MRI (Magnetic Resonance Imaging) operation intelligent management system and management method

Abstract

The invention discloses an MRI (Magnetic Resonance Imaging) operation intelligent management system and management method, and relates to the technical field of medical equipment management.The MRI operation intelligent management system comprises an edge computing layer, and a sensing layer and a cloud platform layer which are connected with the edge computing layer, and the cloud platform layer is connected with a multi-terminal interaction module; the management method comprises the following steps: collecting equipment operation data in real time through a multi-sensor cluster of a sensing layer; the equipment operation data is converted into a hospital system compatible format through the edge computing layer, and data processing is performed on the equipment operation data; data analysis and fault prediction are carried out on the processed data through the cloud platform layer; the operation state of the equipment is visualized through the multi-terminal interaction module, and early warning pushing is carried out according to a data analysis result; comprehensive monitoring and intelligent early warning of the equipment operation state are realized through cooperative work of multiple modules, the system adopts a modular design concept, high-precision data acquisition, intelligent analysis and multi-terminal interaction are integrated, and an innovative solution is provided for preventive maintenance of medical equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment management, and in particular to an intelligent management system and management method for MRI operation. Background Art

[0002] Magnetic resonance imaging (MRI) equipment, with its technical advantages such as no radiation damage and high soft tissue resolution, has become a core imaging diagnostic tool in fields such as early tumor screening, neurodegenerative disease diagnosis, and cardiovascular imaging. However, the contradiction between the equipment's highly complex system architecture and the precise operation and maintenance requirements is becoming a key bottleneck restricting the industry's development.

[0003] From the perspective of system composition, MRI equipment integrates tens of thousands of precision components such as superconducting magnets, gradient coils, and radio frequency systems, involving the coupling of multidisciplinary technologies such as liquid helium phase change refrigeration, superconducting environment maintenance, and electromagnetic interference suppression. This technology-intensive feature makes the propagation of abnormal equipment conditions present a cascade effect, and a relatively low leakage rate can cause the superconducting magnet to quench.

[0004] At the operation and maintenance ecosystem level, the shortage of professional talent in primary medical institutions has exacerbated the operation and maintenance difficulties. Due to the lack of on-site engineers, county hospitals' MRI equipment relies on the manufacturer's passive maintenance model of monthly inspections, which objectively aggravates the uneven distribution of medical resources.

[0005] In existing technologies, although remote maintenance platforms have attempted to achieve breakthroughs, since deep data channels have not yet been established between equipment operating parameters such as liquid helium pressure and magnet vibration spectrum and the hospital's HIS / RIS / PACS systems, operation and maintenance personnel still need to manually integrate information across platforms. In addition, the private data protocols used by third-party tools will form information silos, making time series analysis of key parameters difficult to achieve.

[0006] Therefore, an intelligent MRI operation management system and management method are provided to solve the above problems. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent MRI operation management system and management method. Based on a full-dimensional monitoring network and a predictive maintenance system, it can realize real-time monitoring of MRI equipment status, intelligent fault warning, cross-platform data integration and safety protection, thereby reducing unplanned downtime rate, improving operation and maintenance efficiency, and alleviating the technical service pressure of grassroots medical institutions.

[0008] To achieve the above objectives, the present invention provides an intelligent MRI operation management system, including an edge computing layer and a perception layer and a cloud platform layer connected to the edge computing layer. The cloud platform layer is connected to a multi-terminal interaction module. The edge computing layer is connected to the perception layer through a 16-bit AD conversion chip or an I2C bus communication module. The edge computing layer and the cloud platform layer transmit data through a wireless network, and the cloud platform layer and the multi-terminal interaction module transmit data through a cloud API.

[0009] Preferably, the edge computing layer includes a Raspberry Pi 4B main control board and a digital-to-analog conversion module. The digital-to-analog conversion module is connected to the Raspberry Pi 4B main control board through SDA and SCL signal lines. The operating voltage range of the 16-bit AD conversion chip is set to 3.3V-5.0V, the sampling rate is set to 860 times / second, and the capacity of the I2C bus communication module is set to 1MB.

[0010] Preferably, the perception layer includes a liquid helium capacity real-time monitoring module, a magnet pressure fluctuation monitoring system, a cold head temperature dynamic acquisition unit, a cold head status monitoring module, a helium compressor working status detection device, a water-cooled temperature and humidity monitoring module, an ambient temperature and humidity monitoring module, a scanning timing and number statistics module, a power off alarm module and a water leakage monitoring module.

[0011] Preferably, the water-cooled temperature and humidity monitoring module is set to an SHT31 sensor, the measurement accuracy of the SHT31 sensor is set to ±0.2°C, and the ambient temperature and humidity monitoring module is set to a PT100 platinum resistance temperature sensor, and the measurement accuracy of the PT100 platinum resistance temperature sensor is set to ±0.1°C.

[0012] Preferably, the scanning timing and number counting module includes a reflective infrared photoelectric sensor, a relay control unit and a scanning state judgment unit. The detection distance of the reflective infrared photoelectric sensor is set to 5mm-100mm, and the response time is no more than 1ms.

[0013] Preferably, the power off alarm module includes a 220V AC main power monitoring unit, a 5V DC equipment power monitoring unit, a UPS power switching unit, an audible and visual alarm, and a 4G SMS push unit. The switching time of the UPS power switching unit is no more than 10ms. The water leakage monitoring module includes a 5V signal on-off detection unit, a water leakage detection switch, and a status judgment unit.

[0014] Preferably, the multi-terminal interaction module includes a 4K industrial display screen and a mobile terminal APP, and the size of the 4K industrial display screen is set to 55 inches.

[0015] A management method for an MRI operation intelligent management system includes the following steps: S1: Real-time collection of equipment operation data through the multi-sensor cluster of the perception layer; S2: The edge computing layer converts the equipment operation data into a format compatible with the hospital's HIS / RIS / PACS system and processes the equipment operation data. S3: Performs data analysis and fault prediction on the processed data through the cloud platform layer; S4: Visualize the equipment operation status through the multi-terminal interaction module and push early warnings based on data analysis results.

[0016] Preferably, in step S3, fault prediction is performed on the processed data through the cloud platform layer, specifically including the following steps: S31: Predicting liquid helium leakage risk based on time series analysis; S32: Predict cold head failure based on temperature change trend; S33: Predict equipment maintenance cycles based on usage frequency.

[0017] Preferably, in step S4, an early warning is pushed based on the data analysis results, specifically including the following steps: S41: Local alarm via sound and light alarm; S42: Send SMS warning via 4G network; S43: Push alarm information in real time via mobile terminal APP.

[0018] Therefore, the present invention adopts the above-mentioned MRI operation intelligent management system and management method, which has the following beneficial effects: (1) This solution adopts a three-layer architecture of "cloud-edge-end". By combining edge computing with cloud computing, it realizes efficient data processing and real-time response. The perception layer deploys a high-precision sensor cluster to realize comprehensive collection of equipment operation data. The edge computing layer is based on the Raspberry Pi 4B main control board with a built-in multi-protocol gateway, which supports seamless connection with the hospital HIS / RIS / PACS system and solves the data island problem of traditional MRI equipment. The cloud platform layer provides big data analysis, AI predictive maintenance and visualization display, and supports real-time monitoring of multiple terminals. (2) The sensor data acquisition system of this solution has the characteristics of high precision and low latency. It uses a 16-bit high-precision AD conversion chip to ensure the accurate acquisition of analog signals. It integrates SHT31 temperature and humidity sensor and PT100 platinum resistance temperature sensor to achieve accurate monitoring of the environment and water cooling system. The optical fiber sensor and relay control circuit can accurately count the number of MRI scans, avoiding the errors of traditional mechanical counters. (3) This solution is based on time series analysis and machine learning algorithms to predict the trend of key parameters of MRI equipment, achieve 48-hour fault warning, dual-channel power failure monitoring, and combine UPS power supply and 4G SMS alarm to ensure that monitoring can be maintained and maintenance personnel can be notified when the equipment is abnormally powered off. The intelligent judgment of the cold head status supports two detection modes and is compatible with MRI equipment from different manufacturers, improving the applicability of the system; (4) This solution adopts a modular hardware design to facilitate system upgrades and maintenance, supports multi-protocol data output, can adapt to the interface standards of different brands of MRI equipment, provides local and cloud dual storage solutions to ensure data security, and supports historical data backtracking analysis; (5) This solution uses a 55-inch 4K industrial screen to display the equipment's operating status in real time, push warning information via the mobile APP, support remote operation and maintenance, and achieve full-dimensional visual monitoring.

[0019] The method scheme of the present invention is further described in detail below through the drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a structural diagram of an MRI operation intelligent management system of the present invention; Figure 2 This is a structural diagram of an MRI operation intelligent management system of the present invention; Figure 3 This is a visual interface diagram of an MRI operation intelligent management system of the present invention; Figure 4 This is a circuit diagram of an intelligent management system for MRI operation according to the present invention; Figure 5 This is a flow chart of a management method of an MRI operation intelligent management system according to the present invention.

[0021] Among them: 1. Edge computing layer; 2. Perception layer; 3. Cloud platform layer; 4. Multi-terminal interaction module; 5. 16-bit AD conversion chip; 6. I2C bus communication module; 7. Raspberry Pi 4B main control board; 8. Digital-to-analog conversion module; 9. Liquid helium capacity real-time monitoring module; 10. Magnet pressure fluctuation monitoring system; 11. Cold head temperature dynamic acquisition unit; 12. Cold head status monitoring module; 13. Helium compressor working status detection device; 14. Water cooling temperature and humidity monitoring module; 15. Ambient temperature and humidity monitoring module; 16. Scan timing and number statistics 1. Measuring module; 2. Power failure alarm module; 3. Water leakage monitoring module; 4. Reflective infrared photoelectric sensor; 5. Relay control unit; 6. Scanning status judgment unit; 7. 220V AC main power monitoring unit; 8. 5V DC equipment power monitoring unit; 9. UPS power switching unit; 10. 4G SMS push unit; 11. 5V signal on / off detection unit; 12. Water leakage detection switch; 13. Status judgment unit; 14. Sound and light alarm; 15. 4K industrial display; 16. Mobile terminal APP. DETAILED DESCRIPTION

[0022] The method scheme of the present invention is further described below through the drawings and examples.

[0023] Unless otherwise defined, technical terms or scientific terms used in the present invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0024] The words “include” or “comprising” and similar words used in the present invention mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of also including other elements. The orientation or position relationship indicated by the terms “inside”, “outside”, “upper”, “lower”, etc. is based on the orientation or position relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation of the present invention. When the absolute position of the described object changes, the relative position relationship may also change accordingly. In the present invention, unless otherwise clearly stipulated and limited, the terms such as “attachment” should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral whole; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0025] Example like Figures 1 to 4As shown, this embodiment provides an MRI operation intelligent management system, which adopts a "cloud-edge-end" three-layer architecture, including an edge computing layer 1 and a perception layer 2 connected to the edge computing layer 1, and a cloud platform layer 3. The cloud platform layer 3 is connected to a multi-terminal interaction module 4. The edge computing layer 1 realizes multi-system data access and protocol conversion through a built-in gateway protocol. The perception layer 2 includes multiple sensor clusters deployed on the MRI equipment for collecting equipment operating parameters. The cloud platform layer 3 can provide data storage, analysis and visualization services. The multi-terminal interaction module 4 supports real-time status display and warning push of large-screen monitoring centers and mobile terminals, and supports cross-platform data sharing.

[0026] The edge computing layer 1 is connected to the perception layer 2 through a 16-bit AD conversion chip 5 or an I2C bus communication module 6. The edge computing layer 1 and the cloud platform layer 3 transmit data through a wireless network, and the cloud platform layer 3 and the multi-terminal interaction module 4 transmit data through a cloud API.

[0027] The edge computing layer 1 includes a Raspberry Pi 4B main control board 7 and a digital-to-analog conversion module 8. The digital-to-analog conversion module 8 is connected to the Raspberry Pi 4B main control board 7 through SDA and SCL signal lines. The digital-to-analog conversion module 8 is powered by a 5.0V power supply from the Raspberry Pi 4B main control board 7 and grounded through GND. The data after digital-to-analog conversion is transmitted to the Raspberry Pi 4B main control board 7 via SDA and SCL for integration, which can accurately collect and convert analog signals, and thus accurately measure various analog sensor signals.

[0028] The operating voltage range of the 16-bit AD conversion chip 5 is set to 3.3V-5.0V, the sampling rate is set to 860 times / second, and the capacity of the I2C bus communication module 6 is set to 1MB. The I2C bus communication module 6 is a non-volatile memory that can store device usage data for a long time.

[0029] The sensing layer 2 includes a liquid helium capacity real-time monitoring module 9, a magnet pressure fluctuation monitoring system 10, a cold head temperature dynamic acquisition unit 11, a cold head status monitoring module 12, a helium compressor working status detection device 13, a water-cooled temperature and humidity monitoring module 14, an ambient temperature and humidity monitoring module 15, a scanning timing and number statistics module 16, a power-off alarm module 17 and a water leakage monitoring module 18.

[0030] The cold head status monitoring module 12 supports two monitoring modes. The first monitoring mode is the on-off signal monitoring mode, which is suitable for the case where the cold head status signal of the external magnetic resonance equipment is on or off. The 5V signal is output to the external interface J3-4 through the GPIOPin2 of the Raspberry Pi 4B main control board 7. At the same time, the Pin30GND of the Raspberry Pi 4B main control board 7 is connected to the A1 / A2 / A3 pins of the 16-bit AD conversion chip 5, and the external interface J3-4 is connected to the cold head status relay of the magnetic resonance equipment. The relay returns a 5V signal to External interface J3-2, the 5V status signal of external interface J3-2 is transmitted to the A1 pin of the 16-bit AD conversion chip 5 through the NO2 of the relay. The 16-bit AD conversion chip 5 monitors the voltage status of the A1 pin and converts the voltage status into a digital signal, which is transmitted to the Raspberry Pi 4B main control board 7 through the I2C bus communication module 6. The Raspberry Pi 4B main control board 7 judges the status of the 5V signal in real time through the program to analyze the working status of the cold head. When the 5V signal is normal, it is defined as the cold head operating normally. When the 5V signal is lost, it is defined as a cold head failure.

[0031] The second monitoring mode is 12V voltage monitoring mode. The 12V working voltage of the cold head is connected to the external interface J2-4, and 12VCOM is connected to the external interface J2-3. The 12V signal is transmitted to the IN2 of the relay through the external interface J2-4. The 12V signal is set as the high-level trigger signal of IN2. When the cold head outputs a 12V signal, IN2 triggers the corresponding relay to connect COM2 and NO2. The GPIOPin2 of the Raspberry Pi 4B main control board 7 outputs a 5V signal to the external interface J3-4. The 5V signal is transmitted through the external interface J3 -4 is transmitted to COM2. When the external cold head signal triggers the connection between COM2 and NO2, the 5V signal returns to the A1 pin of the 16-bit AD conversion chip 5 through NO2. The 16-bit AD conversion chip 5 monitors the voltage state of the A1 pin and converts the voltage state into a digital signal. The digital signal is transmitted to the Raspberry Pi 4B main control board 7 through the I2C bus communication module 6. The Raspberry Pi 4B main control board 7 judges the state of the 5V signal in real time through the program to analyze the working state of the cold head. When the 5V signal is normal, it is defined as the cold head operating normally. When the 5V signal is lost, it is defined as a cold head failure.

[0032] The water-cooled temperature and humidity monitoring module 14 is configured as an SHT31 sensor. The measurement accuracy of the SHT31 sensor is set to ±0.2°C and is powered by the Raspberry Pi 4B main control board 7. The current flows through the VCC port and is output to the J1 socket. After being output from the J1 socket to the SHT31 sensor, the current returns from GND to the negative terminal of the Raspberry Pi 4B main control board 7. The data collected by the SHT31 sensor is transmitted back to the Raspberry Pi 4B main control board 7 via the SCL and SDA lines. The ambient temperature and humidity monitoring module 15 is set as a PT100 platinum resistance temperature sensor. The measurement accuracy of the PT100 platinum resistance temperature sensor is set to ±0.1°C. It is powered by the Raspberry Pi 4B main control board 7 with 3.3V-5.5V. After the current flows through the PT100 platinum resistance temperature sensor, it returns to the Raspberry Pi 4B main control board 7 and is grounded through GND. The data collected by the PT100 platinum resistance temperature sensor is transmitted through the GPIO27 line and sent to the Raspberry Pi 4B main control board 7.

[0033] The scanning timing and number counting module 16 is powered by 12.0V from the J2 power port. The current is provided to the scanning timing and number counting module 16 after passing through the positive pole of the relay, and then returns to the power supply COM1 after passing through the negative pole of the relay. The optical fiber sensor amplifier leads out the optical fiber and is installed at the target position of the MRI or CT, such as the inspection bed mark position. When the inspection bed mark position moves to the detection range of the optical fiber sensor, the optical fiber amplifier sends a 12V signal. When the mark position is not within the detection range of the optical fiber sensor, it sends a 0V signal. When the inspection bed mark position appears in the detection range of the optical fiber sensor, the acquisition line sends 12V to IN1. IN1 and the positive pole of the relay form a low level to trigger the relay, and COM1 and NC1 are turned on. The scanning timing and number statistics module 16 includes a reflective infrared photoelectric sensor 19, a relay control unit 20 and a scanning status judgment unit 21. The detection distance of the reflective infrared photoelectric sensor 19 is set to 5mm-100mm, and the response time is no more than 1ms. The relay control unit 20 realizes the status on and off by detecting the 12V signal.

[0034] GPIO Pin 2 of the Raspberry Pi 4B main control board 7 outputs a 5V signal, which is sent to COM1 via external interfaces J3-4 and COM2. When the fiber amplifier signal triggers COM1 and NO1 to conduct, the 5V signal is sent back to the A3 pin of the 16-bit AD converter chip 5 via NO1. The 16-bit AD converter chip 5 monitors the voltage state of the A3 pin and converts the voltage state into a digital signal. The digital signal is transmitted to the Raspberry Pi 4B main control board 7 via the I2C bus communication module 6. The Raspberry Pi 4B main control board 7 uses a program to determine the state of the 5V signal on the A3 pin in real time to analyze the scanning state. The rising edge of 0V to 5V triggers the start of the recording scan, and the falling edge of 5V to 0V triggers the end of the recording scan.

[0035] The power-off alarm module 17 is powered by the power-off 5V. The current returns to the negative pole after the power is cut off in A0 of the 16-bit AD conversion chip 5, and finally returns to the power-off COM1. If the magnetic resonance device suddenly loses power, the loss of the 5V signal will generate a reminder. The front end of the alarm system is connected to the UPS provided by the system for continuous power supply, and it can still operate normally after the system is powered off. The power-off alarm module 17 includes a 220V AC main power monitoring unit 22, a 5V DC device power monitoring unit 23, a UPS power switching unit 24, an audible and visual alarm 29 and a 4G SMS push unit 25. The switching time of the UPS power switching unit 24 is no more than 10ms. The water leakage monitoring module 18 includes a 5V signal on-off detection unit 26, a water leakage detection switch 27 and a status judgment unit 28. The status judgment unit 28 performs fault judgment based on the 5V signal status of the A2 pin of the 16-bit AD conversion chip 5. The GPIOPin2 of the Raspberry Pi 4B main control board 7 outputs a 5V signal to the external interface J3-4. The external interface J3-4 is connected to the water leakage detection switch 27. When no water leakage is detected, the switch is closed, and the 5V signal is returned to the external interface J3-2 through the water leakage detection switch. The external interface J3-2 transmits the 5V status signal to the A2 pin of the 16-bit AD conversion chip 5. The 16-bit AD conversion chip 5 monitors the voltage status of the A2 pin and converts the voltage status into a digital signal, which is transmitted to the Raspberry Pi 4B main control board 7 through the I2C bus communication module 6. The Raspberry Pi 4B main control board 7 uses a program to judge the 5V signal status of the A2 pin in real time to analyze the water leakage status. When 5V is normal, it is defined as normal, and when the 5V signal is lost, it is defined as a fault.

[0036] The multi-terminal interaction module 4 includes a 4K industrial display screen 30 and a mobile terminal APP 31. The size of the 4K industrial display screen 30 is set to 55 inches, which can realize local and cloud dual data storage solutions.

[0037] like Figure 5 As shown, a management method of an MRI operation intelligent management system includes the following steps: S1: Real-time collection of equipment operation data through the multi-sensor cluster of the perception layer; S2: The edge computing layer converts the device operation data into a format compatible with the hospital's HIS / RIS / PACS system to adapt to the communication protocols of different brands of MRI equipment and process the device operation data. S3: Performs data analysis and fault prediction on the processed data through the cloud platform layer; In step S3, fault prediction is performed on the processed data through the cloud platform layer, which specifically includes the following steps: S31: Predicting liquid helium leakage risk based on time series analysis; S32: Predict cold head failure based on temperature change trend; S33: Predict equipment maintenance cycles based on usage frequency.

[0038] S4: Visualize the equipment operation status through the multi-terminal interaction module and push early warnings based on data analysis results.

[0039] In step S4, an early warning is pushed based on the data analysis results, which specifically includes the following steps: S41: Local alarm via sound and light alarm; S42: Send SMS warning via 4G network; S43: Push alarm information in real time via mobile terminal APP.

[0040] Therefore, the present invention adopts the above-mentioned MRI operation intelligent management system and management method, and realizes comprehensive monitoring and intelligent early warning of the operating status of MRI equipment through the collaborative work of multiple modules. The system adopts a modular design concept and integrates high-precision data acquisition, intelligent analysis and multi-terminal interaction functions, providing an innovative solution for the preventive maintenance of medical equipment.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the method scheme of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, ordinary method personnel in this field should understand that they can still modify or replace the method scheme of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified method scheme to deviate from the spirit and scope of the method scheme of the present invention.

Claims

1. An intelligent management system for MRI operation, characterized in that: It includes an edge computing layer and a perception layer and a cloud platform layer connected to the edge computing layer. The cloud platform layer is connected to the multi-terminal interaction module. The edge computing layer is connected to the perception layer through a 16-bit AD conversion chip or an I2C bus communication module. The edge computing layer and the cloud platform layer transmit data through a wireless network. The cloud platform layer and the multi-terminal interaction module transmit data through a cloud API.

2. The intelligent management system for MRI operation according to claim 1, characterized in that: The edge computing layer includes a Raspberry Pi 4B main control board and a digital-to-analog conversion module. The digital-to-analog conversion module is connected to the Raspberry Pi 4B main control board through SDA and SCL signal lines. The operating voltage range of the 16-bit AD conversion chip is set to 3.3V-5.0V, the sampling rate is set to 860 times / second, and the capacity of the I2C bus communication module is set to 1MB.

3. The intelligent management system for MRI operation according to claim 1, characterized in that: The perception layer includes a liquid helium capacity real-time monitoring module, a magnet pressure fluctuation monitoring system, a cold head temperature dynamic acquisition unit, a cold head status monitoring module, a helium compressor working status detection device, a water-cooled temperature and humidity monitoring module, an ambient temperature and humidity monitoring module, a scan timing and number statistics module, a power-off alarm module, and a water leakage monitoring module.

4. The intelligent management system for MRI operation according to claim 3, characterized in that: The water-cooled temperature and humidity monitoring module is set to an SHT31 sensor, and the measurement accuracy of the SHT31 sensor is set to ±0.2°C. The ambient temperature and humidity monitoring module is set to a PT100 platinum resistance temperature sensor, and the measurement accuracy of the PT100 platinum resistance temperature sensor is set to ±0.1°C.

5. The intelligent management system for MRI operation according to claim 3, characterized in that: The scanning timing and number counting module includes a reflective infrared photoelectric sensor, a relay control unit and a scanning state judgment unit. The detection distance of the reflective infrared photoelectric sensor is set to 5mm-100mm, and the response time is no more than 1ms.

6. The intelligent management system for MRI operation according to claim 3, characterized in that: The power off alarm module includes a 220V AC main power monitoring unit, a 5V DC equipment power monitoring unit, a UPS power switching unit, an audible and visual alarm, and a 4G SMS push unit. The switching time of the UPS power switching unit is no more than 10ms. The water leakage monitoring module includes a 5V signal on-off detection unit, a water leakage detection switch, and a status judgment unit.

7. The intelligent management system for MRI operation according to claim 1, characterized in that: The multi-terminal interaction module includes a 4K industrial display and a mobile terminal APP. The size of the 4K industrial display is set to 55 inches.

8. A management method for the MRI operation intelligent management system according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1: Real-time collection of equipment operation data through the multi-sensor cluster of the perception layer; S2: The edge computing layer converts the equipment operation data into a format compatible with the hospital's HIS / RIS / PACS system and processes the equipment operation data. S3: Performs data analysis and fault prediction on the processed data through the cloud platform layer; S4: Visualize the equipment operation status through the multi-terminal interaction module and push early warnings based on data analysis results.

9. The management method of the MRI operation intelligent management system according to claim 8, characterized in that: In step S3, fault prediction is performed on the processed data through the cloud platform layer, which specifically includes the following steps: S31: Predicting liquid helium leakage risk based on time series analysis; S32: Predict cold head failure based on temperature change trend; S33: Predict equipment maintenance cycles based on usage frequency.

10. The management method of the MRI operation intelligent management system according to claim 8, characterized in that: In step S4, an early warning is pushed based on the data analysis results, which specifically includes the following steps: S41: Local alarm via sound and light alarm; S42: Send SMS warning via 4G network; S43: Push alarm information in real time via mobile terminal APP.

Images