Operating room air purification system capable of adjusting air volume in self-adaptive mode and energy saving method of operating room air purification system

Abstract

The invention relates to the technical field of medical environment air purification, in particular to an operating room air purification system capable of adjusting the air volume in a self-adaptive mode and an energy saving method of the operating room air purification system. The method comprises the following steps: constructing an operating room air quality historical database, extracting and weighting air quality time sequence characteristics, constructing a membership function model based on weight, matching the air quality characteristics, forming an optimal matching set, defining and solving a dynamic time warping path model, and generating a new air quality curve sequence. And finally, fusing the sequence and the optimal matching set feature to obtain a final air quality mode. Through self-adaptive air volume adjustment, continuous and accurate adjustment of the air volume is achieved, energy consumption is optimized, and the overall efficiency and economical efficiency of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of air purification and energy saving, and specifically relates to an operating room air purification system for adaptively adjusting air volume and an energy saving method thereof. Background Art

[0002] In modern healthcare, operating room air quality plays a crucial role in the success rate of surgery and patient recovery. Operating room air purification systems must efficiently remove bacteria, viruses, and particulate matter from the air while maintaining stable air pressure to ensure a safe and comfortable surgical environment. However, existing operating room air purification systems still have shortcomings in air volume regulation, energy consumption control, and long-term stability, impacting the overall system's effectiveness and cost-effectiveness.

[0003] After searching, an operating room air purification system with a publication number of CN103267321B was disclosed, and the publication date was August 10, 2016. This patent accelerates the fresh air by using an array of air supply motors, and sends the fresh air into the operating room through a purification component. Each motor is controlled by a main control unit, and only some of the motors can be kept turned on according to the usage, thereby saving electricity. However, in this technical solution, the air volume adjustment mainly depends on the number of motors opened and closed, and continuous and accurate air volume adjustment cannot be achieved, resulting in large fluctuations in the air pressure in the operating room, making it difficult to maintain a stable sterile environment. In addition, the solution has limited adaptability to different working conditions and cannot be dynamically adjusted according to real-time changes in air quality.

[0004] After searching, an air purification circulation device for operating rooms with the publication number CN110017552B was disclosed, and the publication date was October 13, 2020. This patent uses a ring-shaped filter ring to continuously rotate and displace the filter ring, thereby achieving a self-cleaning effect and improving the filtering effect. However, in this technical solution, the rotation speed and position of the filter ring cannot be adjusted in real time according to the indoor air quality, which may lead to unstable purification effect. In addition, the device has a weak ability to adjust the air volume and cannot be dynamically adjusted according to the actual needs in the operating room, which affects the overall energy saving effect and air purification efficiency of the system.

[0005] The above problems indicate that existing operating room air purification systems still have certain deficiencies in terms of air volume adjustment accuracy and dynamic adaptability, energy consumption control, and self-cleaning effectiveness. Therefore, the present invention provides an operating room air purification system with adaptive air volume adjustment and an energy-saving method thereof, which aims to achieve continuous and precise air volume adjustment, optimize energy consumption, improve air purification effectiveness, ensure that the air quality in the operating room is always in an optimal state, and meet the needs of modern medical environments for efficient and intelligent operating room air purification systems. Summary of the Invention

[0006] The purpose of the present invention is to overcome the above-mentioned defects and problems existing in the prior art, and to provide an operating room air purification system with adaptive air volume adjustment and an energy-saving method thereof, aiming to achieve continuous and precise adjustment of air volume, optimize energy consumption, improve air purification effect, ensure that the air quality in the operating room is always in the optimal state, and meet the needs of modern medical environments for efficient and intelligent operating room air purification systems.

[0007] To achieve the above objectives, the technical solution of the present invention is: an operating room air purification system with adaptive air volume adjustment and an energy-saving method thereof, comprising the following steps:

[0008] S1. Build an operating room air quality history database, extract air quality time series features, and assign a weight to each air quality time series feature based on the discreteness of the feature;

[0009] S2. Based on the weights of the air quality time series characteristics, an air quality membership function model is constructed, and the air quality characteristics of the operating room to be identified are matched with the air quality time series characteristics in the air quality membership function model to obtain the best matching set of air quality time series characteristics;

[0010] S3. Based on the best matching set of air quality time series features, define a distance matrix of air quality features, and based on the distance matrix, define a first dynamic time warping path and conditions to obtain a dynamic time warping path model;

[0011] S4. Solve the dynamic time warping path model to obtain a second dynamic time warping path, and expand the air quality curve according to the second dynamic time warping path to obtain a new air quality curve sequence, and calculate the comprehensive air quality curve sequence; based on the comprehensive air quality curve sequence, all air quality curves are integrated with all air quality time series features in the best matching set of air quality time series features to obtain the final air quality pattern.

[0012] The step S1 specifically includes:

[0013] S11. Obtain historical air quality data of the operating room and build an operating room air quality historical database;

[0014] S12. Filtering and normalizing required air quality time series characteristics from the operating room air quality history database to obtain air quality time series characteristics;

[0015] S13. Assign a weight to each air quality time series feature based on the discreteness of all historical air quality data in the operating room air quality history database; the weight is expressed as follows:

[0016]

[0017] Where: Wi represents the weight of the i-th air quality time series feature, and σi2 represents the sample variance of the i-th air quality time series feature in the operating room air quality history database.

[0018] The step S2 specifically includes:

[0019] S21. Based on the weight of the air quality time series characteristics, the air quality membership function model is constructed using weighted Euclidean distance;

[0020] S22. Input the air quality characteristics of the operating room to be identified into the air quality membership function model and match them with the air quality time series characteristics to obtain the best matching set of air quality time series characteristics.

[0021] The step S22 specifically includes:

[0022] S221. Inputting the operating room air quality history database and the air quality time series characteristic value of the operating room to be identified;

[0023] S222, extracting the time series characteristic values of the air quality of all historical operating rooms in the operating room air quality history database and normalizing them;

[0024] S223. Calculating the air quality membership of the operating room to be identified and the historical operating rooms based on the air quality membership function model;

[0025] The expression of the air quality membership function model is as follows:

[0026]

[0027] Where: xik represents the kth air quality time series characteristic value of the operating room to be identified, xjk represents the normalized kth air quality time series characteristic value of the historical operating room, Wk represents the weight of the kth air quality time series characteristic, and μij represents the membership degree between the operating room to be identified and the jth historical operating room;

[0028] S224: Determine whether the air quality membership of the operating room to be identified matches that of the historical operating room; if so, output the corresponding historical operating room number; if not, return to step S223;

[0029] S225. Repeat steps S221-S224 until all historical operating rooms have been retrieved and the air quality membership of all operating rooms to be identified has been calculated, and the best matching set of air quality time series features is output.

[0030] The step S3 specifically includes:

[0031] S31. Let the air quality curve with the highest matching degree in the best matching set be C1; let any other air quality curve in the best matching set be C2; define the distance matrix between air quality curves C1 and C2 as follows:

[0032]

[0033] Where: D represents the distance matrix, dij represents the distance between the air quality curves corresponding to the i-th item in C1 and the j-th item in C2, m and n represent the sequence lengths of C1 and C2 respectively;

[0034] S32. Based on the distance matrix, define a first dynamic time warping path for matching multiple air quality curves as follows:

[0035] P={(p1, p2)|p1∈[1,m], p2∈[1,n]}

[0036] Where: (1,1) and (m,n) represent the starting point and end point of the first dynamic time warping path respectively; l represents the length of the first dynamic time warping path;

[0037] S33. Set conditions that the first dynamic time warping path must meet, and construct a dynamic time warping path model for matching multiple air quality curves. The expression of the dynamic time warping path model is as follows:

[0038]

[0039] Wherein: dpk represents the distance between the construction progress completion rates of the project progress curves C1 and C2 at the kth matching point in the first dynamic time warping path, and |pk+1,1-pk,1|+|pk+1,2-pk,2|=1 represents the satisfaction condition of two adjacent points in the first dynamic time warping path.

[0040] The step S4 specifically includes:

[0041] S41. Solve the dynamic time warping path model based on the constrained dynamic time warping algorithm to obtain a second dynamic time warping path P2 corresponding to C1;

[0042] S42, expanding the air quality curves C1 and C2 into new air quality curve sequences C1′ and C2′ respectively according to the second dynamic time warping path P2;

[0043] S43. Based on the new air quality curve sequences C1′ and C2′, a comprehensive air quality curve sequence C comprehensive is calculated. The length of C comprehensive is the same as the second dynamic time warping path P2. The expression is as follows:

[0044]

[0045] Where: μi1 represents the air quality membership of the operating room to be identified and the operating room corresponding to the air quality curve C1;

[0046] S44. Integrate the air quality curve C2′ into Csynthesis to obtain the air quality curve fusion sequence Cfusion corresponding to the j-th operating room to be identified. The expression is as follows:

[0047]

[0048] Where: μk2 represents the kth curve in the comprehensive air quality curve sequence;

[0049] S45. Determine whether the maximum number of iterations is met; if so, output the final air quality model; if not, update the air quality curve C1 to C comprehensive, and repeat steps S41-S45 until all air quality curves in the best matching set of air quality time series features corresponding to the j-th operating room to be identified are integrated to obtain the final air quality model.

[0050] An operating room air purification system capable of adaptively adjusting air volume, the system comprising:

[0051] The air quality time series feature acquisition module is used to build an operating room air quality history database, extract air quality time series features, and assign a weight to each air quality time series feature according to the degree of discreteness;

[0052] An air quality time series feature best matching set construction module is used to construct an air quality membership function model based on the weight of the air quality time series feature, and match the air quality features of the operating room to be identified with the air quality time series features in the air quality membership function model to obtain the best matching set of air quality time series features;

[0053] A dynamic time warping path model construction module is used to define a distance matrix of air quality characteristics based on the best matching set of air quality time series characteristics, and based on the distance matrix, define a first dynamic time warping path and conditions to obtain a dynamic time warping path model;

[0054] The air quality pattern acquisition module is used to solve the dynamic time warping path model to obtain a second dynamic time warping path, expand the air quality curve according to the second dynamic time warping path to obtain a new air quality curve sequence, and calculate a comprehensive air quality curve sequence; based on the comprehensive air quality curve sequence, all air quality curves are combined with all air quality time series features in the best matching set of air quality time series features to obtain the final air quality pattern;

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention discloses an operating room air purification system and energy-saving method for adaptively adjusting air volume. The method first constructs an operating room air quality history database, extracts and weights air quality time series features; then constructs a membership function model based on the weights, matches the air quality features, and forms an optimal matching set; then defines and solves a dynamic time warping path model, optimizes the path through a distance matrix, and generates a new air quality curve sequence; finally, fuses the sequence with the optimal matching set features to obtain the final air quality model. In application, the present invention significantly improves the prediction accuracy of air quality by accurately capturing and weighting the air quality time series features, and optimizes the recognition and matching algorithm through dynamic time warping technology, thereby enhancing the rationality and accuracy of the comparison between operating room air quality data, while reducing the interference of human factors on the recognition results, and ensuring the objectivity and accuracy of the recognition results. In addition, the present invention realizes continuous and precise adjustment of air volume by adaptively adjusting air volume, optimizes energy consumption, and improves the overall efficiency and economy of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is the overall architecture diagram of the operating room air purification system of the present invention, which includes an air quality time series feature acquisition module, a best matching set construction module, a dynamic time warping path model construction module and an air quality pattern acquisition module.

[0058] Figure 2 The flowchart for constructing the operating room air quality historical database shows the specific steps of obtaining historical data, filtering and normalizing the air quality time series characteristics, and assigning weights.

[0059] Figure 3 This is a flowchart for building an air quality membership function model, showing how to build a weighted Euclidean distance model based on weights and perform air quality feature matching.

[0060] Figure 4 This is a flowchart for constructing a dynamic time warping path model, showing the specific steps of defining the distance matrix, formulating the first dynamic time warping path and its constraints.

[0061] Figure 5 The flowchart of solving the dynamic time warping path model shows the process of solving the second dynamic time warping path based on the constrained dynamic time warping algorithm and generating a new air quality curve sequence.

[0062] Figure 6 The flowchart of calculating the comprehensive air quality curve sequence shows the specific steps of how to calculate the comprehensive air quality curve sequence based on the new air quality curve sequence.

[0063] Figure 7The flowchart for obtaining the final air quality model shows how to fuse all air quality curves with the features in the best matching set to generate the final air quality model.

[0064] Figure 8 This is a schematic diagram of the actual application of the operating room air purification system of the present invention, showing the specific deployment and operation of the system in the operating room. DETAILED DESCRIPTION

[0065] The present invention provides an operating room air purification system with adaptive air volume adjustment and an energy-saving method thereof. The core of the system is to accurately predict and optimize operating room air quality by constructing an air quality history database, matching an optimal air quality feature set, defining a dynamic time-warped path model, and integrating an air quality curve sequence. The following describes a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings.

[0066] like Figure 1 As shown, the overall architecture of the operating room air purification system of the present invention includes four main modules: an air quality time series feature acquisition module, an air quality time series feature best matching set construction module, a dynamic time warping path model construction module, and an air quality pattern acquisition module. These modules work together to complete the entire process from data collection to the final air quality pattern generation. In actual application, the system is deployed in the operating room and linked with the air purification equipment to dynamically adjust the air volume according to the real-time monitored air quality data, thereby achieving the goal of high efficiency and energy saving.

[0067] First, the air quality time series feature acquisition module is responsible for building the operating room air quality history database and extracting the air quality time series features. Figure 2 As shown in Figure 1, the workflow of this module consists of three steps: acquiring historical data, filtering and normalizing air quality time-series features, and assigning weights. In the first step, the system collects air quality data from the operating room through a sensor network, including indicators such as particulate matter concentration, temperature and humidity, and carbon dioxide concentration, and stores this data in a database as a historical record. In the second step, the system filters the air quality time-series features relevant to the operating room to be identified from the database and normalizes them to eliminate dimensional differences. In the third step, the system assigns a weight to each air quality time-series feature based on the degree of dispersion of the historical data. The weight is calculated as Wi = 1σi2Wi = σi21, where Wi represents the weight of the i-th air quality time-series feature and σi2 represents the sample variance of the i-th air quality time-series feature. This weight assignment mechanism ensures that features with lower dispersion receive higher priority in subsequent analysis, thereby improving prediction accuracy.

[0068] Next, the air quality time series feature best matching set construction module constructs an air quality membership function model based on the above weights, and matches the air quality features of the operating room to be identified with the air quality time series features in the model to obtain the best matching set. Figure 3 As shown in Figure 2, the workflow of this module includes data input, normalization processing, membership calculation, and matching judgment. In the data input stage, the system compares the time series characteristic values of the air quality of the operating room to be identified with the characteristic values in the historical database. Subsequently, the system normalizes the characteristic values in the historical database to unify the dimensions. On this basis, the system uses weighted Euclidean distance to construct an air quality membership function model, which is expressed as follows:

[0069] Where xik and xjk represent the kth time-series air quality feature value of the operating room to be identified and the historical operating rooms, respectively. Wk is the weight of the kth feature, and μij represents the degree of membership between the two. By calculating the degree of membership, the system can quantify the similarity between the operating room to be identified and the historical operating rooms. Finally, the system determines whether there is a match based on the membership value and outputs the matching result. If there is no match, the system returns to the process and recalculates until all historical operating rooms have been retrieved, ultimately outputting the optimal matching set of air quality time-series features.

[0070] After obtaining the best matching set, the dynamic time warping path model construction module further defines the distance matrix of air quality characteristics and constructs the first dynamic time warping path model based on the distance matrix. Figure 4 As shown in Figure 2, the workflow of this module includes defining the distance matrix, formulating the first dynamic time warping path and its constraints. First, the system sets the air quality curve with the highest matching degree in the best matching set as C1, and any other curve as C2, and defines the distance matrix D between the two, which is expressed as

[0071] Where dij represents the distance between the air quality curves corresponding to the i-th item in C1 and the j-th item in C2, and m and n are the sequence lengths of the two, respectively. Subsequently, the system defines the first dynamic time warping path P based on the distance matrix, which is expressed as P = {(p1, p2) | p1∈[1,m], p2∈[1,n]}

[0072] Where (1,1) and (m,n) represent the starting point and end point of the path respectively. To ensure the rationality of the path, the system also sets a constraint condition, that is, two adjacent points must satisfy |pk+1,1-pk,1|+|pk+1,2-pk,2|=1. Finally, the system constructs a dynamic time warping path model by minimizing the path distance, and its objective function is Where dpk represents the distance at the kth matching point in the path.

[0073] After completing the construction of the dynamic time warping path model, the air quality pattern acquisition module solves the model and generates a new air quality curve sequence. Figure 5 As shown in the figure, the workflow of this module includes solving the second dynamic time warping path, expanding the air quality curve sequence, and calculating the comprehensive air quality curve sequence. First, the system solves the dynamic time warping path model based on the constrained dynamic time warping algorithm to obtain the second dynamic time warping path P2 corresponding to C1. Subsequently, the system expands the air quality curves C1 and C2 into new air quality curve sequences C1′ and C2′ according to P2. On this basis, the system calculates the comprehensive air quality curve sequence Ccomprehensive, which is expressed as

[0074] Where μi1 represents the air quality membership between the operating room to be identified and the operating room corresponding to C1. In order to further optimize the results, the system integrates C2′ into C synthesis to generate the air quality curve fusion sequence C fusion, which is expressed as

[0075] where μk2 represents the kth curve in the comprehensive air quality curve sequence. Finally, the system determines whether the maximum number of iterations has been met. If so, it outputs the final air quality model. Otherwise, it updates C1 to Ccomprehensive and repeats the above process until all air quality curves are fully integrated.

[0076] like Figure 6 The calculation process for the integrated air quality curve sequence, shown in Figure 2, further details how to generate integrated curves based on the new air quality curve sequence. The system first performs a weighted average on each curve, ensuring that the contributions of different curves are proportional to their membership. Subsequently, the system iteratively updates the system to gradually approach the optimal solution, ultimately generating an integrated curve that fully reflects the changing patterns of operating room air quality.

[0077] like Figure 7 The process for obtaining the final air quality model, shown in Figure 2, demonstrates how all air quality curves are fused with the features from the best matching set. By performing a weighted summation of the membership scores of each curve, the system ensures that the fusion result retains the characteristics of the original data while reflecting the overall trends of the best matching set. The resulting air quality model not only accurately predicts future air quality changes but also provides a scientific basis for air volume adjustment.

[0078] like Figure 8As shown, the operating room air purification system of the present invention performs well in practical applications. The system monitors the air quality data in the operating room in real time through sensors and inputs it into the above-mentioned module for processing. According to the generated air quality pattern, the system automatically adjusts the air volume of the air purification equipment to ensure that the air quality is always in the optimal state. For example, during surgery, when an increase in particulate matter concentration is detected, the system will quickly increase the air volume to accelerate air circulation; when the air quality is stable, the system will appropriately reduce the air volume to save energy. This adaptive adjustment mechanism not only improves the air purification effect, but also significantly reduces operating costs.

[0079] In summary, this invention achieves accurate prediction and optimized control of operating room air quality by constructing a historical air quality database, matching optimal feature sets, defining a dynamic time-warped path model, and integrating air quality curve sequences. In practical applications, the system demonstrates high efficiency and energy conservation, meeting the stringent requirements of modern medical environments for intelligent air purification systems.

[0080] The foregoing description shows and describes several preferred embodiments of the present invention. However, as previously stated, it should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. Rather, the present invention can be used in various other combinations, modifications, and environments and can be modified within the scope of the inventive concept described herein by the teachings above or by techniques or knowledge in the relevant art. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention are intended to be within the scope of the appended claims.

Claims

1. An operating room air purification system with adaptive air volume adjustment and an energy-saving method thereof, characterized in that: The following steps are involved: S1. Build an operating room air quality history database, obtain air quality time series characteristics, and assign a weight to each air quality time series characteristic based on the degree of discreteness; S2. Based on the weights of the air quality time series characteristics, an air quality membership function model is constructed, and the air quality characteristics of the operating room to be identified are matched with the air quality time series characteristics in the air quality membership function model to obtain the best matching set of air quality time series characteristics; S3. Based on the best matching set of air quality time series features, define a distance matrix of air quality features, and based on the distance matrix, define a first dynamic time warping path and conditions to obtain a dynamic time warping path model; S4. Solve the dynamic time warping path model to obtain a second dynamic time warping path, and expand the air quality curve according to the second dynamic time warping path to obtain a new air quality curve sequence, and calculate the comprehensive air quality curve sequence; based on the comprehensive air quality curve sequence, all air quality curves are integrated with all air quality time series features in the best matching set of air quality time series features to obtain the final air quality pattern.

2. The operating room air purification system with adaptive air volume adjustment and energy saving method thereof according to claim 1 is characterized in that: The step S1 specifically includes: S11. Obtain historical air quality data of the operating room and build an operating room air quality historical database; S12. Filter and match required air quality time series characteristics from the operating room air quality history database and perform normalization processing to obtain air quality time series characteristics; S13. Assign a weight to each air quality time series feature based on the discreteness of all historical air quality data in the operating room air quality history database; the weight is expressed as follows: Where: Wi represents the weight of the i-th air quality time series feature, Represents the sample variance of the i-th air quality time series feature in the operating room air quality history database.

3. The operating room air purification system with adaptive air volume adjustment and energy saving method thereof according to claim 2 is characterized in that: The step S2 specifically includes: S21. Based on the weight of the air quality time series characteristics, the air quality membership function model is constructed using weighted Euclidean distance; S22. Input the air quality characteristics of the operating room to be identified into the air quality membership function model and match them with the air quality time series characteristics to obtain the best matching set of air quality time series characteristics.

4. The operating room air purification system with adaptive air volume adjustment and energy saving method thereof according to claim 3 is characterized in that: The step S22 specifically includes: S221. Inputting the operating room air quality history database and the air quality time series characteristic value of the operating room to be identified; S222, extracting the time series characteristic values of the air quality of all historical operating rooms in the operating room air quality history database and normalizing them; S223. Calculating the air quality membership of the operating room to be identified and the historical operating rooms based on the air quality membership function model; The expression of the air quality membership function model is as follows: Where: xik represents the kth air quality time series characteristic value of the operating room to be identified, xjk represents the normalized kth air quality time series characteristic value of the historical operating room, Wk represents the weight of the kth air quality time series characteristic, and μij represents the membership degree between the operating room to be identified and the jth historical operating room; S224, determining whether the air quality membership of the operating room to be identified matches that of the historical operating room; if so, outputting the corresponding historical operating room number; if not, returning to step S223; S225. Repeat steps S221-S224 until all historical operating rooms have been retrieved and the air quality membership of all operating rooms to be identified has been calculated, and the best matching set of air quality time series features is output.

5. An operating room air purification system with adaptive air volume adjustment, characterized in that: The system comprises: The air quality time series feature acquisition module is used to build an operating room air quality history database, obtain air quality time series features, and assign a weight to each air quality time series feature according to the degree of discreteness; An air quality time series feature best matching set construction module is used to construct an air quality membership function model based on the weight of the air quality time series feature, and match the air quality features of the operating room to be identified with the air quality time series features in the air quality membership function model to obtain the best matching set of air quality time series features; A dynamic time warping path model construction module is used to define a distance matrix of air quality characteristics based on the best matching set of air quality time series characteristics, and based on the distance matrix, define a first dynamic time warping path and conditions to obtain a dynamic time warping path model; The air quality pattern acquisition module is used to solve the dynamic time warping path model, obtain the second dynamic time warping path, and expand the air quality curve according to the second dynamic time warping path to obtain a new air quality curve sequence, and calculate the comprehensive air quality curve sequence; based on the comprehensive air quality curve sequence, all air quality curves are integrated with all air quality time series features in the best matching set of air quality time series features to obtain the final air quality pattern.

6. The operating room air purification system with adaptive air volume adjustment according to claim 5, characterized in that: The air quality time series feature acquisition module acquires the air quality time series features and their weights according to the following steps: S11. Obtain historical air quality data of the operating room and build an operating room air quality historical database; S12. Filter and match required air quality time series characteristics from the operating room air quality history database and perform normalization processing to obtain air quality time series characteristics; S13. Assign a weight to each air quality time series feature based on the discreteness of all historical air quality data in the operating room air quality history database; the weight is expressed as follows: Where: Wi represents the weight of the i-th air quality time series feature, and σi2 represents the sample variance of the i-th air quality time series feature in the operating room air quality history database.

7. The operating room air purification system with adaptive air volume adjustment according to claim 5, characterized in that: The air quality time series feature best matching set construction module obtains the air quality time series feature best matching set according to the following steps: S21. Based on the weight of the air quality time series characteristics, the air quality membership function model is constructed using weighted Euclidean distance; S22, inputting the air quality characteristics of the operating room to be identified into the air quality membership function model to match the air quality time series characteristics, and obtaining the best matching set of air quality time series characteristics; The step S22 specifically includes: S221. Inputting the operating room air quality history database and the air quality time series characteristic value of the operating room to be identified; S222, extracting the time series characteristic values of the air quality of all historical operating rooms in the operating room air quality history database and normalizing them; S223. Calculating the air quality membership of the operating room to be identified and the historical operating rooms based on the air quality membership function model; The expression of the air quality membership function model is as follows: Where: xik represents the kth air quality time series characteristic value of the operating room to be identified, xjk represents the normalized kth air quality time series characteristic value of the historical operating room, Wk represents the weight of the kth air quality time series characteristic, and μij represents the membership degree between the operating room to be identified and the jth historical operating room; S224: Determine whether the air quality membership of the operating room to be identified matches that of the historical operating room; if so, output the corresponding historical operating room number; if not, return to step S223; S225. Repeat steps S221-S224 until all historical operating rooms have been retrieved and the air quality membership of all operating rooms to be identified has been calculated, and the best matching set of air quality time series features is output.

8. The operating room air purification system with adaptive air volume adjustment according to claim 5 is characterized in that: The dynamic time warping path model construction module defines and solves the dynamic time warping path model according to the following steps: S31. Let the air quality curve with the highest matching degree in the best matching set be C1; let any other air quality curve in the best matching set be C2; define the distance matrix between air quality curves C1 and C2 as follows: Where: D represents the distance matrix, dij represents the distance between the air quality curves corresponding to the i-th item in C1 and the j-th item in C2, m and n represent the sequence lengths of C1 and C2 respectively; S32. Based on the distance matrix, define a first dynamic time warping path for matching multiple air quality curves as follows: P={(p1,P2)|p1∈[1,m],p2∈[1,n]} Where: (1,1) and (m,n) represent the starting point and end point of the first dynamic time warping path respectively; l represents the length of the first dynamic time warping path; S33. Set conditions that the first dynamic time warping path must meet, and construct a dynamic time warping path model for matching multiple air quality curves. The expression of the dynamic time warping path model is as follows: Where: dpk represents the distance between the construction progress completion rates corresponding to the project progress curves C1 and C2 at the kth matching point in the first dynamic time warping path.

9. The operating room air purification system with adaptive air volume adjustment according to claim 5, characterized in that: The air quality pattern acquisition module solves the dynamic time warping path model and generates a new air quality curve sequence according to the following steps: S41. Solve the dynamic time warping path model based on the constrained dynamic time warping algorithm to obtain a second dynamic time warping path P2 corresponding to C1; S42, expanding the air quality curves C1 and C2 into new air quality curve sequences C1′ and C2′ respectively according to the second dynamic time warping path P2; S43. Based on the new air quality curve sequences C1′ and C2′, a comprehensive air quality curve sequence C comprehensive is calculated; the comprehensive air quality curve sequence C comprehensive is equal in length to the second dynamic time warping path P2; Its expression is as follows: Where: μi1 represents the air quality membership of the operating room to be identified and the operating room corresponding to the air quality curve C1; S44. Integrate the air quality curve C2′ into Csynthesis to obtain the air quality curve fusion sequence Cfusion corresponding to the j-th operating room to be identified. The expression is as follows: Where: μk2 represents the kth curve in the comprehensive air quality curve sequence; S45. Determine whether the maximum number of iterations is met; if so, output the final air quality model; if not, update the air quality curve C1 to C comprehensive, and repeat steps S41-S45 until all air quality curves in the best matching set of air quality time series features corresponding to the j-th operating room to be identified are integrated to obtain the final air quality model.

10. The operating room air purification system and energy-saving method thereof for adaptively adjusting air volume according to any one of claims 1 to 9, characterized in that: The system applies the final air quality model to the air purification equipment in the operating room to achieve adaptive adjustment of air volume, optimize energy consumption, and improve air purification effect.

Images