CN111369527A - Control method and device for medicine manufacturing section - Google Patents
Control method and device for medicine manufacturing section Download PDFInfo
- Publication number
- CN111369527A CN111369527A CN202010139037.8A CN202010139037A CN111369527A CN 111369527 A CN111369527 A CN 111369527A CN 202010139037 A CN202010139037 A CN 202010139037A CN 111369527 A CN111369527 A CN 111369527A
- Authority
- CN
- China
- Prior art keywords
- image
- current
- manufacturing
- section
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 259
- 239000003814 drug Substances 0.000 title claims abstract description 195
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000007905 drug manufacturing Methods 0.000 claims abstract description 59
- 238000006243 chemical reaction Methods 0.000 claims abstract description 45
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 15
- 229940079593 drug Drugs 0.000 abstract description 35
- 238000002425 crystallisation Methods 0.000 description 8
- 230000008025 crystallization Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003204 osmotic effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001954 sterilising effect Effects 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
The invention discloses a control method and a device for a drug manufacturing section, which can obtain the current value of at least one preset physical parameter of a drug in the current drug manufacturing section; respectively comparing the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result; and controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section. According to the invention, the current value of the preset physical parameter is compared with the preset value range through the objective physical parameter, and the drug reaction degree in the drug manufacturing section is determined by combining the current drug manufacturing image of the current drug manufacturing section on the basis of the comparison result, so that the drug manufacturing section is accurately controlled, the quality of the drug produced by the drug manufacturing section is ensured, and the yield of the produced drug is improved.
Description
Technical Field
The invention relates to a workshop section control technology, in particular to a control method and a control device for a medicine manufacturing workshop section.
Background
A number of pharmaceutical manufacturing stations are experienced in a pharmaceutical manufacturing process, such as: crystallization, concentration and other sections, wherein the accuracy of the control of the drug manufacturing section determines the quality of the finally manufactured drug.
Currently, technicians need to visually observe the drug reaction in the drug manufacturing section, and subjectively judge the degree of the drug reaction according to the experience of the technicians, so as to control the drug manufacturing section. However, the quality of the produced medicine cannot be guaranteed only by controlling the medicine production section through the visual observation and experience of technicians, and the yield of the produced medicine is reduced.
Disclosure of Invention
In view of the above problems, the present invention provides a method and a device for controlling a pharmaceutical manufacturing station, which overcome the above problems or at least partially solve the above problems, and the technical solution is as follows:
a method of controlling a pharmaceutical manufacturing station, comprising:
obtaining a current value of at least one preset physical parameter of the medicine in a current medicine manufacturing section;
respectively comparing the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result;
and controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section.
Optionally, the controlling the current pharmaceutical manufacturing process according to each comparison result and the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing process includes:
when the comparison results are that the current numerical value is within a preset numerical value range, displaying the current medicine manufacturing image of the current medicine manufacturing section;
and receiving a control instruction which is input by a user and used for controlling the current medicine manufacturing section, and controlling the current medicine manufacturing section according to the control instruction.
Optionally, the controlling the current pharmaceutical manufacturing process according to each comparison result and the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing process includes:
when the comparison results are that the current numerical value is within a preset numerical value range, obtaining a current medicine manufacturing image of the current medicine manufacturing section;
and performing image recognition on the current medicine manufacturing image of the current medicine manufacturing section, determining whether the current medicine manufacturing section is finished, and stopping the current medicine manufacturing section if the current medicine manufacturing section is finished.
Optionally, the image recognizing the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing section to determine whether the current pharmaceutical manufacturing section is finished includes:
obtaining a target area image in a current drug manufacturing image of the current drug manufacturing section;
carrying out similarity calculation on the target area image and each image in a preset reaction completion image group, and determining the similarity of the target area image and each image in the preset reaction completion image group;
carrying out similarity calculation on the target area image and each image in a preset unreacted image group, and determining the similarity of the target area image and each image in the preset unreacted image group;
and determining the image group where the image with the maximum similarity to the target area image is located, if the image with the maximum similarity to the target area image is in the preset unreacted image group, determining that the current medicine manufacturing section is not finished, and if the image with the maximum similarity to the target area image is in the preset reacted image group, determining that the current medicine manufacturing section is finished.
Optionally, the image recognizing the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing section to determine whether the current pharmaceutical manufacturing section is finished includes:
and inputting the current medicine manufacturing image to a pre-trained manufacturing process judgment model, and obtaining a judgment result of whether the current medicine manufacturing section is finished or not, wherein the judgment result is output by the pre-trained manufacturing process judgment model.
A control device for a pharmaceutical manufacturing station, comprising: a physical parameter value obtaining unit, a physical parameter comparison unit and a control unit,
the physical parameter value obtaining unit is used for obtaining the current value of at least one preset physical parameter of the medicine in the current medicine manufacturing section;
the physical parameter comparison unit is configured to respectively compare the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result;
and the control unit is used for controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section.
Optionally, the control unit includes: an image display subunit and a section control subunit,
the image display subunit is used for displaying the current medicine manufacturing image of the current medicine manufacturing section when the current numerical value of each comparison result is within a preset numerical value range;
the section control subunit is configured to receive a control instruction for controlling the current pharmaceutical manufacturing section, which is input by a user, and control the current pharmaceutical manufacturing section according to the control instruction.
Optionally, the control unit includes: an image acquisition subunit, an image identification subunit and a section stop subunit,
the image obtaining subunit is configured to obtain a current pharmaceutical manufacturing image of the current pharmaceutical manufacturing section when each comparison result is that the current numerical value is within a preset numerical value range;
the image identification subunit is used for carrying out image identification on the current medicine manufacturing image of the current medicine manufacturing section, determining whether the current medicine manufacturing section is finished or not, and triggering the section stopping subunit if the current medicine manufacturing section is finished;
the section stopping subunit is used for stopping the current medicine manufacturing section.
Optionally, the image identifying subunit includes: a target area image obtaining subunit, an image similarity determining subunit and a section process determining subunit,
the target area image obtaining subunit is configured to obtain a target area image in a current medicine manufacturing image of the current medicine manufacturing section;
the image similarity determining subunit is configured to perform similarity calculation on the target area image and each image in a preset reaction completion image group, and determine the similarity between the target area image and each image in the preset reaction completion image group;
the image similarity determining subunit is further configured to perform similarity calculation on the target area image and each image in a preset unreacted completed image group, and determine the similarity between the target area image and each image in the preset unreacted completed image group;
the section process determining subunit is configured to determine an image group in which an image with the greatest similarity to the target area image is located, determine that the current pharmaceutical manufacturing section is not finished if the image with the greatest similarity to the target area image is in the preset unreacted image group, and determine that the current pharmaceutical manufacturing section is finished if the image with the greatest similarity to the target area image is in the preset reacted image group.
Optionally, the image identification subunit is specifically configured to input the current pharmaceutical manufacturing image to a pre-trained manufacturing process judgment model, and obtain a judgment result of whether the current pharmaceutical manufacturing section output by the pre-trained manufacturing process judgment model is finished.
By means of the technical scheme, the control method and the control device for the medicine manufacturing section can obtain the current value of at least one preset physical parameter of the medicine in the current medicine manufacturing section; respectively comparing the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result; and controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section. According to the invention, the current value of the preset physical parameter is compared with the preset value range through the objective physical parameter, and the drug reaction degree in the drug manufacturing section is determined by combining the current drug manufacturing image of the current drug manufacturing section on the basis of the comparison result, so that the drug manufacturing section is accurately controlled, the quality of the drug produced by the drug manufacturing section is ensured, and the yield of the produced drug is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for controlling a pharmaceutical manufacturing station according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating another method for controlling a pharmaceutical manufacturing station according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating another method for controlling a pharmaceutical manufacturing station according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating another method for controlling a pharmaceutical manufacturing station according to an embodiment of the present invention;
FIG. 5 is a flow chart illustrating another method for controlling a pharmaceutical manufacturing station according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating a training process of a manufacturing process judgment model according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram illustrating a control device of a pharmaceutical manufacturing section according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, a method for controlling a pharmaceutical manufacturing section according to an embodiment of the present invention may include:
s100, obtaining the current value of at least one preset physical parameter of the medicine in the current medicine manufacturing section.
The medicine can be a semi-finished product in the process of making one or more raw materials into the medical medicine through physical change or chemical change. The current pharmaceutical manufacturing section may be at least one section including concentration, crystallization, separation, and the like. The preset physical parameters can be temperature, humidity, pressure and other parameters. The embodiment of the invention selects the physical parameters with significant reference value in the current medicine manufacturing section as the preset physical parameters. For example: in the actual production process, the temperature for drug crystallization is generally 20 ℃, and then the temperature in the embodiment of the invention can be used as the preset physical parameter required to be obtained when the drug manufacturing section is crystallization.
The embodiment of the invention can obtain one or more than two preset physical parameter values at different medicine manufacturing sections respectively. For example: according to the embodiment of the invention, when the drug manufacturing section is concentrating, the preset obtained physical parameter can be osmotic pressure under the drug manufacturing section; according to the embodiment of the invention, when the medicine manufacturing section is crystallization, the preset obtained physical parameters can be the temperature and humidity of the medicine manufacturing section.
The embodiment of the invention can obtain the same or different values of the preset physical parameters at different medicine manufacturing sections, such as: according to the embodiment of the invention, when the medicine manufacturing section is crystallization, the preset obtained physical parameter can be the temperature of the medicine manufacturing section; according to the embodiment of the invention, when the medicine manufacturing section is dry, the preset obtained physical parameter can also be the temperature of the medicine manufacturing section.
It can be understood that, in the process of the pharmaceutical manufacturing section, the preset physical parameters at different times may change, and the embodiment of the present invention takes the value of the preset physical parameter collected at the current time as the current value. According to the embodiment of the invention, the current value can be obtained by using the parameter measuring equipment corresponding to the preset physical parameter according to the difference of the preset physical parameter. The parameter measurement device may be a temperature sensor, a pressure sensor, or the like.
S200, respectively comparing the at least one preset physical parameter: and comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result.
The preset numerical range may be a threshold range correspondingly set to the preset physical parameter in the embodiment of the present invention. For example, where embodiments of the present invention may be used in a pharmaceutical manufacturing process where crystallization occurs, the predetermined range of values may be below 20 ℃. In the embodiment of the invention, when the drug manufacturing section is dry sterilization, the preset value range can be more than 120 ℃. It can be understood that, according to the embodiment of the present invention, the preset physical parameters of each pharmaceutical manufacturing section respectively correspond to the preset numerical value ranges according to the actual production requirements, so as to implement the subsequent accurate control of the pharmaceutical manufacturing sections.
S300, controlling the current medicine manufacturing section according to the comparison results and the current medicine manufacturing image of the current medicine manufacturing section.
According to the embodiment of the invention, whether the drug reaction in the current drug manufacturing section is finished or not can be preliminarily judged according to the comparison result, and whether the drug reaction in the current drug manufacturing section is finished or not is determined according to the current drug manufacturing image of the current drug manufacturing section. According to the embodiment of the invention, the drug reaction degree in the current drug manufacturing section can be determined in a mode of combining the comparison result with the current drug manufacturing image, so that the current drug manufacturing section is accurately controlled. For example: in the embodiment of the invention, when the medicine manufacturing section is crystallization, the current value of the preset physical parameter is 18 ℃ and the preset value range is below 20 ℃, the medicine manufacturing section is preliminarily judged to be finished, then whether the current medicine manufacturing image has crystals or not is judged through the current medicine manufacturing image of the medicine manufacturing section, if yes, the current medicine manufacturing section is determined to be finished, and the operation finishing of the current medicine manufacturing section can be controlled.
In the embodiment of the invention, at least one image acquisition device can be arranged in the current medicine manufacturing section to monitor the reaction degree of the medicine. The image acquisition device may be a camera. The image capture device may be a high definition camera with a stable light source. According to the embodiment of the invention, the current medicine manufacturing image of the current medicine manufacturing workshop section can be obtained through the image acquisition equipment arranged in the current medicine manufacturing workshop section. The image acquisition device may be communicatively coupled to the image output device. The image output device can be a computer device such as a desktop computer, a tablet computer and a smart phone. Vxividieo video recognition software may be employed on the image output device. The VXVIDeo video recognition software is software obtained by combining VisualField system software with image recognition software by the inventor of the application.
The embodiment of the invention can store the image collected by the image collecting device in the storage medium.
According to the control method for the medicine manufacturing section, provided by the embodiment of the invention, the current value of at least one preset physical parameter of the medicine in the current medicine manufacturing section can be obtained; respectively comparing the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result; and controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section. According to the embodiment of the invention, the current value of the preset physical parameter is compared with the preset value range through the objective physical parameter, and the drug reaction degree in the drug manufacturing section is determined by combining the current drug manufacturing image of the current drug manufacturing section on the basis of the comparison result, so that the drug manufacturing section is accurately controlled, the quality of the drug produced by the drug manufacturing section is ensured, and the yield of the produced drug is improved.
Alternatively, based on the method shown in fig. 1, as shown in fig. 2, another method for controlling a pharmaceutical manufacturing section according to an embodiment of the present invention, step S300 may include:
and S310, when the comparison results are that the current numerical value is within the preset numerical value range, displaying the current medicine manufacturing image of the current medicine manufacturing section.
Specifically, when each comparison result is that the current numerical value is within the preset numerical value range, the current medicine manufacturing image of the current medicine manufacturing section is displayed on the image output device. The image output device may be equipped with a Distributed Control System (DCS). The image acquisition device may transmit the image to the image output device through the switch.
In practical situations, for some drug reactions, the reaction needs to be completed only when each comparison result is that the current value is within the preset value range and lasts for a period of time, so that the embodiment of the invention can preset duration according to practical situations, and when each comparison result is determined that the current value is within the preset value range, the current drug manufacturing image of the current drug manufacturing section is displayed after the preset duration.
The current pharmaceutical manufacturing image may be a real-time image of the drug reaction at the current pharmaceutical manufacturing process. The user can determine the reaction degree of the medicine in the current medicine manufacturing section through the current medicine manufacturing image displayed by the image output equipment, and further input a control instruction suitable for the current medicine manufacturing section. It is understood that, in practical cases, there may be a key corresponding to each control instruction around an area where the image output apparatus presents the current pharmaceutical manufacturing image while the image output apparatus presents the current pharmaceutical manufacturing image, and when a user clicks a certain key, it is equivalent to inputting the control instruction corresponding to the key. Optionally, while the image output device displays the area of the current pharmaceutical manufacturing image, the related parameters of the current pharmaceutical manufacturing section may also be displayed, and the embodiment of the present invention is not further limited herein.
And S320, receiving a control instruction which is input by a user and used for controlling the current medicine manufacturing section, and controlling the current medicine manufacturing section according to the control instruction.
In the embodiment of the invention, when the comparison results are that the current numerical value is within the preset numerical value range, the drug reaction of the current drug manufacturing section is preliminarily judged to be finished, then, by displaying the real-time current drug manufacturing image, a technician in the field further determines whether the drug reaction of the current drug manufacturing section is finished, and when the technician determines that the drug reaction is finished, the technician inputs a control instruction to finish the current drug manufacturing section. According to the embodiment of the invention, whether the drug reaction of the current drug manufacturing section is finished or not can be accurately determined by combining the systematic judgment and the manual judgment, so that the current drug manufacturing section is accurately controlled.
Alternatively, based on the method shown in fig. 1, as shown in fig. 3, another method for controlling a pharmaceutical manufacturing section according to an embodiment of the present invention, step S300 may include:
s330, when the current numerical value of each comparison result is within a preset numerical value range, obtaining the current medicine manufacturing image of the current medicine manufacturing section.
According to the embodiment of the invention, when the current numerical value of each comparison result is within the preset numerical value range, the current medicine manufacturing image of the current medicine manufacturing section is obtained through the image acquisition equipment arranged in the current medicine manufacturing section.
S340, performing image recognition on the current medicine manufacturing image of the current medicine manufacturing section, determining whether the current medicine manufacturing section is finished, and if so, executing the step S350.
And S350, stopping the current medicine manufacturing section.
It is understood that when it is determined that the current pharmaceutical manufacturing process is not finished, the process returns to perform step S100.
The embodiment of the invention can use the existing image recognition method to perform image recognition on the current drug manufacturing image. For example: image recognition technology based on neural network, image recognition technology based on nonlinear dimension reduction, and the like. According to the embodiment of the invention, when the current numerical value of each comparison result is within the preset numerical value range, whether the drug reaction of the current drug manufacturing section is finished or not can be judged through an image recognition technology. The embodiment of the invention can accurately determine whether the drug reaction of the current drug manufacturing section is finished by means of an image recognition technology, and further accurately control the current drug manufacturing section.
Alternatively, based on the method shown in fig. 3, as shown in fig. 4, another method for controlling a pharmaceutical manufacturing section according to an embodiment of the present invention, step S340 may include:
s341, obtaining a target area image in the current medicine manufacturing image of the current medicine manufacturing section.
It will be appreciated that the pharmaceutical reactions of current pharmaceutical manufacturing stations may be carried out in specific vessels. The specific container may be a concentration reaction tank, a drying cabinet, etc. The current pharmaceutical manufacturing image obtained by the embodiment of the present invention may include images of drug reactions in a specific container, and may also include images other than those in the specific container. Embodiments of the present invention may use an image of the drug response within a particular container as the target area image in the current drug manufacturing image. It is to be understood that, in the embodiment of the present invention, the target area image in the current pharmaceutical manufacturing image may be obtained by an existing image area extraction method, and the image area extraction method is not limited by the present invention.
And S342, carrying out similarity calculation on the target area image and each image in the preset reaction completion image group, and determining the similarity between the target area image and each image in the preset reaction completion image group.
The images in the preset reaction completion image group can be images determined by technicians that the reaction of the medicine is completed in the current medicine manufacturing section, and the quality of the medicine finally manufactured by the medicine is qualified through inspection. According to the embodiment of the invention, the similarity of the target area image and each image in the preset reaction completion image group can be calculated by the conventional image similarity calculation method. The image similarity calculation method may be a histogram matching method, a matrix decomposition method, an image feature point method, or the like, and the image similarity calculation method is not limited herein.
And S343, carrying out similarity calculation on the target area image and each image in a preset unreacted image group, and determining the similarity between the target area image and each image in the preset unreacted image group.
Wherein the images in the preset unreacted completion image group may be images when a technician determines that the drug is not reacted to completion in the current drug manufacturing section. The description of the similarity between the calculation target area image and each image in the preset unreacted image group may refer to the similarity between the calculation target area image and each image in the preset reacted image group, and will not be described herein again.
And S344, determining an image group where the image with the maximum similarity to the target area image is located, executing the step S345 if the image with the maximum similarity to the target area image is in the preset unreacted completed image group, and executing the step S346 if the image with the maximum similarity to the target area image is in the preset reacted completed image group.
And S345, determining that the current medicine manufacturing section is not finished.
S346, determining that the current medicine manufacturing section is finished.
According to the embodiment of the invention, the similarity between the target area image and the image in the reaction completion image group and the similarity between the target area image and the image in the unreacted completion image group are calculated, and when the similarity between the determined target area image and the image in the reaction completion image group is maximum, the drug reaction end in the current drug manufacturing section can be determined. The embodiment of the invention accurately determines whether the drug reaction in the current drug manufacturing section is finished or not by the image similarity calculation method.
Alternatively, based on the method shown in fig. 3, as shown in fig. 5, another method for controlling a pharmaceutical manufacturing section according to an embodiment of the present invention, step S340 may include:
and S347, inputting the current medicine manufacturing image to a pre-trained manufacturing process judgment model, and obtaining a judgment result of whether the current medicine manufacturing section output by the pre-trained manufacturing process judgment model is finished.
Specifically, when the determination result is that the current pharmaceutical manufacturing process is finished, step S350 is executed, and when the determination result is that the current pharmaceutical manufacturing process is not finished, step S100 is executed.
Wherein the manufacturing process judgment model may be a convolutional neural network model. Optionally, as shown in fig. 6, a training process for manufacturing a process judgment model according to an embodiment of the present invention may include:
s001, obtaining a plurality of training sample images, wherein the training sample images are marked with a reaction completion mark or an unreacted completion mark.
S002, performing machine learning on the plurality of training sample images to obtain a manufacturing process determination model, wherein the manufacturing process determination model has the following inputs: a pharmaceutical manufacturing image, the manufacturing process judging the output of the model as: and judging whether the current medicine manufacturing section is finished or not.
It will be appreciated that, since a plurality of pharmaceutical manufacturing stations may be included in an actual pharmaceutical manufacturing process, embodiments of the present invention may be implemented for any of the plurality of pharmaceutical manufacturing stations: and correspondingly training to obtain a manufacturing process judgment model. The embodiment of the invention judges whether the current medicine manufacturing working section is finished or not through the pre-trained manufacturing process judgment model, can accurately identify whether the current medicine manufacturing image is an image with finished medicine reaction or not, and further accurately determines whether the medicine reaction in the current medicine manufacturing working section is finished or not.
Corresponding to the above method embodiment, an embodiment of the present invention further provides a control device for a pharmaceutical manufacturing section, which has a structure as shown in fig. 7, and may include: a physical parameter value obtaining unit 100, a physical parameter comparison unit 200 and a control unit 300.
The physical parameter value obtaining unit 100 is configured to obtain a current value of at least one preset physical parameter of the drug at a current drug manufacturing process.
The physical parameter comparison unit 200 is configured to respectively compare the at least one preset physical parameter: and comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result.
The control unit 300 is configured to control the current pharmaceutical manufacturing process according to each comparison result and the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing process.
The control device for the drug manufacturing section provided by the embodiment of the invention can obtain the current value of at least one preset physical parameter of the drug in the current drug manufacturing section; respectively comparing the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result; and controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section. According to the embodiment of the invention, the current value of the preset physical parameter is compared with the preset value range through the objective physical parameter, and the drug reaction degree in the drug manufacturing section is determined by combining the current drug manufacturing image of the current drug manufacturing section on the basis of the comparison result, so that the drug manufacturing section is accurately controlled, the quality of the drug produced by the drug manufacturing section is ensured, and the yield of the produced drug is improved.
Optionally, the control unit 300 includes: an image display subunit and a section control subunit.
And the image display subunit is used for displaying the current medicine manufacturing image of the current medicine manufacturing section when the current numerical value of each comparison result is within a preset numerical value range.
The section control subunit is configured to receive a control instruction for controlling the current pharmaceutical manufacturing section, which is input by a user, and control the current pharmaceutical manufacturing section according to the control instruction.
Optionally, the control unit 300 includes: an image acquisition subunit, an image identification subunit and a section stop subunit.
And the image obtaining subunit is configured to obtain the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing section when each comparison result is that the current numerical value is within a preset numerical value range.
The image identification subunit is configured to perform image identification on the current pharmaceutical manufacturing image of the current pharmaceutical manufacturing section, determine whether the current pharmaceutical manufacturing section is finished, and trigger the section stopping subunit if the current pharmaceutical manufacturing section is finished.
The section stopping subunit is used for stopping the current medicine manufacturing section.
Optionally, the image identifying subunit includes: the system comprises a target area image obtaining subunit, an image similarity determining subunit and a workshop section process determining subunit.
And the target area image obtaining subunit is used for obtaining a target area image in the current medicine manufacturing image of the current medicine manufacturing section.
The image similarity determining subunit is configured to perform similarity calculation on the target area image and each image in a preset reaction completion image group, and determine the similarity between the target area image and each image in the preset reaction completion image group.
The image similarity determining subunit is further configured to perform similarity calculation on the target area image and each image in a preset unreacted completed image group, and determine the similarity between the target area image and each image in the preset unreacted completed image group.
The section process determining subunit is configured to determine an image group in which an image with the greatest similarity to the target area image is located, determine that the current pharmaceutical manufacturing section is not finished if the image with the greatest similarity to the target area image is in the preset unreacted image group, and determine that the current pharmaceutical manufacturing section is finished if the image with the greatest similarity to the target area image is in the preset reacted image group.
Optionally, the image identification subunit is specifically configured to input the current pharmaceutical manufacturing image to a pre-trained manufacturing process judgment model, and obtain a judgment result of whether the current pharmaceutical manufacturing section output by the pre-trained manufacturing process judgment model is finished.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of controlling a pharmaceutical manufacturing station, comprising:
obtaining a current value of at least one preset physical parameter of the medicine in a current medicine manufacturing section;
respectively comparing the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result;
and controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section.
2. The method of claim 1, wherein said controlling said current pharmaceutical manufacturing station based on each of said comparisons and a current pharmaceutical manufacturing image of said current pharmaceutical manufacturing station comprises:
when the comparison results are that the current numerical value is within a preset numerical value range, displaying the current medicine manufacturing image of the current medicine manufacturing section;
and receiving a control instruction which is input by a user and used for controlling the current medicine manufacturing section, and controlling the current medicine manufacturing section according to the control instruction.
3. The method of claim 1, wherein said controlling said current pharmaceutical manufacturing station based on each of said comparisons and a current pharmaceutical manufacturing image of said current pharmaceutical manufacturing station comprises:
when the comparison results are that the current numerical value is within a preset numerical value range, obtaining a current medicine manufacturing image of the current medicine manufacturing section;
and performing image recognition on the current medicine manufacturing image of the current medicine manufacturing section, determining whether the current medicine manufacturing section is finished, and stopping the current medicine manufacturing section if the current medicine manufacturing section is finished.
4. The method of claim 3, wherein said image recognizing a current pharmaceutical manufacturing image of said current pharmaceutical manufacturing site to determine whether said current pharmaceutical manufacturing site is complete comprises:
obtaining a target area image in a current drug manufacturing image of the current drug manufacturing section;
carrying out similarity calculation on the target area image and each image in a preset reaction completion image group, and determining the similarity of the target area image and each image in the preset reaction completion image group;
carrying out similarity calculation on the target area image and each image in a preset unreacted image group, and determining the similarity of the target area image and each image in the preset unreacted image group;
and determining the image group where the image with the maximum similarity to the target area image is located, if the image with the maximum similarity to the target area image is in the preset unreacted image group, determining that the current medicine manufacturing section is not finished, and if the image with the maximum similarity to the target area image is in the preset reacted image group, determining that the current medicine manufacturing section is finished.
5. The method of claim 3, wherein said image recognizing a current pharmaceutical manufacturing image of said current pharmaceutical manufacturing site to determine whether said current pharmaceutical manufacturing site is complete comprises:
and inputting the current medicine manufacturing image to a pre-trained manufacturing process judgment model, and obtaining a judgment result of whether the current medicine manufacturing section is finished or not, wherein the judgment result is output by the pre-trained manufacturing process judgment model.
6. A control device for a pharmaceutical manufacturing station, comprising: a physical parameter value obtaining unit, a physical parameter comparison unit and a control unit,
the physical parameter value obtaining unit is used for obtaining the current value of at least one preset physical parameter of the medicine in the current medicine manufacturing section;
the physical parameter comparison unit is configured to respectively compare the at least one preset physical parameter: comparing the current value of the preset physical parameter with a preset value range corresponding to the preset physical parameter to obtain a comparison result;
and the control unit is used for controlling the current medicine manufacturing section according to each comparison result and the current medicine manufacturing image of the current medicine manufacturing section.
7. The apparatus of claim 6, wherein the control unit comprises: an image display subunit and a section control subunit,
the image display subunit is used for displaying the current medicine manufacturing image of the current medicine manufacturing section when the current numerical value of each comparison result is within a preset numerical value range;
the section control subunit is configured to receive a control instruction for controlling the current pharmaceutical manufacturing section, which is input by a user, and control the current pharmaceutical manufacturing section according to the control instruction.
8. The apparatus of claim 6, wherein the control unit comprises: an image acquisition subunit, an image identification subunit and a section stop subunit,
the image obtaining subunit is configured to obtain a current pharmaceutical manufacturing image of the current pharmaceutical manufacturing section when each comparison result is that the current numerical value is within a preset numerical value range;
the image identification subunit is used for carrying out image identification on the current medicine manufacturing image of the current medicine manufacturing section, determining whether the current medicine manufacturing section is finished or not, and triggering the section stopping subunit if the current medicine manufacturing section is finished;
the section stopping subunit is used for stopping the current medicine manufacturing section.
9. The apparatus of claim 8, wherein the image recognition subunit comprises: a target area image obtaining subunit, an image similarity determining subunit and a section process determining subunit,
the target area image obtaining subunit is configured to obtain a target area image in a current medicine manufacturing image of the current medicine manufacturing section;
the image similarity determining subunit is configured to perform similarity calculation on the target area image and each image in a preset reaction completion image group, and determine the similarity between the target area image and each image in the preset reaction completion image group;
the image similarity determining subunit is further configured to perform similarity calculation on the target area image and each image in a preset unreacted completed image group, and determine the similarity between the target area image and each image in the preset unreacted completed image group;
the section process determining subunit is configured to determine an image group in which an image with the greatest similarity to the target area image is located, determine that the current pharmaceutical manufacturing section is not finished if the image with the greatest similarity to the target area image is in the preset unreacted image group, and determine that the current pharmaceutical manufacturing section is finished if the image with the greatest similarity to the target area image is in the preset reacted image group.
10. The apparatus of claim 8, wherein the image recognition subunit is configured to input the current pharmaceutical manufacturing image into a pre-trained manufacturing process determination model, and obtain a determination result of whether the current pharmaceutical manufacturing section output by the pre-trained manufacturing process determination model is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139037.8A CN111369527A (en) | 2020-03-03 | 2020-03-03 | Control method and device for medicine manufacturing section |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139037.8A CN111369527A (en) | 2020-03-03 | 2020-03-03 | Control method and device for medicine manufacturing section |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111369527A true CN111369527A (en) | 2020-07-03 |
Family
ID=71206708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010139037.8A Pending CN111369527A (en) | 2020-03-03 | 2020-03-03 | Control method and device for medicine manufacturing section |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111369527A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112053377A (en) * | 2020-08-28 | 2020-12-08 | 常州码库数据科技有限公司 | Method and system for controlling drug synthesis process |
| CN116128272A (en) * | 2023-04-13 | 2023-05-16 | 北京意胜生物科技有限公司 | Production process supervision platform for medicines |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615160A (en) * | 2014-12-24 | 2015-05-13 | 安徽华润金蟾药业股份有限公司 | Liquid level detection device and method for production and concentration process of traditional Chinese medicinal granules |
| CN105784778A (en) * | 2016-05-25 | 2016-07-20 | 安徽华润金蟾药业股份有限公司 | System and method for judging terminal point of cinobufagin ethanol recycling section |
| KR20160116856A (en) * | 2015-03-31 | 2016-10-10 | 정진호 | Apparatus for comparing drag and prescription |
| CN107682662A (en) * | 2017-09-01 | 2018-02-09 | 中车青岛四方机车车辆股份有限公司 | A kind of acquisition system for manufacturing data |
| CN109241897A (en) * | 2018-08-29 | 2019-01-18 | 深圳华远云联数据科技有限公司 | Processing method, device, gateway and the storage medium of monitoring image |
| CN109445388A (en) * | 2018-10-29 | 2019-03-08 | 黄莹 | Industrial control system data analysis processing device and method based on image recognition |
| CN110688977A (en) * | 2019-10-09 | 2020-01-14 | 浙江中控技术股份有限公司 | Industrial image identification method and device, server and storage medium |
-
2020
- 2020-03-03 CN CN202010139037.8A patent/CN111369527A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615160A (en) * | 2014-12-24 | 2015-05-13 | 安徽华润金蟾药业股份有限公司 | Liquid level detection device and method for production and concentration process of traditional Chinese medicinal granules |
| KR20160116856A (en) * | 2015-03-31 | 2016-10-10 | 정진호 | Apparatus for comparing drag and prescription |
| CN105784778A (en) * | 2016-05-25 | 2016-07-20 | 安徽华润金蟾药业股份有限公司 | System and method for judging terminal point of cinobufagin ethanol recycling section |
| CN107682662A (en) * | 2017-09-01 | 2018-02-09 | 中车青岛四方机车车辆股份有限公司 | A kind of acquisition system for manufacturing data |
| CN109241897A (en) * | 2018-08-29 | 2019-01-18 | 深圳华远云联数据科技有限公司 | Processing method, device, gateway and the storage medium of monitoring image |
| CN109445388A (en) * | 2018-10-29 | 2019-03-08 | 黄莹 | Industrial control system data analysis processing device and method based on image recognition |
| CN110688977A (en) * | 2019-10-09 | 2020-01-14 | 浙江中控技术股份有限公司 | Industrial image identification method and device, server and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112053377A (en) * | 2020-08-28 | 2020-12-08 | 常州码库数据科技有限公司 | Method and system for controlling drug synthesis process |
| CN116128272A (en) * | 2023-04-13 | 2023-05-16 | 北京意胜生物科技有限公司 | Production process supervision platform for medicines |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111369527A (en) | Control method and device for medicine manufacturing section | |
| US10835930B2 (en) | Sorting system | |
| JP6810087B2 (en) | Machine learning device, robot control device and robot vision system using machine learning device, and machine learning method | |
| US10416617B2 (en) | Injection molding system for the calculation of optimum operating conditions and machine learning therefor | |
| JP7179722B2 (en) | How to monitor a manufacturing process, how to indirectly estimate systematic dependencies, how to match quality, how to start a manufacturing process, how to manufacture an extruded product, and how to manufacture an extruded product | |
| KR102185886B1 (en) | Colonoscopy image analysis method and apparatus using artificial intelligence | |
| EP1564542A1 (en) | Plant growth analyzing system and method | |
| CN111753635B (en) | Intelligent scoring method and device for chemical experiment operation and storage medium | |
| JP4957406B2 (en) | Batch process analysis system and batch process analysis method | |
| CN108563204B (en) | Control method, control device, electronic equipment and computer-readable storage medium | |
| CN109357629A (en) | A kind of intelligent checking system and application method based on spatial digitizer | |
| CN111831703A (en) | Display method, user interface, display device, and inspection device | |
| US20220297304A1 (en) | System and method for early event detection using generative and discriminative machine learning models | |
| WO2018100917A1 (en) | Information processing device, observation system, information processing method, and program | |
| CN111222798B (en) | Complex industrial process key index soft measurement method | |
| CN113344101A (en) | Intelligent identification method and identification system for livestock abnormal behavior judgment | |
| CN112651649B (en) | Digital printing information acquisition method | |
| CN108398150A (en) | A kind of fermentation automatically records analysis system | |
| CN115359412B (en) | Hydrochloric acid neutralization experiment scoring method, device, equipment and readable storage medium | |
| JP2002214228A (en) | Apparatus and method for evaluating biological specimen | |
| CN110826383B (en) | Analysis system, analysis method, program, and storage medium | |
| CN115393288A (en) | Processing technology control system and method | |
| CN115167582A (en) | Rose drying processing monitoring method and device based on digital twinning | |
| US20230066948A1 (en) | Ultrasound guidance method and system | |
| CN113419502A (en) | Process monitoring method and system for shell manufacturing production process based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200703 |