A micro-high pressure oxygen cabin oxygen supply system and a micro-high pressure oxygen cabin monitoring system

Abstract

The application is particularly a micro-high pressure oxygen cabin oxygen supply system and a micro-high pressure oxygen cabin monitoring system, comprising a data collection module: obtaining air conditioning related data information; a data analysis module: respectively analyzing the state information of the compressor, the clogging state information of the air filter and the leakage state information to obtain a compressor abnormality coefficient, a clogging coefficient and a leakage possibility coefficient; a comprehensive processing module: comprehensively processing the compressor abnormality coefficient, the clogging coefficient and the leakage possibility coefficient to obtain a monitoring evaluation coefficient; and a judgment module. In the application, multi-physical field data fusion and spatial feature analysis are adopted, the system realizes a leap from "single point threshold alarm" to "full system health evaluation", can not only accurately locate the current fault, but also predict potential risks through historical data trends, such as the wear rate of the compressor bearing and the dust accumulation growth trend of the filter, so that preventive maintenance can be intervened in advance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical equipment monitoring, in particular to a micro hyperbaric oxygen chamber oxygen supply system and a micro hyperbaric oxygen chamber monitoring system. BACKGROUND

[0002] As a medical device that promotes human tissue repair by precisely regulating the oxygen concentration and pressure in the chamber, the micro hyperbaric oxygen chamber has been widely used in clinical treatment (such as carbon monoxide poisoning and wound healing), rehabilitation and health care, sports medicine and other fields.

[0003] Its core air conditioning system covers key links such as compressor air supply, filter impurity filtration, pipeline pressure control and sealing, and the performance degradation of any component may cause systemic risk.

[0004] However, the failure of its air conditioning system (such as compressor, filter, pipeline sealing, etc.) may cause treatment interruption, safety risk or reduced efficacy. Existing monitoring technologies are mostly based on a single parameter (such as pressure, temperature), lack comprehensive assessment capability for complex failure modes (such as wear-corrosion coupling, multi-component coordinated failure), and are difficult to achieve early warning and precise positioning of failures.

[0005] Therefore, there is a need for a micro hyperbaric oxygen chamber oxygen supply system and a micro hyperbaric oxygen chamber monitoring system to address the aforementioned problems. SUMMARY

[0006] The purpose of the present application is to solve the above problems and propose a micro hyperbaric oxygen chamber oxygen supply system and a micro hyperbaric oxygen chamber monitoring system.

[0007] To achieve the above purpose, the present application adopts the following technical solutions:

[0008] A micro hyperbaric oxygen chamber oxygen supply system, comprising:

[0009] Oxygen source module: provides the oxygen source required by the oxygen chamber, ensures the purity and supply of oxygen;

[0010] Pressure regulation module: controls the pressure in the oxygen chamber within a safe range

[0011] Flow control module: adjusts the oxygen input flow to meet the needs of different treatment or use scenarios;

[0012] Pipeline and interface module: connects various components and transports gas.

[0013] A micro hyperbaric oxygen chamber monitoring system, comprising the following parts:

[0014] Data collection module: obtains relevant data information of air conditioning;

[0015] Data analysis module: After analyzing the compressor status information, air filter blockage status information, and leakage status information respectively, the compressor abnormality coefficient, blockage coefficient, and leakage probability coefficient are obtained;

[0016] Integrated processing module: The monitoring and evaluation coefficient is obtained by comprehensively processing the compressor abnormality coefficient, blockage coefficient, and leakage possibility coefficient;

[0017] Judgment module: Obtains the corresponding air conditioning fault status level based on monitoring and evaluation coefficients.

[0018] Preferably, the relevant data information of the air conditioner includes compressor status information, air filter blockage status information, and leakage status information.

[0019] Preferably, the process of obtaining the compressor abnormality coefficient includes the following parts:

[0020] Acquire the compressor's status information during startup, including the compressor motor's current, voltage, temperature, operating speed, and torque.

[0021] Set a standard parameter value for any parameter in the status information of the compressor during startup, and calculate the difference between the parameter value during startup and its corresponding standard parameter value to obtain the standard difference value of the parameter.

[0022] Set the allowable range of standard deviation for the parameter. If the standard deviation is not within its corresponding allowable range, then mark the standard deviation as deviating from the standard deviation.

[0023] The time zone between the compressor's start time and the current time is marked as the operating time zone. The time points corresponding to the maximum and minimum standard deviation values ​​within the operating time zone are obtained, and the difference between the two time points is calculated to obtain the duration between the two time points, which is then marked as the time span.

[0024] The standard deviation wave value is obtained by calculating the standard deviation value within the operating time zone.

[0025] Record the generation time of any deviation from the standard deviation within the operating time zone, calculate the time difference between it and the adjacent generation time to obtain the adjacent time difference value; calculate the standard deviation of the adjacent time difference value within the operating time zone to obtain the time deviation fluctuation value.

[0026] Weighted calculations are performed on the cross-time duration, standard deviation fluctuation value, and time deviation fluctuation value to obtain the abnormal single coefficients corresponding to the parameters;

[0027] After assigning corresponding weight factors to each parameter of the compressor, the abnormal coefficients of each parameter are multiplied by their corresponding weight factors, and then summed to obtain the compressor abnormal coefficient.

[0028] Preferably, the process of obtaining the clogging coefficient comprises the following parts:

[0029] acquiring pressure values of each position in the pipeline on the intake side of the filter at preset time intervals, wherein the pressure values of each position in the pipeline are acquired by the pre-installed pressure sensors in the pipeline;

[0030] and presetting a pressure threshold, comparing the pressure values of each position in the pipeline with the pressure threshold, recording the pressure values greater than the pressure threshold as abnormal pressure values, and calculating the pressure deviation values by subtracting the pressure threshold from each abnormal pressure value;

[0031] counting the number of pressure deviation values and dividing by the number of all pressure values to obtain the deviation degree;

[0032] arranging the pressure deviation values in descending order according to the numerical value, extracting the largest four pressure deviation values, and sequentially taking the pressure sensor positions corresponding to the largest four pressure deviation values as the end points, connecting the four end points in a straight line to form a tetrahedron, and calculating the volume of the tetrahedron as the quantification value;

[0033] calculating the clogging coefficient by weighting the deviation degree and the quantification value.

[0034] Preferably, the process of obtaining the leakage possibility coefficient comprises the following parts:

[0035] acquiring the flange image information at the pipeline connection, extracting features of each flange sub-region, extracting features related to wear and corrosion, and marking the extracted features as damaged areas and corrosion areas, respectively;

[0036] calculating the pixel number of the damaged area and the corrosion area of each flange sub-region, converting the pixel number of the damaged area and the corrosion area of each flange sub-region into actual area based on the resolution of the image, and obtaining the damaged area and the corrosion area of each flange sub-region;

[0037] sequentially acquiring the overlapping parts of the damaged area and the corrosion area of each flange sub-region, and the area of the overlapping parts, recorded as the overlapping area; and cumulatively obtaining the total overlapping area value by cumulatively obtaining the overlapping area of each flange sub-region;

[0038] acquiring the outlines of the damaged area and the corrosion area in each flange sub-region, and sequentially arranging marker points along the outlines of the damaged area and the corrosion area;

[0039] connecting any two marker points on the damaged area outline with a straight line, recording the straight line as a damaged line, arranging the obtained damaged lines in descending order according to the numerical value, and extracting the largest damaged line; and sequentially acquiring the largest damaged line in each flange sub-region;

[0040] The maximum damage lines in each flange sub-region are accumulated to obtain a damage span value;

[0041] According to the analysis of the damage area described above, the corrosion area in each flange sub-region is analyzed to obtain a corrosion span value;

[0042] The damage span value and the corrosion span value are multiplied to obtain a corrosion damage value;

[0043] The total overlap surface value and the corrosion damage value are comprehensively analyzed to obtain a leakage possibility coefficient.

[0044] Preferably, the compressor anomaly coefficient, the blockage coefficient and the leakage possibility coefficient are comprehensively processed to obtain a monitoring evaluation coefficient, specifically including:

[0045] After the compressor anomaly coefficient, the blockage coefficient and the leakage possibility coefficient are normalized, the compressor anomaly coefficient and the blockage coefficient are taken as two right-angle sides of a right-angle triangle, and the remaining side is connected to form a complete right-angle triangle. The blockage coefficient is taken as the height of the right-angle triangle to build a three-prism model, and the volume of the three-prism model is calculated as the monitoring evaluation coefficient.

[0046] Preferably, the three groups of threshold values have a value range, and each group of threshold values corresponds to an air conditioning fault state level. The monitoring evaluation coefficient is matched with the value range of the three groups of threshold values to obtain the air conditioning fault state level corresponding to the monitoring evaluation coefficient, including slight anomaly, moderate fault and serious fault.

[0047] As described above, due to the adoption of the technical solutions described above, the present application has the following beneficial effects:

[0048] 1. The present application realizes the leap from "single-point threshold alarm" to "full-system health assessment" through multi-physical field data fusion and spatial feature analysis, which not only accurately locates the current fault, but also predicts potential risks through historical data trends, such as compressor bearing wear rate and filter dust accumulation growth trend, making it possible for preventive maintenance to intervene in advance.

[0049] 2. The present application fills the gap in traditional technology in composite fault assessment and hierarchical disposal through precise diagnosis of multi-dimensional data fusion and intelligent response of geometric model driving, providing "monitoring-analysis-decision-disposal" full-chain technical support for the safe operation of micro-high pressure oxygen cabins, and has significant clinical application value and industry promotion significance. BRIEF DESCRIPTION OF DRAWINGS

[0050] In the following description of exemplary embodiments in conjunction with the drawings, more details, features and advantages of the present application are disclosed, in which:

[0051] Figure 1 Flowchart of the present application; DETAILED DESCRIPTION

[0052] Several embodiments of the present application will be described in greater detail below, with reference to the accompanying drawings, so as to enable persons skilled in the art to implement the present application. The present application can be embodied in many different forms and for many different purposes and should not be limited to the embodiments set forth herein. These embodiments are provided so that the present application is thorough and complete, and fully conveys the scope of the present application to those skilled in the art. The embodiments are not limiting of the present application.

[0053] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and / or the present specification, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0054] Referring to Figure 1 As shown, the present application provides a technical solution:

[0055] A micro-high pressure oxygen cabin oxygen supply system, comprising:

[0056] Oxygen source module: provides the oxygen source required by the oxygen cabin, ensures the oxygen purity and supply amount;

[0057] Comprising:

[0058] Oxygen cylinder group / oxygen generator:

[0059] Oxygen cylinder group: stores high-pressure liquid or gaseous oxygen, and outputs oxygen with stable pressure through a pressure reducing device.

[0060] Oxygen generator (such as PSA pressure swing adsorption oxygen generator): extracts oxygen from air through physical adsorption technology, suitable for scenarios requiring continuous oxygen supply;

[0061] Oxygen purity detection device: real-time monitoring of oxygen purity (usually ≥90%), to ensure compliance with medical or use standards;

[0062] Standby gas source switching system: automatically switches to a standby gas source (such as another set of oxygen cylinders or an emergency oxygen generator) when the main gas source fails, ensuring continuous oxygen supply;

[0063] Pressure regulating module: controls the pressure in the oxygen cabin within a safe range (micro-high pressure usually refers to 0.1~0.3MPa gauge pressure), and realizes stable regulation of the pressure;

[0064] Comprising:

[0065] Pressure reduction device: reduces the high-pressure oxygen in the oxygen cylinder group to a suitable pressure for the oxygen cabin (e.g. 0.5-1 MPa);

[0066] Pressure stabilizing valve / proportional valve: dynamically adjusts the intake volume through a closed-loop control system to maintain constant cabin pressure and avoid excessive pressure fluctuations;

[0067] Safety valve: automatically releases pressure when cabin pressure exceeds a set threshold to prevent overpressure hazards;

[0068] Flow control module: adjusts oxygen input flow to meet different treatment or usage scenarios;

[0069] Includes:

[0070] Flow meter: real-time display of oxygen flow (unit: L / min), common types include rotor flow meter, electromagnetic flow meter;

[0071] Flow regulating valve: manual or electric regulating valve, accurately controls intake flow according to requirements, supports continuous adjustment;

[0072] Pipeline and interface module: connects various components and transports gas;

[0073] Includes:

[0074] Pressure-resistant pipeline: uses stainless steel or food-grade plastic pipe, resistant to slightly high pressure environment (pressure resistance ≥0.6 MPa);

[0075] Quick connector / interface: facilitates device connection and maintenance, including intake valves, exhaust valves, emergency vent valves, etc.;

[0076] Filter: removes impurities (such as dust, oil mist) in the gas to ensure gas cleanliness;

[0077] A slightly high-pressure oxygen cabin monitoring system includes the following parts:

[0078] Data collection module: obtains air conditioning-related data information; air conditioning-related data information includes compressor state information, air filter clogging state information, and leakage state information;

[0079] Data analysis module: analyzes the compressor state information, air filter clogging state information, and leakage state information to obtain the compressor abnormality coefficient, clogging coefficient, and leakage possibility coefficient;

[0080] The process of obtaining the compressor abnormality coefficient includes the following parts:

[0081] Obtain the state information of the compressor in the starting state; including the current, voltage, temperature, operating speed, and torque of the compressor motor;

[0082] Set the standard parameter value of any parameter in the state information in the starting state of the compressor, and calculate the difference between the parameter value in the starting state and the standard parameter value corresponding to the parameter to obtain the standard deviation value corresponding to the parameter;

[0083] Set the allowable floating range of the standard deviation value of the parameter, and if the standard deviation value is not in its corresponding allowable floating range, mark the standard deviation value as a deviation standard deviation value;

[0084] Mark the time zone between the starting time of the compressor and the current time as the operation time zone, obtain the time points corresponding to the maximum deviation standard deviation value and the minimum deviation standard deviation value in the operation time zone, and calculate the difference between the two time points to obtain the time length between the two time points and mark it as the cross-time length;

[0085] Calculate the standard deviation of the standard deviation values in the operation time zone to obtain the standard deviation wave value;

[0086] Record the generation time of any deviation standard deviation value in the operation time zone, calculate the time difference between it and the adjacent generation time to obtain the adjacent time difference value, and calculate the standard deviation of the adjacent time difference values in the operation time zone to obtain the time fluctuation value;

[0087] Weighted calculation of the cross-time length, the standard deviation wave value, and the time fluctuation value to obtain the abnormal single coefficient corresponding to the parameter;

[0088] Mark the cross-time length, the standard deviation wave value, and the time fluctuation value as 、 、 respectively; Obtain the abnormal single coefficient corresponding to the parameter;

[0089] Among them 、 、 are the maximum allowable cross-time length, the reference standard deviation wave value, and the reference time fluctuation value, respectively; a1, a2, and a3 are the weight factors corresponding to the cross-time length, the standard deviation wave value, and the time fluctuation value, respectively;

[0090] After assigning each parameter of the compressor with its corresponding weight factor, multiply the abnormal single coefficient corresponding to each parameter with its corresponding weight factor, and sum to obtain the compressor abnormal coefficient;

[0091] The process of obtaining the blockage coefficient includes the following parts:

[0092] Obtain the pressure values at each position in the pipeline on the intake side of the filter at a predetermined time interval, wherein the pressure values at each position in the pipeline are obtained by a pre-installed pressure sensor in the pipeline;

[0093] Sensor deployment: Install pressure sensors evenly at the positions where airflow disturbance is likely to occur, such as the inlet end, middle, elbow, and near the filter interface of the filter inlet-side pipeline (recommend ≥6, forming a spatial lattice);

[0094] And preset the pressure threshold, compare the pressure values at each position in the pipeline with the pressure threshold, record the pressure values greater than the pressure threshold as abnormal pressure values, and calculate the pressure deviation values by subtracting each abnormal pressure value from the pressure threshold;

[0095] The pressure threshold is set based on historical data during normal operation of the filter, calculating the pressure mean and standard deviation , taking as the threshold (k is the safety factor, usually 1.5~2, corresponding to about 93%~98% confidence interval); or directly set a fixed threshold according to the filter design parameters (such as the absolute pressure corresponding to the normal suction vacuum is 95kPa, then the threshold is set to 90kPa);

[0096] After counting the number of pressure deviation values, divide by the number of all pressure values to get the deviation degree;

[0097] Arrange the pressure deviation values in descending order according to their numerical values, extract the top four pressure deviation values, and sequentially take the pressure sensor positions corresponding to the top four pressure deviation values as the endpoints, connect the four endpoints with straight lines to form a tetrahedron, and calculate the volume of the tetrahedron as the quantification value;

[0098] Record the top four pressure deviation values as , , , ;

[0099] Calculate the volume of the tetrahedron using the vector mixed product formula:

[0100] The volume of the tetrahedron reflects the spatial dispersion degree of the blocked area; if the four endpoints are concentrated on one side of the pipeline, the volume is small, which may correspond to local blockage of the filter element; if the endpoints are distributed dispersedly, the volume is large, which may correspond to uniform blockage of the filter element or multiple blockages in the pipeline;

[0101] Calculate the blockage coefficient by weighting the deviation degree and the quantification value;

[0102] Preset the weight factors of the deviation value and the quantification value, multiply the deviation value and the quantification value by their corresponding weight factors respectively, and then sum them up to get the blockage coefficient;

[0103] The process of obtaining the leakage possibility coefficient includes the following parts:

[0104] Obtain the flange image information of the pipeline connection, extract features of each flange sub-region, extract features related to wear and corrosion, and label the extracted features as damage areas and corrosion areas respectively;

[0105] Flange image acquisition:

[0106] Sensor configuration: deploy an industrial camera (recommended resolution ≥ 2000x1500 pixels, frame rate ≥ 30fps), with LED ring light (eliminate shadows) and optical filter (enhance metal surface features);

[0107] Imaging requirements: shoot the flange plane vertically, ensure that the field of view covers the entire flange (field of view FOV ≥ 120°), and after calibration, the pixel accuracy reaches millimeter level (e.g. 1 pixel = 0.1mm);

[0108] Sub-region division strategy: based on prior knowledge of flange structure, automatically identify functional areas such as bolt holes and sealing surfaces, and divide accordingly;

[0109] Calculate the number of pixels of the damage area and corrosion area of each flange sub-region, convert the number of pixels of the damage area and corrosion area of each flange sub-region to actual area based on the resolution of the image, and obtain the damage area and corrosion area of each flange sub-region;

[0110] Feature extraction algorithm:

[0111] Wear feature: identify surface roughness changes through local texture analysis (LBP operator), and extract wear areas combined with threshold segmentation (Otsu algorithm);

[0112] Corrosion feature: based on HSV color space (Saturation ≥ 0.4, Value ≥ 0.3) combined with morphological operation (opening operation to remove small noise) to segment the rust area;

[0113] Obtain the overlapping part of each flange sub-region damage area and corrosion area in turn, and the area of the overlapping part, recorded as the overlapping area; accumulate the overlapping area of each flange sub-region to obtain the total overlapping value;

[0114] Obtain the outline of the damage area and corrosion area in each flange sub-region, and arrange the marker points along the outline of the damage area and corrosion area in turn;

[0115] Connect any two marker points on the damage area outline with a straight line, record the straight line as a damage line, arrange the obtained damage lines in descending order according to their numerical values, and extract the largest damage line; obtain the largest damage line in each flange sub-region in turn;

[0116] Accumulate the largest damage line in each flange sub-region to obtain the damage span value;

[0117] According to the analysis of the damaged area, the corrosion area in each flange sub-area is analyzed to obtain a corrosion span value;

[0118] The corrosion span value is multiplied by the damage span value to obtain a corrosion damage value;

[0119] The total overlap area value reflects the size of the area affected by wear and corrosion, and the larger the value, the more serious the sealing performance deterioration;

[0120] Corrosion damage value: the product of damage span value and corrosion span value, representing the degree of structural integrity damage (geometric amplification effect);

[0121] The total overlap area value and the corrosion damage value are analyzed to obtain a leakage possibility coefficient;

[0122] The total overlap area value and the corrosion damage value are multiplied by their corresponding weight factors, and the sum is taken to obtain the leakage possibility coefficient;

[0123] The comprehensive processing module: after the compressor abnormality coefficient, the blockage coefficient and the leakage possibility coefficient are comprehensively processed, a monitoring evaluation coefficient is obtained;

[0124] Specifically, it includes:

[0125] After the compressor abnormality coefficient, the blockage coefficient and the leakage possibility coefficient are normalized, the compressor abnormality coefficient and the blockage coefficient are taken as two legs of a right triangle, and the remaining leg is connected to form a complete right triangle. The blockage coefficient is taken as the height of the right triangle to build a three-prism model, the volume of the three-prism model is calculated and recorded as the monitoring evaluation coefficient;

[0126] The judgment module: based on the monitoring evaluation coefficient, the corresponding air conditioning fault state level is obtained, and corresponding processing is performed;

[0127] Three groups of threshold value ranges are preset, each threshold value range corresponds to an air conditioning fault state level, the monitoring evaluation coefficient is matched with the three groups of threshold value ranges to obtain the air conditioning fault state level corresponding to the monitoring evaluation coefficient, including slight abnormality, moderate fault and serious fault;

[0128] When the fault state level is slight abnormality: strengthen monitoring, record abnormal data trend, arrange regular maintenance, prevent fault escalation;

[0129] When the fault state level is moderate fault: immediately start fault troubleshooting, locate the abnormal source (such as pipeline leakage, compressor efficiency decline), preferentially repair or replace damaged parts, and avoid fault spread;

[0130] When the fault state level is a serious fault: emergency shutdown, power off, prohibit continuous operation, professional team comprehensive maintenance, replace the seriously damaged parts, re-debug the system.

[0131] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value, and the influence weight factor and specific coefficient value in the formula are set by the person skilled in the art according to the actual situation, which can be adjusted and modified subsequently.

[0132] The above description of the embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will accord with the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A micro-hyperbaric chamber monitoring system, comprising: Comprise the following parts: Data collection module: obtain air conditioning related data information; Data analysis module: respectively analyze the state information of the compressor, the clogging state information of the air filter and the leakage state information to obtain the compressor abnormality coefficient, the clogging coefficient and the leakage possibility coefficient; The process of obtaining the compressor abnormality coefficient comprises the following parts: Obtain the state information of the compressor in the starting state; including the current, voltage, temperature, running speed and torque of the compressor motor; Set the standard parameter value of any parameter in the state information of the compressor in the starting state, calculate the difference between the parameter value in the starting state and the standard parameter value corresponding to the parameter to obtain the standard deviation value corresponding to the parameter; Set the allowable floating range of the standard deviation value of the parameter, if the standard deviation value is not in its corresponding allowable floating range, mark the standard deviation value as a deviation standard deviation value; Mark the time zone between the starting time of the compressor and the current time as the running time zone, obtain the time points corresponding to the maximum deviation standard deviation value and the minimum deviation standard deviation value in the running time zone, and calculate the difference between the two time points to obtain the time length between the two time points and mark it as the cross time length; Calculate the standard deviation of the standard deviation values in the running time zone to obtain the standard deviation wave value; Record the generation time of any deviation standard deviation value in the running time zone, calculate the time difference between it and the adjacent generation time to obtain the adjacent time difference value; calculate the standard deviation of the adjacent time difference values in the running time zone to obtain the time fluctuation value; Weight the cross time length, the standard deviation wave value and the time fluctuation value to obtain the abnormal single coefficient corresponding to the parameter; Assign each parameter its corresponding weight factor, multiply the abnormal single coefficient corresponding to each parameter by its corresponding weight factor, and sum to obtain the compressor abnormality coefficient; Comprehensive processing module: obtain the monitoring evaluation coefficient by comprehensively processing the compressor abnormality coefficient, the clogging coefficient and the leakage possibility coefficient; Judgment module: obtain the air conditioning fault state level corresponding to the monitoring evaluation coefficient.

2. The micro-hyperbaric chamber monitoring system of claim 1, wherein, The air conditioning related data information includes the state information of the compressor, the clogging state information of the air filter and the leakage state information.

3. The micro-hyperbaric chamber monitoring system of claim 2, wherein, The process of obtaining the clogging coefficient comprises the following parts: Obtain the pressure values at each position in the pipeline on the inlet side of the filter at a preset time interval, wherein the pressure values at each position in the pipeline are obtained by the pressure sensors preinstalled in the pipeline; wherein the deployed sensors form a spatial point array; And preset the pressure threshold value, compare the pressure values at each position in the pipeline with the pressure threshold value, record the pressure values greater than the pressure threshold value as abnormal pressure values, and calculate the pressure deviation values by subtracting the pressure threshold value from each abnormal pressure value; Divide the number of pressure deviation values by the number of all pressure values to obtain the deviation degree; Arrange the pressure deviation values in descending order according to their numerical values, extract the largest four pressure deviation values, and sequentially take the positions of the pressure sensors corresponding to the largest four pressure deviation values as the end points, connect the four end points with straight lines to form a tetrahedron, and calculate the volume of the tetrahedron as the quantization value; The plugging coefficient is obtained by weighting the deviation degree and the quantization value.

4. The micro-hyperbaric chamber monitoring system of claim 3, wherein, The obtaining process of the leakage possibility coefficient comprises the following parts: Obtain the flange image information of the pipeline connection, extract features of each flange sub-region, extract features related to wear and corrosion, and label the extracted features as damaged areas and corrosion areas, respectively; Calculate the number of pixels of the damaged areas and the corrosion areas of each flange sub-region, convert the number of pixels of the damaged areas and the corrosion areas of each flange sub-region into actual areas based on the resolution of the image, and obtain the damaged area and the corrosion area of each flange sub-region; Obtain the overlapping parts of the damaged areas and the corrosion areas of each flange sub-region in turn, and the area of the overlapping parts, denoted as the total overlapping area value; Obtain the profiles of the damaged areas and the corrosion areas in each flange sub-region, and arrange the marker points along the profiles of the damaged areas and the corrosion areas in turn; Connect any two marker points on the profile of the damaged area with a straight line, denote the straight line as a damaged line, arrange the obtained damaged lines in descending order according to the numerical value, and extract the largest damaged line; obtain the largest damaged line in each flange sub-region in turn; Cumulatively obtain the damaged span value of each flange sub-region; Analyze the corrosion areas in each flange sub-region according to the above process of analyzing the damaged areas to obtain the corrosion span value; Multiply the damaged span value and the corrosion span value to obtain the corrosion and damage value; Analyze the total overlapping area value and the corrosion and damage value to obtain the leakage possibility coefficient, including: Pre-set the weight factors of the total overlapping area value and the corrosion and damage value, multiply the total overlapping area value and the corrosion and damage value with their corresponding weight factors respectively, and sum them to obtain the leakage possibility coefficient.

5. The micro-hyperbaric chamber monitoring system of claim 4, wherein, The monitoring evaluation coefficient is obtained by comprehensively processing the compressor abnormality coefficient, the plugging coefficient and the leakage possibility coefficient, specifically including: After normalizing the compressor abnormality coefficient, the plugging coefficient and the leakage possibility coefficient, the compressor abnormality coefficient and the plugging coefficient are taken as two legs of a right triangle, and the remaining leg is connected to form a complete right triangle. The plugging coefficient is taken as the height of the right triangle to construct a three-prism model, calculate the volume of the three-prism model, denoted as the monitoring evaluation coefficient.

6. The micro-hyperbaric chamber monitoring system of claim 5, wherein, Pre-set the value range of three groups of threshold values, each value range of the threshold values corresponds to an air conditioning fault state level, match the monitoring evaluation coefficient with the value range of the three groups of threshold values to obtain the air conditioning fault state level corresponding to the monitoring evaluation coefficient, including slight abnormality, moderate fault and serious fault.

Images