Method and system for controlling output intensity of an x-ray source

Abstract

The present invention discloses an output intensity control method and system for an X-ray source. By predicting the output intensity of the X-ray source using operating voltage, filament current, and operating temperature, and determining the target operating voltage and target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source, the determination process of the target operating voltage and target filament current takes into account the temperature drift problem caused by the temperature rise during long-term operation of the X-ray source, thereby improving the output intensity stability of the X-ray source.

Description

Technical Field

[0001] This invention generally relates to the field of X-rays. More specifically, this invention relates to a method and system for controlling the output intensity of an X-ray source. Background Technology

[0002] Since German physicist Wilhelm Röntgen discovered X-rays in 1985, their applications have become increasingly widespread with socio-economic and technological development. X-rays are used in fields such as medicine and PCB inspection, significantly impacting our scientific and technological progress and daily life. Simultaneously, to meet the diverse needs of X-ray use, X-ray sources are continuously being developed and improved.

[0003] In more specific applications, various X-ray sources need to generate X-rays with corresponding output intensities based on the actual application scenario. Given the specific variations in X-ray output intensity, operating voltage, and filament current, the most common method for controlling X-ray source output intensity is to stabilize the operating voltage and filament current around set values.

[0004] In the process of developing this invention, the inventors discovered that even if the operating voltage and filament current of an X-ray source are stable, its actual output intensity may still fluctuate. However, in some specific application scenarios, the stability of the output intensity of the X-ray source is essential, but existing X-ray sources can only achieve a stable output intensity for a certain period of time or under certain conditions, making it difficult for X-ray sources to meet the requirements of long-term operation. Summary of the Invention

[0005] To address one or more of the aforementioned technical problems, embodiments of the present invention propose using the operating temperature of the X-ray source for controlling the output intensity of the X-ray source. To this end, the present invention provides solutions in the following aspects.

[0006] In a first aspect, embodiments of the present invention provide an output intensity control method for an X-ray source, comprising: acquiring the actual output intensity and operating parameters of the X-ray source, the operating parameters including: operating voltage, filament current, and operating temperature; determining a predicted output intensity value based on the operating voltage, the filament current, the operating temperature, and a preset output intensity prediction model, the preset output intensity prediction model being trained based on sample data; inputting the actual output intensity, the predicted output intensity value, and a target output intensity value of the X-ray source into a preset controller model to determine a target operating voltage and a target filament current corresponding to the target output intensity value;

[0007] The X-ray source is controlled by the target operating voltage and the target filament current.

[0008] In one specific embodiment of the first aspect, the operating parameters further include: X-ray tube shape parameters, air humidity, and equipment transmission loss; determining the output intensity prediction value based on the operating voltage, the filament current, the operating temperature, and a preset output intensity prediction model includes: inputting the operating voltage, the filament current, the operating temperature, the X-ray tube shape parameters, the air humidity, and the equipment transmission loss into the preset output intensity prediction model to obtain the output intensity prediction value.

[0009] In one specific embodiment of the first aspect, determining the target operating voltage and target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source includes: determining the initial target operating voltage and initial target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source; calculating a first difference between the operating voltage setpoint and the initial target operating voltage, and a second difference between the filament current setpoint and the initial target filament current; when the first difference is less than a first difference threshold and the second difference is less than a second difference threshold, using the operating voltage setpoint as the target operating voltage and the filament current setpoint as the target filament current; when the first difference is greater than or equal to the first difference threshold, and / or the second difference is greater than or equal to the second difference threshold, using the initial target operating voltage as the target operating voltage and the initial target filament current as the target filament current.

[0010] In one specific embodiment of the first aspect, controlling the operation of the X-ray source using the target operating voltage and the target filament current includes: generating the target operating voltage and the target filament current using PWM control to control the operation of the X-ray source.

[0011] In one specific embodiment of the present invention, the preset output intensity prediction model is an RBF neural network model.

[0012] In one specific embodiment of the first aspect, the training process of the RBF neural network model is as follows: acquiring multiple sample data, each sample data including: historical actual output intensity, historical operating voltage, historical filament current and historical operating temperature; for each sample data, inputting the historical operating voltage, historical filament current and historical operating temperature into the initial RBF neural network model for training, obtaining the historical output intensity prediction value corresponding to each sample data, until the difference between the historical actual output intensity and the corresponding historical output intensity prediction value in each sample data is less than a preset threshold, and determining the trained initial RBF neural network model as the RBF neural network model.

[0013] In one specific embodiment of the first aspect, the method further includes: inputting the operating voltage, the filament current, and the operating temperature into the RBF neural network model to update the RBF neural network model.

[0014] In one specific embodiment of the first aspect, the preset controller model is a PID controller model.

[0015] In a second aspect, embodiments of the present invention also disclose an output intensity control system for an X-ray source, comprising: a signal acquisition device and an adjustment control device; the signal acquisition device is used to acquire the actual output intensity of the X-ray source and send it to the adjustment control device, the adjustment control device is also connected to the X-ray source to obtain the operating parameters of the X-ray source, and the adjustment control device is used to execute the output intensity control method described in any one of the first aspects.

[0016] In one specific embodiment of the second aspect, it further includes: a monitoring device, which is connected to the signal acquisition device and the X-ray source respectively, and the monitoring device is used to issue an alarm message when it detects that the working state of the signal acquisition device is abnormal and / or the working state of the X-ray source is abnormal.

[0017] In one specific embodiment of the second aspect, the adjustment and control device includes: a control system and a host computer, the host computer being used to train the preset output intensity prediction model and send the preset output intensity prediction model to the control system, the control system being used to perform output intensity control operations of the X-ray source.

[0018] In one specific embodiment of the second aspect, the signal acquisition device includes: a signal receiving and reflecting device and an X-ray detector. The signal receiving and reflecting device is used to receive X-rays output by the X-ray source and partially reflect them to the X-ray detector. The X-ray detector is used to acquire the X-rays reflected by the signal receiving and reflecting device and send the actual output intensity of the X-ray source, which it represents, to the adjustment and control device.

[0019] The present invention provides an X-ray source output intensity control method and system. By predicting the output intensity of the X-ray source using operating voltage, filament current, and operating temperature, and determining the target operating voltage and target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source, the determination process of the target operating voltage and target filament current takes into account the temperature drift problem caused by the temperature rise during long-term operation of the X-ray source, thereby improving the output intensity stability of the X-ray source. Attached Figure Description

[0020] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:

[0021] Figure 1 This is a flowchart illustrating an X-ray source output intensity control method provided in an embodiment of the present invention;

[0022] Figure 2 This is a principle block diagram of an X-ray source output intensity control method provided in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of an X-ray source output intensity control system provided in an embodiment of the present invention; and

[0024] Figure 4 This is a schematic diagram of the output intensity control system of another X-ray source provided in an embodiment of the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] As mentioned earlier, current technologies control the output intensity of an X-ray source by stabilizing its operating voltage and filament current within set values. In other words, the stability of the X-ray source's output intensity is essentially achieved through post-adjustment of the operating voltage and filament current parameters. When the operating voltage and filament current reach a stable state according to the set values, the X-ray source's output intensity is considered stable. This method yields a stable output intensity over a certain period.

[0027] However, the inventors discovered during the implementation of the embodiments of the present invention that as the working time of the X-ray source increases, even if the working voltage and filament current of the X-ray source are stable, the output intensity of the X-ray source will fluctuate.

[0028] Based on this, embodiments of the present invention provide an output intensity control method and system for X-ray sources to improve the stability of the output intensity of X-ray sources.

[0029] To facilitate understanding, the design concept of this invention will first be explained. Based on the discovery that even when the operating voltage and filament current of the X-ray source are stable, the output intensity of the X-ray source will still fluctuate, this invention proposes to consider the influence of factors such as operating temperature or other operating parameters when determining the target operating voltage and target filament current corresponding to the target output intensity value. Specifically, the invention involves: acquiring the operating voltage, filament current, and operating temperature or other operating parameters of the X-ray source in real time; determining the predicted output intensity value based on the real-time acquired operating parameters and a preset output intensity prediction model; and inputting the actual output intensity of the X-ray source, the predicted output intensity value, and the target output intensity value of the X-ray source into a preset controller model to determine the target operating voltage and target filament current corresponding to the target output intensity value. In this way, by incorporating real-time operating temperature or other operating parameters into the determination process of the target operating voltage and target filament current, the target operating voltage and target filament current are dynamic and matched to the real-time operating conditions. This allows the output intensity of the X-ray source to be better maintained near the target output intensity value, thus improving the output stability of the X-ray source. In other words, the embodiments of the present invention take into account the influence of operating temperature on the output intensity value of the X-ray source, that is, it has been found and taken into account that in order to maintain the target output intensity value of the X-ray source, different operating voltages and filament currents need to be configured at different operating temperatures.

[0030] It should be noted that the target output intensity value is the X-ray output intensity value required in a specific application scenario. Understandably, the required X-ray output intensity value may differ in different application scenarios, but within the same specific application scenario, we expect the X-ray output intensity value to be stable, or to fluctuate within an acceptable range.

[0031] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0032] See Figure 1 This is a flowchart illustrating a method for controlling the output intensity of an X-ray source according to an embodiment of the present invention. The execution entity of this method can be an electronic device with information acquisition and computing capabilities, such as a computer, server, or smart terminal; in the corresponding system embodiment, this is referred to as an adjustment and control device. The information here can be either a signal or data. The method may include:

[0033] In step S101, the actual output intensity and operating parameters of the X-ray source are obtained.

[0034] The X-ray source mentioned in step S101 can be a common X-ray source such as a grid X-ray source or a dual-anode X-ray source. The X-ray source may include an X-ray tube, a high-voltage power supply that provides the operating voltage to the X-ray tube, and a water-cooling system for thermal balance.

[0035] In practical applications, a signal acquisition device can be used to acquire the actual output intensity of an X-ray source in real time and send it to an adjustment and control device. In one implementation, the signal acquisition device may include a signal receiving and reflecting device and an X-ray detector. Further, the signal receiving and reflecting device receives the X-rays output by the X-ray source and partially reflects them to the X-ray detector. The X-ray detector acquires the X-rays reflected by the signal receiving and reflecting device and sends the actual output intensity of the X-ray source, representing this intensity, to the adjustment and control device. More specifically, the X-ray detector may be a scintillation counter, which includes a scintillator and a photomultiplier tube, and can be used to acquire the signal intensity of X-rays. It is understood that embodiments of the present invention may also use other methods in the prior art to obtain the actual output intensity of the X-ray source, and embodiments of the present invention are not limited thereto.

[0036] Additionally, the operating parameters obtained in step S101 may include: operating voltage, filament current, and operating temperature. It should be noted that the operating temperature characterizes the X-ray source's own temperature during operation; for example, it could be the target temperature or the tube temperature. In particular, the tube temperature is relatively easy to obtain, therefore, it is generally used as the operating temperature. However, the target temperature can also be used as the operating temperature, although measuring it is relatively more difficult. In practical applications, the tube temperature or target temperature can be obtained by placing a temperature sensor at the tube or target location.

[0037] In step S102, the predicted value of the output intensity is determined based on the operating voltage, filament current, operating temperature, and a preset output intensity prediction model.

[0038] Before providing a detailed explanation of step S102, to facilitate a more comprehensive understanding of the embodiments of the present invention, the reasons for using a preset output intensity prediction model to predict the output intensity of the X-ray source, and the reasons for using operating temperature during the prediction process, will be explained first. The reasons are as follows:

[0039] Existing X-ray sources lack a predictive system for output intensity stability. This system relies on process control to feed back the X-ray source's output intensity using measurements of filament current and operating voltage, which can achieve stable results over a certain period or under specific conditions. However, during the development of this invention, the inventors discovered that filament current and operating voltage cannot uniquely determine the X-ray source's output intensity. Therefore, using existing methods that lack predictability for X-ray source output intensity leads to unstable control over long periods, negatively impacting scenarios requiring prolonged X-ray utilization. For example, applying existing methods to continuous operation for trace and micro-level element detection and analysis yields unreliable results, or even no results at all.

[0040] The reason for using the operating temperature in the prediction process is that the inventors discovered during the development of this invention that the operating temperature (actually the target temperature, but since there is a corresponding relationship between the target temperature and the tube temperature, the tube temperature can be used in practical applications) causes X-ray loss from generation to output from the window. In particular, the temperature change caused by long-term operation will cause output temperature drift, which means that even if the operating voltage and filament current of the X-ray source are stable, its actual output intensity will fluctuate.

[0041] In step S102, the predicted output intensity value is determined based on the operating voltage, filament current, operating temperature, and a preset output intensity prediction model. This allows the embodiment of the present invention to predict the output intensity of the X-ray source while considering the operating temperature factor during prediction, ensuring stable control of the X-ray source's output intensity and making detection and analysis using the X-ray source more reliable. When applied to fields such as fluorescence spectroscopy, the adjustment and control device of the X-ray source can obtain a more stable sampling spectrum, thereby obtaining more accurate qualitative and quantitative analysis data.

[0042] Furthermore, in this embodiment of the invention, the preset output intensity prediction model is trained based on sample data. In practical applications, the preset output intensity prediction model can be a machine learning model that can predict physical quantities (such as output intensity) through training, such as an RBF (Radial Basis Function) neural network model, a random forest algorithm model, an XGBoost model, or a decision tree model.

[0043] The following section uses the RBF neural network model as an example to describe the training process of the model, with the preset output intensity prediction model being an example. In one specific implementation of the first aspect, the training process of the RBF neural network model is as follows:

[0044] First, obtain multiple sample data.

[0045] The amount of sample data is determined based on the actual situation, aiming to make a prediction of the X-ray source's output intensity that meets the application accuracy. Each sample data includes: historical actual output intensity, historical operating voltage, historical filament current, and historical operating temperature. The historical actual output intensity, historical operating voltage, historical filament current, and historical operating temperature can be the output intensity, operating voltage, filament current, and operating temperature collected by the X-ray source in its operating state before the execution of this embodiment of the invention.

[0046] Then, for each sample data point, historical operating voltage, historical filament current, and historical operating temperature are input into the initial RBF neural network model for training. This process yields the predicted historical output intensity value for each sample data point, continuing until the difference between the actual historical output intensity and the corresponding predicted historical output intensity value for each sample data point is less than a preset threshold. The trained initial RBF neural network model is then confirmed as an RBF neural network model. The preset threshold can be a calibration value or an empirical value; in practical applications, its size should ensure both the accuracy of the RBF neural network model's output intensity prediction and keep the training time within an acceptable range.

[0047] More specifically, the RBF neural network model training process is as follows: select the activation function of the hidden layer of the neural network and construct the RBF neural network model → input the sample data into the constructed RBF neural network model → map the sample data into the hidden layer of the neural network → train the RBF neural network model, determine the center point and variance of the basis function, and the weights from the hidden layer to the output layer of the neural network → output the weighted sum of the output values ​​of the hidden layer of the neural network → obtain the predicted output intensity value, until the difference between the historical actual output intensity and the corresponding historical output intensity predicted value in each sample data is less than a preset threshold, and the RBF neural network model is determined to have completed training.

[0048] Understandably, when X-ray sources are relatively consistent, different X-ray sources can use the same preset output intensity prediction model.

[0049] It should be noted that the training process for other preset output intensity models can be found in the RBF neural network model, and will not be repeated in the embodiments of this invention.

[0050] In step S103, the actual output intensity, the predicted output intensity, and the target output intensity of the X-ray source are input into the preset controller model to determine the target operating voltage and the target filament current corresponding to the target output intensity.

[0051] The target value of the output intensity of the X-ray source is the desired output intensity value, which is fixed in a specific scenario.

[0052] Furthermore, in practical applications, a model capable of determining the target operating voltage and target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source can be used as the preset controller model in step S103. The characteristic of this preset controller model is that it can determine the control quantity corresponding to the target value based on the measured, predicted, and target values ​​of the physical quantities. Specifically, in this embodiment of the invention, it is a model capable of determining the target operating voltage and target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source. In specific applications, the preset controller model can be a PID (Proportion Integral Differential) controller model, a Kalman filter algorithm model, etc.

[0053] Through the prediction process in step S102 and the determination process of target operating voltage and target filament current in step S103, the output intensity prediction of the X-ray source is realized on the one hand, and the acquisition process of target operating voltage and target filament current is optimized on the other hand, so that the stability and accuracy of the output intensity of the X-ray source are improved.

[0054] In step S104, the X-ray source is controlled to operate using the target operating voltage and the target filament current.

[0055] Specifically, the method of controlling the X-ray source using the target operating voltage and target filament current is similar to existing technologies. The difference lies in the process of determining the target operating voltage and target filament current in this embodiment of the invention. For example, PWM (Pulse Width Modulation) control can be used to control the X-ray source to obtain a stable X-ray output intensity. In this case, step S104 may include: generating the target operating voltage and the target filament current using PWM control to control the X-ray source.

[0056] Understandably, in practical applications, other methods can also be used to control the operation of X-ray sources, such as using PFM (Pulse Frequency Modulation) control.

[0057] The present invention provides an X-ray source output intensity control method. By predicting the output intensity of the X-ray source using operating voltage, filament current, and operating temperature, and determining the target operating voltage and target filament current corresponding to the target output intensity value based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source, the method takes into account the temperature drift problem caused by the temperature rise during long-term operation of the X-ray source, thereby improving the output intensity stability of the X-ray source.

[0058] In the process of developing this invention, the inventors also discovered that, in addition to the loss of X-rays during the generation and output from the window caused by operating temperature, factors such as the shape of the X-ray tube, air humidity, and internal transmission loss also contribute to the loss of X-rays during this process. The shape of the X-ray tube can be characterized by parameters such as the tilt angle of the target surface and its external dimensions. Internal transmission loss, also known as equipment transmission loss, is determined by the power consumption, heat dissipation, and material temperature rise characteristics of the X-ray source and can be obtained through calibration.

[0059] Therefore, in one specific embodiment of the present invention, the working parameters obtained in step S101 may further include: X-ray tube shape parameters, air humidity, and equipment transmission loss.

[0060] Accordingly, step S102 may include:

[0061] Input the operating voltage, filament current, operating temperature, ray tube shape parameters, air humidity, and equipment transmission loss into the preset output intensity prediction model to obtain the predicted output intensity value.

[0062] Understandably, when training the preset output intensity prediction model, it is necessary to input not only the operating voltage, filament current, and operating temperature, but also operating parameters such as the shape parameters of the X-ray tube, air humidity, and equipment transmission loss.

[0063] Specifically, taking the RBF neural network model as an example again, the training process of the RBF neural network model is as follows:

[0064] First, multiple sample data points are acquired. Each sample data point includes: historical actual output intensity, historical operating voltage, historical filament current, historical operating temperature, X-ray tube shape parameters, historical air humidity, and equipment transmission loss.

[0065] Then, for each sample data, the historical operating voltage, historical filament current, historical operating temperature, X-ray tube shape parameters, historical air humidity, and equipment transmission loss are input into the initial RBF neural network model for training, so as to obtain the historical output intensity prediction value corresponding to each sample data. This process continues until the difference between the historical actual output intensity and the corresponding historical output intensity prediction value in each sample data is less than a preset threshold. The initial RBF neural network model after training is then determined to be the RBF neural network model.

[0066] In this specific implementation, the operating voltage, filament current, and actual emission intensity of the X-ray source are detected. Simultaneously, the power consumption, heat dissipation, and material temperature rise characteristics of the X-ray source are collected. The output intensity of the X-ray source is predicted using a preset output intensity prediction model. The system is then adjusted through feedback by combining this preset output intensity prediction model with a preset controller model. This dynamically adjusts the operating voltage and filament current based on predicted changes in various operating parameters of the X-ray source, thereby achieving precise prediction and control of the X-ray source's output intensity. Ultimately, this improves the stability of the X-ray source's output intensity and ensures output accuracy. In other words, by considering more operating parameters such as the X-ray tube shape parameters, historical air humidity, and equipment transmission losses when predicting the X-ray source's output intensity, the obtained output intensity prediction value is more accurate and reliable, further improving the stability of the X-ray source's output intensity.

[0067] It should be noted that the X-ray tube shape parameters, historical air humidity, and equipment transmission loss are not necessary when predicting the output intensity of an X-ray source. In principle, considering only the operating temperature can improve the stability of the X-ray source's output intensity. However, by considering the X-ray tube shape parameters, historical air humidity, and equipment transmission loss along with the operating temperature, a better preset output intensity prediction model can be trained, and a more accurate output intensity prediction value can be obtained.

[0068] The following is a further improvement to the aforementioned embodiment. Specifically, during the execution of step S103, if the target operating voltage and target filament current calculated in real time are different from those calculated in the previous moment or cycle, i.e., adjustments are made to the target operating voltage and target filament current, it will inevitably lead to frequent switching control processes. Therefore, in a specific embodiment of the present invention, step S103 may include the following steps:

[0069] First, the initial target operating voltage and initial target filament current corresponding to the output intensity target value are determined based on the actual output intensity, the predicted output intensity value, and the target output intensity value of the X-ray source.

[0070] Next, calculate the first difference between the working voltage setting value and the initial target working voltage, and the second difference between the filament current setting value and the initial target filament current.

[0071] The operating voltage and operating current settings are determined based on the specific application scenario. Under the given operating voltage and filament current settings, the X-ray source can produce an X-ray output intensity that meets the requirements of that application scenario, and its stability is guaranteed. For example, during the initial period of normal operation, the X-ray source can produce sufficient X-rays at the specified operating voltage and filament current settings.

[0072] Finally, when the first difference is less than the first difference threshold and the second difference is less than the second difference threshold, the operating voltage setting is taken as the target operating voltage and the filament current setting is taken as the target filament current. Correspondingly, when the first difference is greater than or equal to the first difference threshold and / or the second difference is greater than or equal to the second difference threshold, the initial target operating voltage is taken as the target operating voltage and the initial target filament current is taken as the target filament current.

[0073] The first and second difference thresholds are determined based on the accuracy requirements of output intensity stability and can be empirical or calibrated values. Thus, when both the first and second differences are small, no adjustment is made to the operating voltage and filament current. When either the first or second difference exceeds its corresponding threshold, the operating voltage and filament current are adjusted. This avoids frequent adjustments to the operating voltage and filament current while ensuring output intensity stability, and allows for timely adjustments to the calculated optimal target operating voltage and filament current when the current operating voltage and filament current may not meet the stability requirements.

[0074] In one specific embodiment of the first aspect, the method further includes: inputting the operating voltage, filament current, and operating temperature into the RBF neural network model to update the RBF neural network model.

[0075] Through this implementation method, with the use of X-ray sources, more sample data is provided for the RBF neural network model and it is trained, so that the RBF neural network model is continuously optimized and the output intensity prediction value is more accurate.

[0076] To make it easier to understand, the following will be combined with Figure 2 The specific embodiments shown further illustrate the embodiments of the present invention:

[0077] See Figure 2As shown, firstly, the sampled operating voltage and the reference voltage obtained after D / A conversion of the operating voltage setpoint (used to characterize the reference voltage setpoint), as well as the sampled filament current and the reference current obtained after D / A conversion of the filament current setpoint (used to characterize the filament current setpoint), are input into the hardware circuit including the RBF neural network model and the PID controller model. Then, operating parameters such as the operating voltage, filament current, and operating temperature are input into the RBF neural network model to obtain the predicted output intensity value of the X-ray source. Further, the PID controller model determines the control quantity corresponding to the target output intensity value based on the actual output intensity of the X-ray source, the predicted output intensity value, and the target output intensity value. Here, the control quantity is the initial target operating voltage and the initial target filament current. After obtaining the initial target operating voltage and the initial target filament current, the first difference between the reference voltage and the initial target operating voltage, and the second difference between the reference current and the initial target filament current are calculated.

[0078] Furthermore, the first difference and the second difference are compared with their respective thresholds, i.e., the magnitude of the first difference is compared with the first difference threshold, and the magnitude of the second difference is compared with the second difference threshold, to obtain the actual error. On one hand, when the actual error is characterized by the first difference being less than the first difference threshold and the second difference being less than the second difference threshold, no adjustment is made to the operating voltage and filament current. That is, the operating voltage setting is taken as the target operating voltage, and the filament current setting is taken as the target filament current. Subsequently, the FPGA (Field Programmable Gate Array) generates PWM drive signals corresponding to the operating voltage setting and the filament current setting. On the other hand, when the actual error is characterized by the first difference being greater than or equal to the first difference threshold, and / or the second difference being greater than or equal to the second difference threshold, the initial target operating voltage is taken as the target operating voltage, and the initial target filament current is taken as the target filament current. Subsequently, the FPGA generates PWM drive signals corresponding to the initial target operating voltage and the initial target filament current.

[0079] It should be noted that in practical applications, if the required PWM drive signal has a high duty cycle during filament current adjustment, it will lead to instability in the X-ray source's output intensity control system. Therefore, Figure 2The illustrated embodiment utilizes the concept of slope compensation. Specifically, when the FPGA determines that slope compensation is required, it generates a PWM slope control signal. Based on the actual scenario requirements, a primary current is configured to generate the slope signal. After sampling, a slope compensation signal is obtained. The slope generation circuit generates a corresponding slope signal based on the slope compensation signal and the PWM slope control signal. The slope signal is added to the initial target filament current by a comparator and then truncated to obtain the compensated PWM drive signal.

[0080] Furthermore, in some implementations, after comparing the first difference and the second difference, a status indication can be given based on the comparison result. Specifically, the status of the high-voltage power supply of the X-ray source can be indicated, such as being in constant voltage (CV) mode or constant current (CC) mode. Further, the status of the high-voltage power supply can be sent to the FPGA.

[0081] like Figure 2 As shown, compared with the traditional X-ray source system, the embodiment of the present invention introduces an RBF neural network model to predict the output intensity based on the actual output intensity, and combines it with a PID controller model to obtain the target operating voltage and target filament current, replacing the traditional operating voltage and filament current adjustment method. It comprehensively considers parameters such as the operating temperature of the X-ray source, making the output intensity of the X-ray source more stable and significantly improving the output accuracy of the X-ray source.

[0082] Corresponding to the aforementioned method embodiments, see [link to relevant documentation]. Figure 3 As shown, this embodiment of the invention also discloses an output intensity control system for an X-ray source, including: a signal acquisition device 31 and an adjustment control device 32.

[0083] The signal acquisition device 31 is used to acquire the actual output intensity of the X-ray source 30 and send it to the adjustment and control device 32. The adjustment and control device 32 is also connected to the X-ray source 30 to obtain the operating parameters of the X-ray source 30. The adjustment and control device 32 is used to execute the output intensity control method described in any of the foregoing method embodiments.

[0084] See also Figure 3In one specific embodiment of the present invention, the output intensity control system of the X-ray source may further include a monitoring device 33. The monitoring device 33 is connected to both the signal acquisition device 31 and the X-ray source 30. The monitoring device 33 is used to issue alarm information when it detects an abnormal operating state of the signal acquisition device 31 and / or an abnormal operating state of the X-ray source 30. For example, if the monitoring device 33 detects that the signal acquisition device 31 cannot acquire the actual output intensity of the X-ray source, it will issue an alarm information. Alternatively, if the monitoring device 33 detects that the operating temperature of the X-ray source 30 is too high, the water cooling system is abnormal, or other operating conditions are abnormal, it will issue an alarm information. In some embodiments, the monitoring device 33 may also be connected to a regulating control device 32. When the monitoring device 33 detects an abnormal state, it will send an abnormal signal to the regulating control device 32, causing the regulating control device 32 to control the X-ray source 30 to stop operating.

[0085] It should be noted that in practical applications, the monitoring device 33 is optional. The monitoring device 33 can monitor the status of each device in the X-ray source output intensity control system in real time.

[0086] More specifically, see Figure 4 As shown, Figure 4 This is a schematic diagram of the output intensity control system of another X-ray source provided in an embodiment of the present invention. Figure 4 The central adjustment and control device 32 may include: a control system 321 and a host computer 322.

[0087] The host computer 322 is used to train a preset output intensity prediction model and send the preset output intensity prediction model to the control system 321. The control system 321 is used to execute the output intensity control operation of the X-ray source, that is, to execute the output intensity control method described in any of the aforementioned method embodiments.

[0088] It should be noted that in practical applications, the training of the preset output intensity prediction model and the output intensity control can be integrated into the same control system. However, the separate design allows a single host computer 322 to train multiple preset output intensity prediction models, and the control system 321 has simpler functions, thus saving costs.

[0089] See also Figure 4 As shown, in a specific embodiment of the present invention, the signal acquisition device 31 includes: a signal receiving and reflecting device 311 and an X-ray detector 312. The signal receiving and reflecting device 311 is used to receive X-rays output from the X-ray source 31 and partially reflect them to the X-ray detector 312. The X-ray detector 312 is used to acquire the X-rays reflected by the signal receiving and reflecting device 311 and send the actual output intensity of the X-ray source it represents to the adjustment and control device 32.

[0090] In addition, to solve the heat dissipation problem, a custom-designed housing can be installed for the output intensity control system of the X-ray source. The housing is equipped with liquid cooling system, air cooling system, etc. for heat dissipation, and the housing can also avoid electronic interference.

[0091] In the foregoing description of this specification, unless otherwise expressly specified and limited, the terms "fixed," "installed," "connected," or "linked" should be interpreted broadly. For example, the term "linked" can refer to a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; or it can refer to the internal communication of two components or the interaction between two components. Therefore, unless otherwise expressly limited in this specification, those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0092] Based on the above description in this specification, those skilled in the art will also understand that terms used, such as "upper," "lower," "front," "rear," "left," "right," "length," "width," "thickness," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," "circumferential," "center," "longitudinal," "transverse," "clockwise," or "counterclockwise," are terms indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings of this specification. They are only for the purpose of facilitating the explanation of the present invention and simplifying the description, and do not imply that the devices or elements involved must have the specific orientation, or be constructed and operated in a specific orientation. Therefore, the above-mentioned orientation or positional relationship terms should not be understood or interpreted as limitations on the present invention.

[0093] Furthermore, the terms "first" or "second," etc., used in this specification to refer to numbers or ordinal numbers are for descriptive purposes only and should not be construed as indicating, explicitly or implicitly, relative importance or specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this specification, "a plurality of" means at least two, such as two, three, or more, unless otherwise explicitly specified.

[0094] While various embodiments of the invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of the invention. The appended claims are intended to define the scope of protection of the invention and therefore cover modular compositions, equivalents, or alternatives within the scope of these claims.

Claims

1. A method for controlling the output intensity of an X-ray source, characterized in that, include: The actual output intensity and operating parameters of the X-ray source are obtained. The operating parameters include: operating voltage, filament current, operating temperature, X-ray tube shape parameters, air humidity, and equipment transmission loss. The operating temperature is actually the target temperature. Since there is a corresponding relationship between the target temperature and the tube temperature, the tube temperature is used in actual applications. The X-ray tube shape is characterized by the tilt angle of the target surface and the external dimensions of the X-ray tube. The equipment transmission loss is determined by the power consumption, heat dissipation, and material temperature rise characteristics of the X-ray source. The operating voltage, filament current, operating temperature, ray tube shape parameters, air humidity, and equipment transmission loss are input into a preset output intensity prediction model to obtain the output intensity prediction value. The preset output intensity prediction model is trained based on sample data and is an RBF neural network model. The actual output intensity, the predicted output intensity, and the target output intensity of the X-ray source are input into a preset controller model to determine the target operating voltage and target filament current corresponding to the target output intensity. The preset controller model is a PID controller model. The X-ray source is controlled by the target operating voltage and the target filament current; The training process of the RBF neural network model is as follows: Acquire multiple sample data, each of which includes: historical actual output intensity, historical operating voltage, historical filament current, historical operating temperature, X-ray tube shape parameters, historical air humidity, and equipment transmission loss; For each sample data, the historical operating voltage, historical filament current, historical operating temperature, X-ray tube shape parameters, historical air humidity, and equipment transmission loss are input into the initial RBF neural network model for training, so as to obtain the historical output intensity prediction value corresponding to each sample data. This process continues until the difference between the historical actual output intensity and the corresponding historical output intensity prediction value in each sample data is less than a preset threshold. The initial RBF neural network model after training is then determined to be the RBF neural network model. The process involves inputting the actual output intensity, the predicted output intensity, and the target output intensity value of the X-ray source into a preset controller model to determine the target operating voltage and target filament current corresponding to the target output intensity value, including: The actual output intensity, the predicted output intensity, and the target output intensity of the X-ray source are input into a preset controller model to determine the initial target operating voltage and the initial target filament current corresponding to the target output intensity. Calculate the first difference between the operating voltage setting value and the initial target operating voltage, and the second difference between the filament current setting value and the initial target filament current; When the first difference is less than the first difference threshold and the second difference is less than the second difference threshold, the working voltage setting value is taken as the target working voltage and the filament current setting value is taken as the target filament current. When the first difference is greater than or equal to the first difference threshold, and / or the second difference is greater than or equal to the second difference threshold, the initial target operating voltage is taken as the target operating voltage, and the initial target filament current is taken as the target filament current.

2. The method according to claim 1, characterized in that, Controlling the X-ray source to operate using the target operating voltage and the target filament current includes: The target operating voltage and the target filament current are generated using PWM control to control the operation of the X-ray source.

3. The method according to claim 1, characterized in that, Also includes: The operating voltage, the filament current, and the operating temperature are input into the RBF neural network model to update the RBF neural network model.

4. An output intensity control system for an X-ray source, characterized in that, include: Signal acquisition device and regulation and control device; The signal acquisition device is used to acquire the actual output intensity of the X-ray source and send it to the adjustment and control device. The adjustment and control device is also connected to the X-ray source to obtain the operating parameters of the X-ray source. The adjustment and control device is used to execute the output intensity control method as described in any one of claims 1 to 3.

5. The system according to claim 4, characterized in that, Also includes: The monitoring device is connected to both the signal acquisition device and the X-ray source. The monitoring device is used to issue alarm information when it detects an abnormal working state of the signal acquisition device and / or the X-ray source.

Images