A combined door and window frame combination degree detection system and method

Abstract

The invention relates to the technical field of door and window detection, and in particular to a combined door and window frame combination degree detection system and method, which improves the accuracy and efficiency of door and window combination degree detection; the system comprises: a door and window upper machine platform, which is used to install doors and windows to be detected, after the doors and windows to be detected are installed, adjustable environmental spaces are formed on both sides of the doors and windows to be detected, an environmental simulation unit is arranged on the door and window upper machine platform, and the environmental simulation unit is used to adjust the air pressure, temperature, humidity and concentration of set gas of two adjustable environmental spaces; a mechanical arm execution module, which is arranged in the adjustable environmental space on the side where the door and window handle is installed, and is used to perform multi-angle force application opening and closing actions on the doors and windows to be detected; a sensor integration module, which is used to collect the air pressure, temperature, humidity, concentration of set gas, noise decibel when the doors and windows are opened and closed, and the applied pulling force when the mechanical arm execution module performs the opening and closing operation of the two adjustable environmental spaces according to a set collection frequency.

Description

Technical Field

[0001] The present invention relates to the technical field of door and window detection, and in particular to a combined door and window frame combination degree detection system and method. Background Art

[0002] With the development of the construction industry, doors and windows, as an important part of a building, have a performance that directly affects the thermal insulation, air tightness, water tightness and other properties of the building. Therefore, the detection of the combination degree of door and window frames is particularly important.

[0003] The existing door and window frame combination detection methods mainly rely on manual detection or simple mechanical devices. The manual detection method has problems such as low efficiency, the detection results are greatly affected by human factors, and it is difficult to achieve accurate control and recording. Simple mechanical devices can often only perform detection under a single environmental condition and cannot simulate the complex environment encountered in actual use, such as the impact of different indoor and outdoor temperatures, humidity, and air pressure on the sealing of doors and windows; at the same time, the combination of doors and windows is not only reflected in the sealing, but also needs to consider the matching accuracy of doors and windows. Therefore, a combined door and window frame combination detection system and method is urgently needed to solve the above problems. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a combined door and window frame combination degree detection system and method which improves the accuracy and efficiency of door and window combination degree detection.

[0005] In a first aspect, the present invention provides a combined door and window frame combination degree detection system, the system comprising:

[0006] The door and window machine platform is used to install the doors and windows to be tested. After the doors and windows to be tested are installed, adjustable environmental spaces are formed on both sides of the doors and windows to be tested. The door and window machine platform is provided with an environmental simulation unit, which is used to adjust the air pressure, temperature, humidity and concentration of the set gas in the two adjustable environmental spaces;

[0007] A mechanical arm execution module, which is arranged in an adjustable environment space on one side where a door and window handle is installed, and is used to perform multi-angle force opening and closing actions on the door and window to be inspected;

[0008] The sensor integration module is used to collect the air pressure, temperature, humidity, concentration of set gas, noise decibels when doors and windows are opened and closed, and the pulling force applied by the robot execution module when performing the opening and closing operation of two adjustable environment spaces according to the set collection frequency, and send the collected sensor data information;

[0009] The central data processing module is used to receive the sensor data information sent by the sensor integration module, perform statistical analysis on the sensor data information, calculate and obtain the door and window combination degree detection result of the door and window to be detected; and compare the door and window combination degree detection result with the preset door and window combination degree threshold to obtain the door and window combination degree detection result to be detected;

[0010] The detection result display module is used to read the combination degree detection result obtained by the central data processing module and visually display the combination degree detection result.

[0011] Furthermore, the method is applied to a combined door and window frame combination degree detection system, and the method comprises:

[0012] According to the specification information of the doors and windows to be tested, the corresponding diffusion test scheme and opening and closing test scheme are retrieved from the preset test scheme library;

[0013] Execute the diffusion test plan, and respectively collect the initial diffusion characteristic parameter vectors and the real-time diffusion characteristic parameter vectors after the set time in the two adjustable environmental spaces; the initial diffusion characteristic parameter vectors include the initial air pressure, the initial temperature, the initial humidity and the initial set gas concentration; the real-time diffusion characteristic parameter vectors include the real-time air pressure, the real-time temperature, the real-time humidity and the real-time set gas concentration;

[0014] For each adjustable environment space, the difference between the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector is calculated to obtain the diffusion characteristic parameter fluctuation vector of each adjustable environment space;

[0015] The fluctuation analysis of the diffusion characteristic parameter fluctuation vectors of the two adjustable environmental spaces is performed to obtain the sealing performance evaluation index of the doors and windows to be tested;

[0016] Execute the opening and closing test plan to collect the air pressure difference between the two adjustable environment spaces when the doors and windows to be tested are opened and closed, the decibel of noise generated by the opening and closing action, and the applied pulling force required for the opening and closing action;

[0017] The air pressure difference, the noise decibel generated by the opening and closing action, and the applied pulling force required for the opening and closing action are input into a pre-trained opening and closing feature evaluation model to obtain a matching accuracy evaluation index of the door and window to be tested;

[0018] Perform weighted calculation on the sealing performance evaluation index and matching accuracy evaluation index of the doors and windows to be tested, and obtain the door and window combination test results of the doors and windows to be tested;

[0019] The door and window combination degree detection result is compared with the preset door and window combination degree threshold to determine whether the combination degree of the door and window to be detected is qualified.

[0020] Furthermore, the mathematical calculation formula for calculating the matching accuracy evaluation index of the door and window to be tested by the opening and closing feature evaluation model is:

[0021] ;

[0022] Among them, I fit Indicates the matching accuracy evaluation index of the doors and windows to be tested; w 1 represents the weight coefficient of air pressure difference; w 2 represents the weight coefficient of noise decibel; w 3 represents the weight coefficient of applied tension; Δ P Represents the air pressure difference between two adjustable environmental spaces; N Indicates the decibel of noise generated by the opening and closing action; F Indicates the pulling force required for opening and closing actions; b It is a bias term used to adjust the overall level of the evaluation index.

[0023] Furthermore, the method for constructing the opening and closing feature evaluation model includes:

[0024] Collect historical test data, including test results of different door and window models under various environmental conditions;

[0025] Clean the collected historical test data to remove outliers, missing values ​​and erroneous records;

[0026] Selecting a deep learning model as the basic architecture of the opening and closing feature evaluation model; the deep learning model includes a neural network, a random forest, a gradient boosting tree, a linear regression, and a logistic regression model;

[0027] The preprocessed data is divided into training set, validation set and test set; the division ratio is 70% training, 15% validation, and 15% test;

[0028] Use the training set data to train the model, and use the validation set data to monitor the model performance to prevent overfitting;

[0029] After adjusting the model on the validation set, the model performance is finally evaluated on an independent test set to ensure that the model has good generalization ability;

[0030] The trained model is deployed to the combined door and window frame combination detection system to evaluate the matching accuracy of doors and windows in real time.

[0031] Furthermore, the calculation formula for the door and window combination degree detection result of the door and window to be detected is:

[0032] ;

[0033] Among them, I comboIndicates the door and window combination test result, I seal Indicates the sealing performance evaluation index, I fit represents the matching accuracy evaluation index, w seal Indicates the weight of sealing performance, w fit Indicates the weight of the fit accuracy.

[0034] Furthermore, the method for obtaining the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector includes:

[0035] According to the diffusion test plan, the initial environmental parameters of two adjustable environmental spaces are set;

[0036] After the doors and windows are closed and the environment is stable, immediately record the initial air pressure, initial temperature, initial humidity and initial set gas concentration in the two adjustable environmental spaces;

[0037] Continuously monitor and record changes in environmental parameters according to the duration set in the test plan;

[0038] After the set time period is over, the real-time air pressure, real-time temperature, real-time humidity and real-time set gas concentration in the two adjustable environmental spaces are collected again;

[0039] Accurately record all collected data and mark it with a time stamp;

[0040] Perform a preliminary check on the collected data to check for outliers and data errors.

[0041] Furthermore, a method for performing fluctuation analysis on the diffusion characteristic parameter fluctuation vectors of two adjustable environment spaces includes:

[0042] Sort out the fluctuation vectors of diffusion characteristic parameters and eliminate noise and outliers;

[0043] Compare the fluctuations of corresponding parameters in two adjustable environment spaces and calculate the difference value of the fluctuation of each parameter;

[0044] According to the importance of different parameters on sealing performance, weights are assigned to the difference values ​​of various parameters;

[0045] The weighted difference values ​​are summarized to obtain a comprehensive sealing performance evaluation value;

[0046] The evaluation value is standardized, and the standardized evaluation value is defined as the sealing performance evaluation index of the door and window to be tested;

[0047] The calculated sealing performance evaluation index is output for use in subsequent steps.

[0048] Furthermore, the method of collecting the air pressure difference between the two adjustable environment spaces when the door and window to be tested is opened and closed, the noise decibels generated by the opening and closing action, and the pulling force required for the opening and closing action includes:

[0049] According to the opening and closing test plan, adjust the air pressure of the two adjustable environmental spaces to the preset value;

[0050] Start the robot arm execution module to open and close the doors and windows according to the preset opening and closing action sequence;

[0051] While the robotic arm is performing the opening and closing action, the sensor integration module collects the air pressure difference, noise decibel and applied tension in real time;

[0052] The sensor integration module sends the collected air pressure difference, noise decibel and applied tension data to the central data processing module for recording in real time;

[0053] Perform preliminary verification on the received data;

[0054] When the robot arm completes all preset opening and closing actions, the test phase ends;

[0055] The collected air pressure difference, noise decibel and applied tension data are used as the output of the opening and closing test.

[0056] Furthermore, the structure of the test solution library includes:

[0057] Door and window specification table, used to store specification information of doors and windows;

[0058] The test plan table is used to store specific test plan details, including diffusion test plan and opening and closing test plan;

[0059] Parameter configuration table, used to store the default values, ranges and specific requirements of various parameters;

[0060] An association table is used to establish a many-to-many relationship between the door and window specification table and the test plan table.

[0061] Furthermore, factors affecting the setting of the preset door and window combination threshold include building use environment, door and window usage, customer demand, historical data analysis, technical implementation economy, reliability and durability, and maintenance cost.

[0062] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0063] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0064] Compared with the prior art, the present invention has the following beneficial effects: the system can accurately adjust the air pressure, temperature, humidity and concentration of set gas in two adjustable environmental spaces through the environmental simulation unit, thereby fully simulating various complex environmental conditions that doors and windows may encounter during actual use; ensuring the accuracy and practicality of the test results, making the test results closer to the actual use scenario;

[0065] The use of a robotic arm execution module to automatically perform multi-angle force opening and closing actions not only improves the detection efficiency, but also avoids errors and inconsistencies caused by human factors in manual detection; the precise control of the robotic arm ensures the repeatability and consistency of each test condition, and improves the reliability of the detection data;

[0066] The sensor integration module can collect multiple key parameters in real time and accurately, including environmental parameters and door and window performance parameters, providing a rich data basis for subsequent statistical analysis; the multi-dimensional analysis of these data can more comprehensively evaluate the combination performance of doors and windows;

[0067] The central data processing module statistically analyzes the collected data and automatically compares it with the preset door and window combination threshold to quickly obtain the combination test results; this intelligent processing method not only improves the detection efficiency, but also reduces human intervention and the possibility of misjudgment;

[0068] The test result display module visualizes the combination test results, making the test results intuitive and easy to understand; it not only facilitates the understanding and judgment of the test personnel, but also provides strong support for subsequent quality control and improvement;

[0069] In summary, the combined door and window frame combination detection system improves the accuracy and efficiency of door and window combination detection through the advantages of comprehensive simulation of the actual use environment, efficient automatic detection, multi-dimensional data collection and analysis, intelligent data processing and result judgment, and visual display of results. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a structural diagram of the combined door and window frame combination degree detection system;

[0071] Figure 2 It is a flow chart of a method for detecting the degree of combination of a combined door and window frame;

[0072] Figure 3 It is a flow chart of a method for performing fluctuation analysis on a fluctuation vector of a diffusion characteristic parameter of two adjustable environment spaces. DETAILED DESCRIPTION

[0073] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0074] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0075] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0076] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0077] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0078] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0079] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0080] The present application is described below in conjunction with the drawings in the present application.

[0081] Embodiment 1: Figure 1 As shown, a combined door and window frame combination degree detection system of the present invention specifically includes the following modules:

[0082] The door and window machine platform is used to install the doors and windows to be tested. After the doors and windows to be tested are installed, adjustable environmental spaces are formed on both sides of the doors and windows to be tested. The door and window machine platform is provided with an environmental simulation unit, which is used to adjust the air pressure, temperature, humidity and concentration of the set gas in the two adjustable environmental spaces;

[0083] A mechanical arm execution module, which is arranged in an adjustable environment space on one side where a door and window handle is installed, and is used to perform multi-angle force opening and closing actions on the door and window to be inspected;

[0084] The sensor integration module is used to collect the air pressure, temperature, humidity, concentration of set gas, noise decibels when doors and windows are opened and closed, and the pulling force applied by the robot execution module when performing the opening and closing operation of two adjustable environment spaces according to the set collection frequency, and send the collected sensor data information;

[0085] The central data processing module is used to receive the sensor data information sent by the sensor integration module, perform statistical analysis on the sensor data information, calculate and obtain the door and window combination degree detection result of the door and window to be detected; and compare the door and window combination degree detection result with the preset door and window combination degree threshold to obtain the door and window combination degree detection result to be detected;

[0086] The detection result display module is used to read the combination degree detection result obtained by the central data processing module and visually display the combination degree detection result.

[0087] The system can accurately adjust the air pressure, temperature, humidity and concentration of set gases in two adjustable environmental spaces through the environmental simulation unit, thereby fully simulating various complex environmental conditions that doors and windows may encounter during actual use; ensuring the accuracy and practicality of the test results, making the test results closer to the actual use scenario;

[0088] The use of a robotic arm execution module to automatically perform multi-angle force opening and closing actions not only improves the detection efficiency, but also avoids errors and inconsistencies caused by human factors in manual detection; the precise control of the robotic arm ensures the repeatability and consistency of each test condition, and improves the reliability of the detection data;

[0089] The sensor integration module can collect multiple key parameters in real time and accurately, including environmental parameters and door and window performance parameters, providing a rich data basis for subsequent statistical analysis; the multi-dimensional analysis of these data can more comprehensively evaluate the combination performance of doors and windows;

[0090] The central data processing module statistically analyzes the collected data and automatically compares it with the preset door and window combination threshold to quickly obtain the combination test results; this intelligent processing method not only improves the detection efficiency, but also reduces human intervention and the possibility of misjudgment;

[0091] The test result display module visualizes the combination test results, making the test results intuitive and easy to understand; it not only facilitates the understanding and judgment of the test personnel, but also provides strong support for subsequent quality control and improvement;

[0092] In summary, the combined door and window frame combination detection system improves the accuracy and efficiency of door and window combination detection through the advantages of comprehensive simulation of the actual use environment, efficient automatic detection, multi-dimensional data collection and analysis, intelligent data processing and result judgment, and visual display of results.

[0093] Embodiment 2: Figures 2 to 3 As shown, a method for detecting the degree of assembly of a combined door and window frame of the present invention specifically comprises the following steps:

[0094] S1. According to the specification information of the doors and windows to be tested, the corresponding diffusion test scheme and opening and closing test scheme are retrieved from the preset test scheme library;

[0095] The diffusion test scheme is used to set the initial diffusion characteristic parameter vectors of the two adjustable environmental spaces, and to collect the real-time diffusion characteristic parameter vectors of the two adjustable environmental spaces after a set time period; the opening and closing test scheme is used to set the air pressure of the two adjustable environmental spaces, perform the door and window opening and closing actions through the robotic arm execution module, and collect the noise decibels generated by the opening and closing actions and the applied pulling force required for the opening and closing actions;

[0096] The test plan library contains multiple tables to store different types of data; the structure of the test plan library includes:

[0097] Door and window specification table, which stores basic specification information of doors and windows;

[0098] Test plan table, which stores specific test plan details, including diffusion test plan and opening and closing test plan;

[0099] Parameter configuration table, which stores the default values, ranges and specific requirements of various parameters;

[0100] The association table is used to establish a many-to-many relationship between the door and window specification table and the test plan table, because one door and window specification may correspond to multiple test plans, and one test plan may also be applicable to multiple door and window specifications;

[0101] The test plan table structure contains the following fields:

[0102] Scheme ID: an ID that uniquely identifies a test scheme;

[0103] Door and window specification ID: points to the ID of the door and window specification table, indicating which specifications of doors and windows the test plan is applicable to;

[0104] Test Type: Identifies the type of test scenario, such as "diffusion test", "open and close test", or a more specific classification;

[0105] Initial condition setting: including the specific values ​​or ranges of the initial air pressure, temperature, humidity and set gas concentration of the two adjustable environmental spaces;

[0106] Test duration: For diffusion tests, specify the length of time from setting the initial conditions to collecting real-time diffusion characteristic parameters;

[0107] Data collection frequency: specifies the frequency of data collection during the test;

[0108] Robot arm operation instructions: For the opening and closing test, describe how the robot arm execution module should perform the opening and closing action, including the force direction, angle, speed, etc.

[0109] Noise decibel threshold: For opening and closing tests, set the acceptable noise decibel range;

[0110] Tension threshold: For the opening and closing test, set the normal range of tension required when the robot arm performs the opening and closing action;

[0111] Evaluation model reference: For evaluation indicators that require model calculation, provide a reference or path to a pre-trained evaluation model;

[0112] Comments: Provides additional test protocol description or notes.

[0113] In this step, through the preset test solution library, the system can quickly and automatically call the corresponding diffusion test solution and opening and closing test solution according to the specification information of the doors and windows to be tested; it avoids the tedious process of manually selecting and configuring test parameters, and significantly improves the test efficiency; each test solution in the test solution library has been carefully designed and verified to ensure the standardization and consistency of the test process; it helps to reduce the impact of human factors on the test results and improve the accuracy and reliability of the test results; the test solution library supports a combination of multiple door and window specifications and multiple test types, so that the system can flexibly respond to test tasks with different needs; at the same time, through the design of the association table, a many-to-many relationship between door and window specifications and test solutions is realized, further enhancing the flexibility and scalability of the test; by pre-storing test solutions and parameter configurations, the system can use resources more effectively; during the test process, the system can The settings of the environmental simulation unit and the robotic arm execution module are automatically adjusted according to the test plan, avoiding waste of resources and unnecessary adjustment time. The diffusion test plan allows the system to set the initial diffusion characteristic parameter vectors of two adjustable environmental spaces and collect real-time data after a set period of time. This enables the system to simulate complex environments that may be encountered during actual use, thereby more comprehensively evaluating the sealing performance of doors and windows. The opening and closing test plan not only focuses on the opening and closing actions of doors and windows, but also collects parameters such as noise decibels and applied tension, combined with pre-trained evaluation models, to accurately evaluate the matching accuracy of doors and windows. This multi-parameter, multi-dimensional evaluation method helps to improve the accuracy and comprehensiveness of the evaluation. The structured design of the test plan library makes data management and analysis more convenient. The system can easily retrieve, store and analyze test data, providing strong support for subsequent quality control and product improvement.

[0114] S2, execute the diffusion test plan, respectively collect the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector after the set time in the two adjustable environmental spaces; the initial diffusion characteristic parameter vector includes the initial air pressure, initial temperature, initial humidity and initial set gas concentration; the real-time diffusion characteristic parameter vector includes the real-time air pressure, real-time temperature, real-time humidity and real-time set gas concentration;

[0115] The method for obtaining the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector includes:

[0116] According to the diffusion test plan, the initial environmental parameters of the two adjustable environmental spaces are set, including initial air pressure, initial temperature, initial humidity and initial set gas concentration; these parameters are precisely controlled to the preset values ​​through the environmental simulation unit;

[0117] Ensure that all sensors are calibrated to ensure the accuracy and reliability of measurement data;

[0118] After the doors and windows are closed and the environment is stable, the initial air pressure, initial temperature, initial humidity and initial set gas concentration in the two adjustable environmental spaces are immediately recorded. These data constitute the initial diffusion characteristic parameter vector;

[0119] According to the duration set in the test plan, the system continuously monitors and records the changes in environmental parameters; during this period, the environmental simulation unit may fine-tune certain parameters according to test requirements to simulate more complex environmental conditions;

[0120] After the set time period is over, the real-time air pressure, real-time temperature, real-time humidity and real-time set gas concentration in the two adjustable environmental spaces are collected again, and these data constitute the real-time diffusion characteristic parameter vector;

[0121] Accurately record all collected data and mark them with timestamps for subsequent data analysis;

[0122] Conduct preliminary verification of the collected data to check for outliers and obvious data errors to ensure the integrity and validity of the data;

[0123] During the entire data collection process, the system should continuously monitor the operating status of the environmental simulation unit and sensors to ensure that they are working properly and avoid data deviations caused by equipment failure.

[0124] In this step, by precisely adjusting the initial environmental parameters of the two adjustable environmental spaces and collecting real-time environmental parameters after a set period of time, the sealing performance of doors and windows under specific environmental conditions can be quantified; objective and accurate performance data is provided to door and window manufacturers and testing agencies, which helps to improve product quality and market competitiveness; the environmental simulation unit can fine-tune environmental parameters according to test requirements and simulate various complex environmental conditions that may be encountered during actual use; this simulation test can more realistically reflect the performance of doors and windows in actual applications, and provide strong support for product design and improvement; compared with traditional manual detection or simple mechanical device detection, this step uses an automated data acquisition and monitoring system, which can significantly improve detection efficiency and accuracy; automated detection reduces The system eliminates interference from human factors, ensures data reliability and consistency, and reduces detection costs and time. All collected data are accurately recorded and marked with timestamps, which is helpful for subsequent data analysis and problem tracing. The integrity and traceability of data provide an important basis for continuous improvement and optimization of product quality. During the data collection process, the system continuously monitors the operating status of the environmental simulation unit and sensors to ensure their normal operation. This real-time monitoring can promptly detect and prevent equipment failures, and avoid data deviations and detection failures caused by equipment problems. The S2 step has the beneficial effects of accurately quantifying sealing performance, simulating the actual use environment, improving detection efficiency and accuracy, ensuring data integrity and traceability, and realizing equipment monitoring and fault prevention.

[0125] S3, for each adjustable environment space, calculating the difference between the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector, and obtaining the diffusion characteristic parameter fluctuation vector of each adjustable environment space;

[0126] For each adjustable environment space, the difference between the initial value and the real-time value of each parameter is calculated to obtain the parameter fluctuation value;

[0127] After completing the difference calculation of all parameters, these differences are arranged according to their respective order in the diffusion characteristic parameter vector to form a new vector, namely the diffusion characteristic parameter fluctuation vector; the diffusion characteristic parameter fluctuation vector intuitively shows the changes of various environmental parameters in the adjustable environmental space during the test process, providing an important basis for the subsequent sealing performance evaluation;

[0128] If the fluctuation value of a parameter is found to be abnormally large, it is necessary to check whether there is a sensor failure or external interference, and consider whether it is necessary to retest the parameter;

[0129] The calculated fluctuation vectors are sent to the central data processing module and are the basis for subsequent analysis.

[0130] In this step, by calculating the difference between the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector, the specific changes in various environmental parameters in the adjustable environmental space during the test can be accurately quantified, providing a solid data basis for the subsequent sealing performance evaluation; in the process of calculating the difference, if it is found that the fluctuation value of a certain parameter is abnormally large, this often means that there may be problems such as sensor failure, external interference or poor sealing performance of doors and windows; timely detection of these problems will help to take corresponding measures to investigate and repair them, avoiding adverse effects on the test results; by forming diffusion characteristic parameter fluctuation vectors and using these vectors as the basis for subsequent analysis, it can be more comprehensive , systematically evaluate the sealing performance of doors and windows; not only consider the changes in a single environmental parameter, but also comprehensively consider the mutual influence of multiple parameters, thereby improving the reliability and accuracy of the test results; through the analysis of the fluctuation vector of the diffusion characteristic parameters, it can deeply understand the sealing performance of doors and windows under different environmental conditions; it can help manufacturers adjust product design according to actual needs and improve the overall performance of the product; S3 step is a key link in the combined door and window frame combination detection system, and its implementation depends on advanced sensor technology and data processing technology; the application of this automated detection technology not only improves the detection efficiency, but also reduces the impact of human factors on the detection results.

[0131] S4, performing fluctuation analysis on the diffusion characteristic parameter fluctuation vectors of the two adjustable environmental spaces to obtain the sealing performance evaluation index of the doors and windows to be tested;

[0132] The method for performing fluctuation analysis on the fluctuation vector of diffusion characteristic parameters of two adjustable environment spaces comprises:

[0133] The diffusion characteristic parameter fluctuation vectors are sorted to ensure the integrity and accuracy of the data and eliminate noise and outliers.

[0134] Compare the fluctuations of the corresponding parameters in the two adjustable environmental spaces; if the sealing performance of the doors and windows is good, the difference between the environmental parameters on the inside and outside will be small, because doors and windows with good sealing performance can effectively isolate the exchange of the internal and external environments;

[0135] Calculate the difference value of each parameter fluctuation;

[0136] According to the importance of different parameters on sealing performance, weights are assigned to the difference values ​​of each parameter; the difference in air pressure directly affects air tightness, so its weight is higher; while the difference in humidity has a smaller impact than air pressure, so its weight is lower;

[0137] The weighted difference values ​​are summarized to obtain a comprehensive sealing performance evaluation value; this evaluation value can be a dimensionless value used to quantify the sealing performance of the doors and windows during the test;

[0138] To facilitate comparison and interpretation, the above assessment values ​​can be standardized;

[0139] The standardized evaluation value is defined as the sealing performance evaluation index of the doors and windows to be tested; this index intuitively reflects the sealing performance level of the doors and windows under simulated environmental conditions;

[0140] The calculated sealing performance evaluation index is output for use in subsequent steps.

[0141] In this step, by comparing and analyzing the diffusion characteristic parameter fluctuation vectors of two adjustable environmental spaces, the sealing performance of doors and windows can be accurately quantified; not only the changes in a single parameter are considered, but also the influence of multiple parameters is integrated, thereby more comprehensively reflecting the sealing conditions of doors and windows; the entire analysis process is based on objective data collection and scientific calculation methods, which reduces the influence of human factors on the test results; it helps to improve the accuracy and reliability of the test results and avoid errors caused by human misjudgment; the system can simulate the complex environment that may be encountered during actual use and adjust it through the environmental simulation unit; this makes the test results closer to the actual situation and can more accurately reflect the sealing performance of doors and windows under different environmental conditions; the entire detection process is highly automated, from data collection The system automatically completes the entire process from analysis and calculation to result output; this greatly improves the detection efficiency, shortens the detection cycle, and reduces labor costs; the calculated sealing performance evaluation index is visualized to make the detection results more intuitive and easy to understand; it helps inspectors quickly understand the sealing performance level of doors and windows, and make corresponding judgments and processing; the calculated sealing performance evaluation index can not only be used to judge the current test results, but also can be used as the basic data for subsequent analysis to evaluate its quality stability and consistency; the evaluation index can also be compared with historical data to monitor the changing trend of the sealing performance of doors and windows; step S4 effectively obtains the sealing performance evaluation index of the doors and windows to be tested through a scientific fluctuation analysis method, providing strong support for the comprehensive evaluation of the quality of doors and windows.

[0142] S5, executing the opening and closing test plan, collecting the air pressure difference between the two adjustable environment spaces when the door and window to be tested are opened and closed, the decibel of noise generated by the opening and closing action, and the applied pulling force required for the opening and closing action;

[0143] The method of collecting the air pressure difference between two adjustable environment spaces when the door or window to be tested is opened or closed, the noise decibel generated by the opening or closing action, and the pulling force required for the opening or closing action includes:

[0144] According to the opening and closing test plan, the air pressure of the two adjustable environmental spaces is adjusted to the preset values ​​through the environmental simulation unit; these air pressure values ​​should simulate the indoor and outdoor air pressure differences that doors and windows may encounter in actual use to ensure the accuracy and practicality of the test;

[0145] Ensure that the robot arm execution module has been properly installed in the adjustable environmental space on the side where the door and window handle is installed and is in standby state; the robot arm should be pre-programmed to perform the preset multi-angle force opening and closing action sequence;

[0146] The control system starts the robot execution module to open and close the doors and windows according to the preset opening and closing action sequence;

[0147] While the robotic arm is opening and closing, the sensor integration module starts working, collecting air pressure difference, noise decibels and applied tension in real time;

[0148] Air pressure difference means that the air pressure difference sensor set between two adjustable environment spaces records the change of air pressure during opening and closing, reflecting the air tightness performance of doors and windows;

[0149] The noise decibel is recorded by noise sensors installed at appropriate locations when doors and windows are opened and closed;

[0150] The applied tension means that the tension sensor built into the robot arm execution module records the applied tension required for the opening and closing action; it reflects the mechanical strength and smoothness of the door and window;

[0151] The sensor integration module sends the collected air pressure difference, noise decibel and applied tension data to the central data processing module for recording in real time;

[0152] Perform preliminary verification of the received data, including checking data integrity and identifying outliers;

[0153] When the robot arm completes all preset opening and closing actions, the test phase ends;

[0154] The collected air pressure difference, noise decibel and applied tension data are used as the key output of the opening and closing test, ready for subsequent opening and closing feature evaluation model analysis and door and window combination degree calculation.

[0155] In this step, by simulating the indoor and outdoor air pressure difference that may be encountered in actual use, and combining the mechanical arm to execute the preset multi-angle force opening and closing action sequence, the performance of doors and windows in terms of air tightness, noise control and mechanical strength can be comprehensively and accurately evaluated; the use of the mechanical arm execution module and the sensor integration module realizes the automation and intelligence of the test; the precise control of the mechanical arm and the real-time data collection of the sensor reduce the error of human operation and improve the test efficiency and data accuracy; the sensor integration module sends the collected data to the central data processing module in real time for recording, which is convenient for subsequent data analysis and processing; at the same time, the preliminary verification of the data ensures the integrity of the data. The integrity and accuracy provide a reliable foundation for the subsequent opening and closing feature evaluation model analysis and door and window combination calculation; the key data such as air pressure difference, noise decibel and applied tension obtained through the test can deeply analyze the possible problems in the design and manufacturing process of doors and windows, and provide a scientific basis for product improvement and optimization; through strict opening and closing tests, it can ensure that doors and windows have good air tightness, low noise and smooth operation experience in actual use, thereby improving user satisfaction and comfort; this step provides strong support for quality control, performance evaluation and improvement and optimization of door and window products through comprehensive testing methods, automated intelligent means and data-driven decision support.

[0156] S6, inputting the air pressure difference, the noise decibel generated by the opening and closing action, and the applied pulling force required for the opening and closing action into a pre-trained opening and closing feature evaluation model to obtain a matching accuracy evaluation index of the door and window to be tested;

[0157] The method for constructing the opening and closing feature evaluation model comprises:

[0158] Collect historical test data from previous door and window inspections, including test results of different door and window models under various environmental conditions;

[0159] Clean the collected historical test data to remove outliers, missing values, and erroneous records to ensure data integrity and accuracy; scale feature data to the same range to eliminate the impact of different dimensions on model training;

[0160] According to the characteristics of the data and the complexity of the problem, a deep learning model is selected as the basic architecture of the open and closed feature evaluation model; the deep learning model includes a neural network, a random forest, a gradient boosting tree, a linear regression, and a logistic regression model;

[0161] The preprocessed data is divided into training set, validation set and test set; the division ratio is 70% training, 15% validation, and 15% test;

[0162] Use the training set data to train the model, and use the validation set data to monitor the model performance to prevent overfitting;

[0163] After adjusting the model on the validation set, the model performance is finally evaluated on an independent test set to ensure that the model has good generalization ability; the best model configuration is selected based on the evaluation results;

[0164] The trained model is deployed to the combined door and window frame combination detection system to evaluate the matching accuracy of doors and windows in real time;

[0165] The mathematical calculation formula for calculating the matching accuracy evaluation index of the door and window to be tested by the opening and closing feature evaluation model is:

[0166] ;

[0167] Among them, I fit Indicates the matching accuracy evaluation index of the doors and windows to be tested; w 1 represents the weight coefficient of air pressure difference; w 2 represents the weight coefficient of noise decibel; w 3 represents the weight coefficient of applied tension; Δ P Represents the air pressure difference between two adjustable environmental spaces; N Indicates the decibel of noise generated by the opening and closing action; F Indicates the pulling force required for opening and closing actions; b It is a bias term used to adjust the overall level of the evaluation index.

[0168] In this step, by introducing the pre-trained opening and closing feature evaluation model, multiple key factors such as air pressure difference, noise decibels and applied tension can be comprehensively considered, so as to more accurately evaluate the fitting accuracy of doors and windows; this multi-factor comprehensive evaluation method is more comprehensive and scientific than a single indicator evaluation, and effectively improves the accuracy and reliability of detection; the trained model is deployed in the combined door and window frame combination detection system to realize the automatic evaluation of the door and window matching accuracy; it not only reduces the errors caused by manual intervention and subjective judgment, but also greatly improves the detection efficiency; by collecting and analyzing historical test data, an opening and closing feature evaluation model is constructed; it not only taps the potential value of the data, but also provides strong support for subsequent detection and evaluation; at the same time, with the continuous addition of new data, the model can be continuously optimized and updated to maintain the advancement and accuracy of its evaluation capabilities; in the process of model construction , through preprocessing steps such as data cleaning, feature scaling and data set division, the quality and consistency of the model's input data are ensured; at the same time, the training set, validation set and test set are used for model training and evaluation, which effectively prevents the occurrence of overfitting and ensures that the model has good generalization ability; this makes the model applicable to door and window detection tasks under different models and different environmental conditions; in conjunction with the detection result display module, the calculated matching accuracy evaluation index is visualized, making the detection results more intuitive and easy to understand; it not only helps the inspection personnel to quickly determine whether the matching accuracy of doors and windows is qualified, but also provides a strong basis for subsequent improvements and optimizations; this step realizes the automatic and high-precision evaluation of the matching accuracy of doors and windows by introducing the pre-trained opening and closing feature evaluation model, improves the detection efficiency and accuracy, enhances the utilization value of data, and provides a visual display function.

[0169] S7, performing weighted calculation on the sealing performance evaluation index and the matching accuracy evaluation index of the doors and windows to be tested, and obtaining the door and window combination degree test results of the doors and windows to be tested;

[0170] It is necessary to determine the weights of the sealing performance evaluation index and the matching accuracy evaluation index in the final combination test results; the factors affecting the weight setting include:

[0171] Types and uses of doors and windows: Different types of doors and windows may have different requirements for sealing and fitting accuracy; doors and windows in high-rise buildings may require higher air tightness and water tightness requirements, so the weight of the sealing performance evaluation index may increase accordingly; the use of doors and windows is also an important factor in determining the weight; doors and windows used in cold areas may require stronger thermal insulation performance, which will also affect the weight of the sealing performance evaluation index;

[0172] Environmental conditions: The environmental conditions in which doors and windows are located will directly affect their performance. If doors and windows are often exposed to extreme weather conditions, the weight of the sealing performance evaluation index may be higher to ensure that the doors and windows can still maintain good performance under these conditions. For doors and windows that need to be opened and closed frequently, the weight of the matching accuracy evaluation index will be higher to ensure the smoothness of their operation and durability.

[0173] Industry standards and specifications: The relevant standards and specifications of the door and window industry usually put forward clear requirements for performance indicators such as sealing performance and matching accuracy; when setting weights, these standards and specifications should be referred to to ensure that the evaluation results are consistent with industry standards;

[0174] Customer needs and preferences: Customers’ specific needs and preferences are also one of the factors that need to be considered when setting weights. Some customers may pay more attention to the sound insulation performance or aesthetics of doors and windows, which will indirectly affect the weights of the sealing performance and matching accuracy evaluation index. Through market research and customer demand analysis, we can understand the degree of importance customers place on the performance indicators of doors and windows, so as to set the weights more accurately.

[0175] Historical data and experience: By analyzing historical test data, we can understand the performance of different types of doors and windows under different conditions and their changing patterns. At the same time, the experience of testers is also a factor that cannot be ignored. They can make valuable suggestions on the setting of weights based on the problems and solutions encountered during the actual test process.

[0176] The calculation formula for the door and window combination test result of the door and window to be tested is:

[0177] ;

[0178] Among them, I combo Indicates the door and window combination test result, I seal Indicates the sealing performance evaluation index, I fit represents the matching accuracy evaluation index, w seal Indicates the weight of sealing performance, w fit Indicates the weight of the fit accuracy.

[0179] In this step, the weights of the sealing performance evaluation index and the matching accuracy evaluation index are set by comprehensively considering multiple factors such as the type and purpose of doors and windows, the use environment conditions, industry standards and specifications, customer needs and preferences, historical data and experience, etc., so that the calculation of the door and window combination test results is more comprehensive and accurate; the one-sidedness of the weight determined by a single factor is reduced, and the reliability and scientificity of the test results are improved; taking into account the different requirements of different types of doors and windows and use environments for sealing and matching accuracy, the weights are allowed to be flexibly adjusted according to actual conditions, so as to more accurately reflect the actual performance of doors and windows in different application scenarios; this helps to meet the diverse needs of different customer groups and improve the market of products. Competitiveness; referring to industry standards and specifications when setting weights ensures the consistency of evaluation results with industry standards, which helps promote the standardization and regularization of the door and window industry; it not only improves the manufacturing level of the entire industry, but also provides consumers with more transparent and reliable product information; through scientific and reasonable weight setting, it can reduce unnecessary testing items and duplication of work while ensuring the accuracy of testing, thereby improving testing efficiency and reducing testing costs; by accurately setting weights and calculating the test results of door and window combination, companies can provide customers with door and window products that better meet their actual needs; this helps to improve customer satisfaction and brand loyalty, and lay a solid foundation for the long-term development of the company.

[0180] S8, comparing the door and window combination degree detection result with the preset door and window combination degree threshold value to determine whether the combination degree of the door and window to be detected is qualified;

[0181] The influencing factors for setting the preset door and window combination degree threshold include:

[0182] Building use environment: The climatic conditions in different regions have different requirements for the performance of doors and windows; the specific geographical location of the building will also affect the performance requirements of doors and windows;

[0183] Uses of doors and windows: Different types of doors and windows have different performance characteristics and usage requirements; the use occasions of doors and windows will also affect their performance requirements; the performance requirements of residential doors and windows and industrial doors and windows will be very different;

[0184] Customer demand: Customers’ specific requirements for the performance of doors and windows are an important basis for setting thresholds; doors and windows for high-end projects or specific purposes require more stringent quality standards; companies will set corporate standards higher than national standards based on their own product positioning and technical capabilities to improve product quality and market competitiveness;

[0185] Historical data analysis: By analyzing a large amount of historical test data, we can understand the performance of different types of doors and windows in actual use, so as to set reasonable thresholds;

[0186] Economic feasibility of technology implementation: The threshold to be set should take into account the current technological level and the feasibility of the manufacturing process; too high a threshold may lead to a significant increase in production costs or even make it impossible to achieve; the threshold to be set should also take into account economic costs; too high performance requirements will lead to excessively high product prices and affect market acceptance;

[0187] Reliability and durability: The long-term performance stability of doors and windows is also an important consideration; the set threshold should ensure that the doors and windows can maintain good performance in long-term use;

[0188] Maintenance costs: The maintenance costs of doors and windows are also a consideration when setting thresholds; higher-performing doors and windows may have lower maintenance costs but a higher initial investment.

[0189] In this step, by comprehensively considering the building use environment, door and window purposes, customer needs and other factors to set the preset door and window combination threshold, it can ensure that the doors and windows can meet specific performance requirements in the actual use environment; it helps to improve the overall performance of the building; by setting the threshold scientifically and reasonably, and combining with advanced detection systems and methods, the accuracy and reliability of door and window combination detection can be greatly improved; the interference of human factors is reduced, making the detection results more objective and fair, and providing a strong guarantee for the quality control of door and window products; by comparing the test results with the threshold, the performance deficiencies and potential problems of door and window products can be discovered in time; it helps manufacturers to continuously improve and optimize products based on feedback information, and improve the overall performance and market competitiveness of products; customers have diverse requirements for door and window performance, and by flexibly setting the threshold, the specific needs of different customer groups can be met; This helps to improve customer satisfaction, enhance customer stickiness, and lay a solid foundation for the long-term development of the company; when setting the threshold, factors such as the economy of technology implementation and reliability and durability are fully considered; this ensures that the threshold is set neither too high nor too low, which not only guarantees the performance requirements of the product, but also takes into account the production cost and market acceptance; this helps to achieve a win-win situation of economic and social benefits; by setting reasonable thresholds, it can ensure that doors and windows can still maintain good performance in long-term use; this helps to reduce the maintenance cost of doors and windows and improve the overall operational efficiency of buildings; step S8 achieves a comprehensive evaluation and judgment of the performance of doors and windows by scientifically and reasonably setting the preset door and window combination threshold and comparing it with the test results; this link not only improves the accuracy and reliability of the test results, but also promotes the continuous improvement and optimization of door and window products, meets the diverse needs of customers, and reduces maintenance costs.

[0190] The various variations and specific embodiments of the combined door and window frame combination degree detection method in the aforementioned embodiment 1 are also applicable to the combined door and window frame combination degree detection system in the present embodiment. Through the aforementioned detailed description of the combined door and window frame combination degree detection method, those skilled in the art can clearly know the implementation method of the combined door and window frame combination degree detection system in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0191] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0192] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A combined door and window frame combination detection system, characterized in that: The system comprises: The door and window machine platform is used to install the doors and windows to be tested. After the doors and windows to be tested are installed, adjustable environmental spaces are formed on both sides of the doors and windows to be tested. The door and window machine platform is provided with an environmental simulation unit, which is used to adjust the air pressure, temperature, humidity and concentration of the set gas in the two adjustable environmental spaces; A mechanical arm execution module, which is arranged in an adjustable environment space on one side where a door and window handle is installed, and is used to perform multi-angle force opening and closing actions on the door and window to be inspected; The sensor integration module is used to collect the air pressure, temperature, humidity, concentration of set gas, noise decibels when doors and windows are opened and closed, and the pulling force applied by the robot execution module when performing the opening and closing operation of two adjustable environment spaces according to the set collection frequency, and send the collected sensor data information; The central data processing module is used to receive the sensor data information sent by the sensor integration module, perform statistical analysis on the sensor data information, calculate and obtain the door and window combination degree detection result of the door and window to be detected; and compare the door and window combination degree detection result with the preset door and window combination degree threshold to obtain the door and window combination degree detection result to be detected; The detection result display module is used to read the combination degree detection result obtained by the central data processing module and visually display the combination degree detection result; The method for performing combination degree detection by the combined door and window frame combination degree detection system comprises: According to the specification information of the doors and windows to be tested, the corresponding diffusion test scheme and opening and closing test scheme are retrieved from the preset test scheme library; Execute the diffusion test plan, and respectively collect the initial diffusion characteristic parameter vectors and the real-time diffusion characteristic parameter vectors after the set time in the two adjustable environmental spaces; the initial diffusion characteristic parameter vectors include the initial air pressure, the initial temperature, the initial humidity and the initial set gas concentration; the real-time diffusion characteristic parameter vectors include the real-time air pressure, the real-time temperature, the real-time humidity and the real-time set gas concentration; For each adjustable environment space, the difference between the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector is calculated to obtain the diffusion characteristic parameter fluctuation vector of each adjustable environment space; The fluctuation analysis of the diffusion characteristic parameter fluctuation vectors of the two adjustable environmental spaces is performed to obtain the sealing performance evaluation index of the doors and windows to be tested; Execute the opening and closing test plan to collect the air pressure difference between the two adjustable environment spaces when the doors and windows to be tested are opened and closed, the decibel of noise generated by the opening and closing action, and the applied pulling force required for the opening and closing action; The air pressure difference, the noise decibel generated by the opening and closing action, and the applied pulling force required for the opening and closing action are input into a pre-trained opening and closing feature evaluation model to obtain a matching accuracy evaluation index of the door and window to be tested; Perform weighted calculation on the sealing performance evaluation index and matching accuracy evaluation index of the doors and windows to be tested, and obtain the door and window combination test results of the doors and windows to be tested; Compare the door and window combination degree detection result with the preset door and window combination degree threshold to determine whether the combination degree of the door and window to be detected is qualified; The mathematical calculation formula for calculating the matching accuracy evaluation index of the door and window to be tested by the opening and closing feature evaluation model is: Among them, I fit Indicates the matching accuracy evaluation index of the doors and windows to be tested; w 1 represents the weight coefficient of air pressure difference; w 2 represents the weight coefficient of noise decibel; w 3 represents the weight coefficient of applied tension; Δ P Represents the air pressure difference between two adjustable environmental spaces; N Indicates the decibel of noise generated by the opening and closing action; F Indicates the pulling force required for opening and closing actions; b It is a bias term used to adjust the overall level of the evaluation index.

2. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The method for constructing the opening and closing feature evaluation model comprises: Collect historical test data, including test results of different door and window models under various environmental conditions; Clean the collected historical test data to remove outliers, missing values ​​and erroneous records; Selecting a deep learning model as the basic architecture of the opening and closing feature evaluation model; the deep learning model includes a neural network, a random forest, a gradient boosting tree, a linear regression, and a logistic regression model; The preprocessed data is divided into training set, validation set and test set; the division ratio is 70% training, 15% validation, and 15% test; Use the training set data to train the model, and use the validation set data to monitor the model performance to prevent overfitting; After adjusting the model on the validation set, the model performance is finally evaluated on an independent test set to ensure that the model has good generalization ability; The trained model is deployed to the combined door and window frame combination detection system to evaluate the matching accuracy of doors and windows in real time.

3. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The calculation formula for the door and window combination test result of the door and window to be tested is: Among them, I combo Indicates the door and window combination test result, I seal Indicates the sealing performance evaluation index, I fit represents the matching accuracy evaluation index, w seal Indicates the weight of sealing performance, w fit Indicates the weight of the fit accuracy.

4. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The method for obtaining the initial diffusion characteristic parameter vector and the real-time diffusion characteristic parameter vector includes: According to the diffusion test plan, the initial environmental parameters of two adjustable environmental spaces are set; After the doors and windows are closed and the environment is stable, immediately record the initial air pressure, initial temperature, initial humidity and initial set gas concentration in the two adjustable environmental spaces; Continuously monitor and record changes in environmental parameters according to the duration set in the test plan; After the set time period is over, the real-time air pressure, real-time temperature, real-time humidity and real-time set gas concentration in the two adjustable environmental spaces are collected again; Accurately record all collected data and mark it with a time stamp; Perform a preliminary check on the collected data to check for outliers and data errors.

5. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The method for performing fluctuation analysis on the fluctuation vector of diffusion characteristic parameters of two adjustable environment spaces comprises: Sort out the fluctuation vectors of diffusion characteristic parameters to eliminate noise and outliers; Compare the fluctuations of corresponding parameters in two adjustable environment spaces and calculate the difference value of the fluctuation of each parameter; According to the importance of different parameters on sealing performance, weights are assigned to the difference values ​​of various parameters; The weighted difference values ​​are summarized to obtain a comprehensive sealing performance evaluation value; The evaluation value is standardized, and the standardized evaluation value is defined as the sealing performance evaluation index of the door and window to be tested; The calculated sealing performance evaluation index is output for use in subsequent steps.

6. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The method of collecting the air pressure difference between two adjustable environment spaces when the door or window to be tested is opened or closed, the noise decibel generated by the opening or closing action, and the pulling force required for the opening or closing action includes: According to the opening and closing test plan, adjust the air pressure of the two adjustable environmental spaces to the preset value; Start the robot arm execution module to open and close the doors and windows according to the preset opening and closing action sequence; While the robotic arm is performing the opening and closing action, the sensor integration module collects the air pressure difference, noise decibel and applied tension in real time; The sensor integration module sends the collected air pressure difference, noise decibel and applied tension data to the central data processing module for recording in real time; Perform preliminary verification on the received data; When the robot arm completes all preset opening and closing actions, the test phase ends; The collected air pressure difference, noise decibel and applied tension data are used as the output of the opening and closing test.

7. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The structure of the test solution library includes: Door and window specification table, used to store specification information of doors and windows; The test plan table is used to store specific test plan details, including diffusion test plan and opening and closing test plan; Parameter configuration table, used to store the default values, ranges and specific requirements of various parameters; An association table is used to establish a many-to-many relationship between the door and window specification table and the test plan table.

8. A combined door and window frame combination detection system as claimed in claim 1, characterized in that: The factors affecting the setting of the preset door and window combination threshold include the building use environment, door and window usage, customer needs, historical data analysis, technical implementation economy, reliability and durability, and maintenance cost.

Images