CN116844708A - Medical equipment fault prediction method and system based on artificial intelligence - Google Patents
Medical equipment fault prediction method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN116844708A CN116844708A CN202310863011.1A CN202310863011A CN116844708A CN 116844708 A CN116844708 A CN 116844708A CN 202310863011 A CN202310863011 A CN 202310863011A CN 116844708 A CN116844708 A CN 116844708A
- Authority
- CN
- China
- Prior art keywords
- fault
- signal
- time
- medical equipment
- maintenance
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 238000012423 maintenance Methods 0.000 claims abstract description 114
- 238000001514 detection method Methods 0.000 claims abstract description 54
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention belongs to the technical field of medical equipment supervision, in particular to a medical equipment fault prediction method and a medical equipment fault prediction system based on artificial intelligence, wherein the medical equipment fault prediction system comprises a fault prediction platform, an operation fault history analysis module, an operation maintenance supervision module, a real-time operation parameter detection analysis module and an operation external influence parameter detection analysis module; according to the invention, the operation stop signal or the operation unimpeded signal is generated by analyzing the operation-time maintenance positive correlation signal or the operation-time maintenance uncorrelated signal, the operation of the corresponding medical equipment is stopped in time after the operation stop signal is generated, and the effective prediction and risk detection analysis of the operation faults of the medical equipment are realized by detecting and analyzing the real-time operation parameter data and the external environment influence parameter data of the corresponding medical equipment, so that medical management staff can timely make targeted treatment measures.
Description
Technical Field
The invention relates to the technical field of medical equipment supervision, in particular to a medical equipment fault prediction method and system based on artificial intelligence.
Background
The medical equipment refers to instruments and equipment used for human bodies singly or in combination, and is the most basic element of medical treatment, scientific research, teaching, institutions and clinical discipline work, namely, the medical equipment comprises professional medical equipment and household medical equipment; in the operation process of the medical equipment, the medical equipment is often failed due to various factors, and even the medical equipment is completely scrapped; at present, when the operation of the medical equipment is controlled, effective prediction and risk detection analysis of the operation faults of the medical equipment cannot be realized, accurate early warning feedback cannot be timely performed, corresponding medical management staff cannot timely make targeted treatment measures, the safety and stability operation of the medical equipment are not guaranteed, the service life of the medical equipment is also not improved, the intelligent degree is low, and the improvement is to be performed; in view of the above technical drawbacks, a solution is now proposed. .
Disclosure of Invention
The invention aims to provide a medical equipment fault prediction method and system based on artificial intelligence, which solve the problems that the effective prediction and risk detection analysis of the operation fault of medical equipment cannot be realized, accurate early warning feedback cannot be performed in time, corresponding medical management staff cannot make corresponding countermeasures in time, the safety and stable operation of the medical equipment are not guaranteed, the service life of the medical equipment is not improved, and the intelligent degree is low in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an artificial intelligence-based medical equipment fault prediction method comprises the following steps:
step one, an operation fault history analysis module analyzes to generate a time-of-operation maintenance positive correlation signal or a time-of-operation maintenance non-correlation signal, a step two is performed after the time-of-operation maintenance positive correlation signal is generated, and a step three and a step four are performed after the time-of-operation maintenance non-correlation signal is generated;
analyzing the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal, stopping the operation of the corresponding medical equipment in time after the operation stop signal is generated, maintaining the medical equipment according to the need, and performing the third step and the fourth step after the operation unimpeded signal is generated;
detecting and analyzing real-time operation parameter data of corresponding medical equipment, generating an operation fault early warning signal, an operation fault assessment signal or a preliminary prediction normal signal through analysis, and transmitting the operation fault early warning signal, the operation fault assessment signal or the preliminary prediction normal signal to a fault prediction platform;
detecting and analyzing external environment influence parameter data of corresponding medical equipment, generating an external influence fault early warning signal, an external influence fault consideration signal or an in-depth prediction normal signal through analysis, and sending the external influence fault early warning signal, the external influence fault consideration signal or the in-depth prediction normal signal to a fault prediction platform;
and fifthly, after receiving the preliminary predicted normal signal and the deep predicted normal signal, the fault prediction platform does not send out early warning, and the other conditions send out corresponding early warning to remind medical staff to timely and pertinently make corresponding countermeasures.
Furthermore, the invention also provides a medical equipment fault prediction system based on artificial intelligence, which comprises a fault prediction platform, an operation fault history analysis module, an operation maintenance supervision module, a real-time operation parameter detection analysis module and an operation external influence parameter detection analysis module; the operation fault history analysis module is used for acquiring a fault operation period of the corresponding medical equipment in a history operation process, generating a time-of-operation maintenance positive correlation signal or a time-of-operation maintenance non-correlation signal through analysis, transmitting the time-of-operation maintenance positive correlation signal to the operation maintenance supervision module through the fault prediction platform, and transmitting the time-of-operation maintenance non-correlation signal to the real-time operation parameter detection analysis module and the operation external influence parameter detection analysis module through the fault prediction platform;
the operation maintenance supervision module is used for analyzing the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal when receiving the maintenance operation positive correlation signal, sending the operation stop signal to the fault prediction platform so as to stop the operation of the corresponding medical equipment in time and maintain the medical equipment according to the requirement, and sending the operation unimpeded signal to the real-time operation parameter detection and analysis module and the operation external influence parameter detection and analysis module through the fault prediction platform;
the real-time operation parameter detection and analysis module detects and analyzes the real-time operation parameter data of the corresponding medical equipment, generates an operation fault early-warning signal, an operation fault assessment signal or a preliminary prediction normal signal through analysis, and sends the operation fault early-warning signal, the operation fault assessment signal or the preliminary prediction normal signal to the fault prediction platform; and the external influence parameter detection and analysis module is used for detecting and analyzing external environment influence parameter data of the corresponding medical equipment, generating an external influence fault early warning signal, an external influence fault consideration signal or an in-depth prediction normal signal through analysis, and transmitting the external influence fault early warning signal, the external influence fault consideration signal or the in-depth prediction normal signal to the fault prediction platform.
Further, the specific operation process of the operation fault history analysis module includes:
collecting a fault operation time period of corresponding medical equipment in a historical operation process, collecting a continuous operation time period of an operation process corresponding to the fault operation time period, collecting a maintenance interval time period of the operation process corresponding to the fault operation time period, marking an exceeding value of a continuous operation time period compared with a rated continuous operation time period judgment value as a time exceeding value, and marking an exceeding initial value of the maintenance interval time period compared with the rated maintenance interval time period judgment value as a maintenance exceeding value; the sum of the number of the time-consuming excess values is marked as SC1, the sum of the number of the time-consuming excess values and the sum of the number of the fault operation time periods are subjected to ratio calculation, the ratio result of the sum of the number of the time-consuming excess values and the sum of the number of the fault operation time periods is marked as SC2, the sum of the number of the dimension excess values is marked as SC3, the sum of the number of the dimension excess values and the sum of the number of the fault operation time periods is subjected to ratio calculation, and the ratio result of the sum of the number of the dimension excess values and the sum of the number of the fault operation time periods is marked as SC4;
carrying out numerical computation on the SC1, the SC2, the SC3 and the SC4 to obtain a correlation coefficient, carrying out numerical comparison on the correlation coefficient and a preset correlation coefficient threshold value, if the correlation coefficient exceeds the preset correlation coefficient threshold value, generating a time-of-operation maintenance positive correlation signal, and sending the time-of-operation maintenance positive correlation signal to an operation maintenance supervision module through a fault prediction platform; if the correlation coefficient does not exceed the preset correlation coefficient threshold value, generating a time-running maintenance uncorrelated signal.
Further, the specific operation process of the operation maintenance supervision module comprises the following steps:
acquiring the current time and the starting operation time of the corresponding medical equipment, calculating the time difference between the current time and the starting operation time of the medical equipment to obtain the current operation time, acquiring the last maintenance time of the corresponding medical equipment, calculating the time difference between the current time and the last maintenance time to obtain the current maintenance interval time, calculating the numerical value between the current maintenance interval time and the current operation time to obtain an operation maintenance coefficient, comparing the operation maintenance coefficient with a preset operation maintenance coefficient threshold value, and generating an operation stop signal if the operation maintenance coefficient exceeds the preset operation maintenance coefficient threshold value; and if the operation maintenance coefficient does not exceed the preset operation maintenance coefficient threshold value, generating an operation unimpeded signal.
Further, the specific operation process of the real-time operation parameter detection and analysis module comprises the following steps:
acquiring operation parameter data required to be monitored of corresponding medical equipment, performing difference calculation on the operation parameter data and a corresponding rated operation parameter judgment value, taking an absolute value to obtain a corresponding parameter difference value, performing numerical comparison on the parameter difference value and a corresponding preset parameter difference value threshold, and marking a monitoring item corresponding to the operation parameter data as a deviation item if the parameter difference value exceeds the preset parameter difference value threshold; if deviation items exist in the actual operation process of the corresponding medical equipment, an operation fault early warning signal is generated;
subtracting the corresponding parameter difference value from the corresponding preset parameter difference value threshold value to obtain a parameter threshold difference coefficient if no deviation item exists in the actual operation process of the corresponding medical equipment, carrying out numerical comparison on the parameter threshold difference coefficient and the corresponding preset parameter threshold difference coefficient threshold value, marking a monitoring item corresponding to the operation parameter data as an examination item if the parameter threshold difference coefficient does not exceed the preset parameter threshold difference coefficient, marking the number occupation ratio of the examination item as HT, carrying out numerical comparison on HT and HTmax, and generating an operation fault examination signal if HT is more than or equal to HTmax, otherwise, generating a preliminary prediction normal signal; wherein HTmax is a preset judgment threshold value of the number ratio of the considered items, and HTmax is more than 0.
Further, the specific operation process of the external influence parameter detection and analysis module comprises the following steps:
the method comprises the steps of collecting external environment influence parameter data required to be monitored by corresponding medical equipment, carrying out difference calculation on the corresponding external environment influence parameter data and a corresponding rated influence parameter judgment value, taking an absolute value to obtain a corresponding influence difference value, carrying out numerical comparison on the influence difference value exceeding a preset influence difference value threshold, marking an environment control item corresponding to the external environment influence parameter data as a ring-change item if the influence difference value exceeds the preset influence difference value threshold, and generating an external influence fault early warning signal if the ring-change item exists in the environment of the corresponding medical equipment in actual operation;
subtracting the corresponding influence difference value from the corresponding preset influence difference value threshold value to obtain an influence threshold coefficient if no ring-change item exists in the environment where the corresponding medical equipment belongs in actual operation, carrying out numerical comparison on the influence threshold difference coefficient and the corresponding preset influence threshold difference coefficient threshold value, marking the corresponding external environment influence parameter data as a symbol KR1 if the influence threshold difference coefficient exceeds the corresponding preset influence threshold difference coefficient threshold value, and carrying out statistics to obtain the environment detection item quantity KT represented by the symbol KP 1; comparing the value of KT with the value of KTmax, if the value of KT is more than or equal to the value of KTmax, generating an external influence fault consideration signal, otherwise, generating a deep prediction normal signal; wherein KTmax is a preset judgment threshold value of the number of environment detection items, and KTmax is a positive integer greater than 1.
Further, the fault prediction platform is in communication connection with the operation analysis module, and the specific operation process of the operation analysis module comprises:
when medical staff performs operation of corresponding medical equipment, operation images of the corresponding medical staff are acquired in real time, the operation process of the corresponding medical staff is decomposed into a plurality of operation actions based on the operation images, the operation actions which do not accord with the operation standards of the corresponding medical equipment are marked as abnormal actions, and early warning is sent out to remind the medical staff when the abnormal actions are acquired;
and acquiring the abnormal action quantity and the abnormal action occupation ratio of the corresponding medical personnel in unit time, carrying out numerical calculation on the abnormal action quantity and the abnormal action occupation ratio to obtain an operation risk coefficient, carrying out numerical comparison on the operation risk coefficient and a preset operation risk coefficient threshold value, generating an operation risk early warning signal if the operation risk coefficient exceeds the preset operation risk coefficient threshold value, and generating an operation safety signal if the operation risk coefficient does not exceed the preset operation risk coefficient threshold value.
Compared with the prior art, the invention has the beneficial effects that:
1. in the invention, the operation fault history analysis module is used for analyzing to generate an operation time maintenance positive correlation signal or an operation time maintenance non-correlation signal, the operation time maintenance positive correlation signal is sent to the operation maintenance supervision module, and the operation time maintenance non-correlation signal is sent to the real-time operation parameter detection analysis module and the operation external influence parameter detection analysis module through the fault prediction platform; the operation maintenance supervision module analyzes the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal, sends the operation unimpeded signal to the real-time operation parameter detection analysis module and the operation external influence parameter detection analysis module through the fault prediction platform, stops the operation of the corresponding medical equipment in time after generating the operation stop signal, and maintains the medical equipment according to the requirement, thereby protecting the medical equipment;
2. in the invention, the real-time operation parameter detection and analysis module detects and analyzes the real-time operation parameter data of the corresponding medical equipment to generate an operation fault early warning signal, an operation fault consideration signal or a preliminary prediction normal signal, and the operation external influence parameter detection and analysis module detects and analyzes the external environment influence parameter data of the corresponding medical equipment to generate an external influence fault early warning signal, an external influence fault consideration signal or a deep prediction normal signal; the fault prediction platform receives the preliminary prediction normal signal and the deep prediction normal signal, does not send out early warning, and the other conditions send out corresponding early warning, so that effective prediction and risk detection analysis of the operation fault of the medical equipment are realized, accurate early warning feedback is timely carried out, corresponding medical management personnel can timely make corresponding measures, the safe and stable operation of the medical equipment is guaranteed, the service life of the medical equipment is prolonged, and the intelligent degree is high.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a system block diagram of a second embodiment of the present invention;
fig. 3 is a system block diagram of a third embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one: as shown in fig. 1, the medical equipment fault prediction method based on artificial intelligence provided by the invention comprises the following steps:
step one, an operation fault history analysis module analyzes to generate a time-of-operation maintenance positive correlation signal or a time-of-operation maintenance non-correlation signal, a step two is performed after the time-of-operation maintenance positive correlation signal is generated, and a step three and a step four are performed after the time-of-operation maintenance non-correlation signal is generated;
analyzing the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal, stopping the operation of the corresponding medical equipment in time after the operation stop signal is generated, maintaining the medical equipment according to the need, and performing the third step and the fourth step after the operation unimpeded signal is generated;
detecting and analyzing real-time operation parameter data of corresponding medical equipment, generating an operation fault early warning signal, an operation fault assessment signal or a preliminary prediction normal signal through analysis, and transmitting the operation fault early warning signal, the operation fault assessment signal or the preliminary prediction normal signal to a fault prediction platform;
detecting and analyzing external environment influence parameter data of corresponding medical equipment, generating an external influence fault early warning signal, an external influence fault consideration signal or an in-depth prediction normal signal through analysis, and sending the external influence fault early warning signal, the external influence fault consideration signal or the in-depth prediction normal signal to a fault prediction platform;
and fifthly, after receiving the preliminary predicted normal signal and the deep predicted normal signal, the fault prediction platform does not send out early warning, and the other conditions send out corresponding early warning to remind medical staff to timely and pertinently make corresponding countermeasures.
Embodiment two: as shown in fig. 2, the difference between the present embodiment and embodiment 1 is that the medical equipment fault prediction system based on artificial intelligence provided by the present invention includes a fault prediction platform, an operation fault history analysis module, an operation maintenance supervision module, a real-time operation parameter detection analysis module, and an operation external influence parameter detection analysis module; the operation fault history analysis module is used for generating an operation time maintenance positive correlation signal or an operation time maintenance non-correlation signal through analysis, so that the follow-up targeted fault prediction is facilitated, the operation time maintenance positive correlation signal is sent to the operation maintenance supervision module through the fault prediction platform, and the operation time maintenance non-correlation signal is sent to the real-time operation parameter detection analysis module and the operation external influence parameter detection analysis module through the fault prediction platform; the specific operation process of the operation fault history analysis module is as follows:
collecting a fault operation time period of corresponding medical equipment in a historical operation process, collecting a continuous operation time period of an operation process corresponding to the fault operation time period, collecting a maintenance interval time period of the operation process corresponding to the fault operation time period, marking an exceeding value of a continuous operation time period compared with a rated continuous operation time period judgment value as a time exceeding value, and marking an exceeding initial value of the maintenance interval time period compared with the rated maintenance interval time period judgment value as a maintenance exceeding value; the sum of the number of the time-consuming excess values is marked as SC1, the sum of the number of the time-consuming excess values and the sum of the number of the fault operation time periods are subjected to ratio calculation, the ratio result of the sum of the number of the time-consuming excess values and the sum of the number of the fault operation time periods is marked as SC2, the sum of the number of the dimension excess values is marked as SC3, the sum of the number of the dimension excess values and the sum of the number of the fault operation time periods is subjected to ratio calculation, and the ratio result of the sum of the number of the dimension excess values and the sum of the number of the fault operation time periods is marked as SC4;
calculating the numerical values of SC1, SC2, SC3 and SC4 through a formula XG=a1 xSC 1+a2 xSC 2+a3 xSC 3+a4 to obtain a correlation coefficient XG, wherein a1, a2, a3 and a4 are preset weight coefficients, and the values of a1, a2, a3 and a4 are all larger than zero; and the larger the value of the correlation coefficient XG is, the stronger the correlation between the fault occurrence of the medical equipment and the duration of continuous operation and the duration of maintenance interval is shown; the method comprises the steps of carrying out numerical comparison on a correlation coefficient XG and a preset correlation coefficient threshold value, judging that the possibility of equipment failure is high due to overlong continuous operation time and long maintenance interval time if the correlation coefficient XG exceeds the preset correlation coefficient threshold value, generating a time-of-operation maintenance positive correlation signal, and sending the time-of-operation maintenance positive correlation signal to an operation maintenance supervision module through a failure prediction platform; if the correlation coefficient does not exceed the preset correlation coefficient threshold value, generating a time-running maintenance uncorrelated signal.
The operation maintenance supervision module is used for analyzing the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal when receiving the maintenance operation positive correlation signal, sending the operation stop signal to the fault prediction platform so as to stop the operation of the corresponding medical equipment in time and maintain the medical equipment according to the requirement, protecting the medical equipment, and sending the operation unimpeded signal to the real-time operation parameter detection and analysis module and the operation external influence parameter detection and analysis module through the fault prediction platform; the specific operation process of the operation maintenance supervision module is as follows:
acquiring a current time and a starting operation time of corresponding medical equipment, performing time difference calculation on the current time and the starting operation time of the medical equipment to obtain a current operation time, acquiring a last maintenance time of the corresponding medical equipment, performing time difference calculation on the current time and the last maintenance time to obtain a current maintenance interval time, and performing numerical calculation on the current maintenance interval time WK1 and the current operation time WK2 through a formula WK3=b1+b2 to obtain an operation maintenance coefficient WK3, wherein b1 and b2 are preset weight coefficients, and b2 is more than b3 and more than 0; and, the larger the value of the operation maintenance coefficient WK3 is, the more easily the operation failure of the medical equipment is caused by the continuous operation; comparing the operation maintenance coefficient WK3 with a preset operation maintenance coefficient threshold value in a numerical value mode, and generating an operation stop signal if the operation maintenance coefficient WK3 exceeds the preset operation maintenance coefficient threshold value; and if the operation maintenance coefficient WK3 does not exceed the preset operation maintenance coefficient threshold value, generating an operation unimpeded signal.
The real-time operation parameter detection and analysis module detects and analyzes the real-time operation parameter data of the corresponding medical equipment, generates an operation fault early-warning signal, an operation fault assessment signal or a preliminary prediction normal signal through analysis, and sends the operation fault early-warning signal, the operation fault assessment signal or the preliminary prediction normal signal to the fault prediction platform; the specific operation process of the real-time operation parameter detection and analysis module is as follows:
acquiring operation parameter data required to be monitored of corresponding medical equipment, performing difference calculation on the operation parameter data and a corresponding rated operation parameter judgment value, taking an absolute value to obtain a corresponding parameter difference value, performing numerical comparison on the parameter difference value and a corresponding preset parameter difference value threshold, and marking a monitoring item corresponding to the operation parameter data as a deviation item if the parameter difference value exceeds the preset parameter difference value threshold; if deviation projects exist in the actual operation process of the corresponding medical equipment, an operation fault early warning signal is generated, and corresponding medical personnel should timely conduct relevant reason investigation and pause the operation of the medical equipment so as to ensure the subsequent stable operation of the medical equipment and avoid the damage of the medical equipment caused by equipment faults;
subtracting the corresponding parameter difference value from the corresponding preset parameter difference value threshold value to obtain a parameter threshold difference coefficient if no deviation item exists in the actual operation process of the corresponding medical equipment, carrying out numerical comparison on the parameter threshold difference coefficient and the corresponding preset parameter threshold difference coefficient threshold value, marking a monitoring item corresponding to the operation parameter data as an examination item if the parameter threshold difference coefficient does not exceed the preset parameter threshold difference coefficient, marking the number occupation ratio of the examination item as HT, carrying out numerical comparison on HT and HTmax, generating an operation fault examination signal if HT is larger than or equal to HTmax, carrying out timely relevant reason investigation by the corresponding medical personnel, suspending operation of the medical equipment according to requirements, protecting the medical equipment, and otherwise, generating a preliminary prediction normal signal; wherein HTmax is a preset judgment threshold value of the number ratio of the considered items, and HTmax is more than 0.
The external influence parameter detection and analysis module is operated to detect and analyze external environment influence parameter data of corresponding medical equipment, generate an external influence fault early warning signal, an external influence fault consideration signal or an in-depth prediction normal signal through analysis, and send the external influence fault early warning signal, the external influence fault consideration signal or the in-depth prediction normal signal to the fault prediction platform; the specific operation process is as follows:
acquiring external environment influence parameter data required to be monitored by corresponding medical equipment, carrying out difference calculation on the corresponding external environment influence parameter data and a corresponding rated influence parameter judgment value, taking an absolute value to obtain a corresponding influence difference value, carrying out numerical comparison on the influence difference value exceeding a preset influence difference value threshold, marking an environment control item corresponding to the external environment influence parameter data as a ring-change item if the influence difference value exceeds the preset influence difference value threshold, and generating an external influence fault early warning signal if the ring-change item exists in the environment to which the corresponding medical equipment belongs in actual operation, wherein corresponding medical personnel should timely carry out relevant reason investigation and corresponding environment regulation, so that the corresponding medical equipment is in a proper operation environment to ensure the follow-up stable operation of the medical equipment and avoid the damage of the medical equipment caused by the equipment fault;
subtracting the corresponding influence difference value from the corresponding preset influence difference value threshold value to obtain an influence threshold coefficient if no ring-change item exists in the environment where the corresponding medical equipment belongs in actual operation, carrying out numerical comparison on the influence threshold difference coefficient and the corresponding preset influence threshold difference coefficient threshold value, marking the corresponding external environment influence parameter data as a symbol KR1 if the influence threshold difference coefficient exceeds the corresponding preset influence threshold difference coefficient threshold value, and carrying out statistics to obtain the environment detection item quantity KT represented by the symbol KP 1; comparing the value of KT with the value of KTmax, if the value of KT is more than or equal to the value of KTmax, generating an external influence fault consideration signal, and timely carrying out relevant reason investigation and corresponding environment regulation and control according to the need by corresponding medical staff so as to further ensure the operation stability and operation safety of corresponding medical equipment and avoid the operation fault of the medical equipment; if KT is less than KTmax, generating a deep prediction normal signal; wherein KTmax is a preset judgment threshold value of the number of environment detection items, and KTmax is a positive integer greater than 1.
Embodiment III: as shown in fig. 3, the difference between the present embodiment and embodiments 1 and 2 is that the fault prediction platform is in communication connection with the operation analysis module, and the operation analysis module analyzes the operation process of the corresponding medical personnel, and generates an operation risk early warning signal or an operation safety signal by analysis, and sends the operation risk early warning signal or the operation safety signal to the fault prediction platform, and when the fault prediction platform receives the operation risk early warning signal, the replacement of the medical personnel should be performed in time, and the operation training of the corresponding medical personnel is performed subsequently, so as to enhance the operation proficiency and operation normalization of the corresponding medical personnel, thereby further ensuring the safe and stable operation of the medical equipment, and avoiding the operation fault of the medical equipment; the specific operation process of the operation decomposition evaluation analysis module is as follows:
when medical staff performs operation of corresponding medical equipment, operation images of the corresponding medical staff are acquired in real time, the operation process of the corresponding medical staff is decomposed into a plurality of operation actions based on the operation images, the operation actions which do not accord with the operation standards of the corresponding medical equipment are marked as abnormal actions, and early warning is sent out to remind the medical staff when the abnormal actions are acquired; the abnormal action quantity and the abnormal action occupation ratio of the corresponding medical personnel in unit time are collected, the abnormal action quantity FP1 and the abnormal action occupation ratio FP2 are subjected to numerical calculation through a formula CF=eg1+eg2×FP2 to obtain an operation risk coefficient CF, wherein eg1 and eg2 are preset weight coefficients, and eg2 is more than eg1 and more than 0; moreover, the larger the value of the operation risk coefficient CF is, the larger the operation risk of the medical personnel for corresponding medical equipment is, and the medical equipment is more likely to be broken down; and comparing the operation risk coefficient CF with a preset operation risk coefficient threshold value, generating an operation risk early warning signal if the operation risk coefficient CF exceeds the preset operation risk coefficient threshold value, and generating an operation safety signal if the operation risk coefficient CF does not exceed the preset operation risk coefficient threshold value.
The working principle of the invention is as follows: when the system is used, the operation fault history analysis module analyzes to generate an operation time maintenance positive correlation signal or an operation time maintenance non-correlation signal, the operation time maintenance positive correlation signal is sent to the operation maintenance supervision module through the fault prediction platform, and the operation time maintenance non-correlation signal is sent to the real-time operation parameter detection analysis module and the operation external influence parameter detection analysis module through the fault prediction platform; the operation maintenance supervision module analyzes the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal, stops the operation of the corresponding medical equipment in time after generating the operation stop signal, maintains the medical equipment according to the requirement, protects the medical equipment, and sends the operation unimpeded signal to the real-time operation parameter detection and analysis module and the operation external influence parameter detection and analysis module through the fault prediction platform; the real-time operation parameter detection and analysis module detects and analyzes the real-time operation parameter data of the corresponding medical equipment to generate an operation fault early warning signal, an operation fault consideration signal or a preliminary prediction normal signal, and the operation external influence parameter detection and analysis module detects and analyzes the external environment influence parameter data of the corresponding medical equipment to generate an external influence fault early warning signal, an external influence fault consideration signal or a deep prediction normal signal; the fault prediction platform receives the preliminary prediction normal signal and the deep prediction normal signal, does not send out early warning, and the other conditions send out corresponding early warning, so that effective prediction and risk detection analysis of the operation fault of the medical equipment are realized, accurate early warning feedback is timely carried out, corresponding medical management personnel can timely make corresponding measures, the safe and stable operation of the medical equipment is guaranteed, the service life of the medical equipment is prolonged, and the intelligent degree is high.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation. The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (7)
1. The medical equipment fault prediction method based on artificial intelligence is characterized by comprising the following steps of:
step one, an operation fault history analysis module analyzes to generate a time-of-operation maintenance positive correlation signal or a time-of-operation maintenance non-correlation signal, a step two is performed after the time-of-operation maintenance positive correlation signal is generated, and a step three and a step four are performed after the time-of-operation maintenance non-correlation signal is generated;
analyzing the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal, stopping the operation of the corresponding medical equipment in time after the operation stop signal is generated, maintaining the medical equipment according to the need, and performing the third step and the fourth step after the operation unimpeded signal is generated;
detecting and analyzing real-time operation parameter data of corresponding medical equipment, generating an operation fault early warning signal, an operation fault assessment signal or a preliminary prediction normal signal through analysis, and transmitting the operation fault early warning signal, the operation fault assessment signal or the preliminary prediction normal signal to a fault prediction platform;
detecting and analyzing external environment influence parameter data of corresponding medical equipment, generating an external influence fault early warning signal, an external influence fault consideration signal or an in-depth prediction normal signal through analysis, and sending the external influence fault early warning signal, the external influence fault consideration signal or the in-depth prediction normal signal to a fault prediction platform;
and fifthly, after receiving the preliminary predicted normal signal and the deep predicted normal signal, the fault prediction platform does not send out early warning, and the other conditions send out corresponding early warning to remind medical staff to timely and pertinently make corresponding countermeasures.
2. The medical equipment fault prediction system based on the artificial intelligence is characterized by comprising a fault prediction platform, an operation fault history analysis module, an operation maintenance supervision module, a real-time operation parameter detection analysis module and an operation external influence parameter detection analysis module; the operation fault history analysis module is used for acquiring a fault operation period of the corresponding medical equipment in a history operation process, generating a time-of-operation maintenance positive correlation signal or a time-of-operation maintenance non-correlation signal through analysis, transmitting the time-of-operation maintenance positive correlation signal to the operation maintenance supervision module through the fault prediction platform, and transmitting the time-of-operation maintenance non-correlation signal to the real-time operation parameter detection analysis module and the operation external influence parameter detection analysis module through the fault prediction platform;
the operation maintenance supervision module is used for analyzing the corresponding medical equipment to generate an operation stop signal or an operation unimpeded signal when receiving the maintenance operation positive correlation signal, sending the operation stop signal to the fault prediction platform so as to stop the operation of the corresponding medical equipment in time and maintain the medical equipment according to the requirement, and sending the operation unimpeded signal to the real-time operation parameter detection and analysis module and the operation external influence parameter detection and analysis module through the fault prediction platform;
the real-time operation parameter detection and analysis module detects and analyzes the real-time operation parameter data of the corresponding medical equipment, generates an operation fault early-warning signal, an operation fault assessment signal or a preliminary prediction normal signal through analysis, and sends the operation fault early-warning signal, the operation fault assessment signal or the preliminary prediction normal signal to the fault prediction platform; and the external influence parameter detection and analysis module is used for detecting and analyzing external environment influence parameter data of the corresponding medical equipment, generating an external influence fault early warning signal, an external influence fault consideration signal or an in-depth prediction normal signal through analysis, and transmitting the external influence fault early warning signal, the external influence fault consideration signal or the in-depth prediction normal signal to the fault prediction platform.
3. The medical device fault prediction system based on artificial intelligence according to claim 2, wherein the specific operation procedure of the operation fault history analysis module comprises:
collecting a fault operation time period of corresponding medical equipment in a historical operation process, collecting a continuous operation time period of an operation process corresponding to the fault operation time period, collecting a maintenance interval time period of the operation process corresponding to the fault operation time period, marking an exceeding value of a continuous operation time period compared with a rated continuous operation time period judgment value as a time exceeding value, and marking an exceeding initial value of the maintenance interval time period compared with the rated maintenance interval time period judgment value as a maintenance exceeding value; the sum of the number of the time-consuming excess values is marked as SC1, the sum of the number of the time-consuming excess values and the sum of the number of the fault operation time periods are subjected to ratio calculation, the ratio result of the sum of the number of the time-consuming excess values and the sum of the number of the fault operation time periods is marked as SC2, the sum of the number of the dimension excess values is marked as SC3, the sum of the number of the dimension excess values and the sum of the number of the fault operation time periods is subjected to ratio calculation, and the ratio result of the sum of the number of the dimension excess values and the sum of the number of the fault operation time periods is marked as SC4;
carrying out numerical computation on the SC1, the SC2, the SC3 and the SC4 to obtain a correlation coefficient, carrying out numerical comparison on the correlation coefficient and a preset correlation coefficient threshold value, if the correlation coefficient exceeds the preset correlation coefficient threshold value, generating a time-of-operation maintenance positive correlation signal, and sending the time-of-operation maintenance positive correlation signal to an operation maintenance supervision module through a fault prediction platform; if the correlation coefficient does not exceed the preset correlation coefficient threshold value, generating a time-running maintenance uncorrelated signal.
4. The medical device fault prediction system based on artificial intelligence according to claim 3, wherein the specific operation process of the operation maintenance supervision module comprises:
acquiring the current time and the starting operation time of the corresponding medical equipment, calculating the time difference between the current time and the starting operation time of the medical equipment to obtain the current operation time, acquiring the last maintenance time of the corresponding medical equipment, calculating the time difference between the current time and the last maintenance time to obtain the current maintenance interval time, calculating the numerical value between the current maintenance interval time and the current operation time to obtain an operation maintenance coefficient, comparing the operation maintenance coefficient with a preset operation maintenance coefficient threshold value, and generating an operation stop signal if the operation maintenance coefficient exceeds the preset operation maintenance coefficient threshold value; and if the operation maintenance coefficient does not exceed the preset operation maintenance coefficient threshold value, generating an operation unimpeded signal.
5. The medical equipment fault prediction system based on artificial intelligence according to claim 2, wherein the specific operation process of the real-time operation parameter detection and analysis module comprises:
acquiring operation parameter data required to be monitored of corresponding medical equipment, performing difference calculation on the operation parameter data and a corresponding rated operation parameter judgment value, taking an absolute value to obtain a corresponding parameter difference value, performing numerical comparison on the parameter difference value and a corresponding preset parameter difference value threshold, and marking a monitoring item corresponding to the operation parameter data as a deviation item if the parameter difference value exceeds the preset parameter difference value threshold; if deviation items exist in the actual operation process of the corresponding medical equipment, an operation fault early warning signal is generated;
subtracting the corresponding parameter difference value from the corresponding preset parameter difference value threshold value to obtain a parameter threshold difference coefficient if no deviation item exists in the actual operation process of the corresponding medical equipment, carrying out numerical comparison on the parameter threshold difference coefficient and the corresponding preset parameter threshold difference coefficient threshold value, marking a monitoring item corresponding to the operation parameter data as an examination item if the parameter threshold difference coefficient does not exceed the preset parameter threshold difference coefficient, marking the number occupation ratio of the examination item as HT, carrying out numerical comparison on HT and HTmax, and generating an operation fault examination signal if HT is more than or equal to HTmax, otherwise, generating a preliminary prediction normal signal; wherein HTmax is a preset judgment threshold value of the number ratio of the considered items, and HTmax is more than 0.
6. The medical equipment fault prediction system based on artificial intelligence according to claim 2, wherein the specific operation process of the external influence parameter detection and analysis module comprises:
the method comprises the steps of collecting external environment influence parameter data required to be monitored by corresponding medical equipment, carrying out difference calculation on the corresponding external environment influence parameter data and a corresponding rated influence parameter judgment value, taking an absolute value to obtain a corresponding influence difference value, carrying out numerical comparison on the influence difference value exceeding a preset influence difference value threshold, marking an environment control item corresponding to the external environment influence parameter data as a ring-change item if the influence difference value exceeds the preset influence difference value threshold, and generating an external influence fault early warning signal if the ring-change item exists in the environment of the corresponding medical equipment in actual operation;
subtracting the corresponding influence difference value from the corresponding preset influence difference value threshold value to obtain an influence threshold coefficient if no ring-change item exists in the environment where the corresponding medical equipment belongs in actual operation, carrying out numerical comparison on the influence threshold difference coefficient and the corresponding preset influence threshold difference coefficient threshold value, marking the corresponding external environment influence parameter data as a symbol KR1 if the influence threshold difference coefficient exceeds the corresponding preset influence threshold difference coefficient threshold value, and carrying out statistics to obtain the environment detection item quantity KT represented by the symbol KP 1; comparing the value of KT with the value of KTmax, if the value of KT is more than or equal to the value of KTmax, generating an external influence fault consideration signal, otherwise, generating a deep prediction normal signal; wherein KTmax is a preset judgment threshold value of the number of environment detection items, and KTmax is a positive integer greater than 1.
7. The medical device fault prediction system based on artificial intelligence according to claim 2, wherein the fault prediction platform is in communication connection with an operational resolution assessment analysis module, and the specific operation procedure of the operational resolution assessment analysis module comprises:
when medical staff performs operation of corresponding medical equipment, operation images of the corresponding medical staff are acquired in real time, the operation process of the corresponding medical staff is decomposed into a plurality of operation actions based on the operation images, the operation actions which do not accord with the operation standards of the corresponding medical equipment are marked as abnormal actions, and early warning is sent out to remind the medical staff when the abnormal actions are acquired;
and acquiring the abnormal action quantity and the abnormal action occupation ratio of the corresponding medical personnel in unit time, carrying out numerical calculation on the abnormal action quantity and the abnormal action occupation ratio to obtain an operation risk coefficient, carrying out numerical comparison on the operation risk coefficient and a preset operation risk coefficient threshold value, generating an operation risk early warning signal if the operation risk coefficient exceeds the preset operation risk coefficient threshold value, and generating an operation safety signal if the operation risk coefficient does not exceed the preset operation risk coefficient threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310863011.1A CN116844708A (en) | 2023-07-14 | 2023-07-14 | Medical equipment fault prediction method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310863011.1A CN116844708A (en) | 2023-07-14 | 2023-07-14 | Medical equipment fault prediction method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116844708A true CN116844708A (en) | 2023-10-03 |
Family
ID=88172425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310863011.1A Withdrawn CN116844708A (en) | 2023-07-14 | 2023-07-14 | Medical equipment fault prediction method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116844708A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117198458A (en) * | 2023-10-12 | 2023-12-08 | 药明激创(佛山)生物科技有限公司 | Drug screening device fault prediction system based on Internet of things |
| CN117612687A (en) * | 2024-01-22 | 2024-02-27 | 西安交通大学医学院第一附属医院 | Medical equipment monitoring and analyzing system based on artificial intelligence |
| CN117612687B (en) * | 2024-01-22 | 2024-04-26 | 西安交通大学医学院第一附属医院 | Medical equipment monitoring and analyzing system based on artificial intelligence |
-
2023
- 2023-07-14 CN CN202310863011.1A patent/CN116844708A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117198458A (en) * | 2023-10-12 | 2023-12-08 | 药明激创(佛山)生物科技有限公司 | Drug screening device fault prediction system based on Internet of things |
| CN117612687A (en) * | 2024-01-22 | 2024-02-27 | 西安交通大学医学院第一附属医院 | Medical equipment monitoring and analyzing system based on artificial intelligence |
| CN117612687B (en) * | 2024-01-22 | 2024-04-26 | 西安交通大学医学院第一附属医院 | Medical equipment monitoring and analyzing system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446864B (en) | Big data analysis-based fault early warning system and method for rail transit equipment | |
| CN116404758B (en) | Intelligent seal cabinet power distribution monitoring and early warning control system | |
| CN113299042B (en) | Safety early warning system for frequency conversion equipment of industrial electrical appliance | |
| CN116844708A (en) | Medical equipment fault prediction method and system based on artificial intelligence | |
| CN116320832B (en) | Monitoring equipment fault monitoring method and device | |
| CN106597965A (en) | Nuclear power apparatus running state monitoring system and monitoring method | |
| CN116142913A (en) | Equipment health state analysis method and system based on big data | |
| CN106226621A (en) | A kind of secondary device fault diagnosis based on grey correlation analysis and method for early warning | |
| CN116799927B (en) | Energy storage system management method and energy storage system | |
| CN116660672B (en) | Power grid equipment fault diagnosis method and system based on big data | |
| CN111428984A (en) | Risk early warning and analysis method of intelligent safety electricity utilization management system | |
| CN112328961A (en) | On-line monitoring device quality evaluation system based on fault tree and Bayesian network | |
| CN114594349B (en) | Direct current insulation monitoring method and terminal in energy storage system | |
| CN115657631A (en) | Intelligent monitoring system for industrial control equipment operation field environment | |
| CN115497610A (en) | Medical equipment fault prediction system and method based on data analysis | |
| CN110553686A (en) | Cold header running state monitoring system | |
| CN110992205A (en) | State detection method and system for generator winding of wind turbine generator and related components | |
| CN116465059A (en) | Energy-saving air conditioner operation supervision system based on data analysis | |
| CN116859803A (en) | Variable frequency equipment operation energy-saving intelligent control system based on Internet of things technology | |
| CN110286286B (en) | VSC-HVDC converter station fault identification device and method based on VMD-ELM | |
| CN115406483A (en) | Hydroelectric generating set fault identification method, device, equipment and readable storage medium | |
| CN111443263A (en) | Cable analysis device based on ring main unit and detection method thereof | |
| CN115684833A (en) | Cable line degradation monitoring method and system based on harmonic diagnosis and storage medium | |
| CN115495315A (en) | Fault early warning system of large-scale medical equipment | |
| CN113315236A (en) | Low-voltage power distribution cabinet remote diagnosis system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231003 |
|
| WW01 | Invention patent application withdrawn after publication |