Compensation method, device and equipment for radiation monitoring data of nuclear containment vessel

Abstract

The invention discloses a compensation method, device and equipment for radiation monitoring data of a nuclear safety shell, and relates to the field of nuclear safety. The method comprises the following steps: acquiring sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point; constructing a four-dimensional tensor according to the sensor data and the timestamp, and decomposing the four-dimensional tensor to obtain a corresponding factor matrix and a corresponding coupling strength vector; determining a coupling interference variable according to the temperature factor matrix, the humidity factor matrix, the pressure factor matrix and the coupling strength vector; and performing compensation conversion processing on the gamma radiation counting rate according to the coupling interference variable to obtain a radiation detection result of the nuclear containment. According to the method, real-time separation of multi-parameter interference is realized, the compensation error during synchronous sudden change of the temperature and the humidity can be greatly reduced, the accuracy of a detection result is ensured, meanwhile, the height measurement precision can also be ensured under an extreme working condition, and the method has better adaptability and stability.

Description

Technical Field

[0001] This application relates to the field of nuclear safety technology, and in particular to a method, apparatus and equipment for compensating radiation monitoring data of a nuclear containment structure. Background Technology

[0002] In the field of radiation monitoring within nuclear power plant containment structures, high temperature and humidity environments pose a serious threat to the accuracy of measurement data. Existing technologies typically employ single-parameter compensation mechanisms to address the interference caused by these environments, or utilize hardware anti-interference designs. However, under accident conditions, temperature, humidity, and pressure within the containment structure exhibit strongly coupled nonlinear changes. Existing technologies lead to simultaneous signal attenuation and noise increases. For example, rising temperature causes a decrease in detector sensitivity, and humidity levels exceeding 95% cause an increase in the gamma background count, resulting in a deterioration in the signal-to-noise ratio. Furthermore, the coupling effect of thermal expansion of concrete and moisture expansion of metal components further distorts the spatial distribution of the radiation field due to detector positioning deviation. In addition, temperature compensation requires a response time on the order of seconds, while humidity transmission model updates require calculations on the order of minutes. This timescale mismatch leads to overcompensation, causing timing conflicts and unresolved cross-interference issues.

[0003] Therefore, there is an urgent need to develop a new compensation method to fundamentally break through the technical bottleneck of parameter coupling. Summary of the Invention

[0004] The purpose of this application is to address at least one of the aforementioned technical deficiencies.

[0005] On the one hand, embodiments of this application provide a method for compensating radiation monitoring data of a nuclear containment structure, the method comprising: Acquire sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point. The sensor data includes... c Radiation count rate, surface temperature, ambient humidity, and containment pressure; A four-dimensional tensor is constructed based on sensor data and timestamps, and the four-dimensional tensor is decomposed to obtain the corresponding factor matrix and coupling strength vector. The factor matrix includes temperature factor matrix, humidity factor matrix and pressure factor matrix. The coupling interference amount is determined based on the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector. Based on the coupling interference amount c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

[0006] Optionally, acquire sensor data corresponding to at least one set time point, including: Acquire raw sensor data corresponding to at least one set time point. The raw sensor data includes raw... c Radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure; For the original c The radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure were normalized to obtain sensor data.

[0007] Optionally, a four-dimensional tensor can be constructed based on sensor data and timestamps, including: The surface temperature value, ambient humidity value, and containment pressure value are dynamically discretized and divided into gears to obtain the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. For each time point, the environmental gear corresponding to the time point is determined based on the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. according to c The radiation count rate and the corresponding environmental level at each time point are used to fill the tensor to obtain a four-dimensional tensor.

[0008] Optionally, the four-dimensional tensor can be decomposed to obtain the corresponding factor matrix and coupling strength vector, including: Obtain the preset rank matrix, the set of initialized factor matrices, and the initial weight vector matrix. The set of initialized factor matrices includes the initialized time factor matrix, the initialized temperature factor matrix, the initialized humidity factor matrix, and the initialized pressure factor matrix. The four-dimensional tensor is iteratively updated and decomposed based on the rank matrix, the set of initial factor matrices, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector.

[0009] Optionally, the four-dimensional tensor is iteratively updated and decomposed based on the rank matrix, the initial set of factor matrices, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector, including: For each type of sensor data, the initialization factor matrices in the initialization factor matrix set, except for the initialization factor matrix corresponding to the type of sensor data, are fixed, and the Lekronek product is determined based on the fixed factor matrices in the initialization factor matrix set. Expand the dimensions of the sensor data corresponding to the type in the four-dimensional tensor to obtain the expanded matrix, and determine the least squares matrix based on the expanded matrix and the Lekronek product; Based on the least squares matrix and the initial weight vector matrix, the factor matrix corresponding to the type of sensor data is obtained.

[0010] Optionally, based on the amount of coupling interference... c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment structure, including: according to c The radiation count rate is denormalized to obtain the denormalized value; The radiation detection results of the nuclear containment structure are obtained by scaling the inverse normalized value based on the coupling interference quantity.

[0011] Optionally, after obtaining the radiation detection results of the nuclear containment structure, the following may also be included: If the ambient humidity value is greater than the preset humidity threshold, the humidity compensation amount is determined based on the ambient humidity value. The radiation detection results of the nuclear containment structure are compensated based on the humidity compensation amount to obtain the final radiation detection results of the nuclear containment structure.

[0012] Optionally, after obtaining the radiation detection results of the nuclear containment structure, the following may also be included: Obtain the current ambient temperature value, and determine the sensitivity coefficient based on the radiation detection results and the current ambient temperature value; The temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector are updated based on the sensitivity coefficients, resulting in the updated temperature factor matrix, updated humidity factor matrix, updated pressure factor matrix, and updated coupling strength vector. The set obtained by combining the updated temperature factor matrix, the updated humidity factor matrix, and the updated pressure factor matrix is ​​used as the initial factor matrix set, and the updated coupling strength vector is used as the initial weight vector matrix.

[0013] On the other hand, embodiments of this application provide a compensation device for radiation monitoring data of a nuclear containment structure, comprising: The data acquisition module is used to acquire sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point. The sensor data includes... c Radiation count rate, surface temperature, ambient humidity, and containment pressure; The tensor construction module is used to construct a four-dimensional tensor based on sensor data and timestamps, and decompose the four-dimensional tensor to obtain the corresponding factor matrix and coupling strength vector. The factor matrix includes a temperature factor matrix, a humidity factor matrix, and a pressure factor matrix. The interference determination module is used to determine the coupling interference based on the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector. The result determination module is used to determine the coupling interference amount. c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

[0014] In another aspect, embodiments of this application provide an electronic device, including a processor and a memory: The memory is configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform any of the methods in a method for compensating radiation monitoring data from a nuclear containment facility.

[0015] The beneficial effects of the technical solutions provided in this application include at least the following: In this application, a four-dimensional radiation response matrix (i.e., a four-dimensional tensor) can be constructed based on the acquired sensor data. This four-dimensional tensor fully describes the environment-radiation coupling relationship, thus laying the data structure foundation for subsequent accurate decoupling. Correspondingly, the obtained four-dimensional tensor can be decomposed to extract factor matrices of temperature, humidity, and pressure (i.e., pure interference modes), achieving real-time separation of multi-parameter interference. Furthermore, the coupling interference amount is determined based on the obtained factor matrix to compensate and convert the detected gamma radiation count rate, thereby obtaining the radiation detection results of the nuclear containment structure. This process significantly reduces the compensation error during synchronous abrupt changes in temperature and humidity, ensuring the accuracy of the detection results. Simultaneously, it maintains high measurement accuracy even under extreme operating conditions, exhibiting better adaptability and stability.

[0016] Furthermore, the sensitivity coefficient determined in this application is essentially a transfer function of the radiation measurement system to environmental parameters. Its accurate calibration and dynamic update are the core of achieving multi-parameter decoupling. At this time, updating the factor matrix and weight matrix corresponding to the data of each type of sensor based on the determined sensitivity coefficient can correct detector gain drift, suppress background noise and aerosol loss, and at the same time offset the geometric error caused by containment deformation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for compensating radiation monitoring data from a nuclear containment structure, provided as an embodiment of this application; Figure 2 A flowchart illustrating another method for compensating radiation monitoring data of a nuclear containment structure provided in this application embodiment; Figure 3 A schematic diagram of a compensation device for radiation monitoring data of a nuclear containment structure provided in an embodiment of this application; Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting the invention.

[0020] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0022] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0023] Specifically, such as Figure 1 As shown, the method may include: Step S101: Obtain sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point. The sensor data includes... c Radiation count rate, surface temperature, ambient humidity, and containment pressure.

[0024] The set time point refers to the time point at which sensor data needs to be collected. In practical applications, data collection is generally performed once every 5 seconds and the scheme in this application is executed. At this time, at least one set time point refers to every second within these 5 seconds.

[0025] Optionally, the collected sensor data includes c Radiation count rate, surface temperature, ambient humidity, and containment pressure, along with a timestamp representing each time point. c Radiation count rate can be based on the radiation deployed at the center of the shield. c The X-ray detector collects the data. c The radiation count rate includes units per second (i.e., per point in time). c Radiation count rate, c The X-ray detector uses a silicon photomultiplier tube (SiPM), which provides better resistance to external interference. Surface temperature and ambient humidity values ​​are obtained through temperature and humidity sensors deployed on the outside of the vacuum insulation layer. These values ​​include temperature and humidity values ​​per second (i.e., at each time point). The temperature and humidity sensors include capacitive hygrometers and platinum resistance thermometers. The pressure value inside the containment is collected by strain sensors deployed on the inner wall of the containment. These pressure values ​​include pressure values ​​per second (i.e., at each time point). The strain sensor is a MEMS resonant pressure sensor, which can directly output pressure values ​​through frequency changes, thereby avoiding the influence of temperature drift. Fiber Bragg gratings (FBGs) are used to resist electromagnetic interference.

[0026] In an optional embodiment of this application, acquiring sensor data corresponding to at least one set time point includes: Acquire raw sensor data corresponding to at least one set time point. The raw sensor data includes raw... c Radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure; For the original c The radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure were normalized to obtain sensor data.

[0027] Optionally, data acquired directly from sensors is discrete and unnormalized. Directly processing this data could lead to inaccurate data and complex computations. Therefore, for raw data acquired directly from sensors... c Radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure can be used to analyze the raw... c The radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure are normalized to obtain the sensor data. The normalization process can be determined based on the following formula: X norm = (X-μX ) / σX in, X norm For sensor data, XFor raw sensor data, μX This is the average value of the data over the previous 10 minutes. σX This represents the standard deviation of the data within the first 10 minutes.

[0028] Step S102: Construct a four-dimensional tensor based on sensor data and timestamps, and decompose the four-dimensional tensor to obtain the corresponding factor matrix and coupling strength vector. The factor matrix includes a temperature factor matrix, a humidity factor matrix, and a pressure factor matrix.

[0029] In optional embodiments of this application, a four-dimensional tensor is constructed based on sensor data and timestamps, including: The surface temperature value, ambient humidity value, and containment pressure value are dynamically discretized and divided into gears to obtain the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. For each time point, the environmental gear corresponding to the time point is determined based on the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. according to c The radiation count rate and the corresponding environmental level at each time point are used to fill the tensor to obtain a four-dimensional tensor.

[0030] Optionally, the obtained surface temperature value, ambient humidity value, and containment pressure value can be mapped to discrete gears to obtain the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value.

[0031] For example: For the surface temperature parameter, when the surface temperature value is <60℃, it is level 1 (low temperature), corresponding to index 1, and the surface temperature value is... The setting is 2 (medium temperature), corresponding to index 3, and the surface temperature value is... The temperature setting is 3 (high temperature), corresponding to index 2. When the temperature value is ≥80℃, it is setting 4 (ultra-high temperature), corresponding to index 4. For the ambient humidity parameter, when the ambient humidity value is <70%, it is setting 1 (low humidity), corresponding to index 1. When the ambient humidity value is 70% ≤... HWhen the humidity is <85%, it is position 2 (medium humidity), corresponding to index 3; when the ambient humidity is 85%≤H<95%, it is position 3 (high humidity), corresponding to index 2; when the surface temperature is ≥95%, it is position 4 (saturated humidity), corresponding to index 4. For the containment pressure parameter, when the containment pressure is <0.2MPa, it is position 1 (negative pressure), corresponding to index 1; when the containment pressure is 0.2MPa≤P<0.3MPa, it is position 2 (normal pressure), corresponding to index 3; when the containment pressure is 0.3MPa≤P<0.4MPa, it is position 3 (medium-high pressure), corresponding to index 2; when the containment pressure is ≥0.4MPa-0.4MPa, it is position 4 (ultra-high pressure), corresponding to index 4.

[0032] Optionally, the four-dimensional tensor structure can be represented as It includes a time dimension and an environment dimension. The time dimension is the latest 5 seconds of sensor data contained in the sliding window (index 1 = current second, index 5 = 4 seconds ago). The environment dimension consists of 4×4×4=64 environmental units composed of temperature × humidity × pressure.

[0033] Furthermore, the four-dimensional tensor can be filled, at which point in time... The environmental gear level at a given time point can be determined based on the gear level index corresponding to the determined surface temperature value, the gear level index corresponding to the ambient humidity value, and the gear level index corresponding to the containment pressure value. i T , i H , i P Then, based on the obtained c The radiation count rate and the corresponding environmental level at each time point are used to fill the tensor to obtain this four-dimensional tensor. Each element in this four-dimensional tensor... [ t , i T , i H , i P [This represents the average radiative response under a specific environmental combination.] In practical applications, four-dimensional tensors can be constructed using FPGA (Field-Programmable Gate Array) parallel pipeline modules. The FPGA parallel pipeline modules are configured to synchronously perform data normalization, discretization and tensor filling, while sparse storage units are configured and non-zero tensor units are stored in CSR (Control and Status Register) format, thereby improving the data compression rate.

[0034] In this application, the acquired sensor data can be normalized, that is, the multi-source data can be spatiotemporally aligned, thereby solving the problem of asynchronous timing. At the same time, the continuous sensor parameters are converted into tensor indices, and the state is discretized and filled into tensors to construct a four-dimensional radiation response matrix (i.e., a four-dimensional tensor). This four-dimensional tensor completely describes the environment-radiation coupling relationship, laying the data structure foundation for subsequent accurate decoupling.

[0035] In an optional embodiment of this application, the four-dimensional tensor is decomposed to obtain the corresponding factor matrix and coupling strength vector, including: Obtain the preset rank matrix, the set of initialized factor matrices, and the initial weight vector matrix. The set of initialized factor matrices includes the initialized time factor matrix, the initialized temperature factor matrix, the initialized humidity factor matrix, and the initialized pressure factor matrix. The four-dimensional tensor is iteratively updated and decomposed based on the rank matrix, the set of initial factor matrices, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector.

[0036] Optionally, a preset rank matrix, an initialization factor matrix set, and an initial weight vector matrix can be obtained. The initialization factor matrix set includes an initialization time factor matrix, an initialization temperature factor matrix, an initialization humidity factor matrix, and an initialization pressure factor matrix. The initialization time factor matrix, initialization temperature factor matrix, initialization humidity factor matrix, initialization pressure factor matrix, and initial weight vector matrix are the time factor matrix, temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector obtained in the previous cycle of executing the scheme in this application.

[0037] Furthermore, the four-dimensional tensor can be iteratively updated and decomposed using alternating least squares (ALS) based on the rank matrix, initialization factor matrix, and initial weight vector matrix to obtain the time factor matrix, temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector.

[0038] In optional embodiments of this application, the four-dimensional tensor is iteratively updated and decomposed based on the rank matrix, the initial factor matrix set, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector, including: For each type of sensor data, the initialization factor matrices in the initialization factor matrix set, except for the initialization factor matrix corresponding to that type of sensor data, are fixed, and the Lekronek product is determined based on the fixed factor matrices in the initialization factor matrix set. Expand the dimensions of the four-dimensional tensor corresponding to this type of sensor data to obtain the expanded matrix, and determine the least squares matrix based on the expanded matrix and the Lekronek product; Based on the least squares matrix and the initial weight vector matrix, the factor matrix corresponding to the type of sensor data is obtained.

[0039] Optionally, each type of sensor data corresponds to a factor matrix. For example, surface temperature values ​​correspond to a temperature factor matrix, ambient humidity values ​​correspond to a humidity factor matrix, containment pressure values ​​correspond to a pressure factor matrix, and the acquired timestamps correspond to a time factor matrix.

[0040] Furthermore, for each type of sensor data, the initialization factor matrix set can be fixed if it does not correspond to the sensor data of that type. Then, the Lekronek product is determined based on the fixed factor matrices in the initialization factor matrix set. Correspondingly, the dimension in the four-dimensional tensor corresponding to that type of sensor data is expanded to obtain the expanded matrix. Then, the least squares problem is solved based on the expanded matrix and the Lekronek product to obtain the least squares matrix. Finally, each column of the least squares matrix is ​​normalized, and the norm before normalization is multiplied into the initial weight vector matrix to obtain the factor matrix corresponding to that type of sensor data.

[0041] For example, to update the temperature factor matrix A (temp) For example, the initialization factor matrices corresponding to other types of data in the initialization factor matrix set can be fixed, that is, the initialization time factor matrix A can be fixed. (time) Initialize the humidity factor matrix A (hum) and initial pressure factor matrix A (press) Fix it, and then construct the Khatri-Rao product: K=A (hum) ⊙A (press) ⊙A (time) Where ⊙⊙ represents the Khatri-Rao product (i.e., the Kronecker product).

[0042] Furthermore, the four-dimensional tensor Expanding along the temperature dimension yields the expanded matrix. Then, solve the least squares problem to obtain the least squares matrix: A (temp) =X (temp) ·K·(K T K) † Here, † represents pseudo-inverse processing.

[0043] Correspondingly, for A (temp) Normalize each column and multiply the norm before normalization by the initial weight vector matrix. l rFrom this, we obtain the temperature factor matrix. Similarly, we sequentially obtain the humidity factor matrix, pressure factor matrix, and time factor matrix to obtain the final decomposition result.

[0044] Step S103: Determine the coupling interference amount based on the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector.

[0045] Optionally, the coupling interference can be determined based on the following formula:

[0046] in, This is the amount of coupling interference. For the first r The weights of each component The first element in the temperature factor matrix j line, number Column elements, The first in the humidity factor matrix k line, number r Column elements, The first in the pressure factor matrix line, number The elements of the column.

[0047] Step S104, adjust according to the coupling interference amount c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

[0048] Optionally, after determining the coupling interference amount, the detected interference can be analyzed based on this coupling interference amount. c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

[0049] In an optional embodiment of this application, the coupling interference amount is adjusted accordingly. c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment structure, including: according to c The radiation count rate is denormalized to obtain the denormalized value; The radiation detection results of the nuclear containment structure are obtained by scaling the inverse normalized value based on the coupling interference quantity.

[0050] Optional, can be obtained c The mean and standard deviation of the radiation count rate are calculated, and then the obtained data are analyzed based on these mean and standard deviation. c The radiation count rate is denormalized to obtain a denormalized value. Finally, based on a determined coupling interference, the obtained denormalized value is scaled back to its original scale to obtain the radiation detection result of the nuclear containment structure. The radiation detection result of the nuclear containment structure can be obtained using the following formula:

[0051] in, The radiation detection results for the nuclear containment structure. Acquired c Radiation count rate, This is the amount of coupling interference. for c The mean value corresponding to the radiation count rate. for c The standard deviation of the radiation count rate.

[0052] In an optional embodiment of this application, after obtaining the radiation detection results of the nuclear containment structure, the method further includes: If the ambient humidity value is greater than the preset humidity threshold, the humidity compensation amount is determined based on the ambient humidity value. The radiation detection results of the nuclear containment structure are compensated based on the humidity compensation amount to obtain the final radiation detection results of the nuclear containment structure.

[0053] Optionally, if the current ambient humidity is high, this humidity level can also affect the detected radiation data. Therefore, when the obtained ambient humidity value is determined to be greater than the preset humidity threshold (such as the current ambient humidity), When the humidity is ≥95%, a humidity compensation amount can be determined based on the ambient humidity value. This humidity compensation amount is then used to compensate for the radiation detection results of the nuclear containment structure, yielding the final radiation detection result. The final radiation detection result of the nuclear containment structure can be determined using the following formula:

[0054] in, The final radiation test results for the nuclear containment structure. The radiation detection results for the nuclear containment structure. This represents the current ambient humidity value.

[0055] In an optional embodiment of this application, after obtaining the radiation detection results of the nuclear containment structure, the method further includes: Obtain the current ambient temperature value, and determine the sensitivity coefficient based on the radiation detection results and the current ambient temperature value; The temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector are updated based on the sensitivity coefficients, resulting in the updated temperature factor matrix, updated humidity factor matrix, updated pressure factor matrix, and updated coupling strength vector. The set obtained by combining the updated temperature factor matrix, the updated humidity factor matrix, and the updated pressure factor matrix is ​​used as the initial factor matrix set, and the updated coupling strength vector is used as the initial weight vector matrix.

[0056] Optionally, to ensure data consistency and thus more accurately detect radiation levels in the nuclear containment structure, a sensitivity coefficient can be determined based on the obtained radiation detection results, surface temperature, ambient humidity, and containment pressure. The sensitivity coefficient can be determined using the following formula:

[0057] in, This is the radiation detection result (if humidity compensation is present, it is the final radiation detection result obtained after humidity compensation). The temperature perturbation step size, This represents the current ambient temperature.

[0058] Furthermore, the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector obtained above can be updated according to the determined sensitivity coefficients, resulting in updated temperature factor matrix, updated humidity factor matrix, updated pressure factor matrix, and updated coupling strength vector. Correspondingly, the set obtained by combining the updated temperature factor matrix, updated humidity factor matrix, and updated pressure factor matrix can be used as the initial factor matrix set, and the updated coupling strength vector can be used as the initial weight vector matrix for the next cycle of executing the scheme in this application to determine the radiation detection results.

[0059] The sensitivity coefficient determined in this application is essentially a transfer function of the radiation measurement system to environmental parameters. Its accurate calibration and dynamic update are the core of achieving multi-parameter decoupling. At this time, updating the factor matrix and weight matrix corresponding to the data of each type of sensor based on the determined sensitivity coefficient can correct detector gain drift, suppress background noise and aerosol loss, and at the same time offset the geometric error caused by containment deformation.

[0060] Optionally, to better understand the solution provided in this application, the following will be combined with... Figure 2 The solution provided in this application will be described again. Specifically, based on the deployed sensor group, five sets of raw sensor data (one set per second) are acquired. Then, a tensor is constructed based on the raw sensor data, and the resulting four-dimensional tensor is decomposed. Based on the factor matrix and coupling strength vector obtained from the decomposition, and the environmental humidity data in the raw sensor data, the coupling interference is determined. Finally, the coupling interference is adjusted accordingly. cThe radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment structure. During this process, the current ambient temperature value can also be acquired. Based on the radiation detection results and the current ambient temperature value, a sensitivity coefficient is determined. Then, based on the sensitivity coefficient, the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector are updated respectively, resulting in updated temperature factor matrix, updated humidity factor matrix, updated pressure factor matrix, and updated coupling strength vector. Finally, the set obtained by combining the updated temperature factor matrix, updated humidity factor matrix, and updated pressure factor matrix is ​​used as the initial factor matrix set, and the updated coupling strength vector is used as the initial weight vector matrix. The resulting initial factor matrix set and updated coupling strength vector are stored for future tensor decomposition.

[0061] In this application, a four-dimensional radiation response matrix (i.e., a four-dimensional tensor) can be constructed based on the acquired sensor data. This four-dimensional tensor fully describes the environment-radiation coupling relationship, thus laying the data structure foundation for subsequent accurate decoupling. Correspondingly, the obtained four-dimensional tensor can be decomposed to extract factor matrices of temperature, humidity, and pressure (i.e., pure interference modes), achieving real-time separation of multi-parameter interference. Furthermore, the coupling interference amount is determined based on the obtained factor matrix to compensate and convert the detected gamma radiation count rate, thereby obtaining the radiation detection results of the nuclear containment structure. This process significantly reduces the compensation error during synchronous abrupt changes in temperature and humidity, ensuring the accuracy of the detection results. Simultaneously, it maintains high measurement accuracy even under extreme operating conditions, exhibiting better adaptability and stability.

[0062] This application provides a compensation device for radiation monitoring data of a nuclear containment structure, such as... Figure 3 As shown, the device may include: a data acquisition module 301, a tensor construction module 302, an interference determination module 303, and a result determination module 304, wherein... The data acquisition module is used to acquire sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point. The sensor data includes... c Radiation count rate, surface temperature, ambient humidity, and containment pressure; The tensor construction module is used to construct a four-dimensional tensor based on sensor data and timestamps, and decompose the four-dimensional tensor to obtain the corresponding factor matrix and coupling strength vector. The factor matrix includes a temperature factor matrix, a humidity factor matrix, and a pressure factor matrix. The interference determination module is used to determine the coupling interference based on the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector. The result determination module is used to determine the coupling interference amount. c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

[0063] Optionally, when acquiring sensor data corresponding to at least one set time point, the data acquisition module is specifically used for: Acquire raw sensor data corresponding to at least one set time point. The raw sensor data includes raw... c Radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure; For the original c The radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure were normalized to obtain sensor data.

[0064] Optionally, the tensor construction module constructs a four-dimensional tensor based on sensor data and timestamps, specifically for: The surface temperature value, ambient humidity value, and containment pressure value are dynamically discretized and divided into gears to obtain the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. For each time point, the environmental gear corresponding to the time point is determined based on the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. according to c The radiation count rate and the corresponding environmental level at each time point are used to fill the tensor to obtain a four-dimensional tensor.

[0065] Optionally, the tensor construction module decomposes the four-dimensional tensor to obtain the corresponding factor matrix and coupling strength vector, specifically used for: Obtain the preset rank matrix, the set of initialized factor matrices, and the initial weight vector matrix. The initialized factor matrices include the initialized time factor matrix, the initialized temperature factor matrix, the initialized humidity factor matrix, and the initialized pressure factor matrix. The four-dimensional tensor is iteratively updated and decomposed based on the rank matrix, the set of initial factor matrices, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector.

[0066] Optionally, the tensor construction module iteratively updates and decomposes the four-dimensional tensor based on the rank matrix, the initial factor matrix set, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector, specifically used for: For each type of sensor data, the initialization factor matrices in the initialization factor matrix set, except for the initialization factor matrix corresponding to the type of sensor data, are fixed, and the Lekronek product is determined based on the fixed factor matrices in the initialization factor matrix set. Expand the dimensions of the sensor data corresponding to the type in the four-dimensional tensor to obtain the expanded matrix, and determine the least squares matrix based on the expanded matrix and the Lekronek product; Based on the least squares matrix and the initial weight vector matrix, the factor matrix corresponding to the type of sensor data is obtained.

[0067] Optionally, the result determination module determines the result based on the amount of coupling interference. c The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment structure, which are specifically used for: according to c The radiation count rate is denormalized to obtain the denormalized value; The radiation detection results of the nuclear containment structure are obtained by scaling the inverse normalized value based on the coupling interference quantity.

[0068] Optionally, the result determination module is also used for: After obtaining the radiation detection results of the nuclear containment building, if the ambient humidity value is greater than the preset humidity threshold, the humidity compensation amount is determined based on the ambient humidity value. The radiation detection results of the nuclear containment structure are compensated based on the humidity compensation amount to obtain the final radiation detection results of the nuclear containment structure.

[0069] Optionally, the device also includes an updated model, specifically for: After obtaining the radiation detection results of the nuclear containment structure, the temperature value of the current environment is acquired, and the sensitivity coefficient is determined based on the radiation detection results and the temperature value of the current environment. The temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector are updated based on the sensitivity coefficients, resulting in the updated temperature factor matrix, updated humidity factor matrix, updated pressure factor matrix, and updated coupling strength vector. The set obtained by combining the updated temperature factor matrix, the updated humidity factor matrix, and the updated pressure factor matrix is ​​used as the initial factor matrix set, and the updated coupling strength vector is used as the initial weight vector matrix.

[0070] The nuclear containment radiation monitoring data compensation device of this embodiment can execute the nuclear containment radiation monitoring data compensation method shown in the embodiment of this application. The implementation principle is similar and will not be described again here.

[0071] This application provides an electronic device, which includes a processor and a memory configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform a method for compensating radiation monitoring data of a nuclear containment structure.

[0072] This application provides an electronic device, such as... Figure 4 As shown, Figure 4 The illustrated electronic device includes a processor 2001 and a memory 2003. The processor 2001 and the memory 2003 are connected, for example, via a bus 2002. Optionally, the electronic device 2000 may further include a transceiver 2004. It should be noted that in practical applications, the transceiver 2004 is not limited to one type, and the structure of this electronic device 2000 does not constitute a limitation on the embodiments of this application.

[0073] Processor 2001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 2001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0074] Bus 2002 may include a pathway for transmitting information between the aforementioned components. Bus 2002 may be a PCI bus or an EISA bus, etc. Bus 2002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0075] The memory 2003 may be ROM or other type of static storage device capable of storing static information and instructions, RAM or other type of dynamic storage device capable of storing information and instructions, or EEPROM, CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0076] The memory 2003 stores the application code that executes the scheme of this application, and its execution is controlled by the processor 2001. The processor 2001 executes the application code stored in the memory 2003 to implement... Figure 3 The embodiment shown illustrates the operation of a compensation device for radiation monitoring data from a nuclear containment structure.

[0077] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0078] The above description is only a partial embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for compensating radiation monitoring data from a nuclear containment building, characterized in that, include: Acquire sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point, wherein the sensor data includes... γ Radiation count rate, surface temperature, ambient humidity, and containment pressure; A four-dimensional tensor is constructed based on the sensor data and the timestamp, and the four-dimensional tensor is decomposed to obtain the corresponding factor matrix and coupling strength vector. The factor matrix includes a temperature factor matrix, a humidity factor matrix, and a pressure factor matrix. The coupling interference amount is determined based on the temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector. Based on the coupling interference amount, the γ The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

2. The method according to claim 1, characterized in that, The acquisition of sensor data corresponding to at least one set time point includes: Acquire raw sensor data corresponding to at least one set time point, the raw sensor data including raw γ Radiation count rate, raw surface temperature, raw ambient humidity, and raw containment pressure; For the original γ The radiation count rate, the original surface temperature value, the original ambient humidity value, and the original containment pressure value are normalized to obtain the sensor data.

3. The method according to claim 1, characterized in that, The construction of a four-dimensional tensor based on the sensor data and the timestamp includes: The surface temperature value, the ambient humidity value, and the pressure value inside the containment are dynamically discretized and divided into gears to obtain the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the pressure value inside the containment. For each time point, the environmental gear corresponding to the time point is determined based on the gear index corresponding to the surface temperature value, the gear index corresponding to the ambient humidity value, and the gear index corresponding to the containment pressure value. According to the above γ The radiation count rate and the environmental level corresponding to each time point are used to fill the tensor to obtain the four-dimensional tensor.

4. The method according to claim 1, characterized in that, The decomposition of the four-dimensional tensor to obtain the corresponding factor matrix and coupling strength vector includes: Obtain a preset rank matrix, an initialization factor matrix set, and an initial weight vector matrix. The initialization factor matrix set includes an initialization time factor matrix, an initialization temperature factor matrix, an initialization humidity factor matrix, and an initialization pressure factor matrix. The four-dimensional tensor is iteratively updated and decomposed based on the rank matrix, the set of initial factor matrices, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector.

5. The method according to claim 4, characterized in that, The iterative update decomposition of the four-dimensional tensor based on the rank matrix, the set of initial factor matrices, and the initial weight vector matrix to obtain the corresponding factor matrix and coupling strength vector includes: For each type of sensor data, the initialization factor matrices in the initialization factor matrix set, except for the initialization factor matrix corresponding to the sensor data of that type, are fixed, and the Lekronek product is determined based on the fixed factor matrices in the initialization factor matrix set. Expand the dimensions of the sensor data corresponding to the type in the four-dimensional tensor to obtain the expanded matrix, and determine the least squares matrix based on the expanded matrix and the Lekronek product; Based on the least squares matrix and the initial weight vector matrix, the factor matrix corresponding to the sensor data of the aforementioned type is obtained.

6. The method according to claim 1, characterized in that, The method based on the coupling interference amount γ The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment structure, including: According to the above γ The radiation count rate is denormalized to obtain the denormalized value; The radiation detection results of the nuclear containment structure are obtained by scaling the inverse normalized value based on the coupling interference.

7. The method according to claim 1, characterized in that, After obtaining the radiation detection results of the nuclear containment structure, the process also includes: If the ambient humidity value is greater than the preset humidity threshold, then the humidity compensation amount is determined based on the ambient humidity value; The radiation detection results of the nuclear containment vessel are compensated based on the humidity compensation amount to obtain the final radiation detection results of the nuclear containment vessel.

8. The method according to claim 4, characterized in that, After obtaining the radiation detection results of the nuclear containment structure, the process also includes: Obtain the temperature value of the current environment, and determine the sensitivity coefficient based on the radiation detection results and the temperature value of the current environment; The temperature factor matrix, humidity factor matrix, pressure factor matrix, and coupling strength vector are updated according to the sensitivity coefficients to obtain the updated temperature factor matrix, updated humidity factor matrix, updated pressure factor matrix, and updated coupling strength vector. The set obtained by combining the updated temperature factor matrix, the updated humidity factor matrix, and the updated pressure factor matrix is ​​used as the initial factor matrix set, and the updated coupling strength vector is used as the initial weight vector matrix.

9. A compensation device for radiation monitoring data of a nuclear containment building, characterized in that, include: The data acquisition module is used to acquire sensor data corresponding to at least one set time point and a timestamp corresponding to each set time point, wherein the sensor data includes... γ Radiation count rate, surface temperature, ambient humidity, and containment pressure; The tensor construction module is used to construct a four-dimensional tensor based on the sensor data and the timestamp, and decompose the four-dimensional tensor to obtain the corresponding factor matrix and coupling strength vector. The factor matrix includes a temperature factor matrix, a humidity factor matrix and a pressure factor matrix. The interference determination module is used to determine the coupling interference amount based on the temperature factor matrix, humidity factor matrix, pressure factor matrix and coupling strength vector; The result determination module is used to determine the result based on the coupling interference amount. γ The radiation count rate is compensated and converted to obtain the radiation detection results of the nuclear containment building.

10. An electronic device, characterized in that, Including the processor and memory: The memory is configured to store a computer program that, when executed by the processor, causes the processor to perform the method according to any one of claims 1-8.

Images