A method and apparatus for detecting uniformity of heating

Abstract

The application discloses a kind of heated uniformity detection method and device, belong to detection technical field, method includes: the visible light image and infrared image of the detected object are acquired;According to the optical flow algorithm analysis acquired visible light image, the flow rate size of local is calculated;According to the analysis of acquired infrared image, the temperature gradient size of local is calculated according to Planck radiation law;According to the flow rate size of local and the temperature gradient size of local calculated, the local uniformity score is calculated;According to the local uniformity score calculated in step, the overall uniformity score is calculated;According to the overall uniformity score calculated, the heated uniformity of the detected object is judged;When the overall uniformity score calculated is in the preset threshold range, then the detected object is heated uniformly.The application can solve the problem that existing heated uniformity detection lacks heated uniformity comprehensive evaluation.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of detection, and particularly relates to a heated uniformity detection method and device. BACKGROUND

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

[0003] During the cut tobacco process, the changes in the flowability, temperature and density of the cut tobacco are key factors in determining its heated uniformity. If the flow rate of the cut tobacco is uneven or locally stagnant, it often leads to local overheating or insufficient drying of the cut tobacco; similarly, if the temperature field is unevenly distributed in the cavity, the differences in the heated areas will affect the drying uniformity of the cut tobacco.

[0004] Currently, some improved cut tobacco processes have introduced temperature detection and flow rate monitoring technology, but these technologies usually detect temperature or flow rate separately, lacking a method for comprehensive analysis of flow rate, temperature and density. In addition, the data processing in the prior art is mostly static, unable to respond in real time to the complex working conditions of the cut tobacco flow rate and temperature changes, especially when the temperature gradient in the cavity is significant, lacking a comprehensive evaluation of the heated uniformity. SUMMARY

[0005] The purpose of the present application is to overcome the deficiencies in the prior art, and to provide a heated uniformity detection method and device, solving the problem of lack of comprehensive evaluation of heated uniformity in the prior art.

[0006] To solve the above technical problems, the present application is implemented by using the following technical solutions:

[0007] In a first aspect, the present application provides a heated uniformity detection method, comprising:

[0008] S1: obtaining a visible light image and an infrared image of the detected object;

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

[0010] According to the Planck radiation law, the infrared image obtained in step S1 is analyzed to calculate the local temperature gradient;

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

[0012] S4: calculating a global uniformity score according to the local uniformity score calculated in step S3;

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

[0014] When the global uniformity score calculated in step S4 is within a preset threshold range, the detected object is heated uniformly.

[0015] The heating uniformity detection method described above, step S1 includes:

[0016] The image of the detected object in step S1 is obtained by using a multi-spectral sensing system;

[0017] The multi-spectral sensing system includes a visible light sensor, an infrared sensor, and a synchronous 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 synchronous trigger is used to control the visible light sensor and the infrared sensor to collect images at the same time.

[0018] The heating uniformity detection method described above, step S1 further includes image preprocessing of the obtained image, and the image preprocessing includes image registration and image enhancement;

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

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

[0021] The heating uniformity detection method described above, the calculation of the local flow rate in step S2 includes:

[0022] S211: according to the optical flow algorithm, analyzing the visible light image obtained in step S1, selecting a local window in the obtained visible light image, and the local window includes N pixel points;

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

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

[0025] ,

[0026] wherein V is a 2x1 column vector representing the flow velocity vector of the visible light image; A is an Nx2 matrix representing the brightness gradient of the visible light image, ; b is an Nx1 column vector representing the rate of change of brightness over time, ;

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

[0028] the flow velocity of the pixel point at time t is calculated according to the following formula:

[0029] ,

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

[0031] The aforementioned heated uniformity detection method, wherein the step S2 of calculating the local temperature gradient includes:

[0032] S221: calculating the temperature expression of the detected object according to the Planck radiation law and in combination with the waveband of the infrared sensor;

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

[0034] ,

[0035] wherein R(λ, T) is the radiation intensity at the wavelength λ, T is the temperature, h is the Planck constant, c is the speed of light, and k is the Boltzmann constant;

[0036] simplifying and deforming the relationship between the temperature T and the infrared radiation intensity R to obtain the temperature expression of T;

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

[0038] The calculation of the temperature gradient includes: calculating the spatial variation rate of the temperature field to obtain the temperature gradient of a pixel point at time t, denoted as ∇T(x, y, t), according to the following formula:

[0039] ,

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

[0041] S223: calculating a size of the one-pixel temperature gradient according to the temperature gradient calculated in step S222, the size of the one-pixel temperature gradient being used to represent the local temperature gradient size;

[0042] The size of the one-pixel temperature gradient at time t is calculated using the following formula , and the formula is

[0043] .

[0044] The aforementioned heat uniformity detection method, the calculation formula of the local uniformity score in step S3 is

[0045] ,

[0046] wherein, a represents a preset coefficient.

[0047] The aforementioned heat uniformity detection method, the calculation formula of the overall uniformity score in step S4 is

[0048] ,

[0049] wherein, D represents the total area of the visible light image obtained in step S1.

[0050] The aforementioned heat uniformity detection method, step S5 further comprises: when the overall uniformity score calculated in step S4 is not within the preset threshold range, the detected object is unevenly heated, and the detection result of the detected object being unevenly heated is fed back to a control system, the control system outputs an adjustment process signal, and after a process adjustment measure is received and executed by an execution module, the heat uniformity of the detected object is detected in step S1.

[0051] The aforementioned heat uniformity detection method, the process adjustment measure comprises: adjusting the wind speed and / or adjusting the heating power.

[0052] In a second aspect, the present application provides a heat 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 a detected object.

[0054] The local calculation module is used to analyze the visible light image acquired by the image acquisition module according to an optical flow algorithm, and calculate the local flow rate size; and analyze the infrared image acquired by the image acquisition module according to the Planck radiation law, and calculate the local temperature gradient size.

[0055] ​​The local evaluation module is configured to calculate a local uniformity score according to the local flow rate and the local temperature gradient calculated by the local calculation module.

[0056] The overall evaluation module is configured to calculate an overall uniformity score according to the local uniformity scores calculated by the local evaluation module.

[0057] The judgment and output module is configured to judge the heating uniformity of the detected object according to the overall uniformity score calculated by the overall evaluation module; and 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 application has the following beneficial effects:

[0059] The present application provides a heating uniformity detection method that comprehensively considers the flow rate and temperature changes, solving the problem of lack of comprehensive evaluation of heating uniformity in the prior art.

[0060] The present application collects flow rate and temperature data of the detected object through a multi-spectral sensor, calculates the local flow rate using an optical flow algorithm, and calculates the local temperature gradient according to the Planck radiation law, thereby realizing real-time analysis of the heating uniformity of the detected object.

[0061] The present application proposes an innovative coupling analysis method, defines a coupling method between flow rate and temperature, and calculates the overall heating uniformity score in real time by integrating the local uniformity scores of the entire image area.

[0062] The heating uniformity detection method of the present application can detect areas of uneven heating and generate automatic adjustment suggestions, such as increasing the wind speed or adjusting the heating power, thereby realizing dynamic regulation and control of the heating equipment, real-time detection and comprehensive analysis of the flow state and temperature distribution of the detected object, effectively improving the problem of uneven heating during the heating process, and improving the heating uniformity of the detected object during the entire heating process.

[0063] Through the heating uniformity detection method of the present application, real-time feedback and closed-loop control during the heating process become possible, which significantly improves the automation level of the drying process and the quality consistency of tobacco products when the detected object is tobacco. 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 DRAWINGS

[0064] Figure 1 is a flowchart of the heating uniformity detection method of embodiment 1 of the present application; DETAILED DESCRIPTION

[0065] The technical solutions of the present application will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments and the embodiments can be combined with each other.

[0066] The term "and / or" in this paper is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the associated objects before and after are in an "or" relationship.

[0067] Embodiment one:

[0068] The embodiment provides a heat uniformity detection method, comprising:

[0069] S1: obtaining a visible light image and an infrared image of the detected object;

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

[0071] According to the Planck radiation law, the infrared image obtained in step S1 is analyzed to calculate the local temperature gradient;

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

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

[0074] S5: judging the heat uniformity of the detected 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 detected object is uniformly heated.

[0076] The heat uniformity detection method described above can solve the problem of lack of comprehensive evaluation of heat uniformity in existing heat uniformity detection.

[0077] The specific implementation of the heat uniformity detection method of the embodiment will be described below.

[0078] Step S1 includes:

[0079] A multispectral sensing system is used to obtain the image of the detected object in step S1;

[0080] The multispectral sensing system comprises a visible light sensor, an infrared sensor, and a synchronous trigger; the visible light sensor is used to acquire a visible light image of the detected object, the infrared sensor is used to acquire an infrared image of the detected object, and the synchronous trigger is used to control the visible light sensor and the infrared sensor to collect images at the same time.

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

[0082] The visible light sensor of the embodiment: generally uses a camera with a wave band of 400-700 nm to capture the flow pattern and motion trajectory of the tobacco. The infrared sensor: the infrared camera uses dual wave bands of 3-5 μm and 8-14 μm, which correspond to high-temperature (such as within 550℃) and low-temperature environments (such as 20℃ to 100℃), respectively. These wave 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 cut tobacco equipment that contains and dries the 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 synchronous trigger to control the two sensors to collect images at the same time. According to the motion speed of the tobacco, the frame rate of the visible light sensor and the infrared sensor needs to be dynamically adjusted. Generally, the visible light sensor needs 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. The timestamp technology is used to ensure that each set of visible light image and infrared image has the same timestamp, so as to facilitate subsequent image fusion and data processing.

[0084] Step S1 further comprises pre-processing the acquired images, and the image preprocessing comprises image registration and image enhancement;

[0085] Image registration: due to the difference in optical characteristics of the visible light and infrared sensors, differences in field of view and resolution may occur. Through image registration technology, the visible light image and the infrared image are geometrically aligned to ensure that the two image data can be accurately corresponded to the same spatial position. The image registration technology can adopt the method of feature point extraction and matching, specifically including: selecting a plurality of feature points (such as the edges or key nodes of the tobacco) in the visible light image and the infrared image, and performing registration through an image registration algorithm (such as SIFT, ORB, etc.) to ensure the spatial position consistency of the images.

[0086] Image enhancement: the collected visible light image and infrared image are subjected to filtering processing to reduce noise and enhance the contrast of the image.

[0087] The visible light image and the infrared image can be selected according to the image characteristics Different image enhancement methods can be selected:

[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 profile of the tobacco.

[0089] Infrared image processing: The infrared image is processed by pseudo-color processing to convert temperature information into a visual image, and non-uniformity correction (NUC) is used to improve image quality and reduce temperature measurement errors.

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

[0091] Optical flow is a motion estimation method based on image processing. Optical flow is the instantaneous speed of the pixel motion of a moving object in the observation imaging plane. It is a method that uses the changes of pixels in the time domain and the correlation between adjacent frames to find the corresponding relationship between the previous frame and the current frame, and then calculates the motion information of the object between adjacent frames.

[0092] The basic principle of the optical flow method is to compare the gray value changes (or brightness changes) of the pixel points between adjacent frames to calculate the motion speed and direction of the object in the image. 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 time of taking adjacent video frames is continuous, or the motion of the object between adjacent frames is relatively small.

[0095] 3. Maintain spatial consistency, i.e., the same sub-image pixel points have the same motion.

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

[0097] According to the basic assumption of optical flow, the brightness of the object remains unchanged in a short time, i.e.:

[0098]

[0099] A Taylor expansion of this equation, neglecting higher order terms, gives the following optical flow constraint equation:

[0100]

[0101] where:

[0102]

[0103] This equation contains two unknowns: the flow velocity components u and v, but only one equation, so an additional constraint is needed to solve for the flow velocity.

[0104] One of the most common methods for solving the flow velocity vector is the Lucas-Kanade optical flow algorithm. This method assumes that the motion of an object is consistent within a small local window Ω (e.g., a 3x3 pixel region), and based on this assumption, the system can solve the flow velocity vector using multiple equations.

[0105] The calculation of the local flow velocity in step S2 includes:

[0106] S211: According to the optical flow algorithm, analyze the visible light image obtained in step S1, and select a local window in the obtained visible light image, the local window includes N pixel points;

[0107] S212: Establish 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 of a pixel point according to the flow velocity vector V calculated in step S212, the flow velocity of the pixel point is used to represent the local flow velocity.

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

[0110] , (1)

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

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

[0113] , (2)

[0114] where: , ,

[0115] Solve the above formula (2), the flow velocity components u and v of the tobacco in the local window Ω can be obtained.

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

[0117] , (3)

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

[0119] The calculation of the local temperature gradient size in step S2 includes:

[0120] S221: According to Planck's radiation law, combined with the wave band of the infrared sensor, the temperature expression of the tobacco is calculated;

[0121] S222: According to the temperature expression obtained in step S221, the temperature gradient is calculated;

[0122] S223: According to the temperature gradient calculated in step S222, the temperature gradient size of a pixel point is calculated, which is used to represent the local temperature gradient size;

[0123] Infrared image analysis temperature: The image obtained by the infrared sensor measures the temperature of the tobacco and the cavity through the spectral radiation law. The intensity of infrared radiation energy is directly related to the temperature of the object. According to Planck's radiation law, combined with the wave 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 represented by the following formula:

[0124] , (4)

[0125] Where R(λ, T) is the radiation intensity at wavelength λ, T is the temperature, h is the Planck constant, c is the speed of light, and k is the Boltzmann constant.

[0126] According to the above formula, the expression of temperature T is simplified and deformed, and the expression of temperature gradient is calculated according to the expression of temperature T.

[0127] Temperature gradient calculation: By calculating the spatial variation rate of the temperature field, the temperature gradient ∇T(x, y, t) of a pixel point at time t is obtained, the formula is:

[0128] , (5)

[0129] Where represents the variation rate of temperature in the x direction, 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 of uneven temperature distribution; areas with large temperature gradients may have uneven heating phenomena.

[0131] According to the calculated temperature gradient ∇T(x, y, t), the size of the temperature gradient of a pixel point at time t is calculated using the following formula , the formula is:

[0132] , (6)

[0133] In step S3, a local uniformity score is defined using a coupling analysis method of flow velocity field and temperature field to overall evaluate the uniformity of heating during the tobacco cutting process, the formula is:

[0134] , (7)

[0135] wherein, represents a preset coefficient, used to avoid a denominator of 0, calculated from the above formula (3), calculated from the above formula (6), in the embodiment, 0.2, the local uniformity score is as follows:

[0136] , (8)

[0137] The higher the local uniformity score, the faster the flow velocity 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 avg (t) at time t is obtained by integrating the local uniformity scores of the entire image area, the formula is:

[0139] , (9)

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

[0141] Step S5 includes:

[0142] After calculating the overall heating uniformity score S avg (t) at time t, it is determined whether the heating uniformity meets the requirements by comparing with a preset threshold S threshold . In the embodiment, the threshold is set to 75.

[0143] In this embodiment, an overall heating uniformity score greater than or equal to a threshold indicates that the overall uniformity score is within the preset threshold range and the tobacco is heated evenly; an overall heating uniformity score less than a threshold indicates that the overall uniformity score is not within the 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 temperature is below the preset threshold of 75, the detection result of uneven heating of the tobacco is fed back to the control system. The control system outputs an adjustment process 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 the wind speed: Increase the wind speed in areas with slower airflow to improve uneven heating.

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

[0148] This invention can also continuously monitor the heating uniformity of the wire drying process through real-time flow rate and temperature data feedback, and automatically adjust process parameters based on changes in the uniformity score to ensure optimal heating uniformity throughout the entire wire drying process. This method achieves closed-loop control, further improving the automation and intelligence level of the wire drying process.

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

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

[0151] The control system is connected to the central control system via 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 wire drying process.

[0152] To verify the effectiveness of the heating uniformity detection method of the present invention, we designed a series of experiments to collect data on the flow rate, temperature, and density of tobacco under different operating conditions, and analyzed the data using the method of the present invention to evaluate its heating uniformity. The following are the experimental data samples and their analysis results.

[0153] Wire drying equipment: A standard industrial wire drying machine equipped with a visible light sensor and an 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 to simulate different working conditions.

[0156] Experimental data

[0157] Operating condition Average flow rate (m / s) Flow rate variance Average temperature (°C) Temperature gradient (°C / cm) Overall uniformity of heating score S avg ]] Heating uniformity results Operating condition 1 30 0.15 95 0.4 50 Uneven Operating condition 2 36 0.25 95 0.4 60 Uneven Operating condition 3 36 0.25 85 0.2 90 Uniform

[0158] In the table, the average flow rate of the working condition is the average value of the velocity integral of each pixel point measured; the flow rate variance is calculated according to the flow rate of each pixel point; the average temperature is the average value of the temperature integral of a single pixel point; the temperature gradient is the average value of the temperature gradient of each pixel point; the overall heating uniformity score is calculated by formula (9).

[0159] Data analysis:

[0160] Working 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 tobacco heating uniformity score is 50, and the tobacco is not uniformly heated during the drying process.

[0162] Working condition 2

[0163] On the basis of working condition 1, adjust the fan speed, steam pressure, steam flow, and combustion furnace power process parameters. The tobacco flow rate is increased to 36 m / s, the flow rate variance is 0.25, the tobacco temperature is 95℃, and the temperature gradient is 0.4℃ / cm. At this time, the calculated tobacco heating uniformity score is 60, and the tobacco heating uniformity during the drying process is improved, but still not up to the requirements.

[0164] Working condition 3

[0165] On the basis of working condition 2, adjust the fan speed, steam pressure, steam flow, and combustion furnace power process parameters. The tobacco flow rate is controlled to be 36 m / s, the flow rate variance is 0.25, the tobacco temperature is 85℃, and the temperature gradient is reduced to 0.2℃ / cm. At this time, the calculated tobacco heating uniformity score is 90, and the tobacco heating uniformity during the drying process is greatly improved, meeting the requirements.

[0166] Example two:

[0167] Based on the same inventive concept as example one, this example introduces a heated 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;

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

[0169] The local calculation module is configured to calculate the local flow rate according to the optical flow algorithm analysis of the visible light image acquired by the image acquisition module; and calculate the local temperature gradient according to the Planck radiation law analysis of the infrared image acquired by the image acquisition module;

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

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

[0172] The judgment output module is configured to judge the heated uniformity of the detected object according to the overall uniformity score calculated by the overall evaluation module; and 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 should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take 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 code.

[0174] The present application is described with reference to flowcharts and / or block diagrams according to the method, device (system) and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing apparatus to produce a machine, so that the instructions executed by the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one block or multiple blocks.

[0175] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The functions of a flow or multiple flows and / or a block or multiple blocks in accordance with the present application can be implemented with software, hardware or with a combination of software and / or firmware. Figure 1

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The functions of a flow or multiple flows and / or a block or multiple blocks in accordance with the present application can be implemented with software, hardware or with a combination of software and / or firmware. Figure 1

[0177] The above description is merely that of the preferred embodiments of the application and modifications and alterations are possible without departing from the principles of the application as set forth in the claims.​​

Claims

1. A method for detecting heating uniformity, characterized in that, include: S1: Acquire visible light and infrared images of the object being detected; S2: Based on the visible light image obtained in step S1 using the optical flow algorithm analysis, select a local window within the acquired visible light image, where the local window comprises N pixels; calculate the flow velocity of a pixel at time t. , used to represent the magnitude of local flow velocity; Based on Planck's law of radiation, analyze the infrared image obtained in step S1, and calculate the magnitude of the temperature gradient at a pixel at time t. , used to represent the magnitude of the local temperature gradient; (x, y) are pixel coordinates; S3: Calculate the local uniformity score based on the local flow velocity and local temperature gradient calculated in step S2; Local uniformity score The calculation formula is: ， in, This indicates a preset coefficient used to avoid a denominator of 0; S4: Calculate the overall uniformity score based on the local uniformity score obtained in step S3; the formula for calculating the overall uniformity score is: ， Where D represents the total area of ​​the visible light image obtained in step S1; S5: Determine the heating uniformity of the tested object based on the overall uniformity score calculated in step S4. If the overall uniformity score calculated in step S4 is within the preset threshold range, then the detected object is heated uniformly.

2. The method for detecting heating uniformity according to claim 1, characterized in that, Step S1 includes: A multispectral sensing system is used to acquire an image of the object being detected in step S1; The multispectral sensing system includes a visible light sensor, an infrared sensor, and a synchronization trigger; the visible light sensor is used to acquire a visible light image of the object being detected, the infrared sensor is used to acquire an infrared image of the object being detected, and the synchronization trigger is used to control the visible light sensor and the infrared sensor to acquire images simultaneously.

3. The method for detecting heating uniformity according to claim 2, characterized in that, Step S1 also includes preprocessing the acquired image, including 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 location; The image enhancement is used to filter the acquired visible light and infrared images respectively to reduce noise and enhance image contrast.

4. The method for detecting heating uniformity according to claim 3, characterized in that, Step S2 involves calculating the local flow velocity magnitude, including: S211: Based on the visible light image obtained in step S1 of the optical flow algorithm analysis, a local window is selected in the obtained visible light image, and the local window includes N pixels. S212: Establish optical flow constraint equations and solve for velocity vectors within the local window obtained in step S211; The optical flow constraint equation is expressed as: ， Where V is a 2×1 column vector representing the velocity vector of the visible light image; A is an N×2 matrix representing the brightness gradient of the visible light image, where the pixel brightness value of the image at time t is I(x,y,t). The first column of matrix A represents the brightness gradient of each pixel in the x-direction, and the second column of matrix A represents the brightness gradient of each pixel in the y-direction. b is an N×1 column vector representing the rate of change of brightness over time. ; S213: Calculate the flow velocity magnitude of a pixel based on the flow velocity vector V calculated in step S212. The flow velocity magnitude of a pixel is used to represent the local flow velocity magnitude. The flow rate of a pixel at time t The calculation formula is: ， Where 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 heating uniformity according to claim 4, characterized in that, Step S2 involves calculating the magnitude of the local temperature gradient, including: S221: Based on Planck's law of radiation 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 Boltzmann's constant; The expression for temperature T is obtained by simplifying and transforming the relationship between temperature T and infrared radiation intensity R. S222: Calculate the temperature gradient based on the temperature expression obtained in step S221; The calculation of the temperature gradient includes: obtaining the temperature gradient ∇T(x,y,t) of a pixel at time t by calculating the spatial rate of change of the temperature field, as shown in the formula: ， in, This represents the rate of change of temperature in the x-direction. This represents the rate of change of temperature in the y-direction; S223: The magnitude of the temperature gradient of a pixel is calculated based on the temperature gradient obtained in step S222. The magnitude of the temperature gradient of a pixel is used to represent the magnitude of the local temperature gradient. The temperature gradient of a pixel at time t is calculated using the following formula. The formula is: 。 6. The method for detecting heating uniformity according to claim 1, characterized in that, Step S5 further includes: if the overall uniformity score calculated in step S4 is not within the preset threshold range, the object being tested is not heated evenly. The detection result of the uneven heating of the object being tested is fed back to the control system. The control system outputs an adjustment process signal. After the execution module receives and executes the process adjustment measures, it jumps to step S1 to detect the heating uniformity of the object being tested.

7. The method for detecting heating uniformity according to claim 6, characterized in that, The process adjustment measures include: adjusting the wind speed and / or adjusting the heating power.

8. A device for detecting heating uniformity, characterized in that, include: The system comprises an image acquisition module, a local calculation module, a local evaluation module, an overall evaluation module, and a judgment and output module. The image acquisition module is used to: acquire visible light and infrared images 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; select a local window in the acquired visible light image, the local window including N pixels; and calculate the flow velocity of a pixel at time t. This is used to represent the local flow velocity; based on Planck's radiation law, the infrared image acquired by the image acquisition module is analyzed to calculate the temperature gradient of a pixel at time t. , used to represent the magnitude of the local temperature gradient; (x, y) are pixel coordinates; The local evaluation module is used to: calculate a local uniformity score based on the local flow velocity and local temperature gradient calculated by the local calculation module; the local uniformity score... The calculation formula is: ， in, This indicates a preset coefficient used to avoid a denominator of 0; The overall evaluation module is used to: calculate the overall uniformity score based on the local uniformity score calculated by the local evaluation module; the formula for calculating the overall uniformity score is: ， Where D represents the total area of ​​the visible light image acquired by the image acquisition module; The judgment output module is used to: judge the heating uniformity of the detected object based on the overall uniformity score calculated by the overall evaluation module; when the overall uniformity score calculated by the overall evaluation module is within the preset threshold range, the detected object is heated uniformly.

Images