​​corresponding to different time windows, the fluctuations or instabilities of the sensor during the data acquisition process can be monitored.

[0080] In one embodiment, the process of determining the deviation value for each time window is carried out in a predetermined order. This predetermined order is determined by sorting the widths of each type of time window from largest to smallest. For example, assuming there are 10 types of time windows listed above, the corresponding order is 2week, 1week, 4day, 2day, 24h, 12h, 8h, 4h, 2h, and 1h. That is, the deviation value of the 2week time window configured for each sampling time is determined first, and the deviation value of the 1h time window configured for each sampling time is determined last.

[0081] In this embodiment, determining the deviation value of the time window by ordering the time windows from large to small allows us to start with the overall trend and then gradually delve into smaller time scales, which helps to fully understand the changing patterns of the sensor during the data acquisition process.

[0082] In one embodiment, such as Figure 2 As shown, Figure 2 A flowchart illustrating the process of determining the deviation value corresponding to the time window is shown.

[0083] Step S201: Compare the deviation value corresponding to the determined time window with the preset deviation value corresponding to the type of the time window.

[0084] Step S202: If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value is retained.

[0085] Step S203: If the deviation value is determined to be greater than the preset deviation value, the deviation value corresponding to the time window is updated to the set value.

[0086] After determining the deviation value corresponding to the time window, the deviation value corresponding to the time window is compared with the preset deviation value pre-set for that time window.

[0087] It should be noted that the preset deviation value here is set in advance for different types of time windows. For example, for a 1-hour time window, the corresponding preset deviation value can be set to T_1h, and for a 2-week time window, the corresponding preset deviation value can be set to T_2week. Thus, the preset deviation value corresponding to the time window is actually determined according to the type of the time window. Assuming that the time window is a 2-week time window, the deviation value D_2week corresponding to the determined time window is compared with the preset deviation value T_2week.

[0088] If the deviation value D_2week corresponding to the time window is less than or equal to the preset deviation value T_2week, then the deviation value D_2week is considered to be within a reasonable range, and the calculated deviation value D_2week is retained.

[0089] If the deviation value D_2week corresponding to the time window is greater than the preset deviation value T_2week, the deviation value D_2week is considered a bad value, that is, the deviation value D_2week exceeds the reasonable range. Then, the deviation value D_2week corresponding to the time window is updated to the set value. Here, the set value is a large value, which can be regarded as an infinite value. It can clearly distinguish the deviation value that exceeds the reasonable range from the deviation value that is within the reasonable range. This can clearly mark the time window with a large deviation, making it easier to identify and process in the subsequent calculation of sensor performance score.

[0090] As shown in Table 1, Table 1 shows the deviation values ​​for the time window of each type of sensor.

[0091] Time window Deviation value 2 weeks G_2week 1 week G_1week 4 days G_4day 2 days Setting value 24 hours Setting value 12 hours Setting value 8 hours Setting value 4 hours Setting value 2 hours Setting value 1 hour Setting value

[0092] From Table 1, it can be determined that starting from the 2-day time window, the corresponding deviation value exceeds the reasonable range. Based on this, the deviation value of the 2-day time window and subsequent time windows is set to the set value, while the deviation value of the time window before the 2-day time window is still the calculated deviation value.

[0093] It should be noted that, in this embodiment, the comparison between the deviation value corresponding to the determined time window and the preset deviation value can be performed after the deviation values ​​corresponding to all time windows have been determined, or it can be performed after the deviation value corresponding to one time window has been determined. After the comparison is completed, the deviation value corresponding to the next time window is determined.

[0094] In one embodiment, such as Figure 3 As shown, Figure 3 A flowchart illustrating the process of determining the deviation value corresponding to the time window is shown.

[0095] Step S301: Compare the deviation value corresponding to the currently determined time window with the preset deviation value corresponding to the type of the time window.

[0096] Step S302: If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value corresponding to the next type of time window is determined according to the set order.

[0097] Step S303: If the deviation value is determined to be greater than the preset deviation value, stop calculating the deviation values ​​corresponding to other types of time windows located after the currently determined time window.

[0098] In the process of determining the deviation value corresponding to the time window according to the set order, after determining the deviation value corresponding to the current time window, the deviation value corresponding to the current time window is compared with the corresponding preset deviation value. Here, the comparison result can determine whether it is necessary to determine the deviation value corresponding to the subsequent time windows. The following is a specific example to illustrate this.

[0099] According to the set order, the first thing to determine is the deviation value corresponding to the 2-week time window. After determining the deviation value D_2week corresponding to the 2-week time window, the deviation value D_2week is compared with the preset deviation value T_2week corresponding to the 2-week time window to determine whether the deviation value D_2week is within a reasonable range.

[0100] Here, the preset deviation value is set in advance for each type of time window, meaning that the preset deviation value is the same for time windows of the same type.

[0101] If the deviation value D_2week is determined to be less than or equal to the preset deviation value T_2week, meaning that the deviation value D_2week is within a reasonable range, then the preset deviation value corresponding to the subsequent time window is determined according to the set order.

[0102] If the deviation value D_2week is greater than the preset deviation value T_2week, meaning D_2week is outside the reasonable range, it's understandable that determining the deviation value for each time window in a set order involves determining the degree of deviation between the first and second data points from the larger time dimension to the smaller time dimension. Therefore, if the deviation value for a larger time window is greater than the preset deviation value, the deviation values ​​for smaller time windows obtained in subsequent calculations will also exceed the reasonable range. Based on this, further calculating the deviation values ​​for subsequent time windows is meaningless. Therefore, in this situation, the calculation of deviation values ​​for other types of time windows after the currently determined time window is paused. This simplifies subsequent data analysis and processing steps, while saving significant time and computational resources.

[0103] In one embodiment, if the deviation value corresponding to the currently determined time window is greater than a preset deviation value, the determination of the deviation value corresponding to subsequent time windows will be paused. Based on this, in this embodiment, the deviation values ​​corresponding to the currently determined time window and other types of time windows located after the currently determined time window are determined as set values. This set value is almost infinitely large. For example, assuming that the width of the currently determined time window is 4h, the deviation values ​​corresponding to the 4h time window, the 2h time window and the 1h time window are all set as set values.

[0104] Understandably, in the setting sequence, the width of the earlier time windows will be larger than the width of the later time windows. This means that deviations are first determined from a larger time dimension, and then further determined from a smaller time dimension. Based on this, deviations determined at a larger time dimension will exceed a reasonable range, and deviations determined at a more microscopic level will also exceed a reasonable range. Therefore, after stopping the calculation of deviations for subsequent time windows, the deviations for the currently determined time window and other types of time windows following it are set to setpoints. These setpoints clearly distinguish deviations that exceed a reasonable range from those that are within a reasonable range, clearly marking time windows with significant deviations, making them easier to identify and handle in subsequent calculations of sensor performance scores.

[0105] In one embodiment, such as Figure 4 As shown, Figure 4 A flowchart illustrating the process of determining the deviation value corresponding to the time window is shown.

[0106] Step S401: Determine the vector spacing corresponding to each time window configured at each sampling time based on the first feature and the second feature corresponding to each time window configured at each sampling time.

[0107] Step S402: Sum the vector spacing corresponding to the same type of time window in all sampling times to obtain the deviation value corresponding to each type of time window.

[0108] Here, the vector spacing between the first feature and the second feature is evaluated based on the first feature and the second feature corresponding to each time window.

[0109] The following explanation uses a 2-week time window as an example. For a 2-week time window configured at time T1, the corresponding first feature is represented as: T1: f1_t1, f2_t1, ..., fh_t1, and the corresponding second feature is represented as: T1: f1_t1_M, f2_t1_M, ..., fn_t1_M. In one implementation, the vector distance between the first and second features is the square of the Euclidean distance. That is, the distance between the first and second features can be represented by calculating the square of the magnitude of their difference vector. The corresponding formula is:

[0110] By processing each time window configured at each sampling moment according to the above formula, the vector spacing corresponding to each time window configured at each sampling moment can be determined.

[0111] In practical applications, configuring different types of time windows for different sampling times is to observe the difference between the first and second data at different units of time. After determining the vector spacing corresponding to each time window configured for each sampling time, it is necessary to comprehensively evaluate the overall changes between feature vectors in the entire time series data.

[0112] Based on this, by summing the vector spacing corresponding to the same type of time window across all sampling times, we can obtain the deviation value corresponding to each time window. The deviation value of the time window reflects the overall difference between the feature vectors of the time window in the time series data. For example, taking a 2-week time window as an example, the deviation value corresponding to the 2-week time window... That is, the deviation values ​​of the 2-week time windows corresponding to all sampling times are added together to get D_2week. And so on, so that the deviation value corresponding to each type of time window can be obtained.

[0113] Step S104: Determine the sensor's performance score based on the deviation value corresponding to each time window.

[0114] The deviation value here is used to measure the degree of deviation between the first data and the second data. As you can understand, the second data is the theoretical value obtained by simulating the data collected by the sensor. The second data serves as a reference standard for sensor performance and is the expected value calculated based on the sensor's design principles, physical characteristics, or theoretical model. In other words, the actual data collected by the sensor needs to be close to the theoretical data obtained by simulation. Therefore, the closer the first data is to the second data, the more realistic and reliable the data collected by the sensor is.

[0115] Therefore, by comprehensively considering the deviations within different time windows, a weighted average or other comprehensive methods can be used to determine the sensor's performance score. In practical applications, this performance score can quantify the quality of sensor performance, enabling standardized evaluation of sensor performance and avoiding the influence of subjective factors. Specifically, this performance score is primarily used to assess the overall stability and accuracy of sensor data acquisition.

[0116] In one embodiment, an evaluation function for sensor performance is set. Here, E represents the sensor's performance score, i represents the type of time window, and D... -i This represents the deviation value corresponding to time window type i, which is the sum of the deviation values ​​corresponding to the 10 types of time windows listed above. As can be understood, the deviation value is used to measure the degree of deviation between the first data and the second data. Therefore, the smaller the evaluation score E, the closer the first data actually collected by the sensor is to the simulated second data, indicating better sensor performance.

[0117] It should be noted that in some time windows, the deviation value is a set value, which is a value that is almost infinite. In this case, the performance score calculated by the evaluation function is also a value that is almost infinite. In particular, in the setting order, the earlier the time window is, the higher the performance score of the sensor will be when the deviation value is set. This will be much higher than the performance score of the sensor whose deviation value is not set, thus clearly distinguishing the quality of the sensor performance.

[0118] It should be noted that the above-mentioned sensor performance evaluation method is applicable to sensors from different manufacturers, models, and batches, and can accurately compare the quality of various types of sensors, providing solid theoretical support for the entire sensor industry ecosystem to promote excellence and eliminate inferior products.

[0119] In the above embodiments, by acquiring the first data actually collected by the sensor and the second data obtained by simulation, and by comparing the differences between the first data and the second data using different time windows, the performance of the sensor can be evaluated by the deviation values ​​corresponding to different time windows at different sampling times. The operating status of the sensor can be comprehensively monitored and evaluated by using full and real sensor sampling data.

[0120] In one embodiment, a sensor performance evaluation device is provided, referencing Figure 5 As shown, the sensor performance evaluation device 500 may include: a data acquisition module 501, a first determination module 502, a second determination module 503, and an evaluation module 504.

[0121] The sensor comprises: an acquisition module 501 for acquiring first data actually acquired by the sensor and second data simulated at each sampling moment; a first determination module 502 for configuring multiple types of time windows for each sampling moment, and determining the first and second features corresponding to each time window configured for each sampling moment based on the first and second data within each time window; wherein the set width of each type of time window is different; a second determination module 503 for determining the deviation value of each time window during the sensor sampling process based on the first and second features corresponding to each time window configured for each sampling moment; and an evaluation module 504 for determining the sensor's performance score based on the deviation value corresponding to each time window.

[0122] In one embodiment, the second determining module 503 is specifically used to determine the deviation value corresponding to each type of time window in a predetermined order; the predetermined order is determined based on the width of each type of time window being sorted from largest to smallest.

[0123] In one embodiment, the second determining module 503 is specifically used to compare the deviation value corresponding to the determined time window with the preset deviation value corresponding to the type of the time window; wherein, the preset deviation value is preset for each type of time window;

[0124] If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value is retained.

[0125] If the deviation value is determined to be greater than the preset deviation value, the deviation value corresponding to the time window will be updated to the set value.

[0126] In one embodiment, the second determining module 503 is specifically used to compare the deviation value corresponding to the currently determined time window with the preset deviation value corresponding to the type of the time window; wherein, the preset deviation value is preset for each type of time window;

[0127] If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value corresponding to the next type of time window is determined according to the set order.

[0128] If the deviation value is determined to be greater than the preset deviation value, stop calculating the deviation values ​​for other types of time windows located after the currently determined time window.

[0129] In one embodiment, the second determining module 503 is further configured to, when determining that the deviation value is greater than a preset deviation value, determine the deviation values ​​corresponding to the currently determined time window and other types of time windows located after the currently determined time window as set values.

[0130] In one embodiment, the second determining module 503 is specifically used to determine the vector spacing corresponding to each time window configured at each sampling time based on the first feature and the second feature corresponding to each time window configured at each sampling time.

[0131] The vector spacing corresponding to the same type of time window in all sampling times is summed to obtain the deviation value corresponding to each type of time window.

[0132] In one embodiment, the evaluation module 504 is specifically used to sum the deviation values ​​corresponding to each type of time window to obtain an evaluation score for sensor performance; wherein the evaluation score is negatively correlated with the sensor performance.

[0133] Specific limitations regarding the sensor performance evaluation device can be found in the limitations of the sensor performance evaluation method described above, and will not be repeated here. Each module in the aforementioned sensor performance evaluation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0134] In one embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a sensor performance evaluation method.

[0135] In one embodiment, a computer storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a sensor performance evaluation method.

[0136] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0137] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0138] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0139] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0140] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for evaluating sensor performance, characterized in that, include: The sensor acquires first data actually collected at each sampling moment and second data simulated at each sampling moment; wherein, the second data is the data collected by the sensor under normal operating conditions at each sampling moment. Multiple types of time windows are configured for each sampling time. The first data and the second data falling into each time window of each sampling time are processed using feature functions to determine the first feature of the first data and the second feature of the second data within each time window configured for each sampling time. The set width of each type of time window is different. The feature functions are used to extract the distribution features and statistical features of the data. Based on the first feature and the second feature corresponding to each time window configured at each sampling time, the deviation value of each time window in the sensor sampling process is determined; wherein, determining the deviation value includes: based on the first feature and the second feature corresponding to each time window configured at each sampling time, the vector spacing corresponding to each time window configured at each sampling time is determined; the vector spacing corresponding to the same type of time windows in all sampling times is summed to obtain the deviation value corresponding to each time window; The performance score of the sensor is determined based on the deviation value corresponding to each time window, including: summing the deviation values ​​corresponding to each type of time window to obtain an evaluation score for the sensor performance; wherein the evaluation score is negatively correlated with the sensor performance.

2. The sensor performance evaluation method according to claim 1, characterized in that, When determining the deviation value of each time window during the sensor sampling process based on the first feature and the second feature corresponding to each time window configured for each sampling time, the method includes: The deviation value corresponding to each time window is determined sequentially according to a set order; the set order is determined based on the width of each type of time window being sorted from largest to smallest.

3. The sensor performance evaluation method according to claim 1 or 2, characterized in that, When determining the deviation value of each time window during the sensor sampling process based on the first feature and the second feature corresponding to each time window configured for each sampling time, the method includes: The deviation value corresponding to the determined time window is compared with the preset deviation value corresponding to the type of the time window; wherein, the preset deviation value is preset for each type of time window; If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value is retained; If it is determined that the deviation value is greater than the preset deviation value, the deviation value corresponding to the time window is updated to the set value.

4. The sensor performance evaluation method according to claim 2, characterized in that, The step of determining the deviation value corresponding to each time window in a predetermined order includes: The deviation value corresponding to the currently determined time window is compared with the preset deviation value corresponding to the type of time window; wherein, the preset deviation value is preset for each type of time window; If the deviation value is determined to be less than or equal to the preset deviation value, the deviation value corresponding to the next type of time window is determined according to the set order. If the deviation value is determined to be greater than the preset deviation value, the calculation of deviation values ​​for other types of time windows located after the currently determined time window is stopped.

5. The sensor performance evaluation method according to claim 4, characterized in that, If it is determined that the deviation value is greater than the preset deviation value, the method further includes: The deviation values ​​corresponding to the currently determined time window and other types of time windows located after the currently determined time window are set as the set values.

6. A sensor performance evaluation device, characterized in that, include: The acquisition module is used to acquire the first data actually collected by the sensor at each sampling moment and the second data collected by simulation; wherein, the second data is the data collected by the sensor under normal operating conditions at each sampling moment. The first determining module is configured to configure multiple types of time windows for each sampling time, and to process the first data and the second data falling into each time window of each sampling time using feature functions, and to determine the first feature of the first data and the second feature of the second data within each time window configured for each sampling time; wherein, the set width corresponding to each type of time window is different; the feature function is used to extract the distribution features and statistical features of the data; The second determining module is configured to determine the deviation value of each time window in the sensor sampling process based on the first feature and the second feature corresponding to each time window configured at each sampling time; wherein, determining the deviation value includes: determining the vector spacing corresponding to each time window configured at each sampling time based on the first feature and the second feature corresponding to each time window configured at each sampling time; and summing the vector spacings corresponding to the same type of time windows in all sampling times to obtain the deviation value corresponding to each time window; The evaluation module is used to determine the performance score of the sensor based on the deviation value corresponding to each time window, including: summing the deviation values ​​corresponding to each type of time window to obtain an evaluation score for the sensor performance; wherein the evaluation score is negatively correlated with the sensor performance.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the sensor performance evaluation method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the sensor performance evaluation method according to any one of claims 1 to 5.

Images