Fault detection and early warning method for equipment

By establishing explicit and implicit fault monitoring nodes in the X-ray machine and monitoring different components, the problems of high fault detection cost and insufficient accuracy in the existing technology are solved, and more efficient fault warning and monitoring are achieved.

CN118633963BActive Publication Date: 2024-11-19NANTONG XIFENG MEDICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411088370.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-19
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

In the prior art, X-ray machine fault detection adopts unified monitoring equipment, resulting in high monitoring costs and insufficient targeting, which in turn affects the accuracy of fault detection.

Method used

Establish explicit fault monitoring nodes and implicit fault monitoring nodes to monitor components with surface fault characteristics and fault components that are not easily directly observed. Characteristic analysis is performed through explicit fault monitoring equipment, combined with the temperature monitoring of sealing ring components and The beam path monitoring of the collimator generates fault detection results and achieves targeted fault warning.

Benefits of technology

It improves the accuracy of fault warning, reduces monitoring costs, realizes targeted monitoring of different components, and ensures the stable operation of the X-ray machine.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118633963B_ABST
    Figure CN118633963B_ABST
Patent Text Reader

Abstract

The present application provides a method for fault detection and early warning of an equipment, which relates to the field of fault detection technology, and the method includes: establishing explicit fault monitoring nodes and implicit fault monitoring nodes of a target X-ray machine; generating explicit fault detection results; monitoring the temperature rise of the sealing ring components of the radiation source body sealing node to generate a sealing node fault detection result; monitoring the radiation beam irradiation path of the collimator node to generate a collimator node fault detection result; and combining the explicit fault detection result, the sealing node fault detection result and the collimator node fault detection result to respond to a fault early warning of the target X-ray machine. The present application can solve the technical problem in the prior art that the monitoring cost is too high and the pertinence is insufficient due to the use of unified monitoring equipment for monitoring different parts, which leads to inaccurate fault detection and early warning, and achieves targeted monitoring of different components, thereby achieving the technical effect of improving the accuracy of fault early warning and saving monitoring resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and in particular to a method for early warning of fault detection of equipment. Background Art

[0002] With the development of medical imaging technology, X-ray machines have become an important tool for medical institutions to diagnose diseases. X-ray machines generate X-rays and pass through the human body to obtain images of the internal structure of the human body, thereby helping doctors to make diagnoses. However, due to the complex working environment of X-ray machines, the equipment runs in high voltage and high heat environments for a long time, and equipment failures occur frequently, which directly affects the stable operation of the equipment and the accuracy of diagnosis.

[0003] Traditional X-ray machine fault detection usually uses unified monitoring equipment to monitor different parts of the entire device, such as setting up multiple sensors for monitoring. This results in excessively high monitoring costs and lack of specificity, which in turn leads to inaccurate fault detection and warning. Summary of the invention

[0004] The purpose of this application is to provide a method for fault detection and early warning of equipment, so as to solve the technical problem in the prior art that different parts are monitored by unified monitoring equipment, the monitoring cost is too high and the pertinence is insufficient, which leads to inaccurate fault detection and early warning.

[0005] In view of the above problems, the present application provides a fault detection and early warning method for an equipment, the method comprising: establishing an explicit fault monitoring node and a latent fault monitoring node of a target X-ray machine, wherein the explicit fault monitoring node comprises a component node with surface fault characteristics, and the latent fault monitoring node comprises a radiation source body sealing node and a collimator node; connecting an explicit fault monitoring device of the explicit fault monitoring node to perform explicit characteristic monitoring and analysis to generate an explicit fault detection result; performing temperature rise monitoring of the sealing ring component of the radiation source body sealing node, performing expansion deformation and oil leakage analysis and prediction based on the temperature rise monitoring sequence, performing source body component failure probability prediction based on the prediction results, and generating a sealing node failure detection result; performing radiation beam irradiation path monitoring on the collimator node, performing fault analysis based on the irradiation path and the preset path, and generating a collimator node failure detection result; and performing a fault early warning response to the target X-ray machine based on the explicit fault detection result, the sealing node failure detection result, and the collimator node failure detection result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Establish explicit fault monitoring nodes and implicit fault monitoring nodes of the target X-ray machine, wherein the explicit fault monitoring nodes include component nodes with surface fault characteristics, and the implicit fault monitoring nodes include radiation source body sealing nodes and collimator nodes; connect the explicit fault monitoring equipment of the explicit fault monitoring nodes, perform explicit feature monitoring and analysis, and generate explicit fault detection results; perform temperature rise monitoring of the sealing ring components of the radiation source body sealing node, perform expansion deformation and oil leakage analysis and prediction based on the temperature rise monitoring sequence, and perform source body component failure probability prediction based on the prediction results to generate sealing node fault detection results; perform radiation beam irradiation path monitoring on the collimator node, perform fault analysis based on the irradiation path and the preset path, and generate collimator node fault detection results; perform fault warning response to the target X-ray machine based on the explicit fault detection results, the sealing node fault detection results, and the collimator node fault detection results. By establishing explicit fault monitoring nodes and implicit fault monitoring nodes, targeted monitoring is performed on different components, and targeted monitoring of different components is achieved, so as to improve the accuracy of fault warning and save monitoring resources at the same time.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a method for detecting and warning a fault of a device according to the present application;

[0011] Figure 2 A schematic diagram of a process for establishing an explicit fault monitoring node of a target X-ray machine in a method for fault detection and early warning of an equipment according to the present application. DETAILED DESCRIPTION

[0012] This application provides a method for fault detection and early warning of equipment, which solves the technical problem in the prior art that different parts are monitored by unified monitoring equipment, the monitoring cost is too high, and the pertinence is insufficient, which leads to inaccurate fault detection and early warning. Targeted monitoring of different components is achieved to improve the accuracy of fault early warning and save monitoring resources at the same time.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] Please refer to the attached Figure 1 The present application provides a method for detecting and warning a fault of a device, and the method specifically comprises the following steps:

[0015] Step 1: Establish explicit fault monitoring nodes and implicit fault monitoring nodes of the target X-ray machine, wherein the explicit fault monitoring nodes include component nodes with surface fault characteristics, and the implicit fault monitoring nodes include radiation source body sealing nodes and collimator nodes.

[0016] Specifically, surface fault features usually refer to faults that can be directly observed, such as damage and deformation of components. Components of the target X-ray machine with surface fault features are selected as explicit fault monitoring nodes. For example, the controller power board of the X-ray source controller provides power drive for the X-ray source high-voltage circuit. The main components include electrolytic capacitors and transistors. The main fault phenomena include fuse blowing, diode breakdown, and capacitor bulging. Such faults are explicit faults and can be quickly located through appearance inspection. That is, when a fault occurs, it usually shows obvious features on the surface, such as cracks and deformation. By using visual inspection technology, the status of these components can be monitored in real time, so these components are used as explicit fault monitoring nodes.

[0017] Hidden fault monitoring nodes refer to faulty components that are not easy to observe directly, such as the degradation of the sealing performance of the radiation source body and the internal structure problems of the collimator. The radiation source body sealing node and the collimator node are two key parts. The radiation source body sealing node is responsible for monitoring the sealing performance of the radiation source body. Once the sealing performance deteriorates, it may cause the internal components to burn out due to high temperature operation. The collimator node is responsible for monitoring whether the internal structure of the collimator is normal. The collimator is an important component in the X-ray machine and is responsible for controlling the direction and shape of the X-rays. Once there is a problem with the internal structure of the collimator, it may affect the imaging quality of the X-ray machine.

[0018] The existing technology usually uses a set of monitoring equipment for different components, such as setting up multiple sensors for monitoring, which leads to high monitoring costs and insufficient pertinence. This application can achieve targeted feature monitoring of different faulty components of the X-ray machine status by establishing explicit fault monitoring nodes and implicit fault monitoring nodes, so as to timely discover and handle faults and ensure the normal operation and safe use of the X-ray machine.

[0019] Step 2: Connect the explicit fault monitoring device of the explicit fault monitoring node to perform explicit feature monitoring and analysis to generate explicit fault detection results.

[0020] Specifically, explicit fault monitoring nodes are mainly realized by installing sensors, cameras or other appearance monitoring equipment. These devices can collect images of explicit fault monitoring nodes in real time to monitor the surface fault characteristics of X-ray machine components. The explicit fault monitoring device is a high-precision image acquisition device. The explicit fault monitoring node is imaged and collected by the explicit fault monitoring device. The collected data is processed by a preset analysis algorithm or model to identify the characteristics of the explicit fault. For example, for the detection of fuse blowing, diode breakdown and capacitor bulging, the collected data can be analyzed by image processing technology to identify the shape, length and other characteristics of the crack. According to the identification results, it is determined whether there is an explicit fault, and the type and location of the fault are given to generate the explicit fault detection result. The explicit fault of the X-ray machine can be discovered and handled in a timely manner to ensure the normal operation and safe use of the X-ray machine.

[0021] Step three: monitor the temperature rise of the sealing ring components of the radiation source sealing node, perform expansion deformation and oil leakage analysis and prediction based on the temperature rise monitoring sequence, predict the probability of source device failure based on the prediction results, and generate sealing node failure detection results.

[0022] Specifically, the temperature change of the sealing ring component is monitored in real time through the temperature sensor preset in the sealing ring component. The sealing ring component plays the role of sealing the radiation source body in the X-ray machine. The components inside the radiation source body will generate heat. If the sealing ring component is in a high temperature state for a long time, it will accelerate the expansion and deformation of the sealing component to varying degrees, resulting in gaps between components, causing oil leakage, and then affecting the heat transfer from the source body to the outside, resulting in insufficient heat dissipation of the source body, and the internal ambient temperature of the radiation source continues to rise, eventually burning out the internal components of the radiation source. The temperature rise monitoring sequence refers to the continuous recording of the temperature change data of the sealing ring component over time.

[0023] The expansion deformation and oil leakage analysis prediction based on the temperature rise monitoring sequence refers to the use of the monitored temperature data to predict the possible expansion deformation and oil leakage of the sealing ring components through intelligent models or data-driven models. The expansion deformation analysis prediction is based on the thermal expansion characteristics of the sealing ring material, predicting the size change of the sealing ring when the temperature rises, so as to determine whether it will expand and deform. The oil leakage analysis prediction is based on the expansion deformation analysis prediction results, analyzing the gap characteristics between the components, resulting in oil leakage, and then analyzing the probability of internal components burning out, that is, the source device failure probability. For example, if the prediction results show that the sealing ring components may have serious expansion deformation or oil leakage, then the probability of failure of the radiation source device will increase. According to the results of the source device failure probability prediction, the sealing node fault detection results are generated, including the probability of failure, so that the operator or maintenance personnel can take corresponding measures in time, such as replacing the sealing ring components, adjusting the working parameters of the radiation source body, etc., to reduce the risk of failure and ensure the normal operation and safety of the X-ray machine.

[0024] Step 4: Monitor the irradiation path of the ray beam on the collimator node, perform fault analysis based on the irradiation path and the preset path, and generate a collimator node fault detection result.

[0025] Specifically, beam monitoring equipment, such as beam detectors or beam cameras, is used to monitor the irradiation path of the beam in real time. The irradiation path of the beam refers to the propagation path of the beam after it is emitted from the source and collimated by the collimator. The preset path refers to the path that the beam should follow under normal circumstances. This path is usually preset according to the design of the collimator and the application requirements of the X-ray machine. Fault analysis based on the irradiation path and the preset path refers to comparing the irradiation path of the beam monitored in real time with the preset path and analyzing the difference between the two. If there is a significant deviation between the monitored irradiation path and the preset path, this may indicate that there is a fault in the collimator, such as damage to the internal structure of the collimator, offset of the collimator position, etc., thereby judging whether there is a fault, generating a collimator node fault detection result, realizing fault detection of the collimator node, timely discovering and handling collimator faults, and ensuring the imaging quality and safety of the X-ray machine.

[0026] Step 5: Combine the explicit fault detection result, the sealing node fault detection result and the collimator node fault detection result to perform a fault warning response to the target X-ray machine.

[0027] Specifically, the fault detection results of the explicit fault monitoring nodes, sealing nodes and collimator nodes are summarized and analyzed, and the failure probability and failure severity of each faulty component are comprehensively evaluated. The evaluation results will be used to generate fault warnings, that is, to predict and warn of possible faults in different modes according to the severity of the fault, so as to remind staff to perform fault inspection and repair in time.

[0028] In summary, the present application establishes explicit fault monitoring nodes and implicit fault monitoring nodes to perform targeted monitoring of different components, thereby avoiding excessively high monitoring costs and inaccurate monitoring results due to the same monitoring data type for all components. At the same time, targeted monitoring of different components is achieved, thereby achieving the technical effect of improving the accuracy of fault warnings and saving monitoring resources.

[0029] Further, as attached Figure 2 As shown, step one of this application includes:

[0030] Acquire the model and specification information of the target X-ray machine, perform historical fault detection collection based on the model and specification information as a constraint, and generate a historical fault detection record data set; divide the historical fault detection record data set based on the faulty component as a classification constraint, and generate multiple component detection record sets; perform explicit detection confidence identification on the first component detection record set among the multiple component detection record sets, and generate a first explicit confidence; if the first explicit confidence is greater than or equal to a preset confidence, add the first component to the explicit fault monitoring node.

[0031] Furthermore, the present application also includes the following steps:

[0032] Any detection record in the first component detection record set includes explicit detection result records, implicit feature detection records and fault verification true value records; the explicit detection result records and the fault verification true value records are compared to output the explicit detection accuracy; the implicit feature detection records and the fault verification true value records are compared to output the implicit detection accuracy; the accuracy deviation degree between the explicit detection accuracy and the implicit detection accuracy is calculated, the explicit detection accuracy is feedback-adjusted, and the first explicit confidence is generated.

[0033] Specifically, the steps for establishing the explicit fault monitoring node of the target X-ray machine are as follows:

[0034] Obtaining the model and specification information of the target X-ray machine is the basis for historical fault detection collection. Model and specification information includes the model and technical parameters of the X-ray machine, which can be obtained through the equipment manual, information provided by the manufacturer, or the identification label of the equipment. Historical fault detection collection is performed with model and specification information as a constraint, that is, when collecting historical fault data, only fault cases of the same or similar model as the target X-ray machine are considered. This ensures that the collected data set has a high correlation with the target X-ray machine, thereby improving the accuracy and reliability of subsequent analysis. Any detection record of the historical fault detection record data set includes explicit detection result records, implicit feature detection records, and fault verification true value records of each component. That is to say, when performing fault detection, multiple data will be used for detection, such as images, temperature, operating voltage, current, etc. Among them, the fault detection result identified based on image data is the explicit detection result record, the fault detection record identified based on other data is the implicit feature detection record, and the fault verification true value record refers to the actual fault judgment result.

[0035] Taking the faulty components as classification constraints, the historical fault detection record data set is divided, which is to classify the data set according to the components where the fault occurs, and generate multiple component detection record sets. For example, the data set can be divided into a robot arm fault record set, a detector fault record set, a filter fault record set, etc., and each record set contains all detection records related to the component. The first component detection record set refers to any component detection record set among the multiple component detection record sets. Performing explicit detection confidence identification on the first component detection record set is to evaluate the reliability of the component in fault detection through explicit features and generate a first explicit confidence.

[0036] The specific steps of performing explicit detection confidence identification include: in any detection record in the first component detection record set, comparing the explicit detection result record and the fault verification true value record is to evaluate the accuracy of explicit fault detection. The explicit detection accuracy refers to the consistency between the explicit detection result and the fault verification true value, which can be obtained by calculating the matching degree or accuracy of the two. For example, the ratio between the number of correctly detected faults and the total number of faults can be calculated, or the error between the fault detection result and the real fault can be calculated.

[0037] The purpose of comparing the latent feature detection records with the fault verification true value records is to evaluate the accuracy of latent fault detection. The latent detection accuracy refers to the degree of consistency between the latent feature detection results and the fault verification true value. Similarly, this can be obtained by calculating the matching degree or accuracy rate between the two.

[0038] The accuracy deviation degree of explicit detection accuracy and implicit detection accuracy is calculated to evaluate the difference between explicit detection accuracy and implicit detection accuracy. The accuracy deviation degree can be calculated by comparing the accuracy or matching degree of the two. If the explicit detection accuracy is significantly higher than the implicit detection accuracy, it is said that explicit fault detection is more reliable than implicit fault detection.

[0039] The accuracy deviation degree, the feedback adjustment of the explicit detection accuracy is to combine the accuracy deviation degree of the explicit detection accuracy and the implicit detection accuracy, and more accurately evaluate the reliability of explicit detection, that is, if the explicit detection accuracy is greater than the implicit detection accuracy, it means that for the first component, the reliability of explicit detection is higher, and the explicit detection accuracy can be adjusted upward according to the accuracy deviation degree; conversely, if the explicit detection accuracy is less than the implicit detection accuracy, it means that for the first component, the reliability of explicit detection is not high, and the explicit detection accuracy can be adjusted downward according to the accuracy deviation degree, thereby generating the first explicit confidence. Improve the accuracy of the confidence assessment of explicit fault detection, and then establish an explicit fault monitoring node to improve the accuracy of fault monitoring.

[0040] If the first explicit confidence is greater than or equal to the preset confidence, it means that the reliability of explicit detection is high for the first component, and the first component can be added to the explicit fault monitoring node. The preset confidence is a threshold used to determine whether the reliability of explicit detection reaches an acceptable level. If the confidence is higher than this threshold, it means that the reliability is high enough, and the component can be included in the explicit fault monitoring node to improve the accuracy of the monitoring node, thereby improving the accuracy of fault warning.

[0041] Further, step three of this application includes:

[0042] Acquire the manufacturing material information and component connection structure characteristics of the sealing ring component; perform material expansion and deformation simulation based on the manufacturing material information, the component connection structure characteristics and the temperature rise monitoring sequence to generate an expansion and deformation feature sequence; predict the oil leakage probability of the sealing ring component based on the expansion and deformation feature sequence to generate a source device failure probability; generate the sealing node fault detection result according to the source device failure probability.

[0043] Furthermore, the present application also includes the following steps:

[0044] Digital modeling is performed based on the component connection structural characteristics to obtain a component connection grid model; temperature-thermal expansion coefficient relationship fitting is performed based on the manufacturing material information to generate a temperature-thermal expansion relationship function; the temperature-thermal expansion relationship function is imported into the component connection grid model, a thermal expansion test is performed on the temperature rise monitoring sequence, and the expansion deformation feature sequence is generated.

[0045] Furthermore, the present application also includes the following steps:

[0046] Based on the expansion deformation feature sequence and the component connection structure features, gap fitting between components is performed to generate expansion gap features; the expansion gap features are input into a leakage failure probability predictor, and the leakage probability predictor calls a leakage feature sample library for sample matching to generate an oil leakage probability; wherein the leakage feature sample library includes multiple groups of probability mapping samples, and any group of probability mapping samples includes expansion gap feature samples and leakage probability samples; based on the oil leakage probability, a source device heat transfer influence analysis is performed to generate the source device failure probability.

[0047] Specifically, obtaining the manufacturing material information and component connection structure characteristics of the sealing ring component is the basis for material expansion and deformation simulation and oil leakage probability prediction. Manufacturing material information includes information such as the material type and composition of the sealing ring, which needs to be obtained in combination with actual conditions. Component connection structure characteristics refer to the size, shape, and connection information of the sealing ring with other components, which can be obtained through design drawings or actual measurements. Furthermore, material expansion and deformation simulation based on manufacturing material information, component connection structure characteristics, and temperature rise monitoring sequence is to use computer simulation technology to predict the expansion and deformation of the sealing ring under temperature rise conditions. The specific simulation process is as follows:

[0048] Digital modeling based on the structural features of component connection is to use computer-aided design software or modeling tools in existing technologies to create a virtual model of the sealing ring component. The established model is a three-dimensional model that can accurately reflect the geometric shape and size of the sealing ring. On the basis of digital modeling, the model is discretized into a mesh model using existing finite element analysis software to generate a component connection mesh model. The component connection mesh model is composed of many small elements (such as triangles, quadrilaterals or hexahedrons). These elements can be calculated independently during the simulation process, thereby being able to more accurately simulate the thermal expansion behavior of the component.

[0049] Fitting the temperature-thermal expansion coefficient relationship based on the manufacturing material information is to use the manufacturing material information to determine how the thermal expansion coefficient of the material changes with temperature. Specifically, the thermal expansion coefficient records of the same material at different temperatures can be collected based on the manufacturing material information. For example, a thermal expansion meter is used to measure the length change of the material at different temperatures, and then the thermal expansion coefficient at different temperatures is calculated by existing technology, that is, the rate of change of the material length with temperature, and then the relationship between temperature and thermal expansion coefficient is found. For example, the relationship between temperature and thermal expansion coefficient is determined by existing linear regression, polynomial fitting and other methods, and a linear or nonlinear relationship curve is obtained as a temperature-thermal expansion relationship function.

[0050] Importing the temperature-thermal expansion relationship function into the component connection grid model means setting the material properties in the component connection grid model so that the model can simulate the expansion behavior of the material according to temperature changes. Then, thermal expansion testing is performed on the temperature rise monitoring sequence, which means simulating the thermal expansion behavior of the sealing ring component under temperature rise in the component connection grid model. In other words, by applying a temperature load to the component connection grid model and observing the response of the model, such as dimensional changes, an expansion deformation feature sequence can be generated, that is, the dimensional change data of the sealing ring component at different temperatures, thereby realizing the prediction of the thermal expansion behavior of the sealing ring component under actual working conditions, providing support for the prediction of the probability of oil leakage, facilitating the timely detection of sealing failures of source devices, preventing device damage, and improving the accuracy of fault warning.

[0051] Furthermore, the oil leakage probability prediction of the sealing ring component based on the expansion deformation feature sequence is to use the simulated expansion deformation data to evaluate the possibility of oil leakage in the sealing ring. For example, it is analyzed whether the deformation of the sealing ring will cause the gap of the sealing surface to increase, thereby increasing the risk of oil leakage. According to the prediction results of the oil leakage probability, the specific analysis process of evaluating the probability of failure of the source device is as follows:

[0052] Fitting the gap between components based on the expansion deformation feature sequence and component connection structure features is to analyze the change in the gap between the sealing ring component and other components when the sealing ring component expands and deforms. The component connection structure features contain the connection information between the sealing component and other components, thereby obtaining the original gap size and shape between it and other components, and then combining the expansion deformation feature sequence to analyze the shape change characteristics of the sealing component when it expands and deforms, identify the changes to the original gap after deformation, and generate the final gap size, position, etc. as the expansion gap feature.

[0053] The expansion gap feature is input into the leakage fault probability predictor, and the leakage probability predictor calls the leakage feature sample library for sample matching to generate the oil leakage probability. The leakage feature sample library is a data set containing multiple groups of probability mapping samples, and the multiple groups of probability mapping samples are historical data, where each group of probability mapping samples includes an expansion gap feature sample and a corresponding leakage probability sample. The expansion gap feature and the expansion gap feature sample are compared for similarity, and the leakage probability sample corresponding to the sample with the greatest similarity is obtained as the oil leakage probability.

[0054] Finally, the influence of heat transfer of source devices is analyzed based on the probability of oil leakage, that is, the influence of oil leakage on the heat transfer of source devices is evaluated. Oil leakage may change the temperature transfer inside the radiation source body, so that the temperature cannot be transferred outward, causing the internal devices to run at high temperatures until they burn out. This usually requires the use of a thermodynamic model to analyze the influence of oil leakage on heat transfer. The probability of failure of source devices based on the probability of oil leakage and the influence of heat transfer can be analyzed through a risk assessment model. For example, professional and technical personnel in this field can collect multiple oil leakage probability samples and corresponding multiple device failure probability samples, establish a mapping model of oil leakage probability and device failure probability, input the oil leakage probability into the mapping model for matching mapping, output the source device failure probability, and generate a sealing node failure detection result based on the source device failure probability, so as to provide data support for the maintenance and fault prevention of the X-ray machine, realize targeted detection of sealing components, and ensure the safe operation of the X-ray machine.

[0055] Further, step 4 of this application includes:

[0056] The irradiation path and the preset path are checked for consistency to generate a consistency index; if the consistency index is less than the preset consistency index, the collimator is marked as faulty to generate the collimator node fault detection result.

[0057] Specifically, the irradiation path of the ray beam refers to the propagation path of the ray beam after it is emitted from the ray source and collimated by the collimator. The preset path refers to the path that the ray beam should follow under normal circumstances. The actual irradiation path data is compared with the preset path data to detect the degree of deviation between the two. This can be done by calculating the distance, angle difference or other appropriate measurement methods between the two. The consistency index can be obtained by subtracting the degree of deviation from 1. The consistency index is a quantitative index that reflects the degree of conformity between the monitored irradiation path and the preset path. If there is a significant deviation between the monitored irradiation path and the preset path, the consistency index is less than the preset consistency index, indicating that there is a fault in the collimator, such as damage to the internal structure of the collimator, displacement of the collimator position, etc., thereby judging whether there is a fault. Among them, the preset consistency index is a threshold set in advance by professional and technical personnel in this field, which is used to judge whether the deviation between the irradiation path and the preset path is within an acceptable range; if the consistency index is less than the preset consistency index, it is considered that there is a large deviation.

[0058] When the consistency index is greater than or equal to the preset consistency index, the collimator needs to be marked as faulty, indicating that the collimator is faulty, so as to generate the collimator node fault detection result, realize the fault detection of the collimator node, and ensure the imaging quality and safety of the X-ray machine.

[0059] Further, step five of this application includes:

[0060] The fault persistence characteristics of the explicit fault monitoring node, the radiation source body sealing node and the collimator node are mined to generate node persistence characteristics; node persistence response loss level mapping is performed based on the node persistence characteristics to obtain the node loss level; the node response mode is configured based on the node loss level, and a fault warning response is performed on the explicit fault detection result, the sealing node fault detection result and the collimator node fault detection result.

[0061] Specifically, fault persistence feature mining refers to analyzing the loss characteristics caused by the failure of the explicit fault monitoring node, the radiation source body sealing node, and the collimator node to handle the failure in time when the failure occurs, and the failure continues to develop, such as burning out components, causing harm to users, and causing blurred imaging, that is, the severity of the continued development of the fault. Specifically, the historical fault accident records of the explicit fault monitoring node, the radiation source body sealing node, and the collimator node can be obtained, the severity of the continued fault can be extracted, and the node persistence feature can be generated.

[0062] Next, based on the node persistence characteristics, the node persistence response loss level mapping is performed, that is, the node persistence characteristics are converted into specific loss levels, so as to better understand the severity of the continuous development of faults at different nodes. The loss level can be a quantitative indicator that reflects the severity of the fault. It can be divided by professional and technical personnel in this field according to the node persistence characteristics, that is, the more serious the fault, the higher the corresponding node loss level. Based on the node loss level, the node response mode is configured, that is, the corresponding response strategy is set for each node according to the severity of the fault. For example, for minor faults, early warning and monitoring strategies can be adopted; for serious faults, it may be necessary to stop treatment immediately and perform repairs.

[0063] Finally, according to the configured node response mode, fault warning responses are performed for the explicit fault detection results, the sealing node fault detection results, and the collimator node fault detection results, including sending warning information to the operator, suspending the equipment, etc. In this way, early warning responses are achieved at different nodes to ensure the safe operation of the X-ray machine.

[0064] In summary, the device fault detection and early warning method provided by the present application has the following technical effects:

[0065] Establish explicit fault monitoring nodes and implicit fault monitoring nodes of the target X-ray machine, wherein the explicit fault monitoring nodes include component nodes with surface fault characteristics, and the implicit fault monitoring nodes include radiation source body sealing nodes and collimator nodes; connect the explicit fault monitoring equipment of the explicit fault monitoring nodes, perform explicit feature monitoring and analysis, and generate explicit fault detection results; perform temperature rise monitoring of the sealing ring components of the radiation source body sealing node, perform expansion deformation and oil leakage analysis and prediction based on the temperature rise monitoring sequence, and perform source body component failure probability prediction based on the prediction results to generate sealing node fault detection results; perform radiation beam irradiation path monitoring on the collimator node, perform fault analysis based on the irradiation path and the preset path, and generate collimator node fault detection results; perform fault warning response to the target X-ray machine based on the explicit fault detection results, the sealing node fault detection results, and the collimator node fault detection results. By establishing explicit fault monitoring nodes and implicit fault monitoring nodes, targeted monitoring is performed on different components, and targeted monitoring of different components is achieved, so as to improve the accuracy of fault warning and save monitoring resources at the same time.

[0066] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting and warning faults of equipment, characterized in that: The method comprises: Establishing explicit fault monitoring nodes and implicit fault monitoring nodes of the target X-ray machine, wherein the explicit fault monitoring nodes include component nodes with surface fault characteristics, and the implicit fault monitoring nodes include radiation source body sealing nodes and collimator nodes; An explicit fault monitoring device connected to the explicit fault monitoring node performs explicit feature monitoring and analysis to generate an explicit fault detection result; Perform temperature rise monitoring of the sealing ring components of the radiation source sealing node, perform expansion deformation and oil leakage analysis and prediction based on the temperature rise monitoring sequence, perform source component failure probability prediction based on the prediction results, and generate sealing node failure detection results; Performing irradiation path monitoring of the collimator node with respect to the ray beam, performing fault analysis based on the irradiation path and the preset path, and generating a collimator node fault detection result; The target X-ray machine is subjected to a fault warning response in combination with the explicit fault detection result, the sealing node fault detection result and the collimator node fault detection result.

2. A method for detecting and warning a fault of an equipment as claimed in claim 1, characterized in that: Establish the explicit fault monitoring node of the target X-ray machine, including: Acquire the model and specification information of the target X-ray machine, perform historical fault detection collection based on the model and specification information as constraints, and generate a historical fault detection record data set; Taking the faulty components as classification constraints, dividing the historical fault detection record data set to generate multiple component detection record sets; Performing explicit detection confidence identification on a first component detection record set among the multiple component detection record sets to generate a first explicit confidence; If the first explicit confidence is greater than or equal to a preset confidence, a first component is added to the explicit fault monitoring node.

3. A method for detecting and warning a fault of an equipment as claimed in claim 2, characterized in that: Performing explicit detection confidence identification on the first component detection record set to generate a first explicit confidence includes: Any test record in the first component test record set includes an explicit test result record, an implicit feature test record, and a fault verification true value record; Comparing the explicit detection result record with the fault verification true value record, and outputting the explicit detection accuracy; Comparing the implicit feature detection record with the fault verification true value record, and outputting the implicit detection accuracy; The accuracy deviation degree between the explicit detection accuracy and the implicit detection accuracy is calculated, and feedback adjustment is performed on the explicit detection accuracy to generate the first explicit confidence.

4. A method for detecting and warning a fault of an equipment as claimed in claim 1, characterized in that: The sealing ring component temperature rise monitoring is performed on the sealing node of the radiation source body, and expansion deformation and oil leakage analysis and prediction are performed based on the temperature rise monitoring sequence. The source body component failure probability prediction is performed in combination with the prediction results to generate the sealing node failure detection results, including: Obtaining the manufacturing material information and component connection structure characteristics of the sealing ring component; Perform material expansion and deformation simulation based on the manufacturing material information, the component connection structure characteristics and the temperature rise monitoring sequence to generate an expansion and deformation feature sequence; Based on the expansion deformation feature sequence, the oil leakage probability of the sealing ring component is predicted to generate the source device failure probability; The sealed node fault detection result is generated according to the source body device failure probability.

5. A method for detecting and warning a fault of an equipment as claimed in claim 4, characterized in that: Based on the manufacturing material information, the component connection structure characteristics and the temperature rise monitoring sequence, material expansion and deformation simulation is performed to generate an expansion and deformation feature sequence, including: Perform digital modeling based on the structural features of the component connections to obtain a component connection grid model; Fitting the relationship between temperature and thermal expansion coefficient based on the manufacturing material information to generate a temperature-thermal expansion relationship function; The temperature-thermal expansion relationship function is imported into the component connection grid model, and a thermal expansion test is performed on the temperature rise monitoring sequence to generate the expansion deformation feature sequence.

6. A method for detecting and warning a fault of an equipment as claimed in claim 5, characterized in that: The oil leakage probability of the sealing ring component is predicted based on the expansion deformation feature sequence to generate the source device failure probability, including: Fitting the gap between components based on the expansion deformation feature sequence and the component connection structure features to generate expansion gap features; The expansion gap feature is input into a leakage fault probability predictor, and the leakage fault probability predictor calls a leakage feature sample library for sample matching to generate an oil leakage probability; Wherein, the leakage feature sample library includes multiple groups of probability mapping samples, and any group of probability mapping samples includes expansion gap feature samples and leakage probability samples; Based on the oil leakage probability, the heat transfer impact analysis of the source body component is performed to generate the failure probability of the source body component.

7. A method for detecting and warning a fault of an equipment as claimed in claim 1, characterized in that: Fault analysis is performed based on the irradiation path and the preset path to generate collimator node fault detection results, including: Performing consistency detection on the irradiation path and the preset path to generate a consistency index; If the consistency index is less than a preset consistency index, the collimator is marked as faulty and a collimator node fault detection result is generated.

8. A method for detecting and warning a fault of an equipment as claimed in claim 1, characterized in that: Combining the dominant fault detection result, the sealing node fault detection result and the collimator node fault detection result to perform a fault warning response on the target X-ray machine, including: Performing fault persistence feature mining on the explicit fault monitoring node, the radiation source body sealing node and the collimator node to generate node persistence features; Perform node continuous response loss level mapping based on the node continuous characteristics to obtain the node loss level; A node response mode is configured based on the node loss level, and a fault warning response is performed on the explicit fault detection result, the sealing node fault detection result and the collimator node fault detection result.