A visual monitoring method and system for radiopharmaceutical synthesis reactor

By calculating the noise interference in reactor thermal imaging and setting a suitable Gaussian filter core, the problem of poor filtering effect caused by unreasonable determination of Gaussian filter cores in the prior art is solved, and the accuracy of abnormal monitoring of radiopharmaceutical synthesis reactors is improved sex.

CN118628360BActive Publication Date: 2024-11-15SHAANXI ZHENGZE BIOTECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411111026.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-15
Estimated Expiration
2044-08-14

AI Technical Summary

Technical Problem

The prior art ignores the influence of noise when determining the Gaussian filtering core, resulting in poor filtering effect of thermal imaging of radiopharmaceutical synthesis reactors, affecting the accuracy of abnormal monitoring.

Method used

By obtaining the abnormality of temperature distribution, environmental parameter interference, and cooling heat exchange interference in reactor thermal imaging, the noise interference is calculated, and a suitable Gaussian filter core is set according to the noise interference, the reactor thermal imaging is filtered.

Benefits of technology

The filtering effect of reactor thermal imaging is improved, the accuracy of abnormal monitoring is improved, and the stability and safety of the radiopharmaceutical synthesis reactor is ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118628360B_ABST
    Figure CN118628360B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of image filtering technology, and specifically to a method and system for visual monitoring of a radiopharmaceutical synthesis reactor. The present invention first obtains the abnormality of the temperature distribution of the reactor thermal imaging; obtains the environmental parameter interference degree according to the correlation between the fluctuation characteristics of the environmental parameters at continuous sampling moments and the abnormality of the temperature distribution of the reactor thermal imaging, as well as the fluctuation characteristics of the environmental parameters at the time to be analyzed; obtains the cooling heat exchange interference degree of the thermal imaging to be filtered according to the temperature value difference between the thermal imaging of the reactor before and after cooling during the cooling process; sets the filter kernel according to the noise interference degree, filters the thermal imaging to be filtered, and obtains the reactor filtered image for monitoring. The present invention realizes the reasonable setting of the Gaussian filter kernel by constructing the noise interference degree that reflects the noise situation, improves the Gaussian filtering effect, and ensures the accuracy of reactor abnormality monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of image filtering, and in particular to a visual monitoring method and system for a radiopharmaceutical synthesis reactor. Background Art

[0002] Radiopharmaceuticals are a type of drug that uses radiation or particles emitted by radionuclides for diagnosis or treatment. Radiopharmaceutical synthesis reactors are key equipment specifically used to prepare radiopharmaceuticals. Their safety and efficiency are crucial to the quality of radiopharmaceuticals. In order to ensure the stability and safety of radiopharmaceutical synthesis reactors, it is necessary to monitor the reactor thermal imaging and analyze the reactor conditions. Since the collected reactor thermal imaging is affected by noise and is difficult to reflect the actual abnormal situation, it is necessary to filter the reactor thermal imaging to improve the quality of the reactor thermal imaging.

[0003] Gaussian filtering is a common image filtering method. The existing technology can filter the reactor thermal imaging through Gaussian filtering. However, the effect of Gaussian filtering is affected by the Gaussian filter kernel. When the determined Gaussian filter kernel is too small, some pixels in the reactor thermal imaging may not be fully smoothed, affecting the accuracy of the filtering result. When the determined Gaussian filter kernel is too large, the details and features of the reactor thermal imaging will be lost, affecting the accuracy of the filtering result. The existing technology usually determines the Gaussian filter kernel based on experience, ignoring the performance of noise in the reactor thermal imaging, resulting in unreasonable determination of the Gaussian filter kernel, which in turn leads to poor filtering effect, making the reactor abnormality monitoring effect inaccurate and prone to misjudgment. Summary of the invention

[0004] In order to solve the technical problem that the Gaussian filter kernel is not reasonably determined in the prior art, resulting in poor filtering effect and inaccurate reactor abnormality monitoring effect, the purpose of the present invention is to provide a method and system for visual monitoring of a radiopharmaceutical synthesis reactor, and the technical scheme adopted is as follows:

[0005] A method for visual monitoring of a radiopharmaceutical synthesis reactor, the method comprising:

[0006] Acquire a reactor data set of the synthesis reactor during the synthesis process; the reactor data set includes: environmental parameters and reactor thermal imaging at each sampling time, and reactor thermal imaging before and after cooling of each cooling process; the reactor thermal imaging includes the temperature value of each pixel point;

[0007] According to the difference in temperature value distribution and the uneven distribution of temperature values ​​in the reactor thermal imaging, the abnormal degree of temperature distribution in the reactor thermal imaging is obtained;

[0008] Taking any sampling moment as the moment to be analyzed, and taking the thermal image of the reactor at the moment to be analyzed as the thermal image to be filtered; obtaining the interference degree of the environmental parameter of the thermal image to be filtered according to the correlation between the fluctuation characteristics of the environmental parameters at the continuous sampling moments and the abnormal degree of the temperature distribution of the thermal image of the reactor, and the fluctuation characteristics of the environmental parameters at the moment to be analyzed;

[0009] According to the temperature value difference between the thermal images of the reactor before and after cooling during the cooling process, the cooling heat exchange interference degree of the thermal image to be filtered is obtained; according to the abnormal degree of temperature distribution of the thermal image to be filtered, the environmental parameter interference degree and the cooling heat exchange interference degree, the noise interference degree of the thermal image to be filtered is obtained;

[0010] A filter kernel is set according to the noise interference degree, the thermal image to be filtered is filtered, and a reactor filter image is obtained for monitoring.

[0011] Furthermore, the method for obtaining the abnormal degree of temperature distribution includes:

[0012] Acquiring a reactor surface area and a background area of ​​the reactor thermal imaging according to a difference in pixel value distribution in the reactor thermal imaging;

[0013] Dividing the surface area of ​​the reactor into blocks, and obtaining each surface block area in the thermal imaging of the reactor;

[0014] According to the temperature difference between the surface block area and the background area and the unevenness of the temperature value in the surface block area, the degree of local temperature anomaly in the surface block area is obtained;

[0015] According to the degree of local temperature anomaly in all surface block areas in the reactor thermal imaging, the degree of temperature distribution anomaly in the reactor thermal imaging is obtained.

[0016] Furthermore, the method for obtaining the degree of local temperature anomaly of the surface block area includes:

[0017] According to the difference in the overall distribution characteristics of the temperature values ​​of the surface block area and the background area, the thermal significance of the reactor is obtained;

[0018] According to the fluctuation of the temperature values ​​of all the pixels in the surface block area, the temperature fluctuation degree is obtained;

[0019] The temperature complexity is obtained according to the richness of the temperature values ​​of all pixels in the surface block area;

[0020] According to the temperature fluctuation and the temperature complexity, the temperature non-uniformity of the surface block area is obtained; the temperature fluctuation and the temperature complexity are both positively correlated with the temperature non-uniformity;

[0021] According to the thermal significance of the reactor and the temperature non-uniformity, the degree of local temperature anomaly in the surface block area is obtained; the thermal significance of the reactor and the degree of local temperature anomaly are negatively correlated; the temperature non-uniformity and the degree of local temperature anomaly are positively correlated.

[0022] Furthermore, the method for obtaining the degree of abnormality of temperature distribution in the reactor thermal imaging according to the degree of abnormality of local temperature in all surface block areas in the reactor thermal imaging includes:

[0023] In reactor thermal imaging, the overall temperature non-uniformity of the reactor thermal imaging is obtained based on the difference between the local temperature anomaly degrees of all surface block areas;

[0024] According to the overall distribution of the local temperature anomaly of all surface block areas, the overall temperature anomaly of the reactor thermal imaging is obtained;

[0025] The degree of abnormal temperature distribution of the reactor thermal imaging is obtained according to the overall temperature non-uniformity and the overall temperature anomaly; the overall temperature non-uniformity and the overall temperature anomaly are both positively correlated with the degree of abnormal temperature distribution.

[0026] Furthermore, the method for obtaining the overall temperature non-uniformity includes:

[0027] In reactor thermal imaging, the absolute value of the difference in the degree of local temperature anomaly between every two surface block areas is calculated to obtain the local difference value, and the average of all local difference values ​​is calculated to obtain the overall temperature non-uniformity of the reactor thermal imaging.

[0028] Furthermore, the method for obtaining the environmental parameter interference degree includes:

[0029] Obtain all reference environmental parameters of the environmental parameter at the time to be analyzed within a preset surrounding range; obtain the environmental change degree of the environmental parameter at the time to be analyzed based on the volatility of all reference environmental parameters of the environmental parameter;

[0030] Obtaining the reactor environment responsiveness according to the correlation between the degree of environmental change and the degree of abnormal temperature distribution at continuous sampling moments;

[0031] The environmental parameter interference of the thermal image to be filtered is obtained by comprehensively considering the environmental change degree and the reactor environmental responsiveness at the time to be analyzed; the environmental change degree and the reactor environmental responsiveness at the time to be analyzed are both positively correlated with the environmental parameter interference degree.

[0032] Furthermore, the method for obtaining the reactor environment responsiveness includes:

[0033] According to the time series order, the environmental change degree at all sampling moments is counted in turn to obtain the environmental change degree time series data; the temperature distribution abnormality degree at all sampling moments is counted in turn to obtain the temperature distribution abnormality degree time series data; the Pearson correlation coefficient of the environmental change degree time series data and the temperature distribution abnormality degree time series data is normalized to obtain the reactor environmental responsiveness.

[0034] Furthermore, the method for obtaining the cooling heat exchange interference degree includes:

[0035] In the reactor thermal imaging, the average temperature value of all pixel points in the reactor surface area is calculated to obtain the reactor temperature value of the reactor thermal imaging;

[0036] Calculating the absolute value of the difference between the reactor temperature values ​​of the reactor thermal imaging before and after cooling to obtain the cooling heat exchange value of the cooling process;

[0037] The previous cooling process at the time to be analyzed is taken as the cooling process affecting the reactor;

[0038] The average of the cooling heat exchange values ​​of all cooling processes is calculated to obtain the overall heat exchange value; the absolute value of the difference between the cooling heat exchange value affecting the cooling process of the reactor and the overall heat exchange value is calculated to obtain the cooling heat exchange interference degree of the thermal imaging to be filtered.

[0039] Furthermore, the method for obtaining the noise interference degree includes:

[0040] According to the environmental parameter interference degree and the cooling heat exchange interference degree, the real interference degree of the thermal imaging to be filtered is obtained; the environmental parameter interference degree and the cooling heat exchange interference degree are both positively correlated with the real interference degree;

[0041] The noise interference degree of the thermal image to be filtered is obtained according to the abnormal degree of temperature distribution and the real interference degree of the thermal image to be filtered; the abnormal degree of temperature distribution and the noise interference degree are positively correlated; the real interference degree and the noise interference degree are negatively correlated.

[0042] The present invention proposes a visual monitoring system for a radiopharmaceutical synthesis reactor, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the system implements any one of the steps of a visual monitoring method for a radiopharmaceutical synthesis reactor.

[0043] The present invention has the following beneficial effects:

[0044] The main purpose of the present invention is to construct a suitable Gaussian filter kernel based on the noise performance in the reactor thermal imaging, improve the filtering effect of the reactor thermal imaging, and improve the accuracy of the abnormal monitoring effect of the reactor. Considering that the surface temperature of the reactor of the radioactive drug synthesis reactor is relatively uniform under normal circumstances, that is, the temperature value of the reactor thermal surface is relatively uniform under normal circumstances; when it is disturbed by abnormal environmental parameters and cooling effects, the distribution of the reactor thermal surface temperature values ​​will be uneven; at the same time, when it is disturbed by noise, it will also cause the distribution of the reactor thermal surface temperature values ​​to be uneven, that is, abnormal conditions will cause the distribution of the reactor thermal surface temperature values ​​to be uneven. In order to analyze the uneven temperature distribution of the reactor thermal imaging caused by noise interference, it is first necessary to obtain the degree of abnormality of the temperature distribution of the reactor surface temperature. The greater the degree of abnormality, the more uneven the distribution of the reactor surface temperature.

[0045] Considering that environmental parameters, abnormal cooling effects, and noise interference can all lead to uneven distribution of temperature values ​​on the reactor thermal imaging, in order to determine the uneven temperature distribution of the reactor thermal imaging caused by noise, it is necessary to remove the influence of environmental parameters and abnormal cooling effects on the uneven distribution of temperature values ​​on the reactor thermal imaging. Considering that the materials used in the reactor are more susceptible to the influence of environmental parameters, when the environmental parameters fluctuate violently, the surface temperature of the reactor is more likely to be uneven, that is, the temperature distribution of the reactor thermal imaging is uneven, and the environmental parameter interference degree of the thermal imaging to be filtered is obtained. The greater the environmental parameter interference degree, the greater the degree of uneven temperature distribution of the reactor thermal imaging caused by the environmental parameters. Considering that the uneven surface temperature of the reactor is closely related to the cooling effect, if the cooling effect is better, the less uneven the surface temperature of the reactor will be caused, and the cooling heat exchange interference degree of the thermal imaging to be filtered is obtained. The greater the cooling heat exchange interference degree, the worse the cooling heat exchange effect, and the greater the degree of uneven temperature distribution of the reactor thermal imaging caused by the cooling heat exchange effect. The influence of uneven temperature distribution on the reactor thermal imaging caused by abnormal environmental parameters and cooling effects is removed, and the noise interference degree reflecting the noise level in the reactor thermal imaging is obtained. Therefore, when the noise performance is more obvious, the Gaussian filter kernel is set larger; when the noise performance is less obvious, the Gaussian filter kernel is set smaller, so as to ensure the rationality of the Gaussian filter kernel setting, improve the filtering effect, and ensure the accuracy of reactor abnormality monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0047] Figure 1 A flowchart of a method for visually monitoring a radiopharmaceutical synthesis reactor provided by one embodiment of the present invention;

[0048] Figure 2 A flow chart of a method for obtaining the degree of abnormal temperature distribution provided by an embodiment of the present invention;

[0049] Figure 3 A flow chart of a method for obtaining the degree of local temperature anomaly provided by an embodiment of the present invention;

[0050] Figure 4 A flow chart of a method for obtaining the degree of abnormal temperature distribution provided by an embodiment of the present invention;

[0051] Figure 5 A flow chart of a method for obtaining environmental parameter interference degree provided by an embodiment of the present invention;

[0052] Figure 6 A flow chart of a method for obtaining noise interference degree provided by an embodiment of the present invention;

[0053] Figure 7 A structural diagram of a visual monitoring system for a radiopharmaceutical synthesis reactor provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for visual monitoring of a radiopharmaceutical synthesis reactor proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0055] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0056] The specific scheme of a method and system for visually monitoring a radiopharmaceutical synthesis reactor provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0057] The present invention provides a method and system for visually monitoring a radiopharmaceutical synthesis reactor. Figure 1 , which shows a flow chart of a method for visually monitoring a radiopharmaceutical synthesis reactor provided by an embodiment of the present invention, the method comprising the following steps:

[0058] Step S1: Acquire a reactor data set of the synthesis reactor during the synthesis process; the reactor data set includes: environmental parameters and reactor thermal imaging at each sampling time, and reactor thermal imaging before and after cooling of each cooling process; the reactor thermal imaging includes the temperature value of each pixel point.

[0059] Considering that the temperature distribution of radiopharmaceutical synthesis reactors is a key factor affecting reaction efficiency and product quality, radiopharmaceutical synthesis reactors need to monitor the reactors during the synthesis process by collecting reactor thermal images. Considering that environmental parameters affect the reactor surface temperature distribution during the synthesis process, the cooling medium entering the reactor will also affect the reactor surface temperature distribution. Environmental parameters and reactor thermal images before and after cooling are collected during each cooling process to provide data support for the subsequent analysis of noise performance in reactor thermal images.

[0060] In a drug synthesis laboratory, multiple radioactive drug synthesis reactors are placed. Since the interior of the reactor is not suitable for installing an infrared thermal imager, the safety of the synthesis process is ensured by monitoring the surface of the reactor. The present invention takes monitoring the outer surface of any radioactive drug synthesis reactor in the drug synthesis laboratory during the synthesis process as an example.

[0061] In one embodiment of the present invention, the sampling frequency of the synthetic reactor monitoring system is set to collect once per minute, and the thermal imaging of the reactor at each sampling moment is obtained. Among them, the specific acquisition method of the reactor thermal imaging includes: the synthetic reactor monitoring system collects images of all viewing angles of the reactor surface by using an infrared thermal imager, and splices the images of all viewing angles into one image using image stitching technology to obtain a reactor thermal imaging that can reflect the panoramic view of the reactor surface, and stores the collected reactor thermal imaging in the synthetic reactor monitoring system. It should be noted that the deployment of the specific infrared thermal imager and the parameter settings such as the imaging mode, temperature unit, and color band of the infrared thermal imager can be adjusted by the implementer according to the specific actual situation, and are not limited here; the image stitching technology is a technical means well known to those skilled in the art, and is not described here. It should be noted that the thermal imaging of the reactor is thermal imaging, and thermal imaging is a prior art well known to those skilled in the art, and is only briefly described here: each pixel in the thermal imaging represents the infrared radiation intensity of a point on the surface of the object, and the infrared radiation intensity is directly related to the temperature of the object. Therefore, by measurement and calculation, the infrared radiation intensity of each pixel point can be converted into a corresponding temperature value, that is, each pixel point has a corresponding temperature value.

[0062] In order to reduce the influence of noise on reactor thermal imaging, the reactor thermal imaging needs to be filtered. The main purpose of the present invention is to construct a suitable Gaussian filter kernel based on the noise performance in the reactor thermal imaging to improve the filtering effect. Considering that noise, environmental parameters and cooling effect will lead to uneven surface temperature distribution of reactor thermal imaging, in order to subsequently analyze the noise performance in reactor thermal imaging, it is necessary to obtain environmental parameters and thermal imaging of the reactor before and after cooling during the cooling process. The temperature distribution on the reactor thermal imaging is affected by the ambient temperature. The temperature of the drug synthesis laboratory at each sampling time is obtained from the detection of the synthesis reactor monitoring system, and the temperature is used as an environmental parameter, that is, the environmental parameters at each sampling time are obtained.

[0063] In order to ensure the stable operation of the radiopharmaceutical synthesis reactor, a cooling medium is required for cooling during the synthesis process. The cooling medium from flowing into the reactor to flowing out of the reactor is regarded as a cooling process, and the synthesis process includes various cooling processes. The synthesis reactor monitoring system corresponds the reactor thermal imaging to the previous sampling moment when the cooling medium just flows into the reactor, and marks it as the reactor thermal imaging before cooling; the reactor thermal imaging corresponds to the next sampling moment when the cooling medium just flows out of the reactor, and marks it as the reactor thermal imaging after cooling. That is, the reactor thermal imaging before and after cooling of the cooling process is obtained, and the time when the cooling medium just enters the reactor is regarded as the cooling moment corresponding to the cooling process. It should be noted that the synthesis process includes the reactor thermal imaging of all sampling moments, and the synthesis process also includes each cooling process. By marking the reactor thermal imaging before and after cooling in the reactor thermal imaging at the sampling moment, data support is provided for the subsequent analysis of the impact of the cooling process.

[0064] It should be noted that, in order to facilitate calculation, all indicator data involved in the calculation in the embodiment of the present invention are preprocessed to eliminate the dimension effect. The specific means of eliminating the dimension effect are technical means well known to those skilled in the art and are not limited here.

[0065] Step S2: According to the difference in temperature value distribution and the uneven temperature value distribution in the reactor thermal imaging, the abnormal degree of temperature distribution in the reactor thermal imaging is obtained.

[0066] The main purpose of the present invention is to construct a suitable Gaussian filter kernel based on the noise performance in the reactor thermal imaging, improve the filtering effect of the reactor thermal imaging, and improve the accuracy of the abnormal monitoring effect of the reactor. Considering that the surface temperature of the reactor of the radioactive drug synthesis reactor is relatively uniform under normal circumstances, that is, the temperature value of the reactor thermal surface is relatively uniform under normal circumstances; when it is disturbed by abnormal environmental parameters and cooling effects, the distribution of the reactor thermal surface temperature values ​​will be uneven; at the same time, when it is disturbed by noise, it will also cause the distribution of the reactor thermal surface temperature values ​​to be uneven, that is, abnormal conditions will cause the distribution of the reactor thermal surface temperature values ​​to be uneven. In order to analyze the uneven temperature distribution of the reactor thermal imaging caused by noise interference, it is first necessary to obtain the degree of abnormality of the temperature distribution of the reactor surface temperature. The greater the degree of abnormality, the more uneven the distribution of the reactor surface temperature.

[0067] To analyze the uneven temperature distribution on the reactor surface, refer to Figure 2 , which shows a flow chart of a method for obtaining the degree of abnormal temperature distribution in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining the degree of abnormal temperature distribution includes:

[0068] Step S201: acquiring the reactor surface area and the background area of ​​the reactor thermal imaging according to the difference in pixel value distribution in the reactor thermal imaging.

[0069] Considering that the reactor surface temperature is significantly higher than the background temperature during the synthesis process, the reactor surface area and the background area of ​​the reactor thermal imaging are acquired.

[0070] In one embodiment of the present invention, a method for obtaining a reactor surface area and a background area of ​​a reactor thermal image includes:

[0071] Since the temperature information in the reactor thermal imaging is usually expressed in the form of pixel values, the reactor thermal imaging is divided into multiple superpixels according to the pixel values ​​of the pixels using the superpixel segmentation method; after the superpixel segmentation is completed, the superpixel block with a temperature value greater than the preset temperature threshold is used as the reactor surface area, and the superpixel block with a temperature value not greater than the preset temperature threshold is used as the background area. It should be noted that the superpixel segmentation method is a prior art well known to those skilled in the art and will not be described in detail here. In one embodiment of the present invention, the preset temperature threshold is 37, and the implementer can set it according to the implementation scenario. For example, since the reactor temperature is obviously different from the temperature of other areas, the environmental parameters reflect the temperature of the drug synthesis laboratory where the reactor is located, and the maximum environmental parameter can be used as the preset temperature threshold.

[0072] In other embodiments of the present invention, the method for obtaining the reactor surface area and background area of ​​the reactor thermal imaging includes: graying the reactor thermal imaging to obtain a gray image, using the Otsu threshold algorithm, according to the gray values ​​of all pixels in the gray image, calculating the threshold for distinguishing the foreground and the background, marking each pixel whose gray value is greater than the threshold as each foreground pixel; marking each pixel whose gray value is not greater than the threshold as each background pixel; using the gray image containing only the foreground pixel as the foreground gray area; using the gray image containing only the background pixel as the background gray area; mapping the foreground gray area to the reactor thermal imaging to obtain the reactor surface area of ​​the reactor thermal imaging; mapping the background gray area to the reactor thermal imaging to obtain the background area of ​​the reactor thermal imaging. It should be noted that in the embodiment of the present invention, the weighted average gray algorithm is selected for gray processing, and the Otsu threshold algorithm and the weighted average gray algorithm are both technical means well known to those skilled in the art, and will not be described in detail here.

[0073] Step S202: dividing the surface area of ​​the reactor into blocks, and obtaining each surface block area in the reactor thermal imaging.

[0074] By dividing the reactor surface area into blocks, each surface block area in the reactor thermal imaging is obtained for subsequent analysis of the uniformity of temperature distribution between the surface block areas in the reactor surface area.

[0075] In one embodiment of the present invention, based on the image coordinate system, a dividing line is constructed in the reactor surface area through the center in a direction parallel to the X-axis, and four preset dividing lines are rotated clockwise at preset angles, namely 0 degrees, 45 degrees, 90 degrees and 135 degrees, to obtain four preset dividing lines. The four preset dividing lines divide the reactor thermal imaging into 8 surface block areas. In other embodiments of the present invention, the area corresponding to the image of each viewing angle in the reactor surface area can be used as each surface block area. It should be noted that the image coordinate system is a prior art well known to those skilled in the art and will not be described in detail herein.

[0076] Step S203: according to the temperature difference between the surface block area and the background area and the unevenness of the temperature value in the surface block area, the degree of local temperature anomaly of the surface block area is obtained.

[0077] In order to analyze the degree of abnormal temperature distribution in the surface block area, considering that the surface temperature of the reactor is significantly higher than the background temperature, the closer the surface block area is to the background temperature, the more likely it is an abnormal situation; at the same time, considering that the more uneven the temperature distribution in the surface block area is, the more likely it is an abnormal situation, the degree of local temperature abnormality in the surface block area is obtained. The greater the degree of local temperature abnormality, the more uneven the temperature distribution in the surface block area is, and the more likely the surface block area is in an abnormal situation.

[0078] See also Figure 3 , which shows a flow chart of a method for obtaining the degree of local temperature anomaly in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining the degree of local temperature anomaly in a surface block area includes:

[0079] Step S211: Obtain the thermal significance of the reactor according to the difference in the overall distribution characteristics of the temperature values ​​of the surface block area and the background area.

[0080] When the thermal significance of the reactor is large, it means that the temperature of the surface block area is obviously higher than that of the background area, which means that the surface block area is normal.

[0081] In one embodiment of the present invention, the mean of the temperature values ​​of all pixels in the surface block area is calculated as the block area temperature value of the surface block area; the mean of the temperature values ​​of all pixels in the background area is calculated as the background area temperature value of the background area; the difference is obtained by subtracting the background area temperature value from the block area temperature value; when the difference is greater than the preset threshold, the thermal significance of the reactor is set to 1, and when the difference is not greater than the preset threshold, the thermal significance of the reactor is set to 0. The overall distribution characteristics of the temperature values ​​are reflected by the temperature values ​​of all pixels; the difference is reflected by the absolute value of the difference. In one embodiment of the present invention, the preset threshold is 13. Since the surface temperature of the reactor is significantly higher than the background temperature, the implementer can set the preset threshold according to the degree to which the surface temperature of the reactor is higher than the background temperature.

[0082] Step S212: Obtain the temperature fluctuation degree according to the fluctuation of the temperature values ​​of all pixels in the surface block area.

[0083] The greater the temperature fluctuation, the more uneven the temperature distribution in the surface block area.

[0084] In one embodiment of the present invention, the variance of the temperature values ​​of all pixels in the surface block area is calculated to obtain the temperature fluctuation. In other embodiments of the present invention, the standard deviation of the temperature values ​​of all pixels in the surface block area is calculated to obtain the temperature fluctuation. The variance and standard deviation of the temperature values ​​of all pixels reflect the volatility of the temperature values ​​of all pixels by measuring the degree of deviation between the temperature values ​​of all pixels and their average value.

[0085] Step S213: Obtain temperature complexity according to the richness of the temperature values ​​of all pixels in the surface block area.

[0086] The greater the temperature complexity, the more types of temperature values ​​representing the surface block areas.

[0087] In one embodiment of the present invention, in the surface block area, temperature values ​​of the same size are regarded as one temperature value, and the total number of temperature value types in the surface block area is regarded as the temperature complexity. The total number of temperature value types reflects the richness of the temperature value.

[0088] Step S214: According to the temperature fluctuation and the temperature complexity, the temperature non-uniformity of the surface block area is obtained; the temperature fluctuation and the temperature complexity are both positively correlated with the temperature non-uniformity.

[0089] By comprehensively considering the types of temperature values ​​and the uneven distribution of temperature values ​​in the surface block areas, a temperature unevenness degree that can better represent the temperature unevenness characteristics of the surface block areas is obtained.

[0090] In one embodiment of the present invention, the product of temperature fluctuation and temperature complexity is calculated to obtain the temperature non-uniformity of the surface block area. In other embodiments of the present invention, the sum of temperature fluctuation and temperature complexity is calculated to obtain the temperature non-uniformity of the surface block area.

[0091] Step S215: According to the thermal significance and temperature non-uniformity of the reactor, the degree of local temperature anomaly of the surface block area is obtained; the thermal significance of the reactor and the degree of local temperature anomaly are negatively correlated; the temperature non-uniformity and the degree of local temperature anomaly are positively correlated.

[0092] The degree of local temperature anomaly in the surface block area is obtained by comprehensively considering the situation that the temperature of the surface block area is obviously higher than that of the background area and the temperature unevenness of the surface block area. The greater the degree of local temperature anomaly, the more uneven the temperature of the surface block area is, and it may be in an abnormal situation.

[0093] In one embodiment of the present invention, the degree of local temperature anomaly in the surface block area is obtained by calculating the temperature non-uniformity minus the thermal significance of the reactor.

[0094] Step S204: Obtain the degree of abnormality in temperature distribution of the reactor thermal imaging according to the degree of abnormality in local temperature of all surface block areas in the reactor thermal imaging.

[0095] Considering that the reactor surface temperature is evenly distributed under normal circumstances, without obvious local hot spots and cold spots, the local temperature anomaly of all surface block areas in the reactor thermal imaging is small. When they are close, the reactor is more normal. The degree of temperature distribution anomaly in the reactor thermal imaging is obtained. The degree of temperature distribution anomaly represents the more abnormal the reactor surface temperature.

[0096] See also Figure 4, which shows a flow chart of a method for obtaining the degree of abnormal temperature distribution in one embodiment of the present invention. Preferably, in one embodiment of the present invention, according to the degree of local temperature abnormality of all surface block areas in the reactor thermal imaging, the method for obtaining the degree of abnormal temperature distribution of the reactor thermal imaging includes:

[0097] Step S221: in the reactor thermal imaging, the overall temperature non-uniformity of the reactor thermal imaging is obtained according to the difference between the local temperature anomaly degrees of all surface block areas.

[0098] The greater the overall temperature non-uniformity, the more likely it is that there are local hot spots and cold spots, and the more likely the reactor surface is in an abnormal state.

[0099] In one embodiment of the present invention, the absolute value of the difference between the local temperature anomaly of each two surface block regions is calculated to obtain the local difference value, and the mean of all local difference values ​​is calculated to obtain the overall temperature non-uniformity of the reactor thermal imaging. In other embodiments of the present invention, the variance of the local temperature anomaly of all surface block regions is calculated to obtain the overall temperature non-uniformity of the reactor thermal imaging. The variance of the local temperature anomaly reflects the degree of discreteness of the local temperature anomaly, and can also reflect the degree of difference of the local temperature anomaly from the side.

[0100] Step S222: according to the overall distribution of the local temperature anomaly of all the surface block areas, the overall temperature anomaly of the reactor thermal imaging is obtained.

[0101] The overall temperature anomaly reflects the overall abnormal situation. The larger the value, the more likely the reactor surface is in an abnormal state.

[0102] In one embodiment of the present invention, the average of the local temperature anomaly of all surface block regions is calculated to obtain the overall temperature anomaly of the reactor thermal imaging.

[0103] Step S223: Obtain the degree of abnormal temperature distribution of the reactor thermal imaging according to the overall temperature non-uniformity and the overall temperature abnormality; the overall temperature non-uniformity and the overall temperature abnormality are both positively correlated with the degree of abnormal temperature distribution.

[0104] The greater the abnormality of the temperature distribution, the more likely it is that the reactor surface is in an abnormal state.

[0105] In one embodiment of the present invention, the product of the overall temperature non-uniformity and the overall temperature anomaly is calculated to obtain the degree of abnormality of the temperature distribution of the reactor thermal imaging. In other embodiments of the present invention, the sum of the overall temperature non-uniformity and the overall temperature anomaly is calculated to obtain the degree of abnormality of the temperature distribution of the reactor thermal imaging. It should be noted that the temperature value of the thermal surface of the reactor corresponding to the normal situation is more uniform than that of the abnormal situation, but there is still a difference in the temperature value of the thermal surface of the reactor corresponding to the normal situation.

[0106] Step S3: Take any sampling moment as the moment to be analyzed, and take the reactor thermal image at the moment to be analyzed as the thermal image to be filtered; obtain the environmental parameter interference degree of the thermal image to be filtered according to the correlation between the fluctuation characteristics of the environmental parameters at continuous sampling moments and the degree of abnormality of the temperature distribution of the reactor thermal image, and the fluctuation characteristics of the environmental parameters at the moment to be analyzed; obtain the cooling heat exchange interference degree of the thermal image to be filtered according to the difference in temperature values ​​between the reactor thermal images before and after cooling during the cooling process; obtain the noise interference degree of the thermal image to be filtered according to the degree of abnormality of the temperature distribution of the thermal image to be filtered, the environmental parameter interference degree and the cooling heat exchange interference degree.

[0107] Considering that abnormal conditions of environmental parameters, abnormal conditions of cooling effects, and noise interference can all lead to uneven distribution of temperature values ​​on the reactor thermal imaging, in order to determine the uneven temperature distribution of the reactor thermal imaging caused by noise, it is necessary to remove the influence of environmental parameters and abnormal cooling effects on the uneven temperature distribution of the reactor thermal imaging. Considering that the materials used in the reactor are more susceptible to the influence of environmental parameters, when the environmental parameters fluctuate violently, the surface temperature of the reactor is more likely to be uneven, that is, the temperature distribution of the reactor thermal imaging is uneven, and the environmental parameter interference degree of the thermal imaging to be filtered is obtained. The greater the environmental parameter interference degree, the greater the degree of uneven temperature distribution of the reactor thermal imaging caused by the environmental parameters. Considering that the uneven temperature on the reactor surface is closely related to the cooling effect, if the cooling effect is better, the less uneven temperature on the reactor surface will be caused, and the cooling heat exchange interference degree of the thermal imaging to be filtered is obtained. The greater the cooling heat exchange interference degree, the worse the cooling heat exchange effect, and the greater the degree of uneven temperature distribution of the reactor thermal imaging caused by the cooling heat exchange effect. The influence of uneven temperature distribution on the reactor thermal imaging caused by abnormal environmental parameters and cooling effects is removed to obtain the noise interference degree, which reflects the degree of uneven temperature distribution on the reactor thermal imaging caused by noise when abnormal environmental parameters and cooling effects are excluded.

[0108] Considering the special properties of radioactive materials, the reactor surface usually uses specific materials to contain and process radioactive isotopes. The reactor surface material needs to have certain protective properties. Stainless steel is a common material used for reactor walls and containers. The present invention takes the radiopharmaceutical synthesis reactor using stainless steel as the material of the reactor wall and container as an example. The stainless steel material is easily affected by the change of ambient temperature, resulting in uneven surface temperature. In order to analyze the abnormal degree of the reactor surface caused by the environment, please refer to Figure 5 , which shows a flow chart of a method for obtaining an environmental parameter interference degree in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining an environmental parameter interference degree includes:

[0109] Step S301: Obtain all reference environmental parameters of the environmental parameter at the time to be analyzed within a preset surrounding range; obtain the environmental variation degree of the environmental parameter at the time to be analyzed according to the volatility of all reference environmental parameters of the environmental parameter.

[0110] Taking into account that the reactor surface is easily affected by changes in environmental parameters, resulting in uneven surface temperature, first of all, considering that the environmental parameters have a lag in affecting the reactor surface temperature, based on this, a time-forward method is used to determine the reference environmental parameters of the environmental parameters. By analyzing the volatility of all reference environmental parameters of the environmental parameters, the environmental variability of the environmental parameters is obtained. The greater the environmental variability, the greater the degree of change in the environmental parameters.

[0111] In one embodiment of the present invention, the environmental parameters at all sampling moments are sorted in chronological order, and the range of the environmental parameters including the first preset number of environmental parameters at the time to be analyzed is used as the preset surrounding range of the environmental parameters at the time to be analyzed, and each environmental parameter in the preset surrounding range is used as all reference environmental parameters in the preset surrounding range of the environmental parameters at the time to be analyzed. In one embodiment of the present invention, the preset number is 5, and the implementer can set it according to the implementation scenario. The variance of all reference environmental parameters of the environmental parameters is calculated to obtain the environmental variability of the environmental parameters. The volatility is reflected by the variance, where the environmental parameter refers to temperature.

[0112] Step S302: Acquire the reactor environment responsiveness according to the correlation between the environmental change degree and the abnormal degree of temperature distribution at continuous sampling moments.

[0113] In order to analyze the susceptibility of the reactor surface to changes in environmental parameters, the reactor environmental responsiveness is obtained by considering the correlation between the degree of environmental change and the degree of temperature distribution abnormality at continuous sampling moments. The greater the reactor environmental responsiveness, the more susceptible the reactor material is to changes in environmental parameters.

[0114] In one embodiment of the present invention, a method for obtaining the reactor environment responsiveness includes: counting the environmental variation degree at all sampling moments in sequence in chronological order to obtain environmental variation time series data; counting the temperature distribution abnormality degree at all sampling moments in sequence to obtain temperature distribution abnormality time series data; normalizing the Pearson correlation coefficient of the environmental variation time series data and the temperature distribution abnormality time series data to obtain the reactor environment responsiveness. It should be noted that the Pearson correlation coefficient is a prior art well known to those skilled in the art and will not be described in detail here.

[0115] In other embodiments of the present invention, the method for obtaining the reactor environmental responsiveness includes: calculating the difference between each environmental parameter and the corresponding environmental change degree of the previous environmental parameter in time sequence, and obtaining the local environmental change difference value of each environmental parameter; calculating the difference between the temperature distribution abnormality degree of each reactor thermal image and the previous reactor thermal image, and obtaining the local temperature change difference value of each reactor thermal image; calculating the mean of the absolute value of the difference between the local environmental change difference value and the local temperature change difference value at all sampling moments, and then normalizing to obtain the reactor environmental responsiveness. In one embodiment of the present invention, the linear normalization method is used for normalization, and the value range is limited to between 0 and 1.

[0116] Step S303: comprehensively analyzing the environmental change degree at the time to be analyzed and the reactor environmental responsiveness to obtain the environmental parameter interference degree of the thermal imaging to be filtered; the environmental change degree at the time to be analyzed and the reactor environmental responsiveness are both positively correlated with the environmental parameter interference degree.

[0117] Considering that the reactor material is more susceptible to changes in environmental parameters, it is more likely to cause abnormal temperature distribution on the reactor surface when the environmental parameters fluctuate, and the environmental parameter interference degree of the thermal imaging to be filtered is obtained. The greater the environmental parameter interference degree, the more likely the abnormality on the reactor surface is caused by abnormal environmental parameters.

[0118] In one embodiment of the present invention, the product of the environmental change degree at the time to be analyzed and the reactor environmental responsiveness is calculated to obtain the environmental parameter interference degree of the thermal imaging to be filtered.

[0119] Considering that the uneven distribution of reactor surface temperature is closely related to the effect of the previous cooling process of the reactor, the effect of the cooling process may affect the temperature inside the reactor, thereby affecting the synthesis rate. As the reaction proceeds, the temperature outside the reactor changes. In order to analyze the abnormality of the reactor surface caused by the cooling process, preferably, in one embodiment of the present invention, the method for obtaining the cooling heat exchange interference degree includes:

[0120] In the reactor thermal imaging, the mean temperature value of all pixels in the reactor surface area is calculated to obtain the reactor temperature value of the reactor thermal imaging; the absolute value of the difference between the reactor temperature values ​​of the reactor thermal imaging before and after cooling is calculated to obtain the cooling heat exchange value of the cooling process. The previous cooling process at the time to be analyzed is used as the cooling process affecting the reactor; the mean of the cooling heat exchange values ​​of all cooling processes is calculated to obtain the overall heat exchange value; the absolute value of the difference between the cooling heat exchange value affecting the cooling process of the reactor and the overall heat exchange value is calculated to obtain the cooling heat exchange interference degree of the thermal imaging to be filtered. It should be noted that, from step S1, it can be known that each cooling process corresponds to a cooling moment, and the cooling process corresponding to the previous cooling moment of the time to be analyzed in terms of timing is used as the cooling process affecting the reactor.

[0121] In order to analyze the cooling effect of the cooling process, it is necessary to analyze the change of the overall temperature of the reactor before and after the cooling process. First, it is necessary to obtain the reactor temperature value of the reactor thermal imaging according to the average temperature value of all pixel points of the temperature value of the reactor surface area in the reactor thermal imaging. The larger the reactor temperature value, the larger the overall temperature value of the reactor. Then obtain the cooling heat exchange value. The larger the cooling heat exchange value, the more obvious the overall cooling of the reactor caused by the cooling process. Considering that the cooling process causes abnormal surface temperature of the reactor and has hysteresis, the previous cooling process at the time to be analyzed is used as the cooling process affecting the reactor. Since excessive and small cooling heat exchange values ​​may lead to poor cooling process effects, the cooling heat exchange value can reflect the effect of the cooling process. Considering that the synthetic reactor monitoring system needs to ensure the effect of the cooling process in order to ensure the efficient operation of the reaction, the average of the cooling heat exchange values ​​of all cooling processes is calculated to obtain the overall heat exchange value; the overall heat exchange value represents the cooling heat exchange value corresponding to a good cooling effect. The greater the absolute value of the difference between the cooling heat exchange value affecting the reactor cooling process and the overall heat exchange value, the worse the cooling effect of the reactor cooling process, the greater the cooling heat exchange interference, and the greater the abnormality of the reactor surface caused by the cooling process.

[0122] In order to analyze the uneven temperature distribution of the reactor thermal imaging caused by noise when excluding abnormal environmental parameters and cooling effect, please refer to Figure 6 , which shows a flow chart of a method for obtaining noise interference level in one embodiment of the present invention. In one embodiment of the present invention, the method for obtaining noise interference level includes:

[0123] Step S311: obtaining the real interference degree of the thermal imaging to be filtered according to the environmental parameter interference degree and the cooling heat exchange interference degree; the environmental parameter interference degree and the cooling heat exchange interference degree are both positively correlated with the real interference degree.

[0124] The true interference reflects the abnormality of the reactor surface caused by environmental parameters and cooling effects. The larger the true interference value, the greater the abnormality.

[0125] In one embodiment of the present invention, the sum of the environmental parameter interference degree and the cooling heat exchange interference degree is calculated to obtain the real interference degree of the thermal imaging to be filtered. In other embodiments of the present invention, the product of the environmental parameter interference degree and the cooling heat exchange interference degree is calculated to obtain the real interference degree of the thermal imaging to be filtered.

[0126] Step S312: according to the abnormal degree of temperature distribution of the thermal image to be filtered and the real interference degree, the noise interference degree of the thermal image to be filtered is obtained; the abnormal degree of temperature distribution and the noise interference degree are positively correlated; the real interference degree and the noise interference degree are negatively correlated.

[0127] The noise interference reflects the degree of uneven temperature distribution in the reactor thermal imaging caused by noise, excluding abnormal environmental parameters and cooling effects. The greater the noise interference, the stronger the noise performance in the reactor thermal imaging.

[0128] In one embodiment of the present invention, the sum of the actual interference degree and the denominator adjustment factor is calculated, and the ratio of the temperature distribution abnormality degree to the sum is calculated to obtain the noise interference degree of the thermal imaging to be filtered. In one embodiment of the present invention, the denominator adjustment factor is used to ensure that the denominator is not 0. The denominator adjustment factor is a number greater than 0. This embodiment sets it to 0.001, and the implementer can set it according to the implementation scenario.

[0129] Step S4: setting a filter kernel according to the noise interference degree, filtering the thermal image to be filtered, and obtaining a filtered image of the reactor for monitoring.

[0130] The above steps obtain the noise interference degree that reflects the noise level in the reactor thermal imaging, so that when the noise performance is more obvious, the Gaussian filter kernel is set to be larger; when the noise performance is less obvious, the Gaussian filter kernel is set to be smaller, thereby improving the rationality of the Gaussian filter kernel setting, improving the filtering effect, and ensuring the accuracy of reactor abnormality monitoring.

[0131] Considering that the standard deviation is the core parameter of the Gaussian filter kernel, it determines the degree of filter smoothness. If the standard deviation is too small, the Gaussian filter kernel will be too small, resulting in that some pixels in the reactor thermal imaging may not be fully smoothed, affecting the accuracy of the filtering result; if the standard deviation is too large, the determined Gaussian filter kernel will be too large, resulting in the loss of details and features of the reactor thermal imaging, affecting the accuracy of the filtering result. Preferably, in one embodiment of the present invention, the method for obtaining the reactor filter image includes:

[0132] The noise interference is taken as the standard deviation obeyed by the Gaussian filter kernel, and the Gaussian filter kernel is used to perform Gaussian filtering on the thermal image to be filtered to obtain the reactor filter image. It should be noted that Gaussian filtering is a prior art well known to those skilled in the art and will not be described in detail here.

[0133] In other embodiments of the present invention, the noise interference degree can also be normalized to obtain a noise adjustment value; the product of the noise adjustment value and the preset size is calculated, and the product is rounded up to obtain a length to be processed. Since the size of the Gaussian filter kernel is usually an odd number, if the length to be processed is an even number, the length to be processed is added by 1 to obtain a target length; if the first length is an odd number, the first length is used as the target length; let the target length be L, and the size of the Gaussian filter kernel can be set to L L, use the Gaussian filter kernel to perform Gaussian filtering on the thermal image to be filtered, and obtain the reactor filter image. It should be noted that Gaussian filtering is a prior art well known to those skilled in the art, and will not be described in detail here. In one embodiment of the present invention, the preset size is 9, wherein the preset size implementer can set it according to the implementation scenario. When the preset size corresponding to the target length is used as the size of the Gaussian filter kernel for filtering, if the filtering result loses too many detail features, the preset size can be appropriately reduced.

[0134] Specifically, monitoring is performed through the reactor filter image, and through real-time monitoring and analysis, operational failures and abnormal problems of the reactor can be discovered in a timely manner, and appropriate measures can be taken to adjust and optimize the reactor.

[0135] The present invention also proposes a visual monitoring system for radiopharmaceutical synthesis reactors, see Figure 7 , which shows a structural diagram of a visual monitoring system for a radiopharmaceutical synthesis reactor provided by an embodiment of the present invention, the system includes: a data acquisition module 101, a temperature distribution abnormality degree analysis module 102, a noise interference degree analysis module 103 and a monitoring module 104.

[0136] The data acquisition module 101 is used to obtain the reactor data set of the synthesis reactor during the synthesis process; the reactor data set includes: environmental parameters and reactor thermal imaging at each sampling time, and reactor thermal imaging before and after cooling of each cooling process; the reactor thermal imaging includes the temperature value of each pixel point.

[0137] The temperature distribution abnormality degree analysis module 102 is used to obtain the abnormality degree of the temperature distribution of the reactor thermal imaging according to the difference in the temperature value distribution and the uneven distribution of the temperature value in the reactor thermal imaging.

[0138] The noise interference degree analysis module 103 is used to take any sampling moment as the moment to be analyzed, and take the reactor thermal image at the moment to be analyzed as the thermal image to be filtered; obtain the environmental parameter interference degree of the thermal image to be filtered according to the correlation between the fluctuation characteristics of the environmental parameters at continuous sampling moments and the degree of abnormality of the temperature distribution of the reactor thermal image, and the fluctuation characteristics of the environmental parameters at the moment to be analyzed; obtain the cooling heat exchange interference degree of the thermal image to be filtered according to the difference in temperature values ​​between the reactor thermal images before and after cooling during the cooling process; obtain the noise interference degree of the thermal image to be filtered according to the degree of abnormality of the temperature distribution of the thermal image to be filtered, the environmental parameter interference degree and the cooling heat exchange interference degree.

[0139] The monitoring module 104 is used to set a filter kernel according to the noise interference degree, filter the thermal image to be filtered, and obtain the reactor filtered image for monitoring.

[0140] In summary, the embodiment of the present invention provides a method and system for visual monitoring of a radiopharmaceutical synthesis reactor, firstly obtaining the abnormal degree of temperature distribution of the reactor thermal imaging; obtaining the environmental parameter interference degree of the thermal imaging to be filtered according to the correlation between the fluctuation characteristics of the environmental parameters at continuous sampling moments and the abnormal degree of temperature distribution of the reactor thermal imaging, as well as the fluctuation characteristics of the environmental parameters at the time to be analyzed; obtaining the cooling heat exchange interference degree of the thermal imaging to be filtered according to the temperature value difference between the thermal imaging of the reactor before and after cooling during the cooling process; obtaining the noise interference degree of the thermal imaging to be filtered according to the abnormal degree of temperature distribution of the thermal imaging to be filtered, the environmental parameter interference degree and the cooling heat exchange interference degree; setting the filter kernel according to the noise interference degree, filtering the thermal imaging to be filtered, and obtaining the reactor filtered image for monitoring. In the embodiment of the present invention, by constructing the noise interference degree reflecting the noise degree in the thermal imaging of the reactor, the reasonable setting of the Gaussian filter kernel is achieved, the Gaussian filter effect is improved, and the accuracy of the abnormal monitoring of the reactor is guaranteed.

[0141] It should be noted that: the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the visual monitoring system for radiopharmaceutical synthesis reactor and the visual monitoring method embodiment for radiopharmaceutical synthesis reactor provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0142] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0143] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for visual monitoring of a radiopharmaceutical synthesis reactor, characterized in that: The method comprises: Acquire a reactor data set of the synthesis reactor during the synthesis process; the reactor data set includes: environmental parameters and reactor thermal imaging at each sampling time, and reactor thermal imaging before and after cooling of each cooling process; the reactor thermal imaging includes the temperature value of each pixel point; the environmental parameter is temperature; According to the difference in temperature value distribution and the uneven distribution of temperature values ​​in the reactor thermal imaging, the abnormal degree of temperature distribution in the reactor thermal imaging is obtained; Taking any sampling moment as the moment to be analyzed, and taking the thermal image of the reactor at the moment to be analyzed as the thermal image to be filtered; obtaining the interference degree of the environmental parameter of the thermal image to be filtered according to the correlation between the fluctuation characteristics of the environmental parameters at the continuous sampling moments and the abnormal degree of the temperature distribution of the thermal image of the reactor, and the fluctuation characteristics of the environmental parameters at the moment to be analyzed; According to the temperature value difference between the thermal images of the reactor before and after cooling during the cooling process, the cooling heat exchange interference degree of the thermal image to be filtered is obtained; according to the abnormal degree of temperature distribution of the thermal image to be filtered, the environmental parameter interference degree and the cooling heat exchange interference degree, the noise interference degree of the thermal image to be filtered is obtained; Setting a filter kernel according to the noise interference degree, filtering the thermal image to be filtered, and obtaining a filtered image of the reactor for monitoring; The method for obtaining the abnormal degree of temperature distribution includes: Acquiring a reactor surface area and a background area of ​​the reactor thermal imaging according to a difference in pixel value distribution in the reactor thermal imaging; Dividing the surface area of ​​the reactor into blocks, and obtaining each surface block area in the thermal imaging of the reactor; According to the temperature difference between the surface block area and the background area and the unevenness of the temperature value in the surface block area, the degree of local temperature anomaly in the surface block area is obtained; According to the degree of abnormal local temperature in all surface block areas in the reactor thermal imaging, the degree of abnormal temperature distribution in the reactor thermal imaging is obtained; The method for obtaining the environmental parameter interference degree includes: Obtain all reference environmental parameters of the environmental parameter at the time to be analyzed within a preset surrounding range; obtain the environmental change degree of the environmental parameter at the time to be analyzed based on the volatility of all reference environmental parameters of the environmental parameter; Obtaining the reactor environment responsiveness according to the correlation between the degree of environmental change and the degree of abnormal temperature distribution at continuous sampling moments; The environmental parameter interference degree of the thermal imaging to be filtered is obtained by comprehensively considering the environmental change degree and the reactor environmental responsiveness at the time to be analyzed; the environmental change degree and the reactor environmental responsiveness at the time to be analyzed are both positively correlated with the environmental parameter interference degree; The method for obtaining the degree of environmental change comprises: sorting the environmental parameters at all sampling moments in chronological order, taking the range of the environmental parameters including the environmental parameters at the moment to be analyzed before a preset number as the preset surrounding range of the environmental parameters at the moment to be analyzed, taking each environmental parameter in the preset surrounding range as all reference environmental parameters of the environmental parameters at the moment to be analyzed in the preset surrounding range; calculating the variance of all reference environmental parameters of the environmental parameters to obtain the degree of environmental change of the environmental parameters; The method for obtaining the environmental parameter interference degree of the thermal imaging to be filtered includes: calculating the product of the environmental change degree at the time to be analyzed and the reactor environmental responsiveness to obtain the environmental parameter interference degree of the thermal imaging to be filtered; The method for obtaining the cooling heat exchange interference degree includes: In the reactor thermal imaging, the average temperature value of all pixel points in the reactor surface area is calculated to obtain the reactor temperature value of the reactor thermal imaging; Calculating the absolute value of the difference between the reactor temperature values ​​of the reactor thermal imaging before and after cooling to obtain the cooling heat exchange value of the cooling process; The previous cooling process at the time to be analyzed is taken as the cooling process affecting the reactor; The average of the cooling heat exchange values ​​of all cooling processes is calculated to obtain the overall heat exchange value; the absolute value of the difference between the cooling heat exchange value affecting the cooling process of the reactor and the overall heat exchange value is calculated to obtain the cooling heat exchange interference degree of the thermal imaging to be filtered.

2. The method for visually monitoring a radiopharmaceutical synthesis reactor according to claim 1, characterized in that: The method for obtaining the degree of local temperature anomaly in the surface block area includes: According to the difference in the overall distribution characteristics of the temperature values ​​of the surface block area and the background area, the thermal significance of the reactor is obtained; According to the fluctuation of the temperature values ​​of all the pixels in the surface block area, the temperature fluctuation degree is obtained; The temperature complexity is obtained according to the richness of the temperature values ​​of all pixels in the surface block area; According to the temperature fluctuation and the temperature complexity, the temperature non-uniformity of the surface block area is obtained; the temperature fluctuation and the temperature complexity are both positively correlated with the temperature non-uniformity; According to the thermal significance of the reactor and the temperature non-uniformity, the degree of local temperature anomaly in the surface block area is obtained; the thermal significance of the reactor and the degree of local temperature anomaly are negatively correlated; the temperature non-uniformity and the degree of local temperature anomaly are positively correlated; The method for obtaining the thermal visibility of the reactor comprises: calculating the average of the temperature values ​​of all the pixels in the surface block area as the block area temperature value of the surface block area; calculating the average of the temperature values ​​of all the pixels in the background area as the background area temperature value of the background area; calculating the difference between the block area temperature value and the background area temperature value; when the difference is greater than a preset threshold, setting the thermal visibility of the reactor to 1, and when the difference is not greater than the preset threshold, setting the thermal visibility of the reactor to 0; The method for obtaining the temperature fluctuation comprises: calculating the variance of the temperature values ​​of all pixels in the surface block area to obtain the temperature fluctuation; The method for obtaining the temperature complexity includes: taking the total number of all temperature value types in the surface block area as the temperature complexity; The method for obtaining the temperature non-uniformity comprises: calculating the product of the temperature fluctuation and the temperature complexity to obtain the temperature non-uniformity of the surface block area; The method for obtaining the degree of local temperature anomaly includes: calculating the temperature non-uniformity minus the thermal significance of the reactor to obtain the degree of local temperature anomaly in the surface block area.

3. The method for visually monitoring a radiopharmaceutical synthesis reactor according to claim 1, characterized in that: The method for obtaining the abnormal degree of temperature distribution in the reactor thermal imaging according to the abnormal degree of local temperature in all surface block areas in the reactor thermal imaging comprises: In reactor thermal imaging, the overall temperature non-uniformity of the reactor thermal imaging is obtained based on the difference between the local temperature anomaly degrees of all surface block areas; According to the overall distribution of the local temperature anomaly of all surface block areas, the overall temperature anomaly of the reactor thermal imaging is obtained; According to the overall temperature non-uniformity and the overall temperature anomaly, the degree of temperature distribution anomaly of the reactor thermal imaging is obtained; the overall temperature non-uniformity and the overall temperature anomaly are both positively correlated with the degree of temperature distribution anomaly; The method for obtaining the overall temperature anomaly comprises: calculating the average of the local temperature anomaly degrees of all surface block areas to obtain the overall temperature anomaly degree of the reactor thermal imaging; The method for obtaining the degree of abnormal temperature distribution includes: calculating the product of the overall temperature non-uniformity and the overall temperature abnormality to obtain the degree of abnormal temperature distribution of the reactor thermal imaging.

4. The method for visually monitoring a radiopharmaceutical synthesis reactor according to claim 3, characterized in that: The method for obtaining the overall temperature non-uniformity includes: In reactor thermal imaging, the absolute value of the difference in the degree of local temperature anomaly between every two surface block areas is calculated to obtain the local difference value, and the average of all local difference values ​​is calculated to obtain the overall temperature non-uniformity of the reactor thermal imaging.

5. The method for visually monitoring a radiopharmaceutical synthesis reactor according to claim 1, characterized in that: The method for obtaining the reactor environment responsiveness comprises: According to the time series order, the environmental change degree at all sampling moments is counted in turn to obtain the environmental change degree time series data; the temperature distribution abnormality degree at all sampling moments is counted in turn to obtain the temperature distribution abnormality degree time series data; the Pearson correlation coefficient of the environmental change degree time series data and the temperature distribution abnormality degree time series data is normalized to obtain the reactor environmental responsiveness.

6. The method for visually monitoring a radiopharmaceutical synthesis reactor according to claim 1, characterized in that: The method for obtaining the noise interference degree includes: According to the environmental parameter interference degree and the cooling heat exchange interference degree, the real interference degree of the thermal imaging to be filtered is obtained; the environmental parameter interference degree and the cooling heat exchange interference degree are both positively correlated with the real interference degree; According to the abnormal degree of temperature distribution of the thermal image to be filtered and the real interference degree, the noise interference degree of the thermal image to be filtered is obtained; the abnormal degree of temperature distribution and the noise interference degree are positively correlated; the real interference degree and the noise interference degree are negatively correlated; The method for obtaining the real interference degree comprises: calculating the sum of the environmental parameter interference degree and the cooling heat exchange interference degree to obtain the real interference degree of the thermal imaging to be filtered; The method for obtaining the noise interference degree includes: calculating the sum of the real interference degree and the denominator adjustment factor, calculating the ratio of the temperature distribution abnormality degree to the sum, and obtaining the noise interference degree of the thermal imaging to be filtered.

7. A visual monitoring system for a radiopharmaceutical synthesis reactor, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for visually monitoring a radiopharmaceutical synthesis reactor as described in any one of claims 1 to 6 are implemented.