Shell air tightness testing system and method

Abstract

The invention relates to the technical field of gas leakage detection, in particular to a shell airtightness testing system and method, and the system comprises a pressure monitoring module, a gradient feature module, an abnormality screening module, a leakage path module and a sealing evaluation module. According to the method, the equidistant sampling points are set in the structure, the pressure time sequence difference value is extracted, multi-section continuous pressure data are constructed, the detail capturing capability of pressure change is enhanced, high-precision recognition of stable sections is achieved, the change rate difference value of adjacent sections is combined, local abnormal point positions are accurately extracted, the sensitivity of abnormal recognition and the positioning accuracy are improved, and the accuracy of abnormal recognition is improved. Through combination of periodic pressure intensity ratio analysis and path trend judgment, a pressure intensity change path chain with directivity and continuity can be constructed, the sealing state is evaluated according to a path pressure intensity gradient value and an adjacent region gradient difference, an abnormal path section is accurately recognized, local sealing integrity judgment is supported, and shell local leakage recognition efficiency and result analysis depth are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gas leakage detection, and particularly to a housing airtightness test system and method. Background Art

[0002] Gas leakage detection technology includes relevant methods and equipment for detecting the gas leakage condition in a sealed structure. Its core content is to identify and judge the behavior of gas leakage from a closed structure through methods such as pressure difference, gas concentration change, and acoustic wave response, and conduct classification analysis and positioning based on leakage parameters. This detection technology systematically covers detection schemes for various closed structures such as pressure vessels, pipeline systems, automotive components, electronic devices, and sealed packages, and is widely used in scenarios such as industrial manufacturing, safety monitoring, and quality control. Commonly used gas leakage detection methods on the market include differential pressure method, helium mass spectrometry method, acoustic emission method, pressure holding method, and bubble method, etc. Each detection method selects a suitable detection method and detection device according to the characteristics of the structure to be measured and the sealing requirements.

[0003] Among them, the housing airtightness test scheme refers to a device and its supporting detection method for airtightness detection of a housing with a closed structure and strict sealing requirements. It mainly covers the detection process of filling compressed air into the housing in a sealed state and then judging whether there is leakage by measuring the pressure change. It usually includes a gas filling mechanism, a pressure detection component, and a supporting pressure stability control component and a test chamber. By comparing the pressure data changes before and after detection through a standardized test procedure, the sealing performance of the housing is determined.

[0004] In the existing housing airtightness detection process, the static data comparison method is generally used to judge and analyze the housing sealing state, lacking dynamic modeling of the whole process of pressure change, resulting in the result presentation tending to the overall trend and ignoring local details. In a multi-segment structure, single-point pressure acquisition is difficult to reflect abnormal characteristics in spatial distribution. Especially when the sealing state fluctuates weakly, it is easy to miss detection due to insufficient data coverage. Most of the data processing processes rely on the overall pressure difference judgment, ignoring the internal connection between the pressure change direction, time sequence structure, and local characteristics, and it is difficult to realize trend recognition and path backtracking. The abnormal recognition standard is mainly set based on experience, lacking quantitative analysis for local fluctuation behaviors, restricting the resolution ability of abnormal point positioning. In terms of path determination, traditional methods cannot construct a pressure change path based on the data evolution process, and it is unclear about the starting point and diffusion direction of leakage occurrence, resulting in the difficulty of effectively capturing the sealed failure area. The result evaluation standard is too macroscopic, lacking fine division based on the pressure change gradient and comparison difference with adjacent areas, which is not conducive to accurately identifying the weak area of sealing performance, causing limited detection range, fuzzy spatial judgment, and lagging fault recognition, and reducing the adaptability of the detection scheme in complex structure or high-precision demand scenarios. Summary of the Invention

[0005] The object of the present invention is to solve the drawbacks existing in the prior art, and a shell airtightness test system that can improve the efficiency of local leakage identification of the shell and the depth of result analysis is proposed.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A shell airtightness test system, the shell airtightness test system includes a pressure monitoring module, a gradient feature module, an anomaly screening module, a leakage path module, and a seal evaluation module, wherein: The pressure monitoring module is arranged at equidistant sampling points in each functional section of the shell structure, and is used to collect the pressure sequence of equidistant points in each functional section of the shell structure, calculate the pressure difference between adjacent points and adjacent moments, and generate partition pressure difference data; The gradient feature module is used to extract the extreme value frequency of the sliding window according to the partition pressure difference data, compare the gradient stability threshold to screen the low value section of the fluctuation amplitude, and generate a stable pressure evolution section identification result; The anomaly screening module is used to compare the section change rate difference with the anomaly threshold based on the stable pressure evolution section identification result, screen out the anomaly points, and record the corresponding section number and time tag to obtain a local pressure anomaly identification list; The leakage path module is used to statistically calculate the periodic pressure ratio between each anomaly point and other sections based on the local pressure anomaly identification list, screen the spatial position between the two points with the largest ratio difference, judge the change trend of the pressure value on the path section, and establish a leakage trend path tracking chain; The seal evaluation module is used to compare the path pressure difference with the average value of the gradients on both sides according to the leakage trend path tracking chain, mark the path exceeding the seal boundary value, and obtain the determination result of the local seal integrity of the shell.

[0007] As a further solution of the present invention, the partition pressure difference data includes a multi-section pressure time series structure, sampling point number information, and the pressure change amplitude per unit time; The stable pressure evolution section identification result includes a section stability label, a time period continuity parameter, and a characteristic vector fluctuation amplitude; The local pressure anomaly identification list includes an anomaly point number, time identification information, and a local change rate difference; The leakage trend path tracking chain includes a pressure change direction, a spatial position relationship of the path section, and a periodic pressure accumulation ratio; The determination result of the local seal integrity of the shell includes a pressure change value, an average difference of the pressure gradients in adjacent areas, and an abnormal path section identification record.

[0008] As a further solution of the present invention, the pressure monitoring module includes an equidistant sampling sub-module, a pressure aggregation sub-module, and a pressure difference calculation sub-module, where: The equidistant sampling sub-module is arranged at the equidistant sampling points of each functional section in the housing structure, and is used to calibrate the sampling position numbers of each section according to the total length of the housing structure at fixed intervals, and collect the pressure change values per unit time at each sampling number by using a high-frequency sensor, obtain the bound data set of the section position number and the pressure change value, and generate the section pressure sampling data; The pressure aggregation sub-module is used to, based on the section pressure sampling data, combine the section number and the sampling time sequence value, arrange the pressure change values at multiple moments under the same section number in chronological order, construct the mapping relationship data set of the section number and the corresponding continuous time period pressure value, and establish the partition pressure data sequence; The pressure difference calculation sub-module is used to, based on the partition pressure data sequence, according to the time series pressure value and the section number value, perform an absolute difference calculation on the pressure values at two consecutive moments in each sequence one by one, classify and summarize the difference results according to the section number, and generate the partition pressure difference data.

[0009] As a further solution of the present invention, the gradient feature module includes a sliding window construction sub-module, a frequency extraction sub-module, and a gradient screening sub-module, where: The sliding window construction sub-module is used to obtain the partition pressure difference data, combine the time series value and each section number, construct adjacent interval sliding windows for the pressure difference sequence of each section according to the time index, set the window width and the sliding step value, and divide the window segments by time series grouping under each section to generate the partition sliding window sequence; The frequency extraction sub-module is used to, based on the partition sliding window sequence, according to the pressure difference set in each window, count the number of repetitions of the maximum value in each window, establish the corresponding relationship sequence between the window time index and the frequency value, and generate the window feature vector sequence; The gradient screening sub-module is used to, according to the window feature vector sequence, combine the window index value, the maximum value frequency sequence, and the gradient stability threshold, perform amplitude change calculation and threshold judgment on the feature sequence of each section in chronological order, and use the formula: ; Calculate the characteristic fluctuation amplitude value of each section , judge whether it is continuously lower than the set gradient stability threshold, obtain the continuous time segment set, and establish the stable pressure evolution section identification result, where, is the maximum value frequency of the section in the th window, is the The maximum frequency of the section within the th window, is the total number of section windows.

[0010] As a further solution of the present invention, the abnormal screening module includes a change rate extraction sub-module, a difference calculation sub-module, and an abnormal identification sub-module, where: The change rate extraction sub-module is used to calculate the difference between the pressure values and time values at two consecutive moments in each section based on the stable pressure evolution section identification result, according to the pressure sequence and time tag data of each identified section, and calculate the pressure change rate per unit time in chronological order to obtain a section pressure change rate sequence; The difference calculation sub-module is used to read the change rate of each section and the change rates of its two adjacent sections before and after according to the section pressure change rate sequence, calculate the absolute difference between the change rates of the current section and the two adjacent sections on both sides in chronological order and take the average value to obtain a sequence of change difference amounts between adjacent sections, and establish a pressure change difference sequence; The abnormal identification sub-module is used to call the current difference data and the local abnormal change judgment threshold according to the pressure change difference sequence, and combine the section number and time tag corresponding to each point, and use the formula: ; Calculate the abnormal intensity value of the th section at the current time point , and perform screening, retain the data points with abnormal intensity values greater than zero, extract the time tag and section number, and establish a local pressure abnormal identification list, where, is the pressure change difference of the th section, is the local abnormal change judgment threshold.

[0011] As a further solution of the present invention, the leakage path module includes a period accumulation sub-module, a ratio screening sub-module, and a path tracking sub-module, where: The period accumulation sub-module is used to perform time merging on the pressure change values of each abnormal section within consecutive periods based on the local pressure abnormal identification list, combined with the abnormal section number and the pressure change value per unit time, and accumulate the pressure values according to the period to obtain the total pressure value of the abnormal section in the period, and obtain the total pressure of the abnormal section in the period; The ratio screening sub-module is used to read the corresponding section number and the total pressure value of other sections in the same period according to the total pressure value of the abnormal section in the period, calculate the period pressure ratio pair by pair, extract the two section numbers with the largest ratio difference, and obtain the corresponding spatial position distance value, and obtain the pair of spatial sections with the largest pressure ratio difference; The path tracking submodule is used to determine the start and end segment numbers according to the maximum pressure ratio difference space segment pair, retrieve the pressure change sequence of all segments between the two points in a continuous period, and judge the direction of the pressure value change trend using the formula: ; Calculate the total amount of pressure gradient trend in the path segment , and combined with the trend of symbol changes to determine the overall pressure trend, establish a leakage trend path tracking chain, where For the path The total periodic pressure of the segment, For the path The total periodic pressure of the segment, is the total number of path segments, is a sign function, indicating positive or negative.

[0012] As a further solution of the present invention, the sealing assessment module includes a pressure gradient submodule, a neighboring gradient submodule and a sealing determination submodule, wherein: The pressure variation submodule is used to calculate the pressure variation per unit length on each path segment according to the leakage trend path tracking chain, combining the periodic pressure value and path length parameter in the path segment, determine the pressure variation level along the path segment, and generate a path segment pressure gradient sequence; The adjacent area gradient submodule is used to calculate the pressure gradient per unit length of adjacent segments on both sides of the path segment based on the path segment pressure gradient sequence and the periodic pressure values ​​and segment spacing of the adjacent primary segments on the left and right sides of the path segment, and group them according to the lateral position to obtain the average value group of the adjacent area pressure gradient; The sealing determination submodule is used to calculate the pressure gradient of each path segment and the gradient mean of its left and right adjacent areas based on the adjacent area pressure gradient mean group, compare the degree of gradient difference, and determine whether it exceeds the sealing performance cutoff value, mark the path segments that meet the conditions, and establish the local sealing integrity determination result of the shell.

[0013] Another object of the present invention is to provide a shell air tightness testing method, the method is used to implement the shell air tightness testing system, comprising the following steps: S1: Obtain the pressure values ​​of equidistant sampling points in each section, calculate the pressure difference at consecutive moments, group them by number, and generate partition pressure difference data; S2: constructing a sliding window based on the partition pressure difference data, extracting the maximum frequency, establishing a feature vector, calculating the frequency change amplitude, screening the stable section, and generating a stable pressure evolution section identification result; S3: Calculate the difference in the rate of change between the current and adjacent sections based on the identified results of the stable pressure evolution section, screen for abnormal points, and obtain a list of identified local pressure anomalies; S4: Based on the list of identified local pressure anomalies, statistically calculate the periodic pressure ratio, judge the path trend, judge the trend of the pressure value change on the path section, and establish a leakage trend path tracking chain; S5: Calculate the pressure change value of the path according to the leakage trend path tracking chain, compare it with the average gradient of the adjacent area, mark the path exceeding the seal demarcation value, and form a determination result of the local seal integrity of the housing.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by setting sampling points with equidistant distribution, continuously recording the pressure changes at each point per unit time, establishing partition pressure difference data, enhancing the accuracy expression of the dynamic pressure change, extracting the maximum frequency in the pressure difference according to the sliding time window, constructing a feature vector sequence, realizing the continuous characterization of the pressure fluctuation state, screening the change amplitude of the feature sequence can exclude the interference of random perturbations, accurately define the section with stable pressure trend, conduct a local comparison of the pressure change rate in the stable section, extract abnormal points, realize the differential identification of subtle perturbations, judge the pressure change direction through the periodic pressure ratio comparison of abnormal points, establish a spatial path chain with continuous trend characteristics, further calculate the pressure change value of the path section and the pressure gradient difference of the adjacent area, identify the abnormal change interval, refine the quantitative evaluation of the local seal state of the structure, improve the identification depth of the local leakage risk in the complex structure and the structural response accuracy, and enhance the structural analysis ability and fault tracing ability of the detection data. Description of the Drawings

[0015] Figure 1 is the system flow chart of the present invention; Figure 2 is the flow chart of the pressure monitoring module of the present invention; Figure 3 is the flow chart of the gradient feature module of the present invention; Figure 4 is the flow chart of the abnormal screening module of the present invention; Figure 5 is the flow chart of the leakage path module of the present invention; Figure 6 is the flow chart of the seal evaluation module of the present invention. Detailed Embodiment

[0016] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 The shell air tightness test system provided by the present invention includes a pressure monitoring module, a gradient characteristic module, an abnormality screening module, a leakage path module and a sealing assessment module, wherein: The pressure monitoring module is set at equidistant sampling points of each functional section in the shell structure, and is used to use a high-frequency sensor to record the pressure change value per unit time at each sampling point in real time, group all time series pressure data into a continuous pressure data sequence according to the section number, perform absolute difference calculation on the pressure values ​​at two consecutive moments, and generate partition pressure difference data; The gradient feature module is used to construct a sliding window for adjacent time periods based on the pressure difference set of each functional section in the partition pressure difference data, extract the maximum frequency of the pressure difference in each window and form a window feature vector sequence, screen the change amplitude of the feature vector sequence of each section, extract the time period where the pressure fluctuation amplitude is continuously lower than the gradient stability threshold, and generate the stable pressure evolution section identification result; The anomaly screening module is used to obtain the current pressure change rate in each marked section based on the stable pressure evolution section identification result and compare it with the change rate of the two adjacent sections before and after, calculate the absolute difference between them, compare the difference with the local anomaly change judgment threshold, extract the points greater than the local anomaly change judgment threshold, and record the corresponding section number and time label to obtain the local pressure anomaly identification list; The leakage path module is used to identify all abnormal section numbers in the list based on local pressure anomalies, accumulate and calculate the pressure change value per unit time in continuous cycles, count the periodic pressure ratios of each abnormal point and other sections, screen the spatial position between the two points with the largest ratio difference, determine whether the pressure value on the path segment shows a unidirectional increasing or decreasing trend, and establish a leakage trend path tracking chain; A sealing evaluation module, which is used to calculate the pressure change value per unit path length according to the pressure values of path segments in the leakage trend path tracking chain, synchronously obtain the average pressure gradients of the first-level adjacent areas on both the left and right sides of the path, compare the degree of difference, and mark the path segments with a difference degree greater than the sealing performance demarcation value as abnormal sealing paths, so as to form a determination result of the local sealing integrity of the housing.

[0019] In the embodiments of the present invention, the partition pressure difference data includes a multi-segment pressure time series structure, sampling point number information, and the pressure change amplitude per unit time. The stable pressure evolution segment identification result includes a segment stability label, a time period continuity parameter, and an eigenvector fluctuation amplitude. The local pressure anomaly identification list includes abnormal point number, time identification information, and local change rate difference. The leakage trend path tracking chain includes the pressure change direction, the spatial position relationship of path segments, and the periodic pressure accumulation ratio. The determination result of the local sealing integrity of the housing includes the pressure change value, the average difference of the pressure gradients in adjacent areas, and the identification record of abnormal path segments.

[0020] Please refer to Figure 2 , the pressure monitoring module includes an equidistant sampling sub-module, a pressure collection sub-module, and a pressure difference calculation sub-module, where: The equidistant sampling sub-module is arranged at the equidistant sampling points of each functional segment in the housing structure, and is used to calibrate the sampling position numbers of each segment at a fixed interval according to the total length of the housing structure, collect the pressure change values per unit time at each sampling number using a high-frequency sensor, obtain the bound data set of the segment position number and the pressure change value, and generate segment pressure sampling data; In this embodiment, when setting the equidistant sampling points of each functional segment in the housing structure, first, it is necessary to obtain the structural dimensions and functional segment division information of the housing. For example, the total length is 2.0 meters, divided into section A and section B, each section is 1.0 meter long, and the sampling interval is set to 0.5 meter. Then, two sampling points are arranged in each section, numbered P1, P2, P3, and P4 respectively, and the corresponding spatial positions are 0.0 meter, 0.5 meter, 1.0 meter, and 1.5 meters. This setting is based on the housing length and the range of functional segments, and the number of numbers and position sequences are obtained by integer division of the section boundary position coordinates and the sampling interval value. After the sampling points are arranged, the section attributes and number identifiers are respectively assigned, and at the same time, the pressure sampling values in the initial state are recorded. For example, a high-frequency pressure sensor is used to read the initial pressure value of each position at a sampling frequency of 1 second. During the reading process, it is necessary to ensure that the sampling environment is constant and there is no instantaneous impact change, and the pressure value corresponding to each point is bound by time and position to obtain the following data: Table 1 Initial Pressure Table of Monitoring Points Sampling point number Functional section Sampling location (m) Initial pressure (Pa) P1 Section A 0.0 101325 P2 Section A 0.5 101330 P3 Section B 1.0 101328 P4 Section B 1.5 101332 As shown in Table 1, the pressure sampling values at all sampling points are near atmospheric pressure, with a difference of no more than 10 Pa, reflecting the basic uniformity of the initial air pressure distribution inside the shell. The pressure value record for each sampling point is based on its position number and time identifier. After the sampling data is completed, it is uniformly encapsulated into a data set, and a bound data structure containing fields such as number, section, position, time, and pressure value is constructed in a structured form, and finally the section pressure sampling data is generated.

[0021] The pressure aggregation sub-module is used to, based on the section pressure sampling data, combine the section number and the sampling time sequence value, arrange the pressure change values at multiple moments under the same section number in chronological order, construct a mapping relationship data set between the section number and the pressure values in the corresponding continuous time period, and establish a partition pressure data sequence; Among them, for the above-mentioned based on the section pressure sampling data, it is necessary to call the numbers, functional section attributes, and corresponding time series pressure values of each sampling point, classify and integrate the pressure data with the same section number. For example, for the A section in Table 1, all the time series pressure values of P1 and P2 are extracted, arranged in chronological order, and a mapping array of time and pressure values is constructed. For the data integration operation within each section, it is necessary to ensure that the time step of the pressure data is consistent to form a standardized data sequence format. During the data calling process, the pressure value sequences of each sampling point are read in sequence according to the section number, and a time index is constructed internally, and the corresponding sampling point data is expanded in ascending order. For example, if there are sampling points P1 and P2 in section A, and the pressure values recorded at point P1 from t0 to t4 are 101325, 101326, 101324, 101327, 101325 Pa, and the corresponding values at point P2 are 101330, 101331, 101329, 101330, 101332 Pa, then these two groups of data form the pressure time series of section A. During the pressure value aggregation process, these multi-point data are integrated into a two-dimensional matrix, with each column being the pressure time series of a sampling point, and the rows representing the pressures of each point at the same moment. This matrix is then bound with the section number to form a data block. By performing the above operations on multiple sections, the pressure data of all sections are merged into several independent time series, and each series has a sampling point number index, a section number label, and chronological pressure values, and finally a partition pressure data sequence is obtained.

[0022] The pressure difference calculation sub-module is used to, based on the partition pressure data sequence, calculate the absolute difference between the pressure values at two consecutive moments in each sequence one by one according to the time series pressure value and the section number value, classify and summarize the difference results according to the section number, and generate partition pressure difference data; Among them, based on the partition pressure data sequence, it is necessary to perform difference processing on the pressure sequence of each section. Call the pressure values at consecutive sampling times within each section, and obtain the absolute difference in pressure change between adjacent times through point-by-point difference. During the difference calculation process, traverse each time series according to the section number, and perform difference processing on the pressure values between every two consecutive times. For example, the consecutive pressure records at point P1 in section A are 101325, 101326, 101324, 101327, 101325 Pa, and the difference sequences are 1, 2, 3, 2 Pa respectively. Subsequently, perform averaging and merging on the difference sequences of each sampling point. On this basis, average the difference sequences of all sampling points within the same section according to time points, and finally obtain the average pressure difference of this section at each time step. At the same time, establish the corresponding time index and section number. Through this series of calculation and processing processes, the pressure change trends between different sampling points are integrated into a data set reflecting the pressure fluctuation degree of the overall section. For example, the average differences of section A from t1 to t4 are 2.0, 2.5, 2.0, 2.5 Pa, then the average amplitude of its pressure change within unit time is stable within ±2.5 Pa. After data collection, structured data recording fields such as section number, time node, and average pressure change amplitude are formed, and finally the partition pressure difference data is generated.

[0023] Please refer to Figure 3 , the gradient feature module includes a sliding window construction sub-module, a frequency extraction sub-module, and a gradient screening sub-module, where: The sliding window construction sub-module is used to obtain the partition pressure difference data. Combining the time series values and each section number, construct adjacent interval sliding windows for the pressure difference sequence of each section according to the time index, set the window width and sliding step values, and divide the window segments by time series grouping under each section to generate a partition sliding window sequence; In this embodiment, obtain the partition pressure difference data, group the time series pressure differences of each partition according to the section number, and each group contains the pressure difference data corresponding to consecutive multiple time points. For example, in section A, if sampled at a frequency of once per second within 10 seconds; The data sequence can be expressed as: (unit: kPa). For this sequence to construct a sliding window, it is necessary to set the window width and step size. Let the window width be 4 and the step size be 2. Then the sliding window division results are window 1 (from the 1st second to the 4th second), window 2 (from the 3rd second to the 6th second), window 3 (from the 5th second to the 8th second), and window 4 (from the 7th second to the 10th second). During the window division process, first call the index information of each sampling point in the time series and the pressure difference data for position matching, and then extract the continuous data values within this length according to the set window length. For example, the data corresponding to window 1 is , and window 2 is , and so on. Each window is indexed by the start time, and a mapping data table between the window number and its pressure difference sequence is constructed, as shown in Table 2.

[0024] Table 2 Data Table of Pressure Differences in Sliding Windows

[0025] As shown in Table 2, the construction of the sliding window depends on the original time series data of the partition pressure difference, the set window width, and the step size. After partitioning, the data structure is automatically numbered according to the time index, and the pressure difference sequence is loaded into each sliding window and stored, finally generating a partition sliding window sequence.

[0026] The frequency extraction sub-module is used to, based on the partition sliding window sequence, according to the set of pressure differences within each window, count the number of repetitions of the maximum value in each window, establish a corresponding relationship sequence between the window time index and the frequency value, and generate a window feature vector sequence; Among them, based on the partition sliding window sequence, it is necessary to analyze the pressure difference sequence within each sliding window, extract its maximum value, and determine whether the maximum value appears more than once within the current window. If it appears two or more times, it is recorded as one maximum value repetition event. For example, for the sequence of window 1 , the maximum value is 0.6, which appears 1 time, and the frequency is 1; for window 2 , the maximum value 0.6 still only appears 1 time; and if the sequence in a certain window, such as window 5, is , then the maximum value 0.6 appears 2 times, and the frequency is 2. After performing the statistical process with the same logic for all windows, an ordered pair is established according to the window number and the frequency result, such as , forming a frequency sequence for each section , and this sequence is the window feature vector sequence, and its data structure is used to characterize the local features of the fluctuation behavior of this section from the perspective of pressure difference.

[0027] The gradient screening sub-module is used to, according to the window feature vector sequence, in combination with the window index value, the maximum value frequency sequence, and the gradient stability threshold, calculate the amplitude change and perform threshold judgment on the feature sequence of each section in chronological order, using the formula: ; Calculate the feature fluctuation amplitude value of each section , judge whether it is continuously lower than the set gradient stability threshold, obtain the set of continuous time segments, and establish the identification result of the stable pressure evolution section. Among them, is the maximum value frequency of the section in the th window, is the section in the The maximum frequency within a window is the total number of segment windows; In this embodiment, according to the window feature vector sequence, first call the frequency sequence within each segment, denoted as , as obtained in the previous section is , set the frequency stability threshold The setting basis of is the expected fluctuation range of the maximum frequency within the sliding windows of each segment. This threshold is determined by the joint analysis of the standard deviation and the average value of the frequency sequences under multiple different segments in the same structure. Its value setting depends on the overall mean level and the standard deviation change range of the maximum frequency sequence within the window. Specifically, when the overall mean of the maximum frequency sequence is concentrated between 1.0 and 2.0, and the standard deviation does not exceed 0.5, to avoid misjudging a minor sudden increase as an unstable state, the stability judgment threshold for this type of segment is set to 1.2. In the case where the structural stress response maintains a single peak, the frequency difference fluctuates within 1 for the vast majority. Therefore, 1.2 is set as the fluctuation limit, and this value is slightly adjusted as the sequence mean rises. Usually, when the mean exceeds 2.5, the threshold is raised above 1.8, and then it is necessary to calculate whether the fluctuation value of the segment frequency sequence is lower than this threshold. To achieve quantitative determination, the sequence is brought into the calculation to obtain: ; At this time, it is compared with the frequency stability threshold , , indicating that the fluctuation amplitude of the current segment is within the stable range, and within the time period when the fluctuation is continuously lower than the threshold, that is, windows 1 to 5 continuously meet the conditions. Therefore, it is judged that the overall time period is in a stable state of pressure change, and the stable pressure evolution segment identification result is obtained.

[0028] Please refer to Figure 4 , the anomaly screening module includes a change rate extraction sub-module, a difference calculation sub-module, and an anomaly identification sub-module, where: The change rate extraction sub-module is used to, based on the stable pressure evolution segment identification result, calculate the difference between the pressure values and time values at two consecutive moments in each segment according to the pressure sequence and time tag data of each identified segment, and calculate the pressure change rate per unit time in chronological order to obtain the segment pressure change rate sequence; Among them, based on the identification results of the stable pressure evolution section, the pressure time series data and corresponding time tags recorded in the identified section are extracted. For the time series data in each section, the pressure values and corresponding times at two consecutive time points are extracted point by point, and the pressure change rate per unit time is calculated. In an actual scenario, taking section A1 as an example, if the pressure values of a certain monitoring point at t1 = 10s and t2 = 11s are P1 = 120kPa and P2 = 121.2kPa respectively, then its change rate is (121.2 - 120) / 1 = 1.2kPa / s. In this way, the pressure change rates of sections A2 and A3 are calculated to be 2.8kPa / s and 1.6kPa / s respectively. Then, the previous section (A0) and the next section (A2) of section A1 are extracted respectively. In the case where there is no previous section for A1, it is filled with adjacent known values. Similarly, for A2, the previous one is A1 and the next one is A3. When the next one of A3 is missing (A4), it is filled. Through these operations, the current change rate of each identified section and the change rates of its adjacent sections can be obtained, which are summarized as follows: Table 3 Local Pressure Change Calculation Table

[0029] As shown in Table 3, each section lists the difference after comparing and calculating the change rate with adjacent sections, preparing for subsequent abnormal judgment, and finally obtaining the section pressure change rate sequence.

[0030] The difference calculation sub-module is used to read the change rate of each section and the change rates of its two adjacent sections before and after according to the section pressure change rate sequence, calculate the absolute difference between the change rates of the current section and the sections on both sides in time sequence and take the average value, obtain the change difference sequence between adjacent sections, and establish the pressure change difference sequence; According to the records in each row of Table 3, the current pressure change rate of each identified section and the change rates of its adjacent sections before and after are extracted, and the absolute difference between the three is calculated and averaged to obtain the pressure change difference between this section and its adjacent sections. For example, the current change rate of section A2 is 2.8kPa / s, and the adjacent ones before and after are 1.2kPa / s and 1.6kPa / s. The pressure difference between the three is calculated as follows: , , and the average of the two is (1.6 + 1.2) / 2 = 1.4kPa / s. Therefore, the of A2. Similarly, for A1, the calculation is as follows: , , and the average difference is (0.2 + 0.4) / 2 = 0.3kPa / s. The difference of A3 is (|1.6 - 2.8| + |1.6 - 1.1|) / 2 = (1.2 + 0.5) / 2 = 0.85kPa / s. This calculation process quantifies the difference measurement between each section and its adjacent sections, thus establishing the pressure change difference sequence.

[0031] Anomaly recognition sub-module, which is used to call the current difference data and the local anomaly change judgment threshold according to the pressure change difference sequence, and combine the section number and time label corresponding to each point, and use the formula: ; Calculate the anomaly intensity value of the section at the current time point, and perform screening, retain the data points with anomaly intensity values greater than zero, extract the time label and section number, and establish a local pressure anomaly recognition list. Among them, is the pressure change difference of the section, is the local anomaly change judgment threshold; Among them, according to the calculated pressure change difference sequence above, call each difference and the local judgment threshold , and perform point-by-point anomaly judgment in combination with the section number and time label of each point, calculate the anomaly intensity value using the formula. For the A1 section, substitute the parameters: , , and calculate: ; For the A2 section, substitute: , : ; For the A3 section, substitute: , : ; Compare the of each section with 0. If , then this point is regarded as an anomaly point, record its time label and section number, and finally establish a local pressure anomaly recognition list. This result shows that the anomaly intensity of section A2 is significantly higher than that of the other two sections, and it is more likely to be recognized as an anomaly, indicating that the pressure fluctuation in this section has inconsistent characteristics in the spatial neighborhood and has the value of recognition.

[0032] Please refer to Figure 5 , the leakage path module includes a periodic accumulation sub-module, a ratio screening sub-module, and a path tracking sub-module, where: The periodic accumulation sub-module is used to perform time merging on the pressure change values of each abnormal section in consecutive periods based on the local pressure anomaly recognition list, combine the abnormal section number and the pressure change value per unit time, and accumulate the pressure change values according to the period to obtain the total pressure of the abnormal section in the period; Among them, based on the abnormal section numbers listed in the local pressure anomaly recognition list, for each monitoring area corresponding to each number, collect the pressure change value per unit time. For example, in a continuous cycle with a time interval of 1 second, sequentially collect the pressure value sequences of sections S1 to S5 at each second moment, denoted as , where is the section number, is the time index. When performing the periodic cumulative operation, first calculate the change amplitude of the pressure value within each second, and then sum the change amplitudes of 10 consecutive seconds to obtain the total pressure of this period. For example, the pressure change values of section S1 from t = 1 to t = 10 seconds are: [180.2, 182.5, 183.0, 181.9, 182.1, 183.4, 184.0, 183.5, 183.8, 184.1], and the sum of its change values is 1820.5 Pa. This value is the pressure cumulative amount of S1 in the current period. Similarly, calculate S2 to S5 to obtain their respective periodic totals, and then generate a periodic pressure total record table as shown in Table 1. This process is applicable to the preliminary quantitative assessment of the gas leakage trend in a certain area in the on-site pressure monitoring system to obtain the periodic pressure total of the abnormal section.

[0033] Table 4 Periodic Pressure Total Table

[0034] As shown in Table 4, each section corresponds to a set of periodic pressure values for subsequent ratio comparison and trend recognition.

[0035] The ratio screening sub-module is used to read the corresponding section number and the periodic pressure totals of other sections in the same period according to the periodic pressure totals of the abnormal sections, calculate the periodic pressure ratios pair by pair, extract the two section numbers with the largest ratio difference, obtain the corresponding spatial position distance value, and get the spatial section pair with the largest pressure ratio difference; According to the results of the total periodic pressure, the total pressure of each abnormal section and the remaining non-abnormal sections in the same period is respectively selected for ratio calculation. That is, assuming that the S3 section is the target abnormal section, its periodic pressure is 1955.2 Pa, and the ratios are calculated with S1 (1820.5 Pa), S2 (1750.0 Pa), S4 (1890.7 Pa), and S5 (1785.9 Pa) respectively: 1955.2 / 1820.5≈1.074, 1955.2 / 1750.0≈1.117, 1955.2 / 1890.7≈1.034, 1955.2 / 1785.9≈1.095. The maximum ratio difference is 1.117 between S2. Then, the ratios of S2 to other points are calculated in reverse and the differences are taken. The maximum difference is formed by S2 to S3, and it is recorded as the maximum pressure ratio difference section pair. Combining the section numbers and the corresponding spatial coordinate information, such as S2 is at x = 150 m and S3 is at x = 290 m, and the spatial distance is 140 m. This section of the area is used as the leakage trend interval to be judged, and the maximum pressure ratio difference spatial section pair is obtained.

[0036] The path tracing sub-module is used to determine the starting and ending section numbers according to the maximum pressure ratio difference spatial section pair, retrieve the pressure change sequences of all sections between the two points in consecutive periods, judge the direction of the pressure value change trend, and use the formula: ; Calculate the total pressure change trend of the path segment , and combine the sign change trend to judge the overall pressure direction, and establish a leakage trend path tracing chain. Among them, is the total periodic pressure of the th section on the path, is the total periodic pressure of the th section on the path, is the total number of path sections, is the sign function, indicating positive and negative; According to the obtained maximum pressure ratio difference spatial section pair, taking the section from S2 to S3 as an example, extract the total periodic pressure of each section on this path segment. If there are multiple consecutive sections on this path, record their pressure values in order of number as . Suppose there are 5 consecutive sections, and the pressure values are: 1750.0, 1790.5, 1825.3, 1885.1, 1955.2 Pa. Calculate them in turn using the direction trend formula as follows: ; ; ; ; ; This result shows that the total pressure on the path segment shows a continuous increasing trend, and the total trend intensity is 205.2 Pa. Through this result, it can be judged that the pressure direction is unidirectional growth from S2 to S3, and then a leakage trend path tracking chain is established.

[0037] Please refer to Figure 6 , the seal evaluation module includes a pressure change sub-module, an adjacent area gradient sub-module, and a seal determination sub-module, where: The pressure change sub-module is used to calculate the pressure change per unit length on each path segment according to the leakage trend path tracking chain, combined with the periodic pressure value and path length parameter within the path segment, determine the pressure change level along the path segment, and generate a path segment pressure gradient sequence; Among them, according to the leakage trend path tracking chain, the spatial position information and periodic pressure value of each path segment in the chain are extracted, the path segment pressure data is matched with the corresponding path length data, the start and end numbers, section center position, length range and its periodic pressure measurement value of the path segment are recorded, and the path length is directly measured through the structural CAD data. For example, the length of section P1 is 3.5 meters, the length of section P2 is 4.0 meters, and the length of section P3 is 2.5 meters. The periodic pressure is extracted from the average pressure data per period by a high-frequency sampling device. For example, the periodic pressure difference of P1 is 12.3 Pa, P2 is 16.5 Pa, and P3 is 9.8 Pa. Divide the pressure change value of each path segment by the path length to obtain the pressure gradient per unit length. Calculate the pressure gradient per unit length of P1 as 12.3 / 3.5 = 3.51 Pa / m, P2 as 4.13 Pa / m, and P3 as 3.92 Pa / m in this way. The obtained path segment pressure change result is recorded as the path segment pressure gradient sequence for subsequent comparison and judgment with the adjacent area to obtain the path segment pressure gradient sequence.

[0038] The adjacent area gradient sub-module is used to calculate the pressure gradient per unit length of the adjacent sections on both sides of the path segment based on the path segment pressure gradient sequence, according to the periodic pressure value and section spacing of the first-level adjacent sections on the left and right of the path segment, and group and average according to the lateral position to obtain the adjacent area pressure gradient average group; Among them, based on the sequence of pressure gradients of path segments, the periodic pressure values and corresponding section spacings of the left and right first-level adjacent areas adjacent to each path segment are called, the adjacent area numbers, spatial positions and path segments are associated, the pressure change values of the adjacent areas are extracted and uniformly processed with quantization parameters such as the path segment length, and calculations are performed in a unified dimension. For example, if the pressure difference of the left adjacent area of P1 is 10.5 Pa, the right adjacent area is 9.9 Pa, and the path length is 3.5 m, then the gradients per unit length are calculated as 3.0 Pa / m and 2.83 Pa / m respectively. For P2, the left adjacent area is 13.2 Pa, the right adjacent area is 12.7 Pa, then the gradients per unit length are 3.3 Pa / m and 3.18 Pa / m respectively. The average values of the gradients on the left and right sides are calculated respectively. The average value of the adjacent areas of P1 is (3.0 + 2.83) / 2 = 2.915 Pa / m, and for P2 it is (3.3 + 3.18) / 2 = 3.24 Pa / m. For P3, the left and right adjacent areas are 8.1 Pa and 7.6 Pa respectively, then the average value is (3.24 + 3.04) / 2 = 3.14 Pa / m. In this way, the average group of adjacent area pressure gradients corresponding to each path segment is obtained, forming the average group of adjacent area pressure gradients.

[0039] A seal determination sub-module, which is used to count the pressure gradients of each path segment and the average gradients of its left and right adjacent areas according to the average group of adjacent area pressure gradients, compare the degree of gradient difference, and determine whether it exceeds the seal performance demarcation value, mark the path segments that meet the conditions, and establish the determination result of the local seal integrity of the housing; According to the mean pressure gradient group of the adjacent areas, the path segment pressure gradient sequence is called to compare with the mean gradients on both sides of the adjacent areas, and the difference between the pressure gradient of each path segment and the mean gradient of its adjacent areas is calculated one by one. For example, the pressure gradient of the P1 path segment is 3.51Pa / m, the corresponding adjacent area mean is 2.915Pa / m, and the difference is 0.595Pa / m. The difference of P2 is 4.13-3.24=0.89Pa / m, and that of P3 is 3.92-3.14=0.78Pa / m. The sealing performance boundary value of 1.5Pa / m is set based on the maximum allowable leakage gradient change value of the gas channel inside the structural shell. This value is obtained by measuring the maximum pressure change range per unit length in an isobaric test of multiple groups of shells with different structures under a standard closed state for 10 minutes, combined with the shell unit thickness (generally between 35mm), the average length of the path segment (about 2.55m) and the type of gas (such as the commonly used nitrogen The influence of pressure on the sealing performance of the structural wall is comprehensively evaluated by considering physical factors such as air or dry air, and finally determining that when the pressure difference between the path segment and the adjacent area is greater than 1.5Pa / m, the pressure difference between the path segment and the adjacent area can cause the pressure of the structural gap to increase or decrease in one direction, thereby triggering problems such as crack expansion or sealing ring shedding. The demarcation value shows a weak growth trend with the shortening of the path length and the increase of the pressure change fluctuation degree. It is suitable for the pressure assessment standard of the medium-strength shell of typical precision equipment, and thus has high rationality and versatility. Referring to this threshold, the gradient difference of each path segment is compared with the demarcation value. As shown in Table 5, the difference of all path segments does not exceed the threshold, so it is not marked as an abnormal path segment. When the difference of a path segment exceeds the threshold, the path segment is determined to be a sealing abnormal path segment. The path segment number, interval range and gradient information are integrated and written into the determination record to form the determination result of the local sealing integrity of the shell.

[0040] Table 5 Path segment and adjacent area pressure data

[0041] As shown in Table 5, the pressure data of the path segments and adjacent areas are collected periodically and uniformly converted into pressure differences per unit length. The differences between each path segment and the adjacent area are below the preset boundary value and are not marked as abnormal sealed path segments. If the subsequent periodic fluctuations increase and cause the difference to exceed the threshold, the judgment result will be synchronously updated to an abnormal path.

[0042] In an embodiment of the present invention, the shell air tightness testing method comprises the following steps: S1: Obtain the pressure values ​​of equidistant sampling points in each section, calculate the pressure difference at consecutive moments, group them by number, and generate partition pressure difference data; S2: Construct a sliding window based on the partition pressure difference data, extract the maximum frequency, establish a feature vector, calculate the frequency change amplitude, screen the stable section, and generate the stable pressure evolution section identification result; S3: Calculate the difference in the change rate between the current and adjacent sections based on the identification result of the stable pressure evolution section, screen for abnormal points, and obtain a list of locally abnormal pressure identifications; S4: Based on the list of locally abnormal pressure identifications, calculate the periodic pressure ratio, judge the path trend, judge the change trend of the pressure value on the path section, and establish a leakage trend path tracking chain; S5: Calculate the path pressure gradient value according to the leakage trend path tracking chain, compare it with the average gradient of the adjacent area, mark the path exceeding the seal boundary value, and form a determination result of the local seal integrity of the housing.

[0043] In the embodiment of the present invention, the detailed steps and parameters involved in the above housing airtightness test method refer to the description of the housing airtightness test system shown above Figures 1 to 6 and will not be elaborated here, but it is not used to limit the present invention.

[0044] The above is only a preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as the technical content of the present invention is not departed from, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A shell air tightness test system, characterized in that: The shell air tightness test system includes a pressure monitoring module, a gradient characteristic module, an abnormality screening module, a leakage path module and a sealing assessment module, wherein: The pressure monitoring module is arranged at equidistant sampling points of each functional section in the shell structure, and is used to collect the pressure sequence of equidistant points of each functional section of the shell structure, calculate the pressure difference between adjacent points and adjacent moments, and generate partition pressure difference data; The gradient feature module is used to extract the frequency of sliding window extreme values ​​according to the partition pressure difference data, screen the low-value segment of fluctuation amplitude by comparing the gradient stability threshold, and generate a stable pressure evolution segment identification result; The anomaly screening module is used to compare the segment change rate difference with the anomaly threshold based on the stable pressure evolution segment identification result, screen out abnormal points, and record the corresponding segment number and time label to obtain a local pressure anomaly identification list; The leakage path module is used to count the periodic pressure ratios of each abnormal point and other sections based on the local pressure anomaly identification list, screen the spatial position between the two points with the largest ratio difference, determine the pressure value change trend on the path segment, and establish a leakage trend path tracking chain; The sealing assessment module is used to track the chain according to the leakage trend path, compare the path pressure difference with the average of the gradients on both sides, mark the path that exceeds the sealing boundary value, and obtain the local sealing integrity judgment result of the shell.

2. The housing air tightness testing system according to claim 1, characterized in that: The zone pressure difference data includes a multi-segment pressure time series structure, sampling point number information, and a pressure change amplitude per unit time; The stable pressure evolution section identification result includes a section stability label, a time period continuity parameter, and a characteristic vector fluctuation amplitude; The local pressure anomaly identification list includes the anomaly point number, time identification information and local change rate difference; The leakage trend path tracking chain includes the direction of pressure change, the spatial position relationship of the path segments, and the periodic pressure accumulation ratio; The shell local sealing integrity determination result includes the pressure gradient value, the mean difference of the pressure gradient of the adjacent areas and the abnormal path segment identification record.

3. The housing air tightness testing system according to claim 1, characterized in that: The pressure monitoring module includes an equidistant sampling submodule, a pressure collection submodule and a pressure difference calculation submodule, wherein: The equidistant sampling submodule is set at the equidistant sampling points of each functional section in the shell structure, and is used to calibrate the sampling position number of each section at a fixed interval according to the total length of the shell structure, collect the pressure change value per unit time at each sampling number by using a high-frequency sensor, obtain the binding data set of the section position number and the pressure change value, and generate the section pressure sampling data; The pressure collection submodule is used to arrange the pressure change values ​​at multiple moments under the same segment number in chronological order based on the segment pressure sampling data, in combination with the segment number and the sampling timing value, to construct a mapping relationship data set between the segment number and the pressure value of the corresponding continuous time period, and to establish a partition pressure data sequence; The pressure difference calculation submodule is used to calculate the absolute difference between two consecutive pressure values ​​in each sequence based on the partition pressure data sequence, according to the time series pressure value and the segment number value, and classify and summarize the difference results according to the segment number to generate partition pressure difference data.

4. The housing air tightness testing system according to claim 1, characterized in that: The gradient feature module includes a sliding window construction submodule, a frequency extraction submodule and a gradient screening submodule, wherein: The sliding window construction submodule is used to obtain the partition pressure difference data, combine the time series value and each segment number, construct an adjacent interval sliding window according to the time index of the pressure difference sequence of each segment, set the window width and sliding step value, divide the window fragments according to the time series grouping under each segment, and generate a partition sliding window sequence; The frequency extraction submodule is used to count the number of repetitions of the maximum value in each window based on the partition sliding window sequence and the pressure difference value set in each window, establish a corresponding relationship sequence according to the window time index and the frequency value, and generate a window feature vector sequence; The gradient screening submodule is used to calculate the amplitude change and threshold judgment of the feature sequence of each segment in chronological order according to the window feature vector sequence, combined with the window index value, the maximum frequency sequence and the gradient stability threshold, using the formula: ； Calculate the characteristic fluctuation amplitude value of each segment , determine whether it is continuously below the set gradient stability threshold, obtain a set of continuous time segments, and establish the stable pressure evolution segment identification result, where, For the Section The maximum frequency in the window, For the Section The maximum frequency in the window, is the total number of segment windows.

5. The housing air tightness testing system according to claim 1, characterized in that: The abnormal screening module includes a change rate extraction submodule, a difference calculation submodule and an abnormality identification submodule, wherein: The change rate extraction submodule is used to calculate the difference between the pressure value and time value of two consecutive moments in each segment based on the stable pressure evolution segment identification result and the pressure sequence and time tag data of each identified segment, and calculate the pressure change rate per unit time in chronological order to obtain the segment pressure change rate sequence; The difference calculation submodule is used to read the change rate of each segment and the change rates of the two adjacent segments before and after it according to the segment pressure change rate sequence, perform absolute difference calculation and average of the change rates of the current segment and the segments on both sides in time sequence, obtain the change difference sequence between adjacent segments, and establish the pressure change difference sequence; The anomaly identification submodule is used to call the current difference data and the local anomaly change judgment threshold according to the pressure change difference sequence, and combine the segment number and time label corresponding to each point, using the formula: ； Calculate the The abnormal intensity value of the segment at the current time point , and screen, retain the data points with abnormal intensity values ​​greater than zero, extract the time label and segment number, and establish a local pressure anomaly identification list, where, No. The pressure change difference of the section, It is the threshold for judging local abnormal changes.

6. The housing air tightness testing system according to claim 1, characterized in that: The leakage path module includes a cycle accumulation submodule, a ratio screening submodule and a path tracking submodule, wherein: The cycle accumulation submodule is used to perform time merging of the pressure change values ​​of each abnormal section in a continuous cycle based on the local pressure anomaly identification list, in combination with the abnormal section number and the pressure change value per unit time, and obtain the pressure accumulation value by periodic accumulation to obtain the total pressure of the abnormal section cycle; The ratio screening submodule is used to read the corresponding segment number and the total periodic pressure of other segments in the same period according to the total periodic pressure of the abnormal segment, calculate the periodic pressure ratio pair by pair, extract the two segment numbers with the largest ratio difference, obtain the corresponding spatial position distance value, and obtain the spatial segment pair with the maximum pressure ratio difference; The path tracking submodule is used to determine the start and end segment numbers according to the maximum pressure ratio difference space segment pair, retrieve the pressure change sequence of all segments between the two points in a continuous period, and judge the direction of the pressure value change trend using the formula: ； Calculate the total amount of pressure gradient trend of the path segment , and combined with the trend of symbol changes to determine the overall pressure trend, establish a leakage trend path tracking chain, where For the path The total periodic pressure of the segment, For the path The total periodic pressure of the segment, is the total number of path segments, is a sign function, indicating positive or negative.

7. The housing air tightness testing system according to claim 1, characterized in that: The sealing assessment module includes a pressure variation submodule, a neighboring gradient submodule and a sealing determination submodule, wherein: The pressure variation submodule is used to calculate the pressure variation per unit length on each path segment according to the leakage trend path tracking chain, combining the periodic pressure value and path length parameter in the path segment, determine the pressure variation level along the path segment, and generate a path segment pressure gradient sequence; The adjacent area gradient submodule is used to calculate the pressure gradient per unit length of adjacent segments on both sides of the path segment based on the path segment pressure gradient sequence and the periodic pressure values ​​and segment spacing of the adjacent primary segments on the left and right sides of the path segment, and group them according to the lateral position to obtain the average value group of the adjacent area pressure gradient; The sealing determination submodule is used to calculate the pressure gradient of each path segment and the gradient mean of its left and right adjacent areas based on the adjacent area pressure gradient mean group, compare the degree of gradient difference, and determine whether it exceeds the sealing performance cutoff value, mark the path segments that meet the conditions, and establish the local sealing integrity determination result of the shell.

8. A shell air tightness testing method, characterized in that: The method is used to implement the housing air tightness testing system according to any one of claims 1 to 7, comprising the following steps: S1: Obtain the pressure values ​​of equidistant sampling points in each functional section, calculate the pressure difference at consecutive moments, group them by number, and generate partition pressure difference data; S2: constructing a sliding window based on the partition pressure difference data, extracting the maximum frequency, establishing a feature vector, calculating the frequency change amplitude, screening the stable section, and generating a stable pressure evolution section identification result; S3: Calculate the difference in change rate between the current and adjacent sections based on the stable pressure evolution section identification result, screen abnormal points, and obtain a local pressure anomaly identification list; S4: Based on the local pressure anomaly identification list, the periodic pressure ratio is counted, the path trend is determined, the pressure value change trend on the path segment is determined, and a leakage trend path tracking chain is established; S5: Calculate the path pressure variation value according to the leakage trend path tracking chain, compare it with the gradient average of the adjacent area, mark the path that exceeds the sealing boundary value, and form a local sealing integrity judgment result of the shell.

Images