Heating uniformity detection method and device

Abstract

The invention discloses a heating uniformity detection method and device, and belongs to the technical field of detection, and the method comprises the steps: obtaining a visible light image and an infrared image of a detected object; analyzing the obtained visible light image according to an optical flow algorithm, and calculating the local flow velocity; the obtained infrared image is analyzed according to the Planck's law of radiation, and the local temperature gradient is calculated; calculating a local uniformity score according to the calculated local flow velocity and local temperature gradient; calculating an overall uniformity score according to the local uniformity score obtained by step calculation; and judging the heating uniformity of the detected object according to the calculated overall uniformity score. And when the calculated overall uniformity score is within a preset threshold range, the detected object is heated uniformly. The problem that existing heating uniformity detection lacks heating uniformity comprehensive evaluation can be solved.

Description

Technical Field

[0001] The invention belongs to the field of detection technology, and particularly relates to a method and device for detecting heating uniformity. Background Art

[0002] The tobacco drying process is a key link in the tobacco processing process and directly affects the quality of the final tobacco product. The traditional tobacco drying process mainly relies on simple temperature control and airflow regulation equipment, but these methods are usually based on fixed control parameters and are difficult to adapt to the dynamically changing conditions of tobacco during the tobacco drying process. This fixed control mode often leads to uneven heating of tobacco during the tobacco drying process, resulting in local overheating or overcooling, which affects the drying quality of tobacco and causes uneven moisture distribution in tobacco, which in turn affects the aroma, taste and combustion performance of tobacco.

[0003] During the drying process, the changes in the fluidity, temperature and density of the tobacco are key factors that determine its heating uniformity. If the flow rate of the tobacco is uneven or locally retained, it will often lead to local overheating or insufficient drying of the tobacco; similarly, if the temperature field is unevenly distributed in the cavity, the difference in the heated area will affect the drying uniformity of the tobacco.

[0004] At present, some improved tobacco drying processes have introduced temperature detection and flow rate monitoring technologies, but these technologies usually detect temperature or flow rate alone, and lack methods for comprehensive analysis of flow rate, temperature and density. In addition, the data processing in the existing technology is mostly static, and it is impossible to respond to the complex working conditions of tobacco flow rate and temperature changes in real time, especially when the temperature gradient in multiple areas of the cavity is significant, and there is a lack of comprehensive evaluation of heating uniformity. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method and device for detecting thermal uniformity to solve the problem that the prior thermal uniformity detection lacks a comprehensive evaluation of thermal uniformity.

[0006] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions:

[0007] In a first aspect, the present invention provides a method for detecting thermal uniformity, comprising:

[0008] S1: Acquire visible light image and infrared image of the detected object;

[0009] S2: Analyze the visible light image obtained in step S1 according to the optical flow algorithm to calculate the local flow velocity;

[0010] Analyze the infrared image obtained in step S1 according to Planck's radiation law to calculate the magnitude of the local temperature gradient;

[0011] S3: Calculate the local uniformity score according to the local flow velocity and the local temperature gradient calculated in step S2;

[0012] S4: Calculate the overall uniformity score according to the local uniformity score calculated in step S3;

[0013] S5: judging the heating uniformity of the inspected object according to the overall uniformity score calculated in step S4;

[0014] When the overall uniformity score calculated in step S4 is within the preset threshold range, the object being inspected is heated uniformly.

[0015] In the above-mentioned method for detecting the uniformity of heating, step S1 comprises:

[0016] Acquire an image of the detected object in step S1 using a multispectral sensing system;

[0017] The multi-spectral sensing system includes a visible light sensor, an infrared sensor and a synchronization trigger; the visible light sensor is used to obtain a visible light image of the detected object, the infrared sensor is used to obtain an infrared image of the detected object, and the synchronization trigger is used to control the visible light sensor and the infrared sensor to collect images simultaneously.

[0018] In the aforementioned method for detecting uniformity of heating, step S1 further comprises preprocessing the acquired image, wherein the image preprocessing comprises image registration and image enhancement;

[0019] The image registration is used to geometrically align the acquired visible light image and infrared image so that the two image data correspond to the same spatial position;

[0020] The image enhancement is used to filter the acquired visible light image and infrared image respectively to reduce noise and enhance the contrast of the image.

[0021] In the above-mentioned method for detecting the uniformity of heating, the calculation of the local flow velocity in step S2 includes:

[0022] S211: Analyze the visible light image obtained in step S1 according to the optical flow algorithm, and select a local window in the obtained visible light image, where the local window includes N pixels;

[0023] S212: Establishing an optical flow constraint equation in the local window obtained in step S211 to solve the flow velocity vector;

[0024] Among them, the optical flow constraint equation is expressed as:

[0025] ,

[0026] Among them, V is a 2×1 column vector, which represents the flow velocity vector of the visible light image; A is an N×2 matrix, which represents the brightness gradient of the visible light image. ; b is an N×1 column vector, representing the rate of change of brightness over time, ;

[0027] S213: calculating the flow velocity magnitude of a pixel point according to the flow velocity vector V calculated in step S212, wherein the flow velocity magnitude of the pixel point is used to represent the local flow velocity magnitude;

[0028] The flow velocity of a pixel at time t The calculation formula is:

[0029] ,

[0030] Among them, u(x,y,t) is calculated by the optical flow constraint equation and represents the component of the flow velocity in the x direction; v(x,y,t) is calculated by the optical flow constraint equation and represents the component of the flow velocity in the y direction.

[0031] In the above-mentioned method for detecting the uniformity of heating, the calculation of the magnitude of the local temperature gradient in step S2 includes:

[0032] S221: According to Planck's radiation law and the wavelength of the infrared sensor, calculate the temperature expression of the detected object;

[0033] The relationship between temperature T and infrared radiation intensity R can be expressed by the following formula:

[0034] ,

[0035] Where R(λ,T) is the radiation intensity at wavelength λ, T is the temperature, h is Planck's constant, c is the speed of light, and k is the Boltzmann constant;

[0036] According to the relationship between the temperature T and the infrared radiation intensity R, the expression of the temperature T is obtained by simplifying and deforming;

[0037] S222: Calculate the temperature gradient according to the temperature expression obtained in step S221;

[0038] The calculation of the temperature gradient includes: by calculating the spatial rate of change of the temperature field, the temperature gradient ∇T(x,y,t) of a pixel at time t is obtained, and the formula is:

[0039] ,

[0040] in, represents the rate of change of temperature in the x direction, represents the rate of change of temperature in the y direction;

[0041] S223: Calculate the magnitude of a temperature gradient at a pixel according to the temperature gradient calculated in step S222, where the magnitude of the temperature gradient at a pixel is used to represent the magnitude of a local temperature gradient;

[0042] Use the following formula to calculate the temperature gradient of a pixel at time t , the formula is:

[0043] .

[0044] In the above-mentioned method for detecting the uniformity of heating, the local uniformity score in step S3 is The calculation formula is:

[0045] ,

[0046] in, Indicates the preset coefficient.

[0047] In the above-mentioned heating uniformity detection method, the calculation formula for calculating the overall uniformity score in step S4 is:

[0048] ,

[0049] Wherein, D represents the total area of ​​the visible light image acquired in step S1.

[0050] The aforementioned heating uniformity detection method, step S5 also includes, when the overall uniformity score calculated in step S4 is not within the preset threshold range, the detected object is heated unevenly, and the detection result of the uneven heating of the detected object is fed back to the control system, the control system outputs an adjustment process signal, and after the execution module receives and executes the process adjustment measures, jumps to step S1 to detect the heating uniformity of the detected object.

[0051] In the aforementioned method for detecting heating uniformity, the process adjustment measures include: adjusting wind speed and / or adjusting heating power.

[0052] In a second aspect, the present invention provides a heating uniformity detection device, comprising: an image acquisition module, a local calculation module, a local evaluation module, an overall evaluation module and a judgment output module;

[0053] The image acquisition module is used to: acquire a visible light image and an infrared image of the detected object;

[0054] The local calculation module is used to: analyze the visible light image acquired by the image acquisition module according to the optical flow algorithm to calculate the local flow velocity; analyze the infrared image acquired by the image acquisition module according to the Planck radiation law to calculate the local temperature gradient;

[0055] The local evaluation module is used to calculate the local uniformity score according to the local flow velocity and the local temperature gradient calculated by the local calculation module;

[0056] The overall evaluation module is used to: calculate the overall uniformity score according to the local uniformity score calculated by the local evaluation module;

[0057] The judgment output module is used to judge the heating uniformity of the detected object according to the overall uniformity score calculated by the overall evaluation module; when the overall uniformity score calculated by the overall evaluation module is within a preset threshold range, the detected object is heated uniformly.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention designs a method for coupling analysis of flow rate and temperature, provides a method for detecting heat uniformity by comprehensively considering flow rate and temperature changes, and solves the problem that existing heat uniformity detection lacks comprehensive evaluation of heat uniformity.

[0060] The present invention collects flow velocity and temperature data of the detected object through a multi-spectral sensor, calculates the local flow velocity using an optical flow algorithm, calculates the local temperature gradient according to Planck's radiation law, and analyzes the heating uniformity of the detected object in real time.

[0061] The present invention proposes an innovative coupling analysis method, defines the coupling method between flow velocity and temperature, and obtains a real-time overall heating uniformity score by integrating the local uniformity score of the entire image area.

[0062] The heating uniformity detection method of the present invention can detect areas with uneven heating and generate automatic adjustment suggestions, such as increasing the wind speed, adjusting the heating power, etc., to achieve dynamic regulation of the heating equipment, and real-time detection and comprehensive analysis of the flow state and temperature distribution of the detected object. It can effectively improve the problem of uneven heating during the heating process and improve the heating uniformity of the smoke detected object during the entire heating process.

[0063] The heating uniformity detection method of the present invention makes real-time feedback and closed-loop control possible during the heating process. When the object to be detected is tobacco in the drying process, the automation level of the drying process and the quality consistency of tobacco products are significantly improved. This method not only improves the uniformity of tobacco drying, but also reduces the occurrence of local overheating and insufficient drying, thereby improving the processing efficiency of tobacco and the market competitiveness of the final product. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a schematic flow chart of a method for detecting thermal uniformity according to Embodiment 1 of the present invention; DETAILED DESCRIPTION

[0065] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0066] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0067] Embodiment 1:

[0068] This embodiment provides a method for detecting thermal uniformity, including:

[0069] S1: Acquire visible light image and infrared image of the detected object;

[0070] S2: Analyze the visible light image obtained in step S1 according to the optical flow algorithm to calculate the local flow velocity;

[0071] Analyze the infrared image obtained in step S1 according to Planck's radiation law to calculate the magnitude of the local temperature gradient;

[0072] S3: Calculate the local uniformity score according to the local flow velocity and the local temperature gradient calculated in step S2;

[0073] S4: Calculate the overall uniformity score according to the local uniformity score calculated in step S3;

[0074] S5: judging the heating uniformity of the inspected object according to the overall uniformity score calculated in step S4;

[0075] When the overall uniformity score calculated in step S4 is within the preset threshold range, the object being inspected is heated uniformly.

[0076] The above-mentioned heating uniformity detection method can solve the problem that the existing heating uniformity detection lacks comprehensive evaluation of heating uniformity.

[0077] The specific implementation of the heating uniformity detection method of this embodiment is described below with examples.

[0078] Step S1 includes:

[0079] Acquire an image of the detected object in step S1 using a multispectral sensing system;

[0080] The multi-spectral sensing system includes a visible light sensor, an infrared sensor and a synchronization trigger; the visible light sensor is used to obtain a visible light image of the detected object, the infrared sensor is used to obtain an infrared image of the detected object, and the synchronization trigger is used to control the visible light sensor and the infrared sensor to collect images simultaneously.

[0081] When the detected object is tobacco in the drying process, the multispectral sensing system collects the flow rate and temperature data of the tobacco in real time. The visible light sensor is used to obtain the visible light image of the tobacco in the drying process, and the infrared sensor is used to obtain the infrared image of the tobacco in the drying process.

[0082] The visible light sensor of this embodiment: usually uses a camera with a wavelength of 400-700nm to capture the flow form and movement trajectory of tobacco. Infrared sensor: The infrared camera uses dual bands of 3-5μm and 8-14μm, corresponding to high temperature (such as within 550℃) and low temperature environment (such as 20℃ to 100℃). These bands can provide sufficient sensitivity for effective detection of tobacco and cavity surfaces with a wide temperature range. The cavity refers to the enclosed space in the tobacco drying equipment that contains and dries tobacco.

[0083] To ensure that the visible light image and the infrared image are captured at the same time, the system should be equipped with a synchronization trigger to control the two sensors to collect images at the same time. According to the movement speed of the tobacco, the frame rate of the visible light sensor and the infrared sensor needs to be dynamically adjusted. Generally speaking, the visible light sensor requires a higher frame rate (such as 120 frames per second) to capture the details of the high-speed moving tobacco; while the frame rate of the infrared sensor can be lower (30-60 frames per second) for temperature monitoring. Use timestamp technology to ensure that each set of visible light images and infrared images have the same timestamp for subsequent image fusion and data processing.

[0084] Step S1 also includes preprocessing the acquired image, wherein the image preprocessing includes image registration and image enhancement;

[0085] Image registration: Due to the different optical properties of visible light and infrared sensors, there may be differences in field of view and resolution. Through image registration technology, the visible light image and the infrared image are geometrically aligned to ensure that the two image data can accurately correspond to the same spatial position. Image registration technology can use feature point extraction and matching methods, specifically including: selecting multiple feature points (such as the edge or key nodes of tobacco) in the visible light image and infrared image, and registering them through image registration algorithms (such as SIFT, ORB, etc.) to ensure that the spatial positions of the images are consistent.

[0086] Image enhancement: Filter the collected visible light images and infrared images to reduce noise and enhance image contrast.

[0087] Different image enhancement methods can be used for visible light images and infrared images according to the image characteristics:

[0088] Visible light image processing: Gaussian filtering and other methods can be used to remove image noise, and edge detection can be used to enhance the motion contour of the tobacco.

[0089] Infrared image processing: Pseudo-color processing is performed on infrared images to convert temperature information into visual images. At the same time, non-uniformity correction (NUC) is used to improve image quality and reduce temperature measurement errors.

[0090] In step S2, the calculation of the local flow velocity is mainly based on the optical flow method, which is a calculation method for estimating the speed of an object by analyzing the pixel motion in continuous image frames.

[0091] Optical flow is a motion estimation method based on image processing. Optical flow is the instantaneous speed of pixel movement of a moving object in space on the observation imaging plane. It uses the changes in pixels in the time domain in an image sequence and the correlation between adjacent frames to find the correspondence between the previous frame and the current frame, thereby calculating the motion information of objects between adjacent frames.

[0092] The basic principle of the optical flow method is to calculate the speed and direction of the object in the image by comparing the grayscale value changes (or brightness changes) of pixels between adjacent frames. It is based on the following assumptions:

[0093] 1. The color between adjacent frames is constant (for grayscale images, the brightness is constant).

[0094] 2. The frame-taking time of adjacent video frames is continuous, or the movement of objects between adjacent frames is relatively "small".

[0095] 3. Maintain spatial consistency, that is, the pixels of the same sub-image have the same motion.

[0096] Based on the above assumptions, the optical flow method estimates the speed of an object in an image by analyzing the brightness changes caused by the movement of the object in the image. Assume that the pixel brightness value of the image at time t is I(x,y,t), where (x,y) is the pixel coordinate. Assume that the object moves at time t+Δt and moves to a new position (x+Δx,y+Δy), then the brightness value I(x+Δx,y+Δy,t+Δt) also changes accordingly.

[0097] According to the basic assumption of optical flow, the brightness of an object remains constant over a short period of time, that is:

[0098]

[0099] Taylor expansion of this equation, ignoring higher-order terms, yields the following optical flow constraint equation:

[0100]

[0101] in:

[0102]

[0103] This equation contains two unknowns: the velocity components u and v), but there is only one equation, so additional constraints need to be introduced to solve it.

[0104] To solve the optical flow vector, one of the most commonly used methods is the Lucas-Kanade optical flow algorithm. This method assumes that the movement of objects is consistent within a small local window Ω (such as Ω is a 3×3 pixel area). Based on this assumption, the system can use multiple pairs of equations to solve the optical flow vector.

[0105] Calculating the local flow velocity in step S2 includes:

[0106] S211: Analyze the visible light image obtained in step S1 according to the optical flow algorithm, and select a local window in the obtained visible light image, where the local window includes N pixels;

[0107] S212: Establishing an optical flow constraint equation in the local window obtained in step S211 to solve the flow velocity vector;

[0108] S213: Calculate the flow velocity magnitude of a pixel point according to the flow velocity vector V calculated in step S212, where the flow velocity magnitude of a pixel point is used to represent the local flow velocity magnitude.

[0109] Assume that there are N pixels in a local window Ω of the visible light image, and the motion of all pixels is the same. Therefore, an optical flow constraint equation can be generated for each pixel to solve the flow velocity vector, and N equations are obtained, which are expressed as follows:

[0110] , (1)

[0111] Wherein, A is an N×2 matrix, representing the brightness gradient of the visible light image; V is a 2×1 column vector, representing the flow velocity vector of the visible light image; and b is an N×1 column vector, representing the rate of change of brightness over time.

[0112] In order to solve V, the above formula (1) is transformed and simplified as:

[0113] , (2)

[0114] in, , ,

[0115] By solving the above equation (2), we can obtain the velocity components u and v of the tobacco in the local window Ω.

[0116] According to the calculated flow velocity vector V, the flow velocity of a pixel at time t is calculated using the following formula: , the formula is:

[0117] , (3)

[0118] Among them, u(x,y,t) and v(x,y,t) represent the components of flow velocity in the x and y directions respectively.

[0119] Calculating the local temperature gradient in step S2 includes:

[0120] S221: According to Planck's radiation law and the wavelength of infrared sensor, calculate the temperature expression of tobacco;

[0121] S222: Calculate the temperature gradient according to the temperature expression obtained in step S221;

[0122] S223: Calculate the magnitude of a temperature gradient at a pixel according to the temperature gradient calculated in step S222, where the magnitude of the temperature gradient at a pixel is used to represent the magnitude of a local temperature gradient;

[0123] Infrared image analysis temperature: The image obtained by the infrared sensor measures the temperature of the tobacco and the cavity through the law of spectral radiation. The intensity of infrared radiation energy is directly related to the temperature of the object. According to Planck's radiation law, combined with the band of the infrared sensor, the temperature of the tobacco surface is calculated. The relationship between temperature T and infrared radiation intensity R can be expressed by the following formula:

[0124] , (4)

[0125] Where R(λ,T) is the radiation intensity at wavelength λ, T is the temperature, h is Planck's constant, c is the speed of light, and k is the Boltzmann constant.

[0126] The above formula is simplified and transformed to obtain the expression of temperature T, and the expression of temperature gradient is calculated based on the expression of temperature T.

[0127] Calculation of temperature gradient: By calculating the spatial rate of change of the temperature field, the temperature gradient ∇T(x,y,t) of a pixel at time t is obtained. The formula is:

[0128] , (5)

[0129] in, represents the rate of change of temperature in the x direction, It represents the rate of change of temperature in the y direction.

[0130] The temperature gradient ∇T(x,y,t) is used to represent the rate of change of temperature in space to identify areas with uneven temperature distribution; areas with large temperature gradients may experience uneven heating.

[0131] Based on the calculated temperature gradient ∇T(x,y,t), the following formula is used to calculate the temperature gradient of a pixel at time t: , the formula is:

[0132] , (6)

[0133] In step S3, the coupled analysis method of velocity field and temperature field is used to define the local uniformity score , the overall evaluation of the heating uniformity during the drying process is as follows:

[0134] , (7)

[0135] in, Indicates the preset coefficient, used to avoid the denominator being 0. Calculated from the above formula (3), Calculated by the above formula (6), in this embodiment, Take 0.2, local uniformity score as follows:

[0136] , (8)

[0137] The higher the local uniformity score, the faster the flow rate and the smaller the temperature gradient in the area, and the more uniform the heating of the tobacco.

[0138] In step S4, the overall heating uniformity score S at time t is obtained by integrating the local uniformity score of the entire image area. avg (t), the formula is:

[0139] , (9)

[0140] Wherein, D represents the total area of ​​the visible light image acquired in step S1, wherein the visible light image has the same size as the infrared image.

[0141] Step S5 includes:

[0142] Calculate the overall heating uniformity score S at time t avg (t), through the preset threshold S threshold Compare and judge whether the heating uniformity meets the requirements. In this embodiment, the threshold is set to 75.

[0143] In this embodiment, an overall heating uniformity score greater than or equal to a threshold value indicates that the overall uniformity score is within a preset threshold range and the tobacco is heated evenly; an overall heating uniformity score less than a threshold value indicates that the overall uniformity score is not within a preset threshold range and the tobacco is heated unevenly.

[0144] When the overall heating uniformity score S is detected at time t avg (t) When the value is lower than the preset threshold value 75, the detection result of the uneven heating of the tobacco is fed back to the control system, and the control system outputs a process adjustment signal. After the execution module receives and executes the process adjustment measures, it jumps to step S1 to detect the heating uniformity of the tobacco.

[0145] The process adjustment measures generated by the control system include: adjusting the wind speed and / or adjusting the heating power.

[0146] 1. Adjust wind speed: Increase wind speed in areas with slower flow to improve uneven heating.

[0147] 2. Adjust the heating power: In areas with large temperature gradients, appropriately reduce the heating power to avoid local overheating.

[0148] The present invention can also continuously monitor the heating uniformity through real-time flow rate and temperature data feedback, and automatically adjust the process parameters according to the change of uniformity score to ensure that the entire tofu drying process maintains the best heating uniformity. This method realizes closed-loop control and further improves the automation and intelligence level of the tofu drying process.

[0149] The control system has a real-time feedback function. Through real-time monitoring data of flow rate and temperature, it automatically adjusts the operating parameters of the wire drying equipment, including wind speed, heating power and wire drying time, to ensure uniform heating.

[0150] The control system can make local adjustments based on areas where the tobacco is heated unevenly, dynamically change the heating intensity or wind speed distribution in local areas, and optimize heating uniformity.

[0151] The control system is connected to the central control system through the Internet of Things (IoT) technology, supporting remote monitoring and operation, and can upload real-time data to the cloud for analysis to further optimize the tofu drying process.

[0152] In order to verify the effectiveness of the heat uniformity detection method of the present invention, we designed a series of experiments to collect the flow rate, temperature and density data of tobacco under different working conditions, and analyzed them through the method of the present invention to evaluate its heat uniformity. The following is the data sample of the experiment and its analysis results.

[0153] Tobacco drying equipment: a standard industrial tobacco drying equipment equipped with visible light sensor and infrared sensor.

[0154] Sensor parameters: Visible light sensor: frame rate 120 fps, resolution 1920x1080. Infrared sensor: temperature measurement range 0-600℃, measurement accuracy ±2℃.

[0155] Experimental conditions: Three different combinations of wind speed and heating power were used to simulate different working conditions.

[0156] Experimental data

[0157] Working conditions Average flow rate (m / s) Flow rate variance Average temperature (℃) Temperature gradient (℃ / cm) <![CDATA[Overall heat uniformity score S avg > Thermal uniformity results Condition 1 30 0.15 95 0.4 50 Uneven Condition 2 36 0.25 95 0.4 60 Uneven Condition 3 36 0.25 85 0.2 90 Uniform

[0158] In the table, the average flow velocity of the working condition is the average value calculated by integrating the velocity of each pixel; the flow velocity variance is the variance calculated by the flow velocity of each pixel; the average temperature is the average value calculated by integrating the temperature of a single pixel; the temperature gradient is the average value of the temperature gradient of each pixel; and the overall thermal uniformity score is calculated by formula (9).

[0159] Data Analysis:

[0160] Condition 1

[0161] The tobacco flow rate is 30 m / s, the flow rate variance is 0.15, the tobacco temperature is 95 ℃, and the temperature gradient is 0.4 ℃ / cm. At this time, the calculated heating uniformity score of the tobacco is 50, and the tobacco is heated unevenly during the drying process.

[0162] Condition 2

[0163] Based on working condition 1, the process parameters such as fan speed, steam pressure, steam flow, and combustion furnace thermal power were adjusted. The tobacco flow rate was increased to 36 m / s, the flow rate variance was 0.25, the tobacco temperature was 95 ℃, and the temperature gradient was 0.4 ℃ / cm. At this time, the calculated heat uniformity score of the tobacco was 60. The heat uniformity of the tobacco was improved during the drying process, but it still did not meet the requirements.

[0164] Condition 3

[0165] Based on working condition 2, the process parameters such as fan speed, steam pressure, steam flow, and combustion furnace thermal power were adjusted to control the tobacco flow rate to 36 m / s, the flow rate variance to 0.25, the tobacco temperature to 85 ℃, and the temperature gradient to 0.2 ℃ / cm. At this time, the calculated heat uniformity score of the tobacco was 90, and the heat uniformity of the tobacco was greatly improved during the drying process, meeting the requirements.

[0166] Embodiment 2:

[0167] Based on the same inventive concept as the first embodiment, this embodiment introduces a heating uniformity detection device, including: an image acquisition module, a local calculation module, a local evaluation module, an overall evaluation module and a judgment output module;

[0168] The image acquisition module is used to: acquire a visible light image and an infrared image of the detected object;

[0169] The local calculation module is used to: analyze the visible light image acquired by the image acquisition module according to the optical flow algorithm to calculate the local flow velocity; analyze the infrared image acquired by the image acquisition module according to the Planck radiation law to calculate the local temperature gradient;

[0170] The local evaluation module is used to calculate the local uniformity score according to the local flow velocity and the local temperature gradient calculated by the local calculation module;

[0171] The overall evaluation module is used to: calculate the overall uniformity score according to the local uniformity score calculated by the local evaluation module;

[0172] The judgment output module is used to judge the heating uniformity of the detected object according to the overall uniformity score calculated by the overall evaluation module; when the overall uniformity score calculated by the overall evaluation module is within a preset threshold range, the detected object is heated uniformly.

[0173] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0174] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0177] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting thermal uniformity, characterized in that: include: S1: Acquire visible light image and infrared image of the detected object; S2: Analyze the visible light image obtained in step S1 according to the optical flow algorithm to calculate the local flow velocity; Analyze the infrared image obtained in step S1 according to Planck's radiation law to calculate the magnitude of the local temperature gradient; S3: Calculate the local uniformity score according to the local flow velocity and the local temperature gradient calculated in step S2; S4: Calculate the overall uniformity score according to the local uniformity score calculated in step S3; S5: judging the heating uniformity of the inspected object according to the overall uniformity score calculated in step S4; When the overall uniformity score calculated in step S4 is within the preset threshold range, the object being inspected is heated uniformly.

2. The method for detecting thermal uniformity according to claim 1, characterized in that: Step S1 includes: Using a multispectral sensing system to obtain an image of the detected object in step S1; The multi-spectral sensing system includes a visible light sensor, an infrared sensor and a synchronization trigger; the visible light sensor is used to obtain a visible light image of the detected object, the infrared sensor is used to obtain an infrared image of the detected object, and the synchronization trigger is used to control the visible light sensor and the infrared sensor to collect images simultaneously.

3. The method for detecting thermal uniformity according to claim 2, characterized in that: Step S1 also includes preprocessing the acquired image, wherein the image preprocessing includes image registration and image enhancement; The image registration is used to geometrically align the acquired visible light image and infrared image so that the two image data correspond to the same spatial position; The image enhancement is used to filter the acquired visible light image and infrared image respectively to reduce noise and enhance the contrast of the image.

4. The method for detecting thermal uniformity according to claim 3, characterized in that: Calculating the local flow velocity in step S2 includes: S211: Analyze the visible light image obtained in step S1 according to the optical flow algorithm, and select a local window in the obtained visible light image, where the local window includes N pixels; S212: Establishing an optical flow constraint equation in the local window obtained in step S211 to solve the flow velocity vector; Among them, the optical flow constraint equation is expressed as: ， Among them, V is a 2×1 column vector, which represents the flow velocity vector of the visible light image; A is an N×2 matrix, which represents the brightness gradient of the visible light image. ; b is an N×1 column vector, representing the rate of change of brightness over time, ; S213: calculating the flow velocity magnitude of a pixel point according to the flow velocity vector V calculated in step S212, wherein the flow velocity magnitude of the pixel point is used to represent the local flow velocity magnitude; The flow velocity of a pixel at time t The calculation formula is: ， Among them, u(x,y,t) is calculated by the optical flow constraint equation and represents the component of the flow velocity in the x direction; v(x,y,t) is calculated by the optical flow constraint equation and represents the component of the flow velocity in the y direction.

5. The method for detecting thermal uniformity according to claim 4, characterized in that: Calculating the local temperature gradient in step S2 includes: S221: According to Planck's radiation law and the wavelength of the infrared sensor, calculate the temperature expression of the detected object; The relationship between temperature T and infrared radiation intensity R can be expressed by the following formula: ， Where R(λ,T) is the radiation intensity at wavelength λ, T is the temperature, h is Planck's constant, c is the speed of light, and k is the Boltzmann constant; According to the relationship between the temperature T and the infrared radiation intensity R, the expression of the temperature T is obtained by simplifying and deforming; S222: Calculate the temperature gradient according to the temperature expression obtained in step S221; The calculation of the temperature gradient includes: by calculating the spatial rate of change of the temperature field, the temperature gradient ∇T(x,y,t) of a pixel at time t is obtained, and the formula is: ， in, represents the rate of change of temperature in the x direction, represents the rate of change of temperature in the y direction; S223: Calculate the magnitude of a temperature gradient at a pixel according to the temperature gradient calculated in step S222, where the magnitude of the temperature gradient at a pixel is used to represent the magnitude of a local temperature gradient; Use the following formula to calculate the temperature gradient of a pixel at time t , the formula is: 。 6. The method for detecting thermal uniformity according to claim 5, characterized in that: Local uniformity score in step S3 The calculation formula is: ， in, Indicates the preset coefficient.

7. The method for detecting thermal uniformity according to claim 6, characterized in that: The calculation formula for calculating the overall uniformity score in step S4 is: ， Wherein, D represents the total area of ​​the visible light image acquired in step S1.

8. The method for detecting thermal uniformity according to claim 1, characterized in that: Step S5 also includes: when the overall uniformity score calculated in step S4 is not within the preset threshold range, the detected object is heated unevenly, and the detection result of the uneven heating of the detected object is fed back to the control system, the control system outputs an adjustment process signal, and after the execution module receives and executes the process adjustment measures, it jumps to step S1 to detect the heating uniformity of the detected object.

9. The method for detecting thermal uniformity according to claim 8, characterized in that: The process adjustment measures include: adjusting wind speed and / or adjusting heating power.

10. A heating uniformity detection device, characterized in that: include: Image acquisition module, local calculation module, local evaluation module, overall evaluation module and judgment output module; The image acquisition module is used to: acquire a visible light image and an infrared image of the detected object; The local calculation module is used to: analyze the visible light image acquired by the image acquisition module according to the optical flow algorithm to calculate the local flow velocity; analyze the infrared image acquired by the image acquisition module according to the Planck radiation law to calculate the local temperature gradient; The local evaluation module is used to calculate the local uniformity score according to the local flow velocity and the local temperature gradient calculated by the local calculation module; The overall evaluation module is used to: calculate the overall uniformity score according to the local uniformity score calculated by the local evaluation module; The judgment output module is used to judge the heating uniformity of the detected object according to the overall uniformity score calculated by the overall evaluation module; when the overall uniformity score calculated by the overall evaluation module is within a preset threshold range, the detected object is heated uniformly.

Images