Medical gas remote monitoring system

Abstract

The invention discloses a medical gas remote monitoring system, relates to the technical field of gas detection, and solves the technical problem that faults of different pipelines are difficult to detect respectively according to characteristics and requirements of different pipeline levels. Comprising a data acquisition module which is used for dividing all gas supply pipelines into a gas source pipeline, a first-stage branch pipeline, a second-stage branch pipeline and a third-stage branch pipeline, and processing data acquired by a gas pressure sensor and a gas flow sensor of each pipeline to obtain characteristic spectrum data of each sensor; the template matching module is used for detecting the characteristic frequency spectrum data of the three-stage branch pipeline and the gas supply gas source through a template matching algorithm; when the data of the third-level pipeline is abnormal, the data can be found more easily and corrected in a targeted mode, meanwhile, detection of the gas source pipeline, the first-level branch pipeline and the second-level branch pipeline is not affected, and the fault tolerance and stability of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the field of gas detection, relates to medical gas detection technology, and specifically is a medical gas remote monitoring system. Background Art

[0002] With the modernization and digital development of medical facilities, medical gas equipment plays a crucial role in the medical process. The traditional monitoring method of gas-using equipment mainly relies on manual inspection and regular maintenance, which has problems such as untimely monitoring and low accuracy. With the application of remote monitoring systems, remote real-time monitoring and management of gas-using equipment can be realized, abnormal situations can be quickly captured, the risk of faults can be pre-warned in advance, and the safety, reliability, and efficiency of gas-using equipment in medical facilities can be improved, thereby providing more reliable technical support for medical safety. A medical gas remote monitoring system is a system that can monitor the operating status and gas supply quality of various gas-using equipment in medical facilities in real time and manage them remotely. By using sensors to collect the operating data of gas-using equipment in real time, using network communication technology to transmit the data to a remote monitoring center, and combining data analysis and processing technology, the operating status of the gas system can be monitored, analyzed, and warned.

[0003] Common medical gas remote monitoring systems usually monitor the flow rate of all pipelines, and only judge pipeline leakage faults by comparing flow rates. It is difficult to optimize and adjust the neural network model individually according to the characteristics and requirements of different pipeline levels, making the model more suitable for the prediction needs of each type of pipeline. When the data of the end pipeline is abnormal, it will affect the detection of other pipelines. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention provides a medical gas remote monitoring system, which is used to solve the technical problem that it is difficult to optimize and adjust the neural network model individually according to the characteristics and requirements of different pipeline levels, making the model more suitable for the prediction needs of each type of pipeline. When the data of the end pipeline is abnormal, it will affect the detection of other pipelines.

[0005] To solve the above problems, the first aspect of the present invention provides a medical gas remote monitoring system, including:

[0006] A data acquisition module: used to divide all gas supply pipelines into gas source pipelines, primary branch pipelines, secondary branch pipelines, and tertiary branch pipelines, and process the data collected by the gas pressure sensors and gas flow sensors of each pipeline to obtain the characteristic spectrum data of each sensor;

[0007] Template matching module: It is used to detect the characteristic spectrum data of the three - level branch pipeline and the gas supply source through the template matching algorithm, and transmit the fault signal to the monitoring and alarm module when a fault occurs in the three - level branch pipeline or the gas supply source;

[0008] Historical data acquisition module: Obtain the historical data of the gas pressure and gas flow of the gas source pipeline, the first - level branch pipeline, the second - level branch pipeline, and the third - level branch pipeline when there is a leak and when there is no leak, and screen the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in use;

[0009] Model construction module: It is used to train neural network models for detecting the gas source pipeline, the first - level branch pipeline, and the second - level branch pipeline respectively according to the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are screened by the historical data acquisition module;

[0010] Leakage monitoring module: It is used to obtain the data real - time acquired by the data acquisition module, input the acquired data into the model construction module to detect whether the pipeline is in normal use. Among them, the number of non - zero gas flow data of the third - level branch pipeline is the number of gas supply points in use;

[0011] Evaluation module: It is used to evaluate the leakage risk coefficients of the gas source pipeline, the first - level branch pipeline, and the second - level branch pipeline according to the corresponding characteristic spectrum data of the gas pressure and gas flow data of the gas source pipeline, the first - level branch pipeline, the second - level branch pipeline, and the third - level branch pipeline;

[0012] Monitoring and alarm module: It is used to alarm the gas source pipeline, the first - level branch pipeline, and the second - level branch pipeline detected as not being in normal use by the leakage monitoring module, alarm the fault signal of the template matching module, and display the evaluation data of the evaluation module.

[0013] As a further solution of the present invention: The data acquisition module includes:

[0014] Pipeline division unit: It is used to divide all the pipelines connected to the gas supply source of the hospital. The pipeline connected to the gas supply source of the hospital is set as the gas source pipeline; Divide each area in the hospital that needs to use medical gas into partitions according to departments, and divide each department partition into different gas supply point groups according to the location area of the medical gas supply points. The pipeline leading from the gas source pipeline to each department partition is the first - level branch pipeline, the pipeline leading from the first - level branch pipeline to each gas supply point group within each department partition is the second - level branch pipeline, and the pipeline leading from the second - level branch pipeline to each gas supply point within the gas supply point group is the third - level branch pipeline;

[0015] Pipeline monitoring unit: Pressure sensors and gas flow sensors are installed in the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline to monitor the gas pressure and gas flow in each pipeline in real time;

[0016] Gas source detection unit: An inclination sensor and a gas purity sensor are installed in the electrolysis chamber and the gas storage chamber of the medical electronic atomization mechanism of the gas supply source to monitor the inclination angle of the device and the gas purity;

[0017] Data processing unit: It is used to process the data collected by each sensor, extract the signal sequence, and perform power spectrum analysis to obtain the characteristic spectrum data of each sensor.

[0018] As a further solution of the present invention: The template matching module detects the characteristic spectrum data of the tertiary branch pipeline and the gas supply source through the template matching algorithm. When a fault occurs in the tertiary branch pipeline or the gas supply source, the fault signal is transmitted to the monitoring and alarm module, including the following steps:

[0019] For the tertiary branch pipeline, apply the template matching algorithm to match the characteristic spectrum information corresponding to the gas pressure and gas flow of the gas supply point in the usage state of the corresponding tertiary branch pipeline with the template spectrum of the preset usage state to determine whether there is a leak in the tertiary branch pipeline;

[0020] For the gas supply source, by matching the characteristic spectrum information corresponding to the inclination angle and gas purity data of the electrolysis chamber and the gas storage chamber with the preset template spectrum, to determine whether the electrolysis chamber and the gas storage chamber are in normal use;

[0021] When both the tertiary branch pipeline and the gas supply source are in normal use, then detect other pipelines through the leak monitoring module. When the gas supply source is not in normal use, it is determined that the gas supply source has a fault, and the fault signal is transmitted to the monitoring and alarm module;

[0022] If the tertiary branch pipeline is not in normal use, generate a fault message with the corresponding tertiary branch pipeline number, and transmit the fault signal to the monitoring and alarm module for alarm.

[0023] As a further solution of the present invention: Screen the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in the usage state, including the following steps:

[0024] Screen the gas pressure and gas flow data of the tertiary branch pipeline corresponding to the gas supply point when each gas supply point is in the usage state and not in the usage state in the historical data;

[0025] The gas pressure and gas flow data of the secondary branch pipeline when different numbers of gas supply points in the gas supply point grouping are in the usage state;

[0026] When the gas supply points with different numbers in the department partition are in the use state, the gas pressure and gas flow data of the primary branch pipelines;

[0027] Among all the gas supply points supplied by the gas supply source, when the gas supply points with different numbers are in the use state, the gas pressure and gas flow data of the gas source pipeline.

[0028] As a further solution of the present invention: The model construction module trains neural network models for detecting the gas source pipeline, the primary branch pipeline, and the secondary branch pipeline, including the following steps:

[0029] Establish a neural network model for detecting the secondary branch pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the secondary branch pipeline, and the number of gas supply points in the use state in the gas supply point grouping as inputs, train the neural network model for detecting the secondary branch pipeline;

[0030] Establish a neural network model for detecting the primary branch pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the primary branch pipeline, and the number of gas supply points in the use state in the department partition as inputs, train the neural network model for detecting the primary branch pipeline;

[0031] Establish a neural network model for detecting the gas source pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the gas source pipeline, and the number of gas supply points in the use state among the gas supply points supplied by the gas supply source as inputs, train the neural network model for detecting the gas source pipeline;

[0032] Among them, the number of gas supply points in the use state in the gas supply point grouping is the number of pipelines with non-zero flow in the tertiary branch pipelines corresponding to the gas supply points.

[0033] As a further solution of the present invention: The leakage monitoring module inputs the collected data into the model construction module to detect whether the pipeline is in normal use, including the following steps:

[0034] The gas pressure and gas flow data of the gas source pipeline, the primary branch pipeline, the secondary branch pipeline, and the tertiary branch pipeline obtained in real time by the data acquisition module are processed by the data processing unit to obtain the real-time characteristic spectrum data of the gas pressure and gas flow data; count the number of non-zero gas flow data in the tertiary branch pipeline as the number of gas supply points in the use state; input the obtained real-time characteristic spectrum data of the gas pressure and gas flow data, and the number of gas supply points in the use state corresponding to the tertiary branch pipeline, into the model construction module to detect whether the pipeline is in normal use.

[0035] As a further solution of the present invention: The evaluation module evaluates the leakage risk coefficients of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline, including the following steps:

[0036] If within a preset evaluation interval, when the leakage monitoring module detects that the gas source pipeline, the first-level branch pipeline, the second-level branch pipeline, and the third-level branch pipeline are all in normal use, filter the gas pressure and gas flow data during the time period when the gas flow data fluctuations of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline are greater than the preset threshold, and use them as the risk detection data for the risk period;

[0037] According to the risk detection data of the risk period of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline screened, calculate the leakage risk coefficients of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline respectively;

[0038] For the pipeline whose leakage risk coefficient exceeds the preset threshold, send the pipeline type and the gas pressure and gas flow data of the pipeline to the monitoring and alarm module;

[0039] Among them, for the first-level branch pipeline and the second-level branch pipeline, send the department partition where the pipeline is located and the gas supply point grouping data to the monitoring and alarm module.

[0040] As a further solution of the present invention: Calculate the leakage risk coefficient of the second-level branch pipeline through the following formula:

[0041]

[0042] Among them, N2 is the leakage risk coefficient of the second-level branch pipeline, P max is the maximum pressure value during the risk period of the second-level branch pipeline, P min is the minimum pressure value during the risk period of the second-level branch pipeline, q i is the total flow of the i-th third-level branch pipeline during the risk period in the gas supply point grouping where the second-level branch pipeline is located; Q j is the total flow of the j-th second-level branch pipeline during the risk period in the department partition where the first-level branch pipeline is located, i ∈ (1, 2,, i,, n), and n is the total number of gas supply points in the gas supply point grouping.

[0043] As a further solution of the present invention: Calculate the leakage risk coefficient of the first-level branch pipeline through the following formula:

[0044]

[0045] Among them, N1 is the leakage risk coefficient of the first-level branch pipeline, R max is the maximum pressure value during the risk period of the first-level branch pipeline, R min is the minimum pressure value during the risk period of the first-level branch pipeline, G KIn the department partition connected by the gas source pipeline, the total flow of the k-th primary branch pipeline during the risk period, j ∈ (1, 2,..., j,..., m), where m is the total number of gas supply point groups in the department partition.

[0046] As a further solution of the present invention: The leakage risk coefficient of the gas source pipeline is calculated by the following formula:

[0047]

[0048] Wherein, N1 is the leakage risk coefficient of the gas source pipeline, D max is the maximum pressure of the gas source pipeline during the risk period, D min is the minimum pressure of the gas source pipeline during the risk period, G K is the total flow of the k-th primary branch pipeline in the department partition connected by the gas source pipeline during the risk period; F is the total flow of the gas source pipeline during the risk period, k ∈ (1, 2,..., j,..., w), where w is the total number of department partitions in the gas supply source.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] When the model construction module of the present invention is based on the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are screened by the historical data collection module, neural network models for detecting the gas source pipeline, primary branch pipeline, and secondary branch pipeline are trained respectively; it is convenient to train the neural network model for each pipeline level separately, making the model more focused on the characteristics and data rules of each type of pipeline, improving the accuracy of model prediction; training the model with the data of different pipeline levels separately reduces the model complexity and improves the calculation efficiency. According to the characteristics and requirements of different pipeline levels, the neural network model is optimized and adjusted individually, making the model more suitable for the prediction needs of each type of pipeline. Since the model is trained specifically for each pipeline level, when the data of the tertiary pipeline is abnormal, it can be more easily discovered and corrected accordingly, and at the same time, it will not affect the detection of the gas source pipeline, primary branch pipeline, and secondary branch pipeline, improving the fault tolerance and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0052] Figure 1 It is a schematic diagram of the system framework of the present invention;

[0053] Figure 2Schematic diagram of the framework of the data acquisition module of the present invention Specific embodiments

[0054] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0055] Please refer to Figure 1 - Figure 2 , an embodiment of the first aspect of the present invention provides a medical gas remote monitoring system, including:

[0056] Data acquisition module: used to divide all gas supply pipelines into gas source pipelines, primary branch pipelines, secondary branch pipelines and tertiary branch pipelines, and process the data collected by the gas pressure sensors and gas flow sensors of each pipeline to obtain the characteristic spectrum data of each sensor;

[0057] Template matching module: used to detect the characteristic spectrum data of the tertiary branch pipeline and the gas supply source through the template matching algorithm, and transmit the fault signal to the monitoring and alarm module when a fault occurs in the tertiary branch pipeline or the gas supply source;

[0058] Historical data acquisition module: obtain the historical data of the gas pressure and gas flow of the pipeline when the gas source pipeline, primary branch pipeline, secondary branch pipeline and tertiary branch pipeline have leaks and no leaks, and screen the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in use;

[0059] Model construction module: used to train neural network models for detecting gas source pipelines, primary branch pipelines and secondary branch pipelines respectively according to the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are screened by the historical data acquisition module;

[0060] Leakage monitoring module: used to obtain the data obtained in real time by the data acquisition module, and input the collected data into the model construction module to detect whether the pipeline is in normal use. Among them, the number of non-zero gas flow data of the tertiary branch pipeline is the number of gas supply points in use;

[0061] Evaluation module: used to evaluate the leakage risk coefficients of the gas source pipeline, primary branch pipeline and secondary branch pipeline according to the corresponding characteristic spectrum data of the gas pressure and gas flow data of the gas source pipeline, primary branch pipeline, secondary branch pipeline and tertiary branch pipeline;

[0062] Monitoring and alarming module: used to alarm the abnormal use of gas source pipelines, primary branch pipelines, and secondary branch pipelines detected by the leakage monitoring module, alarm the fault signals of the template matching module, and display the evaluation data of the evaluation module.

[0063] Specifically, in this embodiment, the pipeline division module divides all pipelines connected to the hospital's gas supply source, and divides all gas supply pipelines into gas source pipelines, primary branch pipelines, secondary branch pipelines, and tertiary branch pipelines; the historical data acquisition module obtains the historical data of gas pressure and gas flow of the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline when leakage occurs and does not occur, and filters the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in use; the model construction module trains neural network models for detecting gas source pipelines, primary branch pipelines, and secondary branch pipelines respectively according to the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are selected by the historical data acquisition module; it is convenient to train neural network models for each pipeline level respectively, making the model more focused on the characteristics and data rules of each type of pipeline, and improving the accuracy of model prediction; training the model with data of different pipeline levels respectively reduces the model complexity and improves the calculation efficiency. According to the characteristics and requirements of different pipeline levels, the neural network models are optimized and adjusted individually to make the model more suitable for the prediction needs of each type of pipeline. Since the model is trained specifically for each pipeline level, when the data of the tertiary pipeline is abnormal, it can be more easily detected and corrected accordingly, and at the same time, it will not affect the detection of gas source pipelines, primary branch pipelines, and secondary branch pipelines, improving the fault tolerance and stability of the system.

[0064] In one embodiment of the present invention, the data acquisition module includes:

[0065] Pipeline division unit: used to divide all pipelines connected to the hospital's gas supply source, and the pipelines connected to the hospital's gas supply source are set as gas source pipelines; each area in the hospital that needs to use medical gas is divided into sections according to departments, and each department section is divided into different gas supply point groups according to the location area of the medical gas supply points. The pipelines leading from the gas source pipeline to each department section are primary branch pipelines, and the pipelines leading from the primary branch pipelines to each gas supply point group within each department section are secondary branch pipelines, and the pipelines leading from the secondary branch pipelines to each gas supply point within the gas supply point group are tertiary branch pipelines;

[0066] Pipeline monitoring unit: Install pressure sensors and gas flow sensors on the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline, and are used to monitor the gas pressure and gas flow of each pipeline in real time;

[0067] Gas source detection unit: An inclination sensor and a gas purity sensor are installed in the electrolysis chamber and the gas storage chamber of the medical electronic atomization mechanism of the gas supply source to monitor the inclination angle and gas purity of the device;

[0068] Data processing unit: It is used to process the data collected by each sensor, extract the signal sequence, and perform power spectrum analysis to obtain the characteristic spectrum data of each sensor.

[0069] In one embodiment of the present invention, the template matching module detects the characteristic spectrum data of the three-stage branch pipeline and the gas supply source through the template matching algorithm. When a failure occurs in the three-stage branch pipeline or the gas supply source, a failure signal is transmitted to the monitoring and alarm module, including the following steps:

[0070] For the three-stage branch pipeline, applying the template matching algorithm, match the characteristic spectrum information of the gas pressure and gas flow corresponding to the usage status of the gas supply point corresponding to the three-stage branch pipeline obtained with the template spectrum of the preset usage status to determine whether there is a leak in the three-stage branch pipeline;

[0071] For the gas supply source, by matching the characteristic spectrum information of the inclination angle and gas purity data of the electrolysis chamber and the gas storage chamber obtained with the preset template spectrum, to determine whether the electrolysis chamber and the gas storage chamber are in normal use;

[0072] When both the three-stage branch pipeline and the gas supply source are in normal use, then other pipelines are detected through the leak monitoring module. When the gas supply source is not in normal use, it is determined that the gas supply source has a failure, and the failure signal is transmitted to the monitoring and alarm module;

[0073] If the three-stage branch pipeline is not in normal use, generate a failure message with the corresponding three-stage branch pipeline number, and transmit the failure signal to the monitoring and alarm module for alarm.

[0074] Specifically, in this embodiment, by first detecting the three-stage branch pipeline and the gas supply source, it is avoided that the failures of the three-stage branch pipeline and the gas supply source affect the detection of the hierarchical pipeline. At the same time, the three-stage branch pipeline and the gas supply source are convenient for failure detection. After eliminating the failures of the three-stage branch pipeline and the gas supply source, the gas source pipeline, the first-stage branch pipeline, and the second-stage branch pipeline can be detected more scientifically.

[0075] In one embodiment of the present invention, screening the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in the usage state includes the following steps:

[0076] Screen the gas pressure and gas flow data of the three-stage branch pipeline corresponding to the gas supply point when each gas supply point is in the usage state and not in the usage state in the historical data;

[0077] The gas pressure and gas flow data of the secondary branch pipelines when different numbers of gas supply points in the gas supply point grouping are in the use state;

[0078] The gas pressure and gas flow data of the primary branch pipelines when different numbers of gas supply points in the department partition are in the use state;

[0079] The gas pressure and gas flow data of the gas source pipelines when different numbers of gas supply points among all the gas supply points supplied by the gas supply source are in the use state.

[0080] In one embodiment of the present invention, the model construction module trains a neural network model for detecting the gas source pipeline, the primary branch pipeline, and the secondary branch pipeline, including the following steps:

[0081] Establish a neural network model for detecting the secondary branch pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the secondary branch pipeline, and the number of gas supply points in the gas supply point grouping in the use state as inputs, train the neural network model for detecting the secondary branch pipeline;

[0082] Establish a neural network model for detecting the primary branch pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the primary branch pipeline, and the number of gas supply points in the department partition in the use state as inputs, train the neural network model for detecting the primary branch pipeline;

[0083] Establish a neural network model for detecting the gas source pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the gas source pipeline, and the number of gas supply points among the gas supply points supplied by the gas supply source in the use state as inputs, train the neural network model for detecting the gas source pipeline;

[0084] Wherein, the number of gas supply points in the gas supply point grouping in the use state is the number of pipelines with non-zero flow in the tertiary branch pipelines corresponding to the gas supply points.

[0085] In one embodiment of the present invention, the leakage monitoring module inputs the collected data into the model construction module to detect whether the pipeline is in normal use, including the following steps:

[0086] The gas pressure and gas flow data of the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline obtained in real time by the data acquisition module are processed by the data processing unit to obtain the real-time characteristic spectrum data of the gas pressure and gas flow data; count the number of non-zero gas flow data of the tertiary branch pipeline as the number of gas supply points in the use state; input the obtained real-time characteristic spectrum data of the gas pressure and gas flow data, and the number of gas supply points corresponding to the tertiary branch pipeline in the use state into the model construction module to detect whether the pipeline is in normal use.

[0087] In one embodiment of the present invention, the evaluation module evaluates the leakage risk coefficients of the gas source pipeline, primary branch pipeline, and secondary branch pipeline, including the following steps:

[0088] If the leakage monitoring module detects that the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline are all in normal use within the preset evaluation interval time, screen the gas pressure and gas flow data during the time period when the gas flow data fluctuations of the gas source pipeline, primary branch pipeline, and secondary branch pipeline are greater than the preset threshold as the risk detection data for the risk period;

[0089] According to the screened risk detection data of the risk period of the gas source pipeline, primary branch pipeline, and secondary branch pipeline, calculate the leakage risk coefficients of the gas source pipeline, primary branch pipeline, and secondary branch pipeline respectively;

[0090] For the pipeline with the leakage risk coefficient exceeding the preset threshold, send the pipeline type and the gas pressure and gas flow data of the pipeline to the monitoring and alarm module;

[0091] Among them, for the primary branch pipeline and secondary branch pipeline, send the department partition and gas supply point grouping data where the pipeline is located to the monitoring and alarm module.

[0092] In one embodiment of the present invention, the leakage risk coefficient of the secondary branch pipeline is calculated by the following formula:

[0093]

[0094] Among them, N2 is the leakage risk coefficient of the secondary branch pipeline, P max is the maximum pressure value of the secondary branch pipeline during the risk period, P min is the minimum pressure value of the secondary branch pipeline during the risk period, q i is the total flow of the i-th tertiary branch pipeline during the risk period in the gas supply point grouping where the secondary branch pipeline is located; Q jFor the j-th secondary branch pipeline in the department partition where the primary branch pipeline is located, the total flow rate during the risk period, i ∈ (1, 2,..., i,..., n), and n is the total number of gas supply points in the gas supply point grouping.

[0095] Specifically, since the use of the terminal pipeline will cause pressure fluctuations in the pipeline, and at the same time, when the pipeline flow rate surges, it takes time for the gas to flow to the next-level pipeline, there will be a small error between the flow rate of one type of pipeline and the total flow rate of the next-level pipeline. At this time, the pipeline pressure will also fluctuate. Through the above formula, the influence of the increased number of used terminal pipelines on the pressure can be considered, and the leakage risk coefficient of the pipeline can be calculated through the fluctuation of the flow rate. In this embodiment, through a large amount of data statistics, for pipelines with a leakage risk coefficient exceeding the preset threshold, the pipeline type, gas pressure, and gas flow rate data of the pipeline are sent to the monitoring and alarm module. The preset threshold N2 is 0.2. When N2 is greater than 0.2, the probability of a small leakage in the pipeline increases.

[0096] In one embodiment of the present invention, the leakage risk coefficient of the primary branch pipeline is calculated by the following formula:

[0097]

[0098] Wherein, N1 is the leakage risk coefficient of the primary branch pipeline, R max is the maximum pressure of the primary branch pipeline during the risk period, R min is the minimum pressure of the primary branch pipeline during the risk period, G K is the total flow rate of the k-th primary branch pipeline in the department partition connected to the gas source pipeline during the risk period, j ∈ (1, 2,..., j,..., m), and m is the total number of gas supply point groupings in the department partition.

[0099] In one embodiment of the present invention, the leakage risk coefficient of the gas source pipeline is calculated by the following formula:

[0100]

[0101] Wherein, N1 is the leakage risk coefficient of the gas source pipeline, D max is the maximum pressure of the gas source pipeline during the risk period, D min is the minimum pressure of the gas source pipeline during the risk period, G K is the total flow rate of the k-th primary branch pipeline in the department partition connected to the gas source pipeline during the risk period; F is the total flow rate of the gas source pipeline during the risk period, k ∈ (1, 2,..., j,..., w), and w is the total number of department partitions in the gas supply source.

[0102] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A medical gas remote monitoring system, characterized in that, Including: Data acquisition module: used to divide all gas supply pipelines into gas source pipelines, primary branch pipelines, secondary branch pipelines, and tertiary branch pipelines, and process the data collected by the gas pressure sensors and gas flow sensors of each pipeline to obtain the characteristic spectrum data of each sensor; Template matching module: used to detect the characteristic spectrum data of the tertiary branch pipeline and the gas supply source through the template matching algorithm, and transmit the fault signal to the monitoring and alarm module when a fault occurs in the tertiary branch pipeline or the gas supply source; Historical data acquisition module: obtain the historical data of the gas pressure and gas flow of the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline when there is leakage and no leakage, and screen the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in use; Model construction module: used to train the neural network models for detecting the gas source pipeline, primary branch pipeline, and secondary branch pipeline respectively according to the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are screened by the historical data acquisition module; Leakage monitoring module: used to obtain the data obtained in real time by the data acquisition module, and input the collected data into the model construction module to detect whether the pipeline is in normal use. Among them, the number of non-zero gas flow data of the tertiary branch pipeline is the number of gas supply points in use; Evaluation module: used to evaluate the leakage risk coefficients of the gas source pipeline, primary branch pipeline, and secondary branch pipeline according to the corresponding characteristic spectrum data of the gas pressure and gas flow data of the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline; Monitoring and alarm module: used to alarm the gas source pipeline, primary branch pipeline, and secondary branch pipeline detected as not in normal use by the leakage monitoring module, alarm the fault signal of the template matching module, and display the evaluation data of the evaluation module.

2. The medical gas remote monitoring system according to claim 1, wherein The data acquisition module includes: Pipeline division unit: used to divide all pipelines connected to the gas supply source of the hospital. The pipelines connected to the gas supply source of the hospital are set as gas source pipelines; each area in the hospital that needs to use medical gas is divided by department, and each department area is divided into different gas supply point groups according to the location area of the medical gas supply points. The pipelines leading from the gas source pipeline to each department area are primary branch pipelines, the pipelines leading from the primary branch pipelines to each gas supply point group in each department area are secondary branch pipelines, and the pipelines leading from the secondary branch pipelines to each gas supply point in the gas supply point group are tertiary branch pipelines; Pipeline monitoring unit: install pressure sensors and gas flow sensors in the gas source pipeline, primary branch pipeline, secondary branch pipeline, and tertiary branch pipeline to monitor the gas pressure and gas flow of each pipeline in real time; Gas source detection unit: install tilt sensors and gas purity sensors in the electrolysis chamber and gas storage chamber of the medical electronic atomization mechanism of the gas supply source to monitor the tilt angle and gas purity of the device; Data processing unit: It is used to process the data collected by each sensor, extract the signal sequence, and perform power spectrum analysis to obtain the characteristic spectrum data of each sensor.

3. The medical gas remote monitoring system according to claim 2, wherein The template matching module detects the characteristic spectrum data of the three-level branch pipeline and the gas supply source through the template matching algorithm. When a failure occurs in the three-level branch pipeline or the gas supply source, it transmits the failure signal to the monitoring and alarm module, including the following steps: For the three-level branch pipeline, apply the template matching algorithm to match the characteristic spectrum information corresponding to the gas pressure and gas flow of the gas supply point corresponding to the obtained three-level branch pipeline in the use state with the template spectrum of the preset use state to determine whether there is a leak in the three-level branch pipeline; For the gas supply source, by matching the characteristic spectrum information corresponding to the tilt angle and gas purity data of the electrolysis chamber and the gas storage chamber with the preset template spectrum to determine whether the electrolysis chamber and the gas storage chamber are in normal use; When both the three-level branch pipeline and the gas supply source are in normal use, then detect other pipelines through the leak monitoring module. When the gas supply source is not in normal use, it determines that the gas supply source has a failure and transmits the failure signal to the monitoring and alarm module; If the three-level branch pipeline is not in normal use, generate a failure message with the corresponding three-level branch pipeline number and transmit the failure signal to the monitoring and alarm module for alarm.

4. A medical gas remote monitoring system according to claim 3, wherein Screen the gas pressure and gas flow data of different pipelines when different numbers of gas supply points are in the use state, including the following steps: Screen the gas pressure and gas flow data of the three-level branch pipeline corresponding to the gas supply point when each gas supply point is in the use state and not in the use state in the historical data; The gas pressure and gas flow data of the secondary branch pipeline when different numbers of gas supply points in the gas supply point grouping are in the use state; The gas pressure and gas flow data of the primary branch pipeline when different numbers of gas supply points in the department partition are in the use state; The gas pressure and gas flow data of the gas source pipeline when different numbers of gas supply points among all gas supply points supplied by the gas supply source are in the use state.

5. A medical gas remote monitoring system according to claim 4, wherein The model construction module trains neural network models for detecting the gas source pipeline, the primary branch pipeline, and the secondary branch pipeline, including the following steps: Establish a neural network model for detecting the secondary branch pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the secondary branch pipeline and the number of gas supply points in the gas supply point grouping in the use state as inputs, train the neural network model for detecting the secondary branch pipeline; Establish a neural network model for detecting the primary branch pipeline. By using the characteristic spectrum information corresponding to the gas pressure and gas flow data of the primary branch pipeline and the number of gas supply points in the department partition in the use state as inputs, train the neural network model for detecting the primary branch pipeline; A neural network model for detecting a gas source pipeline is established. By taking the characteristic spectrum information corresponding to the gas pressure and gas flow data of the gas source pipeline, and the number of gas supply points in the used state among the gas supply points supplied by the gas supply source as inputs, the neural network model for detecting the gas source pipeline is trained; Among them, the number of gas supply points in the used state in the gas supply point group is the number of pipelines with non-zero flow rates in the three-level branch pipelines corresponding to the gas supply points.

6. The medical gas remote monitoring system according to claim 5, characterized in that, The leakage monitoring module inputs the collected data into the model construction module to detect whether the pipeline is in normal use, including the following steps: The gas pressure and gas flow data of the gas source pipeline, the first-level branch pipeline, the second-level branch pipeline, and the third-level branch pipeline obtained in real time by the data acquisition module are processed by the data processing unit to obtain the real-time characteristic spectrum data of the gas pressure and gas flow data; the number of non-zero gas flow data in the third-level branch pipeline is counted as the number of gas supply points in the used state; the obtained real-time characteristic spectrum data of the gas pressure and gas flow data, and the number of gas supply points in the used state corresponding to the third-level branch pipeline are input into the model construction module to detect whether the pipeline is in normal use.

7. A medical gas remote monitoring system according to claim 1, wherein The evaluation module evaluates the leakage risk coefficients of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline, including the following steps: If, within the preset evaluation interval, the leakage monitoring module detects that the gas source pipeline, the first-level branch pipeline, the second-level branch pipeline, and the third-level branch pipeline are all in normal use, the gas pressure and gas flow data during the time period when the gas flow data fluctuations of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline are greater than the preset threshold are screened as the risk detection data for the risk period; According to the screened risk detection data for the risk period of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline, the leakage risk coefficients of the gas source pipeline, the first-level branch pipeline, and the second-level branch pipeline are calculated respectively; For the pipeline with the leakage risk coefficient exceeding the preset threshold, the pipeline type and the gas pressure and gas flow data of the pipeline are sent to the monitoring and alarm module; Among them, for the first-level branch pipeline and the second-level branch pipeline, the department partition and the gas supply point group data where the pipeline is located are sent to the monitoring and alarm module.

8. A medical gas remote monitoring system according to claim 7, wherein The leakage risk coefficient of the second-level branch pipeline is calculated by the following formula: Among them, N2 is the leakage risk coefficient of the secondary branch pipeline, P max is the maximum pressure value during the risk period of the secondary branch pipeline, P min is the minimum pressure value during the risk period of the secondary branch pipeline, q i is the total flow rate of the i-th tertiary branch pipeline during the risk period in the gas supply point group where the secondary branch pipeline is located; Q j is the total flow rate of the j-th secondary branch pipeline during the risk period in the department partition where the primary branch pipeline is located, i ∈ (1, 2,, i,, n), and n is the total number of gas supply points in the gas supply point group.

9. A medical gas remote monitoring system according to claim 7, wherein The leakage risk coefficient of the first-level branch pipeline is calculated by the following formula: Among them, N1 is the leakage risk coefficient of the first-level branch pipeline, R max is the maximum pressure value during the risk period of the first-level branch pipeline, R min is the minimum pressure value during the risk period of the first-level branch pipeline, G K is the total flow rate of the k-th first-level branch pipeline during the risk period in the department partition connected to the gas source pipeline, j ∈ (1, 2,, j,, m), and m is the total number of gas supply point groups in the department partition.

10. A medical gas remote monitoring system according to claim 7, wherein The leakage risk coefficient of the gas source pipeline is calculated by the following formula: Among them, N1 is the leakage risk coefficient of the gas source pipeline, D max is the maximum pressure value during the risk period of the gas source pipeline, D min is the minimum pressure value during the risk period of the gas source pipeline, G K is the total flow rate of the k-th primary branch pipeline during the risk period in the department partition connected to the gas source pipeline; F is the total flow rate during the risk period of the gas source pipeline, k ∈ (1, 2,, j,, w), and w is the total number of department partitions in the gas supply source.

Images