Sleep-aiding cabin sound insulation test system and method based on multi-source data analysis

Abstract

The invention discloses a sleep aiding cabin sound insulation test system and method based on multi-source data analysis, and relates to the technical field of sleep aiding cabin acoustic tests.According to the sleep aiding cabin sound insulation test system and method, characteristic environment parameters and characteristic coordinate points corresponding to sound pressure parameters are obtained, and sound pressure parameters of the characteristic environment parameters and the characteristic coordinate points are obtained according to the sound pressure parameters of the characteristic environment parameters and the characteristic coordinate points; calculating to obtain sound ring parameters of the characteristic coordinate points, calculating to obtain sound vibration parameters of the characteristic coordinate points according to sound vibration transmission ratios and vibration energy of the characteristic coordinate points, calculating to obtain sound engineering parameters according to the working condition scores and sound pressure parameters of the characteristic coordinate points, and calculating to obtain health scores; calculating to obtain a health score threshold range, training by constructing an abnormal data set, and generating an abnormal duration prediction formula; and according to the real-time data of the current work, whether a worker needs to carry out maintenance is judged, and the duration of next maintenance is calculated, so that efficient maintenance management is realized, and a guarantee is provided for equipment operation.

Description

Technical Field

[0001] This invention relates to the field of acoustic testing technology for sleep aid cabins, specifically a sound insulation testing system and method for sleep aid cabins based on multi-source data analysis. Background Technology

[0002] Existing methods for testing the sound insulation performance of sleep aid capsules mainly rely on human experience and single-point sound pressure measurement results for evaluation. The method based on fixed measurement points and static rules has obvious limitations in practical applications. On the one hand, single-point measurement results can only reflect the sound insulation performance of a local part of the capsule and cannot fully reflect the sound insulation distribution of the entire capsule. On the other hand, due to the spatial non-uniformity of the sound field inside the sleep aid capsule, the sound pressure level varies significantly at different locations, and traditional methods cannot reveal the overall sound insulation characteristics and its weak areas. In addition, existing tests are mostly conducted under static conditions and fail to consider the dynamic sound insulation performance fluctuations caused by external noise changes, air conditioning system operation, and the opening and closing of doors and windows during actual use, resulting in insufficient representativeness and reliability of the test results. Meanwhile, traditional sound insulation testing methods only focus on acoustic measurements and fail to systematically analyze the sound insulation mechanism by combining multi-source information such as cabin structure vibration. Therefore, how to achieve spatial, dynamic, and multi-source integrated analysis of the sound insulation performance of sleep aid cabins in complex and ever-changing environments, effectively overcome the limitations of traditional single-point measurements, reveal the propagation path and main transmission mechanism of sound energy, and construct a complete evaluation system has become a key technical problem that needs to be solved in the field of sleep aid cabin sound insulation performance testing. Summary of the Invention

[0003] The purpose of this invention is to provide a sound insulation testing system and method for sleep aid cabins based on multi-source data analysis, so as to solve the problems raised in the prior art.

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for testing the sound insulation of a sleep aid cabin based on multi-source data analysis, the method comprising: Step S100: In the sleep aid cabin management platform, obtain the environmental parameters, sound pressure parameters, vibration parameters, and working condition parameters from the historical work records, and classify the historical work records according to whether they are abnormal. Through the correlation analysis algorithm, calculate the correlation coefficient between abnormal parameters and environmental parameters, and determine the characteristic environmental parameters of each sound pressure parameter. Step S200: Construct a sound field spatial coordinate system with the sleep aid chamber and the sound pressure sensor, and calculate the sound pressure parameters of the coordinate points according to the correlation coefficient of the characteristic environmental parameters and the spatial distance between the coordinate points. Then, classify the coordinate points according to their location information to obtain the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber. Step S300: Calculate the difference between the inside and outside of each coordinate point, and calculate the vibration energy of each coordinate point by calculating the structural distance between the coordinate point and the vibration sensor, calculate the sound-vibration transmission ratio of each coordinate point, and determine the characteristic coordinate point; Step S400: Set the training period, obtain the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, calculate the acoustic loop parameters of the characteristic coordinate points based on the characteristic environmental parameters and the sound pressure parameters of the characteristic coordinate points, calculate the acoustic vibration parameters of the characteristic coordinate points based on the acoustic vibration transmission ratio and vibration energy of the characteristic coordinate points, calculate the acoustic engineering parameters based on the working condition score and the sound pressure parameters of the characteristic coordinate points, summarize the acoustic loop parameters, acoustic vibration parameters and acoustic engineering parameters of all characteristic coordinate points, and calculate the health score; Step S500: Obtain work records with abnormal results from manual inspection, calculate the health score threshold range based on the health score of the work records, and generate an abnormal duration prediction formula by constructing an abnormal dataset for training. Step S600: Based on the real-time data of the current work, determine whether maintenance is required. If maintenance is not required, calculate the duration of the next maintenance. When the duration is reached, remind the staff to perform maintenance.

[0005] Furthermore, step S100 includes: Step S101: Install several sound pressure sensors inside and outside the sleep aid chamber to monitor the sound pressure parameters inside and outside the sleep aid chamber. Deploy several environmental monitoring devices around the inside and outside of the sleep aid chamber to collect various environmental parameters inside and outside the sleep aid chamber. Install several vibration sensors on the sleep aid chamber structure to obtain the vibration parameters of the sleep aid chamber during operation. Take the start time of the sleep aid chamber as the start time point and the end time of the sleep aid chamber as the end time point. Set the time period between the start and end time points and the end time point as the working duration of the work. Obtain the working condition parameters of the sleep aid chamber when performing the work. Summarize the sound pressure parameters, vibration parameters, environmental parameters and working condition parameters within the working duration to generate a work record and upload the work record to the sleep aid chamber management platform. Step S102: In the historical work record set, extract the value of the cabin sound pressure parameter in each historical work record, preset the sound pressure parameter threshold, set the sound pressure parameter exceeding the sound pressure parameter threshold as abnormal sound pressure, mark the historical work record with abnormal sound pressure as historical abnormal record, and mark the historical work record without abnormal sound pressure as historical normal record. Step S103: In the historical normal record set, extract the environmental parameters from each historical normal record, calculate the average value of each environmental parameter, in the historical abnormal record set, extract the environmental parameters from each historical abnormal record, and calculate the absolute difference with the average value of the environmental parameters, summarize the historical abnormal records that have the same abnormal parameter, combine the absolute difference of each environmental parameter in the historical abnormal record with the abnormal parameter, use a correlation analysis algorithm to calculate the correlation coefficient of each environmental parameter with the abnormal parameter, preset the correlation coefficient threshold, and set the environmental parameters that exceed the correlation coefficient threshold as the characteristic environmental parameters of the abnormal parameter; By arranging multiple sound pressure sensors and environmental monitoring devices inside and outside the sleep aid chamber, comprehensive and accurate sound pressure and environmental parameters can be obtained, improving the accuracy of monitoring and helping to accurately identify the working status of the sleep aid chamber. During the operation of the sleep aid chamber, sound pressure, vibration and environmental parameters are continuously monitored and detailed work records are generated, which can reflect the operating status of the sleep aid chamber in real time and provide a reliable data foundation for subsequent analysis. By analyzing historical normal and abnormal records, we can extract characteristic environmental parameters related to abnormal parameters, which helps us to better understand the causes of abnormal phenomena and provides data support for subsequent optimization of the design and operation of the sleep aid chamber.

[0006] Furthermore, step S200 includes: Step S201: Obtain the position information of each sound pressure sensor deployed in the sleep aid cabin. Taking the center position of the sleep aid cabin as the spatial origin, extract the position information of each sound pressure sensor into a three-dimensional coordinate point, construct a sound field spatial coordinate system, obtain the position information of the inner and outer edges of the sleep aid cabin in the sound field spatial coordinate system and divide it into several coordinate points, determine the three-dimensional coordinate point of each coordinate point, combine each sound pressure sensor with each coordinate point, calculate the spatial distance of each combination and summarize them to obtain the set of spatial distances between each coordinate point and each sound pressure sensor. Step S202: Extract the sound pressure parameters and environmental parameters of each historical operation record from the historical operation records. Classify the data according to the location of the sleep aid chamber where the data was collected to obtain data sets inside and outside the sleep aid chamber. For any data set, obtain the characteristic environmental parameters of a certain sound pressure parameter. Normalize the characteristic environmental parameters and calculate the sound pressure parameter of each coordinate point according to the following formula: ; Where Ai represents the i-th sound pressure parameter corresponding to the coordinate point, da represents the spatial distance between the a-th sound pressure sensor and the coordinate point, Df represents the correlation coefficient of the f-th characteristic environmental parameter, Eia represents the value of the i-th sound pressure parameter in the a-th sound pressure sensor, e represents the total number of characteristic environmental parameters, b represents the total number of sound pressure sensors, and c represents the preset correction coefficient. Step S203: Summarize the sound pressure parameters corresponding to each coordinate point inside and outside the sleep aid chamber to obtain the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber. By acquiring the location information of each sound pressure sensor and constructing a three-dimensional coordinate system, the sound pressure distribution inside and outside the sleep aid cabin can be accurately located, which helps to analyze the sound field characteristics in depth and provides a basis for effective sound insulation testing. By systematically integrating the sound pressure parameters inside and outside the sleep aid chamber with environmental parameters, the data collection becomes more comprehensive. By classifying and processing the data sets inside and outside the sleep aid chamber, the influence of different environments on sound pressure parameters can be distinguished, providing a rich source of information for subsequent analysis. By normalizing the calculation of characteristic environmental parameters, the consistency and comparability of data in the calculation process are ensured, the calculation accuracy of sound pressure parameters is improved, and effective monitoring of sound pressure parameter changes under different environmental conditions is realized. The sound pressure parameters at each coordinate point are calculated using formulas, which realizes the standardization and systematization of sound pressure data, better reflects the actual sound pressure at different locations, and helps to identify the quality of sound insulation performance.

[0007] Furthermore, step S300 includes: Step S301: In the historical abnormal record set of a certain abnormal parameter, extract the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber from a certain historical abnormal record, and calculate the difference of abnormal parameters inside and outside the sleep aid chamber for each coordinate point; Step S302: Extract the vibration parameters from the historical anomaly records, preset the monitoring time period, calculate the total vibration energy within the time period, calculate the structural distance between the coordinate points and the vibration sensor, and calculate the vibration energy at each coordinate point according to the following formula: ; Where H represents the vibration energy of the coordinate point, lx represents the structural distance between the coordinate point and the x-th vibration sensor, Kx represents the total vibration energy of the x-th vibration sensor, q represents a preset constant, and y represents the total number of vibration sensors; Step S303: Normalize the difference between the abnormal parameters corresponding to the coordinate points and the vibration energy, divide the normalized difference by the vibration energy to calculate the sound-vibration transmission ratio of the coordinate points, summarize the sound-vibration transmission ratio of each coordinate point in the historical abnormal records, calculate the average sound-vibration transmission ratio of each coordinate point, preset the threshold for the number of feature coordinate points as F, sort each coordinate point from high to low according to the average sound-vibration transmission ratio, and select the first F coordinate points as feature coordinate points; By extracting the set of sound pressure parameters from historical anomaly records, the sound pressure difference between the inside and outside of the sleep aid chamber can be effectively calculated, which helps to identify specific anomalies and thus provides the necessary basis for subsequent troubleshooting and handling. In anomaly monitoring, vibration parameters are extracted and vibration energy is calculated, making the assessment of the sleep aid chamber's operating status more comprehensive. By evaluating the vibration energy of different sensors, the impact of vibration on sound field characteristics and sleep aid chamber performance can be better understood. By normalizing the difference in abnormal parameters and the vibration energy, the sound-vibration transmission ratio is obtained, which provides an important quantitative indicator for acoustic systems. It can effectively reflect the propagation performance of sound waves in different media and provide a quantitative basis for sound insulation performance evaluation. By calculating the average acoustic-vibration transmission ratio at each coordinate point and selecting characteristic coordinate points based on preset thresholds, we can focus on the most representative areas for in-depth analysis, ensuring the targeted nature of the analysis and optimization, and helping to improve the effectiveness of the sleep aid cabin design. By automating the calculation and analysis process, the need for manual intervention is reduced, monitoring efficiency is improved, and the interference of human factors on the results is reduced, making data analysis more objective.

[0008] Furthermore, step S400 includes: Step S401: Select a consecutive number of days as the training period, obtain the work records within the training period, obtain the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, extract the characteristic environmental parameters and sound pressure parameters of the characteristic coordinate points from the work records, calculate the sound pressure difference of each characteristic coordinate point, normalize the characteristic environmental parameters and sound pressure parameters, and calculate the acoustic loop parameters of the characteristic coordinate points according to the following formula: ; Where G1 represents the acoustic loop parameter of the feature coordinate point, and Dh represents the correlation coefficient of the h-th feature environmental parameter. U1h represents the deviation between the h-th characteristic environmental parameter after normalization and the historical mean of the characteristic environmental parameter, and S represents the sound pressure difference value after normalization. Step S402: Extract the acoustic-vibration transmissibility and vibration energy of the feature coordinate points from the work record, normalize the acoustic-vibration transmissibility and vibration energy, and calculate the acoustic-vibration parameters of the feature coordinate points according to the following formula: ; Where G2 represents the acoustic vibration parameters of the characteristic coordinate point, R represents the normalized acoustic vibration transmission ratio, and H' represents the normalized vibration energy. Step S403: Extract the operating condition parameters from the work record, assign values ​​to each operating condition parameter, preset the weight of each operating condition parameter, and sum the weighted values ​​of each operating condition parameter to calculate the operating condition score. Calculate the acoustic parameters of the feature coordinate points according to the following formula: ; Wherein, G3 represents the acoustic parameters of the feature coordinate point, M represents the current working condition score, and M' represents the average working condition score; Step S404: Summarize the acoustic ring parameters, acoustic vibration parameters, and acoustic engineering parameters for each feature coordinate point, and calculate the health score according to the following formula: ; Where G represents the health score, G1 wn G2 wn G3 wn Let V1, V2, and V3 represent the acoustic loop parameter, acoustic vibration parameter, and acoustic engineering parameter at the nth feature coordinate point, respectively. Let V1, V2, and V3 represent the weights of the acoustic loop parameter, acoustic vibration parameter, and acoustic engineering parameter, respectively. w Let represent the weight of the w-th sound pressure parameter, u represent the total number of sound pressure parameters, and m represent the total number of feature coordinate points; By setting training cycles and continuously collecting work records, the operating status of the sleep aid chamber and its environmental changes can be effectively captured, which helps to build a more accurate model and improve the reliability of the analysis results. Normalizing the sound pressure difference and related parameters can eliminate data deviations caused by different dimensions, making the comparability between acoustic ring parameters, acoustic vibration parameters and acoustic engineering parameters under different environmental conditions stronger, and improving the accuracy and effectiveness of data analysis. By employing a comprehensive scoring method that combines acoustic ring parameters, acoustic vibration parameters, and acoustic engineering parameters, the operational health status of the sleep aid chamber can be fully assessed from multiple dimensions, providing managers with richer information and helping to formulate more scientific management strategies. By assigning values ​​to the operating parameters and performing weighted summation, the performance of the sleep aid capsule under different operating conditions can be more comprehensively reflected. The introduction of operating condition scoring makes the evaluation results more targeted and facilitates the optimization of equipment operation and maintenance. By summarizing the acoustic ring parameters, acoustic vibration parameters, and acoustic engineering parameters of all characteristic coordinate points and calculating the health score, the working status of the sleep aid pod can be assessed in real time, providing important support for operation and management, and enabling the rapid identification of potential problems and the implementation of countermeasures.

[0009] Furthermore, step S500 includes: Step S501: During the training cycle, when each work task is completed, staff members are arranged to inspect the sleep aid pod and generate inspection results. The inspection results of the work records during the training cycle are obtained, and the work records with abnormal inspection results are extracted. The health score of the work records is obtained, and the mean value of the health score is r1 and the standard deviation is r2. The lower limit threshold of the health score is Q1=r1-j×r2, and the upper limit threshold of the health score is Q2=r1+j×r2, where j represents the preset safety coefficient. The health score threshold range is [Q1,Q2]. Step S502: Divide the time period corresponding to the work record with two consecutive abnormal inspection results, and set the time period as the abnormal duration. Extract all work records within the time period, obtain the time interval between each work record, extract the work duration and health score of each work record, normalize and calculate the time interval, work duration, health score, and abnormal duration, and summarize them to construct an abnormal dataset and generate an abnormal duration prediction formula: ; Among them, G N+1 and T2 N+1 T1 represents the normalized health score and working hours corresponding to the (N+1)th work record, respectively. N Let t represent the normalized time interval corresponding to the Nth work record, T represent the normalized abnormal duration, M represent the total number of work records, t1, t2, and t3 represent the weights of health score, time interval, and work duration, respectively, and t represent the weight of abnormal duration prediction. The abnormal duration prediction formula is updated by training all abnormal datasets. The training process involves calculating the loss value of the current formula and adjusting the weights according to the loss value until the loss value meets the set standard value. The corresponding weights are then substituted into the abnormal duration prediction formula to update the abnormal duration prediction formula. By regularly arranging for staff to inspect the sleep aid pods during the training cycle, a systematic monitoring mechanism can be established, ensuring the operational safety and comfort of the sleep aid pods and providing timely verification for subsequent maintenance. The method of calculating the mean and standard deviation of health scores sets a reasonable threshold range for health scores, which takes into account both the safety and stability of equipment operation and can effectively identify potential failure risks. Extracting abnormal work records and determining their health scores can quickly screen out potential anomalies, helping to detect problems in the early stages, preventing greater damage to equipment, and improving equipment safety and reliability. By dividing the abnormal duration and analyzing the interrelationships between work records, it is possible to easily track abnormal states during equipment operation, enhance the overall understanding of the sleep aid chamber's operation, and facilitate the development of targeted repair and maintenance measures. By constructing anomaly datasets to generate anomaly duration prediction formulas, data support is provided for preventative maintenance, reducing downtime caused by equipment failures and thus improving efficiency.

[0010] Furthermore, step S600 includes: Step S601: Obtain the real-time environmental parameters, real-time sound pressure parameters, real-time vibration parameters, and real-time working condition parameters during the current operation; extract the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter; and calculate the real-time health score for the current operation. Step S602: Compare the real-time health score with the health score threshold range. If it exceeds the health score threshold range, immediately stop the machine and notify the staff for maintenance. If it is within the health score threshold range, notify the staff for maintenance after completing the current work. If it is below the health score threshold range, proceed to step S603. Step S603: Obtain the time interval between the current work and the previous work record, calculate the real-time predicted value of the abnormal duration using the abnormal duration prediction formula, and remind the staff to carry out maintenance when the real-time predicted value is reached; Calculating real-time health scores and comparing them with health score thresholds automates health management, enabling rapid identification of abnormal conditions in equipment operation, promoting timely intervention, and reducing the risk of equipment failure. When the real-time health score exceeds the threshold, the system can immediately shut down and notify staff for maintenance, ensuring equipment safety, reducing potential damage and downtime, and ensuring a safe and comfortable user experience. When the health score is within the normal range, the system will notify maintenance after the current work is completed, which effectively utilizes equipment time, reduces unnecessary downtime, and ensures that the equipment is always working in the best condition. By calculating the time interval between the current work and the last work, and using the abnormal duration prediction formula, it is possible to predict the abnormal duration in real time, providing a scientific basis for equipment maintenance, and timely reminding staff to carry out necessary maintenance to prevent failures caused by overuse of equipment.

[0011] To better implement the above method, a sleep aid cabin sound insulation testing system based on multi-source data analysis is also proposed. The system includes a characteristic environmental parameter module, a sound pressure parameter module, a characteristic coordinate point module, a health score module, a model training module, and a judgment and maintenance module. Characteristic environmental parameter module: In the sleep aid cabin management platform, environmental parameters, sound pressure parameters, vibration parameters, and working condition parameters from historical work records are obtained, and historical work records are classified according to whether they are abnormal. Through correlation analysis algorithm, the correlation coefficient between abnormal parameters and environmental parameters is calculated to determine the characteristic environmental parameters of each sound pressure parameter. Sound pressure parameter module: Construct a sound field spatial coordinate system by connecting the sleep aid cabin and the sound pressure sensor. Calculate the sound pressure parameters of the coordinate points based on the correlation coefficients of characteristic environmental parameters and the spatial distance between coordinate points. Then, classify the coordinate points according to their location information to obtain a set of coordinate sound pressure parameters inside the sleep aid cabin and a set of coordinate sound pressure parameters outside the sleep aid cabin. Feature coordinate point module: Calculates the internal and external differences of each coordinate point, and calculates the vibration energy of each coordinate point by calculating the structural distance between the coordinate point and the vibration sensor, calculates the sound-vibration transmission ratio of each coordinate point, and determines the feature coordinate point; Health scoring module: Set training period, obtain characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, calculate the acoustic loop parameter of the characteristic coordinate point based on the characteristic environmental parameters and the sound pressure parameter of the characteristic coordinate point, calculate the acoustic vibration parameter of the characteristic coordinate point based on the acoustic vibration transmission ratio and vibration energy of the characteristic coordinate point, calculate the acoustic engineering parameter based on the working condition score and the sound pressure parameter of the characteristic coordinate point, and summarize the acoustic loop parameter, acoustic vibration parameter and acoustic engineering parameter of all characteristic coordinate points to calculate the health score; Model training module: Obtain work records that are abnormal according to manual inspection, calculate the health score threshold range based on the health score of the work records, train by constructing an abnormal dataset, and generate an abnormal duration prediction formula; Maintenance Module: Based on real-time data of the current operation, determine whether maintenance is required. If maintenance is not required, calculate the duration of the next maintenance. When the specified duration is reached, remind staff to perform maintenance.

[0012] Furthermore, the characteristic environment parameter module includes a work record unit and a characteristic environment parameter determination unit: Work Recording Unit: Several sound pressure sensors are installed inside and outside the sleep aid chamber to monitor the sound pressure parameters inside and outside the sleep aid chamber. Several environmental monitoring devices are deployed around the sleep aid chamber to collect various environmental parameters inside and outside the sleep aid chamber. Several vibration sensors are installed on the sleep aid chamber structure to obtain the vibration parameters of the sleep aid chamber during operation. The start time of the sleep aid chamber is taken as the start time point, and the end time of the sleep aid chamber is taken as the end time point. The time period between the start and end time points and the end time point is set as the working duration. The working condition parameters of the sleep aid chamber when performing the work are obtained. The sound pressure parameters, vibration parameters, environmental parameters and working condition parameters within the working duration are summarized to generate a work record, and the work record is uploaded to the sleep aid chamber management platform. The characteristic environmental parameter determination unit: In the historical work record set, extract the values ​​of the cabin sound pressure parameters from each historical work record, preset a sound pressure parameter threshold, and set sound pressure parameters exceeding the sound pressure parameter threshold as abnormal sound pressures. Mark historical work records with abnormal sound pressures as historical abnormal records and historical work records without abnormal sound pressures as historical normal records. In the historical normal record set, extract the environmental parameters from each historical normal record and calculate the average value of each environmental parameter. In the historical abnormal record set, extract the environmental parameters from each historical abnormal record and calculate the absolute difference with the average value of the environmental parameters. Summarize historical abnormal records with the same abnormal parameter, combine the absolute difference of each environmental parameter in the historical abnormal records with the abnormal parameter, and use a correlation analysis algorithm to calculate the correlation coefficient of each environmental parameter with the abnormal parameter. Preset a correlation coefficient threshold, and set environmental parameters exceeding the correlation coefficient threshold as characteristic environmental parameters of the abnormal parameters.

[0013] Furthermore, the feature coordinate point module includes a unit for calculating the difference and a unit for determining the feature coordinate points: Calculate the difference unit: In the historical abnormal record set of a certain abnormal parameter, extract the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber from a certain historical abnormal record, and calculate the difference of abnormal parameters inside and outside the sleep aid chamber for each coordinate point; Determine the feature coordinate point unit: Extract the vibration parameters of the historical anomaly records, preset the monitoring time period, calculate the total vibration energy within the time period, calculate the structural distance between the coordinate point and the vibration sensor, calculate the vibration energy of each coordinate point, normalize the difference between the anomaly parameters corresponding to the coordinate point and the vibration energy, divide the normalized difference by the vibration energy to calculate the sound-vibration transmissibility of the coordinate point, summarize the sound-vibration transmissibility of each coordinate point in the historical anomaly records, calculate the average sound-vibration transmissibility of each coordinate point, preset the threshold for the number of feature coordinate points as F, sort each coordinate point from high to low according to the average sound-vibration transmissibility, and select the first F coordinate points as feature coordinate points.

[0014] Compared with the prior art, the beneficial effects of the present invention are: by integrating environmental parameters, sound pressure parameters, vibration parameters and operating condition parameters, the present invention realizes comprehensive real-time monitoring of the operating status of the sleep aid chamber, ensuring that potential abnormalities of the equipment can be detected in a timely manner, and providing a solid foundation for maintenance and safety; By establishing an abnormal duration prediction formula and combining historical records and real-time data for analysis and prediction, we can intelligently provide early warnings of potential equipment failures, thereby improving the scientific nature and effectiveness of equipment management and reducing the occurrence of sudden failures. Based on the health score from the work records, and combined with the mean and standard deviation, the threshold range of the health score is automatically set, which can dynamically reflect the health status of the sleep aid chamber, effectively respond to the impact of environmental changes, provide a management solution that is more adapted to the actual operating environment, avoid unnecessary temporary downtime, and establish an effective correlation between time intervals and work records, which can achieve efficient maintenance management and ensure the continuous operation of the equipment. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a method for testing the sound insulation of a sleep aid cabin based on multi-source data analysis, as described in this invention. Figure 2 This is a schematic diagram of the structure of a sleep aid cabin sound insulation testing system based on multi-source data analysis according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 and Figure 2This invention provides a technical solution: a method for testing the sound insulation of a sleep aid cabin based on multi-source data analysis, the method comprising: Step S100: In the sleep aid cabin management platform, obtain the environmental parameters, sound pressure parameters, vibration parameters, and working condition parameters from the historical work records, and classify the historical work records according to whether they are abnormal. Through the correlation analysis algorithm, calculate the correlation coefficient between abnormal parameters and environmental parameters, and determine the characteristic environmental parameters of each sound pressure parameter. Step S100 includes: Step S101: Install several sound pressure sensors inside and outside the sleep aid chamber to monitor the sound pressure parameters inside and outside the sleep aid chamber. Deploy several environmental monitoring devices around the inside and outside of the sleep aid chamber to collect various environmental parameters inside and outside the sleep aid chamber. Install several vibration sensors on the sleep aid chamber structure to obtain the vibration parameters of the sleep aid chamber during operation. Take the start time of the sleep aid chamber as the start time point and the end time of the sleep aid chamber as the end time point. Set the time period between the start and end time points and the end time point as the working duration of the work. Obtain the working condition parameters of the sleep aid chamber when performing the work. Summarize the sound pressure parameters, vibration parameters, environmental parameters and working condition parameters within the working duration to generate a work record and upload the work record to the sleep aid chamber management platform. Step S102: In the historical work record set, extract the value of the cabin sound pressure parameter in each historical work record, preset the sound pressure parameter threshold, set the sound pressure parameter exceeding the sound pressure parameter threshold as abnormal sound pressure, mark the historical work record with abnormal sound pressure as historical abnormal record, and mark the historical work record without abnormal sound pressure as historical normal record. Step S103: In the historical normal record set, extract the environmental parameters from each historical normal record, calculate the average value of each environmental parameter, in the historical abnormal record set, extract the environmental parameters from each historical abnormal record, and calculate the absolute difference with the average value of the environmental parameters, summarize the historical abnormal records that have the same abnormal parameter, combine the absolute difference of each environmental parameter in the historical abnormal record with the abnormal parameter, use a correlation analysis algorithm to calculate the correlation coefficient of each environmental parameter with the abnormal parameter, preset the correlation coefficient threshold, and set the environmental parameters that exceed the correlation coefficient threshold as the characteristic environmental parameters of the abnormal parameter; For example, three sound pressure sensors are installed inside and outside the sleep aid chamber, and the sensor locations are as follows: internal sensors (IP1, IP2, IP3). External sensors (OP1, OP2, OP3); The environmental monitoring equipment is equipped with the following devices: temperature sensors (T1, T2); Humidity sensors (H1, H2); Barometric pressure sensors (P1, P2); Two vibration sensors (VP1, VP2) were installed on the sleep aid chamber structure. The following data was collected from various sensors during the operation of the sleep aid chamber: At time 08:00:00, the corresponding IPs are: IP1 48.3, IP2 46.7, IP3 47.1, OP1 52.0, OP2 50.0, OP3 49.5, T1 22.5, T2 22.0, H1 45, H2 44, P1 1015, P2 1010, VP1 0.2, and VP2 0.3. The IP values ​​corresponding to the time point 08:05:00 are as follows: IP1 50.2, IP2 47.5, IP3 48.0, OP1 51.5, OP2 50.2, OP3 49.8, T1 22.7, T2 22.1, H1 46, H2 45, P1 1014, P2 1009, VP1 0.4, and VP2 0.5. At time 08:10:00, the corresponding IPs are: IP1 53.5, IP2 48.0, IP3 48.5, OP1 53.0, OP2 51.0, OP3 50.0, T1 23.0, T2 22.3, H1 47, H2 46, P1 1016, P2 1011, VP1 0.6, and VP2 0.4. At time 08:15:00, the corresponding IPs are: IP1 55.0, IP2 49.0, IP3 49.5, OP1 54.0, OP2 52.0, OP3 51.0, T1 23.5, T2 22.5, H1 48, H2 47, P1 1017, P2 1012, VP1 0.7, and VP2 0.5. The work lasts for a total of 20 minutes. During this period, different operating states of the sleep aid cabin were recorded, such as silent mode, music playback, and white noise operation. Set a sound pressure parameter threshold, for example, a sound pressure threshold of 52; At 08:10:00 and 08:15:00, the sound pressure levels of IP1, IP2, and IP3 all exceeded the threshold, therefore they were marked as abnormal sound pressure levels and recorded as historical abnormal records. The sound pressure levels at other times did not exceed the threshold and were recorded as normal historical records; Based on the historical normal records from 08:00:00 to 08:20:00, temperature, humidity, and air pressure data were extracted, and their average values ​​were calculated: the average temperature was 22.56. The average humidity was 46.5%. The average air pressure is 1015.5. For the abnormal record at 08:10:00, calculate the absolute difference of the corresponding environmental parameters: the absolute temperature difference is 0.44; The absolute difference in humidity is 0.5; The absolute pressure difference is 0.5. Assuming a simple linear regression is performed, the following simplified model is used to calculate the correlation coefficient, taking even numbers including the current working value and the abnormal sound pressure value. The simple linear regression calculation shows that the temperature correlation coefficient is 0.85. The humidity correlation coefficient is 0.75; The correlation coefficient for air pressure is 0.65; Assuming the preset correlation coefficient threshold is 0.7, the correlation coefficients of temperature and humidity both exceed this threshold, so they are selected as characteristic environmental parameters.

[0018] Step S200: Construct a sound field spatial coordinate system with the sleep aid chamber and the sound pressure sensor, and calculate the sound pressure parameters of the coordinate points according to the correlation coefficient of the characteristic environmental parameters and the spatial distance between the coordinate points. Then, classify the coordinate points according to their location information to obtain the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber. Step S200 includes: Step S201: Obtain the position information of each sound pressure sensor deployed in the sleep aid cabin. Taking the center position of the sleep aid cabin as the spatial origin, extract the position information of each sound pressure sensor into a three-dimensional coordinate point, construct a sound field spatial coordinate system, obtain the position information of the inner and outer edges of the sleep aid cabin in the sound field spatial coordinate system and divide it into several coordinate points, determine the three-dimensional coordinate point of each coordinate point, combine each sound pressure sensor with each coordinate point, calculate the spatial distance of each combination and summarize them to obtain the set of spatial distances between each coordinate point and each sound pressure sensor. Step S202: Extract the sound pressure parameters and environmental parameters of each historical operation record from the historical operation records. Classify the data according to the location of the sleep aid chamber where the data was collected to obtain data sets inside and outside the sleep aid chamber. For any data set, obtain the characteristic environmental parameters of a certain sound pressure parameter. Normalize the characteristic environmental parameters and calculate the sound pressure parameter of each coordinate point according to the following formula: ; Where Ai represents the i-th sound pressure parameter corresponding to the coordinate point, da represents the spatial distance between the a-th sound pressure sensor and the coordinate point, Df represents the correlation coefficient of the f-th characteristic environmental parameter, Eia represents the value of the i-th sound pressure parameter in the a-th sound pressure sensor, e represents the total number of characteristic environmental parameters, b represents the total number of sound pressure sensors, and c represents the preset correction coefficient. Step S203: Summarize the sound pressure parameters corresponding to each coordinate point inside and outside the sleep aid chamber to obtain the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber.

[0019] Step S300: Calculate the difference between the inside and outside of each coordinate point, and calculate the vibration energy of each coordinate point by calculating the structural distance between the coordinate point and the vibration sensor, calculate the sound-vibration transmission ratio of each coordinate point, and determine the characteristic coordinate point; Step S300 includes: Step S301: In the historical abnormal record set of a certain abnormal parameter, extract the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber from a certain historical abnormal record, and calculate the difference of abnormal parameters inside and outside the sleep aid chamber for each coordinate point; Step S302: Extract the vibration parameters from the historical anomaly records, preset the monitoring time period, calculate the total vibration energy within the time period, calculate the structural distance between the coordinate points and the vibration sensor, and calculate the vibration energy at each coordinate point according to the following formula: ; Where H represents the vibration energy of the coordinate point, lx represents the structural distance between the coordinate point and the x-th vibration sensor, Kx represents the total vibration energy of the x-th vibration sensor, q represents a preset constant, and y represents the total number of vibration sensors; Step S303: Normalize the difference between the abnormal parameters corresponding to the coordinate points and the vibration energy. Divide the normalized difference by the vibration energy to calculate the sound-vibration transmission ratio of the coordinate points. Summarize the sound-vibration transmission ratio of each coordinate point in the historical abnormal records and calculate the average sound-vibration transmission ratio of each coordinate point. Set the preset threshold for the number of feature coordinate points as F. Sort each coordinate point from high to low according to the average sound-vibration transmission ratio and select the first F coordinate points as feature coordinate points.

[0020] Step S400: Set the training period, obtain the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, calculate the acoustic loop parameters of the characteristic coordinate points based on the characteristic environmental parameters and the sound pressure parameters of the characteristic coordinate points, calculate the acoustic vibration parameters of the characteristic coordinate points based on the acoustic vibration transmission ratio and vibration energy of the characteristic coordinate points, calculate the acoustic engineering parameters based on the working condition score and the sound pressure parameters of the characteristic coordinate points, summarize the acoustic loop parameters, acoustic vibration parameters and acoustic engineering parameters of all characteristic coordinate points, and calculate the health score; Step S400 includes: Step S401: Select a consecutive number of days as the training period, obtain the work records within the training period, obtain the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, extract the characteristic environmental parameters and sound pressure parameters of the characteristic coordinate points from the work records, calculate the sound pressure difference of each characteristic coordinate point, normalize the characteristic environmental parameters and sound pressure parameters, and calculate the acoustic loop parameters of the characteristic coordinate points according to the following formula: ; Where G1 represents the acoustic loop parameter of the feature coordinate point, and Dh represents the correlation coefficient of the h-th feature environmental parameter. U1h represents the deviation between the h-th characteristic environmental parameter after normalization and the historical mean of the characteristic environmental parameter, and S represents the sound pressure difference value after normalization. Step S402: Extract the acoustic-vibration transmissibility and vibration energy of the feature coordinate points from the work record, normalize the acoustic-vibration transmissibility and vibration energy, and calculate the acoustic-vibration parameters of the feature coordinate points according to the following formula: ; Where G2 represents the acoustic vibration parameters of the characteristic coordinate point, R represents the normalized acoustic vibration transmission ratio, and H' represents the normalized vibration energy. Step S403: Extract the operating condition parameters from the work record, assign values ​​to each operating condition parameter, preset the weight of each operating condition parameter, and sum the weighted values ​​of each operating condition parameter to calculate the operating condition score. Calculate the acoustic parameters of the feature coordinate points according to the following formula: ; Wherein, G3 represents the acoustic parameters of the feature coordinate point, M represents the current working condition score, and M' represents the average working condition score; Step S404: Summarize the acoustic ring parameters, acoustic vibration parameters, and acoustic engineering parameters for each feature coordinate point, and calculate the health score according to the following formula: ; Where G represents the health score, G1 wn G2 wn G3 wn Let V1, V2, and V3 represent the acoustic loop parameter, acoustic vibration parameter, and acoustic engineering parameter at the nth feature coordinate point, respectively. Let V1, V2, and V3 represent the weights of the acoustic loop parameter, acoustic vibration parameter, and acoustic engineering parameter, respectively. w Let w represent the weight of the w-th sound pressure parameter, u represent the total number of sound pressure parameters, and m represent the total number of feature coordinate points.

[0021] Step S500: Obtain work records with abnormal results from manual inspection, calculate the health score threshold range based on the health score of the work records, and generate an abnormal duration prediction formula by constructing an abnormal dataset for training. Step S500 includes: Step S501: During the training cycle, when each work task is completed, staff members are arranged to inspect the sleep aid pod and generate inspection results. The inspection results of the work records during the training cycle are obtained, and the work records with abnormal inspection results are extracted. The health score of the work records is obtained, and the mean value of the health score is r1 and the standard deviation is r2. The lower limit threshold of the health score is Q1=r1-j×r2, and the upper limit threshold of the health score is Q2=r1+j×r2, where j represents the preset safety coefficient. The health score threshold range is [Q1,Q2]. Step S502: Divide the time period corresponding to the work record with two consecutive abnormal inspection results, and set the time period as the abnormal duration. Extract all work records within the time period, obtain the time interval between each work record, extract the work duration and health score of each work record, normalize and calculate the time interval, work duration, health score, and abnormal duration, and summarize them to construct an abnormal dataset and generate an abnormal duration prediction formula: ; Among them, G N+1 and T2 N+1 T1 represents the normalized health score and working hours corresponding to the (N+1)th work record, respectively. N Let t represent the normalized time interval corresponding to the Nth work record, T represent the normalized abnormal duration, M represent the total number of work records, t1, t2, and t3 represent the weights of health score, time interval, and work duration, respectively, and t represent the weight of abnormal duration prediction. The abnormal duration prediction formula is trained by training all abnormal datasets. The training process involves calculating the loss value of the current formula and adjusting the weights according to the loss value until the loss value meets the set standard value. The corresponding weights are then substituted into the abnormal duration prediction formula to update the abnormal duration prediction formula.

[0022] Step S600: Based on the real-time data of the current work, determine whether maintenance is required. If maintenance is not required, calculate the duration of the next maintenance. When the duration is reached, remind the staff to perform maintenance. Step S600 includes: Step S601: Obtain the real-time environmental parameters, real-time sound pressure parameters, real-time vibration parameters, and real-time working condition parameters during the current operation; extract the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter; and calculate the real-time health score for the current operation. Step S602: Compare the real-time health score with the health score threshold range. If it exceeds the health score threshold range, immediately stop the machine and notify the staff for maintenance. If it is within the health score threshold range, notify the staff for maintenance after completing the current work. If it is below the health score threshold range, proceed to step S603. Step S603: Obtain the time interval between the current work and the previous work record, calculate the real-time predicted value of the abnormal duration using the abnormal duration prediction formula, and remind the staff to carry out maintenance when the real-time predicted value is reached.

[0023] To better implement the above method, a sleep aid cabin sound insulation testing system based on multi-source data analysis is also proposed. The system includes a characteristic environmental parameter module, a sound pressure parameter module, a characteristic coordinate point module, a health score module, a model training module, and a judgment and maintenance module. Characteristic environmental parameter module: In the sleep aid cabin management platform, environmental parameters, sound pressure parameters, vibration parameters, and working condition parameters from historical work records are obtained, and historical work records are classified according to whether they are abnormal. Through correlation analysis algorithm, the correlation coefficient between abnormal parameters and environmental parameters is calculated to determine the characteristic environmental parameters of each sound pressure parameter. The feature environment parameter module includes a work record unit and a feature environment parameter determination unit: Work Recording Unit: Several sound pressure sensors are installed inside and outside the sleep aid chamber to monitor the sound pressure parameters inside and outside the sleep aid chamber. Several environmental monitoring devices are deployed around the sleep aid chamber to collect various environmental parameters inside and outside the sleep aid chamber. Several vibration sensors are installed on the sleep aid chamber structure to obtain the vibration parameters of the sleep aid chamber during operation. The start time of the sleep aid chamber is taken as the start time point, and the end time of the sleep aid chamber is taken as the end time point. The time period between the start and end time points and the end time point is set as the working duration. The working condition parameters of the sleep aid chamber when performing the work are obtained. The sound pressure parameters, vibration parameters, environmental parameters and working condition parameters within the working duration are summarized to generate a work record, and the work record is uploaded to the sleep aid chamber management platform. The characteristic environmental parameter determination unit: In the historical work record set, extract the values ​​of the cabin sound pressure parameters from each historical work record, preset a sound pressure parameter threshold, and set sound pressure parameters exceeding the sound pressure parameter threshold as abnormal sound pressures. Mark historical work records with abnormal sound pressures as historical abnormal records and historical work records without abnormal sound pressures as historical normal records. In the historical normal record set, extract the environmental parameters from each historical normal record and calculate the average value of each environmental parameter. In the historical abnormal record set, extract the environmental parameters from each historical abnormal record and calculate the absolute difference with the average value of the environmental parameters. Summarize historical abnormal records with the same abnormal parameter, combine the absolute difference of each environmental parameter in the historical abnormal records with the abnormal parameter, and use a correlation analysis algorithm to calculate the correlation coefficient of each environmental parameter with the abnormal parameter. Preset a correlation coefficient threshold, and set environmental parameters exceeding the correlation coefficient threshold as characteristic environmental parameters of the abnormal parameters.

[0024] Sound pressure parameter module: Construct a sound field spatial coordinate system by connecting the sleep aid cabin and the sound pressure sensor. Calculate the sound pressure parameters of the coordinate points based on the correlation coefficients of characteristic environmental parameters and the spatial distance between coordinate points. Then, classify the coordinate points according to their location information to obtain a set of coordinate sound pressure parameters inside the sleep aid cabin and a set of coordinate sound pressure parameters outside the sleep aid cabin. Feature coordinate point module: Calculates the internal and external differences of each coordinate point, and calculates the vibration energy of each coordinate point by calculating the structural distance between the coordinate point and the vibration sensor, calculates the sound-vibration transmission ratio of each coordinate point, and determines the feature coordinate point; The feature coordinate point module includes a unit for calculating the difference and a unit for determining the feature coordinate points. Calculate the difference unit: In the historical abnormal record set of a certain abnormal parameter, extract the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber from a certain historical abnormal record, and calculate the difference of abnormal parameters inside and outside the sleep aid chamber for each coordinate point; Determine the feature coordinate point unit: Extract the vibration parameters of the historical anomaly records, preset the monitoring time period, calculate the total vibration energy within the time period, calculate the structural distance between the coordinate point and the vibration sensor, calculate the vibration energy of each coordinate point, normalize the difference between the anomaly parameters corresponding to the coordinate point and the vibration energy, divide the normalized difference by the vibration energy to calculate the sound-vibration transmissibility of the coordinate point, summarize the sound-vibration transmissibility of each coordinate point in the historical anomaly records, calculate the average sound-vibration transmissibility of each coordinate point, preset the threshold for the number of feature coordinate points as F, sort each coordinate point from high to low according to the average sound-vibration transmissibility, and select the first F coordinate points as feature coordinate points.

[0025] Health scoring module: Set training period, obtain characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, calculate the acoustic loop parameter of the characteristic coordinate point based on the characteristic environmental parameters and the sound pressure parameter of the characteristic coordinate point, calculate the acoustic vibration parameter of the characteristic coordinate point based on the acoustic vibration transmission ratio and vibration energy of the characteristic coordinate point, calculate the acoustic engineering parameter based on the working condition score and the sound pressure parameter of the characteristic coordinate point, and summarize the acoustic loop parameter, acoustic vibration parameter and acoustic engineering parameter of all characteristic coordinate points to calculate the health score; Model training module: Obtain work records that are abnormal according to manual inspection, calculate the health score threshold range based on the health score of the work records, train by constructing an abnormal dataset, and generate an abnormal duration prediction formula; Maintenance Module: Based on real-time data of the current operation, determine whether maintenance is required. If maintenance is not required, calculate the duration of the next maintenance. When the specified duration is reached, remind staff to perform maintenance.

[0026] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for testing the sound insulation of a sleep aid chamber based on multi-source data analysis, characterized in that, The methods include: Step S100: In the sleep aid cabin management platform, obtain the environmental parameters, sound pressure parameters, vibration parameters, and working condition parameters from the historical work records, and classify the historical work records according to whether they are abnormal. Through the correlation analysis algorithm, calculate the correlation coefficient between abnormal parameters and environmental parameters, and determine the characteristic environmental parameters of each sound pressure parameter. Step S200: Construct a sound field spatial coordinate system with the sleep aid chamber and the sound pressure sensor, and calculate the sound pressure parameters of the coordinate points according to the correlation coefficient of the characteristic environmental parameters and the spatial distance between the coordinate points. Then, classify the coordinate points according to their location information to obtain the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber. Step S300: Calculate the difference between the inside and outside of each coordinate point, and calculate the vibration energy of each coordinate point by calculating the structural distance between the coordinate point and the vibration sensor, calculate the sound-vibration transmission ratio of each coordinate point, and determine the characteristic coordinate point; Step S400: Set the training period, obtain the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, calculate the acoustic loop parameters of the characteristic coordinate points based on the characteristic environmental parameters and the sound pressure parameters of the characteristic coordinate points, calculate the acoustic vibration parameters of the characteristic coordinate points based on the acoustic vibration transmission ratio and vibration energy of the characteristic coordinate points, calculate the acoustic engineering parameters based on the working condition score and the sound pressure parameters of the characteristic coordinate points, summarize the acoustic loop parameters, acoustic vibration parameters and acoustic engineering parameters of all characteristic coordinate points, and calculate the health score; Step S500: Obtain work records with abnormal results from manual inspection, calculate the health score threshold range based on the health score of the work records, and generate an abnormal duration prediction formula by constructing an abnormal dataset for training. Step S600: Based on the real-time data of the current work, determine whether maintenance is required. If maintenance is not required, calculate the duration of the next maintenance. When the duration is reached, remind the staff to perform maintenance.

2. The method for testing the sound insulation of a sleep aid chamber based on multi-source data analysis according to claim 1, characterized in that, Step S100 includes the following steps: Step S101: Install several sound pressure sensors inside and outside the sleep aid chamber to monitor the sound pressure parameters inside and outside the sleep aid chamber. Deploy several environmental monitoring devices around the inside and outside of the sleep aid chamber to collect various environmental parameters inside and outside the sleep aid chamber. Install several vibration sensors on the sleep aid chamber structure to obtain the vibration parameters of the sleep aid chamber during operation. Take the start time of the sleep aid chamber as the start time point and the end time of the sleep aid chamber as the end time point. Set the time period between the start and end time points and the end time point as the working duration of the work. Obtain the working condition parameters of the sleep aid chamber when performing the work. Summarize the sound pressure parameters, vibration parameters, environmental parameters and working condition parameters within the working duration to generate a work record and upload the work record to the sleep aid chamber management platform. Step S102: In the historical work record set, extract the value of the cabin sound pressure parameter in each historical work record, preset the sound pressure parameter threshold, set the sound pressure parameter exceeding the sound pressure parameter threshold as abnormal sound pressure, mark the historical work record with abnormal sound pressure as historical abnormal record, and mark the historical work record without abnormal sound pressure as historical normal record. Step S103: In the historical normal record set, extract the environmental parameters from each historical normal record and calculate the average value of each environmental parameter. In the historical abnormal record set, extract the environmental parameters from each historical abnormal record and calculate the absolute difference with the average value of the environmental parameters. Summarize the historical abnormal records that have the same abnormal parameter. Combine the absolute difference of each environmental parameter in the historical abnormal record with the abnormal parameter. Use a correlation analysis algorithm to calculate the correlation coefficient of each environmental parameter with the abnormal parameter. Preset a correlation coefficient threshold and set the environmental parameters that exceed the correlation coefficient threshold as the characteristic environmental parameters of the abnormal parameter.

3. The method for testing the sound insulation of a sleep aid chamber based on multi-source data analysis according to claim 2, characterized in that, Step S200 includes the following steps: Step S201: Obtain the position information of each sound pressure sensor deployed in the sleep aid cabin. Taking the center position of the sleep aid cabin as the spatial origin, extract the position information of each sound pressure sensor into a three-dimensional coordinate point, construct a sound field spatial coordinate system, obtain the position information of the inner and outer edges of the sleep aid cabin in the sound field spatial coordinate system and divide it into several coordinate points, determine the three-dimensional coordinate point of each coordinate point, combine each sound pressure sensor with each coordinate point, calculate the spatial distance of each combination and summarize them to obtain the set of spatial distances between each coordinate point and each sound pressure sensor. Step S202: Extract the sound pressure parameters and environmental parameters of each historical operation record from the historical operation records. Classify the data according to the location of the sleep aid chamber where the data was collected to obtain data sets inside and outside the sleep aid chamber. For any data set, obtain the characteristic environmental parameters of a certain sound pressure parameter. Normalize the characteristic environmental parameters and calculate the sound pressure parameter of each coordinate point according to the following formula: ； Where Ai represents the i-th sound pressure parameter corresponding to the coordinate point, da represents the spatial distance between the a-th sound pressure sensor and the coordinate point, Df represents the correlation coefficient of the f-th characteristic environmental parameter, Eia represents the value of the i-th sound pressure parameter in the a-th sound pressure sensor, e represents the total number of characteristic environmental parameters, b represents the total number of sound pressure sensors, and c represents the preset correction coefficient. Step S203: Summarize the sound pressure parameters corresponding to each coordinate point inside and outside the sleep aid chamber to obtain the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber.

4. The method for testing the sound insulation of a sleep aid chamber based on multi-source data analysis according to claim 3, characterized in that, Step S300 includes the following steps: Step S301: In the historical abnormal record set of a certain abnormal parameter, extract the set of coordinate sound pressure parameters inside the sleep aid chamber and the set of coordinate sound pressure parameters outside the sleep aid chamber from a certain historical abnormal record, and calculate the difference of abnormal parameters inside and outside the sleep aid chamber for each coordinate point; Step S302: Extract the vibration parameters from the historical anomaly records, preset the monitoring time period, calculate the total vibration energy within the time period, calculate the structural distance between the coordinate points and the vibration sensor, and calculate the vibration energy at each coordinate point according to the following formula: ； Where H represents the vibration energy of the coordinate point, lx represents the structural distance between the coordinate point and the x-th vibration sensor, Kx represents the total vibration energy of the x-th vibration sensor, q represents a preset constant, and y represents the total number of vibration sensors; Step S303: Normalize the difference between the abnormal parameters corresponding to the coordinate points and the vibration energy. Divide the normalized difference by the vibration energy to calculate the sound-vibration transmission ratio of the coordinate points. Summarize the sound-vibration transmission ratio of each coordinate point in the historical abnormal records and calculate the average sound-vibration transmission ratio of each coordinate point. Set the preset threshold for the number of feature coordinate points as F. Sort each coordinate point from high to low according to the average sound-vibration transmission ratio and select the first F coordinate points as feature coordinate points.

5. The method for testing the sound insulation of a sleep aid cabin based on multi-source data analysis according to claim 4, characterized in that, Step S400 includes the following steps: Step S401: Select a consecutive number of days as the training period, obtain the work records within the training period, obtain the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, extract the characteristic environmental parameters and sound pressure parameters of the characteristic coordinate points from the work records, calculate the sound pressure difference of each characteristic coordinate point, normalize the characteristic environmental parameters and sound pressure parameters, and calculate the acoustic loop parameters of the characteristic coordinate points according to the following formula: ； Where G1 represents the acoustic loop parameter of the feature coordinate point, and Dh represents the correlation coefficient of the h-th feature environmental parameter. U1h represents the deviation between the h-th characteristic environmental parameter after normalization and the historical mean of the characteristic environmental parameter, and S represents the sound pressure difference value after normalization. Step S402: Extract the acoustic-vibration transmissibility and vibration energy of the feature coordinate points from the work record, normalize the acoustic-vibration transmissibility and vibration energy, and calculate the acoustic-vibration parameters of the feature coordinate points according to the following formula: ； Where G2 represents the acoustic vibration parameters of the characteristic coordinate point, R represents the normalized acoustic vibration transmission ratio, and H' represents the normalized vibration energy. Step S403: Extract the operating condition parameters from the work record, assign values ​​to each operating condition parameter, preset the weight of each operating condition parameter, and sum the weighted values ​​of each operating condition parameter to calculate the operating condition score. Calculate the acoustic parameters of the feature coordinate points according to the following formula: ； Wherein, G3 represents the acoustic parameters of the feature coordinate point, M represents the current working condition score, and M' represents the average working condition score; Step S404: Summarize the acoustic ring parameters, acoustic vibration parameters, and acoustic engineering parameters for each feature coordinate point, and calculate the health score according to the following formula: ； Where G represents the health score, G1 wn G2 wn G3 wn Let V1, V2, and V3 represent the acoustic loop parameter, acoustic vibration parameter, and acoustic engineering parameter at the nth feature coordinate point, respectively. Let V1, V2, and V3 represent the weights of the acoustic loop parameter, acoustic vibration parameter, and acoustic engineering parameter, respectively. w Let represent the weight of the w-th sound pressure parameter, u represent the total number of sound pressure parameters, and m represent the total number of feature coordinate points.

6. The method for testing the sound insulation of a sleep aid cabin based on multi-source data analysis according to claim 5, characterized in that, Step S500 includes the following steps: Step S501: During the training cycle, when each work task is completed, staff members are arranged to inspect the sleep aid pod and generate inspection results. The inspection results of the work records during the training cycle are obtained, and the work records with abnormal inspection results are extracted. The health score of the work records is obtained, and the mean value of the health score is r1 and the standard deviation is r2. The lower limit threshold of the health score is Q1=r1-j×r2, and the upper limit threshold of the health score is Q2=r1+j×r2, where j represents the preset safety coefficient. The health score threshold range is [Q1,Q2]. Step S502: Divide the time period corresponding to the work record with two consecutive abnormal inspection results, and set the time period as the abnormal duration. Extract all work records within the time period, obtain the time interval between each work record, extract the work duration and health score of each work record, normalize and calculate the time interval, work duration, health score, and abnormal duration, and summarize them to construct an abnormal dataset and generate an abnormal duration prediction formula: ； Among them, G N+1 and T2 N+1 T1 represents the normalized health score and working hours corresponding to the (N+1)th work record, respectively. N Let t represent the normalized time interval corresponding to the Nth work record, T represent the normalized abnormal duration, M represent the total number of work records, t1, t2, and t3 represent the weights of health score, time interval, and work duration, respectively, and t represent the weight of abnormal duration prediction. The abnormal duration prediction formula is trained by training all abnormal datasets. The training process involves calculating the loss value of the current formula and adjusting the weights according to the loss value until the loss value meets the set standard value. The corresponding weights are then substituted into the abnormal duration prediction formula to update the abnormal duration prediction formula.

7. The method for testing the sound insulation of a sleep aid cabin based on multi-source data analysis according to claim 6, characterized in that, Step S600 includes the following steps: Step S601: Obtain the real-time environmental parameters, real-time sound pressure parameters, real-time vibration parameters, and real-time working condition parameters during the current operation; extract the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter; and calculate the real-time health score for the current operation. Step S602: Compare the real-time health score with the health score threshold range. If it exceeds the health score threshold range, immediately stop the machine and notify the staff for maintenance. If it is within the health score threshold range, notify the staff for maintenance after completing the current work. If it is below the health score threshold range, proceed to step S603. Step S603: Obtain the time interval between the current work and the previous work record, calculate the real-time predicted value of the abnormal duration using the abnormal duration prediction formula, and remind the staff to carry out maintenance when the real-time predicted value is reached.

8. A sound insulation testing system for a sleep aid cabin based on multi-source data analysis, used to implement the sound insulation testing method for a sleep aid cabin based on multi-source data analysis as described in any one of claims 1-7, characterized in that, The system includes a feature environment parameter module, a sound pressure parameter module, a feature coordinate point module, a health scoring module, a model training module, and a judgment and inspection module; The characteristic environmental parameter module: In the sleep aid cabin management platform, it acquires environmental parameters, sound pressure parameters, vibration parameters, and working condition parameters from historical work records, classifies historical work records according to whether they are abnormal, calculates the correlation coefficient between abnormal parameters and environmental parameters through a correlation analysis algorithm, and determines the characteristic environmental parameters of each sound pressure parameter. The sound pressure parameter module: constructs a sound field spatial coordinate system between the sleep aid cabin and the sound pressure sensor, calculates the sound pressure parameters of the coordinate points based on the correlation coefficients of the characteristic environmental parameters and the spatial distance between the coordinate points, and classifies the coordinate points according to their location information to obtain the set of coordinate sound pressure parameters inside the sleep aid cabin and the set of coordinate sound pressure parameters outside the sleep aid cabin; The feature coordinate point module calculates the internal and external differences of each coordinate point, and calculates the vibration energy of each coordinate point by calculating the structural distance between the coordinate point and the vibration sensor, calculates the sound-vibration transmission ratio of each coordinate point, and determines the feature coordinate point. The health scoring module: sets a training cycle, obtains the characteristic environmental parameters and characteristic coordinate points corresponding to each sound pressure parameter, calculates the acoustic loop parameters of the characteristic coordinate points based on the characteristic environmental parameters and the sound pressure parameters of the characteristic coordinate points, calculates the acoustic vibration parameters of the characteristic coordinate points based on the acoustic vibration transmission ratio and vibration energy of the characteristic coordinate points, calculates the acoustic engineering parameters based on the working condition score and the sound pressure parameters of the characteristic coordinate points, and summarizes the acoustic loop parameters, acoustic vibration parameters, and acoustic engineering parameters of all characteristic coordinate points to calculate the health score; The model training module: acquires work records that are abnormal according to manual inspection, calculates the health score threshold range based on the health score of the work records, and generates an abnormal duration prediction formula by constructing an abnormal dataset for training. The maintenance judgment module determines whether maintenance is required based on real-time data. If maintenance is not required, it calculates the duration of the next maintenance and reminds staff to perform maintenance when the duration is reached.

9. The sound insulation testing system for a sleep aid chamber based on multi-source data analysis according to claim 8, characterized in that, The characteristic environment parameter module includes a work record unit and a characteristic environment parameter determination unit: The work recording unit consists of: several sound pressure sensors installed inside and outside the sleep aid chamber to monitor sound pressure parameters inside and outside the chamber; several environmental monitoring devices deployed around the sleep aid chamber to collect various environmental parameters inside and outside the chamber; several vibration sensors installed on the sleep aid chamber structure to obtain vibration parameters during operation; the start time of the sleep aid chamber's operation as the starting time point and the end time of the sleep aid chamber's operation as the ending time point; the time period between the start and end time points and the ending time point as the working duration; the operating parameters of the sleep aid chamber during the operation; the sound pressure parameters, vibration parameters, environmental parameters, and operating parameters within the working duration are summarized to generate a work record; and the work record is uploaded to the sleep aid chamber management platform. The unit for determining characteristic environmental parameters involves: extracting the values ​​of cabin sound pressure parameters from each historical work record in the historical work record set; setting a preset sound pressure parameter threshold; defining sound pressure parameters exceeding the threshold as abnormal sound pressures; marking historical work records with abnormal sound pressures as historical abnormal records; marking historical work records without abnormal sound pressures as historical normal records; extracting environmental parameters from each historical normal record in the historical normal record set; calculating the average value of each environmental parameter; extracting environmental parameters from each historical abnormal record in the historical abnormal record set; calculating the absolute difference between each environmental parameter and the average value of the environmental parameters; summarizing historical abnormal records with the same abnormal parameter; combining the absolute difference of each environmental parameter in the historical abnormal records with the abnormal parameter; using a correlation analysis algorithm to calculate the correlation coefficient of each environmental parameter with the abnormal parameter; setting a preset correlation coefficient threshold; and defining environmental parameters exceeding the correlation coefficient threshold as characteristic environmental parameters of the abnormal parameters.

10. A sound insulation testing system for a sleep aid chamber based on multi-source data analysis according to claim 8, characterized in that, The feature coordinate point module includes a difference calculation unit and a feature coordinate point determination unit: The difference calculation unit: In the historical abnormal record set of a certain abnormal parameter, extract the set of coordinate sound pressure parameters inside the sleep aid cabin and the set of coordinate sound pressure parameters outside the sleep aid cabin from a certain historical abnormal record, and calculate the difference of abnormal parameters inside and outside the sleep aid cabin for each coordinate point; The feature coordinate point determination unit: extracts vibration parameters from the historical anomaly records, presets a monitoring time period, calculates the total vibration energy within the time period, calculates the structural distance between the coordinate point and the vibration sensor, calculates the vibration energy of each coordinate point, normalizes the difference between the anomaly parameters corresponding to the coordinate point and the vibration energy, divides the normalized difference by the vibration energy to calculate the acoustic-vibration transmission ratio of the coordinate point, summarizes the acoustic-vibration transmission ratio of each coordinate point in the historical anomaly records, calculates the average acoustic-vibration transmission ratio of each coordinate point, presets a threshold for the number of feature coordinate points as F, sorts each coordinate point from high to low according to the average acoustic-vibration transmission ratio, and selects the first F coordinate points as feature coordinate points.

Images