A multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurized, air-conditioning, and refrigeration unit.

Abstract

This invention specifically relates to a multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurized air conditioning, and refrigeration unit, comprising: a trigger judgment module: analyzing the temperature at the air outlet of the air conditioner to obtain a trigger judgment coefficient, and using this coefficient to determine whether a refrigeration fault detection is triggered; an information acquisition module: acquiring relevant parameter information of the air conditioner, including refrigerant leakage information data, compressor fault information data, and throttle valve fault information; a data analysis module: analyzing the acquired information to obtain leakage coefficients, compressor fault coefficients, and throttle valve abnormality coefficients; and a fault judgment module. This invention integrates multiple types of data, including temperature, pressure, vibration, images, and flow rate, to avoid misjudgment based on a single parameter; the trigger judgment module assesses the spatial coverage of temperature anomalies through anomaly ratios, and the leakage coefficient quantifies the spatial characteristics of pipeline anomalies through deviation and graphical values; compared to traditional single-point detection, multi-dimensional data fusion can effectively reduce the fault misjudgment rate.

Description

Technical Field

[0001] This invention relates to the field of air conditioning and refrigeration equipment monitoring technology, and in particular to a multi-parameter real-time monitoring system for an integrated oxygen-generating and pressurizing air conditioning and refrigeration unit. Background Technology

[0002] The integrated oxygen generator, pressurizer, air conditioner, and refrigeration unit combines multiple functional modules such as oxygen generation, pressurization, and refrigeration. The stability of its operation is crucial for the normal use of the equipment and the protection of the working environment.

[0003] However, existing technologies for fault monitoring of such complex equipment often suffer from problems such as insufficient accuracy of single parameter detection and delayed fault warnings. They fail to detect potential problems in the early stages of a fault, leading to increased equipment maintenance costs and even affecting the equipment's lifespan and working efficiency.

[0004] For example, when the air conditioning refrigeration module malfunctions, determining the source of the malfunction requires checking each refrigeration-related component one by one, which is tedious, time-consuming, and inefficient.

[0005] The ability to quickly troubleshoot critical refrigeration components can effectively reduce subsequent manual troubleshooting time and facilitate maintenance personnel in quickly locating the source of the fault. Therefore, real-time monitoring of multiple refrigeration-related parameters to determine the source of the fault is of great significance.

[0006] Therefore, a multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit is proposed to address the aforementioned problems. Summary of the Invention

[0007] The purpose of this invention is to provide a multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit in order to solve the above-mentioned problems.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] A multi-parameter real-time monitoring system for an integrated oxygen generator, pressurization, air conditioning, and refrigeration unit includes:

[0010] Trigger Judgment Module: After analyzing the temperature of the air conditioner outlet, a trigger judgment coefficient is obtained, and this coefficient is used to determine whether to trigger the cooling fault detection.

[0011] Information acquisition module: Acquires relevant parameter information of the air conditioner, including refrigerant leakage information data, compressor fault information data, and expansion valve fault information;

[0012] Data analysis module: After analyzing the acquired information, it obtains the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient.

[0013] Fault diagnosis module: After comprehensively analyzing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, a refrigeration fault assessment coefficient is obtained, and the refrigeration fault is determined.

[0014] Preferably, the trigger determination module specifically includes:

[0015] Temperature sensors are installed at various preset locations at the air conditioner outlet to collect the outlet temperature at each preset location and record it as the actual outlet temperature.

[0016] Obtain the command temperature corresponding to the command received by the air conditioner, and the air outlet temperature corresponding to the command temperature, and mark the air outlet temperature as the air outlet reference temperature.

[0017] Compare the actual temperature of the air outlet at each location with the reference temperature of the air outlet, and record the actual temperature of the air outlet that is higher than the reference temperature of the air outlet as the abnormal temperature of the air outlet.

[0018] The abnormal air outlet temperature is obtained by dividing the number of abnormal air outlet temperatures by the number of actual air outlet temperatures.

[0019] Obtain the start and end times corresponding to each abnormal air outlet temperature and mark them on the time axis to obtain the overlapping time period with the most abnormal air outlet temperatures, and record this time period as the duration of the abnormality.

[0020] The trigger judgment coefficient is obtained by weighting the abnormality ratio and the duration of the abnormality.

[0021] A preset trigger judgment coefficient threshold is set. The trigger judgment coefficient is compared with the trigger judgment coefficient threshold. If the trigger judgment coefficient is greater than the trigger judgment coefficient threshold, the air conditioner cooling fault detection is triggered.

[0022] Preferably, the information acquisition module specifically includes:

[0023] Pressure sensors are installed at predetermined pipeline locations to detect pipeline pressure and determine whether there is any damage to the pipeline. The pipeline locations where the pressure sensors are located are marked as leak detection points.

[0024] A vibration sensor is installed on the motor housing of the compressor to obtain vibration data of the motor, and the location of the vibration sensor is marked as a vibration detection point;

[0025] Acquire image information of the area between the expansion valve and the evaporator, and install flow meters at the pipes at both ends of the expansion valve to acquire the refrigerant flow rate detected by the flow meters.

[0026] Preferably, the process of obtaining the leakage coefficient includes:

[0027] Acquire pressure data at each leak detection point, and preset the maximum allowable pressure value for each leak detection point based on the pipeline location of the pressure sensor;

[0028] The pressure data at each leak detection point is compared with the corresponding maximum allowable pressure value. Pressure data exceeding the maximum allowable pressure value is recorded as abnormal pressure value. The deviation pressure value is calculated by the difference between each abnormal pressure value and the maximum allowable pressure value.

[0029] The deviation pressure values ​​are sorted in descending order of magnitude, and the three largest deviation pressure values ​​are extracted. The sensor positions corresponding to the three largest deviation pressure values ​​are used as origins, and projection surfaces are drawn along the direction parallel to the pipeline. The three origins are projected onto the projection surfaces, and the three origins are connected by straight lines to obtain the connecting lines.

[0030] Calculate the length of the connecting line and divide the length of the connecting line by the length of the pipe to obtain the deviation.

[0031] Again, taking the sensor positions corresponding to the three largest deviation pressure values ​​as origins, connect the three origins with straight lines to obtain a triangle. Calculate the area of ​​the triangle and record it as the value of the triangle.

[0032] The leakage coefficient is obtained by combining the deviation and graphical values.

[0033] Preferably, the process of obtaining the compression failure coefficient includes:

[0034] Vibration data of each vibration detection point is acquired at preset time intervals. A preset vibration threshold is set. The vibration value of each vibration detection point at each time interval is compared with the vibration threshold. Vibration data that is greater than the vibration threshold is recorded as vibration excess value. The difference between the vibration excess value and the vibration threshold is calculated to obtain the vibration difference value.

[0035] Arrange the vibration difference values ​​of each vibration detection point according to the time series, and record the time between adjacent vibration difference values ​​as the planning time, with the unit of planning time being seconds;

[0036] Extract three adjacent vibration difference values ​​and three adjacent planning durations, and remove the units of the three vibration difference values ​​and three planning durations. Then, in order, multiply the three vibration difference values ​​with the corresponding three planning durations to obtain three model values.

[0037] The middle value among the three vibration difference values ​​is the maximum vibration difference value determined from the arranged vibration difference values. The vibration difference value before and after the maximum vibration difference value is the first vibration difference value and the last vibration difference value among the three vibration difference values, respectively.

[0038] Arrange the three model values ​​obtained in the order they were acquired. Use the first and second model values ​​as the two legs of a right triangle and connect the remaining leg to obtain a complete right triangle. Use the third model value as the height of the right triangle to construct a triangular pyramid model. Calculate the volume of the triangular pyramid and record it as the single failure coefficient.

[0039] Following the above analysis process, the vibration data at each vibration detection point are analyzed in the same way to obtain the single fault coefficient corresponding to the vibration data at each vibration detection point.

[0040] After sorting all the individual fault coefficients in descending order of size, the largest individual fault coefficient is marked as the compressed fault coefficient.

[0041] Preferably, the process of obtaining the throttle valve abnormality coefficient includes:

[0042] Image information of the area between the throttle valve and the evaporator is acquired at preset time intervals, and the images are preprocessed.

[0043] The convolutional neural network is used to automatically extract frost features from the image and the regions with frost features are marked as frost regions.

[0044] After obtaining the area of ​​each frosting area, the areas are accumulated to obtain the total frosting area. The total frosting area is then divided by the area between the expansion valve and the evaporator to obtain the frosting ratio.

[0045] Subtract the previous frost ratio from the next frost ratio in adjacent time intervals to obtain the frost change ratio; sum all the obtained frost change ratios to obtain the total frost change ratio;

[0046] The flow rates at both ends of the throttle valve are obtained at preset time intervals, and the flow rate thresholds at the front and rear ends of the throttle valve are preset respectively; the difference between the flow rate at the front end of the throttle valve and the front flow rate threshold is calculated to obtain the front flow rate difference; the difference between the flow rate at the rear end of the throttle valve and the rear flow rate threshold is calculated to obtain the rear flow rate difference.

[0047] The allowable fluctuation range of the front-end traffic difference is preset. The front-end traffic difference is compared with the allowable fluctuation range of the front-end traffic difference. The front-end traffic difference that is not within the allowable fluctuation range of the front-end traffic difference is recorded as the front-end traffic deviation value.

[0048] Based on the above process of obtaining the front-end traffic deviation value, the back-end traffic deviation value can be obtained in the same way;

[0049] Based on the time points at which the flow rates before and after the throttle valve are obtained, the flow rate deviation values ​​at each front end and the flow rate deviation values ​​at the back end are matched to obtain the number of time points at which both the flow rate deviation values ​​at the front end and the flow rate deviation values ​​at the back end exist at the same time point, and these are recorded as the number of overlapping points.

[0050] The mean deviation is obtained by averaging the number of front-end and back-end flow deviations. The overlap ratio is obtained by dividing the number of overlapping points by the mean deviation.

[0051] The throttle valve abnormality coefficient is obtained by comprehensively processing the total proportion of frosting changes and the overlap proportion.

[0052] Preferably, the refrigeration failure assessment coefficient is obtained by comprehensively analyzing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, specifically including:

[0053] After normalizing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, an elliptical model is constructed by using the leakage coefficient and compression failure coefficient as the major and minor semi-axes of the ellipse, respectively. An elliptic body model is constructed by using the throttle valve abnormality coefficient as the height of the elliptical model. The volume of the elliptic body model is calculated to obtain the refrigeration failure evaluation coefficient.

[0054] Preferably, the preset refrigeration fault assessment coefficient threshold is used to compare the refrigeration fault assessment coefficient with the refrigeration fault assessment coefficient threshold. If the refrigeration fault assessment coefficient is greater than the refrigeration fault assessment coefficient threshold, it is determined that there is a refrigeration fault.

[0055] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0056] 1. This invention avoids misjudgment based on a single parameter by integrating multiple types of data, including temperature, pressure, vibration, images, and flow rate; the trigger judgment module assesses the spatial coverage of temperature anomalies by anomaly ratio, and the leakage coefficient quantifies the spatial characteristics of pipeline anomalies by deviation and graphical values; compared with traditional single-point detection, multi-dimensional data fusion can effectively reduce the fault misjudgment rate.

[0057] 2. This invention captures the trend of parameter changes over time by using indicators such as the duration of abnormality, the total proportion of frost changes, and the planned duration, thereby enabling dynamic tracking of potential faults rather than focusing solely on instantaneous data. Therefore, it can more accurately determine whether a fault exists and avoid misjudgment. Attached Figure Description

[0058] Further details, features, and advantages of this application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0059] Figure 1 This is a flowchart of the present invention; Detailed Implementation

[0060] Several embodiments of this application will now be described in more detail with reference to the accompanying drawings to enable those skilled in the art to implement this application. This application may be embodied in many different forms and for various purposes and should not be limited to the embodiments set forth herein. These embodiments are provided to make this application thorough and complete, and to fully convey the scope of this application to those skilled in the art. The embodiments described do not limit this application.

[0061] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having a meaning consistent with their meaning in the relevant field and / or the context of this specification, and shall not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0062] Please see Figure 1 As shown, the present invention provides a technical solution:

[0063] A multi-parameter real-time monitoring system for an integrated oxygen generator, pressurization, air conditioning, and refrigeration unit includes:

[0064] Trigger Judgment Module: After analyzing the temperature of the air conditioner outlet, a trigger judgment coefficient is obtained, and this coefficient is used to determine whether to trigger the cooling fault detection.

[0065] Specifically, it includes:

[0066] Temperature sensors are installed at various preset locations at the air conditioner outlet to collect the outlet temperature at each preset location and record it as the actual outlet temperature.

[0067] Obtain the command temperature corresponding to the command received by the air conditioner, and the air outlet temperature corresponding to the command temperature, and mark the air outlet temperature as the air outlet reference temperature.

[0068] Compare the actual temperature of the air outlet at each location with the reference temperature of the air outlet, and record the actual temperature of the air outlet that is higher than the reference temperature of the air outlet as the abnormal temperature of the air outlet.

[0069] The abnormal air outlet temperature is obtained by dividing the number of abnormal air outlet temperatures by the number of actual air outlet temperatures.

[0070] Obtain the start and end times corresponding to each abnormal air outlet temperature and mark them on the time axis to obtain the overlapping time period with the most abnormal air outlet temperatures, and record this time period as the duration of the abnormality.

[0071] The trigger judgment coefficient is obtained by weighting the abnormality ratio and the duration of the abnormality.

[0072] The weighting factors for the abnormality ratio and the duration of abnormality are preset. The abnormality ratio and the duration of abnormality are multiplied by their corresponding weighting factors and then summed to obtain the trigger judgment coefficient.

[0073] A preset trigger judgment coefficient threshold is set. The trigger judgment coefficient is compared with the trigger judgment coefficient threshold. If the trigger judgment coefficient is greater than the trigger judgment coefficient threshold, the air conditioner cooling fault detection is triggered.

[0074] The acquisition of the trigger judgment coefficient combines spatial distribution (abnormal proportion) and time dimension (duration) to avoid single-point misjudgment; it can detect potential problems in advance before the fault is fully manifested;

[0075] Information acquisition module: Acquires relevant parameter information of the air conditioner, including refrigerant leakage information data, compressor fault information data, and expansion valve fault information;

[0076] Specifically, it includes:

[0077] Pressure sensors are installed at predetermined pipeline locations to detect pipeline pressure and determine whether there is any damage to the pipeline. The pipeline locations where the pressure sensors are located are marked as leak detection points.

[0078] A vibration sensor is installed on the motor housing of the compressor to obtain vibration data of the motor, and the location of the vibration sensor is marked as a vibration detection point;

[0079] Acquire image information of the area between the expansion valve and the evaporator, and install flow meters at the pipes at both ends of the expansion valve to acquire the refrigerant flow rate detected by the flow meters;

[0080] Data analysis module: After analyzing the acquired information, it obtains the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient.

[0081] The process of obtaining the leakage coefficient includes:

[0082] Acquire pressure data at each leak detection point, and preset the maximum allowable pressure value for each leak detection point based on the pipeline location of the pressure sensor;

[0083] The pressure data at each leak detection point is compared with the corresponding maximum allowable pressure value. Pressure data exceeding the maximum allowable pressure value is recorded as abnormal pressure value. The deviation pressure value is calculated by the difference between each abnormal pressure value and the maximum allowable pressure value.

[0084] The deviation pressure values ​​are sorted in descending order of magnitude, and the three largest deviation pressure values ​​are extracted. The sensor positions corresponding to the three largest deviation pressure values ​​are used as origins, and projection surfaces are drawn along the direction parallel to the pipeline. The three origins are projected onto the projection surfaces, and the three origins are connected by straight lines to obtain the connecting lines.

[0085] Calculate the length of the connecting line and divide the length of the connecting line by the length of the pipe to obtain the deviation.

[0086] Deviation is a relative value that represents the proportion of the pressure anomaly area along the entire pipeline length. It helps to understand the extent to which the distribution range of pressure anomalies within the pipeline affects the overall pipeline from a macroscopic perspective.

[0087] Again, taking the sensor positions corresponding to the three largest deviation pressure values ​​as origins, connect the three origins with straight lines to obtain a triangle. Calculate the area of ​​the triangle and record it as the value of the triangle.

[0088] The graphical values ​​describe the distribution characteristics of the pressure anomaly region from another perspective. The size of the triangle area reflects the relative positional relationship and the density of the distribution among the three anomaly points.

[0089] The leakage coefficient is obtained by comprehensively analyzing the deviation and graphical values;

[0090] The weighting factors for the deviation and graphic value are preset. The leakage coefficient is obtained by multiplying the deviation and graphic value with their corresponding weighting factors and summing them.

[0091] The process of obtaining the compression failure coefficient includes:

[0092] Vibration data of each vibration detection point is acquired at preset time intervals. A preset vibration threshold is set. The vibration value of each vibration detection point at each time interval is compared with the vibration threshold. Vibration data that is greater than the vibration threshold is recorded as vibration excess value. The difference between the vibration excess value and the vibration threshold is calculated to obtain the vibration difference value.

[0093] A vibration threshold is preset, and the vibration value in each time interval is compared with this threshold. When the vibration value exceeds the threshold, it is recorded as a vibration exceedance value, and the difference between the vibration exceedance value and the vibration threshold is calculated to obtain the vibration difference exceedance value. The vibration threshold is usually set based on the vibration level during normal operation of the compressor and the design standards of the equipment. By comparing it with the threshold, abnormal vibration data can be filtered out, and the vibration difference exceedance value quantifies the degree to which the vibration exceeds the normal range.

[0094] Arrange the vibration difference values ​​of each vibration detection point according to the time series, and record the time between adjacent vibration difference values ​​as the planning time, with the unit of planning time being seconds;

[0095] Arrange the vibration difference values ​​of each vibration detection point according to the time series. This can clearly show how the vibration difference values ​​change over time.

[0096] The planning duration reflects the time interval between abnormal vibration events, which is of great significance for analyzing the frequency and continuity of abnormal vibrations;

[0097] For example, a shorter planning time may indicate more frequent vibration anomalies, which may indicate a potential risk of failure;

[0098] Extract three adjacent vibration difference values ​​and three adjacent planning durations, and remove the units of the three vibration difference values ​​and three planning durations. Then, in order, multiply the three vibration difference values ​​with the corresponding three planning durations to obtain three model values.

[0099] The middle value among the three vibration difference values ​​is the maximum vibration difference value determined from the arranged vibration difference values. The vibration difference value before and after the maximum vibration difference value is the first vibration difference value and the last vibration difference value among the three vibration difference values, respectively.

[0100] Arrange the three model values ​​obtained in the order they were acquired. Use the first and second model values ​​as the two legs of a right triangle and connect the remaining leg to obtain a complete right triangle. Use the third model value as the height of the right triangle to construct a triangular pyramid model. Calculate the volume of the triangular pyramid and record it as the single failure coefficient.

[0101] Following the above analysis process, the vibration data at each vibration detection point are analyzed in the same way to obtain the single fault coefficient corresponding to the vibration data at each vibration detection point.

[0102] After sorting all the single fault coefficients in descending order of size, the largest single fault coefficient is marked as the compressed fault coefficient.

[0103] Analyze all detection points: Following the above analysis process, perform the same analysis on the vibration data of each vibration detection point to obtain the individual fault coefficient for each vibration detection point. This allows for a comprehensive assessment of the operating status of different parts of the entire compressor.

[0104] Determine the compression failure coefficient: Sort all individual failure coefficients in descending order of magnitude, and mark the largest single failure coefficient as the compression failure coefficient. The compression failure coefficient represents the degree of failure of the part of the entire compressor system with the most severe vibration abnormality. By determining the compression failure coefficient, it is possible to quickly locate potentially serious fault areas, providing an important basis for equipment maintenance and troubleshooting.

[0105] The process of obtaining the throttle valve abnormality coefficient includes:

[0106] Image information of the area between the throttle valve and the evaporator is acquired at preset time intervals, and the images are preprocessed, including resizing, normalizing pixel values, and cropping regions of interest. These processes improve image quality, reduce noise interference, and ensure the image data has a uniform format and range, facilitating subsequent model processing.

[0107] The convolutional neural network is used to automatically extract frost features from the image and the regions with frost features are marked as frost regions.

[0108] By collecting a large number of images containing throttle valves, including both frosted and non-frosted images, these images were used as the basic data for training the model. After training the model, it was used to identify frosting features in the images. This is a direct reference to existing technology and will not be elaborated here.

[0109] After obtaining the area of ​​each frosting area, the areas are accumulated to obtain the total frosting area. The total frosting area is then divided by the area between the expansion valve and the evaporator to obtain the frosting ratio.

[0110] Subtract the previous frost ratio from the next frost ratio in adjacent time intervals to obtain the frost change ratio; sum all the obtained frost change ratios to obtain the total frost change ratio;

[0111] Total percentage of frost change: This indicates the trend of frost development; the larger the value, the faster the frost intensifies.

[0112] The flow rates at both ends of the throttle valve are obtained at preset time intervals, and the flow rate thresholds at the front and rear ends of the throttle valve are preset respectively; the difference between the flow rate at the front end of the throttle valve and the front flow rate threshold is calculated to obtain the front flow rate difference; the difference between the flow rate at the rear end of the throttle valve and the rear flow rate threshold is calculated to obtain the rear flow rate difference.

[0113] The allowable fluctuation range of the front-end traffic difference is preset. The front-end traffic difference is compared with the allowable fluctuation range of the front-end traffic difference. The front-end traffic difference that is not within the allowable fluctuation range of the front-end traffic difference is recorded as the front-end traffic deviation value.

[0114] Based on the above process of obtaining the front-end traffic deviation value, the back-end traffic deviation value can be obtained in the same way;

[0115] Front-end traffic difference: The difference between actual traffic and preset threshold, reflecting the upstream supply status;

[0116] Back-end flow difference: The difference between the actual flow rate and the preset threshold reflects the stability of the throttle valve outlet flow rate;

[0117] Deviation identification: The difference that exceeds the allowable fluctuation range is recorded as the deviation value, and the number of deviations at the front end and the back end are counted separately;

[0118] Overlap ratio: The number of time points where traffic deviations occur simultaneously at the front and back ends, divided by the average number of deviations, measures the synchronicity of traffic anomalies.

[0119] Based on the time points at which the flow rates before and after the throttle valve are obtained, the flow rate deviation values ​​at each front end and the flow rate deviation values ​​at the back end are matched to obtain the number of time points at which both the flow rate deviation values ​​at the front end and the flow rate deviation values ​​at the back end exist at the same time point, and these are recorded as the number of overlapping points.

[0120] The mean deviation is obtained by averaging the number of front-end and back-end flow deviations. The overlap ratio is obtained by dividing the number of overlapping points by the mean deviation.

[0121] The throttle valve anomaly coefficient is obtained by comprehensively processing the total proportion of frosting changes and the overlap proportion.

[0122] The total percentage of frosting change and the overlap percentage are respectively labeled as follows: , ;

[0123] Substitute into the formula: ;

[0124] The abnormal coefficient of the throttle valve is obtained, where , These are the maximum permissible total percentage of frosting changes and the reference overlap percentage, respectively. , These are the weighting factors for the total percentage change in frosting and the percentage of overlap, respectively.

[0125] Fault diagnosis module: After comprehensively analyzing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, a refrigeration fault assessment coefficient is obtained, and the refrigeration fault is determined.

[0126] Specifically, it includes:

[0127] After normalizing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, an elliptical model is constructed by using the leakage coefficient and compression failure coefficient as the major and minor semi-axes of the ellipse, respectively, and an elliptic body model is constructed by using the throttle valve abnormality coefficient as the height of the elliptical model. The volume of the elliptic body model is calculated to obtain the refrigeration failure evaluation coefficient.

[0128] A preset threshold for the refrigeration fault assessment coefficient is set. The refrigeration fault assessment coefficient is compared with the threshold. If the refrigeration fault assessment coefficient is greater than the threshold, it is determined that there is a refrigeration fault.

[0129] The above formulas are derived from software simulations using a large amount of data and are selected to be close to the actual values. The influence weight factors and specific coefficient values ​​in the formulas are set by those skilled in the art based on the actual situation and can be adjusted and modified in the future.

[0130] The above description of the embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit, characterized in that, include: Trigger Judgment Module: After analyzing the temperature of the air conditioner outlet, a trigger judgment coefficient is obtained, and this coefficient is used to determine whether to trigger the cooling fault detection. Specifically, this includes: Temperature sensors are installed at various preset locations at the air conditioner outlet to collect the outlet temperature at each preset location and record it as the actual outlet temperature. Obtain the command temperature corresponding to the command received by the air conditioner, and the air outlet temperature corresponding to the command temperature, and mark the air outlet temperature as the air outlet reference temperature. Compare the actual temperature of the air outlet at each location with the reference temperature of the air outlet, and record the actual temperature of the air outlet that is higher than the reference temperature of the air outlet as the abnormal temperature of the air outlet. The abnormal air outlet temperature is obtained by dividing the number of abnormal air outlet temperatures by the number of actual air outlet temperatures. Obtain the start and end times corresponding to each abnormal air outlet temperature and mark them on the time axis to obtain the overlapping time period with the most abnormal air outlet temperatures, and record this time period as the duration of the abnormality. The trigger judgment coefficient is obtained by weighting the abnormality ratio and the duration of the abnormality. A preset trigger judgment coefficient threshold is set. The trigger judgment coefficient is compared with the trigger judgment coefficient threshold. If the trigger judgment coefficient is greater than the trigger judgment coefficient threshold, the air conditioner cooling fault detection is triggered. Information Acquisition Module: Acquires relevant parameter information of the air conditioner, including refrigerant leakage information, compressor fault information, and expansion valve fault information, specifically including: Pressure sensors are installed at predetermined pipeline locations to detect pipeline pressure and determine whether there is any damage to the pipeline. The pipeline locations where the pressure sensors are located are marked as leak detection points. A vibration sensor is installed on the motor housing of the compressor to obtain vibration data of the motor, and the location of the vibration sensor is marked as a vibration detection point; Acquire image information of the area between the expansion valve and the evaporator, and install flow meters at the pipes at both ends of the expansion valve to acquire the refrigerant flow rate detected by the flow meters; Data analysis module: After analyzing the acquired information, it obtains the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient. Fault diagnosis module: After comprehensively analyzing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, a refrigeration fault assessment coefficient is obtained, and the refrigeration fault is determined.

2. The multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit according to claim 1, characterized in that, The process of obtaining the leakage coefficient includes: Acquire pressure data at each leak detection point, and preset the maximum allowable pressure value for each leak detection point based on the pipeline location of the pressure sensor; The pressure data at each leak detection point is compared with the corresponding maximum allowable pressure value. Pressure data exceeding the maximum allowable pressure value is recorded as abnormal pressure value. The deviation pressure value is calculated by the difference between each abnormal pressure value and the maximum allowable pressure value. The deviation pressure values ​​are sorted in descending order of magnitude, and the three largest deviation pressure values ​​are extracted. The sensor positions corresponding to the three largest deviation pressure values ​​are used as origins, and projection surfaces are drawn along the direction parallel to the pipeline. The three origins are projected onto the projection surfaces, and the three origins are connected by straight lines to obtain the connecting lines. Calculate the length of the connecting line and divide the length of the connecting line by the length of the pipe to obtain the deviation. Again, taking the sensor positions corresponding to the three largest deviation pressure values ​​as origins, connect the three origins with straight lines to obtain a triangle. Calculate the area of ​​the triangle and record it as the value of the triangle. The leakage coefficient is obtained by combining the deviation and graphical values.

3. The multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit according to claim 2, characterized in that, The process of obtaining the compression failure coefficient includes: Vibration data of each vibration detection point is acquired at preset time intervals. A preset vibration threshold is set. The vibration value of each vibration detection point at each time interval is compared with the vibration threshold. Vibration data that is greater than the vibration threshold is recorded as vibration excess value. The difference between the vibration excess value and the vibration threshold is calculated to obtain the vibration difference value. Arrange the vibration difference values ​​of each vibration detection point according to the time series, and record the time between adjacent vibration difference values ​​as the planning time, with the unit of planning time being seconds; Extract three adjacent vibration difference values ​​and three adjacent planning durations, and remove the units of the three vibration difference values ​​and three planning durations. Then, in order, multiply the three vibration difference values ​​with the corresponding three planning durations to obtain three model values. The middle value among the three vibration difference values ​​is the maximum vibration difference value determined from the arranged vibration difference values. The vibration difference value before and after the maximum vibration difference value is the first vibration difference value and the last vibration difference value among the three vibration difference values, respectively. Arrange the three model values ​​obtained in the order they were acquired. Use the first and second model values ​​as the two legs of a right triangle and connect the remaining leg to obtain a complete right triangle. Use the third model value as the height of the right triangle to construct a triangular pyramid model. Calculate the volume of the triangular pyramid and record it as the single failure coefficient. Following the above analysis process, the vibration data at each vibration detection point are analyzed in the same way to obtain the single fault coefficient corresponding to the vibration data at each vibration detection point. After sorting all the individual fault coefficients in descending order of size, the largest individual fault coefficient is marked as the compressed fault coefficient.

4. The multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit according to claim 3, characterized in that, The process of obtaining the throttle valve abnormality coefficient includes: Image information of the area between the throttle valve and the evaporator is acquired at preset time intervals, and the images are preprocessed. The convolutional neural network is used to automatically extract frost features from the image and the regions with frost features are marked as frost regions. After obtaining the area of ​​each frosting area, the areas are accumulated to obtain the total frosting area. The total frosting area is then divided by the area between the expansion valve and the evaporator to obtain the frosting ratio. Subtract the previous frost ratio from the next frost ratio in adjacent time intervals to obtain the frost change ratio; sum all the obtained frost change ratios to obtain the total frost change ratio; The flow rates at both ends of the throttle valve are obtained at preset time intervals, and the flow rate thresholds at the front and rear ends of the throttle valve are preset respectively; the difference between the flow rate at the front end of the throttle valve and the front flow rate threshold is calculated to obtain the front flow rate difference; the difference between the flow rate at the rear end of the throttle valve and the rear flow rate threshold is calculated to obtain the rear flow rate difference. The allowable fluctuation range of the front-end traffic difference is preset. The front-end traffic difference is compared with the allowable fluctuation range of the front-end traffic difference. The front-end traffic difference that is not within the allowable fluctuation range of the front-end traffic difference is recorded as the front-end traffic deviation value. Based on the above process of obtaining the front-end traffic deviation value, the back-end traffic deviation value can be obtained in the same way; Based on the time points at which the flow rates before and after the throttle valve are obtained, the flow rate deviation values ​​at each front end and the flow rate deviation values ​​at the back end are matched to obtain the number of time points at which both the flow rate deviation values ​​at the front end and the flow rate deviation values ​​at the back end exist at the same time point, and these are recorded as the number of overlapping points. The mean deviation is obtained by averaging the number of front-end and back-end flow deviations. The overlap ratio is obtained by dividing the number of overlapping points by the mean deviation. The throttle valve abnormality coefficient is obtained by comprehensively processing the total proportion of frosting changes and the overlap proportion.

5. A multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit according to claim 4, characterized in that, The refrigeration failure assessment coefficient is obtained by comprehensively analyzing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient. Specifically, it includes: After normalizing the leakage coefficient, compression failure coefficient, and throttle valve abnormality coefficient, an elliptical model is constructed by using the leakage coefficient and compression failure coefficient as the major and minor semi-axes of the ellipse, respectively. An elliptic body model is constructed by using the throttle valve abnormality coefficient as the height of the elliptical model. The volume of the elliptic body model is calculated to obtain the refrigeration failure evaluation coefficient.

6. A multi-parameter real-time monitoring system for an integrated oxygen-generating, pressurizing, air-conditioning, and refrigeration unit according to claim 5, characterized in that, A preset threshold for the refrigeration fault assessment coefficient is set. The refrigeration fault assessment coefficient is compared with the threshold. If the refrigeration fault assessment coefficient is greater than the threshold, it is determined that there is a refrigeration fault.

Images