Vehicle-mounted lens assembly state monitoring data processing method and system

Abstract

The invention relates to the technical field of data processing, in particular to a vehicle-mounted lens assembly state monitoring data processing method and system, and the method comprises the following steps: collecting a temperature generation matrix, analyzing a difference value, positioning sudden change, extracting features, dividing sections, and constructing a situation output record. According to the method, rapid extraction and boundary positioning of sudden change behaviors in the operation process are realized by constructing a temperature and time bound data structure and performing difference operation analysis, thermal change stages are classified and marked in combination with a fluctuation direction and duration recognition mechanism, division and coding of stable and repetitive sections are realized, and the stability and repeatability of the thermal change stages are improved. Therefore, the structural characteristics of the lens operation situation can be extracted based on the continuous time sequence data, the analysis capability of the lens state is enhanced in the time dimension, the response precision of the nonlinear dynamic change is improved, error accumulation and state blur caused by static threshold judgment are effectively avoided, and the accuracy of lens operation is improved. And the state of the vehicle-mounted lens assembly can be monitored and judged with higher resolution and foresight.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for processing data related to the status monitoring of vehicle-mounted camera components. Background Technology

[0002] The field of data processing technology encompasses the entire process of collecting, cleaning, transforming, analyzing, and storing various types of raw data. This includes data acquisition, data format conversion, feature extraction, data modeling, algorithm selection, and result output. It primarily focuses on structuring complex datasets through mathematical modeling, statistical analysis, and pattern recognition to improve data usability and computational efficiency, and is widely applied across various industries. Traditional methods for processing data related to the status monitoring of automotive camera components refer to methods that process and judge operational status data collected by camera components installed in vehicles during operation, such as temperature, voltage, focal length drift, and image sharpness. These methods typically use preset threshold rules to judge status parameters, comparing one or more operational parameters with standard values ​​to determine whether the camera component is in normal working condition. They often rely on logical judgment or empirical model matching to identify data anomalies.

[0003] In the current process of processing data for the condition monitoring of vehicle-mounted camera components, the main reliance is on a logical judgment mode that compares the collected parameters with set thresholds. This lacks in-depth analysis of the multi-dimensional time series change characteristics, making it difficult to accurately identify the source of the problem when faced with complex or highly volatile changes in operating status. Furthermore, the judgment relies too heavily on static experience models or rule matching, ignoring the dynamic fluctuation patterns during operation. This can easily lead to misjudgments or omissions in the case of multi-parameter coupled fluctuations. In addition, the response of this type of method to abnormal states is usually lagging, and it cannot effectively characterize the structural features of the change process. Ultimately, this results in a coarse granularity of condition assessment, which cannot fully reflect the dynamic characteristics of the thermal response of the camera operation. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a method for processing data related to the status monitoring of vehicle-mounted camera components.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for processing data for monitoring the status of an automotive lens assembly, comprising the following steps: S1: Collect internal temperature data of the vehicle-mounted camera assembly during operation, obtain the operation cycle identification signal, bind the temperature value of each sample with the corresponding sampling time, and generate a heat source temperature time record matrix. S2: Calculate the difference between adjacent temperature sampling points in the heat source temperature time record matrix, filter all sampling points whose absolute difference is greater than the set mutation threshold, extract the time index and sampling number of the corresponding sampling point, perform error regression analysis on the subsequent temperature sequence, calibrate the mutation boundary point interval, and output the thermal mutation event boundary location result. S3: Based on the boundary location results of the thermal mutation event, extract the interval between the start sampling number and the end sampling number, identify the order of temperature fluctuation direction changes, and establish thermal change stage classification labels in combination with the duration to generate a thermal mutation segment response feature label table. S4: Based on the directionality and duration of each thermal change stage in the thermal change segment response feature label table, after dividing the stable segment into the unstable segment, construct the segment behavior feature classification code, and output the lens thermal response segment structure division result; S5: Based on the classification coding in the lens thermal response section structure division result, establish a lens operation status description data body and output the vehicle-mounted lens component status monitoring data processing record.

[0006] As a further aspect of the present invention, the stable segment is specifically a thermal variation stage in which the directionality exhibits continuous unidirectional change and the duration is within a set stable duration threshold range. The unstable segment specifically refers to a thermal fluctuation stage in which the directionality changes repeatedly and the duration exceeds a set stable duration threshold.

[0007] As a further embodiment of the present invention, the heat source temperature time recording matrix includes a sampling time index, a temperature value binding group, and an operating cycle identification signal; the thermal mutation event boundary positioning result includes a mutation point time index, a mutation point sampling number, and mutation interval boundary calibration information; the thermal mutation segment response feature label table includes a temperature segment before mutation, mutation peak position, fallback point index, temperature fluctuation direction sequence, thermal change duration, and thermal change stage classification label; the lens thermal response segment structure division result includes stable segment classification code, unstable segment classification code, and segment relationship mapping information; and the vehicle-mounted lens component status monitoring data processing record includes a lens operating status description data body, a time sequence integrated structure, and a current operating cycle classification code.

[0008] As a further aspect of the present invention, the step of obtaining the heat source temperature-time recording matrix specifically includes: S111: Collect the output signal of the temperature sensor during the operation of the vehicle lens assembly, obtain the temperature value sequence, and record each sampling timestamp based on the time node corresponding to each temperature sampling, extract the correspondence between sampling time and temperature value, construct each sampling pair into a pair data set, and generate a temperature time-bound data frame. S112: Based on the temperature-time binding data frame, retrieve the timestamp sequence recorded in each group of binding data, identify the start and end time points of the current vehicle-mounted lens component's operating cycle, extract the corresponding temperature data pairs within the time period, and generate a binding dataset within the operating cycle. S113: Based on the bound dataset within the aforementioned operating cycle, arrange all temperature values ​​sequentially according to the timestamp order, and reorganize them into a matrix according to the corresponding sampling time. Use timestamps as horizontal indices and temperature values ​​as vertical vector elements to establish a heat source temperature time record matrix.

[0009] As a further aspect of the present invention, the step of obtaining the boundary localization result of the thermal mutation event specifically includes: S211: Based on the heat source temperature time recording matrix, perform a differential operation on the temperature values ​​of adjacent sampling points, extract the position index of any set of continuous sampling points in the vertical temperature value vector, calculate the temperature difference, compare the absolute value of all temperature differences with the set mutation threshold one by one, filter the temperature difference samples with an absolute difference greater than the mutation threshold, extract the timestamp and sequence number of the sampling points accordingly, and generate a temperature mutation sampling index set. S212: Based on the temperature mutation sampling index set, the selected sampling index positions are aggregated, and the segments are marked according to whether the time interval between the indices is continuously less than the preset aggregation interval threshold. The continuous sampling points that meet the aggregation conditions are assigned to the same segment, and the time values ​​and number ranges corresponding to the start and end sampling points of each segment are extracted to generate a mutation time segment index set. S213: Based on the index set of abrupt change time segments, perform residual regression processing on the temperature sampling sequence corresponding to each segment, use the segment temperature sequence to fit the trend curve and measure the deviation with the original sequence, identify the location of the local abrupt change inflection point of the residual curve, mark the boundary time point corresponding to the inflection point, integrate all segment boundary information, and obtain the boundary location result of the thermal abrupt change event.

[0010] As a further aspect of the present invention, the step of obtaining the thermal mutation segment response feature label table specifically includes: S311: Based on the boundary location results of the thermal mutation event, extract the start time point and end time point marked in each mutation segment, and obtain the corresponding start sampling number and end sampling number through the index mapping table, construct the interval number set, and obtain the thermal change sampling interval number set. S312: Obtain the set of thermal variation sampling interval numbers, extract the complete temperature sequence corresponding to each number interval, identify the index position of the highest temperature value in the abrupt change segment as the peak point, trace back to the starting point of the continuous monotonically increasing segment as the reference point before the abrupt change, find the end point of the first monotonically decreasing interval as the fallback point, calculate and obtain the temperature abrupt change response ratio, and construct the thermal variation contour structure by combining the segment number to obtain the thermal variation trend response contour set. S313: Based on the thermal change trend response profile set, jointly judge the temperature rise and fall direction, duration, and response ratio of each segment. If the upward trend is satisfied and the duration is greater than the set temperature rise duration threshold, and the response ratio is higher than the set response intensity threshold, then it is labeled as a rapid rise type; otherwise, it is labeled as a stable fluctuation type. Summarize and classify the labels and establish structured entries according to the numbered segment number to obtain the thermal change segment response feature label table.

[0011] As a further aspect of the present invention, the formula for calculating the temperature change response ratio is as follows: ; in, Represents the ratio of responses to sudden temperature changes. Represents the peak temperature of the mutation. This represents the starting temperature before the mutation. Represents the temperature at the point of retracement. This represents the i-th temperature sample value within the interval. , This indicates the start and end index positions of the mutation.

[0012] As a further aspect of the present invention, the step of obtaining the lens thermal response segment structure division result is specifically as follows: S411: Based on the thermal mutation segment response feature label table, extract the directionality and duration information of each thermal change stage, determine whether the directionality is continuously unidirectional and the duration does not exceed the set stable duration threshold. If both conditions are met at the same time, it is recorded as a stable segment, and a stable trend stage index set is generated. S412: Based on the stable trend stage index set, filter out the segments that have been marked as stable, identify the directional repeated change characteristics of the remaining stages, and determine whether the duration exceeds the set stable duration threshold. If it does, record it as an unstable segment and obtain the unstable trend stage number set. S413: Based on the stable trend stage index set and the unstable trend stage number set, assign a classification identifier to all stages according to their numbers, mark stable segments as 0 and unstable segments as 1, construct a complete classification mapping, and obtain the lens thermal response segment structure division result.

[0013] As a further aspect of the present invention, the step of processing and recording the vehicle-mounted camera assembly status monitoring data specifically comprises: S511: Based on the classification coding information in the lens thermal response segment structure division result, extract all segment numbers and corresponding status labels, combine the segment time index, establish a one-to-one mapping between the number and the time series, and aggregate each segment according to the classification value to generate a segment classification mapping table. S512: Based on the segment classification mapping table, obtain the start and end time range covered by each numbered segment, align it with the current running cycle identifier, perform the intersection calculation of the start and end time and the running cycle timestamp, filter each classification segment within the running cycle and record the order and label, and obtain the hot segment status sequence within the running cycle. S513: Based on the hot zone state sequence within the operating cycle, aggregate and integrate all state labels in chronological order, construct a unified data structure, and embed timestamps, classification labels, and operating number information in sequence to generate vehicle-mounted camera component state monitoring data processing records.

[0014] A vehicle-mounted camera assembly status monitoring data processing system includes: The temperature acquisition module is used to perform S1: acquire internal temperature data of the vehicle-mounted lens assembly during operation, obtain the operation cycle identification signal, bind the temperature value of each sample with the corresponding sampling time, and generate a heat source temperature time record matrix. The mutation localization module is used to perform S2: calculate the difference between adjacent temperature sampling points in the heat source temperature time record matrix, filter all sampling points whose absolute difference value is greater than the set mutation threshold, extract the time index and sampling number of the corresponding sampling point, perform error regression analysis on the subsequent temperature sequence, mark the mutation boundary point interval, and output the thermal mutation event boundary localization result. The response feature module is used to perform S3: based on the boundary location results of the thermal mutation event, extract the interval between the start sampling number and the end sampling number, identify the order of temperature fluctuation direction changes, establish thermal change stage classification labels in combination with the duration, and generate a thermal mutation segment response feature label table. The segment determination module is used to execute S4: based on the directionality and duration of each thermal change stage in the thermal change segment response feature label table, it divides stable segments and unstable segments, constructs segment behavior feature classification codes, and outputs the lens thermal response segment structure division results; The status output module is used to execute S5: based on the classification code in the lens thermal response section structure division result, establish a lens operation status description data body, and output the vehicle lens component status monitoring data processing record.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by constructing a data structure that binds temperature and time and performing difference calculation analysis, rapid extraction and boundary localization of abrupt changes in the operation process are achieved. Combined with the identification mechanism of fluctuation direction and duration, thermal change stages are classified and marked, and stable and repetitive segments are divided and coded. Thus, the structural characteristics of the lens operation status can be extracted based on continuous time-series data, enhancing the ability to analyze the lens status in the time dimension. At the same time, the response accuracy to nonlinear dynamic changes is improved, effectively avoiding error accumulation and status ambiguity caused by static threshold judgment, and achieving more discriminative and forward-looking monitoring and judgment of the status of vehicle-mounted lens components. Attached Figure Description

[0016] Figure 1 This is a flowchart of the main steps of the present invention; Figure 2 This is a flowchart of the process for obtaining the heat source temperature-time recording matrix in this invention; Figure 3 This is a flowchart of the process for obtaining the boundary location results of thermal mutation events in this invention; Figure 4 This is a flowchart of the process for obtaining the thermal mutation section response feature label table of the present invention; Figure 5 This is a flowchart illustrating the process of obtaining the structural division results of the lens thermal response section in this invention. Figure 6 This is a flowchart of the process for obtaining and processing data for the status monitoring of the vehicle-mounted camera assembly of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0019] Please see Figure 1 A method for processing data for monitoring the status of an onboard camera assembly includes the following steps: S1: Collect internal temperature data of the vehicle-mounted camera assembly during operation through a temperature sensor, obtain the operation cycle identification signal, extract the sampling time, bind the temperature value of each sample with the corresponding sampling time, and generate a heat source temperature time record matrix. S2: Calculate the difference between adjacent temperature sampling points in the heat source temperature time record matrix, filter all sampling points whose absolute difference is greater than the set mutation threshold, extract the time index and sampling number of the corresponding sampling point, perform error regression analysis on the subsequent temperature sequence, calibrate the mutation boundary point interval, and output the thermal mutation event boundary location result. S3: Based on the boundary localization results of thermal mutation events, extract the interval between the starting sampling number and the ending sampling number, extract the temperature value of the segment before the mutation, the peak position of the mutation and the index of the fallback point, identify the order of temperature fluctuation direction changes, and establish thermal change stage classification labels in combination with the duration to generate a thermal mutation segment response feature label table. S4: Based on the directionality and duration of each thermal change stage in the thermal change segment response feature label table, thermal change stages with continuous unidirectional changes in direction and duration within the set stable duration threshold are recorded as stable segments, and thermal change stages with repeated changes in direction and duration exceeding the set stable duration threshold are recorded as unstable segments. After completing the mapping of the correspondence between stable and unstable segments, segment behavior feature classification coding is constructed, and the lens thermal response segment structure division result is output. S5: Based on the classification code in the lens thermal response section structure division result, combined with the current operating cycle identifier of the lens control unit, establish a lens operating status description data body, integrate it in chronological order, and output the vehicle lens component status monitoring data processing record.

[0020] The heat source temperature time recording matrix includes sampling time index, temperature value binding group, and operation cycle identification signal. The thermal mutation event boundary location result includes mutation point time index, mutation point sampling number, and mutation interval boundary calibration information. The thermal mutation segment response feature label table includes temperature segment before mutation, mutation peak position, fallback point index, temperature fluctuation direction sequence, thermal change duration, and thermal change stage classification label. The lens thermal response segment structure division result includes stable segment classification code, unstable segment classification code, and segment relationship mapping information. The vehicle-mounted lens component status monitoring data processing record includes lens operation status description data body, time sequence integrated structure, and current operation cycle classification code.

[0021] Please see Figure 2 Step S1 is as follows: S111: Collect the output signal of the temperature sensor during the operation of the vehicle lens assembly, obtain the temperature value sequence, and record each sampling timestamp based on the time node corresponding to each temperature sampling, extract the correspondence between sampling time and temperature value, construct each sampling pair into a pair data set, and generate a temperature time-bound data frame. To acquire the output signal of the temperature sensor during the operation of the vehicle-mounted lens assembly, its internal layout and temperature change response rate need to be confirmed. The temperature sensor should be integrated onto the lens assembly's mainboard and have millisecond-level response capability. For example, a digital temperature sensor TMP117 with a resolution of 0.0625℃ can be selected, with a sampling frequency of 10Hz (sampling once every 0.1 seconds) to stably obtain a continuous sampling data stream. The first step is to read the sensor's instantaneous output value via the digital bus. For example, at t=0s, 0.1s, and 0.2s, the temperature values ​​T0=35.75℃, T1=35.81℃, and T2=35.90℃ are acquired respectively, and their corresponding time points are recorded. By integrating the time information into the data... Within the frame, temperature-time pairs are formed, such as (0, 35.75), (0.1, 35.81), and (0.2, 35.90). The time precision here must be consistent and aligned with the output of the system's internal time synchronization module. During data recording, the sampling jump issue after a system abnormal reset must also be considered. A discontinuous time threshold Δt threshold = 0.5s can be set. If the interval between two samplings is greater than Δt threshold, it is considered the start of a new cycle. Data frame storage is implemented using a structured array. After mapping the sampling time to the temperature value one-to-one, a complete bound data frame is constructed, providing data support for further generating the temperature-time recording matrix. To verify sampling stability, 30 seconds of continuous sampling data are selected, and the sample array is constructed as follows: Table 1 Temperature sensor sampling data: ; As shown in Table 1, all sampled data are recorded in a structured manner and bound to timestamps. No logical operations such as analysis or judgment are involved in the binding process. The data organization is mainly completed through data acquisition, timestamp extraction, data pairing and binding data construction, and finally, temperature and time bound data frames are obtained.

[0022] S112: Based on the temperature-time bound data frames, retrieve the timestamp sequence recorded in each group of bound data, identify the start and end time points of the current vehicle-mounted lens component's operating cycle, extract the corresponding temperature data pairs within the time period, and generate the bound dataset within the operating cycle. When acquiring temperature-time bound data frames, all temperature-time pairs need to be extracted, sorted in ascending time order, and the interval Δt between adjacent time points is read. The boundary of the system's operating cycle is identified by calculating stable segments with continuous Δt. A stable continuous sampling threshold is set to Δt threshold = 0.2s. If Δt between adjacent sampling pairs is less than or equal to 0.2s, and the number of consecutive samples is not less than 50, then this segment is considered a stable sampling segment and is considered a valid segment of the operating cycle. For example, if sampling continues between t = 0 and 10s with a sampling interval of 0.1s, then... The segment is determined to be a valid segment within the operating cycle. Further, all temperature-time pairs within the segment are extracted, and other discontinuous segments are excluded. For example, if Δt reaches 0.6s between 0.3 and 0.4s, the segment is excluded. The time boundaries T_start and T_end of the segment are further extracted and recorded as the start and end points of the cycle. For example, T_start=0.0s and T_end=10.0s. This locates the data range covered by this operating cycle, and the bound data within the segment is reorganized into a subarray structure to generate the bound dataset within the operating cycle.

[0023] S113: Based on the bound dataset within the running cycle, arrange all temperature values ​​sequentially according to the timestamp order, and reorganize them into a matrix according to the corresponding sampling time. Use timestamps as horizontal indices and temperature values ​​as vertical vector elements to establish a heat source temperature time record matrix. Based on the bound dataset within the runtime cycle, the timestamps and corresponding temperature values ​​of each sampling point are read. The data is then reorganized using a matrix organization method. The timestamp sequence is set as the column vector index T = [0, 0.1, 0.2, ..., 10.0], and the temperature value sequence is set as the same-dimensional column vector Θ = [35.75, 35.81, 35.90, ..., 41.94]. A two-dimensional structure M(i, j) is constructed using a matrix reorganization function, where i represents the index position of the temperature value corresponding to the j-th time point in Θ. Each column contains only one temperature value, and the row direction represents the sampling progress. Finally, a heat source record structure with a matrix dimension of N×2 is generated. This structure is manifested in practice as follows: ; To further verify the integrity of the matrix, the difference Δt between the time indices of the matrix is ​​checked to see if it is 0.1s. If any Δt does not meet the requirement, the matrix resampling and completion operation is performed. Linear interpolation is used to fill in the temperature values ​​at the missing time points to ensure the continuity of the matrix. Finally, a two-dimensional matrix structure is established by combining the complete time index and the temperature values ​​to obtain the heat source temperature and time record matrix.

[0024] Please see Figure 3 Step S2 is as follows: S211: Based on the heat source temperature time record matrix, perform a differential operation on the temperature values ​​of adjacent sampling points, extract the position index of any set of continuous sampling points in the vertical temperature value vector, calculate the temperature difference, compare the absolute value of all temperature differences with the set mutation threshold one by one, filter the temperature difference samples with an absolute difference greater than the mutation threshold, extract the timestamp and sequence number of the corresponding sampling points, and generate a temperature mutation sampling index set. Based on the heat source temperature-time recording matrix, a difference sequence is constructed for the temperature values ​​of adjacent sampling points. First, the temperature column vector Θ and the corresponding time index vector T are extracted from the matrix. Let Θ = [35.75, 35.81, 36.02, 36.05, 37.90]. A difference array ΔΘ = [Θ2-Θ1, Θ3-Θ2, Θ4-Θ3, Θ5-Θ4] is constructed using adjacent temperature values, resulting in ΔΘ = [0.06, 0.21, 0.03, 1.85]. Then, the absolute value of each item in the difference array ΔΘ is calculated and compared with a mutation judgment threshold. The mutation threshold is set to θ_threshold = 1.5℃. Therefore, for any item in ΔΘ that satisfies |ΔΘ|... i For terms where |1.85| > 1.5, the condition is met. The corresponding temperature index position i = 4 is extracted; this position represents the point where the temperature abrupt change occurs. The time vector T is then used to obtain the corresponding time value t = 4.0s and the index n = 5. Finally, the times and indices corresponding to all points satisfying the abrupt change condition are extracted and summarized, and an index structure is constructed in key-value pair form, for example, {4.0:5}, for subsequent processing operations, as shown in Table 2. Table 2 Comparison of Temperature Sudden Change Difference and Threshold: ; As shown in Table 2, the temperature point corresponding to number 5 is a mutation event marker. Its difference exceeds the threshold θ=1.5℃. Therefore, its corresponding timestamp and number information are included in the temperature mutation point set to obtain the temperature mutation sampling index set.

[0025] S212: Based on the temperature mutation sampling index set, the selected sampling index positions are aggregated. The indexes are segmented according to whether the time interval between the indices is continuously less than the preset aggregation interval threshold. The continuous sampling points that meet the aggregation conditions are assigned to the same segment. The time values ​​and number ranges corresponding to the start and end sampling points of each segment are extracted to generate a mutation time segment index set. Read the temperature mutation sampling index set, and sequentially read the time index and sampling number corresponding to each mutation point. Sort the data in ascending order of time to form a time series vector T', where T' = [2.3, 2.4, 2.5, 4.0, 4.8, 7.2]. Set the aggregation interval threshold τaggregate = 0.3 s, and calculate the difference Δt between adjacent time points in T'. i =T' i+1−T' i If Δt i If ≤τ clusters, then T' will be... i With T' i+1 Aggregates data into the same group, such as Δt1=2.4-2.3=0.1 and Δt2=2.5-2.4=0.1, both less than the threshold of 0.3. Therefore, T'1 to T'3 are grouped together. Δt3=4.0-2.5=1.5, which does not meet the aggregation condition and is used as the starting point for a new group. This rule is followed to cluster the data sequentially and record the start and end time indices within each group, such as {[2.3, 2.5], [4.0, 4.8], [7.2, 7.2]}. Further, through a dual mapping of sampling numbers and time indices, each group of data is converted into a numbered segment form, recorded as [[24, 26], [40, 48], [72, 72]]. Each group is considered to be within the same mutation interval. The output structure is a set of multiple segment indices, forming a mutation time segment index set.

[0026] S213: Based on the index set of abrupt change time segments, perform residual regression processing on the temperature sampling sequence corresponding to each segment, fit the trend curve with the segment temperature sequence, measure the deviation with the original sequence, identify the local abrupt change inflection point of the residual curve, mark the boundary time point corresponding to the inflection point, integrate all segment boundary information, and obtain the boundary location result of thermal abrupt change event. Based on the abrupt change time interval index set, the temperature time series corresponding to each interval is extracted individually. Assuming the currently processed interval is the temperature sequence Θ'=[36.05, 36.12, 36.10, 36.80, 37.45, 38.20, 38.90, 39.05, 39.10] between numbers 40 and 48, and its corresponding time series is T'=[4.0, 4.1, 4.2, ..., 4.8], linear trend fitting is performed on Θ', and the trend value is estimated using the least squares method. Compare the fitted values ​​with the original values ​​to calculate the residuals. The residual sequence ε = [-0.10, -0.08, -0.13, 0.30, 0.35, 0.40, 0.30, 0.20, 0.05] is formed. The abrupt change residual limit δ = 0.25℃ is set, and the first |ε| in ε is identified. i |>δ and the last|ε i The positions of |>δ correspond to t=4.3s and t=4.7s respectively, and are marked as the start and end time points of the mutation event, which are the thermal mutation boundary points. Finally, the boundary time periods identified in all segments are integrated into a set form, and the output is a structure composed of multiple time pairs, such as {[4.3, 4.7], [7.2, 7.4]}, to establish the boundary location result of the thermal mutation event.

[0027] Please see Figure 4 Step S3 is as follows: S311: Based on the boundary location results of thermal mutation events, extract the start time point and end time point marked in each mutation segment, and obtain the corresponding start sampling number and end sampling number through the index mapping table to construct the interval number set and obtain the thermal change sampling interval number set. Based on the results of thermal mutation event boundary localization, firstly, a numbered index mapping is performed on each set of mutation segment boundary time pairs. Using the established time-number mapping table, the timestamps are converted into corresponding sampling numbers. Assuming the mutation segment start time is 4.0 seconds, the end time is 5.5 seconds, and the sampling period is 0.1 seconds, then the corresponding start number is 40, the end number is 55, and the record number interval is [40, 55]. Then, all mutation segment boundary records are traversed sequentially, and this conversion operation is performed uniformly to form a complete set of numbered segments. For example, if there are multiple mutation segments [4.0s, 5.5s], [7.2s, 8.1s], etc., the conversion is performed. The values ​​[10.0s, 10.6s] correspond to the following number sets after conversion: [[40, 55], [72, 81], [100, 106]]. During this process, it is necessary to determine whether the boundary time deviates from the actual sampling point. If the difference exceeds one sampling period, the number is rounded down to compensate for the discrepancy, ensuring that the numbering interval covers the actual temperature fluctuation range. The compensation strategy is set as follows: if the difference Δt > 0.05 seconds, the number is adjusted forward by one digit to ensure consistency between the numbering and the actual temperature fluctuation range. This method converts the boundary time intervals of all sudden events into numbering intervals and manages them in a unified structure, as shown in Table 3. Table 3. Time Number Mapping Table for Thermal Transition Zones: ; As shown in Table 3, all time values ​​of the abrupt change segments have been successfully converted into numbers and formed a number set structure, resulting in the number set of thermal variation sampling intervals.

[0028] S312: Obtain the set of thermal variation sampling interval numbers, extract the complete temperature sequence corresponding to each interval, identify the index position of the highest temperature value in the abrupt change segment as the peak point, trace back to the starting point of the continuous monotonically increasing segment as the baseline point before the abrupt change, and find the end point of the first monotonically decreasing interval as the fallback point position, using the formula: ; The ratio of responses to temperature abrupt changes is calculated, and combined with the segment numbers to construct a thermal change profile structure, resulting in a thermal change trend response profile set; where... Represents the ratio of responses to sudden temperature changes. Represents the peak temperature of the mutation. This represents the starting temperature before the mutation. Represents the temperature at the point of retracement. This represents the i-th temperature sample value within the interval. , Indicates the start and end index positions of the mutation; Read the set of thermal variation sampling interval numbers, and extract the complete temperature value sequence within each interval sequentially. Let the current interval number be [40, 55], and the corresponding temperature sequence be... First, identify the position corresponding to the maximum value in the sequence, T. p =39.9, corresponding to number 47, is taken as the position of the mutation peak. Then, tracing back to the starting point of the monotonically increasing interval, from T... p Position comparison T 46 <T 47 T 45 <T 46 If the condition is not met, the process stops, eventually backtracking to number 42 with temperature T_b=36.9, which serves as the baseline temperature before the abrupt change. Then, the process searches backwards for the endpoint of the interval where the temperature first forms a monotonically decreasing trend and remains constant, which is between numbers 48 and 55. The process then determines the value of T. 48 >T 49 T 49 >T 50 Continue this process until the decrease ends at number 55, corresponding to a temperature T_r = 36.5, which is the dropout point. Substitute the temperature values ​​and use the formula to calculate the response ratio.

[0029] in, , , Substituting the summation term into each value in the sequence from i=42 to 55 and subtracting T_b, the calculation results are as follows: molecular: ; First term in the denominator: ; Summation term in denominator: ; Sum of denominators: 3.4 + 20.3 = 23.7; Substituting into the formula, we get: ; The results indicate that the intensity of thermal mutation in this segment is relatively weak and the value is too low to meet the subsequent judgment conditions. Therefore, response ratios are constructed and uniformly numbered to form a structured dataset, resulting in a thermal change trend response profile set.

[0030] The formula aims to construct a normalized ratio that measures the intensity of temperature change during a thermal abrupt change. The formula structure reflects the relative relationship between the magnitude of the abrupt change and the degree of temperature disturbance, where the numerator... This represents the temperature rise from the initial point to the peak point during the abrupt change, and is a direct indicator of the intensity of the abrupt change. The denominator consists of two parts, the first term... It represents the amplitude of the temperature drop after the peak, which is used to quantify whether there is a callback behavior in the mutation. The second term is the sum of the offsets of all temperature sampling values from the starting point to the falling point from the starting temperature, reflecting the total temperature fluctuation in the entire interval. The sum of the two constitutes a normalization reference for the amplitude of the molecular temperature rise, forming a structure similar to the signal-to-noise ratio. For the same amplitude of temperature rise, if it is accompanied by more剧烈波动 will be assigned a smaller ratio, while the mutation segment with concentrated temperature rise and small disturbance will exhibit a higher response ratio. This structure helps to highlight the mutation characteristics with clear temperature fluctuation trends and stable signals. Through this construction, the thermal change behavior can be distinguished, classified, and the response intensity evaluated.

[0031] The temperature mutation response ratio sequence is used to characterize the relative intensity and fluctuation characteristics of temperature changes in each thermal mutation segment. It is a numerical set obtained based on normalization calculations. Each ratio corresponds to a specific mutation segment, and the value reflects the comprehensive intensity relationship of the net increase amplitude experienced by the temperature from the start to the peak in this segment relative to its falling amplitude and overall fluctuation degree. When the ratio is large, it indicates that the temperature shows a rapid, concentrated, and less disturbed violent upward trend during the mutation process, with strong mutation characteristics. On the contrary, it indicates that although there is a temperature rise, it is accompanied by disturbance or repeated fluctuations, making this mutation not have typical high-intensity behavior. Therefore, this sequence can be used as an important basic data index for subsequent classification discrimination, thermal feature calibration, and system state identification.

[0032] S313: According to the thermal change trend response profile set, jointly judge the temperature rise and fall directions, duration, and response ratio of each paragraph. If it meets the upward trend and the duration is greater than the set temperature rise duration threshold, and the response ratio is higher than the set response intensity threshold, it is labeled as the rapid rise type; otherwise, it is marked as the stable fluctuation type. Summarize the classification labels and establish a structured table item according to the section number sequence to obtain the thermal mutation section response feature label table; According to the thermal change trend response profile set, sequentially retrieve the calibrated section numbers, response ratios, and start and end times in each group structure. To judge the upward trend, calculate the difference ΔT = T_p - T_b between the starting temperature and the peak temperature, and obtain the number difference Δn = p - b. Combining the sampling period Δt = 0.1s, the temperature rise duration τ = Δn × Δt is obtained. For example, when Δn = 5, τ = 0.5s. Set the temperature rise duration threshold τ_thresh = 1.5s and the response intensity threshold R_thresh = 1.0. If τ ≥ τ_thresh and the response ratio Rs ≥ R_thresh, this section is labeled as "rapid rise type"; if any condition is not met, it is labeled as the stable fluctuation type classification label. For example, in the calculation result of the section number range [40, 55], Rs = 0.1266 < R_thresh and τ = 0.5s < τ_thresh, not meeting the dual conditions, so this section is judged as the stable fluctuation type. After processing all sections in turn, form a structured table of the numbers and classification results, as shown in Table 4: Table 4 Classification of Thermal Change Response Characteristics: ; As shown in Table 4, the classification labels have been completed according to the set threshold, and the response feature label table of the thermal mutation segment has been obtained.

[0033] Please see Figure 5 Step S4 is as follows: S411: Based on the thermal mutation segment response feature label table, extract the directionality and duration information of each thermal change stage, determine whether the directionality is continuously unidirectional and the duration does not exceed the set stable duration threshold. If both conditions are met at the same time, it is recorded as a stable segment, and a stable trend stage index set is generated. Based on the thermal change segment response feature label table, the directional marker and duration value corresponding to each thermal change stage are first extracted. The directionality is represented by a discrete sequence, marked as rising (+1), falling (-1), or flat (0). The duration is calculated by multiplying the difference between adjacent numbers by the sampling period. Assuming a segment number range is [40, 52] and the sampling period is 0.1 seconds, the duration τ = (52 - 40 + 1) × 0.1 = 1.3 seconds. A stable duration threshold τthreshold is set to 2.0 seconds. For this segment's directional sequence... The system determines whether there is a directional mutation, i.e. whether all directional labels are equal. If the directional labels are consistent and τ≤τ threshold, then the segment meets the unidirectional stability condition. The system writes the numbered segment and directional type into the structure list and iterates through all thermal change stages to execute the above judgment process. Finally, the system outputs the set of stage numbers that meet the unidirectional trend condition to form a stable trend stage index set.

[0034] S412: Based on the stable trend stage index set, filter out the segments that have been marked as stable, identify the directional repeated change characteristics of the remaining stages, and determine whether the duration exceeds the set stable duration threshold. If it does, record it as an unstable segment and obtain the unstable trend stage number set. Based on the stable trend stage index set, all segments identified as stable stages are removed from the complete thermal change stage number list. The remaining segments are then subjected to instability assessment. For each remaining segment, a directional marker sequence is extracted, and the number of directional changes is counted. Let the directional sequence be... Five changes can be counted. If this value is greater than the upper limit of stability judgment once, then the direction of the segment is unstable. Further, its duration τ is obtained. For example, if the number range is [60, 81], τ = (81-60+1)×0.1 = 2.2 seconds. Set the stable duration threshold τ threshold = 2.0 seconds. Since 2.2 seconds > 2.0 seconds, the duration exceeds the threshold range. Therefore, the segment meets the unstable condition. Record the segment number, number of changes and duration, etc., and process all remaining thermal change stages in sequence. Filter out all segments that meet the conditions and summarize them into a numbered set to generate an unstable trend stage number set.

[0035] S413: Based on the stable trend stage index set and the unstable trend stage number set, all stages are uniformly assigned classification labels according to their numbers, with stable segments marked as 0 and unstable segments marked as 1, to construct a complete classification mapping and obtain the lens thermal response segment structure division results. Based on the stable trend stage index set and the unstable trend stage number set, all thermal change stages are organized into a unified structure according to segment number. A binary classification method is used to label stable segments as 0 and unstable segments as 1. For example, number [40, 52] corresponds to label 0, and number [60, 81] corresponds to label 1, forming a mapping key-value pair structure. Then, the numbered segments are arranged in chronological order to construct a segment order vector. In this structure mapping, each record item contains a range of segment numbers and a corresponding behavior classification code. The structure type can be defined as a two-dimensional structure array. The fields include "starting number", "ending number" and "classification code". The data is output uniformly by index and summarized and coded to form a structured boundary for the lens in the thermal mutation response process, thus establishing the lens thermal response segment structure division result.

[0036] Please see Figure 6 The S5 steps are as follows: S511: Based on the classification coding information in the segmentation results of the lens thermal response segmentation structure, extract all segment numbers and their corresponding status labels, combine the segment time index, establish a one-to-one mapping between the number and the time series, and aggregate each segment according to the classification value to generate a segment classification mapping table. Based on the classification codes in the lens thermal response segmentation results, the start number, end number, and classification label of all segments are retrieved first. The label value is uniformly encoded as "0" representing stability and "1" representing instability. After extracting the number sequence, the number-time index mapping relationship in the lens temperature sampling records is called to convert each number segment into a time period. For example, the time period corresponding to segment [40, 52] is [4.0s, 5.2s]. The converted results are bound with the corresponding classification labels to form a triplet structure with the fields of start time, end time, and classification code. This is uniformly stored in the classification mapping table structure to establish a unified mapping between the thermal response structure code and the time axis. Sample data is shown in Table 5. Table 5 Segment Classification Mapping Table: ; As shown in Table 5, the classification structure has completed time alignment and type labeling, and a segment classification mapping table has been generated.

[0037] S512: Based on the segment classification mapping table, obtain the start and end time range covered by each numbered segment, align it with the current running cycle identifier, perform the intersection calculation of the start and end time and the running cycle timestamp, filter each category segment within the running cycle and record the order and label, and obtain the hot segment status sequence within the running cycle. Based on each record in the segment classification mapping table, extract its start and end times and compare them with the current lens control unit's operating cycle identifier. The operating cycle identifier is in the form of time pairs, such as [3.5s, 9.0s]. Perform intersection judgment on each time period in the classification table with the operating cycle time period. For example, if the segment [4.0s, 5.2s] falls completely within the operating cycle, retain the segment and extract its classification label and time range. If a certain category segment partially overlaps with the operating cycle, such as [8.5s, 9.5s], then the intersection segment [8.5s, 9.0s] is truncated as a valid segment and written into the record table. Remove the non-intersecting parts. All the time periods after intersection will be sorted according to the chronological order and uniformly assigned segment number numbers, numbered sequentially as D1, D2, D3... and stored in the structure array. For each record, establish a time-series record to obtain the hot segment state sequence within the operating cycle.

[0038] S513: Based on the state sequence of the hot zone within the operating cycle, aggregate and integrate all state labels in chronological order, construct a unified data structure, and embed timestamps, classification labels and operating number information in sequence to generate vehicle-mounted camera component state monitoring data processing records. Based on the state sequence of hot zones within the operating cycle, each segment (D1, D2, D3, etc.) is traversed sequentially according to time. The start time, end time, and status code fields are read and encapsulated into an operating status segment data frame with a standard structure. The structure format is uniformly {operation number, timestamp range, status identifier}, and the current operation number identifier R_ID of the lens control unit is added. If the current cycle number is R05, then each frame is uniformly associated with R_ID=R05. All segment data frames are sequentially spliced ​​to form an operating status description data body and recorded in the lens component status recording area. The summary structure fields are {R_ID, T_start, T_end, S_label}. The output complete record array is the vehicle-mounted lens component status monitoring data processing record.

[0039] A vehicle-mounted camera assembly status monitoring data processing system includes: The temperature acquisition module is used to perform S1: acquire internal temperature data of the vehicle-mounted lens assembly during operation, obtain the operation cycle identification signal, bind the temperature value of each sample with the corresponding sampling time, and generate a heat source temperature time record matrix. The mutation localization module is used to execute S2: calculate the difference between adjacent temperature sampling points in the heat source temperature time record matrix, filter all sampling points whose absolute difference value is greater than the set mutation threshold, extract the time index and sampling number of the corresponding sampling point, perform error regression analysis on the subsequent temperature sequence, calibrate the mutation boundary point interval, and output the thermal mutation event boundary localization result. The response feature module is used to execute S3: based on the boundary location results of thermal mutation events, extract the interval between the start sampling number and the end sampling number, identify the order of temperature fluctuation direction changes, establish thermal change stage classification labels in combination with the duration, and generate a thermal mutation segment response feature label table. The segment determination module is used to execute S4: based on the directionality and duration of each thermal change stage in the thermal change segment response feature label table, it divides stable segments into unstable segments, constructs segment behavior feature classification codes, and outputs the lens thermal response segment structure division results; The status output module is used to execute S5: based on the classification coding in the lens thermal response section structure division result, establish a lens operation status description data body, and output the vehicle-mounted lens component status monitoring data processing record.

[0040] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for processing data of a vehicle-mounted lens assembly state monitoring, characterized in that, The method comprises the following steps: S1: collecting internal temperature data during the operation of the vehicle-mounted lens assembly, obtaining an operation cycle identification signal, binding each temperature sampling value with the corresponding sampling time, and generating a heat source temperature time record matrix; S2: calculating the difference between adjacent temperature sampling points in the heat source temperature time record matrix, screening sampling points with absolute difference values greater than a set mutation threshold, extracting the time index and sampling number of the corresponding sampling points, and performing error regression analysis on the subsequent temperature sequence to determine the mutation boundary point interval and output the heat mutation event boundary positioning result; S3: based on the heat mutation event boundary positioning result, extracting the starting sampling number and ending sampling number interval, identifying the temperature fluctuation direction change sequence, combining the duration to establish a heat variation stage classification label, and generating a heat mutation section response feature label table; S4: according to the directionality and duration of each heat variation stage in the heat mutation section response feature label table, dividing the stable section and the unstable section to construct a section behavior feature classification code, and outputting the lens heat response section structure division result; S5: based on the classification code in the lens heat response section structure division result, establishing a lens operation situation description data body, and outputting the vehicle-mounted lens assembly state monitoring data processing record.

2. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The stable section is a heat variation stage with continuous unidirectional change in directionality and duration within a set stable duration threshold range. The unstable section is a heat variation stage with repeated changes in directionality and duration exceeding the set stable duration threshold range.

3. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The heat source temperature time record matrix includes a sampling time index, a temperature value binding group, and an operation cycle identification signal. The heat mutation event boundary positioning result includes a mutation point time index, a mutation point sampling number, and mutation interval boundary calibration information. The heat mutation section response feature label table includes a pre-mutation temperature section, a mutation peak position, a falling point index, a temperature fluctuation direction sequence, a heat variation duration, and a heat variation stage classification label. The lens heat response section structure division result includes stable section classification code, unstable section classification code, and section relationship mapping information. The vehicle-mounted lens assembly state monitoring data processing record includes a lens operation situation description data body, a time sequence integration structure, and a current operation cycle classification code.

4. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The heat source temperature time record matrix acquisition step specifically comprises: S111: collecting the output signal of the temperature sensor during the operation of the vehicle-mounted lens assembly, obtaining a temperature value sequence, recording each sampling time stamp based on the time node corresponding to each temperature sampling, extracting the correspondence between sampling time and temperature value, constructing each sampling pair into a paired data set, and generating a temperature time binding data frame; S112: according to the temperature time binding data frame, retrieving the time stamp sequence recorded in each binding data, identifying the starting time point and ending time point of the current vehicle-mounted lens assembly operation cycle, extracting the corresponding temperature data pair in the time period, and generating a binding data set within the operation cycle; S113: Based on the running cycle binding data set, all temperature values are arranged in time stamp order in turn, and matrix reorganization is performed according to the corresponding sampling time, the time stamp is used as the horizontal index, and the temperature value is used as the vertical vector element, and the heat source temperature time record matrix is established.

5. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The heat mutation event boundary positioning result obtaining step is specifically: S211: Based on the heat source temperature time record matrix, difference operation is performed on the temperature values of adjacent sampling points, the position index of any one group of continuous sampling points in the vertical temperature value vector is extracted, the temperature difference value is calculated, and all temperature difference values are compared with the set mutation threshold value one by one, the temperature difference sample whose absolute difference value is greater than the mutation threshold value is screened, the sampling point time stamp and sequence number corresponding to the temperature difference sample are extracted, and a temperature mutation sampling index set is generated; S212: Based on the temperature mutation sampling index set, the sampling index position is aggregated, whether the time interval between the indexes is continuous is less than the preset aggregation interval threshold value is used for segment identification, the continuous sampling points meeting the aggregation condition are classified into the same paragraph, the time value and the number range corresponding to the starting and ending sampling points of each paragraph are extracted, and a mutation time section index set is generated; S213: According to the mutation time section index set, residual regression processing is performed on the temperature sampling sequence corresponding to each section, the deviation between the trend curve fitted by the section temperature sequence and the original sequence is measured, the local mutation inflection point position of the residual curve is identified, the boundary time point corresponding to the inflection point is calibrated, all section boundary information is integrated, and the heat mutation event boundary positioning result is obtained.

6. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The heat mutation section response feature label table obtaining step is specifically: S311: Based on the heat mutation event boundary positioning result, the starting time point and the ending time point in each mutation section are extracted, the corresponding starting sampling number and ending sampling number are obtained through the index mapping table, the interval number set is constructed, and the heat variation sampling interval number set is obtained; S312: The heat variation sampling interval number set is obtained, the complete temperature sequence corresponding to each number interval is extracted, the index position of the highest temperature value in the mutation section is identified as the peak point, the starting point of the continuous monotone increasing segment is traced back as the reference point before the mutation, and the terminal point of the first monotone decreasing interval is found as the falling point position. The temperature mutation response ratio is calculated, the heat variation profile structure is constructed combined with the section number, and the heat variation trend response profile set is obtained; S313: According to the heat variation trend response profile set, the temperature rising and falling direction, the duration, and the response ratio of each paragraph are jointly judged. If the rising trend is satisfied and the duration is greater than the set temperature rising duration threshold value, and the response ratio is higher than the set response intensity threshold value, it is marked as rapid rising type, otherwise it is marked as stable fluctuation type. The classified labels are summarized and the structured table items are established according to the number section sequence number, and the heat mutation section response feature label table is obtained.

7. The vehicle-mounted lens assembly state monitoring data processing method according to claim 6, characterized in that, The calculation formula of the temperature mutation response ratio is: ； wherein, represents a temperature jump response ratio, represents a jump peak temperature, represents a temperature start point before the jump, represents a fall back point temperature, denotes the i-th temperature sampling value in the interval, , is the jump start and end index positions.

8. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The lens heat response section structure division result obtaining step is specifically: S411: Based on the heat mutation section response feature label table, the directionality and duration information of each heat variation stage is extracted, and it is judged whether the directionality is unidirectional and the duration is not more than the set stable duration threshold. If both conditions are met, it is recorded as a stable section, and a stable trend stage index set is generated; S412: According to the stable trend stage index set, the stable section is filtered out, the remaining stage is identified for directionality change feature, and it is judged whether the duration exceeds the set stable duration threshold. If it is satisfied, it is recorded as an unstable section, and an unstable trend stage number set is obtained; S413: Based on the stable trend stage index set and the unstable trend stage number set, all stages are uniformly assigned classification marks according to the number. The stable section is marked as 0, and the unstable section is marked as 1. The complete classification mapping is constructed, and the lens heat response section structure division result is obtained.

9. The vehicle-mounted lens assembly state monitoring data processing method according to claim 1, characterized in that, The vehicle-mounted lens component state monitoring data processing record acquisition step is specifically: S511: Based on the classification coding information in the lens heat response section structure division result, all section numbers and corresponding state labels are extracted, a one-to-one mapping of number and time sequence is established combined with section time index, and each section is aggregated according to classification value, and a section classification mapping table is generated; S512: Based on the section classification mapping table, the start and end time range covered by each numbered section is obtained, and is aligned with the current running period identifier. The intersection calculation of start and end time and running period timestamp is performed, the classification sections in the running period are filtered and the order and label are recorded, and the heat section state sequence in the running period is obtained; S513: According to the heat section state sequence in the running period, all state labels are aggregated and integrated in time sequence, and a unified data body structure is constructed. Time stamp, classification label and running number information are embedded in sequence to generate vehicle-mounted lens component state monitoring data processing record.

10. A vehicle-mounted lens assembly status monitoring data processing system, characterized by, The system is used to realize the vehicle-mounted lens component state monitoring data processing method of any one of claims 1-9, comprising: The temperature acquisition module is used to execute S1: collecting internal temperature data of the vehicle-mounted lens component during operation, obtaining a running period identifier signal, binding each sampling temperature value with the corresponding sampling time, and generating a heat source temperature time record matrix; The mutation positioning module is used to execute S2: calculating the difference value of adjacent temperature sampling points in the heat source temperature time record matrix, screening all sampling points with absolute difference value greater than the set mutation threshold, extracting the time index and sampling number of the corresponding sampling points, and performing error regression analysis on the subsequent temperature sequence. The mutation boundary point interval is calibrated, and the heat mutation event boundary positioning result is output; The response feature module is used to execute S3: based on the heat mutation event boundary positioning result, the start sampling number and end sampling number interval are extracted, the temperature fluctuation direction change sequence is identified, the heat variation stage classification label is established combined with the duration, and the heat mutation section response feature label table is generated; The segment determination module is configured to perform S4: according to the direction and duration of each thermal variation stage in the thermal mutation segment response feature label table, dividing the stable segment and the unstable segment to construct the segment behavior feature classification code, and outputting the lens thermal response segment structure division result. The state output module is configured to perform S5: based on the classification code in the lens thermal response segment structure division result, establishing a lens running situation description data body, and outputting the vehicle-mounted lens component state monitoring data processing record.

Images