Hyperbaric oxygen chamber fault self-diagnosis system based on digital twinning

Abstract

The invention provides a hyperbaric oxygen chamber fault self-diagnosis system based on digital twinning. The hyperbaric oxygen chamber fault self-diagnosis system comprises a physical equipment layer, a data acquisition and processing layer, a digital twinning model layer and a fault diagnosis and decision-making layer, the physical equipment layer comprises a hyperbaric oxygen chamber and a sensor array mounted in the hyperbaric oxygen chamber, and is used for monitoring operation data of the hyperbaric oxygen chamber in real time; the data acquisition and processing layer is used for transmitting operation data acquired by the sensor array to a data processing center, and the digital twinborn model layer is used for constructing a digital twinborn model of the hyperbaric oxygen chamber according to the physical characteristics and the operation data of the hyperbaric oxygen chamber; and the fault diagnosis and decision-making layer is used for carrying out real-time analysis on the operation data of the hyperbaric oxygen chamber in combination with a confidence rule base and a digital twin model so as to realize self-diagnosis of faults. According to the method, the digital twin model of the hyperbaric oxygen chamber is constructed by combining physical modeling and a data driving technology, and accurate monitoring and fault self-diagnosis of the operation state of the hyperbaric oxygen chamber are achieved.

Description

Technical Field

[0001] The present invention belongs to the field of digital twin technology and medical equipment management, and specifically relates to a hyperbaric oxygen chamber fault self-diagnosis system based on digital twin. Background Art

[0002] Hyperbaric oxygen chambers are widely used in medical treatment and rehabilitation, and their safety and reliability are of vital importance. Traditional hyperbaric oxygen chamber fault detection methods mainly rely on sensor monitoring and manual maintenance, but this method has problems such as poor real-time performance, high false alarm rate, and insensitive response to complex faults.

[0003] As an emerging technology that combines physical entities with their virtual models, digital twin technology can effectively improve the efficiency and safety of equipment operation through real-time synchronization and dynamic prediction. In aircraft and high-precision equipment, digital twins have been used for fault diagnosis and control optimization, but their application in the field of medical equipment is still in its infancy. The present invention aims to solve the above problems and proposes a hyperbaric oxygen chamber fault self-diagnosis system based on digital twins, which significantly improves the intelligent level of fault detection and processing. Summary of the invention

[0004] The present invention provides a hyperbaric oxygen chamber fault self-diagnosis system based on digital twin, comprising: a physical device layer, a data acquisition and processing layer, a digital twin model layer and a fault diagnosis and decision layer;

[0005] The physical equipment layer includes a hyperbaric oxygen chamber and a sensor array installed in the hyperbaric oxygen chamber, which is used to monitor the operating data of the hyperbaric oxygen chamber in real time;

[0006] The data transmission layer is used to transmit the operation data collected by the sensor array to the data processing center.

[0007] The digital twin model layer is used to build a digital twin model of the hyperbaric oxygen chamber through the physical characteristics and operation data of the hyperbaric oxygen chamber;

[0008] The fault diagnosis and decision-making layer is used to combine the confidence rule base and the digital twin model to perform real-time analysis on the operating data of the hyperbaric oxygen chamber to achieve self-diagnosis of faults.

[0009] Further, the sensor array includes a pressure sensor, a temperature and humidity sensor, an oxygen flow sensor and a cabin door status sensor;

[0010] Among them, the pressure sensor is used to measure the pressure in the cabin; the temperature and humidity sensor is used to collect temperature and humidity data; the flow sensor is used to measure the flow of the oxygen supply system; and the cabin door status sensor is used to monitor the opening and closing status of the cabin door and the air valve.

[0011] Furthermore, the data acquisition and processing layer includes a data preprocessing module and a data transmission module.

[0012] The data preprocessing module is used to perform denoising, missing value filling and outlier detection on the operating data collected by the sensor;

[0013] The data transmission module is used to transmit the preprocessed operation data to the digital twin model layer through wired or wireless communication.

[0014] Further, the digital twin model layer includes a physical modeling unit, a data driving unit and a virtual simulation unit;

[0015] The physical modeling unit constructs a physical model based on the structure and operation principle of the hyperbaric oxygen chamber and uses differential equations to simulate the dynamic changes of pressure, flow and environmental parameters in the chamber;

[0016] The data-driven unit constructs a fault prediction model based on historical operation data and real-time data through a random forest algorithm;

[0017] The virtual simulation unit combines the physical model of the hyperbaric oxygen chamber, the fault prediction model and the actual operation data to construct a digital twin model.

[0018] Further, the fault diagnosis and decision-making layer includes a fault diagnosis module and a decision support module;

[0019] The fault diagnosis module evaluates the system operation status by combining the physical model and the fault prediction model results;

[0020] The decision support module generates maintenance suggestions based on the diagnosis results of the fault diagnosis module.

[0021] Furthermore, the fault diagnosis module evaluates the operating data of the hyperbaric oxygen chamber through a confidence rule base, including:

[0022] Calculate the matching degree between the running data and the rule preconditions;

[0023] Calculate the activation weight of each rule based on the attribute weight;

[0024] The outputs of all activated rules are combined to obtain the fault diagnosis result.

[0025] Furthermore, the system operation status includes:

[0026] Normal state: operating parameters are within the set threshold range;

[0027] Controllable fault: the parameter deviates from the set value but is still within the control range;

[0028] Out-of-control failure: Parameters exceed the control range, leading to serious consequences.

[0029] Furthermore, the fault diagnosis and decision layer adopts a fusion analysis method to fuse the output results of the physical model and the output results of the fault prediction model by weight, and the fusion formula is:

[0030] F=w phy ·F Phy +w RF ·F RF

[0031] Where F is the final failure probability, w phy and w RF are the weights corresponding to the physical model and the fault prediction model, and w phy +w RF =1, F RF is the failure probability output by the fault prediction model, F Phy is the failure probability output by the physical model.

[0032] Furthermore, after the fault diagnosis is completed, the fault diagnosis and decision-making layer triggers an alarm module and generates maintenance suggestions, and the maintenance suggestions include possible faulty components, fault cause analysis and repair step suggestions.

[0033] Compared with the prior art, the present invention has the following advantages:

[0034] The present invention combines physical modeling with data-driven technology to build a digital twin model of the hyperbaric oxygen chamber, achieving accurate monitoring of the operating status of the hyperbaric oxygen chamber and self-diagnosis of faults. The system not only improves the accuracy and efficiency of fault diagnosis, but also can predict the changes in the state of the chamber in real time, providing a scientific basis and intelligent decision-making support for the safe operation of the hyperbaric oxygen chamber, effectively reducing the risk of faults and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings generally illustrate various embodiments by way of example and not limitation, and together with the description and claims, serve to illustrate the embodiments of the invention. Where appropriate, the same reference numerals are used throughout the drawings to refer to the same or similar parts. Such embodiments are illustrative and are not intended to be exhaustive or exclusive embodiments of the present apparatus or method.

[0036] Figure 1 A schematic diagram of the system framework of the present invention is shown. DETAILED DESCRIPTION

[0037] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] The hyperbaric oxygen chamber fault self-diagnosis system of the present invention is composed of the following levels:

[0039] Physical equipment layer: The hyperbaric oxygen chamber body and sensor array are responsible for collecting operating data in real time.

[0040] Data collection and processing layer: preprocess and transmit data, including denoising, missing value filling and feature extraction.

[0041] Digital twin model layer: Combine physical modeling, data-driven modeling, and virtual simulation to achieve state modeling and prediction of the hyperbaric oxygen chamber.

[0042] Fault diagnosis and decision-making layer: Analyze fault status through the confidence rule base (BRB) combined with twin data, generate maintenance recommendations and trigger alarms.

[0043] 1. Physical device layer

[0044] Composition and data collection

[0045] The sensor array installed on the hyperbaric chamber includes:

[0046] Pressure sensor P(t): used to measure the real-time pressure in the cabin.

[0047] Temperature and humidity sensors T(t), H(t): used to monitor the temperature and humidity in the cabin respectively.

[0048] Oxygen supply flow sensor Q(t): used to monitor the flow of the oxygen supply system.

[0049] Status sensor S(t): monitors the status of the door and air valve. The value of S(t) is 0 or 1 (closed or open).

[0050] The raw data generated by these sensors constitute the time series D(t) = {P(t), T(t), H(t), Q(t), S(t)} and are input into the data acquisition and processing layer through the analog-to-digital converter.

[0051] 2. Data collection and processing layer

[0052] Data preprocessing

[0053] A low-pass filter is used to eliminate high-frequency noise from the original data D(t), and the mean and standard deviation of the sampling points are calculated using a sliding window. Data that exceeds the set threshold range is marked as outliers and removed:

[0054] For missing data in a short period of time, the mean of the previous and next sampling points is used for interpolation, and for missing data in a longer period of time, the Lagrange polynomial interpolation method is used;

[0055] Extract feature vectors from a time series using a sliding window:

[0056] X={P(t), T(t), H(t), Q(t), S(t), ΔP, ΔQ}

[0057] Wherein, ΔP is the pressure change rate (unit: Pa / s); ΔQ is the flow rate change rate (unit: L / min).

[0058] The preprocessed data is sent to the digital twin model layer via wired communication or wireless communication (such as Wi-Fi or LoRa).

[0059] 3. Digital Twin Model Layer

[0060] The digital twin model layer consists of a physical modeling unit, a data-driven unit, and a virtual simulation unit.

[0061] Physical Modeling Unit

[0062] Based on the operating principle of the hyperbaric oxygen chamber, a physical model describing the dynamic relationship between pressure and oxygen flow is established, for example:

[0063]

[0064] Among them, P(t) is the pressure in the oxygen cabin, Q(t) is the flow rate of the oxygen supply system, Penv is the ambient pressure, which is usually the standard atmospheric pressure (101325Pa), K1 and K2 are system parameters, which are related to the oxygen supply efficiency and the cabin leakage rate respectively, and are calibrated through experiments.

[0065] Data drive unit

[0066] The data-driven unit uses machine learning methods to build a prediction model using the historical operating data of the hyperbaric oxygen chamber and real-time sensor data.

[0067] Specifically, the Random Forest (RF) algorithm is used to build a fault prediction model based on feature vectors:

[0068] F RF =f RF (X),X={P(t),T(t),H(t),Q(t),S(t),ΔP,ΔQ}

[0069] Among them, F RF is the output failure probability, ranging from 0 to 1, and X is the multi-dimensional feature input vector.

[0070] Virtual Simulation Unit

[0071] Map physical modeling and data-driven results to virtual models for real-time monitoring and prediction.

[0072] State synchronization: Mapping parameters such as cabin pressure and flow to the virtual scene.

[0073] Trend prediction: Predict future status based on the results of physical models and fault prediction models.

[0074] 4. Fault diagnosis and decision-making layer

[0075] Trust rule base construction:

[0076] Based on expert experience and historical failure data, a confidence rule base is constructed. Each rule includes premise conditions (such as pressure range, temperature range, etc.), attribute weights and output conclusions (such as failure type).

[0077] The real-time operation data of the hyperbaric oxygen chamber is obtained, the matching degree between the operation data and the rule premise is calculated, the activation weight of each rule is calculated according to the attribute weight, the output of all activated rules is integrated, and the fault diagnosis result is obtained.

[0078] The fusion analysis method is used to perform weighted fusion of the output results of the physical model and the output results of the fault prediction model. The weights of the physical model and the fault prediction model are determined according to the actual situation. The fusion formula is:

[0079] F=w phy ·F Phy +w RF ·F RF

[0080] The final failure probability is calculated using the fusion formula.

[0081] According to the fault diagnosis results, the operating status of the hyperbaric oxygen chamber is divided into normal status, controllable fault and out-of-control fault.

[0082] This invention integrates physical modeling and data-driven technology to build a system that can monitor and predict the operating status of the hyperbaric oxygen chamber in real time. The core of the system is the digital twin model, which can not only reflect the real-time status of the physical equipment, but also identify potential faults in advance through data analysis and model prediction. In this way, the system can significantly improve the safety and operating efficiency of the hyperbaric oxygen chamber and reduce the risk of failure and maintenance costs.

[0083] In the specific implementation, the system collects the operating data of the hyperbaric oxygen chamber through the sensor array, and after preprocessing in the data acquisition and processing layer, it is input into the digital twin model layer for modeling and prediction. Finally, the fault diagnosis and decision layer combines the results of the physical model and the fault prediction model, conducts fault assessment through the confidence rule base, generates maintenance suggestions, and triggers alarms when necessary.

[0084] Therefore, the present invention provides a hyperbaric oxygen chamber fault self-diagnosis system based on digital twins. The system realizes accurate monitoring of the operating status and fault prediction of the hyperbaric oxygen chamber by integrating physical modeling and data-driven technology, effectively improving the safety and maintenance efficiency of the equipment.

[0085] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A hyperbaric oxygen chamber fault self-diagnosis system based on digital twin, characterized in that: include: Physical equipment layer, data acquisition and processing layer, digital twin model layer, and fault diagnosis and decision-making layer; The physical equipment layer includes a hyperbaric oxygen chamber and a sensor array installed in the hyperbaric oxygen chamber, which is used to monitor the operating data of the hyperbaric oxygen chamber in real time; The data acquisition and processing layer is used to transmit the operating data collected by the sensor array to the data processing center. The digital twin model layer is used to construct a digital twin model of the hyperbaric oxygen chamber through the physical characteristics and operation data of the hyperbaric oxygen chamber; The fault diagnosis and decision-making layer is used to combine the confidence rule base and the digital twin model to perform real-time analysis on the operating data of the hyperbaric oxygen chamber to achieve self-diagnosis of faults.

2. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 1, characterized in that: The sensor array includes a pressure sensor, a temperature and humidity sensor, an oxygen flow sensor and a cabin door status sensor; Among them, the pressure sensor is used to measure the pressure in the cabin; the temperature and humidity sensor is used to collect temperature and humidity data; the flow sensor is used to measure the flow of the oxygen supply system; and the cabin door status sensor is used to monitor the opening and closing status of the cabin door and the air valve.

3. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 1, characterized in that: The data acquisition and processing layer includes a data preprocessing module and a data transmission module. The data preprocessing module is used to perform denoising, missing value filling and outlier detection on the operating data collected by the sensor; The data transmission module is used to transmit the preprocessed operation data to the digital twin model layer through wired or wireless communication.

4. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 1, characterized in that: The digital twin model layer includes a physical modeling unit, a data driving unit and a virtual simulation unit; The physical modeling unit constructs a physical model based on the structure and operation principle of the hyperbaric oxygen chamber and uses differential equations to simulate the dynamic changes of pressure, flow and environmental parameters in the chamber; The data-driven unit constructs a fault prediction model based on historical operation data and real-time data through a random forest algorithm; The virtual simulation unit combines the physical model of the hyperbaric oxygen chamber, the fault prediction model and the actual operation data to construct a digital twin model.

5. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 1, characterized in that: The fault diagnosis and decision-making layer includes a fault diagnosis module and a decision support module; The fault diagnosis module is used to diagnose and classify the hyperbaric oxygen chamber; The decision support module generates maintenance suggestions based on the diagnosis results of the fault diagnosis module.

6. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 5, characterized in that: The fault diagnosis module diagnoses the hyperbaric oxygen chamber through a confidence rule base, specifically: Calculate the matching degree between the running data and the rule preconditions; Calculate the activation weight of each rule based on the attribute weight; The outputs of all activated rules are combined to obtain the fault diagnosis result.

7. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 5, characterized in that: The fault classification of the fault diagnosis module specifically includes: Normal state: operating parameters are within the set threshold range; Controllable fault: the parameter deviates from the set value but is still within the control range; Out-of-control failure: Parameters exceed the control range, leading to serious consequences.

8. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 5, characterized in that: The fault diagnosis module adopts a fusion analysis method to fuse the output results of the physical model with the output results of the fault prediction model according to weights. The fusion formula is: F=w phy ·F Phy +w RF ·F RF Where F is the final failure probability, w phy and w RF are the weights corresponding to the physical model and the data-driven fault prediction model, respectively, and w phy +w RF =1, F RF is the failure probability output by the fault prediction model, F Phy is the failure probability output by the physical model.

9. The hyperbaric oxygen chamber fault self-diagnosis system based on digital twin according to claim 1, characterized in that: After the fault diagnosis is completed, the fault diagnosis and decision-making layer triggers the alarm module and generates maintenance suggestions, which include possible faulty components, fault cause analysis and repair step suggestions.

Images