Drift correction method and device of radiation sensor, electronic equipment and storage medium

By obtaining the to-be-corrected and historical measured values ​​of the radiation sensor, and using the pre-trained radial neural network model to correct the radiation prediction value, the measurement error problem caused by the radiation sensor due to temperature drift is solved, and more accurate radiation monitoring is achieved.

CN118962772APending Publication Date: 2024-11-15GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411262069.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-10
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

When the radiation sensor monitors the radiation dose, the drift caused by temperature changes will cause measurement errors and affect the accuracy of the radiation dose value.

Method used

By obtaining the measured values ​​to be corrected and historical measured values ​​of the target radiation sensor, the pre-trained radial neural network model is used to correct the measurement error due to temperature drift.

Benefits of technology

This ensures more accurate measurement of radiation by the radiation sensor, reduces errors caused by temperature drift, and improves monitoring accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118962772A_ABST
    Figure CN118962772A_ABST
Patent Text Reader

Abstract

The invention discloses a drift correction method and device for a radiation sensor, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-corrected radiation measurement value corresponding to a target radiation sensor, and determining a historical radiation measurement value corresponding to the target sensor; determining a radiation prediction value corresponding to the to-be-corrected radiation measurement value based on the to-be-corrected radiation measurement value and the historical radiation measurement value; and processing the radiation prediction value according to a drift correction model, and determining a target radiation measurement value corresponding to the target radiation sensor. Based on the technical scheme, the predicted value corresponding to the current moment is determined according to the measured value of the radiation sensor and the historical measured value, and then the predicted value is corrected according to the drift correction model, so that measurement errors caused by temperature drift are corrected, and more accurate measurement of the sensor on radiation is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a drift correction method, device, electronic equipment and storage medium for a radiation sensor. Background Art

[0002] With the continuous development of electric power technology, in order to achieve rapid maintenance of gas-insulated metal-enclosed switchgear, X-ray imaging of the gas-insulated metal-enclosed switchgear is usually performed to achieve maintenance of the gas-insulated metal-enclosed switchgear.

[0003] In order to ensure the safety of workers during the imaging process, radiation sensors are used to monitor the radiation dose in the working area. However, the radiation sensors in the radiation dose monitoring device are affected by radiation exposure and will experience obvious temperature changes, causing radiation measurement errors. As a result, there is an error between the radiation dose value displayed in the background and the actual true value, that is, the radiation sensor has temperature drift. Summary of the invention

[0004] The present invention provides a drift correction method, device, electronic device and storage medium for a radiation sensor, which determines a predicted value corresponding to the current moment based on the measured value and historical measured value of the radiation sensor, and then corrects the predicted value according to a drift correction model, thereby correcting the measurement error caused by temperature drift.

[0005] According to one aspect of the present invention, a drift correction method for a radiation sensor is provided, comprising:

[0006] Acquire a radiation measurement value to be corrected corresponding to a target radiation sensor, and determine a historical radiation measurement value corresponding to the target sensor;

[0007] Determine a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value;

[0008] The radiation prediction value is processed according to a drift correction model to determine a target radiation measurement value corresponding to the target radiation sensor, wherein the drift correction model is a radial neural network model obtained by pre-training for correcting sensor temperature offset.

[0009] According to another aspect of the present invention, there is provided a drift correction device for a radiation sensor, comprising:

[0010] A data acquisition module, used to acquire the radiation measurement value to be corrected corresponding to the target radiation sensor, and determine the historical radiation measurement value corresponding to the target sensor;

[0011] A data prediction module, used to determine a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value;

[0012] The target data determination module is used to process the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor, wherein the drift correction model is a radial neural network model pre-trained to correct sensor temperature offset.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the drift correction method for the radiation sensor described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the drift correction method for a radiation sensor described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the radiation measurement value to be corrected corresponding to the target radiation sensor, and determines the historical radiation measurement value corresponding to the target sensor, and then determines the radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value, and finally processes the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor. Based on the above technical solution, by determining the prediction value corresponding to the current moment according to the measurement value and the historical measurement value of the radiation sensor, and then correcting the prediction value according to the drift correction model, the measurement error caused by temperature drift is corrected, ensuring that the sensor measures radiation more accurately.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a flow chart of a drift correction method for a radiation sensor provided by an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of the structure of a drift correction model provided by an embodiment of the present invention;

[0023] Figure 3 is a structural block diagram of a drift correction device for a radiation sensor provided by an embodiment of the present invention;

[0024] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1This is a flow chart of a method for correcting drift of a radiation sensor provided by an embodiment of the present invention. This embodiment can be applied to correct inaccurate measurement values ​​due to temperature offset based on the measurement values ​​collected by the radiation sensor and historical measurement values ​​when overhauling gas-insulated metal-enclosed switchgear. This method can be performed by a drift correction device for the radiation sensor. The drift correction device for the radiation sensor can be implemented in the form of hardware and / or software. The drift correction device for the radiation sensor can be configured in an electronic device, which can be a terminal device or a server, etc. Figure 1 As shown, the method includes:

[0029] S110, obtaining a radiation measurement value to be corrected corresponding to a target radiation sensor, and determining a historical radiation measurement value corresponding to the target sensor.

[0030] The target radiation sensor may be a pre-set sensor for monitoring the radiation dose in the working area, for example, the target radiation sensor may be an X-ray gas detector. The radiation measurement value to be corrected may be understood as a measurement value corresponding to the current moment collected by the radiation sensor. The historical radiation measurement value may be a corrected radiation measurement value at the previous moment. It should be noted that the number of target radiation sensors in the embodiment of the present invention is at least two, that is, at least two radiation sensors are set in the working area.

[0031] Specifically, the radiation measurement value to be corrected corresponding to the target radiation sensor is obtained, and the historical radiation measurement value corresponding to the target sensor is determined. For example, the current radiation measurement value can be directly obtained from the target sensor in real time and the real-time obtained radiation measurement value can be recorded as the radiation measurement value to be corrected. When determining the historical radiation measurement value, the historical radiation measurement value corresponding to the target sensor can be obtained by querying a database. The query conditions can include a unique identifier of the target radiation sensor and corresponding timestamp information. For example, when the target radiation sensor collects radiation measurement values ​​in a working cycle, the historical radiation measurement values ​​can be queried in the database according to the working cycle, and then the data that completely matches the target sensor can be filtered out from the collected data.

[0032] S120. Determine a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value.

[0033] The radiation prediction value may be understood as the measured value after the radiation value to be corrected is corrected.

[0034] Specifically, after obtaining the radiation measurement value to be corrected and the historical radiation measurement value, the corresponding radiation prediction value can be calculated according to a preset data prediction method. For example, the radiation prediction value corresponding to the radiation measurement value to be corrected can be calculated using a simple moving average, a weighted moving average, an exponential smoothing or an autoregressive model. It should be noted that for the calculation methods of simple moving average, weighted moving average and exponential smoothing, it is necessary to pre-select the time window size or the smoothing coefficient, and the staff can set the time window size or the smoothing coefficient according to their needs.

[0035] On the basis of the above technical solution, the method of determining the radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value includes: determining the initial state estimation matrix and the initial error covariance matrix corresponding to the target radiation sensor based on the historical radiation measurement values; determining the state estimation prediction matrix and the covariance prediction matrix corresponding to the radiation measurement value to be corrected based on the initial state estimation value and the initial error covariance matrix; and determining the radiation prediction value based on the state estimation prediction matrix and the covariance prediction matrix.

[0036] Among them, the initial state estimation matrix can be understood as the initial estimate of the radiation intensity. The initial error covariance matrix can be a matrix used to describe the uncertainty of each element in the initial state estimate. The state estimation prediction matrix is ​​the prediction of the system state at the future moment calculated by the Kalman filter based on the dynamic model of the system (i.e., the state transfer equation) and the state estimate of the previous moment. The covariance prediction matrix is ​​a matrix used by the Kalman filter to describe the uncertainty of the predicted state vector, which contains the covariance information of the estimated errors between each element in the predicted state vector.

[0037] It should be noted that in X-ray gas detectors, Kalman filtering can be used to reduce and correct measurement errors caused by temperature drift. The Kalman filter first predicts the state of the radiation amplitude at the next moment based on the current state of the radiation sensor and the entire system model, and then uses the newly measured radiation data to correct the predicted system model state to obtain a more accurate estimate.

[0038] Specifically, the mathematical model of the Kalman filter algorithm is divided into a state transition model and a measurement model. Assuming that the system state is represented by vector x and the measurement value is represented by vector z, the state transition model and measurement model of the system are: k =Fx k-1 +Bu k +w k , z k =Hx k +v k, where F is the state transfer matrix, B is the control input matrix, H is the measurement matrix, and w k and v k They are process noise and measurement noise respectively, xk is the state at time k, that is, the radiation intensity measurement value collected by the radiation sensor, assuming that the process noise and measurement noise are zero-mean Gaussian white noise, and the covariance matrices are Q and R respectively. Then, in the calculation process, the covariance matrix and state estimation matrix are initialized first, and the next step is to predict the state of the radiation sensor and the covariance matrix of the radiation amplitude, that is, the state estimation prediction matrix Covariance prediction matrix P k|k-1 =FP k-1|k-1 F T +Q.

[0039] On the basis of the above technical solution, the radiation prediction value is determined based on the state estimation prediction matrix and the covariance prediction matrix, including: determining the target sensor state matrix and the target radiation amplitude covariance matrix corresponding to the radiation measurement value to be corrected according to the state estimation prediction matrix and the covariance prediction matrix; determining the radiation prediction value based on the target sensor state matrix and the target radiation amplitude covariance matrix.

[0040] Among them, the target sensor state matrix can be understood as the state matrix obtained by further updating the state estimation prediction matrix. Correspondingly, the target radiation amplitude covariance matrix is ​​the amplitude covariance matrix obtained by further updating the covariance prediction matrix.

[0041] Specifically, after determining the state estimation prediction matrix and the covariance prediction matrix, the radiation sensor state and the covariance matrix are updated to obtain K k =P k|k-1 H T (HP k|k-1 H T +R) -1 , and P k|k =(IK k H)P k|k-1 , where K k To calculate the Kalman gain, and P k|k is the updated sensor state matrix and radiation amplitude covariance matrix.

[0042] S130: Process the radiation prediction value according to the drift correction model to determine a target radiation measurement value corresponding to the target radiation sensor.

[0043] The drift correction model is a pre-trained radial neural network model used to correct the temperature offset of the sensor. The target radiation measurement value can be understood as the radiation measurement value output by the drift correction model according to the radiation prediction value.

[0044] Specifically, the radiation prediction value is processed according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor. For example, the radiation prediction value can be used as the input of the drift correction model, and then the data corresponding to the radiation prediction value generated by the drift correction model is obtained and used as the target radiation measurement value.

[0045] It should be noted that when using the drift correction model, the model needs to be trained first to obtain a drift correction model that meets the requirements. For example, a set of training data containing the radiation measurement values ​​of the sensor under different conditions and their corresponding environmental parameters (such as temperature, humidity, etc.) is collected. The above data will be used to train the drift correction model, and the radial neural network model is trained using the collected training data. The goal of the drift correction model is to learn the data mapping relationship between the input parameters (such as the original measurement value of the sensor, the ambient temperature, etc.) and the output parameters (i.e., the corrected radiation measurement value). After the Kalman filter predicts the radiation value, the radiation prediction value is used as input and passed to the trained drift correction model. The drift correction model calculates the corrected radiation measurement value based on the input data.

[0046] On the basis of the above technical solution, the radiation prediction value is processed according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor, including: determining the radiation prediction difference based on the radiation prediction value, and inputting the radiation prediction value and the radiation prediction difference into the drift correction model; obtaining the output result of the drift correction model corresponding to the target radiation sensor, and using the output result as the target radiation measurement value.

[0047] The radiation prediction difference may be understood as the difference between the radiation prediction values ​​corresponding to the two radiation sensors.

[0048] Specifically, an RBF neural network model is established, using the temperature of two acquisition sensors and the temperature difference between them as the input of the RBF neural network, and the corresponding standard X-ray radiation value as the output of the RBF neural network. The number of nodes in the input layer, hidden layer, and output layer of the RBF neural network adopts a 3:7:1 ratio structure. Assuming that there is only one node in the output layer, the radial basis function network can be regarded as a special case of linear regression, that is, Among them,: the number of hidden layer nodes is 7; N is the number of input training samples; ω αi ,ω βi ,ω λiThey are respectively from hidden unit to input unit to α i (n), β i (n), λ i (n) is the weight; d(n) is the expected output of the model, e(n) is the error; α i (n), β i (n), λ i (n) is the regression factor of the model, which is the response of the network under a certain basis function. In this case, the basis function is a Gaussian function, which is: Among them, α i , β i ,λ i are the temperature of the two acquisition sensors and the temperature difference between them respectively; i , β i ,λ i As input, t i is the output of the i-th hidden unit, and the weights are obtained through multiple training. After the RBF radial neural network training is completed, the weights ω αi ,ω βi ,ω λi is a constant. Substituting it into the first formula, we can get the radiation measurement value in the current environment. During the formal measurement, the temperatures of the two acquisition sensors are used as the input of the model, and the output of the model, that is, the radiation measurement value in the current environment, can be obtained.

[0049] On the basis of the above technical solution, the drift correction model includes an input layer, a hidden layer and an output layer; the output result corresponding to the target radiation sensor output by the drift correction model includes: obtaining the radiation prediction value and the radiation prediction difference through the input layer; performing spatial mapping transformation on the radiation prediction value and the radiation prediction difference according to a Gaussian function through the hidden layer; and weighting the spatial mapping transformation result according to a linear function through the output layer to determine the output result.

[0050] Specifically, Figure 2 As shown, the radial basis neural network consists of three layers: the first layer is the input layer, the number of nodes is the same as the dimension of the input data, and only the data information is transmitted without any transformation; the second layer is the hidden layer, the number of nodes is determined according to the complexity of the problem, and the Gaussian function is used as the kernel function to perform spatial mapping transformation on the input data; the third layer is the output layer, the number of nodes is the same as the dimension of the output data, and a linear function is used to linearly weight the output information of the hidden layer to generate the final result. It should be noted that in the technical solution provided in the embodiment of the present invention, the ratio of nodes in the input layer, hidden layer and output layer of the drift correction model is 3:7:1.

[0051] On the basis of the above technical solution, after determining the target radiation measurement value corresponding to the target radiation sensor, it also includes: sending the target radiation measurement value to a main controller so that the main controller displays the target radiation measurement value.

[0052] The main controller may be understood as a main control device when the gas-insulated metal-enclosed switchgear is being repaired.

[0053] Specifically, when the X-ray imager starts working, the staff will detect the X-ray radiation dose in the designated safe area. During the detection process, they are easily irradiated, which may cause physical harm. The radiation dose in the working area can be detected by setting up multiple radiation sensors. The working area may be (high-voltage site, high-voltage room, main control building, work corridor, etc.). After the radiation dose is collected by the sensor in the detection device and processed by Kalman filtering and radial neural network model, the measured radiation dose is displayed on the background main control.

[0054] The technical solution of the embodiment of the present invention obtains the radiation measurement value to be corrected corresponding to the target radiation sensor, and determines the historical radiation measurement value corresponding to the target sensor, and then determines the radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value, and finally processes the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor. Based on the above technical solution, by determining the prediction value corresponding to the current moment according to the measurement value and the historical measurement value of the radiation sensor, and then correcting the prediction value according to the drift correction model, the measurement error caused by temperature drift is corrected, ensuring that the sensor measures radiation more accurately.

[0055] Embodiment 2

[0056] Figure 3 This is a structural block diagram of a drift correction device for a radiation sensor provided by an embodiment of the present invention. Figure 3 As shown, the device includes: a data acquisition module 310, a data prediction module 320 and a target data determination module 330.

[0057] The data acquisition module 310 is used to acquire the radiation measurement value to be corrected corresponding to the target radiation sensor and determine the historical radiation measurement value corresponding to the target sensor;

[0058] A data prediction module 320, configured to determine a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value;

[0059] The target data determination module 330 is used to process the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor, wherein the drift correction model is a radial neural network model pre-trained to correct sensor temperature offset.

[0060] On the basis of the above technical solution, the data prediction module is used to determine the initial state estimation matrix and the initial error covariance matrix corresponding to the target radiation sensor based on the historical radiation measurement values; determine the state estimation prediction matrix and the covariance prediction matrix corresponding to the radiation measurement values ​​to be corrected based on the initial state estimation values ​​and the initial error covariance matrix; and determine the radiation prediction value based on the state estimation prediction matrix and the covariance prediction matrix.

[0061] On the basis of the above technical solution, the data prediction module is used to determine the target sensor state matrix and the target radiation amplitude covariance matrix corresponding to the radiation measurement value to be corrected according to the state estimation prediction matrix and the covariance prediction matrix; and determine the radiation prediction value based on the target sensor state matrix and the target radiation amplitude covariance matrix.

[0062] Based on the above technical solution, the target data determination module is used to determine the radiation prediction difference based on the radiation prediction value, and input the radiation prediction value and the radiation prediction difference into the drift correction model; obtain the output result of the drift correction model corresponding to the target radiation sensor, and use the output result as the target radiation measurement value.

[0063] Based on the above technical solution, the drift correction model includes an input layer, a hidden layer and an output layer; the target data determination module is used to obtain the radiation prediction value and the radiation prediction difference through the input layer; the radiation prediction value and the radiation prediction difference are spatially mapped and transformed according to a Gaussian function through the hidden layer; and the spatial mapping transformation result is weighted according to a linear function through the output layer to determine the output result.

[0064] Based on the above technical solution, the ratio of nodes in the input layer, the hidden layer and the output layer is 3:7:1.

[0065] On the basis of the above technical solution, the device further includes a display module, which is used to send the target radiation measurement value to a main controller so that the main controller displays the target radiation measurement value.

[0066] The technical solution of the embodiment of the present invention obtains the radiation measurement value to be corrected corresponding to the target radiation sensor, and determines the historical radiation measurement value corresponding to the target sensor, and then determines the radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value, and finally processes the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor. Based on the above technical solution, by determining the prediction value corresponding to the current moment according to the measurement value and the historical measurement value of the radiation sensor, and then correcting the prediction value according to the drift correction model, the measurement error caused by temperature drift is corrected, ensuring that the sensor measures radiation more accurately.

[0067] The drift correction device for a radiation sensor provided in an embodiment of the present invention can execute the drift correction method for a radiation sensor provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0068] Embodiment 3

[0069] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0070] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0071] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0072] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a drift correction method for a radiation sensor.

[0073] In some embodiments, the drift correction method of the radiation sensor may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the drift correction method of the radiation sensor described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the drift correction method of the radiation sensor in any other appropriate manner (e.g., by means of firmware).

[0074] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0076] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0077] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0078] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0079] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0080] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0081] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for correcting drift of a radiation sensor, characterized in that: include: Acquire a radiation measurement value to be corrected corresponding to a target radiation sensor, and determine a historical radiation measurement value corresponding to the target sensor; Determine a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value; The radiation prediction value is processed according to a drift correction model to determine a target radiation measurement value corresponding to the target radiation sensor, wherein the drift correction model is a radial neural network model obtained by pre-training for correcting sensor temperature offset.

2. The method according to claim 1, characterized in that The step of determining a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value comprises: Determine an initial state estimation matrix and an initial error covariance matrix corresponding to the target radiation sensor based on the historical radiation measurement values; Determine a state estimation prediction matrix and a covariance prediction matrix corresponding to the radiation measurement value to be corrected based on the initial state estimation value and the initial error covariance matrix; The radiation prediction value is determined based on the state estimation prediction matrix and the covariance prediction matrix.

3. The method according to claim 2, characterized in that The determining the radiation prediction value based on the state estimation prediction matrix and the covariance prediction matrix includes: Determine a target sensor state matrix and a target radiation amplitude covariance matrix corresponding to the radiation measurement value to be corrected according to the state estimation prediction matrix and the covariance prediction matrix; The radiation prediction value is determined based on the target sensor state matrix and the target radiation amplitude covariance matrix.

4. The method according to claim 1, characterized in that: The step of processing the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor includes: Determine a radiation prediction difference based on the radiation prediction value, and input the radiation prediction value and the radiation prediction difference into the drift correction model; An output result of the drift correction model corresponding to the target radiation sensor is obtained, and the output result is used as the target radiation measurement value.

5. The method according to claim 4, characterized in that The drift correction model includes an input layer, a hidden layer and an output layer; The obtaining the output result of the drift correction model corresponding to the target radiation sensor includes: Acquire the radiation prediction value and the radiation prediction difference through the input layer; Performing spatial mapping transformation on the radiation prediction value and the radiation prediction difference value according to a Gaussian function through the hidden layer; The output layer weights the spatial mapping transformation result according to a linear function to determine the output result.

6. The method according to claim 5, characterized in that The ratio of nodes in the input layer, the hidden layer and the output layer is 3:7:

1.

7. The method according to claim 1, characterized in that After determining the target radiation measurement value corresponding to the target radiation sensor, the method further includes: The target radiation measurement value is sent to a main controller so that the main controller displays the target radiation measurement value.

8. A drift correction device for a radiation sensor, characterized in that: include: A data acquisition module, used to acquire the radiation measurement value to be corrected corresponding to the target radiation sensor, and determine the historical radiation measurement value corresponding to the target sensor; A data prediction module, used to determine a radiation prediction value corresponding to the radiation measurement value to be corrected based on the radiation measurement value to be corrected and the historical radiation measurement value; The target data determination module is used to process the radiation prediction value according to the drift correction model to determine the target radiation measurement value corresponding to the target radiation sensor, wherein the drift correction model is a radial neural network model pre-trained to correct sensor temperature offset.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so as to enable the at least one processor to perform the drift correction method for the radiation sensor according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the drift correction method for a radiation sensor according to any one of claims 1 to 7 when executed.