Intelligent ventilation control system and control method for medical laboratories

Abstract

The present invention relates to the field of ventilation control technology, and in particular to an intelligent ventilation control system for medical laboratories and a control method thereof. The method comprises the following steps: obtaining medical laboratory structural data; constructing a multi-point distributed sensor network for the medical laboratory structural data to generate a medical laboratory distributed sensor network; performing environmental multi-point data collection on the medical laboratory distributed sensor network to obtain a standard environmental collection data stream; performing dynamic environmental state modeling through the standard environmental collection data stream to generate environmental sensing state data; performing wind speed and airflow pattern calculation on the standard environmental collection data stream to generate laboratory cabinet door state sensing data. The present invention improves the safety and efficiency of intelligent ventilation control in medical laboratories through real-time data collection, dynamic modeling, comprehensive air quality and waste liquid treatment control, and system integration optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of ventilation control, and in particular to an intelligent ventilation control system and a control method thereof for a medical laboratory. Background Art

[0002] Early ventilation systems mostly used simple mechanical ventilation, which could not monitor and adjust indoor air quality in real time. With the increasing attention paid to air pollution and infection control, especially in special places such as hospitals and laboratories, the design of ventilation systems has gradually developed in a more intelligent direction. The rise of sensor technology and the Internet of Things (IoT) has provided new opportunities for the research and development of intelligent ventilation systems. By combining environmental sensors with ventilation equipment, parameters such as temperature, humidity, and carbon dioxide concentration can be monitored in real time, thereby achieving more accurate ventilation control. In addition, the application of intelligent algorithms enables ventilation systems to self-adjust according to real-time data, improve energy efficiency and ensure air quality in laboratories. Modern technologies, such as big data analysis and artificial intelligence, have further improved the intelligence level of ventilation systems, enabling them to predict and respond to sudden changes in air quality. However, the current traditional methods are not perfect in airflow pattern calculation and air filtration control, which can easily lead to uneven airflow distribution or ineffective removal of harmful gases. At the same time, traditional waste liquid treatment systems often lack monitoring and control mechanisms, resulting in untimely or inefficient waste liquid treatment, which in turn leads to low safety and efficiency of intelligent ventilation control. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent ventilation control system and a control method thereof for medical laboratories to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent ventilation control method for a medical laboratory is provided, the method comprising the following steps:

[0005] Step S1: Acquire medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental collection data stream; perform dynamic environmental state modeling through the standard environmental collection data stream to generate environmental sensing state data;

[0006] Step S2: Calculate the wind speed and airflow pattern of the standard environment collection data stream to generate laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment collection database;

[0007] Step S3: monitoring the waste liquid status according to the waste liquid treatment collection database to generate waste liquid status monitoring data; using the waste liquid status monitoring data to automatically control waste liquid collection to generate waste liquid collection control operation data; synchronizing and storing the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data;

[0008] Step S4: Based on the circulating air distribution data and the waste liquid collection cloud storage data, an internal and external circulation monitoring network is constructed to generate a medical laboratory cabinet ventilation circulation control monitoring network; the medical laboratory cabinet ventilation circulation control monitoring network is optimized for circulation efficiency feedback to generate medical laboratory cabinet ventilation control optimization data to perform intelligent ventilation control operations.

[0009] The present invention can fully perceive the environmental conditions inside the laboratory and provide accurate environmental information by acquiring medical laboratory structural data and constructing a multi-point distributed sensor network. The generated standard environment acquisition data stream ensures the consistency and accuracy of the data and provides a reliable basis for subsequent analysis and modeling. Dynamic environmental state modeling is performed through the standard environment acquisition data stream, and the generated environmental sensing state data can reflect the changes in the laboratory environment in real time and support rapid response. The calculation of wind speed and airflow pattern can monitor the state of the laboratory cabinet door in real time, thereby effectively evaluating the air flow and ventilation conditions and ensuring the laboratory air quality. Through the multiple filtration and degradation control of air, the generated circulating air distribution data can ensure the cleanliness of the air inside the laboratory and reduce the concentration of harmful substances. The toxic gas decomposition and compression control of the circulating air distribution data ensures the high efficiency of waste gas treatment and provides protection for the safety of the laboratory environment. The generation of waste liquid status monitoring data can track the state of the waste liquid in real time, discover and deal with potential problems in a timely manner, and ensure the safety and compliance of the laboratory. The waste liquid status monitoring data is used to automatically control the waste liquid collection, improve the efficiency of waste liquid treatment, reduce manual intervention, and improve work efficiency. The cloud-based synchronous storage of waste liquid collection and control operation data ensures the security and accessibility of the data, and provides support for subsequent analysis and decision-making. The internal and external circulation monitoring network constructed based on the circulating air distribution data and the waste liquid collection cloud storage data can realize comprehensive monitoring of laboratory air and waste liquid, and improve laboratory management efficiency. By optimizing the circulation efficiency feedback of the ventilation cycle control monitoring network, the efficiency and reliability of the laboratory ventilation system are ensured, and energy consumption and operating costs are reduced. Perform intelligent ventilation control operations, improve the automation level of the laboratory, reduce the manual burden, and improve the safety and accuracy of operations. Therefore, the present invention improves the safety and efficiency of intelligent ventilation control in medical laboratories through real-time data acquisition, dynamic modeling, comprehensive air quality and waste liquid treatment control, and system integration optimization.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire medical laboratory structure data;

[0012] Step S12: Select key positions based on the medical laboratory structure data to obtain key position data of the medical laboratory; construct a multi-point distributed sensor network based on the key position data of the medical laboratory to generate a distributed sensor network of the medical laboratory;

[0013] Step S13: collecting environmental multi-point data on the medical laboratory distributed sensor network to obtain an original environmental collection data stream; performing data preprocessing on the original environmental collection data stream to generate a standard environmental collection data stream, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0014] Step S14: Dynamic environment state modeling is performed through the standard environment acquisition data stream to generate environment sensing state data.

[0015] By acquiring the structural data of the medical laboratory, the present invention can fully understand the layout and spatial distribution of the laboratory, laying the foundation for subsequent data collection and analysis. The acquisition of structural data can help identify key areas and equipment in the laboratory, optimize resource allocation and sensor layout. Based on the structural data of the medical laboratory, key positions are selected to ensure that the deployment of the sensor network is highly targeted and can accurately capture the environmental information of important positions. The construction of a multi-point distributed sensor network can simultaneously monitor the environment of multiple key positions and improve the comprehensiveness and accuracy of data collection. The distributed sensor network of the medical laboratory performs environmental multi-point data collection to obtain rich original environmental data, providing a basis for subsequent analysis. Through data preprocessing (including data cleaning, denoising, missing value filling and standardization), the quality and reliability of the data can be significantly improved, ensuring the accuracy of subsequent analysis and modeling. Dynamic environmental state modeling is performed using standard environmental acquisition data streams, and the generated environmental sensing state data can reflect the environmental changes in the laboratory in real time, support rapid response, and provide data support for management and operation decisions, which helps to improve the safety and efficiency of the laboratory. By acquiring structural data, selecting key positions, building sensor networks and dynamic modeling, a systematic environmental monitoring framework is formed. This framework not only improves the accuracy and efficiency of laboratory environment monitoring, but also provides a solid foundation for subsequent intelligent control and optimization.

[0016] Preferably, step S14 comprises the following steps:

[0017] Step S141: performing feature sequence decomposition on the standard environment collection data stream to generate environment collection feature sequence data, wherein the feature sequence decomposition includes air temperature and humidity feature decomposition and particle concentration feature decomposition; performing window analysis on the environment collection feature sequence data to generate environment time series correlation data;

[0018] Step S142: using the environmental time series association data to perform laboratory space feature distribution analysis on the environmental collection feature sequence data to generate laboratory space feature parameter distribution data; performing convolution and nesting on the laboratory space feature parameter distribution data layer by layer to generate environmental space feature modeling data;

[0019] Step S143: Based on the preset RNN neural network, the environmental space feature modeling data is used to predict the environmental state and generate environmental sensing state data.

[0020] The present invention can analyze environmental data from multiple dimensions by decomposing the characteristic sequence of the standard environment acquisition data stream, including the decomposition of air temperature, humidity and particle concentration characteristics, which helps to identify the key factors affecting the laboratory environment. The environmental time series correlation data generated by window analysis can reveal the regularity of environmental parameters changing over time, and provide basic data for further analysis and modeling. Using environmental time series correlation data to analyze the distribution of laboratory space characteristics helps to understand the differences in environmental characteristics in different spatial areas and provide a basis for optimizing environmental control strategies. Convolution and layer-by-layer nesting of laboratory space characteristic parameter distribution data can extract deeper features, enhance the model's ability to understand complex environments, and make the model more effective in processing high-dimensional data. Based on the preset RNN (recurrent neural network), environmental space feature modeling data is used to predict environmental status, which can capture the dependencies in time series data, improve the accuracy and timeliness of prediction, and the generated environmental sensing status data can provide real-time support for laboratory management and operational decisions, help to respond to environmental changes in a timely manner, and ensure the safety and stability of the laboratory. Through multi-dimensional feature extraction, spatial analysis and dynamic prediction, a powerful environmental monitoring and control framework is formed. This framework not only improves the ability to understand and respond to the laboratory environment, but also enables precise environmental control through intelligent data analysis, providing a solid foundation for the efficient operation of the laboratory. Through these steps, the laboratory can achieve more intelligent management and control.

[0021] Preferably, step S2 comprises the following steps:

[0022] Step S21: Calculate the wind speed and airflow pattern of the standard environment collection data stream to obtain dynamic wind speed distribution data; perform laboratory cabinet door state sensing on the environment sensing state data through the dynamic wind speed distribution data to generate laboratory cabinet door state sensing data;

[0023] Step S22: performing air flow monitoring on the dynamic wind speed distribution data based on the laboratory cabinet door state sensing data to generate air flow monitoring data; performing air stratification on the air flow monitoring data to generate air stratification data; performing multiple filtering guidance control on the air flow monitoring data based on the air stratification data to generate circulating air distribution data;

[0024] Step S23: Analyze the toxic gas composition of the circulating air distribution data to generate toxic gas composition data; calculate the gas proportion of the circulating air distribution data using the toxic gas composition data to obtain toxic gas proportion data;

[0025] Step S24: Compare the toxic gas proportion data with the preset standard toxic gas proportion threshold. When the toxic gas proportion data is greater than the preset standard toxic gas proportion threshold, the circulating air distribution data is controlled to decompose and compress the toxic gas according to the toxic gas proportion data to generate a waste liquid treatment collection database.

[0026] The present invention collects the wind speed and airflow pattern of the data stream of the standard environment, and the generated dynamic wind speed distribution data can accurately reflect the air flow in the laboratory, which is helpful to understand the efficiency and dynamic changes of air exchange. The generated laboratory cabinet door state sensing data can timely identify the opening and closing state of the cabinet door, and then help analyze the impact of air flow on the cabinet environment, and ensure the safety of laboratory samples and equipment. Based on the laboratory cabinet door state sensing data, the dynamic wind speed distribution data is monitored for air flow, which can provide a more comprehensive air flow situation and help understand the air circulation effect of the laboratory. By performing air stratification analysis on the air flow monitoring data, the air quality changes at different levels can be identified, providing a basis for air quality optimization control, and ensuring that all areas of the laboratory have good air conditions. Based on the air stratification guidance data, the air flow monitoring data is subjected to multiple filtering guidance control, which can effectively reduce the diffusion of pollutants in the air, improve the air purification effect, and maintain the air safety of the laboratory. The toxic gas composition analysis of the circulating air distribution data can timely identify potential air pollution risks and provide protection for laboratory safety. Using toxic gas composition data to calculate gas proportions helps to understand the proportions of different toxic gases in the air, so as to take targeted control measures to reduce health threats to laboratory workers. Comparing the toxic gas proportion data with the preset standard toxic gas proportion threshold can establish an effective safety early warning mechanism and promptly discover potential safety hazards. When the toxic gas proportion data exceeds the preset threshold, toxic gas decomposition and compression control measures are taken to quickly reduce the concentration of toxic gases in the air and generate a waste liquid treatment database for subsequent safe treatment and management. Through precise air flow monitoring and toxic gas analysis, a comprehensive laboratory air quality management system is formed. This system not only improves the safety and comfort of the laboratory environment, but also effectively prevents potential toxic gas hazards, providing a guarantee for the efficient and safe operation of the laboratory.

[0027] Preferably, step S21 includes the following steps:

[0028] Step S211: extracting air quality and humidity and temperature information from the standard environment collection data stream to obtain regional air quality data and regional humidity and temperature information data; performing preliminary velocity field modeling based on the regional air quality data and regional humidity and temperature information data to generate preliminary velocity field data;

[0029] Step S212: Perform three-dimensional path planning on the preliminary velocity field data to generate laboratory optimal air flow path data;

[0030] Step S213: performing discrete element method simulation on the laboratory optimal air flow path data to generate regional air resistance change data; performing dynamic flow pressure calculation on the regional air resistance change data to obtain regional dynamic pressure distribution data;

[0031] The formula for calculating dynamic flow pressure is as follows:

[0032]

[0033] In the formula, represents the dynamic flow pressure, Expressed as the fluid resistance coefficient, Expressed as air density, Expressed as wind speed;

[0034] Step S214: Detect the door flow field change of the medical laboratory cabinet through the regional dynamic pressure distribution data to generate the door state flow field change data; perform three-dimensional fluid simulation on the door state flow field change data to generate dynamic wind speed distribution data; perform abnormal wind speed change analysis on the dynamic wind speed distribution data to generate abnormal wind speed change data;

[0035] Step S215: Confirm the change of laboratory door status by comparing the environmental sensing status data with the abnormal wind speed change data, and perform airflow direction offset analysis on the door status flow field change data to generate an airflow direction offset matrix; perform state sensing on the laboratory door according to the airflow direction offset matrix and the regional dynamic pressure distribution data to generate laboratory door status sensing data.

[0036] The present invention can monitor the air quality in the laboratory in real time by extracting air quality and humidity temperature information from the standard environment acquisition data stream, and provide basic data for subsequent air flow modeling. Preliminary velocity field modeling based on the extracted regional air quality data and humidity temperature information is helpful to understand the basic characteristics of airflow in the laboratory and lay the foundation for optimizing the air flow path. The optimal air flow path data of the laboratory is generated by performing three-dimensional path planning on the preliminary velocity field data. This path planning can effectively reduce the resistance in the air flow, improve the air exchange efficiency, and ensure that the air quality of the laboratory is improved. By performing discrete element method simulation on the optimal air flow path data of the laboratory, regional air resistance change data can be obtained. This analysis can identify the obstacles that affect the air flow, thereby providing a reference for subsequent improvement of the air flow path. The regional dynamic pressure distribution is calculated by the dynamic flow pressure calculation formula to provide an important physical quantity basis for the state of air flow. This data can help understand the behavior of air flow under different environmental conditions and provide support for optimizing air flow design. By detecting the change of the door flow field of the medical laboratory cabinet through the regional dynamic pressure distribution data, the influence of the door opening or closing on the laboratory airflow can be timely identified. This helps ensure the safety of samples and equipment in the cabinet and reduce potential contamination risks. By analyzing the abnormal wind speed changes in the dynamic wind speed distribution data, it is possible to monitor and identify unstable airflow in real time, so that corresponding measures can be taken to ensure the stability of airflow in the laboratory. By confirming the change of the state of the laboratory cabinet door through the environmental sensing state data based on the abnormal wind speed change data, it is possible to respond to the change of the cabinet door state in a timely manner and effectively manage the laboratory environment. By sensing the state of the laboratory cabinet door based on the airflow direction offset matrix and the regional dynamic pressure distribution data, the offset of the airflow direction can be identified, thereby providing guidance for optimizing air flow and ensuring stable air quality in the laboratory. Through a series of refined analyses and simulations, a systematic laboratory air flow monitoring and control mechanism was established. This mechanism not only improves the air flow efficiency and air quality in the laboratory, but also helps to identify and deal with potential air flow anomalies in a timely manner, providing a guarantee for the safe and efficient operation of the laboratory. Through these measures, the laboratory can achieve more intelligent and dynamic air quality management.

[0037] Preferably, step S22 includes the following steps:

[0038] Step S221: performing air flow monitoring on the dynamic wind speed distribution data based on the laboratory cabinet door state sensing data to generate air flow monitoring data;

[0039] Step S222: performing air particle size identification on the air flow monitoring data to obtain air flow particle size data; performing gaseous pollutant component identification on the air flow monitoring data to generate gaseous pollutant component identification data; performing air stratification on the air flow monitoring data according to the air flow particle size data and the gaseous pollutant component identification data to generate air stratification data, wherein the air stratification data includes primary air stratification data, secondary air stratification data and tertiary air stratification data;

[0040] Step S223: Based on the primary air stratification data, the medical laboratory cabinet is subjected to nanofiber air filtration control to generate primary filtration control data; based on the secondary air stratification data, the medical laboratory cabinet is subjected to porous activated carbon air filtration control to generate medium filtration control data; based on the tertiary air stratification data, the medical laboratory cabinet is subjected to nano-scale membrane air filtration control to generate high efficiency filtration control data;

[0041] Step S224: Integrate the primary filtration control data, the medium filtration control data and the high efficiency filtration control data to generate air stratification data; perform multiple degradation efficiency calculations on the air stratification data to obtain multiple filtration degradation efficiency data; wherein the formula for multiple degradation efficiency calculation is as follows:

[0042]

[0043] In the formula, Expressed as the multiple degradation efficiency, Represented as the weight coefficient of the first layer of filtering, Represented as the weight coefficient of the second layer of filtering, Expressed as the weight coefficient of the third layer of filtering, Represented as primary filtration control data, Expressed as medium efficiency filtration control data, Represents efficient filtering control data;

[0044] Step S225: Perform multiple filtering guidance control on the air flow monitoring data through multiple filtering degradation efficiency data to generate circulating air distribution data.

[0045] The present invention can obtain the state of air flow in real time by monitoring the dynamic wind speed distribution data based on the state sensing data of the laboratory cabinet door. This provides important basic data for subsequent air quality control and ensures the rationality and stability of air flow in the laboratory. By identifying the air particle size of the air flow monitoring data, the air flow particle size data is obtained. This information helps to understand the impact of different particulate matter on air quality and provides a basis for subsequent filtration control. The components of gaseous pollutants are identified to generate gaseous pollutant component identification data. This data can help identify and evaluate potential air pollution sources and provide a scientific basis for subsequent purification measures. Air stratification is performed according to the air flow particle size data and the gaseous pollutant component identification data to generate air stratification data of different levels (such as primary, secondary, and tertiary air stratification data). This stratification process makes air management more refined and helps to achieve targeted filtration. Based on the air stratification data of different levels, targeted filtration control is performed: large particles are initially filtered to prevent them from entering the medical laboratory cabinet. Materials such as porous activated carbon are used to further adsorb medium particles and some gaseous pollutants in the air. Nano-scale filter membranes are used for final filtration to ensure the effective removal of tiny particles and harmful gases. The primary, medium and high efficiency filtration control data are integrated to generate comprehensive air stratification data. This integration makes the control of the filtration process more systematic and provides a comprehensive air treatment effect. The overall filtration effect is evaluated through the degradation efficiency calculation formula. This formula takes into account the weights of different levels of filtration, provides a quantitative basis for laboratory air quality management, and helps to optimize the filtration strategy. The air flow monitoring data is multi-filtered and guided by multiple filtration degradation efficiency data to generate circulating air distribution data. This not only improves the efficiency of air filtration, but also effectively reduces the concentration of harmful gases in the laboratory, ensuring that the air quality in the laboratory meets the standards. Through sophisticated air flow monitoring, stratified control and multi-level filtration strategies, an efficient laboratory air quality management system is constructed. The system can effectively identify different components and particulate matter in the air, implement targeted filtration control, and minimize the risk of air pollution.

[0046] Preferably, step S225 includes the following steps:

[0047] Using the air flow monitoring data to screen the air quality inside the medical laboratory cabinet, and obtaining the air quality data inside the cabinet; performing air quality evaluation on the air quality data inside the cabinet, and generating the air quality evaluation data inside the cabinet;

[0048] Perform zoning demand analysis on air flow monitoring data based on cabinet air quality assessment data to generate regional air quality demand data; perform air redistribution demand priority setting on regional air quality demand data to generate internal circulation priority data;

[0049] Based on the internal circulation priority data, dynamic airflow distribution is performed on the regional air quality demand data to generate dynamic airflow distribution data; regional wind speed is adjusted through the dynamic airflow distribution data to generate regional wind speed adjustment data; the air flow path of the laboratory optimal air flow path data is optimized according to the regional wind speed adjustment data to generate circulating air distribution data.

[0050] The present invention obtains cabinet air quality data by screening the cabinet air quality of air flow monitoring data. This process can quickly identify the pollution of the cabinet air and timely discover potential air quality problems. The cabinet air quality data is evaluated to generate cabinet air quality evaluation data. This evaluation provides a scientific basis for subsequent air treatment decisions and helps to ensure the safety of the laboratory environment. According to the cabinet air quality evaluation data, the air flow monitoring data is analyzed for partition demand to generate regional air quality demand data. This partition analysis can accurately identify the air quality requirements in different areas and ensure the pertinence and effectiveness of air treatment measures. Priority is set for the regional air quality demand data to generate internal circulation priority data. Through this priority setting, resources can be effectively allocated, and severely polluted areas can be given priority to maximize air quality. Based on the internal circulation priority data, the regional air quality demand data is dynamically distributed to generate dynamic air flow distribution data. This dynamic distribution can achieve flexible air flow adjustment to ensure that the air quality of important areas is improved in a timely manner. The regional wind speed is adjusted through the dynamic air flow distribution data to generate regional wind speed adjustment data. Reasonable adjustment of wind speed can further optimize air flow, avoid air stagnation or dead corners, and thus improve air renewal rate. According to the regional wind speed adjustment data, the laboratory's optimal air flow path data is optimized to generate circulating air distribution data. This optimization ensures the scientificity and effectiveness of the air flow path, thereby improving the overall air quality. Through multi-level air quality assessment, demand analysis and dynamic air flow distribution, an efficient air flow management system is established. The system can effectively monitor and optimize the air quality in the laboratory cabinet to ensure the safety and comfort of the laboratory environment.

[0051] Preferably, step S24 includes the following steps:

[0052] Step S241: comparing the toxic gas proportion data with a preset standard toxic gas proportion threshold value. When the toxic gas proportion data is greater than the preset standard toxic gas proportion threshold value, the circulating air distribution data is subjected to toxic gas identification using a gas sensor according to the toxic gas proportion data to generate toxic gas identification data.

[0053] Step S242: designing a gas decomposition scheme for the toxic gas identification data to generate a gas decomposition treatment scheme; setting and debugging a decomposition device based on the gas decomposition treatment scheme to generate decomposition device performance evaluation data;

[0054] Step S243: Record the implementation of toxic gas decomposition of the gas decomposition treatment plan through the decomposition device performance evaluation data to generate a decomposition gas conversion record; perform waste liquid compression and centralized data collection on the toxic gas identification data based on the decomposition gas conversion record to generate a waste liquid treatment collection database.

[0055] The present invention compares the toxic gas proportion data with the preset standard toxic gas proportion threshold. This step can quickly identify the concentration level of toxic gases in the air and promptly determine whether it exceeds the safety standard, thereby providing a scientific basis for subsequent countermeasures. If the toxic gas proportion data is greater than the standard threshold, the gas sensor is used to identify the toxic gas in the circulating air distribution data to generate toxic gas identification data. By accurately identifying the types and concentrations of toxic gases, it is possible to quickly respond to potential hazards, reduce the impact on laboratory staff and the environment, and improve the level of safety management. A gas decomposition scheme is designed for the toxic gas identification data to generate a gas decomposition treatment scheme. The scheme can specifically treat specific types of toxic gases, thereby improving the efficiency and effectiveness of gas treatment and ensuring the pertinence of waste gas treatment. The decomposition device is set and debugged based on the gas decomposition treatment scheme, and the decomposition device performance evaluation data is generated. Ensure the normal operation of the decomposition device, maximize the waste gas treatment effect, and avoid secondary pollution. The gas decomposition treatment scheme is recorded for toxic gas decomposition implementation through the decomposition device performance evaluation data, and a decomposition gas conversion record is generated. Recording each gas decomposition process and its effect is convenient for subsequent quality evaluation and improvement, which helps to form a complete operating specification and standard. According to the decomposition gas conversion records, the toxic gas identification data is compressed and centralized to collect data to generate a waste liquid treatment database. This database can provide data support for future waste liquid treatment, help evaluate the treatment effect of waste liquid and optimize the treatment process, thereby reducing the impact on the environment. Through the effective monitoring and treatment of toxic gases, a systematic management mechanism is established to ensure a safe environment in medical laboratories. These measures not only improve the safety of the laboratory, but also provide reliable protection for scientific research work, avoiding the adverse effects of toxic gases on the health of staff and experimental results. By implementing gas identification, decomposition and waste liquid treatment, this step provides a comprehensive environmental management solution for medical laboratories to support safe and sustainable scientific research activities.

[0056] Preferably, step S3 comprises the following steps:

[0057] Step S31: Designing a waste liquid collection system according to a waste liquid treatment and collection database to generate a waste liquid collection system design document; configuring intelligent sensors for the medical laboratory cabinet based on the waste liquid collection system design document to generate sensor configuration data, wherein the intelligent sensor configuration includes a liquid level sensor and a pressure sensor;

[0058] Step S32: monitoring the waste liquid status of the sensor configuration data to generate waste liquid status monitoring data; automatically regulating the waste liquid collection system using the waste liquid status monitoring data to generate waste liquid collection regulation operation data;

[0059] Step S33: Synchronize and store the waste liquid collection and control operation data in the cloud to generate waste liquid collection cloud storage data.

[0060] The present invention designs a waste liquid collection system according to a waste liquid treatment and collection database to generate a waste liquid collection system design document. The system design document provides detailed guidance for subsequent implementation, ensures the rationality and scientificity of the waste liquid collection system, and thus improves the collection efficiency and effect. Based on the design document, the medical laboratory cabinet is configured with intelligent sensors to generate sensor configuration data, including a liquid level sensor and a pressure sensor. By installing the liquid level sensor and the pressure sensor, the state of the waste liquid is monitored in real time, the automation of the system is improved, the need for manual intervention is reduced, and the operation risk is reduced. The sensor configuration data is used to monitor the waste liquid state and generate waste liquid state monitoring data. The state of the waste liquid (such as liquid level and pressure) is monitored in real time, and abnormal conditions are discovered in time, thereby improving the safety of waste liquid management and avoiding potential leakage or overflow risks. The waste liquid state monitoring data is used to automatically control the waste liquid collection system and generate waste liquid collection control operation data. The automatic control system adjusts the waste liquid collection process according to the real-time monitoring data to ensure the timeliness and effectiveness of the waste liquid collection and avoid delays or errors caused by manual operation. The waste liquid collection control operation data is synchronized and stored in the cloud to generate waste liquid collection cloud storage data. Storing waste liquid collection data in the cloud facilitates centralized data management and long-term preservation, and enables data access and analysis across devices and locations. This not only enhances data security, but also supports subsequent data analysis and optimized decision-making. By establishing an efficient waste liquid collection system, combined with intelligent sensor technology and cloud data management, real-time monitoring, automatic control and centralized storage of waste liquid are achieved. These measures improve laboratory safety, operational efficiency and the level of intelligent waste liquid management. Through scientific design and implementation, this step provides a sustainable and efficient waste liquid management solution for medical laboratories, ensuring the safety and hygiene of the laboratory environment.

[0061] In this specification, an intelligent ventilation control system for a medical laboratory is provided, which is used to execute the above-mentioned intelligent ventilation control method for a medical laboratory. The intelligent ventilation control system for a medical laboratory includes:

[0062] The external environment acquisition module is used to obtain the medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental acquisition data stream; perform dynamic environmental state modeling through the standard environmental acquisition data stream to generate environmental sensing state data;

[0063] The air purification module is used to calculate the wind speed and airflow pattern of the standard environment acquisition data stream to generate laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment collection database;

[0064] The waste liquid monitoring module is used to monitor the waste liquid status according to the waste liquid treatment and collection database to generate waste liquid status monitoring data; use the waste liquid status monitoring data to automatically control the waste liquid collection to generate waste liquid collection control operation data; synchronize the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data;

[0065] The internal and external circulation feedback module is used to build an internal and external circulation monitoring network based on the circulating air distribution data and the waste liquid collection cloud storage data, and generate a medical laboratory cabinet ventilation circulation control monitoring network; the medical laboratory cabinet ventilation circulation control monitoring network is optimized by circulation efficiency feedback, and the medical laboratory cabinet ventilation control optimization data is generated to perform intelligent ventilation control operations.

[0066] The beneficial effect of the present invention is that by acquiring the structural data of the medical laboratory, a comprehensive understanding of the internal layout and environmental conditions of the laboratory is ensured, laying the foundation for subsequent analysis. Full coverage monitoring is achieved through a distributed sensor network to improve the accuracy and reliability of data. Real-time acquisition of environmental information ensures comprehensive monitoring of air quality and status, provides data support for dynamic adjustment, generates environmental sensing status data, can timely reflect changes in the laboratory, and improve the intelligent level of environmental monitoring. Wind speed and airflow pattern calculation generates laboratory cabinet door status sensing data, which helps to understand the distribution of airflow in the laboratory and improve the effectiveness of air flow. Adjust the air flow according to the cabinet door status to achieve more efficient air filtration and reduce the concentration of harmful substances. Toxic gas decomposition and compression control generates a waste liquid treatment database, improves the monitoring and treatment capabilities of toxic gases, and ensures the safety of the laboratory environment. By monitoring the waste liquid status, potential problems are discovered and solved in a timely manner, and the safety and efficiency of waste liquid treatment are improved. Automatic regulation of waste liquid collection realizes automatic regulation of waste liquid collection, reduces manual intervention, and improves work efficiency and safety. The waste liquid collection and regulation operation data is stored in the cloud to ensure the security and traceability of the data, which is convenient for subsequent analysis and auditing. By integrating the circulating air distribution and waste liquid collection data, a comprehensive monitoring network is formed to enhance the control of the overall laboratory environment. Feedback optimization is performed on the monitoring network to improve the operating efficiency of the ventilation system and waste liquid treatment, and to achieve the rational use of resources. Ultimately, intelligent ventilation control is achieved to ensure the air quality and safety of medical laboratories and provide good environmental support for scientific research and experiments. Therefore, the present invention improves the safety and efficiency of intelligent ventilation control in medical laboratories through real-time data acquisition, dynamic modeling, comprehensive air quality and waste liquid treatment control, and system integration optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A schematic diagram of a process flow of an intelligent ventilation control method for a medical laboratory;

[0068] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0069] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0070] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0071] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0072] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0073] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0074] To achieve this, please refer to Figures 1 to 3 , an intelligent ventilation control method for a medical laboratory, the method comprising the following steps:

[0075] Step S1: Acquire medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental collection data stream; perform dynamic environmental state modeling through the standard environmental collection data stream to generate environmental sensing state data;

[0076] Step S2: Calculate the wind speed and airflow pattern of the standard environment collection data stream to generate laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment database;

[0077] Step S3: monitoring the waste liquid status according to the waste liquid treatment collection database to generate waste liquid status monitoring data; using the waste liquid status monitoring data to automatically control waste liquid collection to generate waste liquid collection control operation data; synchronizing and storing the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data;

[0078] Step S4: Based on the circulating air distribution data and the waste liquid collection cloud storage data, an internal and external circulation monitoring network is constructed to generate a medical laboratory cabinet ventilation circulation control monitoring network; the medical laboratory cabinet ventilation circulation control monitoring network is optimized for circulation efficiency feedback to generate medical laboratory cabinet ventilation control optimization data to perform intelligent ventilation control operations.

[0079] The present invention can fully perceive the environmental conditions inside the laboratory and provide accurate environmental information by acquiring medical laboratory structural data and constructing a multi-point distributed sensor network. The generated standard environment acquisition data stream ensures the consistency and accuracy of the data and provides a reliable basis for subsequent analysis and modeling. Dynamic environmental state modeling is performed through the standard environment acquisition data stream, and the generated environmental sensing state data can reflect the changes in the laboratory environment in real time and support rapid response. The calculation of wind speed and airflow pattern can monitor the state of the laboratory cabinet door in real time, thereby effectively evaluating the air flow and ventilation conditions and ensuring the laboratory air quality. Through the multiple filtration and degradation control of air, the generated circulating air distribution data can ensure the cleanliness of the air inside the laboratory and reduce the concentration of harmful substances. The toxic gas decomposition and compression control of the circulating air distribution data ensures the high efficiency of waste gas treatment and provides protection for the safety of the laboratory environment. The generation of waste liquid status monitoring data can track the state of the waste liquid in real time, discover and deal with potential problems in a timely manner, and ensure the safety and compliance of the laboratory. The waste liquid status monitoring data is used to automatically control the waste liquid collection, improve the efficiency of waste liquid treatment, reduce manual intervention, and improve work efficiency. The cloud-based synchronous storage of waste liquid collection and control operation data ensures the security and accessibility of the data, and provides support for subsequent analysis and decision-making. The internal and external circulation monitoring network constructed based on the circulating air distribution data and the waste liquid collection cloud storage data can realize comprehensive monitoring of laboratory air and waste liquid, and improve laboratory management efficiency. By optimizing the circulation efficiency feedback of the ventilation cycle control monitoring network, the efficiency and reliability of the laboratory ventilation system are ensured, and energy consumption and operating costs are reduced. Perform intelligent ventilation control operations, improve the automation level of the laboratory, reduce the manual burden, and improve the safety and accuracy of operations. Therefore, the present invention improves the safety and efficiency of intelligent ventilation control in medical laboratories through real-time data acquisition, dynamic modeling, comprehensive air quality and waste liquid treatment control, and system integration optimization.

[0080] In the embodiment of the present invention, reference Figure 1The above is a schematic flow chart of the steps of an intelligent ventilation control method for a medical laboratory of the present invention. In this example, the intelligent ventilation control method for a medical laboratory includes the following steps:

[0081] Step S1: Acquire medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental collection data stream; perform dynamic environmental state modeling through the standard environmental collection data stream to generate environmental sensing state data;

[0082] In the embodiment of the present invention, by obtaining the architectural design drawings, floor plans and structural drawings of the medical laboratory, focus on the layout of equipment, laboratory benches and pipelines. Prepare a detailed equipment list, including various types of medical equipment and their models, specifications and location information. Use a laser scanner (such as Leica BLK360 or FARO Focus) to obtain three-dimensional spatial data in the laboratory. Scan from multiple angles to ensure the integrity of the data. Use a high-resolution camera to take multi-angle photos of the interior of the laboratory, and use software (such as Agisoft Metashape or Pix4D) to stitch and 3D reconstruct the photos. If necessary, use GIS tools to integrate data related to the external environment (such as sanitary facilities, traffic conditions, etc.). Use BIM software (such as AutodeskRevit or Archicad) to integrate laser scanning data and CAD drawings to generate an accurate 3D model. Convert all data into a unified format (such as OBJ, FBX or DGN) for subsequent analysis. Select sensors for specific environmental monitoring, such as temperature and humidity sensors (such as DHT22), gas sensors (such as MQ-2) and air quality sensors (such as MQ-135). According to the type of sensor, select the corresponding communication protocol (such as Zigbee, LoRa, Wi-Fi, etc.) to ensure the stability and reliability of data transmission. According to the structure of the medical laboratory, develop a sensor layout plan to ensure that all key areas are covered, such as laboratory entrances, equipment surroundings, and vents. Consider the installation height of the sensor to ensure that the sensor can accurately obtain the required environmental data. Set a unique network address for each sensor to ensure the uniqueness of the data. Design the sensor network topology according to the layout of the laboratory, specifically using a star, mesh, or hybrid topology. Install all sensors according to the layout design and connect the power and data cables. Configure routers, gateways, and relay devices to ensure that data can be smoothly transmitted to the central processing unit. Test the sensors one by one to ensure that they can normally collect data and transmit it to the central server. Check the stability of the network connection to ensure that the data can be updated in real time, and adjust the sensor position if necessary. Develop a detailed data collection plan, including the collection time interval (such as once every 5 minutes) and the monitored environmental parameters. Select a suitable database (such as MySQL, MongoDB) to store the collected environmental data to ensure data scalability. Use stream processing tools (such as Apache Kafka or RabbitMQ) to implement real-time processing of data streams and transfer data to the data processing module. Record sensor data in real time and generate a standard environmental collection data stream. Use programming languages ​​such as Python or R to write data cleaning scripts to remove noise, missing values, and outliers. Convert the output of different sensors into a unified unit and format to generate a standard environmental collection data stream (such as CSV or JSON format).Select a specific dynamic modeling method, such as a state-space model, ARIMA model, or deep learning model (such as LSTM) to capture changes in environmental states. Divide the standard environmental acquisition data stream into a training set and a test set, usually in an 80%:20% ratio. Use the training set data to train the model and optimize the model parameters to accurately predict the environmental state. Use the cross-validation method to evaluate the model performance to ensure that the model can accurately predict the new environmental state. Calculate the error between the model prediction and the actual data, and adjust the model parameters to improve the prediction accuracy. Input the real-time collected environmental data into the trained model to generate real-time environmental sensing state data. According to the modeling requirements, extract important features from the real-time data, such as temperature change trends, humidity fluctuations, etc. Store the generated environmental sensing state data in the database to ensure the integrity and traceability of the data.

[0083] Step S2: Calculate the wind speed and airflow pattern of the standard environment collection data stream to generate laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment database;

[0084] In an embodiment of the present invention, by selecting a suitable calculation model, such as a CFD (computational fluid dynamics) model, software (such as ANSYS Fluent or OpenFOAM) is used to perform airflow simulation. Simulation parameters are set, including the internal structure of the laboratory, the location of the gas source, the wind speed range, and the air flow direction. Airflow simulation is performed in the software to generate an airflow distribution diagram and analyze the flow pattern of the airflow in the laboratory. The wind speed data at each position is calculated through the simulation results to generate a wind speed and airflow pattern data set. The state of the laboratory cabinet door (open or closed) is inferred based on the airflow pattern and wind speed data, and the cabinet door state sensing data is generated. The cabinet door state sensing data is timestamped and labeled with a location to facilitate subsequent analysis and query. Specific filters (such as HEPA filters, activated carbon filters) are selected and configured according to the laboratory air quality requirements. The layout of the air multi-filtration system is designed, including the air inlet and outlet positions and the installation positions of the filters. The working parameters of the air filtration system, such as wind speed, flow rate, and filtration intensity, are set according to the cabinet door state sensing data. A dynamic adjustment mechanism is developed to adjust the working state of the filtration system in real time according to the air quality monitoring data and the cabinet door state. Using the airflow pattern data, an air distribution model is designed to ensure uniform distribution of air in the laboratory. Record the operating status of each filtration and air distribution, and generate circulating air distribution data, including flow, pressure, filter status, etc. Install toxic gas sensors (such as CO 2 NH 3, VOC, etc.), monitor the concentration of harmful gases in the air in real time. Integrate the monitoring data of toxic gas sensors with the circulating air distribution data to analyze the relationship between gas concentration and air circulation. According to the concentration of toxic gases, formulate corresponding decomposition control strategies and reduce the gas concentration through activated carbon, catalysts and other means. Integrate the gas decomposition system with the air filtration system to achieve intelligent control. Record the waste liquid data generated during each gas decomposition process, including the type of waste liquid, treatment method and treatment results.

[0085] Step S3: monitoring the waste liquid status according to the waste liquid treatment collection database to generate waste liquid status monitoring data; using the waste liquid status monitoring data to automatically control waste liquid collection to generate waste liquid collection control operation data; synchronizing and storing the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data;

[0086] In an embodiment of the present invention, the waste liquid composition, treatment method, treatment time and other information in the waste liquid treatment collection database are extracted. Real-time data of relevant sensors (such as liquid level sensor, pH sensor, temperature sensor) are collected to ensure comprehensive monitoring of the waste liquid state. Key parameters for waste liquid state monitoring are set, including liquid level, pH value, temperature and odor of the waste liquid. According to laboratory requirements and safety standards, thresholds for each monitoring parameter are set to determine alarm conditions. Sensor data is collected in real time using a data acquisition system (such as Arduino or Raspberry Pi). A state evaluation model is established to analyze the relationship between the collected data and the set thresholds to generate waste liquid state monitoring data. The generated waste liquid state monitoring data is stored in real time in the waste liquid treatment collection database to ensure data traceability. A visual monitoring interface is developed (using a Web application or a mobile application) to display the waste liquid state monitoring data for real-time monitoring by users. An automatic control system for waste liquid collection is designed, including control algorithms and logic, such as automatically starting or stopping waste liquid collection equipment according to liquid level height and waste liquid state. Appropriate actuators (such as pumps and valves) are selected for automatic collection and transfer of waste liquid. Based on the waste liquid status monitoring data, develop an automatic control algorithm to realize the intelligent control of waste liquid collection equipment. According to the real-time monitoring data, dynamically adjust the frequency and time of waste liquid collection to avoid excessive collection or missed collection. Record each start and stop of waste liquid collection and related data (such as collection time, liquid level changes, etc.) to generate waste liquid collection control operation data. Feedback the control effect (such as collection efficiency, waste liquid composition changes) to the system to optimize the subsequent control strategy. Select a suitable cloud service provider (such as AWS, Google Cloud, Microsoft Azure) to establish a cloud storage environment. Design a database architecture for waste liquid collection control operation data in the cloud to ensure data structuring and efficient query. Use secure data transmission protocols (such as HTTPS, MQTT) to synchronize operation data to the cloud in real time. Set up a scheduled backup mechanism to ensure the secure storage of data in the cloud and prevent data loss. Use data analysis tools (such as Pandas and NumPy in Python) to analyze cloud data and generate statistical reports on waste liquid collection.

[0087] Step S4: Based on the circulating air distribution data and the waste liquid collection cloud storage data, an internal and external circulation monitoring network is constructed to generate a medical laboratory cabinet ventilation circulation control monitoring network; the medical laboratory cabinet ventilation circulation control monitoring network is optimized for circulation efficiency feedback to generate medical laboratory cabinet ventilation control optimization data to perform intelligent ventilation control operations.

[0088] In an embodiment of the present invention, relevant parameters are extracted from the circulating air distribution data and the waste liquid collection cloud storage data to ensure that the data format is unified and interoperable. A real-time data stream connection is established, and a data transmission protocol (such as MQTT, WebSocket) is used to realize real-time data update. The topology of the monitoring network is designed, and a suitable network architecture (such as star, ring) is selected to achieve efficient data transmission and processing. Monitoring nodes are set inside and outside the medical laboratory cabinet, including temperature and humidity sensors, wind speed sensors, air quality monitors, etc., to monitor the environmental status inside and outside the cabinet in real time. A central control platform is developed (a web interface or mobile application can be used), which integrates the data of all monitoring nodes and provides a unified monitoring interface. Machine learning or deep learning algorithms are used to analyze air circulation data and waste liquid collection data to generate real-time monitoring feedback. The internal and external circulation data are processed and analyzed by the control platform to generate a medical laboratory cabinet ventilation circulation control monitoring network, including real-time status monitoring, alarm system and data visualization interface. Set circulation performance evaluation indicators, including air flow efficiency, waste liquid collection efficiency, temperature and humidity control effect in the cabinet, etc. According to historical data and laboratory standards, baseline data is established for subsequent performance evaluation. Develop a real-time feedback system to obtain circulation efficiency data through the monitoring network and evaluate the current system operation status. Set abnormal thresholds, monitor various indicators in real time, and send alarms to the control platform when the data is abnormal. Select a suitable optimization model (such as genetic algorithm, particle swarm optimization, etc.) to optimize the current circulation control strategy. According to the feedback data, dynamically adjust the ventilation control strategy, such as changing the wind speed, air filtration frequency and waste liquid collection plan to improve the overall circulation efficiency. Record the adjustment parameters, monitoring data and feedback results in the optimization process into the database to generate the ventilation control optimization data of the medical laboratory cabinet. Generate optimization reports regularly to show the performance changes before and after optimization, which is convenient for subsequent analysis and decision-making. Based on the optimization data, design an automatic ventilation control system to realize the intelligent adjustment of air flow in the cabinet. Implement a ventilation strategy based on the optimization algorithm, dynamically adjust the working status of fans, valves and filters, and ensure the stability of the laboratory environment. Continuously monitor the air quality, temperature and humidity and waste liquid status in the cabinet to ensure the real-time response of the control system. According to the real-time monitoring data, adjust the control strategy, optimize the ventilation efficiency, and improve the environmental quality of the laboratory.

[0089] Preferably, step S1 comprises the following steps:

[0090] Step S11: Acquire medical laboratory structure data;

[0091] Step S12: Select key positions based on the medical laboratory structure data to obtain key position data of the medical laboratory; construct a multi-point distributed sensor network based on the key position data of the medical laboratory to generate a distributed sensor network of the medical laboratory;

[0092] Step S13: collecting environmental multi-point data on the medical laboratory distributed sensor network to obtain an original environmental collection data stream; performing data preprocessing on the original environmental collection data stream to generate a standard environmental collection data stream, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0093] Step S14: Dynamic environment state modeling is performed through the standard environment acquisition data stream to generate environment sensing state data.

[0094] In an embodiment of the present invention, structural data including room layout, equipment location and ventilation system configuration are extracted from the architectural CAD drawings of the medical laboratory. On-site surveys are conducted to collect actual laboratory structural information to ensure the accuracy and completeness of the data. A database structure is created to store the structural data of the medical laboratory, including room name, area, purpose, etc. The collected structural data is entered into the database and initially verified to ensure data consistency. According to the functional requirements of the laboratory (such as biosafety, chemical treatment, etc.), key locations for monitoring, such as vents, laboratory benches, and waste liquid collection areas, are determined. The impact of each location on the overall laboratory environment is evaluated, and key locations that can effectively monitor the environmental status are selected. The coordinate data of each key location is recorded, including the specific location relative to the laboratory structure (using an absolute coordinate system). The key location data is stored in the database to provide a basis for the subsequent construction of the sensor network. Appropriate types of sensors (such as temperature, humidity, gas concentration, flow rate sensors, etc.) are selected according to the monitoring requirements. The topology of the sensor network is designed to ensure that the signal covers all key locations, and a suitable wireless communication protocol (such as Zigbee, LoRa, Wi-Fi) is selected to achieve data transmission. Sensors are installed at selected key locations to ensure that the sensors accurately monitor environmental parameters. Test the constructed sensor network to check the stability and accuracy of data transmission and ensure the normal operation of the sensor network. Configure the data acquisition system to collect environmental data in real time through sensors to form the original environmental acquisition data stream. Remove outliers and noise from the original data and use statistical methods (such as mean, median, etc.) for preliminary cleaning. Apply filters (such as Kalman filtering or median filtering) to remove random noise in sensor data. Use interpolation or mean filling to fill missing values ​​in the data to ensure data integrity. Standardize the data (such as Z-score standardization) to ensure that different sensor data are compared on the same scale. Format the preprocessed data into a standard data stream to ensure that the data is easy to store and analyze. Store the standard environmental acquisition data stream in the database for subsequent analysis and modeling. Select appropriate dynamic modeling methods (such as time series analysis, state space model, etc.) to model the standard environmental acquisition data stream. Set model parameters such as sampling frequency and time window according to environmental monitoring requirements. Input the standard environmental acquisition data stream into the model to perform dynamic analysis and modeling of the environmental state. Use the modeling results to estimate the current environmental state, including the changing trends of parameters such as temperature, humidity, and gas concentration. The modeling results are output as environmental sensing status data to form an environmental status monitoring system that can be updated in real time.

[0095] Preferably, step S14 comprises the following steps:

[0096] Step S141: performing feature sequence decomposition on the standard environment collection data stream to generate environment collection feature sequence data, wherein the feature sequence decomposition includes air temperature and humidity feature decomposition and particle concentration feature decomposition; performing window analysis on the environment collection feature sequence data to generate environment time series correlation data;

[0097] Step S142: using the environmental time series association data to perform laboratory space feature distribution analysis on the environmental collection feature sequence data to generate laboratory space feature parameter distribution data; performing convolution and nesting on the laboratory space feature parameter distribution data layer by layer to generate environmental space feature modeling data;

[0098] Step S143: Based on the preset RNN neural network, the environmental space feature modeling data is used to predict the environmental state and generate environmental sensing state data.

[0099] In an embodiment of the present invention, the temperature and humidity data in the standard environment acquisition data stream are decomposed and processed, and the temperature and humidity are used as independent feature sequences, and the main frequency components and trends are separated using Fourier transform or wavelet transform. The air particulate matter concentration data (such as PM2.5, PM10, etc.) is feature decomposed, and the different particle concentration data are layered and analyzed using wavelet decomposition to identify short-term fluctuations and long-term trends in the data. According to the dynamic change cycle of the laboratory environment, an appropriate time window (such as 1 minute, 5 minutes, etc.) is set, and the decomposed feature sequence is windowed. The feature statistics (such as mean, standard deviation, maximum value, minimum value, etc.) are calculated in each window to obtain environmental time series correlation data, which can reflect the change relationship of environmental parameters over time. The environmental acquisition feature sequence data and time series correlation data are stored in the database to provide support for subsequent analysis and modeling. According to the spatial structure information of the laboratory, the environmental time series correlation data is divided into spatial areas (such as ventilation areas, experimental operation areas, etc.), and the distribution of environmental parameters is calculated for different areas. In the segmented spatial area, the spatial distribution characteristics of parameters such as temperature, humidity, and particle concentration are extracted using statistical analysis methods to generate laboratory spatial characteristic parameter distribution data. An appropriate convolutional neural network is constructed to nest convolutions on the laboratory spatial characteristic parameter distribution data layer by layer to gradually extract spatial features. In each convolution layer, different convolution kernels are used to filter and abstract environmental features, and environmental spatial characteristic data is generated layer by layer to ensure the deep representation of spatial features. The spatial feature data after convolution is output as environmental spatial feature modeling data for subsequent environmental state prediction. A recurrent neural network (RNN) is constructed, which is suitable for the prediction of time series data. Long short-term memory (LSTM) or gated recurrent unit (GRU) layers are used to enhance the model's memory and processing capabilities for long-term and short-term environmental changes. The network parameters such as the number of layers, the number of nodes, and the learning rate are set, and the model structure is optimized according to the laboratory environmental state prediction requirements. The environmental spatial feature modeling data is input into the RNN model, and the time series processing capabilities of the RNN network are used to generate prediction results for future environmental states. As real-time data is updated, the RNN model is incrementally learned to correct the prediction accuracy of the model in real time. The prediction results are output as environmental sensing status data to record the changing trend and abnormal status of the laboratory environment status in the future. The environmental sensing status data is stored in the cloud database for real-time monitoring, early warning, intelligent ventilation control and other operations.

[0100] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0101] Step S21: Calculate the wind speed and airflow pattern of the standard environment collection data stream to obtain dynamic wind speed distribution data; perform laboratory cabinet door state sensing on the environment sensing state data through the dynamic wind speed distribution data to generate laboratory cabinet door state sensing data;

[0102] Step S22: performing air flow monitoring on the dynamic wind speed distribution data based on the laboratory cabinet door state sensing data to generate air flow monitoring data; performing air stratification on the air flow monitoring data to generate air stratification data; performing multiple filtering guidance control on the air flow monitoring data based on the air stratification guidance data to generate circulating air distribution data;

[0103] Step S23: Analyze the toxic gas composition of the circulating air distribution data to generate toxic gas composition data; calculate the gas proportion of the circulating air distribution data using the toxic gas composition data to obtain toxic gas proportion data;

[0104] Step S24: Compare the toxic gas proportion data with the preset standard toxic gas proportion threshold. When the toxic gas proportion data is greater than the preset standard toxic gas proportion threshold, the circulating air distribution data is controlled to decompose and compress the toxic gas according to the toxic gas proportion data to generate a waste liquid treatment database.

[0105] In an embodiment of the present invention, wind speed sensor data in a data stream is acquired by acquiring a standard environment. A fluid dynamics model is used to perform spatial grid division on the wind speed in the laboratory, and the wind speed value of each grid node is calculated to obtain dynamic wind speed distribution data. In this process, eddy simulation and turbulence model can be combined to accurately describe the wind speed change. The dynamic wind speed distribution data is input into the sensing model to identify the wind speed change caused by the door opening and closing state, and generate a door state change pattern. The door state sensing result is converted into laboratory door state sensing data for subsequent air flow monitoring and control. Based on the laboratory door state sensing data and combined with the dynamic wind speed distribution data, an air flow monitoring model is constructed. The model is used to track the air flow in real time and generate air flow monitoring data. The air flow monitoring data is input into the air stratification algorithm to stratify the air, distinguish different air quality levels such as the heavily polluted layer and the recyclable air layer, and generate air stratification data. The air stratification data is used to guide the multiple filtering control of the air flow monitoring data, ensuring that different filtering strategies are used in different air layers, thereby reducing the accumulation of pollutants and generating circulating air distribution data. Use gas analysis sensors to decompose the components in the circulating air distribution data, extract the concentration of toxic components (such as benzene, formaldehyde, etc.), and generate toxic gas component data. The toxic gas component data obtained by analysis is stored in the toxic gas component database to facilitate historical data analysis and standard threshold comparison. Based on the toxic gas component data, calculate the proportion of each toxic component in the air. The proportion value of each component is obtained through the atmospheric pollution comparison algorithm to form the toxic gas proportion data. Compare and analyze the toxic gas proportion data with the preset toxic gas proportion threshold in the laboratory safety standard. If the toxic gas proportion data exceeds the preset threshold, the toxic gas decomposition and compression control is triggered to ensure that the air quality meets the safety standards. Under the toxic gas decomposition and compression control strategy, the decomposition module and the compression module are started. The decomposition module decomposes the toxic components by chemical reaction or ultraviolet irradiation, and the compression module concentrates the residual toxic substances by air pressure control. The waste gas and waste liquid data generated by decomposition and compression are sorted and recorded to generate a waste liquid treatment database, and the treatment results are stored for further management and analysis.

[0106] Preferably, step S21 includes the following steps:

[0107] Step S211: extracting air quality and humidity and temperature information from the standard environment collection data stream to obtain regional air quality data and regional humidity and temperature information data; performing preliminary velocity field modeling based on the regional air quality data and regional humidity and temperature information data to generate preliminary velocity field data;

[0108] Step S212: Perform three-dimensional path planning on the preliminary velocity field data to generate laboratory optimal air flow path data;

[0109] Step S213: performing discrete element method simulation on the laboratory optimal air flow path data to generate regional air resistance change data; performing dynamic flow pressure calculation on the regional air resistance change data to obtain regional dynamic pressure distribution data;

[0110] The formula for calculating dynamic flow pressure is as follows:

[0111]

[0112] In the formula, represents the flow pressure, Expressed as the fluid resistance coefficient, Expressed as air density, Expressed as wind speed;

[0113] Step S214: Detect the door flow field change of the medical laboratory cabinet through the regional dynamic pressure distribution data to generate the door state flow field change data; perform three-dimensional fluid simulation on the door state flow field change data to generate dynamic wind speed distribution data; perform abnormal wind speed change analysis on the dynamic wind speed distribution data to generate abnormal wind speed change data;

[0114] Step S215: Confirm the change of laboratory door status by comparing the environmental sensing status data with the abnormal wind speed change data, and perform airflow direction offset analysis on the door status flow field change data to generate an airflow direction offset matrix; perform state sensing on the laboratory door according to the airflow direction offset matrix and the regional dynamic pressure distribution data to generate laboratory door status sensing data.

[0115] In the embodiment of the present invention, air quality data (including PM2.5, PM10, CO 2 concentration, etc.) and humidity and temperature information. The extracted data is divided into spatial grids to generate air quality data and humidity and temperature information data for each area, which is convenient for monitoring air changes in space. Based on the regional air quality and humidity and temperature information data, a preliminary velocity field model is established to estimate the air flow direction and speed. The velocity field data is output through the preliminary velocity field model as the basis for subsequent air flow optimization. Using a three-dimensional path planning algorithm (such as the Dijkstra algorithm), the preliminary velocity field data is used to plan the shortest path and the optimal air flow path to ensure uniform and efficient air circulation in the laboratory. Record the wind speed and air quality data of each path to generate the laboratory's optimal air flow path data for guiding air circulation. Based on the laboratory's optimal air flow path data, the discrete element method is used to simulate the change in air resistance and analyze the impact of air flow obstruction on the path. Calculate the resistance at each point on the path to generate regional air resistance change data. Using the formula Calculate the flow pressure, and obtain the regional dynamic pressure distribution data according to the wind speed and resistance at each point on the path, which is used to identify the pressure change of air flow. Based on the regional dynamic pressure distribution data, establish a cabinet door flow field change detection model to detect the flow field change caused by the cabinet door opening and closing. Output the flow field change data of the cabinet door state for subsequent flow simulation and wind speed analysis. Perform three-dimensional fluid simulation on the cabinet door state flow field change data to generate dynamic wind speed distribution data in the cabinet. Monitor the dynamic wind speed distribution data, detect abnormal wind speed fluctuations, and generate abnormal wind speed change data for further confirmation of the cabinet door state. Confirm the change of the cabinet door state through the abnormal wind speed change data, and mark the change of air flow state caused by the cabinet door opening and closing. Use the airflow direction offset analysis technology to calculate the direction offset of the airflow for the cabinet door state flow field change data and generate the airflow direction offset matrix. Combine the airflow direction offset matrix and the regional dynamic pressure distribution data to finally confirm the state of the laboratory cabinet door, and output the laboratory cabinet door state sensing data for subsequent air flow monitoring and ventilation control.

[0116] Preferably, step S22 includes the following steps:

[0117] Step S221: performing air flow monitoring on the dynamic wind speed distribution data based on the laboratory cabinet door state sensing data to generate air flow monitoring data;

[0118] Step S222: performing air particle size identification on the air flow monitoring data to obtain air flow particle size data; performing gaseous pollutant component identification on the air flow monitoring data to generate gaseous pollutant component identification data; performing air stratification on the air flow monitoring data according to the air flow particle size data and the gaseous pollutant component identification data to generate air stratification data, wherein the air stratification data includes primary air stratification data, secondary air stratification data and tertiary air stratification data;

[0119] Step S223: Based on the primary air stratification data, the medical laboratory cabinet is subjected to nanofiber air filtration control to generate primary filtration control data; based on the secondary air stratification data, the medical laboratory cabinet is subjected to porous activated carbon air filtration control to generate medium filtration control data; based on the tertiary air stratification data, the medical laboratory cabinet is subjected to nano-scale membrane air filtration control to generate high efficiency filtration control data;

[0120] Step S224: Integrate the primary filtration control data, the medium filtration control data and the high efficiency filtration control data to generate air stratification data; perform multiple filtration efficiency calculations on the air stratification data to obtain multiple filtration degradation efficiency data; wherein the formula for multiple degradation efficiency calculation is as follows:

[0121]

[0122] In the formula, Expressed as the overall filtration degradation efficiency, Represented as the weight coefficient of the first layer of filtering, Represented as the weight coefficient of the second layer of filtering, Expressed as the weight coefficient of the third layer of filtering, Represented as primary filtration control data, Expressed as medium efficiency filtration control data, Represents efficient filtering control data;

[0123] Step S225: Perform multiple filtering guidance control on the air flow monitoring data through multiple filtering degradation efficiency data to generate circulating air distribution data.

[0124] In the embodiment of the present invention, the state sensing data of the laboratory cabinet door and the dynamic wind speed distribution data are used as input. The air flow monitoring algorithm is used to analyze the flow direction, speed and flow rate of the air to obtain the air flow monitoring data to identify the key areas and circulation paths in the air circulation. The air flow monitoring data is subjected to air particle size identification to generate air flow particle size data. The air flow monitoring data is subjected to gaseous pollutant component identification to generate gaseous pollutant component identification data. Based on the air flow particle size data and the gaseous pollutant component identification data, the air flow monitoring data is subjected to air stratification to generate air stratification data, which is divided into a three-level structure, including primary air stratification data (larger particles and higher concentrations of pollutants), secondary air stratification data (medium particles and medium concentrations of pollutants) and tertiary air stratification data (small particles and low concentrations of pollutants) for subsequent graded filtration. Based on the primary air stratification data, a nanofiber filter is used for filtration control to remove larger particles and pollutants and generate primary filtration control data. Based on the secondary air stratification data, porous activated carbon is used for medium efficiency filtration to adsorb harmful gases and medium particles and generate medium efficiency filtration control data. Based on the three-level air stratification data, nano-scale filter membranes are used for high-efficiency filtration to remove small particles and residual gaseous pollutants, and generate high-efficiency filtration control data. The primary filtration control data, medium-efficiency filtration control data, and high-efficiency filtration control data are integrated to generate unified air stratification data to characterize the overall effect of air filtration treatment. Use the formula Calculate the overall filtration degradation efficiency and output multiple filtration degradation efficiency data to evaluate and guide the further circulation and distribution of air. Use multiple filtration degradation efficiency data to guide and control the air flow monitoring data, generate circulating air distribution data, and achieve efficient and uniform air circulation in the laboratory by guiding the air circulation path and redistributing the air flow.

[0125] Preferably, step S225 includes the following steps:

[0126] Using the air flow monitoring data to screen the air quality inside the medical laboratory cabinet, and obtaining the air quality data inside the cabinet; performing air quality assessment on the air quality data inside the cabinet, and generating the air quality assessment data inside the cabinet;

[0127] Perform zoning demand analysis on air flow monitoring data based on cabinet air quality assessment data to generate regional air quality demand data; perform air redistribution demand priority setting on regional air quality demand data to generate internal circulation priority data;

[0128] Based on the internal circulation priority data, dynamic airflow distribution is performed on the regional air quality demand data to generate dynamic airflow distribution data; regional wind speed is adjusted through the dynamic airflow distribution data to generate regional wind speed adjustment data; the air flow path of the laboratory optimal air flow path data is optimized according to the regional wind speed adjustment data to generate circulating air distribution data.

[0129] In an embodiment of the present invention, the air quality in the medical laboratory cabinet is screened by using air flow monitoring data. Through the screening process, the air quality data in the cabinet is generated, including information such as air particle concentration, pollutant composition, and wet temperature. The air quality data in the cabinet is evaluated, and the pollutant concentration, particle size distribution, temperature and humidity in the air are considered to generate the air quality evaluation data in the cabinet, indicating whether the air quality meets the standard requirements in the laboratory, and indicating the areas and indicators that need to be improved. According to the air quality evaluation data in the cabinet, the air flow monitoring data is analyzed for partition demand, and regional air quality demand data is generated to identify the demand priority and flow demand for clean air in different regions for subsequent dynamic air distribution. According to the regional air quality demand data, the demand priority of air redistribution is set, and the internal circulation priority data is generated to indicate which areas are given priority in air redistribution to ensure the air quality of key areas. Based on the internal circulation priority data, the regional air quality demand data is dynamically distributed, and dynamic air flow distribution data is generated to guide the redistribution of airflow in different areas so as to optimize air quality more efficiently. The wind speed of each area is finely adjusted through dynamic airflow distribution data to generate regional wind speed adjustment data, which is used to control and adjust the air flow rate in the area to ensure that the air can flow to the target area. According to the regional wind speed adjustment data, the air flow path is optimized for the laboratory's optimal air flow path data to generate the final circulating air distribution data, so as to achieve efficient circulation of air in the laboratory, ensure that the air quality continues to meet the experimental requirements, and optimize the air flow path to minimize the risk of contamination diffusion.

[0130] Preferably, step S24 includes the following steps:

[0131] Step S241: comparing the toxic gas proportion data with a preset standard toxic gas proportion threshold value. When the toxic gas proportion data is greater than the preset standard toxic gas proportion threshold value, the circulating air distribution data is subjected to toxic gas identification using a gas sensor according to the toxic gas proportion data to generate toxic gas identification data.

[0132] Step S242: designing a gas decomposition scheme for the toxic gas identification data to generate a gas decomposition treatment scheme; setting and debugging a decomposition device based on the gas decomposition treatment scheme to generate decomposition device performance evaluation data;

[0133] Step S243: Record the implementation of toxic gas decomposition of the gas decomposition treatment plan through the decomposition device performance evaluation data to generate a decomposition gas conversion record; perform waste liquid compression and centralized data collection on the toxic gas identification data based on the decomposition gas conversion record to generate a waste liquid treatment database.

[0134] In an embodiment of the present invention, the toxic gas proportion data is compared with a preset standard toxic gas proportion threshold. When the toxic gas proportion data is higher than the preset threshold, the toxic gas identification process is entered. According to the toxic gas proportion data, the toxic gas in the circulating air distribution data is identified by a gas sensor, and toxic gas identification data is generated, indicating the type, concentration and other information of the toxic gas, which is convenient for the design of subsequent treatment schemes. Based on the toxic gas identification data, a gas decomposition treatment scheme is designed. The scheme includes a gas decomposition method, a target concentration, reaction conditions, etc., and a gas decomposition treatment scheme is generated to ensure that toxic gases of different types and concentrations can be safely and effectively decomposed and treated. According to the gas decomposition treatment scheme, a decomposition device is set and debugged to ensure that the device operating parameters match the decomposition scheme. The performance of the debugged decomposition device is evaluated to ensure that it can process toxic gases according to the scheme requirements, and the performance evaluation data of the decomposition device is generated to provide reliability guarantee for subsequent decomposition operations. According to the performance evaluation data of the decomposition device, a gas decomposition operation is implemented and the process is recorded, including the decomposition time, efficiency, generated gas or liquid products, etc., and a decomposition gas conversion record is generated to record the data in the decomposition process of the toxic gas in detail. According to the decomposition gas conversion records, the toxic gas identification data is compressed and centrally collected to ensure that all toxic products are safely handled. A waste liquid treatment database is generated, including the centralized collection data, storage method and subsequent treatment method of the decomposition waste liquid.

[0135] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0136] Step S31: Designing a waste liquid collection system according to a waste liquid treatment and collection database to generate a waste liquid collection system design document; configuring intelligent sensors for the medical laboratory cabinet based on the waste liquid collection system design document to generate sensor configuration data, wherein the intelligent sensor configuration includes a liquid level sensor and a pressure sensor;

[0137] Step S32: monitoring the waste liquid status of the sensor configuration data to generate waste liquid status monitoring data; automatically regulating the waste liquid collection system using the waste liquid status monitoring data to generate waste liquid collection regulation operation data;

[0138] Step S33: Synchronize and store the waste liquid collection and control operation data in the cloud to generate waste liquid collection cloud storage data.

[0139] In the embodiment of the present invention, by accessing the waste liquid treatment and collection database, the storage requirements and treatment methods of different types of waste liquids are analyzed, including the physical properties of the waste liquid (such as chemical composition, corrosiveness, liquid level changes, etc.), and according to the waste liquid treatment requirements, the pipeline layout, storage container, liquid flow control valve and safety protection measures of the waste liquid collection system are designed to generate the "Waste Liquid Collection System Design Document". Based on the design document, the waste liquid collection cabinet of the medical laboratory is configured with an intelligent sensor, including: for monitoring the liquid level of the waste liquid container to prevent liquid overflow; monitoring the internal pressure of the waste liquid container to detect abnormal conditions (such as blockage or leakage). The model, installation location, sampling frequency and data transmission method of each sensor are recorded to generate sensor configuration data for subsequent monitoring and control. Start the sensor configuration, monitor the liquid level and pressure changes in the waste liquid collection system in real time, and flow the monitored data into the system monitoring center to generate waste liquid status monitoring data. Based on the waste liquid status monitoring data, the system is automatically regulated, mainly including: liquid level control: when the liquid level reaches the preset threshold, the waste liquid discharge or transfer process is automatically started. Pressure regulation: When the pressure fluctuates abnormally, the alarm mechanism is activated and the on / off valve of the waste liquid pipeline is adjusted to release the pressure. The execution status and adjustment results of the automatic control are recorded to generate waste liquid collection and control operation data to provide data support for the safe and stable operation of the system. The waste liquid collection and control operation data is transmitted to the cloud storage through the Internet of Things (IoT) system to ensure real-time synchronization of data between different devices. Classification labels are set for the data (such as liquid level status, pressure status, control response time, etc.) to facilitate quick retrieval and analysis. The data stored in the cloud can be used as a reference for subsequent system maintenance and optimization, and waste liquid collection cloud storage data is generated to ensure long-term data preservation and access at any time.

[0140] In this specification, an intelligent ventilation control system for a medical laboratory is provided, which is used to execute the above-mentioned intelligent ventilation control method for a medical laboratory. The intelligent ventilation control system for a medical laboratory includes:

[0141] The external environment acquisition module is used to obtain the medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental acquisition data stream; perform dynamic environmental state modeling through the standard environmental acquisition data stream to generate environmental sensing state data;

[0142] The air purification module is used to calculate the wind speed and airflow pattern of the standard environment acquisition data stream to generate the laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate the circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment database;

[0143] The waste liquid monitoring module is used to monitor the waste liquid status according to the waste liquid treatment and collection database to generate waste liquid status monitoring data; use the waste liquid status monitoring data to automatically control the waste liquid collection to generate waste liquid collection control operation data; synchronize the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data;

[0144] The internal and external circulation feedback module is used to build an internal and external circulation monitoring network based on the circulating air distribution data and the waste liquid collection cloud storage data, and generate a medical laboratory cabinet ventilation circulation control monitoring network; the medical laboratory cabinet ventilation circulation control monitoring network is optimized by circulation efficiency feedback, and the medical laboratory cabinet ventilation control optimization data is generated to perform intelligent ventilation control operations.

[0145] The beneficial effect of the present invention is that by acquiring the structural data of the medical laboratory, a comprehensive understanding of the internal layout and environmental conditions of the laboratory is ensured, laying the foundation for subsequent analysis. Full coverage monitoring is achieved through a distributed sensor network to improve the accuracy and reliability of data. Real-time acquisition of environmental information ensures comprehensive monitoring of air quality and status, provides data support for dynamic adjustment, generates environmental sensing status data, can timely reflect changes in the laboratory, and improve the intelligent level of environmental monitoring. Wind speed and airflow pattern calculation generates laboratory cabinet door status sensing data, which helps to understand the distribution of airflow in the laboratory and improve the effectiveness of air flow. Adjust the air flow according to the cabinet door status to achieve more efficient air filtration and reduce the concentration of harmful substances. Toxic gas decomposition and compression control generates a waste liquid treatment database, improves the monitoring and treatment capabilities of toxic gases, and ensures the safety of the laboratory environment. By monitoring the waste liquid status, potential problems are discovered and solved in a timely manner, and the safety and efficiency of waste liquid treatment are improved. Automatic regulation of waste liquid collection realizes automatic regulation of waste liquid collection, reduces manual intervention, and improves work efficiency and safety. The waste liquid collection and regulation operation data is stored in the cloud to ensure the security and traceability of the data, which is convenient for subsequent analysis and auditing. By integrating the circulating air distribution and waste liquid collection data, a comprehensive monitoring network is formed to enhance the control of the overall laboratory environment. Feedback optimization is performed on the monitoring network to improve the operating efficiency of the ventilation system and waste liquid treatment, and to achieve the rational use of resources. Ultimately, intelligent ventilation control is achieved to ensure the air quality and safety of medical laboratories and provide good environmental support for scientific research and experiments. Therefore, the present invention improves the safety and efficiency of intelligent ventilation control in medical laboratories through real-time data acquisition, dynamic modeling, comprehensive air quality and waste liquid treatment control, and system integration optimization.

[0146] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0147] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent ventilation control method for a medical laboratory, characterized in that: Acting on a medical laboratory cabinet, includes the following steps: Step S1: Acquire medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental collection data stream; perform dynamic environmental state modeling through the standard environmental collection data stream to generate environmental sensing state data; Step S2: Calculate the wind speed and airflow pattern of the standard environment collection data stream to generate laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment collection database; Step S3: monitoring the waste liquid status according to the waste liquid treatment collection database to generate waste liquid status monitoring data; using the waste liquid status monitoring data to automatically control waste liquid collection to generate waste liquid collection control operation data; synchronizing and storing the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data; Step S4: constructing an internal and external circulation monitoring network based on the circulating air distribution data and the waste liquid collection cloud storage data to generate a medical laboratory cabinet ventilation circulation control monitoring network; optimizing the circulation efficiency feedback of the medical laboratory cabinet ventilation circulation control monitoring network to generate medical laboratory cabinet ventilation control optimization data to perform intelligent ventilation control operations; wherein, step S2 includes the following steps: Step S21: Calculate the wind speed and airflow pattern of the standard environment collection data stream to obtain dynamic wind speed distribution data; perform laboratory cabinet door state sensing on the environment sensing state data through the dynamic wind speed distribution data to generate laboratory cabinet door state sensing data; Step S22: performing air flow monitoring on the dynamic wind speed distribution data based on the laboratory cabinet door state sensing data to generate air flow monitoring data; performing air stratification on the air flow monitoring data to generate air stratification data; performing multiple filtering guidance control on the air flow monitoring data based on the air stratification data to generate circulating air distribution data; Step S23: Analyze the toxic gas composition of the circulating air distribution data to generate toxic gas composition data; calculate the gas proportion of the circulating air distribution data using the toxic gas composition data to obtain toxic gas proportion data; Step S24: Compare the toxic gas proportion data with the preset standard toxic gas proportion threshold. When the toxic gas proportion data is greater than the preset standard toxic gas proportion threshold, the circulating air distribution data is subjected to toxic gas decomposition and compression control according to the toxic gas proportion data to generate a waste liquid treatment collection database; wherein step S21 includes the following steps: Step S211: extracting air quality and humidity and temperature information from the standard environment collection data stream to obtain regional air quality data and regional humidity and temperature information data; performing preliminary velocity field modeling based on the regional air quality data and regional humidity and temperature information data to generate preliminary velocity field data; Step S212: Perform three-dimensional path planning on the preliminary velocity field data to generate laboratory optimal air flow path data; Step S213: performing discrete element method simulation on the laboratory optimal air flow path data to generate regional air resistance change data; performing dynamic flow pressure calculation on the regional air resistance change data to obtain regional dynamic pressure distribution data; The formula for calculating dynamic flow pressure is as follows: In the formula, represents the dynamic flow pressure, Expressed as the fluid resistance coefficient, Expressed as air density, Expressed as wind speed; Step S214: Detect the door flow field change of the medical laboratory cabinet through the regional dynamic pressure distribution data to generate the door state flow field change data; perform three-dimensional fluid simulation on the door state flow field change data to generate dynamic wind speed distribution data; perform abnormal wind speed change analysis on the dynamic wind speed distribution data to generate abnormal wind speed change data; Step S215: Confirm the change of laboratory door status by comparing the environmental sensing status data with the abnormal wind speed change data, and perform airflow direction offset analysis on the door status flow field change data to generate an airflow direction offset matrix; perform state sensing on the laboratory door according to the airflow direction offset matrix and the regional dynamic pressure distribution data to generate laboratory door status sensing data.

2. The intelligent ventilation control method for medical laboratories according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire medical laboratory structure data; Step S12: Select key positions based on the medical laboratory structure data to obtain key position data of the medical laboratory; construct a multi-point distributed sensor network based on the key position data of the medical laboratory to generate a distributed sensor network of the medical laboratory; Step S13: collecting environmental multi-point data on the medical laboratory distributed sensor network to obtain an original environmental collection data stream; performing data preprocessing on the original environmental collection data stream to generate a standard environmental collection data stream, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S14: Dynamic environment state modeling is performed through the standard environment acquisition data stream to generate environment sensing state data.

3. The intelligent ventilation control method for medical laboratories according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: performing feature sequence decomposition on the standard environment collection data stream to generate environment collection feature sequence data, wherein the feature sequence decomposition includes air temperature and humidity feature decomposition and particle concentration feature decomposition; performing window analysis on the environment collection feature sequence data to generate environment time series correlation data; Step S142: using the environmental time series association data to perform laboratory space feature distribution analysis on the environmental collection feature sequence data to generate laboratory space feature parameter distribution data; performing convolution and nesting on the laboratory space feature parameter distribution data layer by layer to generate environmental space feature modeling data; Step S143: Based on the preset RNN neural network, the environmental space feature modeling data is used to predict the environmental state and generate environmental sensing state data.

4. The intelligent ventilation control method for medical laboratories according to claim 1, characterized in that: Step S22 includes the following steps: Step S221: performing air flow monitoring on the dynamic wind speed distribution data based on the laboratory cabinet door state sensing data to generate air flow monitoring data; Step S222: performing air particle size identification on the air flow monitoring data to obtain air flow particle size data; performing gaseous pollutant component identification on the air flow monitoring data to generate gaseous pollutant component identification data; performing air stratification on the air flow monitoring data according to the air flow particle size data and the gaseous pollutant component identification data to generate air stratification data, wherein the air stratification data includes primary air stratification data, secondary air stratification data and tertiary air stratification data; Step S223: Based on the primary air stratification data, the medical laboratory cabinet is subjected to nanofiber air filtration control to generate primary filtration control data; based on the secondary air stratification data, the medical laboratory cabinet is subjected to porous activated carbon air filtration control to generate medium filtration control data; based on the tertiary air stratification data, the medical laboratory cabinet is subjected to nano-scale membrane air filtration control to generate high efficiency filtration control data; Step S224: Integrate the primary filtration control data, the medium filtration control data and the high efficiency filtration control data to generate air stratification data; perform multiple degradation efficiency calculations on the air stratification data to obtain multiple filtration degradation efficiency data; wherein the formula for multiple degradation efficiency calculation is as follows: In the formula, Expressed as the multiple degradation efficiency, Represented as the weight coefficient of the first layer of filtering, Represented as the weight coefficient of the second layer of filtering, Expressed as the weight coefficient of the third layer of filtering, Represented as primary filtration control data, Expressed as medium efficiency filtration control data, Represents efficient filtering control data; Step S225: Perform multiple filtering guidance control on the air flow monitoring data through multiple filtering degradation efficiency data to generate circulating air distribution data.

5. The intelligent ventilation control method for medical laboratories according to claim 1, characterized in that: Step S24 includes the following steps: Step S241: comparing the toxic gas proportion data with a preset standard toxic gas proportion threshold value. When the toxic gas proportion data is greater than the preset standard toxic gas proportion threshold value, the circulating air distribution data is subjected to toxic gas identification using a gas sensor according to the toxic gas proportion data to generate toxic gas identification data. Step S242: designing a gas decomposition scheme for the toxic gas identification data to generate a gas decomposition treatment scheme; setting and debugging a decomposition device based on the gas decomposition treatment scheme to generate decomposition device performance evaluation data; Step S243: Record the implementation of toxic gas decomposition of the gas decomposition treatment plan through the decomposition device performance evaluation data to generate a decomposition gas conversion record; perform waste liquid compression and centralized data collection on the toxic gas identification data based on the decomposition gas conversion record to generate a waste liquid treatment collection database.

6. The intelligent ventilation control method for medical laboratories according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Designing a waste liquid collection system according to a waste liquid treatment and collection database to generate a waste liquid collection system design document; configuring intelligent sensors for the medical laboratory cabinet based on the waste liquid collection system design document to generate sensor configuration data, wherein the intelligent sensor configuration includes a liquid level sensor and a pressure sensor; Step S32: monitoring the waste liquid status of the sensor configuration data to generate waste liquid status monitoring data; automatically regulating the waste liquid collection system using the waste liquid status monitoring data to generate waste liquid collection regulation operation data; Step S33: Synchronize and store the waste liquid collection and control operation data in the cloud to generate waste liquid collection cloud storage data.

7. An intelligent ventilation control system for a medical laboratory, characterized in that: For executing the intelligent ventilation control method for a medical laboratory as claimed in claim 1, the intelligent ventilation control system for a medical laboratory comprises: The external environment acquisition module is used to obtain the medical laboratory structure data; construct a multi-point distributed sensor network for the medical laboratory structure data to generate a medical laboratory distributed sensor network; collect environmental multi-point data for the medical laboratory distributed sensor network to obtain a standard environmental acquisition data stream; perform dynamic environmental state modeling through the standard environmental acquisition data stream to generate environmental sensing state data; The air purification module is used to calculate the wind speed and airflow pattern of the standard environment acquisition data stream to generate laboratory cabinet door status sensing data; perform air multiple filtration and degradation control based on the laboratory cabinet door status sensing data to generate circulating air distribution data; perform toxic gas decomposition and compression control on the circulating air distribution data to generate a waste liquid treatment collection database; The waste liquid monitoring module is used to monitor the waste liquid status according to the waste liquid treatment and collection database to generate waste liquid status monitoring data; use the waste liquid status monitoring data to automatically control the waste liquid collection to generate waste liquid collection control operation data; synchronize the waste liquid collection control operation data in the cloud to generate waste liquid collection cloud storage data; The internal and external circulation feedback module is used to build an internal and external circulation monitoring network based on the circulating air distribution data and the waste liquid collection cloud storage data, and generate a medical laboratory cabinet ventilation circulation control monitoring network; the medical laboratory cabinet ventilation circulation control monitoring network is optimized by circulation efficiency feedback, and the medical laboratory cabinet ventilation control optimization data is generated to perform intelligent ventilation control operations.

Images