Medical compressed air quality online monitoring method, system, equipment and medium

Abstract

The invention relates to the technical field of air quality monitoring, in particular to a medical compressed air quality online monitoring method, system and equipment and a medium. The method comprises the following steps: firstly, acquiring multi-point real-time monitoring data, then calculating a concentration gradient value, then analyzing propagation characteristics, then determining the position of a pollution source, then evaluating the pollution risk, and finally giving a response instruction; by introducing historical data comparison and multi-parameter collaborative analysis, the accuracy of pollution event identification and the timeliness of early warning are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of air quality monitoring, and in particular to a method, system, equipment and medium for online monitoring of medical compressed air quality. Background Art

[0002] Medical compressed air is an important power source for medical institutions and is widely used in ventilators, surgical instruments, medical equipment, etc. Its quality directly affects medical safety and treatment effects, and the content of pollutants such as moisture and oil needs to be strictly controlled to ensure compliance with medical gas standards.

[0003] At present, the quality monitoring of medical compressed air mainly adopts online monitoring system, which collects parameters such as moisture, oil, pressure in real time through distributed sensor network, and combines intelligent algorithm to dynamically evaluate and warn the gas quality; however, the existing quality monitoring method does not accurately identify the propagation law of pollutants, cannot effectively locate the source of pollution, and it is difficult to detect and deal with pollution incidents in time. This situation needs to be further improved. Summary of the invention

[0004] In order to solve the problems that the existing quality monitoring methods cannot accurately identify the propagation law of pollutants, cannot effectively locate the pollution source, and are difficult to timely discover and deal with pollution incidents, the present application provides a medical compressed air quality online monitoring method, system, equipment and medium, which adopts the following technical solutions: In a first aspect, the present application provides a method for online monitoring of medical compressed air quality, comprising the following steps: Acquire a multi-point compressed air real-time monitoring data set, wherein the real-time monitoring data set includes moisture content, oil content, pressure value and ambient temperature; According to the real-time monitoring data set and the pipe network topology information, the pollutant concentration gradient value of each monitoring point is obtained; Based on the pollutant concentration gradient value, the pollutant diffusion rate and diffusion direction between adjacent monitoring points are calculated to obtain pollutant propagation characteristic parameters; According to the pollutant propagation characteristic parameters and historical data, the location of the pollution source and the scope of influence are determined to obtain characteristic information of the pollution event; Based on the characteristic information of the pollution event, calculate the current pollution level and development trend to obtain the risk assessment result; Based on the risk assessment results, the warning level and emergency response plan are determined, and response instructions are obtained.

[0005] By adopting the above technical solution, in order to ensure that the content of pollutants such as moisture and oil in the medical compressed air system always meets medical requirements, it is necessary to accurately monitor the diffusion law of pollutants in the pipeline network and timely warn; this application first obtains real-time monitoring data from multiple points, then calculates the concentration gradient value, then analyzes the propagation characteristics, and then determines the location of the pollution source, and then evaluates the pollution risk, and finally gives response instructions; by introducing historical data comparison and multi-parameter collaborative analysis, the accuracy of pollution event identification and the timeliness of warning are significantly improved.

[0006] Optionally, obtaining a multi-point compressed air real-time monitoring data set includes the following steps: According to a preset sampling period, the sensor array of each monitoring point is synchronously triggered to obtain initial sampling data, wherein the sensor array includes a moisture sensor, an oil sensor, a pressure sensor and a temperature sensor; Performing sliding window segmented sampling on the initial sampling data to obtain data segments of multiple sampling time windows; Calculate the mean and standard deviation of the data in each time window to obtain the window characteristic value; Compare the window characteristic value with the characteristic values ​​of three adjacent time windows, and if the difference exceeds a preset threshold, mark it as a fluctuation point; The fluctuation point is sampled again for confirmation. If the deviation between the secondary sampling result and the initial sampling result is within the allowable range, it is confirmed as valid data. Otherwise, the data point is deleted. The effective data is subjected to time-weighted averaging to obtain a stable real-time monitoring data set.

[0007] By adopting the above technical solution, in order to improve the reliability of medical compressed air quality monitoring data, it is necessary to solve the problem of data instability caused by environmental interference and sensor fluctuations; this application first realizes the synchronous sampling of multi-point sensors, and then uses a sliding window to segment the data, and then calculates the window eigenvalues, and then identifies the fluctuation points by comparing with adjacent windows, and then performs secondary sampling verification on suspicious data, and finally uses time-weighted averaging to obtain stable results; through time correlation analysis and secondary sampling confirmation, the reliability and accuracy of the data are significantly improved.

[0008] Optionally, obtaining the pollutant concentration gradient value of each monitoring point according to the real-time monitoring data set and the pipe network topology information specifically includes the following steps: Obtain the relative position of each monitoring point in the pipe network topology and the pipeline connection relationship to obtain the point spatial distribution data; According to the point spatial distribution data, the upstream point and the downstream point of each monitoring point are determined to obtain point association information; Based on the point association information, the actual pipeline distance and pipeline diameter between adjacent monitoring points are calculated to obtain pipeline characteristic parameters; Grouping the real-time monitoring data set according to the point association information to obtain pollutant concentration pairs of upstream and downstream points; According to the pollutant concentration pair and the pipeline characteristic parameter, combined with the flow data, the pollutant concentration change rate per unit distance is calculated to obtain an initial gradient value; The initial gradient value is pressure compensated and temperature corrected to obtain a pollutant concentration gradient value under a standard state.

[0009] By adopting the above technical solution, the traditional method only considers the linear distance and ignores the actual pipeline layout. The present application first establishes a point spatial distribution model, then introduces point association information, determines the upstream and downstream relationship of the point, and then considers the characteristic parameters of the actual length and diameter of the pipeline, extracts the pipeline characteristic parameters, and then establishes a concentration correspondence relationship, combining the point association information with the real-time monitoring data to avoid the gradient calculation deviation caused by point matching errors, and then calculates the initial gradient value to correct the environmental parameters; finally, through pressure compensation and temperature correction, the accuracy of pollutant concentration gradient calculation is significantly improved.

[0010] Optionally, according to the pollutant concentration pair and the pipeline characteristic parameter, combined with flow data, the pollutant concentration change rate per unit distance is calculated to obtain an initial gradient value, which specifically includes the following steps: Matching the pollutant concentration pairs according to the water content pairs and the oil content pairs respectively to obtain concentration differences of different types of pollutants; Calculating a flow correction coefficient according to the flow data; The moisture content difference and the oil content difference are divided by the corresponding pipe section lengths respectively, and multiplied by the flow correction coefficient to obtain their respective initial gradient values.

[0011] By adopting the above technical solution, in order to accurately calculate the concentration gradients of different types of pollutants in medical compressed air systems, the present application first calculates the concentration difference of water and oil pollutants respectively, then establishes a correction coefficient based on real-time flow data, and finally combines the distance-standardized concentration difference with the flow correction coefficient to obtain the initial gradient value; thus, an accurate description of the diffusion characteristics of different types of pollutants is achieved.

[0012] Optionally, based on the pollutant concentration gradient value, the pollutant diffusion rate and diffusion direction between adjacent monitoring points are calculated to obtain pollutant propagation characteristic parameters, which specifically includes the following steps: Calculating the change rate of pollutant concentration based on the pollutant concentration gradient value and the time series data of adjacent points; According to the change speed and the pipe network topology, the diffusion direction and diffusion rate of the pollutants between various points are determined to obtain the pollutant propagation characteristic parameters.

[0013] By adopting the above technical solution, this application first uses time series data to analyze the dynamic change characteristics of pollutant concentration, and then determines the actual diffusion direction and rate in combination with the pipeline network structure; it can accurately capture the actual propagation behavior of pollutants in the pipeline network.

[0014] Optionally, according to the pollutant propagation characteristic parameters and historical data, the location of the pollution source and the scope of influence are determined to obtain characteristic information of the pollution event, which specifically includes the following steps: Extracting propagation characteristic parameters of similar pollution events from the historical data and matching them with current pollutant propagation characteristic parameters; According to the matching results and the diffusion direction, the propagation path of the pollutants is traced back to determine the location of the pollution source; Based on the diffusion rate and historical impact range data, the current diffusion impact range of the pollutant is calculated.

[0015] By adopting the above technical solution, in order to quickly locate the pollution source in the medical compressed air system and evaluate its impact range; this application first matches the historical case features, then performs reverse tracking based on the diffusion direction, and finally predicts the impact range based on historical data; thereby improving the accuracy of pollution source positioning and the reliability of impact range prediction.

[0016] In a second aspect, the present application provides a medical compressed air quality online monitoring system, comprising: A monitoring data set acquisition module is used to acquire a multi-point compressed air real-time monitoring data set, wherein the real-time monitoring data set includes moisture content, oil content, pressure value and ambient temperature; A pollutant concentration gradient value acquisition module is used to obtain the pollutant concentration gradient value of each monitoring point according to the real-time monitoring data set and the pipe network topology information; A propagation characteristic parameter acquisition module is used to calculate the pollutant diffusion rate and diffusion direction between adjacent monitoring points based on the pollutant concentration gradient value to obtain pollutant propagation characteristic parameters; A pollution event characteristic information acquisition module is used to determine the location of the pollution source and the scope of influence according to the pollutant propagation characteristic parameters and historical data, and obtain the pollution event characteristic information; A risk assessment module, used to calculate the current pollution level and development trend based on the pollution event characteristic information to obtain risk assessment results; The response instruction acquisition module is used to determine the warning level and emergency response plan according to the risk assessment results and obtain the response instruction.

[0017] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for online monitoring of medical compressed air quality when executing the computer program.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for online monitoring of medical compressed air quality.

[0019] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application first obtains real-time monitoring data from multiple points, then calculates the concentration gradient value, then analyzes the propagation characteristics, then determines the location of the pollution source, then assesses the pollution risk, and finally gives a response instruction; by introducing historical data comparison and multi-parameter collaborative analysis, the accuracy of pollution event identification and the timeliness of early warning are significantly improved; 2. In order to improve the reliability of medical compressed air quality monitoring data, it is necessary to solve the problem of data instability caused by environmental interference and sensor fluctuations; this application first realizes the synchronous sampling of multi-point sensors, then uses a sliding window to segment the data, and then calculates the window characteristic value, and then identifies the fluctuation point by comparing with the adjacent window, and then performs secondary sampling verification on the suspicious data, and finally uses time-weighted average to obtain stable results; through time correlation analysis and secondary sampling confirmation, the reliability and accuracy of the data are significantly improved; 3. Traditional methods only consider linear distance and ignore the actual pipeline layout. This application first establishes a point spatial distribution model, then introduces point association information, determines the upstream and downstream relationship of the point, and then considers the characteristic parameters of the actual length and diameter of the pipeline, extracts the pipeline characteristic parameters, and then establishes a concentration correspondence. The point association information is combined with the real-time monitoring data to avoid gradient calculation deviations caused by point matching errors, and then calculates the initial gradient value and corrects the environmental parameters; finally, through pressure compensation and temperature correction, the accuracy of pollutant concentration gradient calculation is significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a method for online monitoring of medical compressed air quality according to an embodiment of the present application; Figure 2 It is a flow chart of step S100 in a method for online monitoring of medical compressed air quality in an embodiment of the present application; Figure 3 It is a flowchart of step S200 in a method for online monitoring of medical compressed air quality in an embodiment of the present application; Figure 4It is a flow chart of step S250 in a method for online monitoring of medical compressed air quality in an embodiment of the present application; Figure 5 It is a flowchart of step S300 in a method for online monitoring of medical compressed air quality in an embodiment of the present application; Figure 6 It is a flow chart of step S400 in a method for online monitoring of medical compressed air quality in an embodiment of the present application; Figure 7 This is a module schematic diagram of a medical compressed air quality online monitoring system according to an embodiment of the present application; Figure 8 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0022] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0023] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0024] In the first aspect, the present application provides a method for online monitoring of medical compressed air quality, referring to Figure 1 , including the following steps: S100, obtaining a multi-point compressed air real-time monitoring data set, where the real-time monitoring data set includes moisture content, oil content, pressure value, and ambient temperature.

[0025] In this embodiment, multiple points refer to 8-12 key monitoring points set in the medical compressed air pipe network system, including the air compressor outlet, the air tank outlet, the air branch pipe interface of each department, etc. The real-time monitoring data set includes key parameters such as moisture content, oil content, pressure value and ambient temperature.

[0026] Specifically, a sensor array is installed at each monitoring point, including a high-precision dew point meter, an oil content detector, a pressure transmitter, and a temperature sensor. The sampling frequency is adaptively adjusted according to the system status. During normal monitoring, the sampling is performed once every 5 minutes, and when an abnormality is detected, it is automatically increased to once per minute. Data is collected through the RS485 bus, and after preliminary screening and outlier processing, a standardized real-time monitoring data set is formed.

[0027] Furthermore, in order to monitor the quality of medical compressed air more comprehensively, in some embodiments, the real-time monitoring data set may include particulate matter content, various gases such as carbon monoxide, carbon dioxide, nitrogen oxides, sulfur dioxide content, and microbial content in addition to the original moisture content, oil content, pressure value, and ambient temperature. Comprehensive monitoring is achieved by installing laser particle counters, gas analyzers, and microbial samplers at each monitoring point. The laser particle counter is used to monitor the number concentration of particulate matter that meets the conditions, the gas analyzer is used to monitor the content of various gases, and the microbial sampler regularly collects samples for microbial culture counting to ensure that the total number of bacteria is within the preset standard range. Differentiated sampling strategies are adopted for different parameters. Conventional parameters (moisture, oil, pressure, etc.) are sampled every 5 minutes, gas components are sampled every 15 minutes, particulate matter is sampled every 30 minutes, and microorganisms are sampled no less than twice a day. The collected data are processed in a targeted manner, the particle data is processed by moving average to eliminate the impact of instantaneous fluctuations, the gas composition data is converted to the standard state using the temperature and pressure compensation algorithm, the microbial data is correlated with the environmental parameters and a pollution warning model is established, and all processed data are integrated into the real-time monitoring data set to achieve comprehensive monitoring of the quality of medical compressed air.

[0028] S200: Obtain the pollutant concentration gradient value of each monitoring point according to the real-time monitoring data set and the pipe network topology information.

[0029] In this embodiment, the pipe network topology information includes basic parameters such as pipe connection relationship, pipe section length, pipe diameter, etc. By establishing a point spatial distribution model and combining real-time monitoring data, the pollutant concentration change trend between adjacent points is calculated.

[0030] Specifically, first establish a digital model of the pipeline network and enter the pipeline layout and connection relationship; then calculate the concentration difference between adjacent points based on the measured data; finally, consider the influence of pipeline characteristics and environmental parameters to obtain an accurate concentration gradient value.

[0031] S300. Based on the pollutant concentration gradient value, the pollutant diffusion rate and diffusion direction between adjacent monitoring points are calculated to obtain pollutant propagation characteristic parameters.

[0032] In this embodiment, the time series analysis method is used to calculate the change rate of the pollutant concentration at each monitoring point, and the diffusion direction is determined in combination with the flow direction of the pipeline network. For example, when it is observed that the oil content at point A increases from 0.15 mg / m³ to 0.25 mg / m³ in 30 minutes, and the adjacent point B subsequently shows a similar change trend, it can be calculated that the diffusion rate of this section is about 2 m / min, and the diffusion direction is from A to B.

[0033] S400: Determine the location of the pollution source and the scope of influence based on the pollutant propagation characteristic parameters and historical data, and obtain characteristic information of the pollution event.

[0034] In this embodiment, the system pre-establishes a pollution event feature library, which stores a large amount of propagation feature data of typical pollution cases, including information such as pollution source type, diffusion pattern, and impact range.

[0035] Specifically, the system compares the current pollutant propagation characteristics with the similarity of historical cases and selects the case with the highest matching degree as a reference. For example, a monitoring found that the moisture content of the oxygen production center branch pipe was abnormally high. By comparing with historical data, it was found that it was highly similar to a cold dryer failure case. Based on this, it was determined that the pollution source was located in the drying device in the area, and the impact range was expected to cover three downstream departments.

[0036] S500: Based on the characteristic information of the pollution event, calculate the current pollution level and development trend to obtain the risk assessment result.

[0037] In this embodiment, a four-level pollution level assessment system is set up, corresponding to light pollution, moderate pollution, heavy pollution and severe pollution. The system comprehensively assesses the pollution level based on multi-dimensional indicators such as pollutant concentration, diffusion range, and duration.

[0038] Specifically, by establishing a pollution trend prediction model, the pollution index is calculated in real time and its changing trend is predicted. For example, when it is detected that the moisture content in a certain area continues to rise and exceeds 50ppm, and the affected area gradually expands, the system will judge it as moderate pollution (level 2) and predict that it may be upgraded to severe pollution within 2 hours.

[0039] S600. Determine the warning level and emergency response plan based on the risk assessment results, and obtain response instructions.

[0040] In this embodiment, the warning level corresponds to the pollution level, and each level is equipped with a corresponding emergency disposal plan. The system automatically matches the optimal disposal plan based on the pollution characteristics and development trends.

[0041] Specifically, when the system issues an early warning, it automatically generates a response instruction containing information such as the location of the pollution source, the scope of impact, and disposal suggestions. For example, in response to the aforementioned moderate pollution situation, the system will issue a yellow early warning and recommend specific measures such as starting the backup drying device, closing the gas supply branch pipes in the affected area, and increasing the monitoring frequency.

[0042] In one embodiment, referring to Figure 2 In step S100, a multi-point compressed air real-time monitoring data set is obtained, which specifically includes the following steps: S110 , according to a preset sampling period, synchronously trigger the sensor array of each monitoring point to obtain initial sampling data.

[0043] Among them, the sensor array includes a moisture sensor, an oil sensor, a pressure sensor and a temperature sensor.

[0044] S120 , performing sliding window segmented sampling on the initial sampling data to obtain data segments of multiple sampling time windows.

[0045] In this embodiment, the sliding window technology is used to process the initial sampled data in segments. The window size can be adjusted according to the actual operation requirements, and is usually set to 12 sampling points, with an overlap rate of 50% for adjacent windows to ensure the continuity and smoothness of the data.

[0046] Specifically, for data with a 5-minute sampling period, each window covers 1 hour of monitoring data, and adjacent windows overlap for 30 minutes. The system segments the continuously collected data according to the window size to form multiple time series segments.

[0047] S130, calculating the mean and standard deviation of the data in each time window to obtain the window characteristic value.

[0048] In this embodiment, statistical feature extraction is performed on the data of each time window. The overall level in the window is reflected by calculating the mean value, and the fluctuation degree of the data is characterized by the standard deviation. These two indicators together constitute the window feature value.

[0049] Specifically, the window mean is calculated using the arithmetic mean method, and the degree of dispersion is calculated using the overall standard deviation formula.

[0050] S140: Compare the window feature value with the feature values ​​of three adjacent time windows. If the difference exceeds a preset threshold, mark it as a fluctuation point.

[0051] In this embodiment, the system establishes an abnormality detection mechanism based on adjacent window comparison. The system compares the characteristic value of the current window with the characteristic values ​​of the three windows before and after, and sets the difference threshold criteria: moisture content ±5ppm, oil content ±0.1mg / m³, pressure value ±0.05MPa, temperature ±2℃.

[0052] Specifically, when the difference between the characteristic value of a window and the adjacent window exceeds the preset threshold, the system automatically marks the window as a fluctuation point. For example, if the average moisture content of a window suddenly increases by 7ppm compared with the previous window, the system will mark the window as an abnormal point to be confirmed.

[0053] S150, perform secondary sampling to confirm the fluctuation point. If the deviation between the secondary sampling result and the initial sampling result is within the allowable range, it is confirmed as valid data. Otherwise, the data point is deleted.

[0054] In this embodiment, a secondary sampling confirmation mechanism is used to verify the reliability of the fluctuation point. For the marked fluctuation point, the system automatically triggers encrypted sampling, the sampling interval is shortened to 1 minute, and 5 sets of data are continuously collected for verification.

[0055] Specifically, the system compares the average value of the secondary sampling with the first sampling result and sets the allowable deviation range: moisture content ±3ppm, oil content ±0.05mg / m³, pressure value ±0.03MPa, temperature ±1℃. If the secondary sampling result is within the allowable deviation range, it is confirmed as valid data; otherwise, it is determined as interference data and deleted.

[0056] S160, performing time-weighted averaging on the effective data to obtain a stable real-time monitoring data set.

[0057] In this embodiment, a time-weighted average algorithm is used to process valid data. The weight of recent data is relatively large, and the weight of long-term data decreases, ensuring that the processed data retains the change trend and has good stability.

[0058] In one embodiment, referring to Figure 3 In step S200, the pollutant concentration gradient value of each monitoring point is obtained according to the real-time monitoring data set and the pipe network topology information, which specifically includes the following steps: S210, obtaining the relative position of each monitoring point in the pipe network topology and the pipeline connection relationship, and obtaining point spatial distribution data.

[0059] In this embodiment, the system pre-establishes a digital model of the medical compressed air pipeline network. The pipeline network topology is stored in a graph database, including the spatial location information of key components such as trunk pipes, branch pipes, valves, and geometric features such as pipeline connection methods, directions, and intersections.

[0060] Specifically, a three-dimensional coordinate system is used to describe the spatial position of each monitoring point, and an adjacency matrix is ​​used to record the pipeline connection relationship. For example, a hospital compressed air system includes a DN80 trunk pipe and six DN50 branches. Three monitoring points A, B, and C are set on the trunk pipe, and six monitoring points D1-D6 are set on the branch pipe, forming a "one main and multiple branches" tree network structure.

[0061] S220. Determine the upstream and downstream points of each monitoring point according to the point spatial distribution data, and obtain point association information.

[0062] In this embodiment, the airflow direction model is constructed by analyzing the spatial distribution data of the points. Based on the air supply principle of the compressed air system and in combination with the characteristics of the pipe network structure, the upstream and downstream relationships between the points are determined, and a point association database is established.

[0063] Specifically, the system hierarchically numbers the monitoring points according to the direction of airflow, with the air compressor outlet as the zero layer and extending step by step downstream. For example, the monitoring points A, B, and C on the trunk are defined as the first, second, and third layer nodes respectively, and the branch monitoring points D1 and D2 connected to point B are defined as the downstream nodes of the point, realizing the hierarchical association between the points.

[0064] S230. Based on the point association information, the actual pipeline distance and pipeline diameter between adjacent monitoring points are calculated to obtain pipeline characteristic parameters.

[0065] In this embodiment, the system pre-establishes a pipeline characteristic parameter calculation model. By analyzing the geometric characteristics of the pipeline network, taking into account pipeline bends and branches, the actual pipeline length between any two adjacent monitoring points is calculated. At the same time, the physical parameters such as the diameter and wall thickness of the pipe section are recorded.

[0066] Specifically, the pipeline tracking algorithm is used to calculate the actual pipe length, and the lengths of each straight segment and elbow segment are accumulated. For example, the pipeline from point B to point D1 contains a 2-meter straight pipe and a 90-degree elbow. The equivalent length is 2.5 meters according to the elbow coefficient. Combined with the parameters of the pipe diameter DN50, the complete characteristic parameter set of this section of the pipeline is obtained.

[0067] S240, grouping the real-time monitoring data set according to point association information to obtain pollutant concentration pairs of upstream and downstream points.

[0068] In this embodiment, based on the point association information, the real-time monitoring data are paired according to the upstream and downstream relationship to form a pollutant concentration pair data set. Each set of data contains complete monitoring parameters of two adjacent points.

[0069] S250. According to the pollutant concentration pair and the pipeline characteristic parameters, combined with the flow data, the pollutant concentration change rate per unit distance is calculated to obtain an initial gradient value.

[0070] In this embodiment, the change in pollutant concentration per unit distance is calculated by combining pipeline characteristic parameters and flow data. The model takes into account the influence of flow velocity on material transmission and introduces a flow correction coefficient.

[0071] Specifically, the linear gradient calculation formula is used, the concentration difference is divided by the actual pipe length, and multiplied by the flow correction coefficient.

[0072] S260, performing pressure compensation and temperature correction on the initial gradient value to obtain the pollutant concentration gradient value under standard conditions.

[0073] In this embodiment, the system establishes an environmental parameter compensation mechanism, taking into account the influence of pressure and temperature on the pollutant concentration measurement, and converting the initial gradient value into a value under standard conditions through compensation calculation.

[0074] Specifically, the system uses the ideal gas state equation for correction. For example, when the actual pressure is 0.9MPa and the temperature is 25°C, the initial gradient value of 2.4ppm / m is corrected to obtain a concentration gradient value of 2.1ppm / m under the standard state as the final calculation result.

[0075] In one embodiment, referring to Figure 4 In step S250, based on the pollutant concentration pair and the pipeline characteristic parameters, combined with the flow data, the pollutant concentration change rate per unit distance is calculated to obtain the initial gradient value, which specifically includes the following steps: S251. Match the pollutant concentration pairs according to the water content pairs and the oil content pairs respectively to obtain the concentration differences of different types of pollutants.

[0076] S252. Calculate the flow correction coefficient according to the flow data.

[0077] In this embodiment, the system pre-establishes a correction coefficient comparison table, the correction coefficient is non-linearly related to the flow rate, and a correction curve is obtained by fitting experimental data.

[0078] Specifically, the system queries the correction coefficient comparison table based on the current flow value. For example, when the flow rate of the pipe section is 150m³ / h, the corresponding correction coefficient is 0.8; when the flow rate increases to 300m³ / h, the correction coefficient rises to 1.2. This dynamic correction mechanism can more accurately reflect the transmission characteristics of pollutants under different flow conditions.

[0079] S253. Divide the moisture content difference and the oil content difference by the corresponding pipe section length respectively, and multiply by the flow correction coefficient to obtain their respective initial gradient values.

[0080] In one embodiment, referring to Figure 5In step S300, based on the pollutant concentration gradient value, the pollutant diffusion rate and diffusion direction between adjacent monitoring points are calculated to obtain the pollutant propagation characteristic parameters, which specifically includes the following steps: S310. Calculate the changing speed of pollutant concentration based on the pollutant concentration gradient value and the time series data of adjacent points.

[0081] In this embodiment, the system uses a sliding time window method to perform time series analysis on the pollutant concentration data of each monitoring point and calculate the rate of change of concentration over time.

[0082] S320. According to the change speed and the topological structure of the pipe network, the diffusion direction and diffusion rate of the pollutants between various points are determined to obtain characteristic parameters of pollutant propagation.

[0083] In this embodiment, a pollutant diffusion model is established by using a pollutant propagation characteristic analysis algorithm, taking into account the change rate of pollutant concentration, pipe network structure characteristics and gas flow direction. The actual propagation path and speed of pollutants are determined by analyzing the time correlation of concentration changes at adjacent points.

[0084] Specifically, the system first identifies the initial point where the pollutant concentration increases abnormally, and then tracks the propagation process of the pollutant concentration change in the pipe network. For example, when the moisture content at point A is monitored to rise suddenly from 35ppm to 50ppm, the adjacent point B also shows a similar concentration increase trend 10 minutes later. Combined with the actual pipeline distance of 20 meters between the two points, the diffusion rate of the pollutant can be calculated to be 2 meters / minute. At the same time, according to the order of concentration changes, the diffusion direction is determined to be from point A to point B. The system combines these parameters to form a pollutant propagation characteristic parameter set, including information such as diffusion rate, diffusion direction, and impact range. Taking the gas supply branch pipe in the operating area of ​​a hospital as an example, when the system detects that the oil content at the gas source (point A) rises from 0.15mg / m³ to 0.25mg / m³ within 15 minutes, and the downstream monitoring point (point B) shows a similar change after 8 minutes, considering the distance between the two points is 16 meters, it can be calculated that the diffusion rate of the oil pollutant is about 2 meters / minute, and the diffusion direction is determined to be from the gas source to the operating area.

[0085] In one embodiment, referring to Figure 6 In step S400, the location of the pollution source and the impact range are determined according to the pollutant propagation characteristic parameters and historical data, and the characteristic information of the pollution event is obtained, which specifically includes the following steps: S410: Extract propagation characteristic parameters of similar pollution events from historical data and match them with current pollutant propagation characteristic parameters.

[0086] In this embodiment, the system pre-establishes a pollution event feature library matching system. The system stores a large number of characteristic parameters of historical pollution events, including key indicators such as pollutant type, concentration change pattern, and propagation rate. A multi-dimensional feature vector is used to represent each pollution event, and event matching is performed by calculating the similarity between feature vectors.

[0087] Specifically, the system calculates the similarity between the characteristic parameters of the current pollution event and historical cases. For example, a monitoring found that the moisture content of a point continued to rise at a rate of 0.8ppm / min, and the affected area expanded in a fan-shaped manner. The system searched the historical database and found that the characteristics were highly similar to a dryer failure case (the similarity reached 85%). The diffusion rate in this case was 0.9ppm / min, and the diffusion pattern also showed similar characteristics. Through this feature matching, potential pollution source types can be quickly identified.

[0088] S420: According to the matching results and diffusion direction, the pollutant propagation path is traced in reverse to determine the location of the pollution source.

[0089] In this embodiment, based on the diffusion direction and propagation characteristics of pollutants and combined with the topological structure of the pipe network, a reverse tracking model of the pollutant propagation path is constructed.

[0090] Specifically, the system establishes a pollution propagation time sequence diagram based on the time sequence of pollutants detected at each monitoring point. For example, when it is found that the oil content at points B, C, and D is abnormally increased, with time intervals of 5 minutes and 8 minutes respectively, combined with the pipe network structure analysis, it can be inferred that the pollution source is located upstream of point B. Further combined with the diffusion rate (2 meters / minute) and the distance between points, the specific location of the pollution source is located at a valve component 10 meters upstream of point B.

[0091] S430: Calculate the diffusion impact range of the current pollutant based on the diffusion rate and historical impact range data.

[0092] In this embodiment, the current diffusion rate of pollutants, the characteristics of the pipe network structure and historical case data are comprehensively considered, and a numerical simulation method is used to predict the potential impact range of pollutants.

[0093] Specifically, the system uses the diffusion equation to calculate the spread range of pollutants based on the location of the identified pollution source. For example, in a pollution incident, the pollution source is located at a branch point of the main pipeline, and the diffusion rate of the pollutant (water) is 1.5 meters per minute. Referring to the data of similar historical cases, it is predicted that the pollutant will spread 180 meters downstream along the main pipeline within 2 hours, and the impact range will cover the three departments supplied by the pipeline network. Based on this, the system generates a pollution impact range map, marking high-risk areas and potential impact areas.

[0094] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0095] In the second aspect, the present application provides a medical compressed air quality online monitoring system. The medical compressed air quality online monitoring system of the present application is described below in combination with the above-mentioned medical compressed air quality online monitoring method.

[0096] Reference Figure 7 , a medical compressed air quality online monitoring system, comprising: A monitoring data set acquisition module is used to acquire a real-time monitoring data set of compressed air at multiple points. The real-time monitoring data set includes moisture content, oil content, pressure value and ambient temperature; The pollutant concentration gradient value acquisition module is used to obtain the pollutant concentration gradient value of each monitoring point based on the real-time monitoring data set and the pipe network topology information; The propagation characteristic parameter acquisition module is used to calculate the pollutant diffusion rate and diffusion direction between adjacent monitoring points based on the pollutant concentration gradient value, and obtain the pollutant propagation characteristic parameters; The pollution event characteristic information acquisition module is used to determine the location of the pollution source and the scope of influence based on the pollutant propagation characteristic parameters and historical data, and obtain the pollution event characteristic information; The risk assessment module is used to calculate the current pollution level and development trend based on the characteristic information of pollution events and obtain risk assessment results; The response instruction acquisition module is used to determine the warning level and emergency response plan according to the risk assessment results and obtain the response instruction.

[0097] In one embodiment, the monitoring data set acquisition module includes: A sampling trigger unit is used to synchronously trigger the sensor array of each monitoring point according to a preset sampling period to obtain initial sampling data, wherein the sensor array includes a moisture sensor, an oil sensor, a pressure sensor and a temperature sensor; A data segmentation unit, used for performing sliding window segmentation sampling on the initial sampling data to obtain data segments of multiple sampling time windows; A feature calculation unit is used to calculate the mean and standard deviation of the data in each time window to obtain the window feature value; A fluctuation detection unit is used to compare the characteristic value of a window with the characteristic values ​​of three adjacent time windows. If the difference exceeds a preset threshold, it is marked as a fluctuation point; The data verification unit is used to perform secondary sampling confirmation on the fluctuation point. If the deviation between the secondary sampling result and the first sampling result is within the allowable range, it is confirmed as valid data, otherwise the data point is deleted; The data averaging unit is used to perform time-weighted averaging on the valid data to obtain a stable real-time monitoring data set.

[0098] In one embodiment, the pollutant concentration gradient value acquisition module includes: The point distribution acquisition unit is used to obtain the relative position of each monitoring point in the pipe network topology and the pipeline connection relationship to obtain the point spatial distribution data; A point association determination unit is used to determine the upstream point and the downstream point of each monitoring point according to the point spatial distribution data, and obtain point association information; A pipeline characteristic calculation unit is used to calculate the actual pipeline distance and pipeline diameter between adjacent monitoring points based on point association information to obtain pipeline characteristic parameters; A concentration pair acquisition unit is used to group the real-time monitoring data set according to the point association information to obtain the pollutant concentration pairs of the upstream and downstream points; The initial gradient calculation unit is used to calculate the pollutant concentration change rate per unit distance according to the pollutant concentration pair and the pipeline characteristic parameters in combination with the flow data to obtain the initial gradient value; The parameter correction unit is used to perform pressure compensation and temperature correction on the initial gradient value to obtain the pollutant concentration gradient value under standard conditions.

[0099] In one embodiment, the initial gradient calculation unit includes: The concentration difference calculation subunit is used to match the pollutant concentration pairs according to the water content pairs and the oil content pairs respectively, and obtain the concentration differences of different types of pollutants; A flow correction coefficient calculation subunit, used for calculating the flow correction coefficient according to the flow data; The gradient value calculation subunit is used to divide the moisture content difference and the oil content difference by the corresponding pipe section length respectively, and multiply them by the flow correction coefficient to obtain their respective initial gradient values.

[0100] In one embodiment, the propagation characteristic parameter acquisition module includes: A change speed calculation unit, used to calculate the change speed of pollutant concentration according to the pollutant concentration gradient value and the time series data of adjacent points; The diffusion characteristic determination unit is used to determine the diffusion direction and diffusion rate of pollutants between various points according to the change speed and the pipe network topology, and obtain the pollutant propagation characteristic parameters.

[0101] In one embodiment, the pollution event characteristic information acquisition module includes: A feature matching unit is used to extract the propagation feature parameters of similar pollution events from historical data and match them with the current pollutant propagation feature parameters; The pollution source tracking unit is used to reversely track the pollutant propagation path and determine the location of the pollution source based on the matching results and diffusion direction; The impact range calculation unit is used to calculate the diffusion impact range of the current pollutant based on the diffusion rate and historical impact range data.

[0102] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for online monitoring of medical compressed air quality is implemented.

[0103] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0104] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0105] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0106] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for online monitoring of medical compressed air quality, characterized in that: The steps include: Acquire a multi-point compressed air real-time monitoring data set, wherein the real-time monitoring data set includes moisture content, oil content, pressure value and ambient temperature; According to the real-time monitoring data set and the pipe network topology information, the pollutant concentration gradient value of each monitoring point is obtained; Based on the pollutant concentration gradient value, the pollutant diffusion rate and diffusion direction between adjacent monitoring points are calculated to obtain pollutant propagation characteristic parameters; According to the pollutant propagation characteristic parameters and historical data, the location of the pollution source and the scope of influence are determined to obtain characteristic information of the pollution event; Based on the pollution event characteristic information, calculate the current pollution level and development trend to obtain risk assessment results; Based on the risk assessment results, the warning level and emergency response plan are determined, and response instructions are obtained.

2. The method for online monitoring of medical compressed air quality according to claim 1, characterized in that: Obtaining a multi-point compressed air real-time monitoring data set includes the following steps: According to a preset sampling period, the sensor array of each monitoring point is synchronously triggered to obtain initial sampling data, wherein the sensor array includes a moisture sensor, an oil sensor, a pressure sensor and a temperature sensor; Performing sliding window segmented sampling on the initial sampling data to obtain data segments of multiple sampling time windows; Calculate the mean and standard deviation of the data in each time window to obtain the window characteristic value; Compare the window characteristic value with the characteristic values ​​of three adjacent time windows, and if the difference exceeds a preset threshold, mark it as a fluctuation point; The fluctuation point is sampled again for confirmation. If the deviation between the secondary sampling result and the initial sampling result is within the allowable range, it is confirmed as valid data. Otherwise, the data point is deleted. The effective data is subjected to time-weighted averaging to obtain a stable real-time monitoring data set.

3. The method for online monitoring of medical compressed air quality according to claim 1, characterized in that: According to the real-time monitoring data set and the pipe network topology information, the pollutant concentration gradient value of each monitoring point is obtained, which specifically includes the following steps: Obtain the relative position of each monitoring point in the pipe network topology and the pipeline connection relationship to obtain the point spatial distribution data; According to the point spatial distribution data, the upstream point and the downstream point of each monitoring point are determined to obtain point association information; Based on the point association information, the actual pipeline distance and pipeline diameter between adjacent monitoring points are calculated to obtain pipeline characteristic parameters; Grouping the real-time monitoring data set according to the point association information to obtain pollutant concentration pairs of upstream and downstream points; According to the pollutant concentration pair and the pipeline characteristic parameter, combined with the flow data, the pollutant concentration change rate per unit distance is calculated to obtain an initial gradient value; The initial gradient value is pressure compensated and temperature corrected to obtain a pollutant concentration gradient value under a standard state.

4. The method for online monitoring of medical compressed air quality according to claim 3, characterized in that: According to the pollutant concentration pair and the pipeline characteristic parameter, combined with the flow data, the pollutant concentration change rate per unit distance is calculated to obtain the initial gradient value, which specifically includes the following steps: Matching the pollutant concentration pairs according to the water content pairs and the oil content pairs respectively to obtain concentration differences of different types of pollutants; Calculating a flow correction coefficient according to the flow data; The moisture content difference and the oil content difference are divided by the corresponding pipe section lengths respectively, and multiplied by the flow correction coefficient to obtain their respective initial gradient values.

5. The method for online monitoring of medical compressed air quality according to claim 1, characterized in that: Based on the pollutant concentration gradient value, the pollutant diffusion rate and diffusion direction between adjacent monitoring points are calculated to obtain pollutant propagation characteristic parameters, which specifically includes the following steps: Calculating the change rate of pollutant concentration based on the pollutant concentration gradient value and the time series data of adjacent points; According to the change speed and the pipe network topology, the diffusion direction and diffusion rate of the pollutants between various points are determined to obtain the pollutant propagation characteristic parameters.

6. The method for online monitoring of medical compressed air quality according to claim 5, characterized in that: According to the pollutant propagation characteristic parameters and historical data, the location of the pollution source and the scope of influence are determined to obtain characteristic information of the pollution event, which specifically includes the following steps: Extracting propagation characteristic parameters of similar pollution events from the historical data and matching them with current pollutant propagation characteristic parameters; According to the matching results and the diffusion direction, the propagation path of the pollutants is traced back to determine the location of the pollution source; Based on the diffusion rate and historical impact range data, the current diffusion impact range of the pollutant is calculated.

7. A medical compressed air quality online monitoring system, characterized in that: include: A monitoring data set acquisition module is used to acquire a multi-point compressed air real-time monitoring data set, wherein the real-time monitoring data set includes moisture content, oil content, pressure value and ambient temperature; A pollutant concentration gradient value acquisition module is used to obtain the pollutant concentration gradient value of each monitoring point according to the real-time monitoring data set and the pipe network topology information; A propagation characteristic parameter acquisition module is used to calculate the pollutant diffusion rate and diffusion direction between adjacent monitoring points based on the pollutant concentration gradient value to obtain pollutant propagation characteristic parameters; A pollution event characteristic information acquisition module is used to determine the location of the pollution source and the scope of influence according to the pollutant propagation characteristic parameters and historical data, and obtain the pollution event characteristic information; A risk assessment module, used to calculate the current pollution level and development trend based on the pollution event characteristic information to obtain risk assessment results; The response instruction acquisition module is used to determine the warning level and emergency response plan according to the risk assessment results and obtain the response instruction.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the medical compressed air quality online monitoring method described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for online monitoring of medical compressed air quality according to any one of claims 1 to 6 are implemented.

Images