Fault monitoring system and method

Abstract

The invention discloses a fault monitoring system and method, relates to the technical field of medical equipment fault monitoring, and aims to monitor the operation stability of a multi-leaf collimator. The multi-leaf collimator comprises a leaf box body, the fault monitoring system comprises a vibration sensor, a processor and a remote diagnosis system, the vibration sensor is arranged on the leaf box body, and the processor is respectively connected with the vibration sensor and the remote diagnosis system. The vibration sensor is used for collecting vibration signals of the blade box body; the processor can obtain a vibration signal collected by the vibration sensor, convert the vibration signal into corresponding waveform data and transmit the waveform data to the remote diagnosis system; and the remote diagnosis system can generate corresponding state information based on the waveform data transmitted by the processor. The fault monitoring system is used for carrying out fault monitoring on the multi-leaf collimator of the radiotherapy system so as to monitor the operation state of the multi-leaf collimator, so that stable and reliable operation of the multi-leaf collimator can be ensured, and normal implementation of a treatment plan can be ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical device fault monitoring, and particularly to a fault monitoring system and method. Background Art

[0002] Radiation therapy is a method for treating tumors, which mainly uses high-energy rays to kill or control the growth of cancer cells to achieve the treatment of tumors. Intensity-modulated radiotherapy (IMRT) is an important means of radiation therapy. The multi-leaf collimator is an important component for carrying out IMRT. It is mainly used to shield part of the rays emitted by the radiation source and adjust the shape of the radiation field formed by the rays, so that the radiation source rays can be concentrated on the target area to achieve high-precision treatment. During long-term use, the multi-leaf collimator will gradually age, resulting in a decrease in the movement accuracy of its leaves and a decrease in treatment accuracy.

[0003] At present, in order to ensure the stable and reliable operation of the multi-leaf collimator to ensure treatment accuracy, means such as daily inspection, weekly inspection, monthly inspection, annual inspection, and regular patrol inspection are usually used to monitor and maintain the multi-leaf collimator. The prior art usually monitors the movement position and movement speed of the multi-leaf collimator to judge whether there is an abnormality in the movement of each leaf of the multi-leaf collimator. However, the above means of monitoring and maintaining the multi-leaf collimator have the problem of insufficient real-time performance, resulting in poor stability of the operation of the multi-leaf collimator, unable to monitor and feedback the operation status of the multi-leaf collimator in real time, and affecting the implementation of the treatment plan. Summary of the Invention

[0004] The purpose of the present invention is to provide a fault monitoring system and method, aiming to monitor the stability of the operation of the multi-leaf collimator.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present application provides a fault monitoring system for fault monitoring of a multi-leaf collimator of a radiotherapy system. The multi-leaf collimator includes a blade box body. The fault monitoring system includes: a vibration sensor, a processor, and a remote diagnosis system. The vibration sensor is arranged on the blade box body. The processor is respectively connected to the vibration sensor and the remote diagnosis system. Among them, the vibration sensor is used to collect the vibration signal of the blade box body. The processor can obtain the vibration signal collected by the vibration sensor, convert it into corresponding waveform data, and transmit it to the remote diagnosis system. The remote diagnosis system can generate corresponding status information based on the waveform data transmitted by the processor. The status information is used to reflect the status of the multi-leaf collimator.

[0007] The fault monitoring system in this application can collect the vibration signals of the blade box in the multi-leaf collimator in real time through vibration sensors, and transmit them to the processor. After being converted by the processor into corresponding waveform data, it is transmitted to the remote diagnosis system. The remote diagnosis system can process and analyze the waveform data transmitted by the processor to generate information reflecting the state of the multi-leaf collimator. In this way, the real-time monitoring of the operating state of the multi-leaf collimator can be realized to quickly and accurately reflect the operating state of the multi-leaf collimator, ensure the stable and reliable operation of the multi-leaf collimator, and further enable unattended real-time monitoring.

[0008] In addition, users can also obtain the state of the multi-leaf collimator through the fault monitoring system before the multi-leaf collimator shows obvious aging or abnormalities. Thus, when the multi-leaf collimator has problems but can still work, the problems can be discovered in advance and the maintenance plan can be started to reduce the situation where the multi-leaf collimator cannot move, ensuring that the treatment plan can be implemented normally.

[0009] In some embodiments, the vibration signal of the blade box includes one or more of a sine wave, a sharp pulse, and a clipped wave when the blade box vibrates.

[0010] In some embodiments, the processor can obtain the vibration signal collected by the vibration sensor and convert it into corresponding waveform data, including: converting the vibration signal of the blade box into corresponding time-domain waveform data and / or frequency-domain waveform data.

[0011] In some embodiments, the remote diagnosis system includes: a remote center and a fault diagnosis module. The remote center is respectively connected to the processor and the fault diagnosis module. Among them, the remote center can receive and integrate the waveform data transmitted by the processor to obtain the target data waveform and transmit it to the fault diagnosis module. The fault diagnosis module can generate corresponding state information based on the target data waveform transmitted by the remote center.

[0012] In some embodiments, the remote diagnosis system further includes: an alarm module. The alarm module is connected to the fault diagnosis module. The alarm module can issue corresponding alarm signals based on the state information generated by the fault diagnosis module.

[0013] In a second aspect, this application provides a fault monitoring method, which is applied to the fault monitoring system in any of the above embodiments. The method includes: obtaining waveform data corresponding to the vibration signal of the blade box; converting the waveform data into a corresponding target data waveform, determining a matching template corresponding to the target data waveform, matching the target data waveform with the corresponding matching template to generate a detection result; based on the detection result, determining whether there is a fault in the multi-leaf collimator.

[0014] In some embodiments, the vibration signal of the blade housing includes one or more of a sine wave, sharp pulses, and clipped waves when the blade housing vibrates.

[0015] In some embodiments, obtaining waveform data corresponding to the vibration signal of the blade housing includes: periodically detecting whether the blades of the multi-leaf collimator are in a moving state; when the blades of the multi-leaf collimator are in a moving state, controlling a vibration sensor to collect the vibration signal of the blade housing and transmit it to a processor; and converting the vibration signal transmitted by the vibration sensor into corresponding waveform data through the processor.

[0016] In some embodiments, converting the vibration signal transmitted by the vibration sensor into corresponding waveform data through the processor includes: converting the vibration signal transmitted by the vibration sensor into corresponding time-domain waveform data and / or frequency-domain waveform data through the processor.

[0017] In some embodiments, determining a matching template corresponding to the target data waveform includes: obtaining a standard data waveform corresponding to the waveform data of the vibration signal of the blade housing; increasing the data in the standard data waveform by a tolerance value to obtain a first data waveform; decreasing the data in the standard data waveform by a tolerance value to obtain a second data waveform; and forming a matching template with the first data waveform and the second data waveform as boundaries.

[0018] In some embodiments, matching the target data waveform with the corresponding matching template to generate a detection result includes: inputting the target data waveform into the matching template to obtain the out-of-bounds frequency of the target data waveform; the out-of-bounds frequency is the percentage of the number of amplitudes of the target data waveform that exceed the boundaries of the matching template to the total number of amplitudes of the target data waveform; if the out-of-bounds frequency is less than or equal to a preset value, it is determined that the target data waveform is normal; if the out-of-bounds frequency is greater than the preset value, it is determined that the target data waveform is abnormal.

[0019] In some embodiments, based on the detection result, determining whether there is a fault in the multi-leaf collimator includes: generating corresponding status information based on the detection result; and determining whether there is a fault in the multi-leaf collimator according to the status information.

[0020] In some embodiments, after determining whether there is a fault in the multi-leaf collimator according to the status information, it further includes: when it is determined that there is a fault in the multi-leaf collimator according to the status information, determining the type of the fault of the multi-leaf collimator based on the status information and controlling an alarm module to emit a corresponding alarm signal.

[0021] The technical effects brought by any of the embodiments in the second aspect above can be referred to the technical effects brought by the corresponding embodiments in the first aspect, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 It is a schematic structural diagram of a multi-leaf collimator provided by an embodiment of the present application;

[0024] Figure 2 It is a schematic structural diagram of a fault monitoring system provided by an embodiment of the present application;

[0025] Figure 3 It is one of the schematic flowcharts of a fault monitoring method provided by an embodiment of the present application;

[0026] Figure 4 It is another schematic flowchart of a fault monitoring method provided by an embodiment of the present application;

[0027] Figure 5 It is yet another schematic flowchart of a fault monitoring method provided by an embodiment of the present application;

[0028] Figure 6 It is still another schematic flowchart of a fault monitoring method provided by an embodiment of the present application;

[0029] Figure 7 It is the fifth schematic flowchart of a fault monitoring method provided by an embodiment of the present application.

[0030] Reference numerals:

[0031] 100 - multi-leaf collimator; 1 - blade; 2 - box body; 3 - drive assembly; 31 - nut; 32 - lead screw; 33 - motor;

[0032] 200 - fault monitoring system; 10 - vibration sensor; 20 - processor; 30 - remote diagnosis system; 301 - remote center; 302 - fault diagnosis module; 303 - alarm module. Detailed implementation manners

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0034] It should be noted that in practical applications, due to the limitations of device precision or installation errors, it is difficult to achieve absolute parallel or perpendicular effects. In this application, the descriptions of "perpendicular", "parallel" or "in the same direction" are not absolute limiting conditions, but mean that a perpendicular or parallel structural setting can be achieved within a preset error range and the corresponding preset effects can be achieved. In this way, the technical effects of the limiting features can be maximally realized, and the corresponding technical solutions are easy to implement and have high feasibility. For example, "perpendicular" includes absolute perpendicular and approximate perpendicular, and the acceptable deviation range of approximate perpendicular can be, for example, within 5°. "Parallel" includes absolute parallel and approximate parallel, and the acceptable deviation range of approximate parallel can be, for example, within 5°. "In the same direction" includes absolute in the same direction and approximate in the same direction, and the acceptable deviation range of approximate in the same direction can be, for example, within 5°.

[0035] In the description of the embodiments of this application, "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0036] In the description of the embodiments of this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected to", and "communicated with" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection. It may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0037] In the description of the embodiments of this application, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, article or device. Without further limitation, an element defined by the phrase "including one..." does not exclude the existence of additional identical elements in the process, article or device including such element.

[0038] In the description of the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0039] Radiation therapy is a method of tumor treatment that mainly uses high-energy rays to kill or control the growth of cancer cells to achieve the treatment of tumors. Intensity-modulated radiotherapy (IMRT) is an important means of radiation therapy. The multi-leaf collimator is an important component for carrying out IMRT. It is mainly used to shield part of the rays emitted by the radiation source and adjust the shape of the radiation field formed by the rays, so that the radiation source rays can be concentrated on the target area to achieve high-precision treatment.

[0040] Among them, as Figure 1 shown, the multi-leaf collimator 100 may include blades 1, a blade housing 2, and a drive assembly 3. The blades 1 are movably connected to the blade housing 2, and the drive assembly 3 can drive the blades 1 to move relative to the blade housing 2, thereby enveloping and forming a complex radiation field to make the shape of the radiation field match the shape of the tumor.

[0041] Exemplarily, the drive assembly 3 includes a nut 31, a screw 32, and a motor 33. The nut 31 is screwed with the screw 32. The nut 31 is connected to the blade 1, and the motor 33 is connected to the screw 32. It should be noted that the motor 33 can drive the screw 32 to rotate, thereby driving the nut 31 to move along the axial direction of the screw 32, and further driving the blade 1 to move relative to the blade housing 2 along the axial direction of the screw 32 to achieve the adjustment of the shape of the radiation field.

[0042] It can be understood that during long-term use, the multi-leaf collimator 100 will gradually age, resulting in a decrease in the movement accuracy of its blades 1, leading to a decrease in treatment accuracy, and even a slight error may have an inestimable impact on the treatment effect.

[0043] Currently, in order to ensure that the multi-leaf collimator 100 can operate stably and reliably to ensure treatment accuracy, means such as daily inspection, weekly inspection, monthly inspection, annual inspection, and regular patrol inspection are usually used to monitor and maintain the multi-leaf collimator 100. The prior art usually monitors the movement position and movement speed of the multi-leaf collimator 100 to determine whether there is any abnormality in the movement of each blade 1 of the multi-leaf collimator 100. However, the above means for monitoring and maintaining the multi-leaf collimator 100 have the problem of insufficient real-time performance, resulting in poor stability of the operation of the multi-leaf collimator 100, and it is unable to monitor and feedback the operation state of the multi-leaf collimator 100 in real time, affecting the normal implementation of the treatment plan.

[0044] Based on this, the present application provides a fault monitoring system and method for fault monitoring of the multi-leaf collimator 100 of a radiotherapy system to ensure that the multi-leaf collimator 100 can operate stably and reliably and guarantee the normal implementation of a treatment plan.

[0045] As Figure 1 and Figure 2 shown, the fault monitoring system 200 in the embodiment of the present application includes a vibration sensor 10, a processor 20, and a remote diagnosis system 30. The vibration sensor 10 is disposed on the blade housing 2, and the processor 20 is respectively connected to the vibration sensor 10 and the remote diagnosis system 30.

[0046] Among them, the vibration sensor 10 is used to collect the vibration signal of the blade housing 2; the processor 20 can obtain the vibration signal collected by the vibration sensor 10, convert it into corresponding waveform data, and transmit it to the remote diagnosis system 30; the remote diagnosis system 30 can generate corresponding status information based on the waveform data transmitted by the processor 20, and the status information is used to reflect the status of the multi-leaf collimator 100.

[0047] Exemplarily, the vibration signal of the blade housing 2 includes one or more of a sine wave, a sharp pulse, and a clipped wave when the blade housing 2 vibrates.

[0048] It should be noted that the sine wave is a regular vibration signal generated when the multi-leaf collimator 100 operates normally. By monitoring the sine wave, it can be identified whether the multi-leaf collimator 100 deviates from the normal working state. For example, when it is monitored that the frequency or amplitude of the sine wave has changed significantly, it can be preliminarily determined that there may be problems such as wear, imbalance, and looseness of the moving parts in the multi-leaf collimator 100. The sharp pulse is a sudden vibration signal that appears during the operation of the multi-leaf collimator 100. By monitoring the sharp pulse, it can be identified whether the multi-leaf collimator 100 has serious mechanical failures. For example, when a high-frequency sharp pulse is monitored, it can be preliminarily determined that the bearing in the multi-leaf collimator 100 may be damaged; when a low-frequency sharp pulse is monitored, it can be preliminarily determined that components such as gears and shafts in the multi-leaf collimator 100 may be damaged. The clipped wave can be used to monitor the effectiveness of the vibration damping measures in the multi-leaf collimator 100 to ensure that the multi-leaf collimator 100 can operate stably and reliably.

[0049] The fault monitoring system 200 in this application can collect the vibration signals of the blade box 2 in the multi-leaf collimator 100 in real time through the vibration sensor 10, and transmit them to the processor 20. After being converted by the processor 20 into corresponding waveform data, the data is transmitted to the remote diagnosis system 30; while the remote diagnosis system 30 can process and analyze the waveform data transmitted by the processor 20 to generate information reflecting the state of the multi-leaf collimator 100. In this way, it is possible to realize real-time monitoring of the operating state of the multi-leaf collimator 100, quickly and accurately reflect the operating state of the multi-leaf collimator 100, ensure the stable and reliable operation of the multi-leaf collimator 100, and further enable unattended real-time monitoring.

[0050] In addition, the user can also obtain the state of the multi-leaf collimator 100 through the fault monitoring system 200 before the multi-leaf collimator 100 shows obvious aging or abnormalities. Thus, when there are problems with the multi-leaf collimator 100 but it can still move, the problems can be discovered in advance and the maintenance plan can be started, reducing the situation where the multi-leaf collimator 100 cannot move and ensuring that the treatment plan can be implemented normally.

[0051] In some embodiments, the processor 20 can obtain the vibration signals collected by the vibration sensor 10 and convert them into corresponding waveform data, including: converting the vibration signals of the blade box 2 into corresponding time-domain waveform data and / or frequency-domain waveform data.

[0052] That is to say, the processor 20 can either convert the vibration signals collected by the vibration sensor 10 into corresponding time-domain waveform data, or convert the vibration signals collected by the vibration sensor 10 into corresponding frequency-domain waveform data, and can be specifically selected according to the actual situation. This application does not make any limitations in this regard. For example, the processor 20 can convert vibration signals such as sine waves, sharp pulses, and clipped waves collected by the vibration sensor 10 into corresponding time-domain waveform data and frequency-domain waveform data.

[0053] Among them, the time-domain waveform data directly shows the change of the signal over time, which is very intuitive for observing transient phenomena, pulse events, or any time-varying characteristics, and is suitable for detecting sudden abnormalities such as impacts and sudden amplitude changes; the frequency-domain waveform data shows the energy distribution of the signal at different frequencies, and is particularly suitable for analyzing complex signals with periodicity or containing multiple frequency components, which can help identify problems such as equipment wear status, imbalance, and misalignment.

[0054] It should be noted that the processor 20 can be a Field Programmable Gate Array (FPGA) chip. After the FPGA chip is manufactured, it can be configured through software tools to implement specific logic functions, without going through the high cost and long cycle of traditional Application-Specific Integrated Circuit (ASIC) design and manufacturing.

[0055] In some embodiments, the remote diagnosis system 30 includes a remote center 301 and a fault diagnosis module 302. The remote center 301 is respectively connected to the processor 20 and the fault diagnosis module 302.

[0056] Among them, the remote center 301 can receive and integrate the waveform data transmitted by the processor 20 to obtain a target data waveform, and transmit it to the fault diagnosis module 302; the fault diagnosis module 302 can generate corresponding status information based on the target data waveform transmitted by the remote center 301.

[0057] It should be noted that the target data waveform includes a time-domain waveform and a frequency-domain waveform. For example, the remote center 301 can convert the time-domain waveform data transmitted by the processor 20 into a corresponding time-domain waveform, and convert the frequency-domain waveform data transmitted by the processor 20 into a corresponding frequency-domain waveform.

[0058] Exemplarily, when the blade 1 of the multi-leaf collimator 100 moves relative to the blade box 2, the blade box 2 will vibrate. At this time, the vibration sensor 10 can be controlled to collect vibration signals such as sine waves, sharp pulses, and clipped waves when the blade box 2 vibrates, and transmit the collected vibration signals to the processor 20; the processor 20 can analyze and process the vibration signals transmitted by the vibration sensor 10, and then convert them into corresponding time-domain waveform data and / or frequency-domain waveform data, and transmit them to the remote center 301; the remote center 301 can receive and integrate the waveform data transmitted by the processor 20 to obtain the corresponding time-domain waveform and / or frequency-domain waveform, and transmit it to the fault diagnosis module 302; the fault diagnosis module 302 can perform time-domain analysis based on the time-domain waveform and frequency-domain analysis based on the frequency-domain waveform, and then generate corresponding status information. Based on this, the user can obtain the status information to know the status of the multi-leaf collimator 100, and realize real-time monitoring of the operating status of the multi-leaf collimator 100 to ensure that the multi-leaf collimator 100 can operate stably and reliably.

[0059] In some embodiments, the remote diagnosis system 30 further includes an alarm module 303. The alarm module 303 is connected to the fault diagnosis module 302, and the alarm module 303 can issue corresponding alarm signals based on the status information generated by the fault diagnosis module 302.

[0060] For example, when the status information generated by the fault diagnosis module 302 reflects that the multi-leaf collimator 100 has a fault, the alarm module 303 can send an alarm signal to remind the user that the multi-leaf collimator 100 has a fault. This can achieve unattended real-time monitoring, facilitating timely maintenance and servicing of the multi-leaf collimator 100 to ensure that the treatment plan can be implemented normally.

[0061] The alarm signal can be a sound signal such as an alarm sound or a beeping sound, or a visual signal such as a flashing light or a rotating light, or other types of signals. The present application does not make specific limitations thereto.

[0062] The embodiment of the present application also provides a fault monitoring method, which can be applied to the fault monitoring system in any of the above embodiments. The following will describe this fault monitoring method in detail with reference to the accompanying drawings.

[0063] In some embodiments, as Figure 3 shown, the fault monitoring method provided by the embodiment of the present application includes the following steps:

[0064] S100. Obtain waveform data corresponding to the vibration signal of the blade housing.

[0065] The vibration signal of the blade housing includes one or more of a sine wave, a sharp pulse, and a clipped wave when the blade housing vibrates. The waveform data corresponding to the vibration signal of the blade housing includes time-domain waveform data and / or frequency-domain waveform data.

[0066] Exemplarily, when the multi-leaf collimator is operating (i.e., when the blades of the multi-leaf collimator move relative to the blade housing), the vibration sensor is controlled to collect vibration signals such as sine waves, sharp pulses, and clipped waves generated by the vibration of the blade housing, and the collected vibration signals are transmitted to the processor; then, the processor analyzes and processes the vibration signals transmitted by the vibration sensor and converts them into corresponding time-domain waveform data and / or frequency-domain waveform data, and then transmits the waveform data to the remote diagnosis system.

[0067] S200. Convert the waveform data into a corresponding target data waveform, determine the matching template corresponding to the target data waveform, and match the target data waveform with the corresponding matching template to generate a detection result.

[0068] Exemplarily, the remote diagnosis system can receive the waveform data transmitted by the processor and integrate and process the waveform data to convert the waveform data into a corresponding target data waveform. The target data waveform may include 1,600 integers in the range of -127 to +127. On this basis, 0 to 1,599 is the T-axis, i.e., the time axis, and -127 to 127 is the Y-axis, i.e., the waveform amplitude.

[0069] Among them, the target data waveform includes a time-domain waveform and a frequency-domain waveform. For example, the remote diagnosis system can transform the received time-domain waveform data into the corresponding time-domain waveform and transform the received frequency-domain waveform data into the corresponding frequency-domain waveform.

[0070] It can be understood that the waveform data generated by the transformation of different vibration signals will be transformed into different target data waveforms. For example, the waveform data (time-domain waveform data and / or frequency-domain waveform data) generated by the transformation of the sine wave during the vibration of the blade box can be transformed by the remote diagnosis system into the corresponding sine wave waveform (time-domain waveform and / or frequency-domain waveform); the waveform data (time-domain waveform data and / or frequency-domain waveform data) generated by the transformation of the sharp pulse during the vibration of the blade box can be transformed by the remote diagnosis system into the corresponding sharp pulse waveform (time-domain waveform and / or frequency-domain waveform); the waveform data (time-domain waveform data and / or frequency-domain waveform data) generated by the transformation of the wave cancellation during the vibration of the blade box can be transformed by the remote diagnosis system into the corresponding wave cancellation waveform (time-domain waveform and / or frequency-domain waveform).

[0071] It should be noted that different target data waveforms correspond to different matching templates. Matching the target data waveform with the corresponding matching template can identify the abnormal data in the target data waveform, and then determine whether there is an abnormality in the target data waveform. For example, in the case where the maximum amplitude in the target data waveform is much larger than the maximum amplitude of the matching template or the minimum amplitude in the target data waveform is much smaller than the minimum amplitude of the matching template, it is determined that there is an abnormality in the target data waveform. Another example is that in the case where the proportion of the abnormal data in the target data waveform in the total data is greater than the set value, it is determined that there is an abnormality in the target data waveform.

[0072] S300. Based on the detection result, determine whether there is a fault in the multi-leaf collimator.

[0073] For example, within a sampling period, if the number of abnormal target data waveforms is greater than the set number, it is determined that there is a fault in the multi-leaf collimator. Another example is that within a sampling period, if the proportion of the number of abnormal target data waveforms in the total number of target data waveforms is greater than the set ratio, it is determined that there is a fault in the multi-leaf collimator.

[0074] The technical effects brought by the fault monitoring method in the embodiments of the present application are the same as those brought by the above-mentioned fault monitoring system, and will not be elaborated here.

[0075] In some embodiments, as Figure 4 shown, obtaining the waveform data corresponding to the vibration signal of the blade box in S100 includes the following steps:

[0076] S101. Periodically detect whether the blades of the multi-leaf collimator are in a moving state.

[0077] S102. When the leaves of the multi-leaf collimator are in a moving state, control the vibration sensor to collect the vibration signal of the leaf box body and transmit it to the processor.

[0078] S103. Through the processor, convert the vibration signal transmitted by the vibration sensor into corresponding waveform data.

[0079] It can be understood that through S101 - S103, the waveform data corresponding to the vibration signal of the leaf box body can be obtained in real time, and unattended real-time monitoring of the multi-leaf collimator can be realized to ensure the stable and reliable operation of the multi-leaf collimator.

[0080] In some embodiments, as Figure 5 shown, determining the matching template corresponding to the target data waveform in S200 includes the following steps:

[0081] S201. Obtain the standard data waveform corresponding to the waveform data of the vibration signal of the leaf box body.

[0082] Exemplarily, the standard data waveform is stored in the remote diagnosis system. After the remote diagnosis system obtains the waveform data corresponding to the vibration signal of the leaf box body, it can retrieve the corresponding standard data waveform.

[0083] It should be noted that the standard data waveform can be the data waveform generated by converting the vibration signal of the leaf box body obtained when the multi-leaf collimator operates stably and reliably.

[0084] Similar to the target data waveform, the standard data waveform can also include 1600 integers in the range of -127 to +127. On this basis, 0 to 1599 is the T-axis, that is, the time axis, and -127 to 127 is the Y-axis, that is, the waveform amplitude, which is convenient for comparing with the target data waveform to identify the abnormalities existing in the target data waveform.

[0085] It can be understood that different vibration signals can be converted into different waveform data, and different waveform data correspond to different standard data waveforms; moreover, the time-domain waveform data and frequency-domain waveform data generated from the same vibration signal respectively correspond to different standard data waveforms. For example, the time-domain waveform data and frequency-domain waveform data corresponding to the sine wave when the leaf box body vibrates, the time-domain waveform data and frequency-domain waveform data corresponding to the sharp pulse when the leaf box body vibrates, and the time-domain waveform data and frequency-domain waveform data corresponding to the clipped wave when the leaf box body vibrates respectively correspond to different standard data waveforms.

[0086] S202. Increase the tolerance value for the data in the standard data waveform to obtain the first data waveform; decrease the tolerance value for the data in the standard data waveform to obtain the second data waveform.

[0087] Among them, the tolerance value is used to limit the maximum allowable deviation range between the target data waveform and the corresponding standard data waveform. For example, when the deviation between the target data waveform and the corresponding standard data waveform is less than the tolerance value, the target data waveform can be recorded as a normal waveform. It can be understood that the magnitude of the tolerance value can be set according to the actual situation, and the present application does not make specific limitations thereon.

[0088] It should be noted that different standard data waveforms correspond to different tolerance values. For example, when the waveform data corresponding to the standard data waveform is time-domain waveform data, the tolerance value is the amplitude tolerance; when the waveform data corresponding to the standard data waveform is frequency-domain waveform data, the tolerance value is the time tolerance.

[0089] S203. Use the first data waveform and the second data waveform as boundaries to form a matching template.

[0090] It can be understood that a region similar to a winding road can be defined between the first data waveform and the second data waveform, and this region is the matching template.

[0091] On this basis, when matching the target data waveform with the matching template, the target data waveform whose all amplitudes fall within the above-mentioned region similar to a winding road can be recorded as a normal waveform.

[0092] In order to improve the accuracy of the detection result of the target data waveform, in some embodiments, as Figure 6 shown, in S200, matching the target data waveform with the corresponding matching template to generate a detection result includes the following steps:

[0093] S204. Input the target data waveform into the matching template to obtain the out-of-bounds frequency of the target data waveform.

[0094] Among them, the out-of-bounds frequency is the percentage of the number of amplitudes of the target data waveform that exceed the boundary of the matching template to the total number of amplitudes of the target data waveform.

[0095] S205. If the out-of-bounds frequency is less than or equal to the preset value, determine that there is no abnormality in the target data waveform.

[0096] Among them, the preset value can be the maximum out-of-bounds frequency of the target data waveform obtained when the multi-leaf collimator operates stably and reliably. That is to say, when the out-of-bounds frequency is less than the preset value, it means that the number of amplitudes of the target data waveform that exceed the boundary of the matching template is small. At this time, the multi-leaf collimator has not failed and can operate stably and reliably.

[0097] Based on this, when the out-of-bounds frequency is less than the preset value, determining that the target data waveform is normal can reduce false alarms and contribute to accurate monitoring of the multi-leaf collimator status.

[0098] It should be noted that the preset value can be set according to the actual situation, and this application does not make specific limitations thereto.

[0099] Exemplarily, the preset value is 0.1%. At this time, if the out-of-bounds frequency is equal to the preset value, that is, the out-of-bounds frequency is equal to 0.1%, the percentage of the number of amplitudes of the target data waveform exceeding the boundary of the matching template in the total number of amplitudes of the target data waveform is 0.1%.

[0100] S206. If the out-of-bounds frequency is greater than the preset value, determine that the target data waveform is abnormal.

[0101] When the out-of-bounds frequency is greater than or equal to the preset value, it indicates that the number of amplitudes of the target data waveform exceeding the boundary of the matching template is large. At this time, there is a high probability that the multi-leaf collimator has failed.

[0102] Based on this, when the out-of-bounds frequency is greater than or equal to the preset value, determining that the target data waveform is abnormal can remind the user to perform maintenance on the multi-leaf collimator, thereby ensuring the stable and reliable operation of the multi-leaf collimator.

[0103] It can be understood that S204 - S206 in the embodiments of this application can be implemented by a waveform filter.

[0104] In some embodiments, as Figure 7 shown, determining whether the multi-leaf collimator has a fault based on the detection result in S300 includes the following steps:

[0105] S301. Generate corresponding status information based on the detection result.

[0106] Exemplarily, the status information includes: within a detection period, the type of vibration signal collected, the total number of target data waveforms respectively generated by various vibration signals after transformation, and the number of target data waveforms with abnormalities.

[0107] For example, the status information includes: within a detection period, the vibration signals collected include sine waves during the vibration of the blade box, the total number of target data waveforms corresponding to the time-domain waveform data generated by the sine waves after transformation and the number of target data waveforms with abnormalities, and the total number of target data waveforms corresponding to the frequency-domain waveform data generated by the sine waves after transformation and the number of target data waveforms with abnormalities.

[0108] For another example, the status information includes: within one detection period, the collected vibration signals include the sharp pulses during the vibration of the blade box, the total number of target data waveforms corresponding to the time-domain waveform data generated by the transformation of the sharp pulses, and the number of target data waveforms with abnormalities, the total number of target data waveforms corresponding to the frequency-domain waveform data generated by the transformation of the sharp pulses, and the number of target data waveforms with abnormalities.

[0109] For yet another example, the status information includes: within one detection period, the collected vibration signals include the wave cancellation during the vibration of the blade box, the total number of target data waveforms corresponding to the time-domain waveform data generated by the transformation of the wave cancellation, and the number of target data waveforms with abnormalities, the total number of target data waveforms corresponding to the frequency-domain waveform data generated by the transformation of the wave cancellation, and the number of target data waveforms with abnormalities.

[0110] S302. Determine whether the multi-leaf collimator has a fault according to the status information.

[0111] For example, within one sampling period, if the number of target data waveforms with abnormalities is greater than the set number, it is determined that the multi-leaf collimator has a fault. For yet another example, within one sampling period, if the proportion of the number of target data waveforms with abnormalities in the total number of target data waveforms is greater than the set ratio, it is determined that the multi-leaf collimator has a fault.

[0112] In some embodiments, as Figure 7 shown, after determining whether the multi-leaf collimator has a fault according to the status information, the following steps are further included:

[0113] S303. In the case where it is determined that the multi-leaf collimator has a fault according to the status information, determine the fault type of the multi-leaf collimator based on the status information, and control the alarm module to send out corresponding alarm signals.

[0114] Based on this, the user can preliminarily judge the fault type of the multi-leaf collimator according to the alarm signal, and then start the corresponding maintenance plan, which can improve the maintenance efficiency of the multi-leaf collimator.

[0115] In the description of this specification, the specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0116] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A fault monitoring system for performing fault monitoring on a multi-leaf collimator of a radiotherapy system, wherein the multi-leaf collimator comprises a leaf box, characterized in that: The fault monitoring system comprises: a vibration sensor, a processor and a remote diagnosis system, wherein the vibration sensor is arranged on the blade housing, and the processor is respectively connected to the vibration sensor and the remote diagnosis system; Among them, the vibration sensor is used to collect the vibration signal of the blade box; the processor can obtain the vibration signal collected by the vibration sensor, convert it into corresponding waveform data, and transmit it to the remote diagnosis system; the remote diagnosis system can generate corresponding status information based on the waveform data transmitted by the processor, and the status information is used to reflect the status of the multi-leaf collimator.

2. The fault monitoring system according to claim 1, characterized in that: The vibration signal of the blade box includes one or more of a sine wave, a sharp pulse and a clipped wave when the blade box vibrates.

3. The fault monitoring system according to claim 1, characterized in that: The processor can obtain the vibration signal collected by the vibration sensor and convert it into corresponding waveform data, including: The vibration signal of the blade box is converted into corresponding time domain waveform data and / or frequency domain waveform data.

4. The fault monitoring system according to any one of claims 1 to 3, characterized in that: The remote diagnosis system comprises: a remote center and a fault diagnosis module, wherein the remote center is connected to the processor and the fault diagnosis module respectively; Among them, the remote center can receive and integrate the waveform data transmitted by the processor, obtain the target data waveform, and transmit it to the fault diagnosis module; the fault diagnosis module can generate corresponding status information based on the target data waveform transmitted by the remote center.

5. The fault monitoring system according to claim 4, characterized in that: The remote diagnosis system further comprises: an alarm module, the alarm module being connected to the fault diagnosis module; The alarm module can send out a corresponding alarm signal based on the status information generated by the fault diagnosis module.

6. A fault monitoring method, applied to the fault monitoring system according to any one of claims 1 to 5, characterized in that: include: Obtaining waveform data corresponding to the vibration signal of the blade box; Convert the waveform data into a corresponding target data waveform, determine a matching template corresponding to the target data waveform, match the target data waveform with the corresponding matching template, and generate a detection result; Based on the detection result, it is determined whether the multi-leaf collimator is faulty.

7. The method according to claim 6, characterized in that The vibration signal of the blade box includes one or more of the sine wave, the sharp pulse and the clipped wave when the blade box vibrates.

8. The method according to claim 6, characterized in that The step of obtaining waveform data corresponding to the vibration signal of the blade box includes: Periodically detecting whether the leaves of the multi-leaf collimator are in motion; When the leaves of the multi-leaf collimator are in motion, controlling the vibration sensor to collect vibration signals of the leaf box and transmit the signals to the processor; The processor converts the vibration signal transmitted by the vibration sensor into the corresponding waveform data.

9. The method according to claim 8, characterized in that The converting the vibration signal transmitted by the vibration sensor into the corresponding waveform data by the processor includes: The processor converts the vibration signal transmitted by the vibration sensor into corresponding time domain waveform data and / or frequency domain waveform data.

10. The method according to claim 6, characterized in that The determining of the matching template corresponding to the target data waveform includes: Obtaining a standard data waveform corresponding to the waveform data corresponding to the vibration signal of the blade box; The data in the standard data waveform is increased by a tolerance value to obtain a first data waveform; the data in the standard data waveform is decreased by a tolerance value to obtain a second data waveform; The matching template is formed with the first data waveform and the second data waveform as a boundary.

11. The method according to claim 6, characterized in that The step of matching the target data waveform with the corresponding matching template to generate a detection result includes: Input the target data waveform into the matching template to obtain the cross-boundary frequency of the target data waveform; the cross-boundary frequency is the percentage of the number of amplitudes of the target data waveform exceeding the boundary of the matching template to the number of all amplitudes of the target data waveform; If the out-of-bounds frequency is less than or equal to a preset value, it is determined that there is no abnormality in the target data waveform; If the out-of-bounds frequency is greater than a preset value, it is determined that the target data waveform is abnormal.

12. The method according to claim 6, characterized in that Determining whether the multi-leaf collimator is faulty based on the detection result includes: Based on the detection result, generating corresponding status information; It is determined whether the multi-leaf collimator has a fault according to the status information.

13. The method according to claim 12, characterized in that After determining whether the multi-leaf collimator has a fault according to the state information, the method further includes: In the case that it is determined according to the state information that the multi-leaf collimator has a fault, the fault type of the multi-leaf collimator is determined based on the state information, and an alarm module is controlled to send a corresponding alarm signal.

Images