Fault prediction and health management system

Abstract

The invention discloses a fault prediction and health management system, which comprises a data collection module, an equipment monitoring module and an equipment management and control module, and is characterized in that the data collection module is used for collecting state data in the operation process of medical equipment, historical fault data of the equipment and diagnosis data of a patient; the equipment monitoring module is used for detecting whether the running state of equipment is abnormal or not and predicting the failure rate of the equipment according to the running state of the equipment, and the equipment management and control module is used for recording historical maintenance data of the equipment, giving an alarm and managing the full life cycle and the part maintenance cycle of the equipment when the equipment fails. The data collection module, the equipment monitoring module and the equipment management and control module are electrically connected with one another, the data collection module comprises a historical data entry module, a data acquisition module and a diagnostic data entry module, and the data acquisition module is used for collecting equipment operation data.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment management, and in particular to a fault prediction and health management system. Background Art

[0002] With the rapid development of medical technology, medical equipment is an indispensable device in the diagnosis and treatment process of doctors. Therefore, the stable operation of medical equipment is crucial in the process of treating patients.

[0003] At present, most departments are equipped with medical equipment. However, in the process of managing medical equipment, since the patients detected by the equipment have different degrees of health problems, it is easy to misjudge or misjudge whether the equipment is faulty, which in turn leads to misdiagnosis of the patient's condition and affects the patient's treatment. Moreover, since the existing technology uses traditional regular maintenance methods to manage medical equipment, it is easy to have untimely equipment maintenance and maintenance, equipment failure and downtime, resulting in low equipment utilization, affecting the patient's treatment progress. Therefore, it is very necessary to design a fault prediction and health management system that improves accuracy and equipment utilization. Summary of the invention

[0004] The purpose of the present invention is to provide a fault prediction and health management system to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a fault prediction and health management system, comprising a data collection module, an equipment monitoring module and an equipment control module, characterized in that: the data collection module is used to collect status data of medical equipment during operation, historical fault data of the equipment and diagnostic data of patients, the equipment monitoring module is used to detect whether the equipment operation status is abnormal and predict the failure rate of the equipment according to the equipment operation status, the equipment control module is used to record the historical maintenance data of the equipment, issue an alarm when the equipment fails, and manage the entire life cycle and parts maintenance cycle of the equipment, and the data collection module, the equipment monitoring module and the equipment control module are electrically connected to each other;

[0006] The fault detection module includes a data analysis submodule, a condition analysis submodule and a fault judgment submodule. The data analysis submodule is used to analyze whether the equipment operation status data is normal, the condition analysis submodule is used to analyze whether the equipment detection result is consistent with the doctor's analysis result, and the fault judgment submodule is used to judge whether the equipment has a fault according to the analysis result;

[0007] The fault prediction module includes a model training submodule, a failure rate submodule and a result evaluation submodule. The model training submodule is used to train the equipment's fault prediction model based on the equipment's historical failure data entered into the system. The result evaluation submodule is used to analyze the factors affecting the equipment's failure rate and to correct the prediction results based on the analysis results. The failure rate prediction submodule is used to predict the equipment's operating status based on the fault prediction model.

[0008] According to the above technical solution, the data collection module includes a historical comprehensive data entry module, a data acquisition module and a diagnostic data entry module. The data acquisition module is used to collect equipment operation status data, the historical comprehensive data entry module is used to enter the equipment's historical fault data into the system, and the diagnostic data entry module is used to enter the doctor's diagnostic data into the system.

[0009] According to the above technical solution, the equipment monitoring module includes a fault detection module and a fault prediction module. The fault detection module is used to analyze the operating status of the equipment, analyze the patient's test results and the doctor's diagnosis results, and then determine whether the equipment has a fault. The fault prediction module is used to analyze the historical fault data of the equipment, use the historical fault data to train a fault prediction model, and modify the model according to the equipment's test results, and use the fault prediction model to predict the operating status of the equipment.

[0010] According to the above technical solution, the equipment management and control module includes a cycle management module and a maintenance record module. The cycle management module is used to manage the entire life cycle of the equipment and the maintenance cycle of equipment parts, and the maintenance record module is used to record the historical maintenance data of the equipment.

[0011] According to the above technical solution, the equipment management and control module also includes an early warning module, which is used to issue an alarm based on the fault detection result and fault prediction result of the equipment to remind the administrator to repair the equipment.

[0012] According to the above technical solution, the operation method of the fault prediction and health management system mainly includes the following steps:

[0013] Step S1: Collect comprehensive data of the equipment in real time during operation through the data acquisition module, enter the historical fault data of the equipment into the system through the historical comprehensive data entry module, and enter the doctor's diagnosis results into the system through the diagnosis data entry module;

[0014] Step S2: After the data is entered into the system, the system starts the fault detection module, starts analyzing the equipment's operating status data and the patient's condition test results at this time, and determines whether the equipment has a fault based on the analysis results;

[0015] Step S3: After detecting that the equipment has no faults, the system sends an electrical signal to start the fault prediction module, starts analyzing the historical fault data of the equipment, builds a fault prediction model based on the analysis results, analyzes the equipment operation data to correct the fault prediction model, and uses the corrected fault prediction model to analyze the operation of the equipment;

[0016] Step S4: When a device fails, the system reminds the administrator to perform maintenance on the device through the early warning module, and records the maintenance data and maintenance cycle of the device.

[0017] According to the above technical solution, step S2 further includes the following steps:

[0018] Step S21: When the host computer issues an instruction to the device, the instruction in the device execution module is obtained. When there is no instruction in the device execution module, the device circuit board is divided into m×n identical circuit modules, and the circuit modules are marked according to the transmission order of the instruction. The potential D1 between adjacent circuit modules is identified respectively, and compared with the rated potential D2 in the database. If the difference between the potentials D1 and D2 is greater than the minimum threshold and less than the maximum threshold, the device maintenance cycle is retrieved, and the device maintenance cycle is identified to be less than the threshold. The current device is marked as a software failure. Otherwise, the current device data transmission is marked as a failure. When there is an instruction in the device execution module, the actual working time and total running time of the device are retrieved, and the load rate of the device is calculated by the formula. In the formula, F represents the load rate of the equipment, t represents the actual working time of the equipment, and T represents the total running time of the equipment. If the load rate of the equipment is greater than the threshold, the equipment is marked as overload protection, otherwise the equipment execution module is marked as faulty.

[0019] Step S22: retrieve the patient test results of the current device and the diagnosis results entered into the system by the doctor, extract the disease characteristics of each device test result and doctor's diagnosis result respectively, import the disease characteristics into the disease knowledge graph, if there is a direct relationship between the disease characteristics in the knowledge graph, then mark the current device as fault-free, if there is a disease characteristic that has no direct relationship with other disease characteristics in the knowledge graph, then mark the disease characteristic and the corresponding test device, otherwise the system continues to detect, retrieve the relationship between the disease characteristics of other patients in the knowledge graph, identify the number of tags in the marked device, if the number of tags is greater than the system threshold, clear all tags in the current device, and mark the device as a faulty device, otherwise the system continues to detect.

[0020] According to the above technical solution, step S3 further includes the following steps:

[0021] Step S31: retrieve historical equipment fault data and equipment operation status data before the fault, identify the historical fault data and equipment operation status data, and perform data cleaning and normalization on the historical fault data and equipment operation status data to make the data meet the model training standard;

[0022] Step S32: retrieve the processed data, use the processed data as sample data, train the fault prediction model, identify the fault data features and the equipment operation status features respectively, match the fault feature data with the equipment operation status feature data, and perform weighted fusion, modify the fault prediction model according to the fused feature data, and use the fault prediction model to predict the failure rate of the equipment;

[0023] Step S33: retrieve the real-time operation data of the equipment, import the data into the fault prediction model, retrieve the fault prediction model corresponding to the equipment, compare the real-time operation status data of the equipment with the data in the fault prediction model, if there is data with a similarity greater than a threshold in the fault prediction model, identify the fault type corresponding to the fault prediction model data, retrieve the influence coefficient α of the corresponding fault probability in the database, and calculate the first probability of the equipment failure by the formula Q1=α·U×100%, where Q1 represents the first probability of the equipment failure, and U represents the similarity between the real-time operation status data of the equipment and the data in the fault prediction model, otherwise the system continues to detect.

[0024] According to the above technical solution, step S33 further includes the following steps:

[0025] Step S331: retrieve the equipment historical fault records of the target date to be predicted, identify the equipment historical fault frequency, retrieve the total fault frequency of the month in which the date is located and the total fault frequency of the year, calculate the proportion of the fault frequency of the month in the total fault frequency of the year, obtain the fault coefficient G of the corresponding ratio according to the ratio calculation database, calculate the proportion of the fault frequency of the date in the month, retrieve the influence coefficient β of the corresponding ratio in the database, retrieve the time from the date to the last maintenance date, and retrieve the corresponding influence coefficient μ in the database according to the time;

[0026] Obtain the usage frequency of the device in the system, construct a line graph based on the usage frequency of the device, calculate the slope K of the line graph, and if K is greater than the system set threshold, retrieve the corresponding growth coefficient η in the database according to the K value, and calculate the number of people on the target date through the formula M=m·η, where M represents the number of people on the target date, and m represents the number of people on the current date. According to the predicted number of people on the target date, retrieve the influence coefficient ω of a number of people on the probability of equipment failure in the database, and calculate the second probability of equipment failure through the formula Q2=G·β·μ·ω×100%, where Q2 represents the second probability of equipment failure;

[0027] Step S332: retrieve the first probability and the second probability of equipment failure. When both the first probability and the second probability of equipment failure are less than the minimum threshold, the average of the first probability and the second probability is used as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is less than the first threshold, the average of the first probability and the second probability is used as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is greater than the first threshold and less than the second threshold, retrieve the corresponding weighted fusion coefficient in the first scheme according to the difference to perform weighted fusion to obtain the failure rate Q3, and use Q3 as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is greater than the second threshold, compare the first probability and the second probability, and select the larger one as the failure rate Q4 of the equipment.

[0028] According to the above technical solution, the failure rate of each device is retrieved in step S4. If the predicted failure rate of the device is greater than the system threshold, an alarm is issued through the early warning module to notify the administrator to dispatch a technician for maintenance. Otherwise, detection is continued. When the technician performs maintenance, the technician obtains information about the parts replaced or maintained, and the maintenance database is retrieved based on the parts information. The corresponding information is updated in the maintenance database. When the parts reach the maintenance cycle, the system issues an alarm in advance through the early warning module to remind the technician to perform maintenance.

[0029] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention can accurately determine the reason why the device does not respond, and then accurately determine the failure of the device, by detecting the execution of the device on the instructions, analyzing the potential between the circuit modules of the device and the load rate of the device, making the device failure detection more accurate, enabling the administrator to discover the device failure in time and perform repairs, greatly improving the utilization rate of the device, and by analyzing the relationship between the patient's condition characteristics detected by each device in the knowledge graph, it can accurately determine whether the device has a failure, and promptly notify the management personnel to perform repairs, avoiding the failure of the device to detect the failure but fail to discover it in time, resulting in misdiagnosis of the patient's condition and delayed treatment of the patient, greatly improving the accuracy and timeliness of equipment failure detection, analyzing the failure trend of the device through the fault prediction model, and Calculating the failure probability of equipment can quickly predict whether the equipment will fail, and then maintain the equipment in advance to avoid equipment failure and downtime, greatly improving the utilization rate of the equipment. By analyzing the equipment's failure rate and maintenance cycle and their impact on the failure probability, combined with the impact of the equipment's use frequency on the equipment's failure probability, the equipment's failure probability can be predicted more accurately, avoiding equipment failures during use, which could result in patients being unable to receive timely treatment, further improving the accuracy of fault prediction and the utilization rate of the equipment. By analyzing the failure probabilities predicted by the two methods and performing weighted fusion, it is possible to avoid sudden changes in the equipment's failure rate caused by different influencing factors, reduce the error in equipment failure prediction, make the system's predicted failure probability more accurate, and greatly improve the accuracy of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0031] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] See also Figure 1, the present invention provides a technical solution: a fault prediction and health management system, including a data collection module, an equipment monitoring module and an equipment control module, characterized in that: the data collection module is used to collect status data of medical equipment during operation, historical fault data of equipment and patient diagnosis data, the equipment monitoring module is used to detect whether the equipment operation status is abnormal and predict the failure rate of the equipment according to the equipment operation status, the equipment control module is used to record the historical maintenance data of the equipment, issue an alarm when the equipment fails, and manage the entire life cycle and parts maintenance cycle of the equipment, and the data collection module, the equipment monitoring module and the equipment control module are electrically connected to each other;

[0034] The fault detection module includes a data analysis submodule, a condition analysis submodule and a fault judgment submodule. The data analysis submodule is used to analyze whether the equipment operation status data is normal, the condition analysis submodule is used to analyze whether the equipment detection results are consistent with the doctor's analysis results, and the fault judgment submodule is used to judge whether the equipment has a fault according to the analysis results;

[0035] The fault prediction module includes a model training submodule, a failure rate submodule and a result evaluation submodule. The model training submodule is used to train the equipment's fault prediction model based on the equipment's historical failure data entered into the system. The result evaluation submodule is used to analyze the factors affecting the equipment's failure rate and to correct the prediction results based on the analysis results. The failure rate prediction submodule is used to predict the equipment's operating status based on the fault prediction model.

[0036] The data collection module includes a historical comprehensive data entry module, a data acquisition module and a diagnostic data entry module. The data acquisition module is used to collect equipment operation status data, the historical comprehensive data entry module is used to enter the equipment's historical fault data into the system, and the diagnostic data entry module is used to enter the doctor's diagnostic data into the system.

[0037] The equipment monitoring module includes a fault detection module and a fault prediction module. The fault detection module is used to analyze the operating status of the equipment, analyze the patient's test results and the doctor's diagnosis results, and then determine whether the equipment has a fault. The fault prediction module is used to analyze the historical fault data of the equipment, use the historical fault data to train the fault prediction model, and modify the model according to the equipment's test results, and use the fault prediction model to predict the operating status of the equipment.

[0038] The equipment management and control module includes a cycle management module and a maintenance record module. The cycle management module is used to manage the entire life cycle of the equipment and the maintenance cycle of equipment parts. The maintenance record module is used to record the historical maintenance data of the equipment.

[0039] The equipment management and control module also includes an early warning module, which is used to issue alarms based on the equipment's fault detection results and fault prediction results to remind the administrator to repair the equipment.

[0040] The operation method of the fault prediction and health management system mainly includes the following steps:

[0041] Step S1: Collect comprehensive data of the equipment in real time during operation through the data acquisition module, enter the historical fault data of the equipment into the system through the historical comprehensive data entry module, and enter the doctor's diagnosis results into the system through the diagnosis data entry module;

[0042] Step S2: After the data is entered into the system, the system starts the fault detection module, starts analyzing the equipment's operating status data and the patient's condition test results at this time, and determines whether the equipment has a fault based on the analysis results;

[0043] Step S3: After detecting that the equipment has no faults, the system sends an electrical signal to start the fault prediction module, starts analyzing the historical fault data of the equipment, builds a fault prediction model based on the analysis results, analyzes the equipment operation data to correct the fault prediction model, and uses the corrected fault prediction model to analyze the operation of the equipment;

[0044] Step S4: When a device fails, the system reminds the administrator to perform maintenance on the device through the early warning module, and records the maintenance data and maintenance cycle of the device.

[0045] Step S2 further comprises the following steps:

[0046] Step S21: When the host computer issues an instruction to the device, the instruction in the device execution module is obtained. When there is no instruction in the device execution module, the device circuit board is divided into m×n identical circuit modules, and the circuit modules are marked according to the transmission order of the instruction. The potential D1 between adjacent circuit modules is identified respectively, and compared with the rated potential D2 in the database. If the difference between the potentials D1 and D2 is greater than the minimum threshold and less than the maximum threshold, the device maintenance cycle is retrieved, and the device maintenance cycle is identified to be less than the threshold. The current device is marked as a software failure. Otherwise, the current device data transmission is marked as a failure. When there is an instruction in the device execution module, the actual working time and total running time of the device are retrieved, and the load rate of the device is calculated by the formula. In the formula, F represents the load rate of the device, t represents the actual working time of the device, and T represents the total running time of the device. If the load rate of the device is greater than the threshold, the device is marked as overload protection, otherwise the device execution module failure is marked. By detecting the execution of the device on the instruction, analyzing the potential between the circuit modules of the device and the load rate of the device, the reason why the device does not respond can be accurately determined, and then the device failure can be accurately determined, making the device failure detection more accurate, so that the administrator can find the equipment failure in time and repair it, which greatly improves the utilization rate of the equipment;

[0047] Step S22: retrieve the patient test results of the current device and the diagnosis results entered into the system by the doctor, extract the disease characteristics of each device test result and the doctor's diagnosis result respectively, import the disease characteristics into the disease knowledge graph, if there is a direct relationship between the disease characteristics in the knowledge graph, mark the current device as fault-free, if there is a disease characteristic in the knowledge graph that has no direct relationship with other disease characteristics, mark the disease characteristic and the corresponding detection device, otherwise the system continues to detect, retrieve the relationship between the disease characteristics of other patients in the knowledge graph, identify the number of tags in the marked device, if the number of tags is greater than the system threshold, clear all tags in the current device, and mark the device as a faulty device, otherwise the system continues to detect, by analyzing the relationship between the patient disease characteristics detected by each device in the knowledge graph, it is possible to accurately determine whether the equipment has a fault, and promptly notify the management personnel for maintenance, to avoid the equipment detection failure that cannot be discovered in time, resulting in misdiagnosis of the patient's condition and delayed treatment of the patient, greatly improving the accuracy and timeliness of equipment fault detection.

[0048] Step S3 further comprises the following steps:

[0049] Step S31: retrieve historical equipment fault data and equipment operation status data before the fault, identify the historical fault data and equipment operation status data, and perform data cleaning and normalization on the historical fault data and equipment operation status data to make the data meet the model training standard;

[0050] Step S32: retrieve the processed data, use the processed data as sample data, train the fault prediction model, identify the fault data features and the equipment operation status features respectively, match the fault feature data with the equipment operation status feature data, and perform weighted fusion, modify the fault prediction model according to the fused feature data, and use the fault prediction model to predict the failure rate of the equipment;

[0051] Step S33: retrieve the real-time operation data of the equipment, import the data into the fault prediction model, retrieve the fault prediction model corresponding to the equipment, compare the real-time operation status data of the equipment with the data in the fault prediction model, if there is data with a similarity greater than a threshold in the fault prediction model, identify the fault type corresponding to the fault prediction model data, retrieve the influence coefficient α of the corresponding fault probability in the database, and calculate the first probability of the equipment failure through the formula Q1=α·U×100%, where Q1 represents the first probability of the equipment failure, and U represents the similarity between the real-time operation status data of the equipment and the data in the fault prediction model. Otherwise, the system continues to detect, analyzes the failure trend of the equipment through the fault prediction model, and calculates the failure probability of the equipment, so as to quickly predict whether the equipment will fail, and then maintain the equipment in advance to avoid equipment failure and downtime, thereby greatly improving the utilization rate of the equipment.

[0052] Step S33 further includes the following steps:

[0053] Step S331: retrieve the equipment historical fault records of the target date to be predicted, identify the equipment historical fault frequency, retrieve the total fault frequency of the month in which the date is located and the total fault frequency of the year, calculate the proportion of the fault frequency of the month in the total fault frequency of the year, obtain the fault coefficient G of the corresponding ratio according to the ratio calculation database, calculate the proportion of the fault frequency of the date in the month, retrieve the influence coefficient β of the corresponding ratio in the database, retrieve the time from the date to the last maintenance date, and retrieve the corresponding influence coefficient μ in the database according to the time;

[0054] Obtain the usage frequency of the device in the system, construct a line graph based on the usage frequency of the device, calculate the slope K of the line graph, if K is greater than the system set threshold, then retrieve the corresponding growth coefficient η in the database according to the K value, and calculate the number of people on the target date through the formula M = m·η, where M represents the number of people on the target date, and m represents the number of people on the current date. According to the predicted number of people on the target date, retrieve the influence coefficient ω of a number of people on the probability of equipment failure in the database, and calculate the second probability of equipment failure through the formula Q2 = G·β·μ·ω×100%, where Q2 represents the second probability of equipment failure. By analyzing the equipment failure rate and maintenance cycle and their impact on the failure probability, combined with the impact of the equipment usage frequency on the equipment failure probability, the equipment failure probability prediction is made more accurate, avoiding equipment failure during use, resulting in patients being unable to receive timely treatment, and further improving the accuracy of fault prediction and equipment utilization;

[0055] Step S332: retrieve the first probability and the second probability of equipment failure. When the first probability and the second probability of equipment failure are both less than the minimum threshold, the average of the first probability and the second probability is used as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is less than the first threshold, the average of the first probability and the second probability is used as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is greater than the first threshold and less than the second threshold, retrieve the corresponding weighted fusion coefficient in the first scheme according to the difference to perform weighted fusion to obtain the failure rate Q3, and use Q3 as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is greater than the second threshold, compare the first probability and the second probability, and select the larger one as the failure rate Q4 of the equipment. By analyzing the failure probabilities predicted by the two methods and performing weighted fusion, it is possible to avoid a dramatic change in the equipment failure rate caused by sudden changes in different influencing factors, reduce the error in equipment failure prediction, make the failure probability predicted by the system more accurate, and greatly improve the accuracy of the system.

[0056] In step S4, the failure rate of each device is retrieved. If the predicted failure rate of the device is greater than the system threshold, an alarm is issued through the early warning module to notify the administrator to dispatch technicians for maintenance. Otherwise, the detection continues. When the technicians perform maintenance, the technicians obtain information about the parts replaced or maintained, and the maintenance database is retrieved based on the parts information. The corresponding information is updated in the maintenance database. When the parts reach the maintenance cycle, the system sends an alarm in advance through the early warning module to remind the technicians to perform maintenance.

[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0058] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fault prediction and health management system, comprising a data collection module, an equipment monitoring module and an equipment control module, characterized in that: The data collection module is used to collect status data of the medical device during operation, historical fault data of the device and diagnostic data of the patient; the device monitoring module is used to detect whether the operation status of the device is abnormal and predict the failure rate of the device according to the operation status of the device; the device management and control module is used to record the historical maintenance data of the device, issue an alarm when the device fails, and manage the entire life cycle and parts maintenance cycle of the device; the data collection module, the device monitoring module and the device management and control module are electrically connected to each other; The fault detection module includes a data analysis submodule, a condition analysis submodule and a fault judgment submodule. The data analysis submodule is used to analyze whether the equipment operation status data is normal, the condition analysis submodule is used to analyze whether the equipment detection result is consistent with the doctor's analysis result, and the fault judgment submodule is used to judge whether the equipment has a fault according to the analysis result; The fault prediction module includes a model training submodule, a failure rate submodule and a result evaluation submodule. The model training submodule is used to train the equipment's fault prediction model based on the equipment's historical failure data entered into the system. The result evaluation submodule is used to analyze the factors affecting the equipment's failure rate and to correct the prediction results based on the analysis results. The failure rate prediction submodule is used to predict the equipment's operating status based on the fault prediction model.

2. A fault prediction and health management system according to claim 1, characterized in that: The data collection module includes a historical data entry module, a data acquisition module and a diagnostic data entry module. The data acquisition module is used to collect equipment operating status data, the historical data entry module is used to enter the equipment's historical fault data into the system, and the diagnostic data entry module is used to enter the doctor's diagnostic data into the system.

3. A fault prediction and health management system according to claim 2, characterized in that: The equipment monitoring module includes a fault detection module and a fault prediction module. The fault detection module is used to analyze the operating status of the equipment, analyze the patient's test results and the doctor's diagnosis results, and then determine whether the equipment has a fault. The fault prediction module is used to analyze the historical fault data of the equipment, use the historical fault data to train a fault prediction model, and modify the model according to the equipment's test results, and use the fault prediction model to predict the operating status of the equipment.

4. A fault prediction and health management system according to claim 3, characterized in that: The equipment management and control module includes a cycle management module and a maintenance record module. The cycle management module is used to manage the entire life cycle of the equipment and the maintenance cycle of equipment parts, and the maintenance record module is used to record the historical maintenance data of the equipment.

5. A fault prediction and health management system according to claim 4, characterized in that: The equipment management and control module also includes an early warning module, which is used to issue an alarm based on the fault detection result and the fault prediction result of the equipment to remind the administrator to repair the equipment.

6. A fault prediction and health management system according to claim 5, characterized in that: The operation method of the fault prediction and health management system mainly includes the following steps: Step S1: Collect comprehensive data of the equipment in real time during operation through the data acquisition module, enter the historical fault data of the equipment into the system through the historical data entry module, and enter the doctor's diagnosis results into the system through the diagnosis data entry module; Step S2: After the data is entered into the system, the system starts the fault detection module, starts analyzing the equipment's operating status data and the patient's condition test results at this time, and determines whether the equipment has a fault based on the analysis results; Step S3: After detecting that the equipment has no faults, the system sends an electrical signal to start the fault prediction module, starts analyzing the historical fault data of the equipment, builds a fault prediction model based on the analysis results, analyzes the equipment operation data to correct the fault prediction model, and uses the corrected fault prediction model to analyze the operation of the equipment; Step S4: When a device fails, the system reminds the administrator to perform maintenance on the device through the early warning module, and records the maintenance data and maintenance cycle of the device.

7. A fault prediction and health management system according to claim 6, characterized in that: The step S2 further comprises the following steps: Step S21: When the host computer issues an instruction to the device, the instruction in the device execution module is obtained. When there is no instruction in the device execution module, the device circuit board is divided into m×n identical circuit modules, and the circuit modules are marked according to the transmission order of the instruction. The potential D1 between adjacent circuit modules is identified respectively, and compared with the rated potential D2 in the database. If the difference between the potentials D1 and D2 is greater than the minimum threshold and less than the maximum threshold, the device maintenance cycle is retrieved, and the device maintenance cycle is identified to be less than the threshold. The current device is marked as a software failure. Otherwise, the current device data transmission is marked as a failure. When there is an instruction in the device execution module, the actual working time and total running time of the device are retrieved, and the load rate of the device is calculated by the formula. In the formula, F represents the load rate of the equipment, t represents the actual working time of the equipment, and T represents the total running time of the equipment. If the load rate of the equipment is greater than the threshold, the equipment is marked as overload protection, otherwise the equipment execution module is marked as faulty. Step S22: retrieve the patient test results of the current device and the diagnosis results entered into the system by the doctor, extract the disease characteristics of each device test result and doctor's diagnosis result respectively, import the disease characteristics into the disease knowledge graph, if there is a direct relationship between the disease characteristics in the knowledge graph, then mark the current device as fault-free, if there is a disease characteristic that has no direct relationship with other disease characteristics in the knowledge graph, then mark the disease characteristic and the corresponding test device, otherwise the system continues to detect, retrieve the relationship between the disease characteristics of other patients in the knowledge graph, identify the number of tags in the marked device, if the number of tags is greater than the system threshold, clear all tags in the current device, and mark the device as a faulty device, otherwise the system continues to detect.

8. A fault prediction and health management system according to claim 7, characterized in that: The step S3 further comprises the following steps: Step S31: retrieve historical equipment fault data and equipment operation status data before the fault, identify the historical fault data and equipment operation status data, and perform data cleaning and normalization on the historical fault data and equipment operation status data to make the data meet the model training standard; Step S32: retrieve the processed data, use the processed data as sample data, train the fault prediction model, identify the fault data features and the equipment operation status features respectively, match the fault feature data with the equipment operation status feature data, and perform weighted fusion, modify the fault prediction model according to the fused feature data, and use the fault prediction model to predict the failure rate of the equipment; Step S33: retrieve the real-time operation data of the equipment, import the data into the fault prediction model, retrieve the fault prediction model corresponding to the equipment, compare the real-time operation status data of the equipment with the data in the fault prediction model, if there is data with a similarity greater than a threshold in the fault prediction model, identify the fault type corresponding to the fault prediction model data, retrieve the influence coefficient α of the corresponding fault probability in the database, and calculate the first probability of the equipment failure by the formula Q1=α·U×100%, where Q1 represents the first probability of the equipment failure, and U represents the similarity between the real-time operation status data of the equipment and the data in the fault prediction model, otherwise the system continues to detect.

9. A fault prediction and health management system according to claim 8, characterized in that: The step S33 further comprises the following steps: Step S331: retrieve the equipment historical fault records of the target date to be predicted, identify the equipment historical fault frequency, retrieve the total fault frequency of the month in which the date is located and the total fault frequency of the year, calculate the proportion of the fault frequency of the month in the total fault frequency of the year, obtain the fault coefficient G of the corresponding ratio according to the ratio calculation database, calculate the proportion of the fault frequency of the date in the month, retrieve the influence coefficient β of the corresponding ratio in the database, retrieve the time from the date to the last maintenance date, and retrieve the corresponding influence coefficient μ in the database according to the time; Obtain the usage frequency of the device in the system, construct a line graph based on the usage frequency of the device, calculate the slope K of the line graph, and if K is greater than the system set threshold, retrieve the corresponding growth coefficient η in the database according to the K value, and calculate the number of people on the target date through the formula M=m·η, where M represents the number of people on the target date, and m represents the number of people on the current date. According to the predicted number of people on the target date, retrieve the influence coefficient ω of a number of people on the probability of equipment failure in the database, and calculate the second probability of equipment failure through the formula Q2=G·β·μ·ω×100%, where Q2 represents the second probability of equipment failure; Step S332: retrieve the first probability and the second probability of equipment failure. When both the first probability and the second probability of equipment failure are less than the minimum threshold, the average of the first probability and the second probability is used as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is less than the first threshold, the average of the first probability and the second probability is used as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is greater than the first threshold and less than the second threshold, retrieve the corresponding weighted fusion coefficient in the first scheme according to the difference to perform weighted fusion to obtain the failure rate Q3, and use Q3 as the failure rate of the equipment. When the difference between the first probability and the second probability of equipment failure is greater than the second threshold, compare the first probability and the second probability, and select the larger one as the failure rate Q4 of the equipment.

10. A fault prediction and health management system according to claim 9, characterized in that: In step S4, the failure rate of each device is retrieved. If the predicted failure rate of the device is greater than the system threshold, an alarm is issued through the early warning module to notify the administrator to dispatch a technician for maintenance. Otherwise, the detection is continued. When the technician performs maintenance, the technician obtains information about the parts replaced or maintained, and the maintenance database is retrieved based on the parts information. The corresponding information is updated in the maintenance database. When the parts reach the maintenance cycle, the system issues an alarm in advance through the early warning module to remind the technician to perform maintenance.

Images