Medical equipment operation and maintenance management system based on AI

Abstract

The invention relates to the field of operation and maintenance management, and discloses an AI-based medical equipment operation and maintenance management system, which comprises an equipment monitoring module used for monitoring operation parameters of equipment in real time and taking the operation parameters as equipment monitoring data; the equipment fault prediction module is used for cleaning, fusing and processing the equipment monitoring data based on a pre-trained recurrent neural network model to obtain a fault prediction coefficient and a fault type; the safety detection module is used for analyzing equipment safety according to the fault prediction coefficient and the fault type of the equipment fault diagnosis module and establishing a priority maintenance equipment list according to an analysis result; and the operation and maintenance execution module is used for executing the maintenance task according to the priority maintenance list of the security detection module. Through cooperation of the equipment fault prediction module and the safety detection module, predictive judgment on whether the equipment needs to be maintained or not is realized, and the equipment needing to be maintained is subjected to priority ranking, so that the purpose of efficient maintenance is achieved.

Description

Technical Field

[0001] The present invention relates to the field of operation and maintenance management, and in particular to an AI-based medical equipment operation and maintenance management system. Background Art

[0002] The operation and maintenance management of medical equipment is to ensure the safety, reliability and efficiency of the equipment, avoid equipment failure, reduce maintenance time and cost, and improve the service level of medical institutions and the safety of patients. The effective operation of medical equipment directly affects the patient's experience and the timely and effective medical services that patients receive in medical institutions. If a large number of medical devices cannot operate, it will obviously be a big problem for patients. The existing medical equipment operation and maintenance management system can monitor the performance and status of the equipment in real time, predict equipment failures and errors, and avoid sudden interruptions of the equipment.

[0003] In actual use, it is found that it is particularly necessary to sort the equipment according to its importance and the possibility of failure to determine which equipment needs to be maintained first. However, the existing equipment does not take into account the impact of equipment failure types during maintenance. For example, for different equipment, maintenance can be performed faster when certain types of failure occur, so even if a sudden interruption occurs, maintenance can be performed in a shorter time to restore the equipment to operation; while certain types of failures require longer maintenance time once they occur, so once this type of failure occurs, the equipment will be offline and affect normal use, causing other medical equipment of the same type to be overloaded in a short period of time, and ultimately causing a series of collateral effects. Summary of the invention

[0004] The purpose of the present invention is to provide an AI-based medical equipment operation and maintenance management system to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] An AI-based medical equipment operation and maintenance management system, including:

[0007] Equipment monitoring module, used to monitor the operating parameters of the equipment in real time and serve as equipment monitoring data;

[0008] The equipment fault prediction module, based on the pre-trained recurrent neural network model, cleans, fuses and processes the equipment monitoring data to obtain the fault prediction coefficient;

[0009] The safety detection module analyzes the equipment safety according to the fault prediction coefficient of the equipment fault diagnosis module, and establishes a list of equipment with priority maintenance based on the analysis results;

[0010] The operation and maintenance execution module is used to execute maintenance tasks according to the priority maintenance list of the safety detection module.

[0011] As a further technical solution, the operating parameters include temperature, pressure, current, voltage and usage time; the equipment failure types include mechanical failure, electrical failure and software failure. The pressure is air pressure, and each operating parameter is obtained by special detection instruments or sensors. It is an existing technology and will not be elaborated here.

[0012] As a further technical solution, the process of analyzing equipment safety is as follows:

[0013] Obtain the failure prediction coefficient P of the equipment;

[0014] The equipment safety analysis model F(P, K) is established based on the fault prediction coefficient P and the maintenance difficulty coefficient K; the expression is:

[0015]

[0016] Among them, α and β are weight coefficients, is the extreme value difference of the fault prediction coefficient of the current equipment in unit time, P max , P min are the maximum and minimum values ​​of the fault prediction coefficient of the current equipment in unit time, i is the i-th fault type, k i is the maintenance difficulty coefficient corresponding to the i-th fault type, p i is the preset fixed coefficient of the i-th fault type, P0 and K0 are the thresholds of the fault prediction coefficient and maintenance difficulty coefficient of the current equipment;

[0017] The device safety analysis model F(P, K) is used to determine whether the current device is safe.

[0018] As a further technical solution, the process of determining whether the current device is safe is as follows:

[0019] The failure prediction coefficient P of the jth device j And the maintenance difficulty coefficient K j Substitute it into the equipment safety analysis model and calculate the fault estimation F(P j , K j );

[0020] F(P j , K j ) is compared with a preset safety threshold F(P, K)0;

[0021] If F(P j , K j )≥F(P, K)0, then the current device is judged to be unsafe;

[0022] Otherwise, the current device is considered safe.

[0023] As a further technical solution, the process of obtaining the maintenance difficulty coefficient is as follows:

[0024] Mark mechanical failure, software failure, and electrical failure as l1, l2, and l3 respectively;

[0025] Fit and obtain the curves of mechanical failure, software failure and electrical failure frequency over time in each unit time: l1q(t), l2q(t), l3q(t);

[0026] According to the change amplitude and extreme value of the change curve corresponding to the frequency of each fault type, the maintenance difficulty coefficients k1, k2, and k3 corresponding to each fault type are calculated respectively.

[0027] As a further technical solution, the expressions of k1, k2, and k3 are:

[0028]

[0029] Among them, l1q(t)0, l2q(t)0, l3q(t)0 are reference curves, l1q max 、l1q min are the maximum and minimum values ​​of the frequency of mechanical failure, respectively. max 、l2q min are the maximum and minimum values ​​of the frequency of software failures, respectively. max 、l3q mi n is the maximum and minimum value of the frequency of electrical faults; S1, S2, S3 are the fluctuation coefficients corresponding to each fault type; t0 and t1 are the starting and ending points of the statistical period.

[0030] As a further technical solution, the process of obtaining the fluctuation coefficient corresponding to each fault type is:

[0031] The number of times the i-th fault type occurs n and the duration of each maintenance process Δt e Substitute into the formula Calculate the average maintenance processing time S for each fault type i ;

[0032] Among them, e is the e-th time, is the mean maintenance processing time for the i-th fault type.

[0033] As a further technical solution, the process of establishing a priority maintenance equipment list based on the analysis results is as follows:

[0034] The condition F(Pj , K j )≥F(P, K)0 is added to the maintenance equipment list;

[0035] Arrange each device in the maintenance equipment list in descending order according to the maintenance difficulty coefficient K;

[0036] Each device is numbered in sequence as 1, 2, 3, ... N, which serves as a list of priority maintenance equipment.

[0037] Beneficial effects of the present invention:

[0038] (1) The present invention uses the above-mentioned technical solution and utilizes the pre-trained recurrent neural network model in the equipment fault prediction module, so as to obtain the fault prediction coefficient according to the operating parameters of the equipment. Obviously, the larger the fault prediction coefficient, the greater the risk of the current equipment, and the greater the probability of a fault interruption in the subsequent operation process, so the more timely maintenance is needed. Then, the safety detection module comprehensively establishes a safety analysis model based on the fault prediction coefficient and the fault type existing in the current equipment, so as to evaluate the equipment safety from multiple aspects, and finally obtain a more accurate equipment fault valuation, so as to provide data support for the subsequent establishment of a priority maintenance list, thereby achieving the purpose of effectively allocating maintenance resources and establishing a key monitoring list;

[0039] (2) The present invention provides a process for obtaining the maintenance difficulty coefficient corresponding to each fault type through the above technical solution. Because different equipment encountering different fault types puts different pressures on maintenance personnel, the curve of the change in the frequency of mechanical faults, software faults, and electrical faults in each unit time over time is obtained by fitting, and then the deviation between the curve and the reference curve is obtained in the form of integration, so that the stability of each equipment encountering each fault type can be judged. The worse the stability, the greater the maintenance difficulty. In order to reduce the error caused by only the amplitude of the change, the difference between the maximum and minimum values ​​of each fault type is increased, thereby achieving the purpose of more accurate judgment of the maintenance difficulty.

[0040] (3) The present invention uses the above-mentioned technical solution to conduct a comprehensive analysis of the historical situations of each fault type, so as to ultimately determine which fault type or two fault types corresponding to each medical device will increase the difficulty of maintenance when they occur simultaneously, and then focus on monitoring and give priority to predictive maintenance to reduce the adverse effects of this fault type on the equipment. At the same time, it can also reduce the collateral effects of excessive pressure on other equipment in a short period of time due to long-term disconnection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 As shown, the present invention is an AI-based medical equipment operation and maintenance management system, comprising:

[0045] Equipment monitoring module, used to monitor the operating parameters of the equipment in real time and serve as equipment monitoring data;

[0046] The equipment fault prediction module, based on the pre-trained recurrent neural network model, cleans, fuses and processes the equipment monitoring data to obtain the fault prediction coefficient. The establishment and training process of the recurrent neural network model is a mature technology, so it is not elaborated in this article.

[0047] The safety detection module analyzes the equipment safety according to the fault prediction coefficient of the equipment fault diagnosis module, and establishes a list of equipment with priority maintenance based on the analysis results;

[0048] The operation and maintenance execution module is used to perform maintenance tasks according to the priority maintenance list of the safety detection module. The operating parameters include temperature, pressure, current, voltage and usage time; the equipment failure types include mechanical failure, electrical failure and software failure. The pressure is air pressure, and each operating parameter is obtained through special detection instruments or sensors. It is a prior art and will not be elaborated here.

[0049] In this embodiment, the pre-trained recurrent neural network model in the equipment fault prediction module can obtain the fault prediction coefficient according to the operating parameters of the equipment. Obviously, the larger the fault prediction coefficient, the greater the risk of the current equipment, and the greater the probability of a fault interruption in the subsequent operation process, so timely maintenance is more needed. Then, the safety detection module comprehensively establishes a safety analysis model based on the fault prediction coefficient and the fault type of the current equipment to evaluate the equipment safety from multiple aspects, and finally obtain a more accurate equipment failure valuation, which provides data support for the subsequent establishment of a priority maintenance list, thereby achieving the purpose of effectively allocating maintenance resources and establishing a key monitoring list.

[0050] The process of analyzing device security is as follows:

[0051] Obtain the failure prediction coefficient P of the equipment;

[0052] The equipment safety analysis model F(P, K) is established based on the fault prediction coefficient P and the maintenance difficulty coefficient K; the expression is:

[0053]

[0054] Among them, α and β are weight coefficients, which are comprehensively formulated based on historical experience data. is the extreme value difference of the fault prediction coefficient of the current equipment in unit time, P max , P min are the maximum and minimum values ​​of the fault prediction coefficient of the current equipment in unit time, i is the i-th fault type, k i is the maintenance difficulty coefficient corresponding to the i-th fault type, p i is the preset fixed coefficient of the i-th fault type, which is a constant determined based on historical data. P0 and K0 are the thresholds of the fault prediction coefficient and maintenance difficulty coefficient of the current equipment;

[0055] Determine whether the current device is safe through the device safety analysis model F(P, K);

[0056] The process of determining whether the current device is safe is as follows:

[0057] The failure prediction coefficient P of the jth device j And the maintenance difficulty coefficient K j Substitute it into the equipment safety analysis model and calculate the fault estimation F(P j , K j );

[0058] F(P j , K j ) is compared with a preset safety threshold F(P, K)0;

[0059] If F(P j , K j )≥F(P, K)0, then the current device is judged to be unsafe;

[0060] Otherwise, the current device is considered safe.

[0061] In this embodiment, a specific method for equipment safety analysis is provided. First, an equipment safety analysis model F(P, K) is established based on the fault prediction coefficient P and the maintenance difficulty coefficient K. The expression is: According to the above expressions, it can be seen that the larger the maintenance difficulty coefficient K and the fault prediction coefficient P, the greater the impact on the final fault valuation of the equipment. The overall change range of the fault prediction coefficient of each device can be expressed by the extreme value difference. Obviously, the larger the extreme value difference, the greater the stability of the fault prediction coefficient of the equipment, and therefore the greater the impact on the final fault valuation of the equipment. Obviously, the larger the fault valuation, the higher the failure probability of the current equipment, and therefore the greater the need to add it to the maintenance list; then by comparing the fault valuation calculated for each device with the system preset safety threshold, if the fault valuation exceeds the safety threshold, it means that the probability of failure of the device is higher, and the greater the joint impact of the failure, so the more it needs to be focused on maintenance; conversely, it means that the joint impact of the equipment is smaller, although timely maintenance is also required, but the importance is obviously placed at the back.

[0062] The process of obtaining the maintenance difficulty coefficient is as follows:

[0063] Mark mechanical failure, software failure, and electrical failure as l1, l2, and l3 respectively;

[0064] The fitting curves of mechanical failure, software failure and electrical failure frequency over time in each unit time are obtained: l1q(t), l2q(t) and l3q(t). Obviously, the greater the cumulative change in the frequency of a certain type of failure, the greater the threat of this type of failure in the next operating time. If the maintenance difficulty of this type of failure is relatively low, the demand for maintenance resources in the next stage can be further reduced, or if the maintenance resources remain unchanged, the number of medical devices that can be kept online at the same time can be increased.

[0065] According to the change amplitude and extreme value of the change curve corresponding to the frequency of each fault type, the maintenance difficulty coefficients k1, k2, and k3 corresponding to each fault type are calculated respectively.

[0066] The expressions of k1, k2 and k3 are:

[0067]

[0068] Among them, l1q(t)0, l2q(t)0, l3q(t)0 are reference curves, l1q max 、l1q min are the maximum and minimum values ​​of the frequency of mechanical failure, respectively. max 、l2q min are the maximum and minimum values ​​of the frequency of software failures, respectively. max 、l3q minare the maximum and minimum values ​​of the frequency of electrical faults, respectively; S1, S2, and S3 are the fluctuation coefficients corresponding to each fault type, and t0 and t1 are the starting and ending points of the statistical period, respectively;

[0069] The process of obtaining the fluctuation coefficient corresponding to each fault type is:

[0070] The number of times the i-th fault type occurs n and the duration of each maintenance process Δt e Substitute into the formula Calculate the average maintenance processing time S for each fault type i ;

[0071] Among them, e is the e-th time, is the mean maintenance processing time for the i-th fault type.

[0072] In this embodiment, a process for obtaining the maintenance difficulty coefficient corresponding to each fault type is provided. Because different equipment encountering different fault types puts different pressures on maintenance personnel, the curves of the change in the frequency of mechanical faults, software faults, and electrical faults over time in each unit time are obtained by fitting, l1q(t), l2q(t), and l3q(t), and then the deviation between the curves and the reference curves is obtained in the form of integration, so that the stability of each equipment encountering each fault type can be judged. The worse the stability, the greater the maintenance difficulty may be. In order to reduce the error caused by the amplitude of the change alone, the difference between the maximum and minimum values ​​of each fault type is increased, thereby achieving the purpose of more accurate judgment of the maintenance difficulty. In addition, in order to further reduce the error, the fluctuation coefficient corresponding to each fault type is introduced. By calculating the standard deviation, the handling situation of each fault type can be accurately judged. Obviously, the smaller the fluctuation coefficient, the greater the maintenance difficulty of the fault type.

[0073] Through the above technical solution, a comprehensive analysis is conducted on the historical situations of each fault type to ultimately determine which fault type corresponds to each medical device or which two fault types occurring simultaneously will increase the difficulty of maintenance, and then focus on monitoring and prioritize predictive maintenance to reduce the adverse effects of this fault type on the equipment. At the same time, it can also reduce the collateral effects of excessive pressure on other equipment in a short period of time due to long-term disconnection.

[0074] The process of establishing a priority maintenance equipment list based on the analysis results is as follows:

[0075] The condition F(P j , K j )≥F(P, K)0 is added to the maintenance equipment list;

[0076] Arrange each device in the maintenance equipment list in descending order according to the maintenance difficulty coefficient K;

[0077] Each device is numbered in sequence as 1, 2, 3, ... N, which serves as a list of priority maintenance equipment.

[0078] In this embodiment, a method for establishing a priority maintenance list is provided. Specifically, according to F(P j , K j )≥F(P, K)0, to achieve the preliminary establishment of a maintenance equipment list, and then sort them in descending order according to the maintenance difficulty coefficient corresponding to each device, so as to obtain a priority maintenance equipment list, so as to give priority to the maintenance of equipment with high maintenance difficulty, so as to avoid the deterioration of the equipment condition leading to excessive interruption of maintenance time; through the above technical scheme, it is possible to focus on monitoring and pre-maintain equipment with high maintenance difficulty, so as to avoid the use problems caused by continuous disconnection of a certain type of equipment in the same period when the maintenance resources are insufficient, and further maintain the medical equipment to the maximum extent possible when the situation is severe.

[0079] It should be noted that the calculation formulas and various parameters involved in the calculation in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0080] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An AI-based medical equipment operation and maintenance management system, characterized in that: include: Equipment monitoring module, used to monitor the operating parameters of the equipment in real time and serve as equipment monitoring data; The equipment fault prediction module, based on the pre-trained recurrent neural network model, cleans, fuses and processes the equipment monitoring data to obtain the fault prediction coefficient; The safety detection module analyzes the equipment safety according to the fault prediction coefficient of the equipment fault diagnosis module, and establishes a list of equipment with priority maintenance based on the analysis results; The operation and maintenance execution module is used to execute maintenance tasks according to the priority maintenance list of the safety detection module.

2. The AI-based medical equipment operation and maintenance management system according to claim 1, characterized in that: The operating parameters include temperature, pressure, current, voltage and usage time; the equipment failure types include mechanical failure, electrical failure and software failure.

3. The AI-based medical equipment operation and maintenance management system according to claim 2 is characterized in that: The process of analyzing device security is as follows: Obtain the failure prediction coefficient P of the equipment; The equipment safety analysis model F(P, K) is established based on the fault prediction coefficient P and the maintenance difficulty coefficient K; the expression is: Among them, α and β are weight coefficients, is the extreme value difference of the fault prediction coefficient of the current equipment in unit time, P max , P min are the maximum and minimum values ​​of the fault prediction coefficient of the current equipment in unit time, i is the i-th fault type, k i is the maintenance difficulty coefficient corresponding to the i-th fault type, p i is the preset fixed coefficient of the i-th fault type, P0 and K0 are the thresholds of the fault prediction coefficient and maintenance difficulty coefficient of the current equipment; The device safety analysis model F(P, K) is used to determine whether the current device is safe.

4. The AI-based medical equipment operation and maintenance management system according to claim 3 is characterized in that: The process of determining whether the current device is safe is as follows: The failure prediction coefficient P of the jth device j And the maintenance difficulty coefficient K j Substitute it into the equipment safety analysis model and calculate the fault estimation F(P j , K j ); F(P j , K j ) is compared with a preset safety threshold F(P, K)0; If F(P j , K j )≥F(P, K)0, then the current device is judged to be unsafe; Otherwise, the current device is judged to be safe.

5. The AI-based medical equipment operation and maintenance management system according to claim 3 is characterized in that: The process of obtaining the maintenance difficulty coefficient is as follows: Mark mechanical failure, software failure, and electrical failure as l1, l2, and l3 respectively; Fit and obtain the curves of mechanical failure, software failure and electrical failure frequency over time in each unit time: l1q(t), l2q(t), l3q(t); According to the change amplitude and extreme value of the change curve corresponding to the frequency of each fault type, the maintenance difficulty coefficients k1, k2, and k3 corresponding to each fault type are calculated respectively.

6. The AI-based medical equipment operation and maintenance management system according to claim 5 is characterized in that: The expressions of k1, k2 and k3 are: Among them, l1q(t)0, l2q(t)0, l3q(t)0 are reference curves, l1q max 、l1q min are the maximum and minimum values ​​of the frequency of mechanical failure, respectively. max 、l2q min are the maximum and minimum values ​​of the frequency of software failures, respectively. max 、l3q min are the maximum and minimum values ​​of the frequency of electrical faults, respectively; S1, S2, S3 are the fluctuation coefficients corresponding to each fault type, and t0 and t1 are the starting and ending points of the statistical period, respectively.

7. The AI-based medical equipment operation and maintenance management system according to claim 6, characterized in that: The process of obtaining the fluctuation coefficient corresponding to each fault type is: The number of times the i-th fault type occurs n and the duration of each maintenance process Δt e Substitute into the formula Calculate the average maintenance processing time S for each fault type i ; Among them, e is the e-th time, is the mean maintenance processing time for the i-th fault type.

8. The AI-based medical equipment operation and maintenance management system according to claim 1, characterized in that: The process of establishing a priority maintenance equipment list based on the analysis results is as follows: The condition F(P j , K j )≥F(P, K)0 is added to the maintenance equipment list; Arrange each device in the maintenance equipment list in descending order according to the maintenance difficulty coefficient K; Each device is numbered in sequence as 1, 2, 3, ... N, which serves as a list of priority maintenance equipment.

Images