Medical Gas Monitoring and Intelligent Regulation Method, System, Device and Medium

Abstract

This application relates to the technical field of medical gas monitoring, and particularly to a medical gas monitoring and intelligent adjustment method, system, device and medium. First, this application collects real-time data such as pressure, flow rate, and temperature through multiple sensors, transmits this data to the cloud for in-depth analysis, and extracts the system operation state characteristics; then performs similarity analysis based on a pre-established historical failure case library to achieve the assessment of the risk level; then obtains the deviation value by comparing with the preset target parameters, and finally formulates a scientific adjustment strategy according to the deviation value and the risk level; significantly improving the reliability and safety of the system operation.

Description

Technical Field

[0001] The present application relates to the technical field of medical gas monitoring, and in particular to a method, system, device and medium for medical gas monitoring and intelligent regulation. Background Art

[0002] Medical gas systems are important infrastructure in modern hospitals, providing necessary gas media for various medical devices and treatment processes. With the development of medical technology and the expansion of hospital scale, higher requirements are put forward for the safety, reliability and intelligent level of medical gas systems. Especially in critical departments such as intensive care units and operating rooms, the stability of gas supply is directly related to patient safety.

[0003] Currently, the medical gas monitoring system mainly adopts the methods of fixed threshold alarm and single-parameter monitoring, and conducts simple status monitoring by setting upper and lower pressure limits, flow warning values, etc. The adjustment of system operation parameters mainly relies on regular inspections and empirical judgments, lacking intelligent analysis and prediction capabilities; this situation needs to be further improved. Summary of the Invention

[0004] In order to solve the problem that the existing medical gas monitoring system lacks intelligent analysis and prediction capabilities, the present application provides a method, system, device and medium for medical gas monitoring and intelligent regulation, and adopts the following technical solutions:

[0005] In a first aspect, the present application provides a method for medical gas monitoring and intelligent regulation, including the following steps:

[0006] Collect the pressure, flow rate, and temperature data of the medical gas system to obtain real-time operation parameters;

[0007] Transmit the real-time operation parameters to the cloud data center for data analysis to obtain system operation state characteristics;

[0008] Based on the system operation state characteristics, combined with a pre-established database containing historical failure cases, evaluate the current system risk level;

[0009] Compare the system operation state characteristics with preset target parameters, and calculate a parameter deviation value;

[0010] Based on the parameter deviation value and the current system risk level, determine a system adjustment strategy to obtain a control instruction.

[0011] By adopting the above technical solutions, there are problems such as insufficient collaborative analysis of multiple parameters and lagging fault warning during the operation of the medical gas system. For example, in a certain top-three hospital during the peak gas usage period in the operating room, due to the inability to timely detect the correlation between abnormal pressure fluctuations and flow rate changes, the gas supply was interrupted, affecting the surgical process. In this application, first, real-time data such as pressure, flow rate, and temperature are collected through multiple sensors, and these data are transmitted to the cloud for in-depth analysis to extract the characteristics of the system operation state. Then, similarity analysis is performed based on a pre-established historical fault case library to achieve the assessment of the risk level. Next, the deviation value is obtained by comparing with the preset target parameters, and finally, a scientific adjustment strategy is formulated according to the deviation value and the risk level, significantly improving the reliability and safety of the system operation.

[0012] Optionally, the real-time operation parameters are transmitted to the cloud data center for data analysis to obtain the characteristics of the system operation state, which specifically includes the following steps:

[0013] Perform time series decomposition on the real-time operation parameters to obtain periodic fluctuations, seasonal variations, and random disturbance components;

[0014] Determine the daily fluctuation range and the time period when the peak value appears for each operation parameter;

[0015] According to the preset types of medical scenarios, identify the usage patterns of the real-time operation parameters, and the usage patterns include regular gas usage patterns, emergency gas usage patterns, and equipment maintenance patterns;

[0016] Calculate the matching degree between the usage pattern and the fluctuation range at the current time period;

[0017] Based on the matching degree and the usage pattern, obtain the characteristics of the system operation state.

[0018] By adopting the above technical solutions, in the case of a large number of day surgeries and frequent emergency rescues, if the system cannot accurately distinguish the demand for regular gas and emergency gas, resulting in unreasonable gas allocation and affecting the gas supply quality. In this application, first, time series decomposition is performed on the real-time operation parameters, innovatively separating the parameter changes into three dimensions: periodic fluctuations, seasonal variations, and random disturbances. Then, the dynamic fluctuation law of the parameters is determined through statistical analysis. Next, according to the preset medical scenario feature library, a discrimination mechanism for three typical patterns of regular gas usage, emergency gas usage, and equipment maintenance is established. Then, accurate identification of the scenario is achieved through matching degree calculation. Finally, accurate characteristics of the system operation state are obtained, improving the adaptability to scenarios.

[0019] Optionally, based on the matching degree and the usage pattern, obtain the characteristics of the system operation state, which specifically includes the following steps:

[0020] Determine characteristic indicators according to the usage pattern, where the characteristic indicators include pressure stability, flow uniformity, and temperature volatility;

[0021] Calculate the weight coefficients of each characteristic indicator based on the matching degree, and use the weight coefficients to perform weighted calculation on the characteristic indicators to obtain a quantization value;

[0022] Combine the quantization values to construct a system state vector, and perform normalization processing on the system state vector to obtain the system operation state characteristics.

[0023] By adopting the above technical solution, the present application first dynamically selects pressure stability, flow uniformity, and temperature volatility according to the usage pattern; then introduces the scenario matching degree into the weight calculation process to realize the dynamic adjustment of the characteristic indicator weights; finally, through the construction and normalization processing of the state vector, a unified evaluation standard is established to realize the quantization of the system state, and the accuracy of the state evaluation is improved through adaptive weight allocation.

[0024] Optionally, according to the system operation state characteristics, combined with a pre-established database containing historical fault cases, evaluate the current system risk level, which specifically includes the following steps:

[0025] Extract the top N fault cases with the highest feature similarity from the historical fault case database;

[0026] Calculate the feature distance between the system operation state characteristics and each fault case;

[0027] Weight the fault cases based on the feature distance to obtain a fault type probability distribution;

[0028] Calculate a comprehensive risk index according to the fault type probability distribution and the severity of each type of fault;

[0029] Map the comprehensive risk index to a preset risk level interval to obtain the current system risk level.

[0030] By adopting the above technical solution, the present application first uses a similarity matching algorithm in the historical fault case library to screen out the most valuable N similar cases; then calculates the feature distance to quantify the proximity of the current state to the historical faults; then establishes a fault probability distribution model based on the distance weight to realize the accurate evaluation of the occurrence possibility of different types of faults; then combines the fault severity to construct a comprehensive risk index; finally, determines the risk level through intelligent mapping; improving the accuracy and forward-looking of the risk assessment, and significantly improving the safety and reliability of the system operation.

[0031] Optionally, based on the comparison between the system operation state characteristics and preset target parameters, calculate a parameter deviation value, which specifically includes the following steps:

[0032] Obtain the gas usage priority and importance level of each department, and establish a department weight matrix;

[0033] Based on the department weight matrix, calculate the dynamic adjustment coefficients of each operating parameter;

[0034] Perform parameter normalization processing on the system operation state characteristics, calculate the deviation between the normalized parameters and their respective target values to obtain the basic deviation value;

[0035] According to the dynamic adjustment coefficient, perform weighted correction on the basic deviation value to obtain the final parameter deviation value.

[0036] By adopting the above technical solution, the present application first introduces a department weight matrix, quantifies the gas usage priority and importance level of each department into specific indicators; then dynamically generates the adjustment coefficient of the operating parameter based on the weight matrix, realizing the differential management of parameter adjustment; then establishes a standardized deviation calculation system through parameter normalization and target value comparison; finally performs weighted correction through the dynamic adjustment coefficient; not only realizes the differential management of departments, but also improves the pertinence and rationality of parameter adjustment through dynamic weight adjustment.

[0037] Optionally, according to the parameter deviation value and the current system risk level, determine the system adjustment strategy to obtain a control instruction, specifically including the following steps:

[0038] Construct a decision matrix according to the parameter deviation value and the current system risk level;

[0039] Determine the position of the current system state point in the decision matrix, and select the corresponding adjustment strategy template according to the position of the state point;

[0040] Generate a specific parameter adjustment plan based on the adjustment strategy template, and convert the parameter adjustment plan into a control instruction.

[0041] By adopting the above technical solution, the present application constructs a system state decision matrix based on the parameter deviation value and the risk level; then accurately identifies the system state point through matrix positioning technology, realizing the precise matching of the adjustment strategy; finally generates a specific control instruction based on the preset strategy template, establishing a decision execution chain, and improving the scientificity and timeliness of the decision.

[0042] Optionally, the method further includes the following steps:

[0043] Establish a graphical user interface with hierarchical permissions, and the user interface includes a real-time data visualization module, a fault diagnosis module, and a remote control module;

[0044] Display the system operation status characteristics in the form of a trend chart, which includes a line chart of pressure changes, a bar chart of flow distribution, and a pie chart of temperature distribution;

[0045] Call the fault diagnosis library according to the current system risk level, and generate a maintenance guide manual containing fault definitions, cause analysis, and repair suggestions;

[0046] Connect the user interface to the remote monitoring terminal, and open corresponding data access and control based on the user permission level.

[0047] By adopting the above technical solutions, when dealing with system anomalies, the maintenance personnel in the hospital need to switch between multiple independent systems to view data, and lack clear fault diagnosis guidelines, resulting in low problem-solving efficiency. When remotely managing, security risks are caused due to improper permission settings; this application first designs a graphical interface framework with hierarchical permissions, and organically integrates real-time monitoring, fault diagnosis, and remote control functions; then through diversified data visualization technologies, uses intuitive forms such as line charts, bar charts, and pie charts to display the system operation status; then establishes a fault diagnosis support system to automatically generate a professional guide manual containing fault definitions, cause analysis, and repair suggestions; finally, through a permission-based access control mechanism, ensures system security and improves the efficiency of system maintenance.

[0048] In a second aspect, this application provides a medical gas monitoring and intelligent regulation system, including:

[0049] A real-time operation parameter acquisition module, which is used to collect the pressure, flow, and temperature data of the medical gas system to obtain real-time operation parameters;

[0050] A system operation status characteristic acquisition module, which is used to transmit the real-time operation parameters to the cloud data center for data analysis to obtain system operation status characteristics;

[0051] A current system risk level assessment module, which is used to evaluate the current system risk level according to the system operation status characteristics in combination with a pre-established database containing historical fault cases;

[0052] A parameter deviation value calculation module, which is used to compare the system operation status characteristics with preset target parameters and calculate the parameter deviation value;

[0053] A control instruction acquisition module, which is used to determine the system adjustment strategy according to the parameter deviation value and the current system risk level to obtain control instructions.

[0054] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned medical gas monitoring and intelligent adjustment method are implemented.

[0055] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned medical gas monitoring and intelligent adjustment method are implemented.

[0056] In summary, the present application includes at least one of the following beneficial technical effects:

[0057] First, the present application collects real-time data such as pressure, flow rate, and temperature through multiple sensors, transmits this data to the cloud for in-depth analysis, and extracts the characteristics of the system operation state; then, similarity analysis is performed based on a pre-established historical fault case library to realize the assessment of the risk level; then, a deviation value is obtained by comparing with preset target parameters, and finally, a scientific adjustment strategy is formulated according to the deviation value and the risk level, significantly improving the reliability and safety of the system operation;

[0058] In the case of a large number of day surgeries and frequent emergency rescues, if the system cannot accurately distinguish the demand for regular gas and emergency gas, resulting in unreasonable gas allocation and affecting the gas supply quality; first, the present application performs time series decomposition on the real-time operation parameters, innovatively separating the parameter changes into three dimensions: periodic fluctuations, seasonal variations, and random disturbances; then, the dynamic fluctuation law of the parameters is determined through statistical analysis; then, according to the preset medical scenario feature library, a discrimination mechanism for three typical modes of regular gas use, emergency gas use, and equipment maintenance is established; then, accurate identification of the scenario is achieved through matching degree calculation; finally, the accurate characteristics of the system operation state are obtained, improving the adaptability of the scenario;

[0059] First, the present application dynamically selects the pressure stability, flow rate uniformity, and temperature volatility according to the usage mode; then, the scenario matching degree is introduced into the weight calculation process to realize the dynamic adjustment of the weights of the characteristic indicators; finally, through the construction and standardization processing of the state vector, a unified evaluation standard is established to realize the quantification of the system state, and the accuracy of the state evaluation is improved through adaptive weight allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a flowchart of a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application Figure 1 ;

[0061] Figure 2 is a flowchart of step S200 in a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application;

[0062] Figure 3 It is a schematic flowchart of step S250 in a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application;

[0063] Figure 4 It is a schematic flowchart of step S300 in a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application;

[0064] Figure 5 It is a schematic flowchart of step S400 in a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application;

[0065] Figure 6 It is a schematic flowchart of step S500 in a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application;

[0066] Figure 7 It is a schematic flowchart of a medical gas monitoring and intelligent adjustment method according to an embodiment of the present application Figure 2 ;

[0067] Figure 8 It is a schematic diagram of modules of a medical gas monitoring and intelligent adjustment system according to an embodiment of the present application;

[0068] Figure 9 It is an internal structure diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0069] 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 limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above-mentioned", "said", and "this" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations including one or more of the listed items.

[0070] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0071] The following further describes the embodiments of the present application in conjunction with the accompanying drawings of the specification.

[0072] In a first aspect, the present application provides a medical gas monitoring and intelligent adjustment method. Referring to Figure 1 , the method includes the following steps:

[0073] S100. Collect the pressure, flow rate, and temperature data of the medical gas system to obtain real-time operating parameters.

[0074] In this embodiment, the operating data is collected by arranging a sensor network at the key nodes of the medical gas system. The medical gas system includes supply pipelines such as oxygen, nitrogen, and compressed air. High-precision sensors are installed on the main roads, department branches, and terminal gas-using points of each pipeline to achieve real-time monitoring of the system operating parameters.

[0075] Specifically, pressure sensors, flow sensors, and temperature sensors are installed at the key positions of the medical gas system. Among them, the pressure sensors are arranged at the main gas supply pipeline and the branch points of each floor to monitor the pressure state of the pipe network; the flow sensors are installed at the air inlets of each department to record the changes in gas consumption in real time; the temperature sensors are used to monitor the gas temperature inside the pipeline. These sensors transmit the collected data to the nearby data acquisition unit through the industrial bus to form a complete monitoring network.

[0076] S200. Transmit the real-time operating parameters to the cloud data center for data analysis to obtain the system operating state characteristics.

[0077] In this embodiment, an architecture combining edge computing and cloud analysis is adopted to process the data. A local processing unit is set up inside the hospital to perform preliminary processing on the collected data, and then the processed data is uploaded to the cloud for in-depth analysis, improving the data processing efficiency.

[0078] Specifically, the local processing unit first preprocesses the sensor data, and the cloud analysis module combines the pipe network structure model to extract and analyze the system operating characteristics.

[0079] S300. According to the system operating state characteristics, combined with the pre-established database containing historical fault cases, evaluate the current system risk level.

[0080] In this embodiment, the system has pre-established a fault case database for the medical gas system. The database records various fault situations that occurred during the historical operation process, including information such as fault characteristics, type classification, and handling methods, providing a reference basis for risk assessment.

[0081] Specifically, the system evaluates the current operating risk through a feature matching method. The real-time operating features are compared and analyzed with the historical cases, and the risk level is determined according to the similarity degree and fault level. For example, when the system detects that the operating features of a certain area are similar to the historical gas cut-off fault features, a warning signal is sent in a timely manner.

[0082] S400. Based on the comparison between the system operating state characteristics and the preset target parameters, calculate the parameter deviation value.

[0083] In this embodiment, the system pre-sets different target parameters for different departments. Higher control standards are adopted for key departments such as intensive care units and operating rooms, while conventional standards are adopted for ordinary areas.

[0084] Specifically, the system compares the real-time operation parameters with the department target values. By calculating the difference between the actual value and the target value, a standardized deviation index is obtained. For example, when there is a deviation in the air supply pressure in the operating room, the system can timely calculate the degree of deviation from the target value to provide a reference for adjustment.

[0085] S500. Determine the system adjustment strategy according to the parameter deviation value and the current system risk level, and obtain the control instruction.

[0086] In this embodiment, a hierarchical adjustment strategy is adopted to formulate the control plan. According to the combination of the parameter deviation degree and the risk level, the corresponding adjustment measures are selected to ensure the stable operation of the system.

[0087] Specifically, the system pre-sets multi-level strategies of basic adjustment, medium adjustment and emergency adjustment. The appropriate adjustment plan is automatically selected according to the real-time state and the control instruction is generated. For example, when there is an abnormality in the air supply of a certain department, the system can select the appropriate adjustment plan according to the specific situation, such as adjusting the air supply parameters or enabling the standby pipeline, etc.

[0088] In one embodiment, referring to Figure 2 , in step S200, the real-time operation parameters are transmitted to the cloud data center for data analysis to obtain the system operation state characteristics, which specifically include the following steps:

[0089] S210. Perform time series decomposition on the real-time operation parameters to obtain periodic fluctuations, seasonal variations and random disturbance components.

[0090] In this embodiment, a time series analysis method is used to process the operation parameters of the medical gas system. By decomposing the continuously collected data, the change characteristics on different time scales are identified.

[0091] Specifically, the system uses a sliding time window to segment the data to identify hourly periodic fluctuations, daily and monthly seasonal variations, and irregular random disturbances. For example, after decomposing the pressure data of the oxygen supply system in a certain hospital, the gas usage patterns during the day and night, as well as the seasonal variation characteristics during holidays, can be clearly seen.

[0092] S220. Determine the daily fluctuation range and the peak occurrence time period of each operation parameter.

[0093] In this embodiment, the system establishes a dynamic parameter fluctuation range management mechanism. The system calculates the statistical characteristics of the parameters at different time periods according to the historical operation data, and establishes a scientific fluctuation range determination standard.

[0094] Specifically, the system statistically analyzes the variation patterns of various parameters according to time periods, determines the normal fluctuation range and the occurrence pattern of peaks. For example, by analyzing the gas consumption data of the emergency department of a certain hospital, it is found that gas consumption peaks often occur from 9 to 11 am on weekdays, and based on this, a more targeted gas supply strategy is formulated.

[0095] S230. According to the preset types of medical scenarios, identify the usage patterns of real-time operation parameters. The usage patterns include regular gas usage patterns, emergency gas usage patterns, and equipment maintenance patterns.

[0096] In this embodiment, the system presets various typical gas usage patterns for medical scenarios. By analyzing the characteristics of real-time operation parameters, the current gas usage status is classified into the corresponding usage patterns.

[0097] Specifically, the system identifies the current gas usage pattern according to the parameter change characteristics. The regular gas usage pattern is characterized by stable parameter changes; the emergency gas usage pattern has the characteristic of sudden rapid increase; the equipment maintenance pattern shows regular periodic changes. For example, when the system detects a sudden increase in the flow rate of a certain department, it can quickly determine whether it has entered the emergency gas usage pattern.

[0098] S240. Calculate the matching degree between the usage pattern and the fluctuation range of the current time period.

[0099] In this embodiment, the system pre-establishes a pattern matching evaluation system. By calculating the matching degree between the current operation parameters and the characteristics of various usage patterns, an accurate judgment of the system operation status is achieved.

[0100] Specifically, the system conducts a correlation analysis between the real-time parameters and the preset pattern characteristics, and calculates the matching degree score. For example, when the similarity between the gas usage parameters in a certain area and the characteristics of the emergency mode reaches a relatively high level, the system will give priority to responding according to the emergency gas usage mode.

[0101] S250. Based on the matching degree and the usage pattern, obtain the characteristics of the system operation status.

[0102] Specifically, the system comprehensively considers the matching degree score and the type of usage pattern, constructs a characteristic description of the system operation status. Determine the dominant operation mode according to the matching degree score, and combine the specific performance of each parameter to generate a characteristic report of the system operation status. For example, during the morning routine surgery period in the operating area of a certain hospital, the system can accurately identify the regular gas usage pattern and give the corresponding operation status evaluation result.

[0103] In one embodiment, referring to Figure 3 , in step S250, based on the matching degree and the usage pattern, obtaining the characteristics of the system operation status specifically includes the following steps:

[0104] S251. Determine characteristic indicators according to the usage pattern. The characteristic indicators include pressure stability, flow uniformity, and temperature volatility.

[0105] In this embodiment, according to the characteristics of different usage patterns, corresponding characteristic indicators are selected for status evaluation. Under the normal gas usage mode, the system stability is focused on. Under the emergency gas usage mode, the response speed is emphasized. Under the equipment maintenance mode, the system regulation ability is mainly monitored.

[0106] Specifically, the system sets a corresponding combination of characteristic indicators for each usage pattern. The pressure stability reflects the fluctuation of the gas supply pressure. The flow uniformity characterizes the balance of gas usage distribution. The temperature volatility reflects the temperature change characteristics of the system. For example, under the normal gas usage mode in a hospital operating room, the system mainly monitors the pressure stability indicator to ensure the stability of the gas supply pressure during the operation.

[0107] S252. Calculate the weight coefficients of each characteristic indicator based on the matching degree, and use the weight coefficients to perform weighted calculation on the characteristic indicators to obtain a quantization value.

[0108] In this embodiment, a dynamic weight allocation mechanism is adopted to adaptively adjust the importance of each indicator according to the mode matching degree. The higher the matching degree of the mode, the higher the weight of the corresponding characteristic indicator.

[0109] Specifically, the system designs a weight calculation formula through the mode matching degree to perform weighted operations on various characteristic indicators. When the matching degree of a certain usage pattern is high, the characteristic indicators related to this pattern will obtain a larger weight coefficient. For example, under the emergency gas usage mode, the weight coefficient of the flow uniformity will be increased accordingly to ensure the stable supply at each gas usage point.

[0110] S253. Combine the quantization values to construct a system state vector, and perform normalization processing on the system state vector to obtain the system operation state characteristics.

[0111] In this embodiment, the system establishes a multi-dimensional state vector to represent the system operation state. By combining various quantization indicators according to a preset rule, a characteristic vector reflecting the overall state of the system is constructed and normalized to make it comparable.

[0112] Specifically, the system organizes the weighted characteristic indicators into a state vector according to a predetermined format, and uses a normalization method to map each component to a unified interval.

[0113] In one embodiment, referring to Figure 4 , in step S300, according to the system operation state characteristics, combined with a pre-established database containing historical failure cases, evaluate the current system risk level, which specifically includes the following steps:

[0114] S310. Extract the top N fault cases with the highest feature similarity from the historical fault case database.

[0115] In this embodiment, a feature similarity retrieval method is used to screen relevant cases from the historical fault database. The system retrieves fault records with similar features in the historical database according to the current operating state features.

[0116] Specifically, the system uses a multi-dimensional feature matching algorithm to calculate the similarity score and selects several cases with the highest similarity for analysis.

[0117] S320. Calculate the feature distance between the system operating state features and each fault case.

[0118] Specifically, by calculating the distance between the current state and the historical case in the feature space, the similarity degree between the two is quantified.

[0119] S330. Weight the fault cases based on the feature distance to obtain the fault type probability distribution.

[0120] In this embodiment, cases with smaller feature distances are given larger weights, thus playing a more important role in the probability distribution calculation.

[0121] Specifically, the system designs a weight calculation function according to the feature distance and statistically calculates the weighted probabilities of various faults occurring. For example, when an abnormal situation occurs in a gas supply system, historical gas cut-off fault cases with similar feature distances to the current state features will obtain higher weights, and the corresponding fault type probabilities will also increase accordingly.

[0122] S340. Calculate the comprehensive risk index according to the fault type probability distribution and the severity of each fault type.

[0123] Specifically, the system multiplies the fault type probability by the severity level and sums them up to obtain a comprehensive index reflecting the overall risk. For example, when the system detects that a gas supply interruption fault may occur in a certain area, considering the high severity of this type of fault, even if the probability is low, a relatively high risk index will be obtained.

[0124] S350. Map the comprehensive risk index to a preset risk level interval to obtain the current system risk level.

[0125] In this embodiment, the system has pre-set a hierarchical risk assessment standard. According to the numerical range of the risk index, the operating state of the system is divided into different risk levels.

[0126] Specifically, the system has pre-set multiple level intervals such as low risk, medium risk, and high risk, and determines the current risk level through risk index mapping.

[0127] In one embodiment, with reference to Figure 5, in step S400, based on the comparison between the system operation state characteristics and the preset target parameters, a parameter deviation value is calculated, which specifically includes the following steps:

[0128] S410. Obtain the gas use priority and importance level of each department, and establish a department weight matrix.

[0129] In this embodiment, according to the medical task characteristics and the importance of gas use requirements of each department, each department in the hospital is divided into different priority levels to form a differential management strategy among departments.

[0130] Specifically, the system evaluates the importance of gas use for each department and establishes a weight matrix including the priority and importance level. For example, the operating room and the intensive care unit are given the highest priority, while the general ward is set to a lower priority, so as to ensure the gas use requirements of key departments during resource allocation.

[0131] S420. Based on the department weight matrix, calculate the dynamic adjustment coefficient of each operating parameter.

[0132] In this embodiment, a dynamic weight allocation mechanism is adopted to calculate the adjustment coefficient of the operating parameter according to the department weight matrix.

[0133] Specifically, the system designs an adjustment coefficient calculation formula based on the department weight to realize the differential management of parameter control. Among them, αi = Wi × Pi × Ci, where αi is the adjustment coefficient of the i-th department; Wi is the department weight value (between 0 and 1); Pi is the priority coefficient (between 1 and 3, and 3 represents the highest priority); Ci is the department importance correction coefficient (between 1.0 and 1.5).

[0134] S430. Perform parameter normalization processing on the system operation state characteristics, and calculate the deviation between the normalized parameter and its respective target value to obtain the basic deviation value.

[0135] In this embodiment, by performing normalization processing on the operation state characteristics, parameters with different dimensions are made comparable, which is convenient for calculating the deviation from the target value.

[0136] S440. Weight and correct the basic deviation value according to the dynamic adjustment coefficient to obtain the final parameter deviation value.

[0137] In this embodiment, the system performs a weighted operation on the dynamic adjustment coefficient and the basic deviation value to generate a deviation result reflecting the actual control requirement. For example, when the gas supply parameter of the ICU fluctuates, due to its higher adjustment coefficient, the system will give a larger deviation value, indicating that priority adjustment is required.

[0138] In one embodiment, with reference to Figure 6, in step S500, according to the parameter deviation value and the current system risk level, determine the system adjustment strategy to obtain a control instruction, which specifically includes the following steps:

[0139] S510. Construct a decision matrix according to the parameter deviation value and the current system risk level.

[0140] S520. Determine the position of the current system state point in the decision matrix, and select the corresponding adjustment strategy template according to the position of the state point.

[0141] In this embodiment, the system presets a variety of adjustment strategy templates. According to the position of the system state point in the decision matrix, select the adjustment strategy template most suitable for the current situation.

[0142] Specifically, the system configures corresponding strategy templates for different regions of the decision matrix, including types such as stable maintenance, fine-tuning optimization, rapid adjustment, and emergency intervention. For example, when the state point falls in the high deviation-high risk area, the system will select the emergency intervention strategy template and take more radical adjustment measures.

[0143] S530. Generate a specific parameter adjustment plan based on the adjustment strategy template, and convert the parameter adjustment plan into a control instruction.

[0144] In this embodiment, the system has pre-established a conversion mechanism from the strategy template to the specific control instruction. The system generates a detailed adjustment plan according to the selected strategy template and the current operating parameters, and converts it into a control instruction executable by the device.

[0145] Specifically, the system sets specific parameter adjustment targets and adjustment steps based on the strategy template, and then generates a corresponding control instruction sequence. For example, when it is necessary to adjust the gas supply pressure in a certain area, the system will determine the adjustment amplitude and rate according to the template rules, and generate specific control instructions such as valve opening and flow adjustment.

[0146] In one embodiment, referring to Figure 7 , the method further includes the following steps:

[0147] S600. Establish a graphical user interface with hierarchical permissions, and the user interface includes a real-time data visualization module, a fault diagnosis module, and a remote control module.

[0148] In this embodiment, the system has developed a user interaction system based on the B / S architecture. Through hierarchical permission management, different functional modules and data access permissions are provided for users in different positions to achieve refined management of system operation.

[0149] Specifically, the system is designed with a three - level permission architecture, including operator level, administrator level, and system level. For example, operator - level users can view real - time data and basic fault information, administrator - level users can perform parameter settings and fault handling, while system - level users have all control permissions, including advanced functions such as remote debugging and system configuration.

[0150] S700. Display the system operation status characteristics in the form of trend charts, which include line charts of pressure changes, bar charts of flow distribution, and pie charts of temperature distribution.

[0151] In this embodiment, the system converts the operation status characteristics into intuitive graphical displays to help users quickly grasp the system operation trend and abnormal situations.

[0152] Specifically, the system selects suitable graphical expression methods according to different parameter characteristics. For example, the pressure change is displayed using a line chart with real - time updates to show the time trend, the flow distribution of each department is shown using a dynamic bar chart to display the usage comparison, and the temperature distribution is reflected by a pie chart to show the temperature proportion of different regions.

[0153] S800. Call the fault diagnosis library according to the current system risk level and generate a maintenance guide manual containing fault definitions, cause analysis, and repair suggestions.

[0154] In this embodiment, corresponding fault cases and treatment plans are automatically matched according to the current risk level to provide professional technical guidance for maintenance personnel.

[0155] Specifically, the system is designed with a hierarchical fault diagnosis manual generation mechanism. For example, when the system detects abnormal gas supply pressure in a certain area, it will automatically generate a maintenance guide document containing the definition description of pressure abnormality, possible cause analysis, and specific repair steps, and recommend appropriate treatment plans according to the actual situation.

[0156] S900. Connect the user interface to the remote monitoring terminal and open corresponding data access and control based on the user permission level.

[0157] In this embodiment, the system allows authorized users to monitor the system operation status in real - time through mobile devices via a secure data transmission channel and perform corresponding control operations according to their permissions.

[0158] Specifically, the system develops access interfaces adapted to different terminal devices. For example, maintenance personnel can view the operation data of the areas they are responsible for and receive fault alarm information through the mobile phone APP, while management personnel can perform remote parameter adjustment and system configuration through the tablet computer.

[0159] It should be understood that the sequence numbers of the steps in the above embodiments do not indicate the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0160] In a second aspect, the present application provides a medical gas monitoring and intelligent regulation system. The medical gas monitoring and intelligent regulation system of the present application will be described below in combination with the above-mentioned medical gas monitoring and intelligent regulation method.

[0161] Referring to Figure 8 , a medical gas monitoring and intelligent regulation system includes:

[0162] A real-time operating parameter acquisition module, configured to acquire pressure, flow rate, and temperature data of a medical gas system to obtain real-time operating parameters;

[0163] A system operating state feature acquisition module, configured to transmit the real-time operating parameters to a cloud data center for data analysis to obtain system operating state features;

[0164] A current system risk level assessment module, configured to evaluate the current system risk level according to the system operating state features and in combination with a pre-established database containing historical failure cases;

[0165] A parameter deviation value calculation module, configured to calculate a parameter deviation value based on a comparison between the system operating state features and preset target parameters;

[0166] A control instruction acquisition module, configured to determine a system regulation strategy according to the parameter deviation value and the current system risk level to obtain a control instruction.

[0167] In one embodiment, the system operating state feature acquisition module includes:

[0168] A time series decomposition unit, configured to perform time series decomposition on the real-time operating parameters to obtain periodic fluctuations, seasonal variations, and random disturbance components;

[0169] A fluctuation range determination unit, configured to determine the daily fluctuation range and peak occurrence period of each operating parameter;

[0170] A usage pattern recognition unit, configured to recognize the usage pattern of the real-time operating parameters according to a preset medical scenario type, and the usage pattern includes a regular gas usage pattern, an emergency gas usage pattern, and an equipment maintenance pattern;

[0171] A matching degree calculation unit, configured to calculate the matching degree between the usage pattern and the fluctuation range of the current period;

[0172] A state feature acquisition unit, configured to obtain system operating state features based on the matching degree and the usage pattern.

[0173] In one embodiment, the status feature acquisition unit includes:

[0174] A feature index determination component, configured to determine feature indexes according to the usage pattern, where the feature indexes include pressure stability, flow uniformity, and temperature volatility;

[0175] A weight calculation component, configured to calculate the weight coefficients of each feature index based on the matching degree, and perform weighted calculation on the feature indexes by using the weight coefficients to obtain a quantization value;

[0176] A status vector processing component, configured to combine the quantization values to construct a system status vector, and perform normalization processing on the system status vector to obtain the system operation status features.

[0177] In one embodiment, the current system risk level assessment module includes:

[0178] A failure case extraction unit, configured to extract the top N failure cases with the highest feature similarity from the historical failure case database;

[0179] A feature distance calculation unit, configured to calculate the feature distance between the system operation status features and each failure case;

[0180] A probability distribution acquisition unit, configured to weight the failure cases based on the feature distance to obtain a failure type probability distribution;

[0181] A risk index calculation unit, configured to calculate a comprehensive risk index according to the failure type probability distribution and the severity of each type of failure;

[0182] A risk level determination unit, configured to map the comprehensive risk index to a preset risk level interval to obtain the current system risk level.

[0183] In one embodiment, the parameter deviation value calculation module includes:

[0184] A weight matrix establishment unit, configured to obtain the gas usage priorities and importance levels of each department, and establish a department weight matrix;

[0185] An adjustment coefficient calculation unit, configured to calculate the dynamic adjustment coefficients of each operation parameter based on the department weight matrix;

[0186] A basic deviation calculation unit, configured to perform parameter normalization processing on the system operation status features, and calculate the deviation between the normalized parameters and their respective target values to obtain a basic deviation value;

[0187] A weighted correction unit, configured to perform weighted correction on the basic deviation value according to the dynamic adjustment coefficient to obtain the final parameter deviation value.

[0188] In one embodiment, the control instruction acquisition module includes:

[0189] A decision matrix construction unit, configured to construct a decision matrix according to the parameter deviation value and the current system risk level;

[0190] A state point positioning unit, configured to determine the position of the current system state point in the decision matrix and select a corresponding adjustment strategy template according to the state point position;

[0191] An instruction generation unit, configured to generate a specific parameter adjustment plan based on the adjustment strategy template and convert the parameter adjustment plan into a control instruction.

[0192] In one embodiment, it further includes:

[0193] A user interface module, configured to establish a graphical user interface with hierarchical permissions. The user interface includes a real-time data visualization module, a fault diagnosis module, and a remote control module;

[0194] A data display module, configured to display the system operation state characteristics in the form of a trend chart. The trend chart includes a pressure change line chart, a flow distribution bar chart, and a temperature distribution pie chart;

[0195] A fault diagnosis module, configured to call a fault diagnosis library according to the current system risk level and generate a maintenance guide manual including fault definition, cause analysis, and repair suggestions;

[0196] A remote monitoring module, configured to connect the user interface to a remote monitoring terminal and open corresponding data access and control based on the user permission level.

[0197] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as Figure 9 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, it implements a medical gas monitoring and intelligent adjustment method.

[0198] Those skilled in the art can understand, Figure 9The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the electronic device to which the solution of this application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0199] In one embodiment, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0200] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The above 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 above method embodiments. Among them, any reference to the memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0201] The above are all the preferred embodiments of this application. Without limiting the protection scope of this application accordingly, therefore: Any equivalent changes made according to the structure, shape, and principle of this application should be covered within the protection scope of this application.

Claims

1. A medical gas monitoring and intelligent regulation method, characterized in that: The steps include: Collect pressure, flow and temperature data of medical gas system to obtain real-time operating parameters; Transmitting the real-time operating parameters to a cloud data center for data analysis to obtain system operating status characteristics; According to the system operation status characteristics, combined with a pre-established database containing historical failure cases, the current system risk level is evaluated; Based on the comparison between the system operation state characteristics and the preset target parameters, a parameter deviation value is calculated; Determine a system adjustment strategy based on the parameter deviation value and the current system risk level, and obtain a control instruction; The real-time operating parameters are transmitted to a cloud data center for data analysis to obtain system operating status characteristics, which specifically includes the following steps: Performing time series decomposition on the real-time operating parameters to obtain periodic fluctuations, seasonal changes and random disturbance components; Determine the daily fluctuation range and peak period of each operating parameter; According to a preset medical scenario type, identifying a usage mode of the real-time operating parameter, the usage mode including a conventional gas usage mode, an emergency gas usage mode, and an equipment maintenance mode; Calculate the matching degree between the usage pattern and the fluctuation range of the current time period; Based on the matching degree and the usage mode, a system operation status feature is obtained.

2. The medical gas monitoring and intelligent regulation method according to claim 1, characterized in that: Based on the matching degree and the usage mode, a system operation status feature is obtained, which specifically includes the following steps: Determining characteristic indicators according to the usage mode, wherein the characteristic indicators include pressure stability, flow uniformity and temperature fluctuation rate; Calculating a weight coefficient of each characteristic index based on the matching degree, and performing weighted calculation on the characteristic index using the weight coefficient to obtain a quantized value; The quantized values ​​are combined to construct a system state vector, and the system state vector is standardized to obtain a system operation state feature.

3. The medical gas monitoring and intelligent regulation method according to claim 1, characterized in that: According to the system operation status characteristics, combined with a pre-established database containing historical fault cases, the current system risk level is evaluated, specifically including the following steps: Extracting the top N fault cases with the highest feature similarity from the historical fault case database; Calculating the characteristic distance between the system operation state characteristic and each fault case; Weighting the fault cases based on the characteristic distance to obtain a probability distribution of fault types; Calculate a comprehensive risk index based on the probability distribution of the fault types and the severity of each type of fault; The comprehensive risk index is mapped to a preset risk level interval to obtain the current system risk level.

4. The medical gas monitoring and intelligent regulation method according to claim 1, characterized in that: Based on the comparison between the system operation state characteristics and the preset target parameters, the parameter deviation value is calculated, which specifically includes the following steps: Obtain the gas usage priority and importance level of each department and establish a department weight matrix; Based on the department weight matrix, the dynamic adjustment coefficient of each operating parameter is calculated; Perform parameter normalization on the system operation status characteristics, calculate the deviation between the normalized parameters and their respective target values, and obtain the basic deviation value; The basic deviation value is weightedly corrected according to the dynamic adjustment coefficient to obtain a final parameter deviation value.

5. The medical gas monitoring and intelligent regulation method according to claim 4, characterized in that: According to the parameter deviation value and the current system risk level, a system adjustment strategy is determined to obtain a control instruction, which specifically includes the following steps: Constructing a decision matrix according to the parameter deviation value and the current system risk level; Determine the current system state point position in the decision matrix, and select a corresponding adjustment strategy template according to the state point position; A specific parameter adjustment scheme is generated based on the adjustment strategy template, and the parameter adjustment scheme is converted into a control instruction.

6. The medical gas monitoring and intelligent regulation method according to claim 1, characterized in that: The method further comprises the steps of: Establishing a hierarchical authority graphical user interface, the user interface including a real-time data visualization module, a fault diagnosis module and a remote control module; Displaying the system operation status characteristics in the form of a trend graph, wherein the trend graph includes a pressure change line graph, a flow distribution bar graph, and a temperature distribution pie chart; Invoke a fault diagnosis library according to the current system risk level to generate a maintenance guide including fault definition, cause analysis and repair suggestions; The user interface is connected to a remote monitoring terminal, and corresponding data access and control are enabled based on user authority levels.

7. A medical gas monitoring and intelligent regulation system, characterized in that: include: Real-time operation parameter acquisition module, used to collect pressure, flow and temperature data of the medical gas system to obtain real-time operation parameters; A system operation status feature acquisition module is used to transmit the real-time operation parameters to a cloud data center for data analysis to obtain system operation status features; A current system risk level assessment module, used to assess the current system risk level based on the system operation status characteristics and in combination with a pre-established database containing historical fault cases; A parameter deviation value calculation module is used to compare the system operation state characteristics with the preset target parameters to calculate the parameter deviation value; A control instruction acquisition module, used to determine the system adjustment strategy and obtain the control instruction according to the parameter deviation value and the current system risk level; The system operation status feature acquisition module includes: The time series decomposition unit is used to perform time series decomposition on real-time operation parameters to obtain periodic fluctuations, seasonal changes and random disturbance components; A fluctuation range determination unit, used to determine the daily fluctuation range and peak occurrence period of each operating parameter; A usage mode recognition unit is used to identify the usage mode of the real-time operating parameters according to the preset medical scenario type, and the usage mode includes a conventional gas usage mode, an emergency gas usage mode and an equipment maintenance mode; A matching degree calculation unit, used to calculate the matching degree between the usage pattern and the fluctuation range of the current time period; The state feature acquisition unit is used to obtain the system operation state feature based on the matching degree and the usage mode.

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 the processor implements the steps of the medical gas monitoring and intelligent regulation method described in any one of claims 1 to 6 when executing the computer program.

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 medical gas monitoring and intelligent regulation method described in any one of claims 1-6 are implemented.

Images