Medical accelerator system fault risk disposal method, device and equipment and storage medium
By obtaining parameter data of medical accelerator systems and equipment, using the fault risk identification model to identify potential hazards and implement disposal measures, the problem of insufficient response speed and accuracy of the interlocking system is solved, and the safety and operation efficiency of the equipment are improved.
Patent Information
- Application Number
- CN202411002878.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-12
AI Technical Summary
The existing medical accelerator interlocking system has limited response speed and accuracy, and cannot identify and deal with potential dangers in a timely manner. It is prone to misjudgment or misjudgment in complex fault scenarios, affecting the safety and use efficiency of the equipment.
By obtaining parameter data of medical accelerator system and related equipment, input it into the preset fault risk identification model for processing, determine the fault risk treatment measures, and implement corresponding measures to reduce risks.
It realizes the rapid identification and handling of potential hazards, improves the safety and operation efficiency of equipment, adapts to complex fault scenarios, and reduces misjudgment and misjudgment.
Smart Images

Figure CN118942660A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical accelerator systems, and in particular to a method, device, equipment and storage medium for handling fault risks of a medical accelerator system. Background Art
[0002] Medical accelerator is an important medical device used for radiotherapy. It can generate high-energy rays for treating tumors and other diseases. In order to ensure the safe operation of medical accelerator, it can be equipped with an interlocking system. The interlocking system of medical accelerator is a safety protection system used to monitor and control various operating parameters of the accelerator to ensure that the equipment operates within a safe range and avoid potential dangerous situations.
[0003] In the prior art, the interlocking system has the technical problem of untimely risk identification. Summary of the invention
[0004] The purpose of the present invention is to overcome the above technical deficiencies and provide a method, device, equipment and storage medium for handling fault risks of a medical accelerator system to solve the technical problem of untimely risk identification in the interlocking system in the related art.
[0005] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:
[0006] In a first aspect, the present invention provides a method for handling failure risks of a medical accelerator system, the method comprising:
[0007] Acquiring parameter data of at least one subsystem and parameter data of at least one target device in the medical accelerator system; wherein the target device is a device that assists the normal operation of the medical accelerator system;
[0008] Inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result;
[0009] Based on the fault risk identification result, determining a target fault risk disposal measure from a preset fault risk disposal library;
[0010] Execute the target failure risk handling measures.
[0011] In a second aspect, the present invention provides a device for handling failure risks of a medical accelerator system, the device comprising:
[0012] An acquisition module, which is used to acquire parameter data of at least one subsystem in the medical accelerator system and parameter data of at least one target device; wherein the target device is a device that assists the normal operation of the medical accelerator system;
[0013] A processing module, which is used to input the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result;
[0014] A determination module, which is used to determine a target fault risk disposal measure from a preset fault risk disposal library based on the fault risk identification result;
[0015] An execution module is used to execute the target fault risk handling measure.
[0016] The third aspect proposes an electronic device, comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the above-mentioned method.
[0017] A fourth aspect provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.
[0018] Beneficial effects:
[0019] The present invention provides a method, device, equipment and storage medium for handling fault risks of a medical accelerator system. First, parameter data of at least one subsystem and parameter data of at least one target device in a medical accelerator system are obtained; wherein the target device is a device that assists the normal operation of the medical accelerator system; then the parameter data of the at least one subsystem and the parameter data of the at least one target device are input into a preset fault risk identification model for processing to obtain a fault risk identification result; then, based on the fault risk identification result, target fault risk handling measures are determined from a preset fault risk handling library; finally, the target fault risk handling measures are executed. This method not only obtains the parameter data of the medical accelerator system itself but also obtains the parameter data related to the medical accelerator system, and determines whether there is a risk of failure in the current scenario by obtaining a variety of parameter data. This method has a fast response speed and can promptly discover and handle some potential dangers. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 is a schematic diagram of a method for handling failure risks of a medical accelerator system provided by an embodiment of the present invention;
[0021] Figure 2 is a schematic diagram of a method for handling failure risks of a medical accelerator system provided by an embodiment of the present invention;
[0022] Figure 3is a schematic diagram of a preset fault risk identification model adopted in an embodiment of the present invention;
[0023] Figure 4 is a block diagram of a medical accelerator system failure risk management device used in an embodiment of the present invention;
[0024] Figure 5 is a block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0026] Overview:
[0027] In the related technology, medical accelerator is an important medical device, which is widely used in the fields of tumor treatment. Medical accelerators produce high-energy particle beams, such as electron beams, proton beams or X-rays, to accurately irradiate tumors, thereby achieving therapeutic effects. However, due to the complexity and high energy output of medical accelerators, there are certain safety hazards in their operation. Therefore, it is crucial to establish an intelligent interlocking system to monitor and control the operating status of the accelerator in real time to ensure the safety of patients and equipment.
[0028] In some technical solutions, the medical accelerator interlocking system is mainly implemented through hardware circuits and software programs. The hardware circuit is mainly responsible for monitoring various physical parameters, such as voltage, current, temperature, etc. When these parameters exceed the preset range, the hardware circuit will immediately cut off the power supply of the accelerator to prevent equipment damage or accidents. The software program is responsible for monitoring the working status of the equipment. Once an abnormal situation is detected, it will immediately trigger the interlocking and stop the accelerator. Although the existing interlocking system guarantees the safe operation of medical accelerators to a certain extent, there are still some problems and shortcomings. Specifically, first of all, most of the existing interlocking systems are based on hardware circuits, and their reaction speed and accuracy are limited, and they may not be able to detect and deal with some potential dangers in time. In other words, in these solutions, risks can only be identified by relying on limited parameters. This mechanized approach may cause some risks to not be immediately identified or to be identified slowly. In many cases, there is often a risk abnormality stage in the normal operation stage to the failure stage of the medical accelerator. This risk abnormality stage means that although the medical accelerator has not failed, the corresponding operating parameter data has some abnormalities. These abnormalities indicate that failures may occur later. However, for this situation, the existing interlocking system based on hardware circuits cannot respond in time, and often only handles it after the failure occurs. It is understandable that rapid response capability is the primary condition to ensure the safety of patients and equipment. Once the interlocking system can respond quickly, measures can be taken immediately, such as cutting off power supply, stopping treatment, etc., to minimize risks. Secondly, the existing interlocking system can often only respond to a single fault, and for complex fault scenarios, misjudgment or missed judgment may occur. In addition, when handling faults, the existing interlocking system may affect the normal operation of other equipment, reducing the efficiency of equipment use.
[0029] In summary, the present invention provides a method, device, equipment and storage medium for handling fault risks of a medical accelerator system. First, parameter data of at least one subsystem and parameter data of at least one target device in a medical accelerator system are obtained; wherein the target device is a device that assists the normal operation of the medical accelerator system; then the parameter data of the at least one subsystem and the parameter data of the at least one target device are input into a preset fault risk identification model for processing to obtain a fault risk identification result; then, based on the fault risk identification result, target fault risk handling measures are determined from a preset fault risk handling library; finally, the target fault risk handling measures are executed. This method not only obtains the parameter data of the medical accelerator system itself but also obtains the parameter data related to the medical accelerator system, and determines whether there is a risk of failure in the current scenario by obtaining a variety of parameter data. This method has a fast response speed and can promptly discover and handle some potential dangers.
[0030] According to an embodiment of the present invention, a method for handling the risk of failure of a medical accelerator system is provided, and the method can be applied to an interlocking system. Figures 1 to 5 .
[0031] Specific as Figure 1 As shown, the method includes:
[0032] Step S102: Acquire parameter data of at least one subsystem and parameter data of at least one target device in the medical accelerator system; wherein the target device is a device that assists the normal operation of the medical accelerator system.
[0033] In this embodiment, the acquisition action can be represented by configuring sensors on the subsystem in the medical accelerator system and the target device, and then acquiring the parameter data through the sensor. The medical accelerator system subsystem may include: an accelerator subsystem, a water cooling system, an ionization chamber, an air-filled waveguide system, and a titanium pump power supply. Specifically, the accelerator subsystem is the core component in the medical accelerator system, and mainly plays the role of generating a high-energy radiation beam. The accelerator subsystem focuses and accelerates charged particles (such as electrons or protons), and then guides them to the target site in the patient's body, thereby achieving the purpose of tumor killing. The water cooling system is used to cool the heat generated in the accelerator and maintain the stable operating temperature of the system. The ionization chamber is used to measure the dose and energy of the radiation beam generated by the accelerator. The ionization chamber helps doctors adjust the radiotherapy plan by measuring the dose distribution of the radiation beam in the patient's body to ensure the accuracy and safety of radiotherapy. The air-filled waveguide system is used to transmit microwaves. The titanium pump power supply is used to provide power to the titanium pump in the accelerator system to ensure the normal operation of the titanium pump, and the titanium pump is used to ensure and monitor the vacuum state of the accelerator subsystem.
[0034] The target device may include: a high-voltage power supply system, a sensor system or a treatment room shielding door. The high-voltage power supply system is used to provide the required high-voltage energy for the accelerator subsystem, the sensor system is used to monitor and control the operating status of the medical accelerator system, and the treatment room shielding door is used to ensure radiation safety during radiotherapy.
[0035] In this embodiment, parameter data of the accelerator subsystem, the water cooling system, the ionization chamber, the gas-filled waveguide system, the high-voltage power supply system, the sensor system, or the treatment room shielding door can be obtained in real time, or according to a preset time frequency. For example, the parameter data can be obtained in real time or every 5 seconds.
[0036] In this embodiment, for the accelerator subsystem, its parameter data may be the accelerator energy value, the radiation beam position, the radiation beam intensity, etc. For the water cooling system, its parameter data may be the temperature of the water in the water cooling system, the pressure of the water in the water cooling system, and the flow rate or flow of the water in the water cooling system. For the ionization chamber, its parameter data may be the air pressure in the ionization chamber, the humidity level in the ionization chamber, and the temperature in the ionization chamber. For the inflatable waveguide system, its parameter data may be the air pressure in the inflatable waveguide system and the temperature in the inflatable waveguide system. For the high-voltage power supply system, its parameter data may be the voltage value and current value output by the high-voltage power supply system. For the sensor system, its parameter data may be the working status and operation status of each sensor. For the treatment room shielding door, its parameter data may be the open and closed status of the treatment room shielding door.
[0037] In a specific embodiment, a water temperature sensor can be installed in the water circuit or water tank of the water cooling system to monitor the temperature change of the water in real time, and a water pressure sensor can also be installed on the water cooling system pipeline to monitor the water pressure. An air pressure sensor can be installed in the ionization chamber to monitor the air pressure in the ionization chamber. The air pressure sensor can be a pressure sensor or a barometer and other equipment, which is used to monitor the air pressure change in the ionization chamber in real time. The data obtained by the air pressure sensor can be used to adjust the parameters of the ionization chamber and ensure the accuracy and stability of the radiation beam.
[0038] Step S104: inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result.
[0039] In this embodiment, the preset fault risk identification model can be a machine learning model. Specifically, if it is a machine model, a support vector machine (SVM) model, a decision tree model or a random forest model can be used. The fault risk identification model can be pre-trained. Specifically, first, parameter data from each subsystem and target device of the medical accelerator system can be collected, including data under normal operating conditions and fault conditions. Then, the collected data is preprocessed, for example, data cleaning, feature extraction and other operations can be performed to ensure the accuracy and availability of the data. Then, according to the characteristics of the data and the fault risk level, the data is marked or labeled, and the data is divided into different categories or fault risk levels to provide supervision labels for the training of the model. Finally, the marked training data is used to train the model through a machine learning algorithm so that it can learn from the data and establish patterns and laws for fault risk identification. It can be understood that the machine learning algorithm can be a support vector machine (SVM) algorithm, a decision tree algorithm or a random forest algorithm.
[0040] In this embodiment, the preset fault risk identification model may also be a deep learning model. For example, a convolutional neural network (CNN), a recurrent neural network (RNN) or a long short-term memory network (LSTM) may be used. When the preset fault risk identification model adopts a deep learning model, the preset fault risk identification model may also be pre-trained. It is understandable that training data may also be pre-constructed, and then the selected deep learning model may be trained using the training data. After the training is completed, the preset fault risk identification model may be obtained. In some embodiments, a test set may also be pre-constructed. After the deep learning model is trained, the trained deep learning model may be tested using the test set. Only when the test passes, the deep learning model may be output as a preset fault risk identification model. It is understandable that if the test fails, the deep learning model may be trained again using the training data until it can pass the test. It is also understandable that the completion of the training of the above-mentioned deep learning model may refer to the convergence of the loss function.
[0041] In a specific implementation scheme, first, a convolutional neural network (CNN) can be used to automatically extract spatiotemporal features from the parameter data of at least one subsystem and the parameter data of at least one target device, and a recurrent neural network (RNN) can be used to capture the change pattern of the parameters over time, thereby obtaining rich feature data. Then, an attention mechanism is used to weightedly fuse the features extracted from different subsystems and target devices to enhance the focus on key risk factors. Finally, an ensemble learning strategy is used to combine multiple machine learning algorithms (such as support vector machine SVM, random forest RF) for comprehensive risk assessment, and finally determine the fault risk identification result to ensure the accuracy and robustness of the identification.
[0042] In this embodiment, the fault risk identification result may include a fault risk identification level. For example, fault risk level one may be indicated as the absence of any fault risk, and fault risk levels two to five may be indicated as fault risks increasing in sequence. Accordingly, for each fault risk level above level two, it may also be subdivided into specific fault risk types. For example, the risk of excessive water temperature in the water cooling system is indicated as the risk that the cooling water temperature in the water cooling system exceeds the safe or normal operating range, which may lead to a fault. It is understandable that the higher the value of the cooling water temperature in the water cooling system exceeding the safe or normal operating range, the higher the probability of a fault, and the higher the risk. Therefore, for each fault risk level above level two, there may be a risk of excessive water temperature in the water cooling system, but the risk level indicated is different.
[0043] In some embodiments, the fault risk identification level and the specific fault risk type in each fault risk identification level can be flexibly set. Specifically, a certain type of fault risk may be involved in fault risk levels of level two and above, for example, the risk type of excessive water temperature in a water cooling system. It may also be that a certain type of fault risk only appears in high-level fault risk identification levels, and this fault risk type does not appear in low-level fault risk identification levels. For example, the risk type of abnormal water pressure in a water cooling system. It is understandable that this type of fault risk may cause serious adverse consequences, and therefore, it may appear in high-level fault risk identification levels, but not in low-level fault risk identification levels.
[0044] In a specific embodiment, the fault risk identification result may include a fault risk identification level. In addition to other fault risk identification levels indicating no fault risk, the fault risk identification level may include at least one fault risk type. Specifically, the fault risk type may include:
[0045] (1) Risk type of excessive water temperature in the water cooling system: The cooling water temperature in the water cooling system exceeds the safe or normal operating range but does not reach the critical value for failure.
[0046] (2) Risk type of low water temperature in the water cooling system: The cooling water temperature in the water cooling system is lower than the set minimum value, which may affect the normal operation of the system, but is not lower than the fault critical value.
[0047] (3) Risk type of excessive air pressure in the ionization chamber or air-filled waveguide system: The air pressure in the ionization chamber or air-filled waveguide system exceeds the normal operating range but does not reach the critical value for failure.
[0048] (4) Risk type of low air pressure in the ionization chamber or air-filled waveguide system: The air pressure in the ionization chamber or air-filled waveguide system is lower than the normal operating range, but not lower than the fault critical value.
[0049] (5) Risk type of abnormal water pressure in the water cooling system: The water pressure in the water cooling system is too high or too low, but not lower than the fault critical value or higher than the fault critical value.
[0050] Step S106: Based on the fault risk identification result, determine a target fault risk handling measure from a preset fault risk handling library.
[0051] In this embodiment, the fault risk disposal library may be provided with a plurality of fault risk disposal measures, and the fault risk disposal measures may correspond to at least one fault risk identification result. Specifically, the fault risk disposal library may be provided with the following fault risk disposal measures, for example, it may be an early warning measure or a notification measure, and for situations where the fault risk level is low, the relevant personnel may be reminded by early warning or notification so that corresponding measures can be taken in time. It may also be a measure for automatically adjusting parameters, a measure for automatic fault diagnosis and repair, a measure for automatic shutdown, and so on.
[0052] In a possible scenario example, the fault risk identification result can be expressed as a risk type of excessive water temperature in the water cooling system. Accordingly, the fault risk disposal measures configured in the fault risk disposal library can be early warning measures or notification measures. In this case, a signal can be sent to the early warning device so that the early warning device issues an early warning to remind the corresponding personnel. The early warning device can be set in the medical room or not. Specifically, the early warning device can be a flashing early warning light, or other forms of early warning devices, etc. In this scenario example, it is also possible to directly generate early warning information, which can be sent to at least one display device on site to prompt the corresponding personnel to deal with the risk. For example, a display screen can be set inside the medical room to display early warning information, and the early warning information can be "Please check whether the cooling water circulation of the water cooling system is normal and eliminate possible blockages or leakage problems."
[0053] Step S108: Execute the target fault risk handling measures.
[0054] In this embodiment, the target fault risk treatment measure may be a warning measure or a notification measure, or an automatic parameter adjustment measure, an automatic fault diagnosis and repair measure, or an automatic shutdown measure, etc.
[0055] In a specific implementation scheme, when the fault risk identification result indicates that the fault risk identification level is very high, an immediate instruction can be sent to the system's built-in early warning module to trigger the early warning module to perform multi-channel early warning operations, including but not limited to starting sound and light alarms, pushing warning messages to the operation interface, and sending emergency fault warning signals to the remote monitoring center through the network interface.
[0056] When the fault risk identification result indicates a low fault risk identification level, an early warning message containing risk details and recommended preventive measures can be sent to a designated target account, such as the maintenance team's communication platform, to ensure that relevant maintenance personnel can receive the early warning in a timely manner and take pre-emptive intervention measures to prevent the actual occurrence of the fault.
[0057] At the same time, according to the level and nature of the fault risk identification level, the corresponding preset protection measures can be automatically or manually selected and activated, such as adjusting system operating parameters, starting backup equipment or implementing a temporary operating mode to maintain the continuous and stable operation of the medical accelerator system until the fault risk is eliminated or properly handled.
[0058] In this embodiment, on the one hand, not only the parameter data of the medical accelerator system itself but also the parameter data related to the medical accelerator system are obtained. By obtaining a variety of parameter data to determine whether there is a risk of failure in the current scenario, various parameter data in the use scenario can be more comprehensively monitored, and then the fault risk identification is performed based on the comprehensive parameter data. Compared with the mechanical identification of faults based on hardware circuits in the prior art, the method provided by this embodiment can identify the risk that may cause the failure before the failure occurs, and then determine the target fault risk disposal measures based on the preset fault risk disposal library, and then execute the target fault risk disposal measures to eliminate the risk that may cause the failure. Therefore, the method provided by this embodiment has a fast response speed, can timely discover and deal with some potential dangers, avoids the problem of limited response speed and accuracy of hardware circuits in the prior art, and improves the operating efficiency of the equipment. On the other hand, as mentioned above, this embodiment is based on comprehensive parameter data to identify fault risks, can adapt to complex fault scenarios, and reduce the occurrence of misjudgment or missed judgment. Specifically, this embodiment can comprehensively monitor the water temperature and water pressure in the water cooling system of the medical linear accelerator, the air pressure around the ionization chamber, the air pressure in the air-filled waveguide system, the current of the titanium pump power supply, the switch of the shielding lead door of the treatment room, and the faults of each subsystem, thereby realizing all-round monitoring of the accelerator's operating status, improving the safety of the equipment, and being able to determine corresponding risk measures based on the fault risk identification results, thus avoiding the defect of the prior art that only a single fault can be responded to.
[0059] In some embodiments, in the method described above, the target device includes: a high-voltage power supply system, a sensor system, or a treatment room shielding door. In this embodiment, limiting the target device to a high-voltage power supply system, a sensor system, or a treatment room shielding door helps focus on the part that has the greatest impact on system safety and stability. This can more effectively manage and control failure risks and improve system reliability and safety.
[0060] In some embodiments, before the step of inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result, the method further includes: inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a fault identification rule base for identification to obtain a fault identification result; and when the fault identification result indicates that a fault has occurred, executing preset fault handling measures based on the fault identification result.
[0061] In this embodiment, the fault identification rule base may be a fault identification rule base established based on historical fault cases and expert experience. The fault identification rule base performs preliminary pattern matching and logical judgment on the parameter data of the at least one subsystem and the parameter data of the at least one target device to obtain a fault identification result.
[0062] The fault identification result may include whether a fault has not occurred or whether a fault has occurred. Specifically, when the fault identification result indicates that a fault has occurred, the fault identification result may also include a specific fault type. The specific fault type may include:
[0063] (1) Fault of excessive water temperature in the water cooling system: The cooling water temperature in the water cooling system exceeds the safe or normal operating range and exceeds the fault critical value.
[0064] (2) Fault of low water temperature in the water cooling system: The cooling water temperature in the water cooling system is lower than the set minimum value and lower than the fault critical value.
[0065] (3) Fault of excessive air pressure in the ionization chamber or air-filled waveguide system: The air pressure in the ionization chamber or air-filled waveguide system exceeds the normal operating range and exceeds the fault critical value.
[0066] (4) Fault of too low air pressure in the ionization chamber or air-filled waveguide system: The air pressure in the ionization chamber or air-filled waveguide system is lower than the normal operating range and lower than the fault critical value.
[0067] (5) Abnormal water pressure in the water cooling system: The water pressure in the water cooling system is too high or too low, and is lower than the critical value or higher than the critical value.
[0068] (6) Failure due to abnormal current: The titanium pump power supply may indicate an abnormal vacuum state, or abnormal current readings of other key components may indicate electronic problems or component failures.
[0069] (7) Failure of shielding lead door not closing: The shielding lead door of the treatment room is not closed properly, which may cause radiation leakage.
[0070] (8) System leakage failure: Current leakage may be dangerous to patients and operators.
[0071] (9) System overheating failure: Overheating of certain components may indicate poor heat dissipation or equipment overload.
[0072] (10) Sensor failure: The sensor fails and cannot accurately transmit data.
[0073] (11) Communication failure: Communication interruption or failure within the medical accelerator system or between the system and the interlocking system.
[0074] (12) Software failure: software crashes or logical errors occur.
[0075] (13) Mechanical failure: abnormal operation of mechanical parts such as pumps and valves.
[0076] (14) Abnormal radiation dose failure: An abnormal dose rate is detected.
[0077] In this implementation, the preset fault handling measure may be automatic shutdown or automatic isolation, that is, isolating the faulty device from other normally operating devices.
[0078] In the above-mentioned implementation, on the one hand, by first processing the fault identification rule base, it is possible to quickly identify obvious faults that have occurred, avoiding the waste of time and resources in inputting these fault data into the fault risk identification model for processing. This can improve the efficiency of the entire fault risk identification process. On the other hand, the fault identification rule base can contain a series of identification rules for known faults. By inputting parameter data into the fault identification rule base for identification, it is possible to quickly and accurately identify obvious faults that have occurred, avoiding the situation where these faults are misjudged as risks. Moreover, when the fault identification result indicates that a fault has occurred, the preset fault handling measures can be immediately executed. The fault handling measures include but are not limited to cutting off the power supply of the faulty device, starting the backup system or isolating the faulty area to prevent the fault from spreading and ensure the normal operation of the rest of the system. In this way, the faults that have occurred can be handled in a timely manner, reducing the impact on the system, and ensuring the normal operation of the equipment and the safety of the users.
[0079] In some embodiments, when the fault identification result indicates that no fault has occurred, the parameter data of the at least one subsystem and the parameter data of the at least one target device are input into a preset fault risk identification model for processing to obtain a fault risk identification result.
[0080] In this implementation, when the fault identification result indicates that no fault has occurred, the parameter data of the at least one subsystem and the parameter data of the at least one target device are input into a preset fault risk identification model for processing. The preset fault risk identification model can perform multi-level feature extraction, feature fusion and risk assessment to assess potential fault risks in a more sophisticated manner, thereby obtaining a more accurate fault risk identification result.
[0081] In the implementation method, when the fault identification result indicates that no fault has occurred, the parameter data is input into a preset fault risk identification model for processing to obtain a fault risk identification result. In this way, potential fault risks can be identified. Even if the parameter data reflects that there is no fault in the current system, further identification is required to determine whether there is a risk of causing a fault in the current system, so that corresponding preventive measures can be taken in advance to avoid the occurrence of the fault. In this way, efficiency can be improved, faults can be accurately identified, and risks can be identified, thereby ensuring the normal operation of the equipment and the safety of users.
[0082] In some embodiments, electromagnetic relays are configured in the subsystems of the medical accelerator system and the target device, and the electromagnetic relays are used to isolate the faulty subsystems and target devices from the normally operating subsystems and target devices. The step of executing preset fault handling measures based on the fault identification result includes: determining the faulty device based on the fault identification result; and sending a first start signal to the electromagnetic relay of the faulty device so that the electromagnetic relay of the faulty device starts.
[0083] In this embodiment, the first start signal can be a signal that can be understood to start the electromagnetic relays in each subsystem and each target device. In this embodiment, electromagnetic relays can be configured in advance for each subsystem and each target device of the medical accelerator system, and the faulty device can be automatically isolated from other normal devices when handling a fault. For example, when the current of the titanium pump power supply exceeds the set threshold, the system will automatically isolate the titanium pump from other devices to protect the normal operation of other devices.
[0084] In this implementation, on the one hand, by sending a first start signal to the electromagnetic relay of the faulty device, the faulty device can be quickly isolated from other normal devices. This can prevent the faulty device from affecting the normal operation of other devices and ensure the stability and reliability of the system. On the other hand, by pre-configuring electromagnetic relays for each subsystem and target device, and sending a first start signal when the fault identification result indicates that a fault has occurred, automated fault handling measures can be implemented. This can reduce the need for manual intervention and improve the efficiency and accuracy of fault handling.
[0085] In some embodiments, an automatic reset circuit is configured in the subsystem of the medical accelerator system and the target device, and the automatic reset circuit is used to automatically restore the corresponding device to a normal state after the fault of the faulty device is processed. The method also includes: when it is determined that the fault of the faulty device has been eliminated, sending a second start signal to trigger the automatic reset circuit so that the corresponding device is restored to a normal state.
[0086] In this embodiment, the second start signal may be a signal that can trigger the automatic reset circuit in each subsystem and each target device. In this embodiment, the automatic reset circuit may be configured in advance for each subsystem and each target device of the medical accelerator system, and the device may be automatically restored to a normal state after the fault is handled. For example, when the switch of the shielding lead door of the treatment room fails, the system will automatically restore the lead door to a normal state to ensure the continuous operation of the device.
[0087] In this embodiment, by configuring an automatic reset circuit and sending a second start signal after the fault is handled, automatic recovery of the device can be achieved, which can reduce the need for manual intervention and improve the availability and continuity of the device.
[0088] In some embodiments, the step of executing the target fault risk handling measures includes: sending a third start signal to the early warning device so that the early warning device performs an early warning operation; or, sending an early warning message to the target account to prompt the target person.
[0089] In this embodiment, the third start signal is a signal that can start the early warning device. The third start signal can be sent to the early warning device, so that the early warning device warns to remind the corresponding personnel. The early warning device can be set in the medical room or not. Specifically, the early warning device can be a flashing early warning light, or other forms of early warning devices, etc. The target account can be understood as the account of the target person, and the account can be logged in on one or more smart terminals, for example, a smart phone. Once the smart phone receives the early warning information, the target person can quickly view it to eliminate the risk.
[0090] In this embodiment, by sending the third start signal to the early warning device and sending the early warning information to the target account, the target person can be warned in time and quickly notified, thereby improving the reaction speed and reducing risks and losses. This can ensure the safety of equipment and personnel and improve work efficiency and quality.
[0091] In some embodiments, the step of inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result is specifically as follows: Figure 2 As shown, it may include:
[0092] Step S1042: extracting features from the parameter data of the at least one subsystem and the parameter data of the at least one target device to obtain corresponding feature data.
[0093] In this embodiment, the structure of the fault risk identification model can be as follows: Figure 3 As shown. A preset feature extraction network can be used to extract features from parameter data of at least one subsystem and parameter data of at least one target device, respectively, so as to extract useful feature data. The feature extraction network can include multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layer is used to extract local features, the pooling layer is used to reduce feature dimensions and extract higher-level features, and the fully connected layer is used to map the extracted features to the final feature representation space. For example, deep learning network models such as convolutional neural networks (CNN) or recurrent neural networks (RNN) can be used to extract feature data.
[0094] Step S1044: performing a fusion operation on the obtained feature data to obtain fused feature data.
[0095] In this embodiment, a feature fusion network can be used to perform a fusion operation on the obtained feature data to obtain fused feature data. The feature fusion network can be used to fuse feature data of different subsystems and target devices to obtain a more comprehensive and integrated feature representation. The feature fusion network can use a multi-layer perceptron (MLP) network.
[0096] Step S1046: Based on the fused feature data, fault risk identification is performed to obtain a fault risk identification result.
[0097] In this embodiment, the fused feature data can be input into a fault risk identification network for identification, thereby obtaining a fault risk identification result. The fault risk identification network can use a convolutional neural network (CNN) or a long short-term memory network (LSTM).
[0098] In this implementation, on the one hand, by extracting and fusing the features of the parameter data of the subsystems and target devices, the useful information in these data can be fully utilized to improve the accuracy and reliability of fault risk identification. On the other hand, through the feature fusion operation, the feature data of different subsystems and target devices can be fused, considering the correlation and mutual influence between them, to obtain a more comprehensive and integrated feature representation. This helps to improve the comprehensive performance of fault risk identification. Therefore, by comprehensively considering the feature data of multiple subsystems and target devices, as well as the correlation between them, a more accurate and robust fault risk identification result can be obtained. This helps to discover potential fault risks in advance, take corresponding measures for prevention and maintenance, and improve the reliability and safety of the equipment.
[0099] According to an embodiment of the present invention, a medical accelerator system failure risk management device is provided. Figure 4 As shown, the device comprises:
[0100] An acquisition module, which is used to acquire parameter data of at least one subsystem in the medical accelerator system and parameter data of at least one target device; wherein the target device is a device that assists the normal operation of the medical accelerator system;
[0101] A processing module, which is used to input the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result;
[0102] A determination module, which is used to determine a target fault risk disposal measure from a preset fault risk disposal library based on the fault risk identification result;
[0103] An execution module is used to execute the target fault risk handling measure.
[0104] According to an embodiment of the present invention, an electronic device is provided. Figure 5 The electronic device in this embodiment may include one or more of the following components: a processor, a network interface, a memory, a non-volatile memory, and one or more applications, wherein the one or more applications may be stored in the non-volatile memory and configured to be executed by one or more processors, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.
[0105] According to an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the computer executes the method described in any of the above embodiments.
[0106] According to an embodiment of the present invention, a computer program product including instructions is also provided. When the instructions are executed by a computer, the computer executes the method described in any one of the above embodiments.
[0107] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0108] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.
[0109] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0110] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.
[0111] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A method for handling the risk of failure of a medical accelerator system, characterized in that: The method comprises: Acquiring parameter data of at least one subsystem and parameter data of at least one target device in the medical accelerator system; wherein the target device is a device that assists the normal operation of the medical accelerator system; Inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result; Based on the fault risk identification result, determining a target fault risk disposal measure from a preset fault risk disposal library; Execute the target failure risk handling measures.
2. The method according to claim 1, characterized in that Before the step of inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result, the method further includes: Inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a fault identification rule library for identification, thereby obtaining a fault identification result; When the fault identification result indicates that a fault has occurred, a preset fault handling measure is executed based on the fault identification result.
3. The method according to claim 2, characterized in that When the fault identification result indicates that no fault has occurred, the parameter data of the at least one subsystem and the parameter data of the at least one target device are input into a preset fault risk identification model for processing to obtain a fault risk identification result.
4. The method according to claim 2, characterized in that: The subsystem of the medical accelerator system and the target device are provided with an electromagnetic relay, and the electromagnetic relay is used to isolate the subsystem and the target device that have a fault from the subsystem and the target device that are in normal operation, and the step of executing a preset fault handling measure based on the fault identification result includes: Based on the fault identification result, determining the faulty device; A first start signal is sent to the electromagnetic relay of the faulty device so that the electromagnetic relay of the faulty device is started.
5. The method according to claim 4, characterized in that The subsystem of the medical accelerator system and the target device are provided with an automatic reset circuit, and the automatic reset circuit is used to automatically restore the corresponding device to a normal state after the fault of the faulty device is handled, and the method further includes: When it is determined that the fault of the faulty device has been eliminated, a second start signal is sent to trigger the automatic reset circuit so that the corresponding device returns to a normal state.
6. The method according to claim 1, characterized in that The step of executing the target fault risk handling measure includes: A third start signal is sent to the early warning device, so that the early warning device performs an early warning operation; or, an early warning message is sent to the target account to prompt the target person.
7. The method according to claim 1, characterized in that The step of inputting the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result includes: Extracting features from the parameter data of the at least one subsystem and the parameter data of the at least one target device to obtain corresponding feature data; Performing a fusion operation on the obtained feature data to obtain fused feature data; Based on the fused feature data, fault risk identification is performed to obtain a fault risk identification result.
8. A medical accelerator system failure risk management device, characterized in that: The device comprises: An acquisition module, which is used to acquire parameter data of at least one subsystem in the medical accelerator system and parameter data of at least one target device; wherein the target device is a device that assists the normal operation of the medical accelerator system; A processing module, which is used to input the parameter data of the at least one subsystem and the parameter data of the at least one target device into a preset fault risk identification model for processing to obtain a fault risk identification result; A determination module, which is used to determine a target fault risk treatment measure from a preset fault risk treatment library based on the fault risk identification result; An execution module is used to execute the target fault risk handling measure.
9. An electronic device, characterized in that: include: a memory, and one or more processors communicatively coupled to the memory; The memory stores instructions that can be executed by the one or more processors. The instructions are executed by the one or more processors to enable the one or more processors to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
