CN111025128A - Medical equipment fault detection system and method based on AI - Google Patents
Medical equipment fault detection system and method based on AI Download PDFInfo
- Publication number
- CN111025128A CN111025128A CN201911330429.6A CN201911330429A CN111025128A CN 111025128 A CN111025128 A CN 111025128A CN 201911330429 A CN201911330429 A CN 201911330429A CN 111025128 A CN111025128 A CN 111025128A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- neural network
- network model
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/28—Testing of electronic circuits, e.g. by signal tracer
- G01R31/2832—Specific tests of electronic circuits not provided for elsewhere
- G01R31/2836—Fault-finding or characterising
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of fault detection, and particularly discloses a medical equipment fault detection system and method based on AI (artificial intelligence), wherein the system comprises a detection terminal, a server and a receiving terminal; the detection terminal is used for acquiring fault data of the working circuit of the medical equipment; the server is used for acquiring fault data from the detection terminal; classifying fault data according to the type of the fault and establishing a training sample data set; the service end is also used for inputting the training sample data set into the BP neural network model for training to obtain the trained BP neural network model; the detection terminal is also used for acquiring the operating data of the working circuit of the medical equipment; the service end is used for acquiring operation data from the detection terminal and inputting the operation data into the trained BP neural network model; when the trained BP neural network model outputs an output result containing a fault type, the server is also used for sending the output result to the receiving end. By adopting the technical scheme of the invention, the detection data can be flexibly analyzed and the fault type can be judged.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a medical equipment fault detection system and method based on AI.
Background
At present, equipment of a large-scale three-in-one hospital is rapidly increased, clinical maintenance engineers are insufficient, and the hospital guarantee requirement is urgent; meanwhile, secondary hospitals and community hospitals cannot fully guarantee normal operation of hospital equipment because of few maintenance personnel, insufficient experience of the maintenance personnel and few processing faults. Therefore, large hospitals, such as the third-class hospitals and the second-class hospitals and community hospitals, face a great pressure for equipment maintenance and guarantee.
Although the present large-scale equipment generally has a detection circuit (a voltage detection circuit and a current detection circuit according to the system requirement) for detecting signals in an external circuit or an internal circuit; however, the collected signals are usually used as reference data for understanding the operation condition of the equipment for a certain period of time or as reference data for analyzing faults after the equipment is out of order. And the collected signals usually need to be actively called by maintenance personnel, so that the prior fault early warning and the active analysis of fault reasons cannot be carried out by means of the signals.
Therefore, chinese patent publication No. CN106597160A discloses a method and an apparatus for detecting failure of electronic equipment. The method comprises the steps of acquiring environment data of the electronic equipment when the electronic equipment runs; extracting operation characteristics from the environmental data, wherein the operation characteristics comprise the phase and amplitude of a voltage waveform, the phase and amplitude of a current waveform, the phase and amplitude of a temperature waveform and the phase and amplitude of a humidity waveform; comparing the operating characteristics with prestored comparison characteristics; and carrying out fault detection on the electronic equipment according to the comparison result.
In the above scheme, although the operating characteristics can be compared with the pre-stored comparison characteristics; the electronic equipment is subjected to fault detection according to the comparison result, however, the detection mode is mainly specific to a specific fault due to the fact that the comparison is carried out through the comparison features stored in advance, the detection mode is narrow in detection area and poor in flexibility. In practical applications, the current and voltage waveforms of the medical device during a failure usually vary greatly, and accurate detection is difficult to be made only by comparing with the pre-stored comparison features.
Therefore, a fault detection system and method capable of flexibly analyzing the detection data and determining the fault type are needed.
Disclosure of Invention
The invention provides a medical equipment fault detection system and method based on AI, which can flexibly analyze detection data and judge fault types.
In order to solve the technical problem, the present application provides the following technical solutions:
the medical equipment fault detection system based on the AI comprises a detection terminal, a server and a receiving terminal;
the detection terminal is used for acquiring fault data of the working circuit of the medical equipment;
the server is used for acquiring fault data from the detection terminal; classifying fault data according to the type of the fault and establishing a training sample data set; the service end is also used for inputting the training sample data set into the BP neural network model for training to obtain the trained BP neural network model; the detection terminal is also used for acquiring the operating data of the working circuit of the medical equipment; the service end is used for acquiring operation data from the detection terminal and inputting the operation data into the trained BP neural network model; when the trained BP neural network model outputs an output result containing a fault type, the server is also used for sending the output result to the receiving end.
The basic scheme principle and the beneficial effects are as follows:
in the scheme, a BP neural network model with self-learning capability is introduced, and the BP neural network model is trained according to a training sample data set, so that the BP neural network model has the capability of judging the fault type, namely the AI intelligence is realized in the judgment of the fault type, manual intervention is not needed, and the complex and variable faults can be dealt with. After the training of the BP neural network model is finished, the operation data of the medical equipment working circuit collected by the detection terminal can be analyzed, and when the medical equipment fails, the trained BP neural network model can output the failure type in time, so that the failure judgment is intelligent. Compared with the prior art, the fault judgment is more flexible and the accuracy is higher.
Further, the receiving end is further used for sending a maintenance suggestion to the service end according to the received fault type, and the service end is further used for establishing a maintenance suggestion library according to the fault type and the maintenance suggestion.
And a maintenance engineer sends a maintenance suggestion to the service end according to the fault type, so that the service end is facilitated to integrate the existing maintenance experience into a maintenance suggestion library.
Further, the server is also used for matching the corresponding maintenance suggestions from the maintenance suggestion library according to the fault types and sending the maintenance suggestions to the receiving end.
And outputting the fault type through the existing experience data, simultaneously giving a maintenance suggestion, and finally repairing the fault equipment through the maintenance suggestion after an engineer checks the information on the receiving end. The system is popularized to secondary hospitals and community hospitals, so that the secondary hospitals and the community hospitals have a 'virtual engineer' with superior capability, and the purposes of improving the maintenance capability of fault equipment and the guarantee level of medical equipment of the secondary hospitals and the community hospitals are finally achieved.
Further, the fault data and the operational data each include current characteristic data.
The fault type can be accurately judged by the change of the current.
Further, the receiving end is also used for sending actual fault information to the server end when the received fault type is not consistent with the actual fault type; the server is also used for feeding back actual fault information to the BP neural network model.
Because the BP neural network model cannot achieve 100% accuracy, when the PB neural network model judges an error, an engineer feeds back the error in time through a receiving end, and the BP neural network model is convenient to self-adjust so as to improve the accuracy of judgment. The method is also a process of continuously learning and continuously optimizing, so that the operation efficiency and accuracy of the system are finally improved, and the working quality and credibility of a virtual engineer are improved.
Further, the detection terminal is in wireless connection with the server side.
Through wireless connection, data transmission between the detection terminal and the server side which are far away from each other in physical distance is facilitated.
The AI-based medical equipment fault detection method comprises the following steps:
s1, the detection terminal collects fault data of the working circuit of the medical equipment;
s2, the server side acquires fault data from the detection terminal; classifying fault data according to the type of the fault and establishing a training sample data set; inputting the training sample data set into a BP neural network model for training to obtain a trained BP neural network model;
s4, acquiring the operation data of the medical equipment working circuit by the detection terminal;
s5, the server side obtains operation data and inputs the operation data into the trained BP neural network model; and when the trained BP neural network model outputs an output result containing the fault type, the server side sends the output result to the receiving side.
In the scheme, a BP neural network model with self-learning capability is introduced, and the BP neural network model is trained according to a training sample data set, so that the BP neural network model has the capability of judging the fault type, namely the AI intelligence is realized in the judgment of the fault type, manual intervention is not needed, and the complex and variable faults can be dealt with. After the training of the BP neural network model is finished, the operation data of the medical equipment working circuit collected by the detection terminal can be analyzed, and when the medical equipment fails, the trained BP neural network model can output the failure type in time, so that the failure judgment is intelligent. Compared with the prior art, the fault judgment is more flexible and the accuracy is higher.
Further, the method also comprises S6, the receiving end sends maintenance suggestions to the service end according to the received fault types, and the service end establishes a maintenance suggestion library according to the fault types and the maintenance suggestions.
And a maintenance engineer sends a maintenance suggestion to the service end according to the fault type, so that the service end is facilitated to integrate the existing maintenance experience into a maintenance suggestion library.
Further, the method further comprises S7, and the service end matches the corresponding maintenance suggestion from the maintenance suggestion library according to the fault type and sends the maintenance suggestion to the receiving end.
And outputting the fault type through the existing experience data, simultaneously giving a maintenance suggestion, and finally repairing the fault equipment through the maintenance suggestion after an engineer checks the information on the receiving end. The system is popularized to secondary hospitals and community hospitals, so that the secondary hospitals and the community hospitals have a 'virtual engineer' with superior capability, and the purposes of improving the maintenance capability of fault equipment and the guarantee level of medical equipment of the secondary hospitals and the community hospitals are finally achieved.
Further, the method also comprises S8, and the receiving end sends actual fault information to the service end when the received fault type is not consistent with the actual fault type; and the server side feeds back the actual fault information to the BP neural network model.
Because the BP neural network model cannot achieve 100% accuracy, when the PB neural network model judges an error, an engineer feeds back the error in time through a receiving end, and the BP neural network model is convenient to self-adjust so as to improve the accuracy of judgment. The method is also a process of continuously learning and continuously optimizing, so that the operation efficiency and accuracy of the system are finally improved, and the working quality and credibility of a virtual engineer are improved.
Drawings
Fig. 1 is a block diagram of a first embodiment of an AI-based medical device fault detection system.
Detailed Description
The following is further detailed by way of specific embodiments:
example one
As shown in fig. 1, the AI-based medical device fault detection system of the present embodiment includes a detection terminal, a server, and a receiving terminal.
The detection terminal and the receiving terminal are both in wireless connection with the server. The detection terminal is used for collecting fault data of the working circuit of the medical equipment. The fault data includes current signature data. In this embodiment, the current characteristic data includes a current change value at the instant of occurrence of the fault and within a certain time before the occurrence of the fault.
In the embodiment, the detection terminal adopts a sonoff pow R2 power monitor and has a WiFi function, so that the wireless uploading of current characteristic data can be realized; the maximum power is 3500W, and the device can adapt to most medical equipment. If the medical equipment exceeds the power, a power monitor with a larger dosage range can be selected. Because the detection terminal does not have the capacity of judging the fault, when the medical equipment has the fault in the early stage, a maintenance engineer confirms the fault on site and maintains the medical equipment, and meanwhile, the detection terminal is controlled to upload fault data; that is, the resolution of the earlier fault data is mainly done by human.
And the server is used for acquiring fault data from the detection terminal. Classifying fault data according to the type of the fault and establishing a training sample data set; and the server is also used for inputting the training sample data set into the BP neural network model for training to obtain the trained BP neural network model. Because a large number of medical devices are arranged in a hospital, a training sample data set with a large enough data size can be obtained by collecting fault data of the medical devices for a long time; through training of the training sample data set, the BP neural network model has the capability of distinguishing fault types, and becomes an online 'virtual engineer'. In this embodiment, the server is a remote server.
The detection terminal is also used for acquiring the operating data of the working circuit of the medical equipment; the operational data includes current signature data. In other words, after the BP neural network model is trained successfully, the detection terminal acquires and uploads the current characteristic data of the working circuit of the medical equipment in real time, and a maintenance engineer is not required to perform screening.
The service end is used for acquiring operation data from the detection terminal and inputting the operation data into the trained BP neural network model; when the trained BP neural network model outputs an output result containing a fault type, the server is also used for sending the output result to the receiving end. If the medical equipment has no fault, after the BP neural network model after data input training is operated, the BP neural network model can output a normal output result of the equipment, and the normal output result of the equipment cannot be sent to a receiving end because the equipment is normal and does not need to be processed.
The receiving end is also used for sending maintenance suggestions to the service end according to the received fault types, and the service end is also used for establishing a maintenance suggestion library according to the fault types and the maintenance suggestions. The receiving end is a mobile device used by a maintenance engineer, such as a mobile phone, a tablet and the like. In the early stage, a maintenance engineer sends a maintenance suggestion to the service end according to the fault type, and the service end is helped to integrate the existing maintenance experience into a maintenance suggestion library.
After a period of operation, the maintenance suggestion library is gradually enriched; after having a large number of maintenance suggestions, when the BP neural network model outputs the output result containing the fault type again, the server is further configured to match the corresponding maintenance suggestions from the maintenance suggestion library according to the fault types, and send the maintenance suggestions to the receiving end. At this time, the maintenance engineer is not required to have rich experience, and even the maintenance engineer with poor capability can also carry out maintenance on the medical equipment through the maintenance advice, so that the capability requirement on the maintenance engineer is reduced.
The receiving end is also used for sending actual fault information to the server end when the received fault type is not consistent with the actual fault type; the server is also used for feeding back actual fault information to the BP neural network model. Because the BP neural network model is not 100% accurate, when the PB neural network model makes a fault, the PB neural network model can feed back timely, so that the BP neural network model can adjust itself conveniently, and the accuracy of judgment is improved.
In the scheme, the BP neural network model is introduced, so that the fault detection system has the autonomous learning capability and becomes a 'virtual engineer' which can monitor equipment, identify faults, judge the faults and give repair suggestions.
The embodiment also provides a medical equipment fault detection method based on AI, which comprises the following steps:
s1, the detection terminal collects fault data of the working circuit of the medical equipment; the fault data includes current signature data. In this embodiment, the current characteristic data includes a current change value at the instant of occurrence of the fault and within a certain time before the occurrence of the fault.
S2, the server side acquires fault data from the detection terminal; classifying fault data according to the type of the fault and establishing a training sample data set; inputting the training sample data set into a BP neural network model for training to obtain a trained BP neural network model;
s4, acquiring the operation data of the medical equipment working circuit by the detection terminal;
s5, the server side obtains operation data and inputs the operation data into the trained BP neural network model; and when the trained BP neural network model obtains and outputs an output result containing the fault type, the server side sends the output result to the receiving side. And when the trained BP neural network model outputs a normal output result of the equipment, the server does not send the output result.
S6, the receiving end sends maintenance suggestions to the service end according to the received fault types, and the service end establishes a maintenance suggestion library according to the fault types and the maintenance suggestions.
And S7, the server side matches the corresponding maintenance suggestions from the maintenance suggestion library according to the fault types and sends the maintenance suggestions to the receiving side.
S8, the receiving end sends actual fault information to the service end when the received fault type is not in accordance with the actual fault type; and the server side feeds back the actual fault information to the BP neural network model.
Example two
The difference between this embodiment and the first embodiment is that, in the AI-based medical device fault detection system in this embodiment, the detection terminal is configured to collect fault data of the working circuit of the medical device and send the fault data to the server, and the receiving terminal is further configured to send a maintenance suggestion associated with the fault data to the server. The method is convenient for the server to establish the training sample data set and simultaneously establish the maintenance suggestion library, is beneficial to the early judgment of the fault phenomenon of a virtual engineer and the fault diagnosis result, and has the capability of giving a repair suggestion.
The above are merely examples of the present invention, and the present invention is not limited to the field related to this embodiment, and the common general knowledge of the known specific structures and characteristics in the schemes is not described herein too much, and those skilled in the art can know all the common technical knowledge in the technical field before the application date or the priority date, can know all the prior art in this field, and have the ability to apply the conventional experimental means before this date, and those skilled in the art can combine their own ability to perfect and implement the scheme, and some typical known structures or known methods should not become barriers to the implementation of the present invention by those skilled in the art in light of the teaching provided in the present application. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. The medical equipment fault detection system based on AI is characterized by comprising a detection terminal, a server and a receiving terminal; the detection terminal is used for acquiring fault data of the working circuit of the medical equipment; the server is used for acquiring fault data from the detection terminal; classifying fault data according to the type of the fault and establishing a training sample data set; the service end is also used for inputting the training sample data set into the BP neural network model for training to obtain the trained BP neural network model; the detection terminal is also used for acquiring the operating data of the working circuit of the medical equipment; the service end is used for acquiring operation data from the detection terminal and inputting the operation data into the trained BP neural network model; when the trained BP neural network model outputs an output result containing a fault type, the server is also used for sending the output result to the receiving end.
2. The AI-based medical device fault detection system of claim 1, wherein: the receiving end is further used for sending maintenance suggestions to the service end according to the received fault types, and the service end is further used for establishing a maintenance suggestion library according to the fault types and the maintenance suggestions.
3. The AI-based medical device fault detection system of claim 2, wherein: and the server is also used for matching the corresponding maintenance suggestions from the maintenance suggestion library according to the fault types and sending the maintenance suggestions to the receiving end.
4. The AI-based medical device fault detection system of claim 3, wherein: the fault data and the operational data each include current signature data.
5. The AI-based medical device fault detection system of claim 4, wherein: the receiving end is also used for sending actual fault information to the server end when the received fault type is not consistent with the actual fault type; the server is also used for feeding back actual fault information to the BP neural network model.
6. The AI-based medical device fault detection system of claim 5, wherein: and the detection terminal is in wireless connection with the server.
7. The AI-based medical equipment fault detection method is characterized by comprising the following steps of:
s1, the detection terminal collects fault data of the working circuit of the medical equipment;
s2, the server side acquires fault data from the detection terminal; classifying fault data according to the type of the fault and establishing a training sample data set; inputting the training sample data set into a BP neural network model for training to obtain a trained BP neural network model;
s4, acquiring the operation data of the medical equipment working circuit by the detection terminal;
s5, the server side obtains operation data and inputs the operation data into the trained BP neural network model; and when the trained BP neural network model outputs an output result containing the fault type, the server side sends the output result to the receiving side.
8. The AI-based medical device fault detection method of claim 7, wherein: and S6, the receiving end sends maintenance suggestions to the service end according to the received fault types, and the service end establishes a maintenance suggestion library according to the fault types and the maintenance suggestions.
9. The AI-based medical device fault detection method of claim 8, wherein: and S7, the server matches the corresponding maintenance suggestion from the maintenance suggestion library according to the fault type and sends the maintenance suggestion to the receiving end.
10. The AI-based medical device fault detection method of claim 9, wherein: the method also comprises S8, wherein the receiving end sends actual fault information to the service end when the received fault type is not consistent with the actual fault type; and the server side feeds back the actual fault information to the BP neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911330429.6A CN111025128A (en) | 2019-12-20 | 2019-12-20 | Medical equipment fault detection system and method based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911330429.6A CN111025128A (en) | 2019-12-20 | 2019-12-20 | Medical equipment fault detection system and method based on AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111025128A true CN111025128A (en) | 2020-04-17 |
Family
ID=70212436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911330429.6A Pending CN111025128A (en) | 2019-12-20 | 2019-12-20 | Medical equipment fault detection system and method based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111025128A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903327A (en) * | 2021-01-26 | 2021-06-04 | 普天数字健康城市科技有限公司 | Medical equipment fault detection method based on deep learning |
| CN115157324A (en) * | 2022-08-29 | 2022-10-11 | 湖南医科医工科技有限公司 | Fault protection system and method for surgical robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| CN205750856U (en) * | 2016-04-13 | 2016-11-30 | 云南电网有限责任公司电力科学研究院 | A kind of power equipment analysis and decision system |
| CN107192939A (en) * | 2017-06-08 | 2017-09-22 | 京东方科技集团股份有限公司 | A kind of detection method and detecting system of the working condition of circuit |
| CN108172288A (en) * | 2018-01-05 | 2018-06-15 | 深圳倍佳医疗科技服务有限公司 | Medical Devices intelligent control method, device and computer readable storage medium |
| CN108256654A (en) * | 2018-01-02 | 2018-07-06 | 中电长城(长沙)信息技术有限公司 | A kind of equipment report barrier and fault diagnosis method and system |
| CN109086889A (en) * | 2018-09-30 | 2018-12-25 | 广东电网有限责任公司 | Terminal fault diagnostic method neural network based, device and system |
| CN109978190A (en) * | 2019-03-29 | 2019-07-05 | 中国原子能科学研究院 | A kind of medical cyclotron remote failure diagnosis system based on artificial intelligence |
| CN110390404A (en) * | 2019-07-12 | 2019-10-29 | 杭州培慕科技有限公司 | A kind of RCM in knowledge based library and data management |
-
2019
- 2019-12-20 CN CN201911330429.6A patent/CN111025128A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| CN205750856U (en) * | 2016-04-13 | 2016-11-30 | 云南电网有限责任公司电力科学研究院 | A kind of power equipment analysis and decision system |
| CN107192939A (en) * | 2017-06-08 | 2017-09-22 | 京东方科技集团股份有限公司 | A kind of detection method and detecting system of the working condition of circuit |
| CN108256654A (en) * | 2018-01-02 | 2018-07-06 | 中电长城(长沙)信息技术有限公司 | A kind of equipment report barrier and fault diagnosis method and system |
| CN108172288A (en) * | 2018-01-05 | 2018-06-15 | 深圳倍佳医疗科技服务有限公司 | Medical Devices intelligent control method, device and computer readable storage medium |
| CN109086889A (en) * | 2018-09-30 | 2018-12-25 | 广东电网有限责任公司 | Terminal fault diagnostic method neural network based, device and system |
| CN109978190A (en) * | 2019-03-29 | 2019-07-05 | 中国原子能科学研究院 | A kind of medical cyclotron remote failure diagnosis system based on artificial intelligence |
| CN110390404A (en) * | 2019-07-12 | 2019-10-29 | 杭州培慕科技有限公司 | A kind of RCM in knowledge based library and data management |
Non-Patent Citations (2)
| Title |
|---|
| 罗林聪 等: "基于BP神经网络的医疗设备精准预防性维护", 《医疗卫生装备》 * |
| 陈刚 等: "基于人工神经网络的医疗设备故障诊断研究", 《现代机械》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903327A (en) * | 2021-01-26 | 2021-06-04 | 普天数字健康城市科技有限公司 | Medical equipment fault detection method based on deep learning |
| CN115157324A (en) * | 2022-08-29 | 2022-10-11 | 湖南医科医工科技有限公司 | Fault protection system and method for surgical robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10288043B2 (en) | Wind turbine condition monitoring method and system | |
| EP3557819A8 (en) | Server failure detection method and system | |
| CN105424395B (en) | Method and device for determining equipment fault | |
| RU2557771C1 (en) | Technical control and diagnostics of drone onboard hardware with decision making support and complex of check-and-adjust hardware with intellectual decision making support system to this end | |
| CN116125361B (en) | Voltage transformer error evaluation method, system, electronic equipment and storage medium | |
| KR102648377B1 (en) | Intelligent integrated wiring board with network cable quality monitoring | |
| CN111025128A (en) | Medical equipment fault detection system and method based on AI | |
| CN106529834A (en) | Method and system for evaluating nuclear power plant safety state and nuclear power plant device | |
| CN110503977A (en) | A kind of substation equipment audio signal sample analysis system | |
| CN110723166A (en) | Turnout monitoring method and system | |
| CN115877198A (en) | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation | |
| CN106803797A (en) | A kind of VoIP speech quality method for objectively evaluating based on network parameter | |
| CN111275215A (en) | Voltage monitor fault self-diagnosis method and system based on Internet of things | |
| CN110988560A (en) | Medical equipment fault detection system and method based on real-time current | |
| CN115689320A (en) | Health management method and device for base station operation and computer readable storage medium | |
| CN104950832B (en) | Steel plant's control system | |
| CN115586402B (en) | Power distribution network fault diagnosis and processing method | |
| CN117119015A (en) | Operation and maintenance management system and method based on Internet of things | |
| CN116466166A (en) | Fault detection method, system and device for large-screen equipment | |
| RU2700302C1 (en) | Method and device for remote monitoring and technical diagnostics of railway automation and telemechanics devices | |
| CN116106656A (en) | Auxiliary identification method for defects of power equipment based on mobile application terminal | |
| CN115456065A (en) | Cloud edge cooperation-based power distribution terminal health state diagnosis method and device | |
| CN118432710B (en) | Method for reporting fault of optical fiber communication link | |
| CN118101429B (en) | Power distribution network communication fault diagnosis method and system | |
| US20230131038A1 (en) | Distribution grid failure symptom cause estimation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |
|
| RJ01 | Rejection of invention patent application after publication |