Radio frequency power supply temperature prediction method, device, equipment and medium

Abstract

The invention relates to a radio frequency power supply temperature prediction method and device, equipment and a medium, and the method comprises the steps: obtaining an infrared image sequence of a radio frequency power supply, and extracting a plurality of key frames; acquiring a rectangular area with increased brightness; setting a sliding window with a corresponding size; sliding the sliding window along the buffer edge of the brightness-increased rectangular area to obtain a target rectangular area as a foreground area; obtaining an outer surface infrared temperature distribution diagram in the foreground area of the radio frequency power supply image according to the surface material and the shooting distance parameter; the internal temperature is calculated through the heat conduction model, and the internal temperature trend after the preset time period is predicted. By adopting the scheme, the internal temperature trend of the radio frequency power supply can be accurately and reliably predicted, so that potential safety hazards can be found in time.

Description

Technical Field

[0001] The present disclosure relates to the field of electrical digital data processing, and in particular to a method, device, equipment and medium for predicting the temperature of a radio frequency power supply. Background Art

[0002] RF power supply is a power supply device whose main function is to convert direct current into high-frequency alternating current. Its operating frequency is generally above 1KHz and can even reach hundreds of megahertz. This high-frequency characteristic makes RF power supply widely used in many fields such as mechanical processing, medical equipment, communication systems, and environmental monitoring.

[0003] Temperature monitoring measurement and prediction are key to ensuring the normal operation of RF power supplies. RF power supplies generate heat during operation. If the temperature is too high, it may cause damage to the internal components of the power supply, thus affecting the stability and reliability of the power supply. Therefore, temperature monitoring and measurement of RF power supplies can detect abnormal conditions in time, take necessary measures to cool down or maintain, and ensure the normal operation of the power supply.

[0004] In the prior art, when measuring the temperature of an RF power supply, a common method is to collect an image of the RF power supply for temperature recognition. However, the heat generated by the RF power supply during operation will be converted into radiation, which may be confused with other radiation in the background area, thereby reducing the clarity of the image and making the outline of the main shell of the RF power supply difficult to identify. In addition, RF power supplies usually have the characteristics of high power output and may experience rapid changes in power in a short period of time. Such rapid changes may cause the brightness of the main shell of the RF power supply in the image to change rapidly, and the outline of the RF power supply often cannot be accurately identified. Then, the temperature measurement area may be incorrectly positioned outside the power supply or at a non-critical position, resulting in the measured temperature data failing to truly reflect the actual temperature of the RF power supply.

[0005] In addition, the current RF power supply temperature measurement only measures the outer surface temperature. During the operation of the RF power supply, there are a large number of electronic components inside the RF power supply, such as inductors, capacitors, transistors, etc., which are closely arranged according to a specific circuit layout. This complex layout makes the heat distribution inside the power supply uneven, especially when running at high power, the internal temperature is often higher than the surface temperature, and may show nonlinear and dynamic characteristics. If only the surface temperature is measured, it will be impossible to accurately understand the actual temperature of the internal components, thereby underestimating the heat accumulation inside the power supply, resulting in the inability to obtain a comprehensive and accurate evaluation result.

[0006] Therefore, a method is needed to accurately and reliably predict the internal temperature trend of an RF power supply. Summary of the invention

[0007] The present disclosure provides a method, device, equipment and medium for predicting the temperature of a radio frequency power supply, so as to realize a method for accurately and reliably predicting the internal temperature trend of a radio frequency power supply.

[0008] In a first aspect, the present disclosure provides a method for predicting temperature of a radio frequency power supply, comprising:

[0009] Acquire an infrared image sequence of the radio frequency power source and extract multiple key frames;

[0010] Acquire the brightness matrices of the multiple key frames, perform a variance operation on the brightness matrix value of the current frame image and the brightness matrix value of the previous frame image in the multiple key frame images, and acquire a brightness-increased rectangular area;

[0011] Setting a sliding window of a corresponding size according to the size of the brightness-increased rectangular area;

[0012] Buffering the edge of the brightness-increased rectangular area to obtain a buffer edge, sliding the sliding window along the buffer edge and adjusting the real-time sliding step length to obtain a target rectangular area as a foreground area;

[0013] Acquire the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum, and acquire the infrared temperature distribution map of the outer surface in the foreground area of ​​the radio frequency power source image according to the surface material and shooting distance parameters;

[0014] A heat conduction model between the outer surface infrared temperature and the internal temperature is established, the internal temperature is calculated by the heat conduction model, and the internal temperature trend after a preset time period is predicted.

[0015] According to the RF power supply temperature prediction method provided by the present disclosure, extracting multiple key frames includes:

[0016] Calculating the similarity between each image and adjacent images in the infrared image sequence of the radio frequency power source, and taking images with similarity greater than a first threshold as a first image set;

[0017] Determine the total number M of pixels in each image in the first image set; determine the number N of pixels in each image in the first image set whose grayscale value is greater than a second threshold;

[0018] S=N / M is calculated, and if S is greater than a third threshold, the image is extracted as a key frame.

[0019] According to the RF power supply temperature prediction method provided by the present disclosure, setting a sliding window of a corresponding size according to the size of the brightness-increasing rectangular area includes the following steps:

[0020] When the sliding window slides along the long side of the rectangular area with increased brightness, the length and width of the rectangular area with increased brightness are proportionally reduced to serve as the length and width of the sliding window respectively;

[0021] When the sliding window slides along the wide side of the brightness increasing rectangular area, the length and width of the brightness increasing rectangular area are proportionally reduced to serve as the width and length of the sliding window respectively.

[0022] According to the RF power supply temperature prediction method provided by the present disclosure, buffering the edge of the brightness-increased rectangular area to obtain a buffer edge includes:

[0023] The pixel brightness value of the edge of the rectangular area with increased brightness is obtained, and the pixel brightness value is used as the outer buffer distance of the corresponding pixel. The shape of the buffer zone at the intersection of the length and width of the rectangular area is a right angle to obtain the buffer edge.

[0024] According to the RF power supply temperature prediction method provided by the present disclosure, obtaining the surface material and shooting distance parameters of the RF power supply according to the infrared spectrum includes:

[0025] According to the radiation characteristics of the outer surface of the RF power source, its surface material is obtained through a machine learning algorithm;

[0026] The distance between the infrared sensor and the radio frequency power source is calculated by the infrared sensor's sensitivity to infrared radiation and the infrared spectrum radiation energy attenuation rate.

[0027] According to the RF power supply temperature prediction method provided by the present disclosure, calculating the internal temperature through a heat conduction model includes:

[0028] Calculate the foreground temperature T1 at the center of the foreground area;

[0029] The foreground image is used as a mask to cover the key frame image, and the background image is obtained after the mask area is deleted from the key frame image;

[0030] The temperature values ​​of the four corner points of the background image, namely, the upper left, lower left, upper right, and lower right, are obtained and averaged to obtain the background temperature T2.

[0031] According to the RF power supply temperature prediction method provided in the present disclosure, the internal temperature is calculated by the heat conduction model as follows:

[0032] T n =T1+P* / L / K;

[0033] Among them, T n is the internal temperature, P is the RF power consumption, L is the length of the foreground area, and K is the width of the foreground area.

[0034] In a second aspect, the present disclosure further provides a radio frequency power supply temperature prediction device, comprising:

[0035] A key frame acquisition module acquires an infrared image sequence of the radio frequency power source and extracts a plurality of key frames;

[0036] A brightness increase rectangular region extraction module is used to obtain the brightness matrices of the multiple key frames, and to perform a variance operation on the brightness matrix value of the current frame image and the brightness matrix value of the previous frame image in the multiple key frame images to obtain a brightness increase rectangular region;

[0037] A sliding window setting module, which sets a sliding window of a corresponding size according to the size of the brightness-enhanced rectangular area;

[0038] a foreground area acquisition module, which performs buffer processing on the edge of the brightness-increased rectangular area to obtain a buffer edge, slides the sliding window along the buffer edge and adjusts the real-time sliding step length to obtain a target rectangular area as the foreground area;

[0039] An outer surface infrared temperature distribution module obtains the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum, and obtains an outer surface infrared temperature distribution map in the foreground area of ​​the radio frequency power source image according to the surface material and shooting distance parameters;

[0040] The internal temperature trend prediction module establishes a heat conduction model between the outer surface infrared temperature and the internal temperature, calculates the internal temperature through the heat conduction model, and predicts the internal temperature trend after a preset time period.

[0041] Compared with the prior art, the disclosed method, device, equipment and medium for predicting the temperature of a radio frequency power supply include: obtaining an infrared image sequence of a radio frequency power supply and extracting multiple key frames; obtaining a rectangular area with increased brightness; setting a sliding window of corresponding size; sliding the sliding window along the buffer edge of the rectangular area with increased brightness to obtain a target rectangular area as a foreground area; obtaining an infrared temperature distribution map of the outer surface in the foreground area of ​​the radio frequency power supply image according to the surface material and shooting distance parameters; calculating the internal temperature through a heat conduction model, and predicting the internal temperature trend after a preset time period. By adopting the above scheme, the internal temperature trend of the radio frequency power supply can be accurately and reliably predicted, thereby timely discovering safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present disclosure, the drawings required for use in the embodiments or prior art descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 is a flow chart of a method for predicting temperature of a radio frequency power supply provided by the present disclosure;

[0044] Figure 2 is a schematic diagram of a foreground area and a background area provided by the present disclosure;

[0045] Figure 3 It is a schematic diagram of a radio frequency power supply temperature prediction device provided by the present disclosure;

[0046] Figure 4 A schematic diagram of the electronic device provided in the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions in the present disclosure will be clearly and completely described below in conjunction with the drawings in the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0048] RF power supply is a high-performance, multifunctional power supply device. Temperature is one of the key factors affecting the performance and stability of RF power supply. RF power supply generates heat during operation. If the temperature is too high, it may cause the performance of the internal components of the power supply to degrade or even be damaged. Through temperature measurement, the operating temperature of the RF power supply can be monitored in real time to ensure that it operates within a safe temperature range and avoid performance degradation or equipment damage caused by excessive temperature.

[0049] The principle of infrared temperature measurement is mainly based on the relationship between infrared radiation and object temperature. Any object, as long as its temperature is above absolute zero, will emit infrared radiation. The intensity of this radiation is closely related to the temperature of the object. The higher the temperature, the greater the radiation intensity. Infrared temperature measurement uses infrared sensors to receive infrared radiation emitted by the object being measured and convert it into an electrical signal. By measuring the size of this electrical signal, the temperature of the object can be inferred.

[0050] Infrared temperature measurement technology has the characteristics of non-contact measurement, and can measure temperature without interfering with the normal operation of the RF power supply. Since the RF power supply may generate dangerous conditions such as high voltage and high current during operation, the use of traditional contact temperature measurement methods may pose safety hazards. Using infrared measurement technology to detect the internal temperature of the RF power supply has the advantages of non-contact, high sensitivity, fast response, large-area scanning imaging, and high-precision measurement. These advantages make infrared temperature measurement technology play an increasingly important role in temperature monitoring and fault prevention of RF power supplies.

[0051] Figure 1is a flow chart of a method for predicting the temperature of a radio frequency power supply provided by the present disclosure, such as Figure 1 As shown, the method includes:

[0052] Step 1: Obtain an infrared image sequence of the RF power source and extract multiple key frames;

[0053] Specifically, key frames are images that can represent significant features and important content in an infrared image sequence. In an infrared image sequence, there are often many similar or repeated frames, which may not have much difference in content. By extracting key frames, redundant information can be removed and only the most representative frames are retained, thereby greatly reducing the workload of data processing and analysis.

[0054] Step 2: Obtain the brightness matrices of the multiple key frames, perform a variance operation on the brightness matrix value of the current frame image and the brightness matrix value of the previous frame image in the multiple key frame images, and obtain a brightness-increased rectangular area;

[0055] Specifically, the pixel brightness variance matrix represents the degree of fluctuation of the pixel brightness value. The larger the variance, the greater the brightness fluctuation. In an infrared image of an RF power source, the area with the largest brightness fluctuation is the edge junction of the foreground area and the background area. The foreground area represents the temperature of the RF power source, and the background area represents the ambient temperature. The obvious temperature difference between the two causes the pixel brightness variance to fluctuate violently. The area within the junction is the rectangular area with increased brightness.

[0056] like Figure 2 As shown, the infrared image consists of two parts: the foreground area and the background area. The foreground area refers to the core outline of the RF power supply itself, which can directly and comprehensively reflect the temperature of the RF power supply; the background area refers to the environment and objects outside the foreground area. The background may include a laboratory bench, other equipment, walls, doors and windows, etc. Interference factors in the background will affect the recognition of the core outline of the RF power supply.

[0057] Furthermore, for two adjacent key frames, first, the variance between the brightness of their corresponding pixels is calculated. For each pixel position, the square of the brightness difference between the pixel values ​​of the two images at that position is calculated. Then, the squared brightness differences of all pixel positions are summed and divided by the total number of pixels to obtain the pixel variance. Then, a pixel brightness variance matrix is ​​constructed: the calculated pixel brightness variance is organized into a matrix according to the position information of the image, namely the pixel variance matrix. The size of this matrix is ​​the same as that of the original image, and each element represents the brightness variance value of the corresponding pixel position. Finally, the connected area with a variance greater than the preset threshold is set as a brightness-increasing rectangular area, where the variance fluctuates greatly and the brightness changes greatly.

[0058] Step 3: setting a sliding window of a corresponding size according to the size of the brightness-increased rectangular area;

[0059] Specifically, a suitable sliding window size can reduce unnecessary computation. If the window size is too large, more pixels in non-target areas will be processed, increasing the computational burden; if the window size is too small, the target area may not be fully covered, resulting in information loss. By setting a sliding window of the corresponding size by increasing the size of the rectangular area with brightness, it can ensure that the computation is minimized while covering the target.

[0060] Step 4: Buffering the edge of the brightness-enhanced rectangular area to obtain a buffer edge, sliding the sliding window along the buffer edge and adjusting the real-time sliding step length to obtain a target rectangular area as the foreground area;

[0061] By buffering the edges of the lines in the rectangular area outward, the coverage of the edge area can be expanded, allowing the edge detection algorithm to more accurately identify and locate the edge. This helps reduce edge detection errors caused by factors such as image noise, blur, or lighting changes.

[0062] The processing of the sliding window can accurately identify the outline of the RF power supply, so that the measured temperature data truly reflects the actual temperature of the RF power supply.

[0063] Step 5: obtaining the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum, and obtaining the infrared temperature distribution map of the outer surface in the foreground area of ​​the radio frequency power source image according to the surface material and shooting distance parameters;

[0064] Step 6: Establish a heat conduction model between the outer surface infrared temperature and the internal temperature, calculate the internal temperature through the heat conduction model, and predict the internal temperature trend after a preset time period.

[0065] Compared with the prior art, the present invention adopts the above scheme to obtain the infrared image sequence of the RF power supply and extract multiple key frames; obtain the rectangular area with increased brightness; set a sliding window of corresponding size; slide the sliding window along the buffer edge to obtain the target rectangular area as the foreground area; obtain the outer surface infrared temperature distribution map in the foreground area of ​​the RF power supply image according to the surface material and shooting distance parameters; calculate the internal temperature through the heat conduction model, and predict the internal temperature trend after a preset time period. By adopting the above scheme, the internal temperature trend of the RF power supply can be accurately and reliably predicted, so as to timely discover safety hazards.

[0066] In one implementation, extracting multiple key frames in step 1 includes:

[0067] S11: calculating the similarity between each image and adjacent images in the infrared image sequence of the radio frequency power source, and taking images with similarity greater than a first threshold as a first image set;

[0068] First, the image sequence often contains a lot of redundant information, that is, the content of multiple consecutive frames of images is similar or almost the same. By calculating the similarity, the first image set containing more key information can be quickly extracted at the beginning, which greatly reduces the invalid images in the infrared image sequence, thereby improving the efficiency of subsequent image processing and analysis. This is especially important for real-time applications or RF power supply temperature detection that requires fast response;

[0069] S12: Determine the total number M of pixels in each image in the first image set; determine the number N of pixels in each image in the first image set whose grayscale value is greater than a second threshold;

[0070] Secondly, the key frames containing key information can be accurately extracted through the number of effective pixels in the first image set, thereby ensuring the quality and accuracy of the extraction results.

[0071] For example, the total number of pixels of an image in the first image set is 2000, and it is determined that the number of pixels in the image whose grayscale values ​​are greater than 100 is 1500.

[0072] S13: Calculate S=N / M. If S is greater than a third threshold, extract the image as a key frame.

[0073] Through the formula, it can be determined that the number of valid pixels in the image is 75%. When 75% is greater than the third threshold of 60%, the image is extracted as a key frame, that is, the key frame image contains more valid information.

[0074] In one implementation, setting a sliding window of a corresponding size according to the size of the brightness-increased rectangular area in step 3 comprises the following steps:

[0075] The sliding window starts from the long side of the rectangular area with increasing brightness and slides clockwise: First, let the sliding window move to the right along the upper edge of the rectangular area with increasing brightness until it reaches the right edge. Then, let the sliding window move downward along the right edge until it reaches the lower edge. Next, let the window move to the left along the lower edge until it returns to the left edge. Finally, let the sliding window move upward along the left edge until it returns to the starting position;

[0076] When the sliding window slides along the long side of the rectangular area with increased brightness, the length and width of the rectangular area with increased brightness are proportionally reduced to serve as the length and width of the sliding window respectively;

[0077] When the sliding window slides along the wide side of the brightness increasing rectangular area, the length and width of the brightness increasing rectangular area are proportionally reduced to serve as the width and length of the sliding window respectively.

[0078] In one implementation, the buffering of the edge of the brightness-increased rectangular area to obtain the buffered edge in step 4 includes:

[0079] The pixel brightness value of the edge of the rectangular area with increased brightness is obtained, and the pixel brightness value is used as the outer buffer distance of the corresponding pixel. The shape of the buffer zone at the intersection of the length and width of the rectangular area is a right angle to obtain the buffer edge.

[0080] In one embodiment, obtaining the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum in step 5 includes:

[0081] According to the radiation characteristics of the outer surface of the RF power supply, the surface material is obtained through machine learning algorithms, including:

[0082] (5.1) Data collection: Collect radiation characteristic data of the outer surface of RF power sources made of various materials, including measurement data of electromagnetic radiation, thermal radiation and other characteristics. Ensure the diversity and representativeness of the data set to cover a variety of possible materials and radiation characteristics;

[0083] (5.2) Feature extraction: Extract key features such as frequency response, radiation intensity, and radiation pattern from radiation characteristic data, so as to fully reflect the differences between different materials;

[0084] (5.3) Dataset preparation: Pair the extracted features with the corresponding surface material labels to form the dataset required for supervised learning. Preprocess the dataset, such as normalization and standardization, to improve the performance of the machine learning model;

[0085] (5.4) Model selection: Select appropriate machine learning algorithms, such as support vector machine (SVM), random forest, neural network, etc.;

[0086] (5.5) Model training and optimization: Use the extracted features and labels to train the machine learning model. Optimize the performance of the model through cross-validation, adjusting hyperparameters, etc. Evaluate the model's accuracy, recall, and other indicators to ensure that it can meet the needs of actual applications;

[0087] (5.6) Model verification and testing: Use an independent test dataset to verify the performance of the model. Compare the difference between the surface material predicted by the model and the actual material to evaluate the generalization ability of the model.

[0088] The distance between the infrared sensor and the radio frequency power source is calculated by the infrared sensor's sensitivity to infrared radiation and the infrared spectrum radiation energy attenuation rate.

[0089] Among them, the attenuation rate of infrared spectrum radiation energy is related to distance. Generally, as the distance increases, the infrared radiation energy will decay according to the law. As the shooting distance increases, the infrared temperature measurement will show a downward trend. This is because the infrared radiation emitted by the surface of the object decreases as the distance increases with the infrared sensor, and the energy received by the infrared sensor will also decrease.

[0090] In one embodiment, calculating the internal temperature by using a heat conduction model in step 6 includes:

[0091] Calculate the foreground temperature T1 at the center of the foreground area;

[0092] The foreground image is used as a mask to cover the key frame image, and the background image is obtained after the mask area is deleted from the key frame image;

[0093] The temperature values ​​of the four corner points of the background image, namely, the upper left, lower left, upper right, and lower right, are obtained and averaged to obtain the background temperature T2.

[0094] The calculation of the internal temperature by the heat conduction model also includes:

[0095] (6.1) Establishing a heat conduction model: Establishing a heat conduction model based on the geometry of the RF power source, material properties, and heat source distribution;

[0096] (6.2) Set boundary conditions: Use the known surface temperature of the RF power source as the boundary condition of the heat conduction model;

[0097] (6.3) Set initial conditions: determine the temperature distribution of the RF power supply at the initial time;

[0098] (6.4) Solve the heat conduction equation: Use numerical methods to solve the heat conduction equation. Through iterative calculations, the temperature is gradually updated until a steady state is reached or certain convergence conditions are met;

[0099] (6.5) Calculate the internal temperature: During the solution process, record the temperature changes at various locations inside the RF power supply. The value is the internal temperature calculated using the heat conduction model.

[0100] In one implementation, step 6 specifically further includes:

[0101] The internal temperature is calculated by the heat conduction model as:

[0102] T n =T1+P* / L / K;

[0103] Among them, T n is the internal temperature, P is the RF power consumption, L is the length of the foreground area, and K is the width of the foreground area.

[0104] A radio frequency power supply temperature prediction device provided by the present disclosure is described below. The detection system described below and the detection method described above can be referenced to each other.

[0105] like Figure 3 As shown, a radio frequency power supply temperature prediction device comprises:

[0106] A key frame acquisition module acquires an infrared image sequence of the radio frequency power source and extracts a plurality of key frames;

[0107] A brightness increase rectangular region extraction module is used to obtain the brightness matrices of the multiple key frames, and to perform a variance operation on the brightness matrix value of the current frame image and the brightness matrix value of the previous frame image in the multiple key frame images to obtain a brightness increase rectangular region;

[0108] A sliding window setting module, which sets a sliding window of a corresponding size according to the size of the brightness-enhanced rectangular area;

[0109] a foreground area acquisition module, which performs buffer processing on the edge of the brightness-increased rectangular area to obtain a buffer edge, slides the sliding window along the buffer edge and adjusts the real-time sliding step length to obtain a target rectangular area as the foreground area;

[0110] An outer surface infrared temperature distribution module obtains the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum, and obtains an outer surface infrared temperature distribution map in the foreground area of ​​the radio frequency power source image according to the surface material and shooting distance parameters;

[0111] The internal temperature trend prediction module establishes a heat conduction model between the outer surface infrared temperature and the internal temperature, calculates the internal temperature through the heat conduction model, and predicts the internal temperature trend after a preset time period.

[0112] An electronic device provided in an embodiment of the present application is Figure 4 As shown, the electronic device includes a processor 402 and a memory 401, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the above embodiment when executing the computer program.

[0113] See also Figure 4 The electronic device further includes: a bus 403 and a communication interface 404, a processor 402, a communication interface 404 and a memory 401 are connected via the bus 403; the processor 402 is used to execute an executable module stored in the memory 401, such as a computer program.

[0114] The memory 401 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 404 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0115] The bus 403 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0116] Among them, the memory 401 is used to store programs, and the processor 402 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 402 or implemented by the processor 402.

[0117] The processor 402 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 402. The above processor 402 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor can be combined to execute. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 401, and the processor 402 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.

[0118] Corresponding to the above-mentioned RF power supply temperature prediction method, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned RF power supply temperature prediction method.

[0119] The RF power supply temperature prediction device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0120] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0121] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0124] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the RF power supply temperature prediction method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0125] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0126] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for predicting the temperature of a radio frequency power supply, characterized in that: The following steps are involved: Acquire an infrared image sequence of the radio frequency power source and extract multiple key frames; Acquire the brightness matrices of the multiple key frames, perform a variance operation on the brightness matrix value of the current frame image and the brightness matrix value of the previous frame image in the multiple key frame images, and acquire a brightness-increased rectangular area; Setting a sliding window of a corresponding size according to the size of the brightness-increased rectangular area; Buffering the edge of the brightness-increased rectangular area to obtain a buffer edge, sliding the sliding window along the buffer edge and adjusting the real-time sliding step length to obtain a target rectangular area as a foreground area; Acquire the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum, and acquire the infrared temperature distribution map of the outer surface in the foreground area of ​​the radio frequency power source image according to the surface material and shooting distance parameters; A heat conduction model between the outer surface infrared temperature and the internal temperature is established, the internal temperature is calculated by the heat conduction model, and the internal temperature trend after a preset time period is predicted.

2. The method for predicting the temperature of a radio frequency power supply according to claim 1, characterized in that: The extracting of multiple key frames comprises: Calculating the similarity between each image and adjacent images in the infrared image sequence of the radio frequency power source, and taking images with similarity greater than a first threshold as a first image set; Determine the total number M of pixels in each image in the first image set; determine the number N of pixels in each image in the first image set whose grayscale value is greater than a second threshold; S=N / M is calculated, and if S is greater than a third threshold, the image is extracted as a key frame.

3. The method for predicting the temperature of a radio frequency power supply according to claim 1, characterized in that: The step of setting a sliding window of a corresponding size according to the size of the brightness-increasing rectangular area comprises the following steps: When the sliding window slides along the long side of the brightness increasing rectangular area, the length and width of the brightness increasing rectangular area are proportionally reduced to serve as the length and width of the sliding window respectively; When the sliding window slides along the wide side of the brightness increasing rectangular area, the length and width of the brightness increasing rectangular area are proportionally reduced to serve as the width and length of the sliding window respectively.

4. The method for predicting the temperature of a radio frequency power supply according to claim 1, characterized in that: The buffering process for the edge of the brightness-increased rectangular area to obtain a buffered edge comprises: The pixel brightness value of the edge of the rectangular area with increased brightness is obtained, and the pixel brightness value is used as the outer buffer distance of the corresponding pixel. The shape of the buffer zone at the intersection of the length and width of the rectangular area is a right angle to obtain the buffer edge.

5. The method for predicting the temperature of a radio frequency power supply according to claim 1, characterized in that: The method of obtaining the surface material and shooting distance parameters of the radio frequency power source includes: According to the radiation characteristics of the outer surface of the RF power source, the outer surface material is obtained through a machine learning algorithm; The distance between the infrared sensor and the radio frequency power source is calculated by the infrared sensor's sensitivity to infrared radiation and the infrared spectrum radiation energy attenuation rate.

6. The method for predicting the temperature of a radio frequency power supply according to claim 1, characterized in that: Calculating the internal temperature by using a heat conduction model includes: Calculate the foreground temperature T1 at the center of the foreground area; The foreground image is used as a mask to cover the key frame image, and the background image is obtained after the mask area is deleted from the key frame image; The temperature values ​​of the four corner points of the background image, namely, the upper left, lower left, upper right, and lower right, are obtained and averaged to obtain the background temperature T2.

7. The method for predicting the temperature of a radio frequency power supply according to claim 6, characterized in that The internal temperature is calculated by the heat conduction model as: T n =T1+P* / L / K; Among them, T n is the internal temperature, P is the RF power consumption, L is the length of the foreground area, and K is the width of the foreground area.

8. A radio frequency power supply temperature prediction device, characterized in that: include: A key frame acquisition module acquires an infrared image sequence of the radio frequency power source and extracts a plurality of key frames; A brightness increase rectangular region extraction module is used to obtain the brightness matrices of the multiple key frames, and to perform a variance operation on the brightness matrix value of the current frame image and the brightness matrix value of the previous frame image in the multiple key frame images to obtain a brightness increase rectangular region; A sliding window setting module, which sets a sliding window of a corresponding size according to the size of the brightness-enhanced rectangular area; a foreground area acquisition module, which performs buffer processing on the edge of the brightness-increased rectangular area to obtain a buffer edge, slides the sliding window along the buffer edge and adjusts the real-time sliding step length to obtain a target rectangular area as the foreground area; An outer surface infrared temperature distribution module obtains the surface material and shooting distance parameters of the radio frequency power source according to the infrared spectrum, and obtains an outer surface infrared temperature distribution map in the foreground area of ​​the radio frequency power source image according to the surface material and shooting distance parameters; The internal temperature trend prediction module establishes a heat conduction model between the outer surface infrared temperature and the internal temperature, calculates the internal temperature through the heat conduction model, and predicts the internal temperature trend after a preset time period.

9. An electronic device, comprising: processor; A memory storing a program, wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer-readable storage medium stores instructions or computer programs, and when the instructions or computer programs are executed on a device, the device executes the method according to any one of claims 1 to 7.

Images