CN112053377A - A kind of drug synthesis process control method and system - Google Patents

Abstract

The invention discloses a drug synthesis process control method and system, which obtains several historical drug final state pictures, preprocesses the drug final state pictures to obtain the gray mean value and deviation of the drug synthesis final state; obtains drugs in a rotating traditional Chinese medicine tank in real time Each frame of picture information from the beginning of the synthesis reaction to the end; the information of each frame of pictures is divided into thresholds based on the color model in time sequence, and the gray mean value and deviation of the frame picture are calculated after determining the area where the drug is located; The gray mean value and deviation of the obtained picture information of each frame are compared with the gray mean value and deviation of the final state of drug synthesis; if the error range is within the preset range, it means that the specified state is reached, and the rotation of the medicine tank is stopped; otherwise, continue Rotate and continue to compare the gray mean and deviation of the next frame of picture information. Advantages: reduce labor cost and realize automation; can realize accurate judgment of drug synthesis reaction process and improve drug synthesis rate.

Description

A kind of drug synthesis process control method and system

technical field

The invention relates to a drug synthesis process control method and system, in particular to a machine vision-based drug synthesis process control method and system, belonging to the technical field of image processing and machine vision.

Background technique

Today, the complete machines or production lines produced by pharmaceutical machine companies are assembled from thousands of components. These parts have various defects in the processing process, and the means of quality control are mostly manual inspection, with the help of some tooling inspection tools and measuring instruments for auxiliary measurement. As we all know, the most difficult factor to control in "4M1E" is the "human" factor, which is limited by these unavoidable defects of the human body, which can easily lead to missed inspection of defective parts.

However, if these minor defects are not found in time, there will be huge safety hazards for the safety of pharmaceutical companies; if they are found in time, re-manufacturing and replacement can eliminate the risks, but for pharmaceutical machine companies, there are also a large number of safety hazards. The waste of human, financial and material resources is more likely to affect the delivery of products and reduce the reputation of the enterprise.

SUMMARY OF THE INVENTION

The technical problem to be solved by the present invention is to overcome the defects of the prior art, and to provide a method and system for controlling a drug synthesis process.

In order to solve the above-mentioned technical problems, the present invention provides a method for controlling a drug synthesis process, obtaining several historical pictures of the final state of the drug, preprocessing the pictures of the final state of the drug, and obtaining the gray mean value and deviation of the final state of the drug synthesis;

Obtain real-time picture information of each frame of the medicine in the rotating Chinese medicine tank from the start of the synthesis reaction to the end;

Perform threshold segmentation on the basis of color model for each frame of picture information in chronological order, and calculate the grayscale mean and deviation of the frame of pictures after determining the area where the drug is located;

Compare the gray mean value and deviation of each frame of picture information obtained by calculation with the gray mean value and deviation of the final state of drug synthesis in turn;

If the error range is within the preset range, it means that the designated state is reached, and the rotation of the medicine can is stopped; otherwise, the rotation is continued, and the gray mean value and deviation of the next frame of picture information are compared.

Further, the process of performing threshold segmentation on the basis of the color model for each frame of picture information in chronological order, and determining the area where the medicine is located, and calculating its grayscale mean and deviation include:

Determine the YUV model according to the change of drug color, and convert the RGB model of each frame of picture information into a YUV model:

Among them, the YUV model represents the brightness and chrominance model, where Y represents the brightness, U and V represent the chromaticity, the RGB model is an additive color mixing model, R represents the percentage of red, G represents the percentage of green), B represents blue percentage of color;

Threshold segmentation based on the YUV model, denoting T as the segmentation threshold between foreground and background, the proportion of foreground pixels in the image is ω ₀ , and the average gray level is u ₀ ; the proportion of background pixels in the image is ω ₁ , and the average gray level is u ₁ , the total average gray level of the image is u, and the variance g of the foreground and background images is:

u=ω ₀ ×u ₀ +ω ₁ ×u ₁

g=ω ₀ ×(u ₀ -u) ² +ω ₁ ×(u ₁ -u) ²

Combine the above equations to get:

g=ω ₀ ×ω ₁ ×(u ₀ -u ₁ ) ²

or:

When the variance g is the largest, the difference between the foreground and the background is the largest at this time, and the gray level T at this time is the best threshold, and the area where the drug is located is determined by dividing the brightness and chromaticity thresholds;

The mean value and deviation of the determined drug area are calculated to obtain the gray mean value and deviation of the frame picture.

The YUV color model of this step separates luminance and chrominance, which is suitable for the field of image processing.

Further, it also includes: selecting the medicine tank as the reference object to set the coordinate system, and calculating the position transformation of the medicine;

The described selection medicine tank is the reference object to set the coordinate system, and the process of calculating the medicine position transformation includes:

The medicine tank is a spherical medicine tank, and according to the characteristics of the spherical medicine tank, the inclined axis of the spherical medicine tank is selected as the Y axis, and the center of the spherical medicine tank is the coordinate origin to establish a Cartesian coordinate system;

Calculate the diameter of the spherical medicine tank, calculate the coordinates P(x, y) of the two-thirds position, and draw a line segment AB according to the inclination of the Y-axis and the coordinates of point P, which is two-thirds of the medicine tank. When the movement of the medicine exceeds this limit, the rotation speed of the medicine tank is reduced, and vice versa.

This step can quickly and accurately locate the specific position of the medicine in the medicine tank.

Further, it also includes: performing image testing on the control method and adjusting parameters, and the process includes:

Record the drug synthesis reaction process multiple times, and repeatedly adjust the threshold parameters of the YUV model to make it compatible;

Compare the specified state obtained by multiple synthesis with the actual situation, and determine the gray mean value and deviation as the optimal termination value;

Adjust the coordinate system to determine the position of the medicine can in the picture, and ensure the relative stability of the two-thirds position.

A drug synthesis process control system, comprising:

The first acquisition module is used to acquire several historical drug final state pictures, and preprocess the final drug state pictures to obtain the gray mean value and deviation of the final drug synthesis state;

The second acquisition module is used to acquire in real time the picture information of each frame of the medicine in the rotating Chinese medicine tank from the start of the synthesis reaction to the end;

The segmentation and calculation module is used to perform threshold segmentation on the basis of the color model for each frame of picture information in chronological order, and calculate the gray mean value and deviation of the frame of pictures after determining the area where the drug is located;

The comparison module is used to sequentially compare the calculated grayscale mean value and deviation of each frame of picture information with the grayscale mean value and deviation of the final state of drug synthesis;

The judgment module is used to judge that if the error range is within the preset range, it means that the designated state is reached, and the rotation of the medicine can is stopped;

Further, the segmentation and calculation module includes:

The model conversion module is used to determine the YUV model according to the change of drug color, and convert the RGB model of each frame of picture information into a YUV model:

Among them, the YUV model represents the brightness and chrominance model, where Y represents the brightness, U and V represent the chromaticity, the RGB model is an additive color mixing model, R represents the percentage of red, G represents the percentage of green), B represents blue percentage of color;

The segmentation module is used for threshold segmentation based on the YUV model, denoting T as the segmentation threshold between foreground and background, the proportion of foreground pixels in the image is ω ₀ , the average gray level is u ₀ ; the proportion of background pixels in the image is ω ₁ , The average gray level is u ₁ , the total average gray level of the image is u, and the variance g of the foreground and background images is:

u=ω ₀ ×u ₀ +ω ₁ ×u ₁

g=ω ₀ ×(u ₀ -u) ² +ω ₁ ×(u ₁ -u) ²

Combine the above equations to get:

g=ω ₀ ×ω ₁ ×(u ₀ -u ₁ ) ²

or:

When the variance g is the largest, the difference between the foreground and the background is the largest at this time, and the gray level T at this time is the best threshold, and the area where the drug is located is determined by dividing the brightness and chromaticity thresholds;

The calculation module is used to calculate the mean value and deviation of the determined drug area, and obtain the grayscale mean value and deviation of the frame picture.

Further, it also includes a coordinate system determination and calculation module, which is used to select the medicine tank as the reference object to set the coordinate system, and calculate the position transformation of the medicine;

The coordinate system determination and calculation module includes:

The coordinate system establishment module is used to determine that the medicine tank is a spherical medicine tank, and according to the characteristics of the spherical medicine tank, the inclined axis of the spherical medicine tank is selected as the Y axis, and the center of the spherical medicine tank is the coordinate origin to establish a Cartesian coordinate system;

The position transformation calculation module is used to calculate the diameter of the spherical medicine tank, calculate the coordinates P(x, y) of the two-thirds position, and draw a line segment AB according to the inclination of the Y axis and the coordinates of the point P. This line segment It is the dividing line of two-thirds of the medicine tank. When the movement of the medicine exceeds this limit, the rotation speed of the medicine tank is reduced, and vice versa.

Further, it also includes: a test and adjustment module for performing image testing on the control method and adjusting parameters;

The test and adjustment modules include:

The model threshold adjustment module is used to record the drug synthesis reaction process multiple times, and repeatedly adjust the threshold parameters of the YUV model to make it compatible;

The gray mean value and deviation determination module is used to compare the specified state obtained by multiple synthesis with the actual situation, and determine the gray mean value and deviation as the optimal termination value;

The coordinate system adjustment module is used to adjust the coordinate system to determine the position of the medicine can in the picture, so as to ensure the relative stability of two-thirds of the position.

Beneficial effects achieved by the present invention:

The invention reduces labor cost and realizes automation; accurate judgment can be realized for the drug synthesis reaction process, and the drug synthesis rate can be improved.

Description of drawings

Fig. 1 is a schematic diagram of a drug detection process flow;

2 and 3 are schematic diagrams of the effect of the invention.

Detailed ways

In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

As shown in Figure 1, the machine vision-based drug synthesis process control method realizes precise control of the drug synthesis process through traditional image processing, reduces labor costs, and improves the drug synthesis rate. It includes the following steps:

Step 1: Convert the video content captured by the camera in real time into a frame-by-frame picture format;

(1), use the monocular camera to shoot the whole process video of the drug in the medicine tank from the start of the synthesis reaction to the end, and convert the obtained video into .avi format;

(2), create a new ImageDrug folder, use the method of obtaining video frames to convert the video in .avi format into pictures in .png format and store them in the folder;

Step 2, pretreatment of the final synthetic state of the drug;

Prepare several pictures of the final state of the drug for preprocessing. Since the final state of drug synthesis is a uniform liquid with a certain color, the measurement methods of mean and deviation are used to judge whether the drug reaches the required state. Manually select the region of interest R as the drug region, p is the pixel point from R, its gray value is g(p), and F is the plane (F=|R|), the calculation formula is as follows:

The mean value Mean1 and the deviation Dev1 of the final state of drug synthesis can be calculated by the above formula;

Step 3, select a color model, including the following steps:

(1), observe and select the YUV (luminance and chromaticity) model according to the change of the color of the drug, where "Y" represents the brightness (Luminance or Luma), that is, the grayscale value; and "U" and "V" represent The chrominance (Chrominance or Chroma) is used to describe the color and saturation of the image, and is used to specify the color of the pixel. For images represented by YUV, the Y and UV components are separated. If there is only a Y component and no UV separation, then the image represents a black and white image. Therefore, not every pixel needs to contain three components of Y, U, and V. According to different sampling formats, each Y component can correspond to its own UV component, or several Y components can share UV components. YUV is mainly used to optimize the transmission of color video signals. Compared with RGB video signal transmission, its biggest advantage is that it only takes up very little bandwidth (RGB requires three independent video signals to be transmitted at the same time). The main sampling formats are YCbCr 4:2:0, YCbCr 4:2:2, YCbCr 4:1:1 and YCbCr 4:4:4. Among them, YCbCr 4:1:1 is more commonly used, and its meaning is: each point saves an 8-bit brightness value (that is, the Y value), and every 2x2 points saves a Cr and Cb value, and the image will not feel in the naked eye. too much change. Therefore, the original RGB (R, G, B are all 8bit unsigned) model, 1 point needs 8x3=24bits (the first picture below), (after full sampling, YUV still occupies 8bits). After sampling by 4:1:1, and now the average only needs 8+(8/4)+(8/4)=12bits (4 points, 8*4(Y)+8(U)+8(V) =48bits), each point occupies 12bits on average (the second picture below). This compresses the image data in half. So convert the original RGB model to a YUV model:

Step 4: On the basis of the color model, threshold segmentation is performed to select the area where the drug is located, and then the average gray value and deviation of the gray level are calculated, and compared with the final state of the drug, including the following steps:

(1), first perform grayscale enhancement on the image, and then perform threshold segmentation based on the YUV model, denote T as the segmentation threshold between foreground and background, the proportion of foreground pixels in the image is 0 ₀ , and the average gray level is u ₀ ; background The proportion of pixels in the image is ω ₁ , the average gray level is u ₁ , the total average gray level of the image is u, and the variance g of the foreground and background images is:

u=ω ₀ ×u ₀ +ω ₁ ×u ₁

g=ω ₀ ×(u ₀ -u) ² +ω ₁ ×(u ₁ -u) ²

Combine the above equations to get:

g=ω ₀ ×ω ₁ ×(u ₀ -u ₁ ) ²

or:

When the variance g is the largest, it can be considered that the difference between the foreground and the background is the largest at this time, and the gray level T at this time is the best threshold, and the area where the drug is located is selected by dividing the brightness and chromaticity thresholds;

(2) Use morphological methods to expand the area and appropriately expand the range of the selected area. The dilation operation is to convolve the image (or a part of the image, denoted as A) with the kernel (denoted as B). The kernel can be of any shape and size, and it has a separately defined reference point, called the anchor point. In most cases, the kernel is a small solid square or disk with a reference point in the middle, but the kernel can actually be thought of as a template or mask. The expansion is the operation of finding the local maximum value. The kernel B is convolved with the graph, that is, the maximum value of the pixel points in the area covered by the kernel B (reflecting the local area) is calculated, and this maximum value is assigned to the pixel specified by the reference point. This will cause the highlighted areas in the image to grow gradually. (x, y) represents the area that needs to be expanded, and x', y' represent the pixel value of expansion:

(3), perform mean (Mean) and deviation (Deviation) calculation on the selected drug area;

(4) Comparing the obtained mean value and deviation with the final actual required drug state described in step 2, within the error range ±0.2, it means that the specified state is reached, and the rotation of the medicine tank is stopped.

In step 5, the medicine tank is selected as the reference object to set the coordinate system, and the position transformation of the medicine is calculated, including the following steps:

以球形药罐中心为坐标原点建立笛卡尔坐标系；(4-1) Observe the characteristics of the medicine tank, select its inclination direction as the Y axis, and calculate its inclination angle relative to the horizontal direction as

The Cartesian coordinate system is established with the center of the spherical medicine tank as the coordinate origin;

根据Y轴的倾斜率θ和P点坐标可画出一条直线L：(4-2) Select the outline of the spherical medicine tank according to the methods such as threshold segmentation and shape selection. Since the medicine tank is spherical, its diameter l is obtained, and the coordinates of the two-thirds position are calculated.

According to the slope θ of the Y-axis and the coordinates of point P, a straight line L can be drawn:

时表明药罐内液体超出三分之二区域，此时药罐转速降低，反之增加。The straight line L is the dividing line of two-thirds of the medicine tank. Use the method in step 4 to detect the area where the medicine is located, and calculate the length and width of the smallest circumscribed rectangle of the medicine along the inclined axis. Let the side along the inclined axis be the width l _c , and the adjacent side is of length l _h . When the width of the enclosing rectangle

When the liquid in the medicine tank exceeds two-thirds of the area, the rotation speed of the medicine tank decreases, and vice versa.

Step 6: Algorithm testing and evaluation. Use the completed algorithm to test a large number of images and adjust parameters to improve the accuracy of the algorithm.

(1) Record the drug synthesis reaction process multiple times, repeatedly adjust the threshold parameters of the YUV model to make it compatible, and finally select U (80-115);

(2) Comparing the program running results with the actual situation, multiple tests show that the gray mean value (218.5±0.2 and deviation (13.2±0.2) is the best termination value;

(3) Repeat the test, adjust the coordinate system to determine the position of the medicine can in the picture, and ensure the relative stability of two-thirds of the position.

Enter images of different reaction times to test

(1), the schematic diagram of the result of the drug termination reaction is shown in Figure 2;

(2) The schematic diagram of the speed control of the medicine tank is shown in Figure 3.

(3) After testing, the traditional image processing-based drug synthesis process control method used in the present invention solves the problem of inaccurate human eye observations and errors, reduces labor costs, and enables automation to further enter life and serve the society.

Correspondingly, the present invention also provides a drug synthesis process control system, comprising:

The first acquisition module is used to acquire several historical drug final state pictures, and preprocess the final drug state pictures to obtain the gray mean value and deviation of the final drug synthesis state;

The second acquisition module is used to acquire in real time the picture information of each frame of the medicine in the rotating Chinese medicine tank from the start of the synthesis reaction to the end;

The segmentation and calculation module is used to perform threshold segmentation on the basis of the color model for each frame of picture information in chronological order, and calculate the gray mean value and deviation of the frame of pictures after determining the area where the drug is located;

The comparison module is used to sequentially compare the calculated grayscale mean value and deviation of each frame of picture information with the grayscale mean value and deviation of the final state of drug synthesis;

The judgment module is used to judge that if the error range is within the preset range, it means that the designated state is reached, and the rotation of the medicine can is stopped;

The segmentation and calculation module includes:

The model conversion module is used to determine the YUV model according to the change of drug color, and convert the RGB model of each frame of picture information into a YUV model:

Among them, the YUV model represents the brightness and chrominance model, where Y represents the brightness, U and V represent the chromaticity, the RGB model is an additive color mixing model, R represents the percentage of red, G represents the percentage of green), B represents blue percentage of color;

The segmentation module is used for threshold segmentation based on the YUV model, denoting T as the segmentation threshold between foreground and background, the proportion of foreground pixels in the image is ω ₀ , the average gray level is u ₀ ; the proportion of background pixels in the image is ω ₁ , The average gray level is u ₁ , the total average gray level of the image is u, and the variance g of the foreground and background images is:

u=ω ₀ ×u ₀ +ω ₁ ×u ₁

g=ω ₀ ×(u ₀ -u) ² +ω ₁ ×(u ₁ -u) ²

Combine the above equations to get:

g=ω ₀ ×ω ₁ ×(u ₀ -u ₁ ) ²

or:

When the variance g is the largest, the difference between the foreground and the background is the largest at this time, and the gray level T at this time is the best threshold, and the area where the drug is located is determined by dividing the brightness and chromaticity thresholds;

The calculation module is used to calculate the mean value and deviation of the determined drug area, and obtain the grayscale mean value and deviation of the frame picture.

It also includes a coordinate system determination and calculation module, which is used to select the medicine tank as the reference object to set the coordinate system and calculate the position transformation of the medicine;

The coordinate system determination and calculation module includes:

The coordinate system establishment module is used to determine that the medicine tank is a spherical medicine tank, and according to the characteristics of the spherical medicine tank, the inclined axis of the spherical medicine tank is selected as the Y axis, and the center of the spherical medicine tank is the coordinate origin to establish a Cartesian coordinate system;

The position transformation calculation module is used to calculate the diameter of the spherical medicine tank, calculate the coordinates P(x, y) of the two-thirds position, and draw a line segment AB according to the inclination of the Y axis and the coordinates of the point P. This line segment It is the dividing line of two-thirds of the medicine tank. When the movement of the medicine exceeds this limit, the rotation speed of the medicine tank is reduced, and vice versa.

Also includes: a test and adjustment module for performing image testing on the control method and adjusting parameters;

The test and adjustment modules include:

The model threshold adjustment module is used to record the drug synthesis reaction process multiple times, and repeatedly adjust the threshold parameters of the YUV model to make it compatible;

The grayscale mean value and deviation determination module is used to compare the specified state obtained by multiple synthesis with the actual situation, and determine the grayscale mean value and deviation as the optimal termination value;

The coordinate system adjustment module is used to adjust the coordinate system to determine the position of the medicine can in the picture, so as to ensure the relative stability of two-thirds of the position.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. A method for controlling the process of synthesizing a drug,

acquiring a plurality of historical drug final state pictures, and preprocessing the drug final state pictures to obtain a gray average value and deviation of a drug synthesis final state;

acquiring information of each frame of picture from the beginning to the end of the synthesis reaction of the medicine in the rotary traditional Chinese medicine tank in real time;

performing threshold segmentation on each frame of picture information on the basis of a color model according to a time sequence, and calculating a gray average value and deviation of the frame of picture after determining a region where a medicine is located;

sequentially comparing the gray level mean value and the deviation of each frame of image information obtained by calculation with the gray level mean value and the deviation of the final state of the drug synthesis;

if the error range is within the preset range, indicating that the specified state is reached, and stopping the rotation of the medicine tank; and if not, continuing to rotate, and continuing to compare the gray average value and the deviation of the next frame of picture information.

2. The method of claim 1, wherein the process of performing threshold segmentation on each frame of image information based on the color model according to the time sequence and calculating the mean value and deviation of the gray scale after determining the region where the drug is located comprises:

determining a YUV model according to the change condition of the medicine color, and converting the RGB model of each frame of picture information into a YUV model:

the YUV model represents a brightness and chrominance model, wherein Y represents brightness, U and V represent chrominance, the RGB model is an additive color mixing model, R represents the percentage of red, G represents the percentage of green), and B represents the percentage of blue;

based on YUV model, threshold segmentation is carried out, T is recorded as a segmentation threshold of the foreground and the background, and the number of foreground pixels in the image is omega₀Average gray of u₀(ii) a The number of background pixels in the image is omega₁Average gray of u₁Total average gray of the image is u, variance of the foreground and background imagesg, then there are:

u＝ω₀×u₀+ω₁×u₁

g＝ω₀×(u₀-u)²+ω₁×(u₁-u)²

the simultaneous expression is as follows:

g＝ω₀×ω₁×(u₀-u₁)²

or:

when the variance g is maximum, the difference between the foreground and the background is maximum, the gray level T is the optimal threshold value, and the region where the medicine is located is determined by segmenting the brightness threshold value and the chroma threshold value;

and calculating the mean value and the deviation of the determined medicine area to obtain the mean value and the deviation of the gray level of the frame of picture.

3. The method for controlling a drug synthesis process according to claim 1, further comprising: selecting a medicine tank as a reference object, setting a coordinate system, and calculating the position transformation of the medicine;

the method is characterized in that a coordinate system is set for the medicine tank as a reference object, and the process of calculating the position change of the medicine comprises the following steps:

the medicine pot is a spherical medicine pot, according to the characteristics of the spherical medicine pot, an inclined shaft of the spherical medicine pot is selected as a Y axis, and the center of the spherical medicine pot is taken as a coordinate origin to establish a Cartesian coordinate system;

calculating the diameter of the spherical medicine tank, calculating coordinates P (x, Y) of two-thirds positions, drawing a line segment AB according to the inclination of the Y axis and the coordinates of the point P, wherein the line segment is a boundary of two-thirds positions of the medicine tank, and when the medicine movement exceeds the boundary, the rotation speed of the medicine tank is reduced, otherwise, the medicine movement is accelerated.

4. The method for controlling a drug synthesis process according to claim 3, further comprising: the control method is subjected to image test and parameter adjustment, and the process comprises the following steps:

recording the drug synthesis reaction process for multiple times, and repeatedly adjusting the threshold parameter of the YUV model to ensure that the YUV model has compatibility;

comparing the designated state obtained by multiple synthesis with the actual situation, and determining the gray average value and the deviation as the optimal termination value;

and adjusting the coordinate system to determine the position of the medicine tank in the picture, and ensuring the relative stability of the two-thirds position.

5. A drug synthesis process control system, comprising:

the first acquisition module is used for acquiring a plurality of historical drug final state pictures, preprocessing the drug final state pictures and acquiring the gray average value and deviation of the drug synthesis final state;

the second acquisition module is used for acquiring each frame of picture information from the beginning to the end of the synthesis reaction of the medicine in the rotary traditional Chinese medicine tank in real time;

the segmentation and calculation module is used for performing threshold segmentation on each frame of picture information on the basis of the color model according to the time sequence, and calculating the gray average value and the deviation of the frame of picture after determining the region where the medicine is;

the contrast module is used for sequentially comparing the gray average value and the deviation of each frame of image information obtained by calculation with the gray average value and the deviation of the final state of the drug synthesis;

the judgment module is used for judging, if the error range is within the preset range, the specified state is reached, and the rotation of the medicine tank is stopped; and if not, continuing to rotate, and continuing to compare the gray average value and the deviation of the next frame of picture information.

6. The drug synthesis process control system of claim 5, wherein the segmentation and calculation module comprises:

the model conversion module is used for determining a YUV model according to the change condition of the medicine color and converting the RGB model of each frame of picture information into the YUV model:

the YUV model represents a brightness and chrominance model, wherein Y represents brightness, U and V represent chrominance, the RGB model is an additive color mixing model, R represents the percentage of red, G represents the percentage of green), and B represents the percentage of blue;

a segmentation module for threshold segmentation based on YUV model, wherein T is the segmentation threshold of foreground and background, and the ratio of foreground pixel point to image is omega₀Average gray of u₀(ii) a The number of background pixels in the image is omega₁Average gray of u₁The total average gray of the image is u, and the variance g of the foreground and background images is:

u＝ω₀×u₀+ω₁×u₁

g＝ω₀×(u₀-u)²+ω₁×(u₁-u)²

the simultaneous expression is as follows:

g＝ω₀×ω₁×(u₀-u₁)²

or:

when the variance g is maximum, the difference between the foreground and the background is maximum, the gray level T is the optimal threshold value, and the region where the medicine is located is determined by segmenting the brightness threshold value and the chroma threshold value;

and the calculation module is used for calculating the mean value and the deviation of the determined medicine area to obtain the mean value and the deviation of the gray level of the frame of picture.

7. The system of claim 5, further comprising a coordinate system determination and calculation module for selecting the canister for setting a coordinate system for a reference, calculating a drug position transformation;

the coordinate system determination and calculation module comprises:

the coordinate system establishing module is used for determining that the medicine tank is a spherical medicine tank, selecting a tilting shaft of the spherical medicine tank as a Y axis according to the characteristics of the spherical medicine tank, and establishing a Cartesian coordinate system by taking the center of the spherical medicine tank as an origin of coordinates;

and the position transformation calculation module is used for calculating the diameter of the spherical medicine tank, calculating coordinates P (x, Y) of two-thirds positions, drawing a line segment AB according to the inclination rate of the Y axis and the coordinates of a point P, wherein the line segment is a two-thirds boundary of the medicine tank, and when the medicine movement exceeds the boundary, the rotation speed of the medicine tank is reduced, otherwise, the medicine tank is accelerated.

8. The pharmaceutical synthesis process control system of claim 7, further comprising: the test and adjustment module is used for carrying out image test on the control method and adjusting parameters;

the test and adjustment module includes:

the model threshold adjusting module is used for recording the drug synthesis reaction process for multiple times and repeatedly adjusting the threshold parameter of the YUV model to ensure that the YUV model has compatibility;

the gray mean and deviation determining module is used for comparing the specified state obtained by multiple times of synthesis with the actual situation and determining the gray mean and deviation as the optimal termination value;

and the coordinate system adjusting module is used for adjusting a coordinate system to determine the position of the medicine tank in the picture and ensure the relative stability of the two-thirds position.

Images