CN118011991B - Raw material mixing and stirring equipment control system for transdermal drug delivery product production - Google Patents
Raw material mixing and stirring equipment control system for transdermal drug delivery product production Download PDFInfo
- Publication number
- CN118011991B CN118011991B CN202410428183.0A CN202410428183A CN118011991B CN 118011991 B CN118011991 B CN 118011991B CN 202410428183 A CN202410428183 A CN 202410428183A CN 118011991 B CN118011991 B CN 118011991B
- Authority
- CN
- China
- Prior art keywords
- mixing
- control parameter
- data
- correction
- mixed
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Manufacturing & Machinery (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Accessories For Mixers (AREA)
Abstract
The invention relates to the technical field of equipment control, and discloses a raw material mixing and stirring equipment control system for transdermal drug delivery product production, which comprises a data acquisition module, a control module and a control module, wherein the data acquisition module is used for acquiring component proportion data, internal monitoring data and actual measurement control parameter data; the coefficient prediction module is used for acquiring a set mixing duration, a mixing quality coefficient interval and a time difference value, inputting component proportion data, internal monitoring data, the time difference value and actually measured control parameter data into a first machine learning model, and predicting a mixing quality coefficient; the quality judging module is used for judging whether the obtained sticky finished product accords with the mixing quality standard or not within the preset mixing duration; the parameter control module is used for controlling according to the actually measured control parameter data or the corrected control parameter data, so that T=T+K and triggering the data acquisition module; the self-adaptive adjustment module is used for repeating the data acquisition module to the parameter control module until T=M, and ending the cycle; the invention is beneficial to the adjustment and control of the self-adaptive parameters.
Description
Technical Field
The invention relates to the technical field of equipment control, in particular to a raw material mixing and stirring equipment control system for transdermal drug delivery product production.
Background
Transdermal drug delivery is a drug delivery method widely used in the medical and skin care fields; the process for the production of transdermal drug delivery products (e.g., gels, ointments, etc.) involves a number of steps such as raw material preparation, mixing, coating, drying, cutting and packaging; the mixing step is particularly critical, because the mixing quality directly determines the delivery quality of the final product; the traditional mixing process is mostly dependent on manual operation, such as a mode of manually controlling a stirring rod, which leads to lack of consistency of mixing effect and stirring speed, and difficulty in ensuring product quality; at present, in the production process of transdermal drug delivery products, a mixing device generally lacks an intelligent mixing quality prediction function; this results in an inability to adjust the stirring rate based on the predicted result of the mixing quality, thereby affecting the production quality and efficiency; in addition, this lack of intelligent production limits the automation and optimization potential of the process; in view of these challenges, it is particularly important to develop a transdermal drug delivery process quality prediction system.
Currently, there is a lack of systems for quality prediction for mixing links in transdermal drug delivery processes, although there are some related documents, such as chinese patent publication No. CN112023817B, which discloses a control method for a mechanical seal stirrer; although the method can realize intelligent control of stirring and mixing equipment, research and practical application of the method and the prior art find that the method and the prior art have at least the following partial defects:
(1) The quality prediction mechanism is lacking, and further, parameter correction cannot be performed on the actually measured control parameter data based on the quality prediction result;
(2) The control parameters of the mixing device cannot be adaptively adjusted in real time according to the change of external influencing factors (such as temperature and pressure) in the mixing device, so that excessive mixing of mixed substances is easily caused in a given time, or the mixing quality of the mixed substances does not reach the standard.
Disclosure of Invention
In order to overcome the above-described drawbacks of the prior art, embodiments of the present invention provide a raw material mixing and stirring device control system for transdermal drug delivery product production.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A raw material mixing and stirring device control system for transdermal drug delivery product production, the system comprising:
the data acquisition module is used for acquiring component proportion data of the raw materials of the sticky matters and acquiring internal monitoring data and actually measured control parameter data of the mixing and stirring device at the moment T in the mixing process of the raw materials of the sticky matters; the internal monitoring data comprise density ratio and viscosity ratio of the raw materials of the sticky matters, the control parameters comprise pressure, temperature and stirring speed, and T is an integer larger than zero;
the coefficient prediction module is used for extracting a preset mixing duration M of the sticky material and a mixing quality coefficient interval under the preset mixing duration M, calculating a time difference value N between a mixing time Q and a time T obtained according to the preset mixing duration M, inputting component proportion data, internal monitoring data, the time difference value N and actually measured control parameter data into a first machine learning model which is preconfigured for predicting mixing quality, and predicting the mixing quality coefficient under the mixing time Q, wherein M, Q and N are integers larger than zero;
The quality judging module is used for judging whether the sticky raw materials are mixed within a preset mixing time length M according to the mixing quality coefficient to obtain a sticky finished product which accords with the mixing quality standard, and if so, the mixing stirring device is continuously controlled according to the actually measured control parameter data; if the data do not accord with the preset data, inputting the mixed quality coefficient, the time difference value N and the actually measured control parameter data into a second machine learning model which is preconfigured for feeding back the correction control parameter to obtain the correction control parameter data, wherein K is an integer larger than zero;
The parameter control module is used for controlling the mixing device to continuously stir and mix the raw materials of the sticky matters according to the actually measured control parameter data or the corrected control parameter data, enabling T=T+K, and triggering the data acquisition module;
and the self-adaptive adjustment module is used for repeating the data acquisition module to the parameter control module until T=M, ending the circulation, and completing stirring and mixing of the raw materials of the sticky matters to obtain the finished sticky matters.
Further, the measured control parameter data comprises a measured pressure value, a measured temperature value and a measured stirring speed value;
the internal monitoring data acquisition logic includes:
acquiring an actual measurement density value of the viscous material in the mixing process at the time T, and acquiring a standard density value;
And calculating the ratio of the measured density value to the standard density value to obtain the density ratio of the raw materials of the sticky matters.
Further, the internal monitoring data acquisition logic further comprises:
Acquiring an actually measured viscosity value of the raw materials of the viscous matters in the mixing process at the moment T, and acquiring a standard viscosity value;
and calculating the ratio of the measured viscosity value to the standard viscosity value to obtain the viscosity ratio of the raw materials of the sticky matters.
Further, the predetermined mixing period M of extracting the dope includes:
acquiring finished product identification data of the sticky material raw material;
And determining the preset mixing duration M of the corresponding sticky object according to the preset relation between the finished product identification data and the preset mixing duration M.
Further, the acquisition logic of the mixing quality coefficient interval under the given mixing duration M is as follows:
acquiring finished product identification data of the sticky material raw material;
and determining a mixing quality coefficient interval of the corresponding sticky material under the preset mixing duration M according to the preset relation between the finished product identification data and the mixing quality coefficient interval.
Further, the first machine learning model generation logic is as follows:
Acquiring mixed quality historical data, and dividing the mixed quality historical data into a mixed quality training set and a mixed quality testing set; the mixing quality historical data comprises component proportioning data, internal monitoring data, a time difference value N, actual measurement control parameter data and corresponding mixing quality coefficients thereof;
Constructing a first regression network, taking component proportion data, internal monitoring data, a time difference value N and measured control parameter data in a mixed quality training set as input data of the first regression network, taking a mixed quality coefficient in the mixed quality training set as output data of the first regression network, and training the first regression network to obtain an initial first regression network;
and performing model verification on the initial first regression network by using the mixed quality test set, and outputting the initial first regression network with the test error less than or equal to the preset test error as a first machine learning model for predicting the mixed quality.
Further, the logic for acquiring the mixing quality coefficient in the mixing quality historical data is as follows:
acquiring a real shooting mixed image of a viscous material in a mixing process, and acquiring a standard mixed image;
respectively carrying out gray processing on the actual shooting mixed image and the standard mixed image to obtain an actual shooting gray image and a standard gray image;
dividing the real shot gray level image and the standard gray level image into Z areas according to the same dividing rule;
Carrying out formulated calculation according to pixel values in Z areas in the real shot gray image and the standard gray image to obtain a mixed quality coefficient; the calculation formula is as follows:
；
Wherein: is a mixed quality coefficient,/> Is the pixel value of the v pixel in the i-th area in the standard gray scale image,For the pixel value of the (r) th pixel in the (j) th region in the real shot gray image, D is the total number of pixels in the (i) th region in the standard gray image,/>For the total number of pixels in the j-th region in the real shot gray image,/>The total number of areas in the real shot gray image and the standard gray image.
Further, the correction control parameter data includes first correction control parameter data, second correction control parameter data and third correction control parameter data, wherein the first correction control parameter data is a correction stirring speed value, the second correction control parameter data is a correction pressure value, and the third correction control parameter data is a correction temperature value.
Further, judging whether the sticky material raw materials are mixed within a preset mixing time M to obtain a sticky material finished product which meets the mixing quality standard, including:
Comparing the mixed quality coefficient with the mixed quality coefficient interval;
if the mixing quality coefficient belongs to the mixing quality coefficient interval, judging that the raw materials of the sticky matters are mixed within a preset mixing time length M to obtain a finished sticky matter product which meets the mixing quality standard;
If the mixing quality coefficient does not belong to the mixing quality coefficient interval, judging that the mixture of the raw materials of the sticky matters in the preset mixing time length M to obtain a finished sticky matter product does not accord with the mixing quality standard.
Further, the second machine learning model includes a speed control parameter correction model for feedback correcting the speed control parameter, a pressure control parameter correction model for feedback correcting the pressure control parameter, and a temperature control parameter correction model for feedback correcting the temperature control parameter.
Further, the generation logic of the speed control parameter correction model for feedback correction of the speed control parameter is as follows:
Acquiring control parameter historical data, and dividing the control parameter historical data into a control parameter training set and a control parameter testing set; the control parameter history data comprises a mixing quality coefficient, a time difference value N, measured control parameter data and corresponding first correction control parameter data;
Constructing a second regression network, taking the mixed quality coefficient, the time difference value N and the actually measured control parameter data in the control parameter training set as input data of the second regression network, taking the first corrected control parameter data in the control parameter training set as output data of the second regression network, and training the second regression network to obtain an initial second regression network;
And performing model verification on the initial second regression network by using the control parameter test set, and outputting the initial second regression network with the test error less than or equal to the preset test error as a speed control parameter correction model for feedback correction of the speed control parameter.
Compared with the prior art, the invention has the beneficial effects that:
(1) The application discloses a raw material mixing and stirring equipment control system for transdermal drug delivery product production, which comprises a data acquisition module, a control module and a control module, wherein the data acquisition module is used for acquiring component proportion data, internal monitoring data and actual measurement control parameter data; the coefficient prediction module is used for acquiring the established mixing duration, the mixing quality coefficient interval and the time difference value, inputting the component proportioning data, the internal monitoring data, the time difference value and the actually measured control parameter data into the first machine learning model, and predicting the mixing quality coefficient; the quality judging module is used for judging whether the finished sticky product obtained in the preset mixing time accords with the mixing quality standard or not; the parameter control module is used for controlling according to the actually measured control parameter data or the corrected control parameter data, so that T=T+K and triggering the data acquisition module; the self-adaptive adjustment module is used for repeating the data acquisition module to the parameter control module; based on the module, the application can carry out real-time self-adaptive adjustment on the control parameters of the mixing device according to the change of the internal and external influencing factors (such as temperature, pressure and the like) of the mixing device, thereby avoiding excessive mixing of the mixed substances in a set time or avoiding the mixing quality of the mixed substances not reaching the standard.
(2) The application discloses a raw material mixing and stirring equipment control system for transdermal drug delivery product production, which can carry out parameter correction on measured control parameter data on the basis of a quality prediction result by introducing a quality prediction mechanism, thereby being beneficial to improving the automation and intelligent level of transdermal drug delivery product processing.
Drawings
FIG. 1 is a schematic diagram of a control system of a raw material mixing and stirring device for transdermal drug delivery product production provided by the invention;
fig. 2 is a flowchart of a method for controlling a raw material mixing and stirring device for transdermal drug delivery product production.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the present embodiment discloses a raw material mixing and stirring device control system for transdermal drug delivery product production, which includes:
The data acquisition module 110 is configured to acquire component proportion data of the raw materials of the viscous material, and acquire internal monitoring data and actually measured control parameter data of the mixing and stirring device at time T in a mixing process of the raw materials of the viscous material; the internal monitoring data comprise density ratio and viscosity ratio of the raw materials of the sticky matters, the control parameters comprise pressure, temperature and stirring speed, and T is an integer larger than zero;
Specifically, the actually measured control parameter data comprise an actually measured pressure value, an actually measured temperature value and an actually measured stirring speed value;
It should be appreciated that: the component proportion data comprise components and specific weights of viscous raw materials, and the viscous raw materials specifically refer to raw materials of transdermal administration products, wherein the transdermal administration products comprise, but are not limited to, essence, dressing paste, repairing cream and the like; the component proportion data of the raw materials of the sticky matters with different specifications and different types are obtained by manual weighing and inputting;
it should be noted that: the actual measurement control parameter data and the internal monitoring data are acquired and analyzed by various sensors installed on the mixing and stirring device, and the various sensors comprise, but are not limited to, a temperature sensor, a pressure sensor, a rotation speed detection meter, a densimeter, a viscometer and the like;
In one embodiment, the internal monitoring data acquisition logic includes:
acquiring an actual measurement density value of the viscous material in the mixing process at the time T, and acquiring a standard density value;
Calculating the ratio of the measured density value to the standard density value to obtain the density ratio of the raw materials of the sticky matters;
in another embodiment, the internal monitoring data acquisition logic further includes:
Acquiring an actually measured viscosity value of the raw materials of the viscous matters in the mixing process at the moment T, and acquiring a standard viscosity value;
calculating the ratio of the measured viscosity value to the standard viscosity value to obtain the viscosity ratio of the raw materials of the sticky matters;
It should be noted that: the standard density value and the standard viscosity value refer to a set density value and a design viscosity value of a transdermal drug delivery product which meet the factory standard, and the set density value and the design viscosity value limit the factory standard of the transdermal drug delivery product;
The coefficient prediction module 120 is configured to extract a given mixing duration M of the viscous material and a mixing quality coefficient interval under the given mixing duration M, calculate a time difference N between a mixing time Q obtained according to the given mixing duration M and a time T, input component proportioning data, internal monitoring data, the time difference N and actually measured control parameter data into a first machine learning model preconfigured for predicting mixing quality, and predict mixing quality coefficients under the mixing time Q, where M, Q and N are integers greater than zero;
It should be noted that: the preset mixing time length M refers to a set mixing time span of the sticky matters, and further illustrates that standard mixing time lengths are preset for the raw materials of the sticky matters with different specifications and different types, and the standard mixing time lengths of the raw materials of the sticky matters with different specifications and different types are determined according to specific experimental conditions; it will be appreciated that each of the raw materials of the dope will be subjected to the mixing process within a predetermined mixing time period M;
In practice, the predetermined mixing duration M of the extraction of the dope comprises:
acquiring finished product identification data of the sticky material raw material;
determining the preset mixing duration M of the corresponding sticky matters according to the preset relation between the finished product identification data and the preset mixing duration M;
In practice, the acquisition logic for the mixing quality coefficient interval at a given mixing duration M is as follows:
acquiring finished product identification data of the sticky material raw material;
determining a mixing quality coefficient interval of the corresponding sticky material under a preset mixing duration M according to a preset relation between the finished product identification data and the mixing quality coefficient interval;
specifically, the product identification data includes, but is not limited to, one of a sticky product name, a product model number, a product serial number, and the like;
It should be noted that: the system database is pre-stored with a preset relation between a plurality of product identification data and a mixing quality coefficient interval and a preset relation between a plurality of product identification data and a preset mixing time length M, and the preset mixing time length M corresponding to the corresponding raw materials of the sticky matters and the mixing quality coefficient interval of the mixed finished products of the sticky matters, which the mixing quality coefficient of the obtained sticky matters should belong to, can be obtained by obtaining the product identification data of the raw materials of the sticky matters;
Further to be described is: the mixing time Q is generated according to the preset mixing time M and the starting time, and the exemplary illustration is that the starting time of the mixing stirring device for mixing the viscous material of the transdermal administration product is 9 points 00 minutes, and the preset mixing time M of the viscous material of the transdermal administration product is 1 hour, so that the mixing time Q of the viscous material of the transdermal administration product is 10 points 00 minutes; further, assuming that the time T is 9 points and 10 minutes, the time difference N between the mixing time Q and the time T is 50 minutes;
specifically, the generating logic of the first machine learning model is as follows:
Acquiring mixed quality historical data, and dividing the mixed quality historical data into a mixed quality training set and a mixed quality testing set; the mixing quality historical data comprises component proportioning data, internal monitoring data, a time difference value N, actual measurement control parameter data and corresponding mixing quality coefficients thereof;
the logic for acquiring the mixing quality coefficient in the mixing quality historical data is as follows:
acquiring a real shooting mixed image of a viscous material in a mixing process, and acquiring a standard mixed image;
It should be noted that: the standard mixed images are stored in a system database in advance, are determined according to the specific number of the transdermal drug delivery products, and are extracted according to the specific types of the transdermal drug delivery products; the standard mixed image is a mixed shooting image meeting factory standards, which is obtained after the mixed processing of the sticky material in the preset mixing time length M; further described is that it is a blended image of a dope meeting a blending criterion;
respectively carrying out gray processing on the actual shooting mixed image and the standard mixed image to obtain an actual shooting gray image and a standard gray image;
dividing the real shot gray level image and the standard gray level image into Z areas according to the same dividing rule;
It should be appreciated that: when the real shot gray image and the standard gray image are divided into Z areas according to the same dividing rule, the dividing mode of the areas in the real shot gray image and the standard gray image is completely consistent with the size of the areas;
Carrying out formulated calculation according to pixel values in Z areas in the real shot gray image and the standard gray image to obtain a mixed quality coefficient; the calculation formula is as follows:
；
Wherein: is a mixed quality coefficient,/> Is the pixel value of the v pixel in the i-th area in the standard gray level image,/>For the pixel value of the (r) th pixel in the (j) th region in the real shot gray image, D is the total number of pixels in the (i) th region in the standard gray image,/>For the total number of pixels in the j-th region in the real shot gray image,/>The total number of areas in the real shot gray image and the standard gray image is calculated;
Constructing a first regression network, taking component proportion data, internal monitoring data, a time difference value N and measured control parameter data in a mixed quality training set as input data of the first regression network, taking a mixed quality coefficient in the mixed quality training set as output data of the first regression network, and training the first regression network to obtain an initial first regression network;
performing model verification on the initial first regression network by using the mixed quality test set, and outputting the initial first regression network with the test error less than or equal to the preset test error as a first machine learning model for predicting the mixed quality;
it should be noted that: the first regression network is specifically one of model algorithms such as decision tree regression, support vector machine regression, random forest regression, long-short-term memory network or cyclic neural network;
The quality judging module 130 is configured to judge whether the viscous material is mixed within a predetermined mixing duration M according to the mixing quality coefficient to obtain a viscous material finished product, and if so, continuously controlling the mixing and stirring device according to the actually measured control parameter data; if the data do not accord with the preset data, inputting the mixed quality coefficient, the time difference value N and the actually measured control parameter data into a second machine learning model which is preconfigured for feeding back the correction control parameter to obtain the correction control parameter data, wherein K is an integer larger than zero;
Specifically, the correction control parameter data comprises first correction control parameter data, second correction control parameter data and third correction control parameter data, wherein the first correction control parameter data is a correction stirring speed value, the second correction control parameter data is a correction pressure value, and the third correction control parameter data is a correction temperature value;
in the implementation, judging whether the sticky raw materials are mixed within a preset mixing time M to obtain a sticky finished product accords with a mixing quality standard or not comprises the following steps:
Comparing the mixed quality coefficient with the mixed quality coefficient interval;
if the mixing quality coefficient belongs to the mixing quality coefficient interval, judging that the raw materials of the sticky matters are mixed within a preset mixing time length M to obtain a finished sticky matter product which meets the mixing quality standard;
If the mixing quality coefficient does not belong to the mixing quality coefficient interval, judging that the mixture of the raw materials of the sticky matters in the preset mixing time length M to obtain a finished sticky matter product which does not accord with the mixing quality standard;
It should be noted that: when the mixing processing is completed within the predetermined mixing time period M, the mixing quality coefficient of the corresponding mixed raw materials (i.e. finished products of the sticky materials) should belong to the mixing quality coefficient interval, and the mixed raw materials of the sticky materials (i.e. finished products of the sticky materials) can be considered to meet the quality standard of factory delivery;
specifically, the second machine learning model includes a speed control parameter correction model for feedback correction of a speed control parameter, a pressure control parameter correction model for feedback correction of a pressure control parameter, and a temperature control parameter correction model for feedback correction of a temperature control parameter;
in one specific embodiment, the generation logic of the speed control parameter correction model for feedback correction of the speed control parameter is as follows:
Acquiring control parameter historical data, and dividing the control parameter historical data into a control parameter training set and a control parameter testing set; the control parameter history data comprises a mixing quality coefficient, a time difference value N, measured control parameter data and corresponding first correction control parameter data;
Constructing a second regression network, taking the mixed quality coefficient, the time difference value N and the actually measured control parameter data in the control parameter training set as input data of the second regression network, taking the first corrected control parameter data in the control parameter training set as output data of the second regression network, and training the second regression network to obtain an initial second regression network;
Performing model verification on the initial second regression network by using the control parameter test set, and outputting the initial second regression network with the test error less than or equal to the preset test error as a speed control parameter correction model for feedback correction of the speed control parameter;
It should be noted that: the second regression network is a specific one of model algorithms such as decision tree regression, support vector machine regression, random forest regression, long-short-time memory network or cyclic neural network;
Also to be described is: the generating logic of the pressure control parameter correction model for feedback correction of the pressure control parameter and the temperature control parameter correction model for feedback correction of the temperature control parameter is the same as the generating process of the speed control parameter correction model for feedback correction of the speed control parameter, and detailed description thereof will not be repeated in detail with reference to the above; it should be understood that the output data of the pressure control parameter correction model for feedback correction of the pressure control parameter and the temperature control parameter correction model for feedback correction of the temperature control parameter are different from the output data of the speed control parameter correction model for feedback correction of the speed control parameter, further explaining that the output data of the speed control parameter correction model for feedback correction of the speed control parameter is the first correction control parameter data and the output data of the pressure control parameter correction model for feedback correction of the pressure control parameter is the second correction control parameter data, and the output data of the generation logic of the temperature control parameter correction model for feedback correction of the temperature control parameter is the third correction control parameter data;
The parameter control module 140 is configured to control the mixing device to continuously mix the raw materials of the viscous material according to the actually measured control parameter data or the corrected control parameter data, and make t=t+k, and trigger the data acquisition module 110;
It should be noted that: further exemplary explanation is that, assuming that the actually measured control parameter data at time T is a pressure of 101,325 pascals, a temperature of 60 ℃ and a stirring speed of 200 revolutions, respectively, then assuming that according to the above process, the system may assume that the actually measured control parameter data at time T is used for controlling the mixing device, so that the raw materials of the sticky materials can be mixed within a preset mixing duration M to obtain a finished sticky product which meets the mixing quality standard, the process is always controlled by the actually measured control parameter data, and the process is a single continuous process; however, if at time t+k, the internal condition of the mixing and stirring device changes due to the influence of internal and external factors, the system may determine that the mixing and stirring device is controlled by the actually measured control parameter data at time T, and the viscous material raw material cannot be mixed within the predetermined mixing duration M to obtain a viscous material finished product which meets the mixing quality standard, so that the corrected control parameter data needs to be obtained, and if the corrected control parameter data are respectively the pressure of 101,530 pascals, the temperature of 70 ℃ and the stirring speed of 230 revolutions, the mixing and stirring device is controlled by the corrected control parameter data, so that the viscous material raw material is mixed within the predetermined mixing duration M to obtain the viscous material finished product which meets the mixing quality standard, and the process is a continuous conversion process; it should be further appreciated that in the actual process, the modified control parameter data may also change in real time as the mixing time continues to advance and the internal and external factors continue to affect;
the self-adaptive adjustment module 150 is configured to repeat the data acquisition module 110 to the parameter control module 140 until t=m, end the cycle, and complete stirring and mixing of the raw materials of the dope, so as to obtain a finished product of the dope;
it should be appreciated that: through the continuous lapse of mixing time, the system can continuously carry out self-adaptive parameter adjustment and control in the process, so that the finished sticky product prepared in the set time accords with the factory quality standard, and further, excessive mixing of mixed substances is avoided in the set time, or the mixing quality of the mixed substances is prevented from not reaching standards.
Example 2
Referring to fig. 2, and referring to the above embodiment 1, the present embodiment discloses a method for controlling a raw material mixing and stirring device for producing a transdermal drug delivery product, which includes:
step 1: acquiring component proportion data of the raw materials of the sticky matters, and acquiring internal monitoring data and actually measured control parameter data of the mixing and stirring device at the moment T in the mixing process of the raw materials of the sticky matters; the internal monitoring data comprise density ratio and viscosity ratio of the raw materials of the sticky matters, the control parameters comprise pressure, temperature and stirring speed, and T is an integer larger than zero;
Specifically, the actually measured control parameter data comprise an actually measured pressure value, an actually measured temperature value and an actually measured stirring speed value;
It should be appreciated that: the component proportion data comprise components and specific weights of viscous raw materials, and the viscous raw materials specifically refer to raw materials of transdermal administration products, wherein the transdermal administration products comprise, but are not limited to, essence, dressing paste, repairing cream and the like; the component proportion data of the raw materials of the sticky matters with different specifications and different types are obtained by manual weighing and inputting;
it should be noted that: the actual measurement control parameter data and the internal monitoring data are acquired and analyzed by various sensors installed on the mixing and stirring device, and the various sensors comprise, but are not limited to, a temperature sensor, a pressure sensor, a rotation speed detection meter, a densimeter, a viscometer and the like;
In one embodiment, the internal monitoring data acquisition logic includes:
acquiring an actual measurement density value of the viscous material in the mixing process at the time T, and acquiring a standard density value;
Calculating the ratio of the measured density value to the standard density value to obtain the density ratio of the raw materials of the sticky matters;
in another embodiment, the internal monitoring data acquisition logic further includes:
Acquiring an actually measured viscosity value of the raw materials of the viscous matters in the mixing process at the moment T, and acquiring a standard viscosity value;
calculating the ratio of the measured viscosity value to the standard viscosity value to obtain the viscosity ratio of the raw materials of the sticky matters;
It should be noted that: the standard density value and the standard viscosity value refer to a set density value and a design viscosity value of a transdermal drug delivery product which meet the factory standard, and the set density value and the design viscosity value limit the factory standard of the transdermal drug delivery product;
Step 2: extracting a preset mixing duration M of the sticky matters and a mixing quality coefficient interval under the preset mixing duration M, calculating a time difference value N between a mixing time Q and a time T obtained according to the preset mixing duration M, inputting component proportion data, internal monitoring data, the time difference value N and actually measured control parameter data into a first machine learning model which is preconfigured for predicting mixing quality, and predicting the mixing quality coefficient under the mixing time Q, wherein M, Q and N are integers larger than zero;
It should be noted that: the preset mixing time length M refers to a set mixing time span of the sticky matters, and further illustrates that standard mixing time lengths are preset for the raw materials of the sticky matters with different specifications and different types, and the standard mixing time lengths of the raw materials of the sticky matters with different specifications and different types are determined according to specific experimental conditions; it will be appreciated that each of the raw materials of the dope will be subjected to the mixing process within a predetermined mixing time period M;
In practice, the predetermined mixing duration M of the extraction of the dope comprises:
acquiring finished product identification data of the sticky material raw material;
determining the preset mixing duration M of the corresponding sticky matters according to the preset relation between the finished product identification data and the preset mixing duration M;
In practice, the acquisition logic for the mixing quality coefficient interval at a given mixing duration M is as follows:
acquiring finished product identification data of the sticky material raw material;
determining a mixing quality coefficient interval of the corresponding sticky material under a preset mixing duration M according to a preset relation between the finished product identification data and the mixing quality coefficient interval;
specifically, the product identification data includes, but is not limited to, one of a sticky product name, a product model number, a product serial number, and the like;
It should be noted that: the system database is pre-stored with a preset relation between a plurality of product identification data and a mixing quality coefficient interval and a preset relation between a plurality of product identification data and a preset mixing time length M, and the preset mixing time length M corresponding to the corresponding raw materials of the sticky matters and the mixing quality coefficient interval of the mixed finished products of the sticky matters, which the mixing quality coefficient of the obtained sticky matters should belong to, can be obtained by obtaining the product identification data of the raw materials of the sticky matters;
Further to be described is: the mixing time Q is generated according to the preset mixing time M and the starting time, and the exemplary illustration is that the starting time of the mixing stirring device for mixing the viscous material of the transdermal administration product is 9 points 00 minutes, and the preset mixing time M of the viscous material of the transdermal administration product is 1 hour, so that the mixing time Q of the viscous material of the transdermal administration product is 10 points 00 minutes; further, assuming that the time T is 9 points and 10 minutes, the time difference N between the mixing time Q and the time T is 50 minutes;
specifically, the generating logic of the first machine learning model is as follows:
Acquiring mixed quality historical data, and dividing the mixed quality historical data into a mixed quality training set and a mixed quality testing set; the mixing quality historical data comprises component proportioning data, internal monitoring data, a time difference value N, actual measurement control parameter data and corresponding mixing quality coefficients thereof;
the logic for acquiring the mixing quality coefficient in the mixing quality historical data is as follows:
acquiring a real shooting mixed image of a viscous material in a mixing process, and acquiring a standard mixed image;
It should be noted that: the standard mixed images are stored in a system database in advance, are determined according to the specific number of the transdermal drug delivery products, and are extracted according to the specific types of the transdermal drug delivery products; the standard mixed image is a mixed shooting image meeting factory standards, which is obtained after the mixed processing of the sticky material in the preset mixing time length M; further described is that it is a blended image of a dope meeting a blending criterion;
respectively carrying out gray processing on the actual shooting mixed image and the standard mixed image to obtain an actual shooting gray image and a standard gray image;
dividing the real shot gray level image and the standard gray level image into Z areas according to the same dividing rule;
It should be appreciated that: when the real shot gray image and the standard gray image are divided into Z areas according to the same dividing rule, the dividing mode of the areas in the real shot gray image and the standard gray image is completely consistent with the size of the areas;
Carrying out formulated calculation according to pixel values in Z areas in the real shot gray image and the standard gray image to obtain a mixed quality coefficient; the calculation formula is as follows:
；
Wherein: is a mixed quality coefficient,/> Is the pixel value of the v pixel in the i-th area in the standard gray level image,/>For the pixel value of the (r) th pixel in the (j) th region in the real shot gray image, D is the total number of pixels in the (i) th region in the standard gray image,/>For the total number of pixels in the j-th region in the real shot gray image,/>The total number of areas in the real shot gray image and the standard gray image is calculated;
Constructing a first regression network, taking component proportion data, internal monitoring data, a time difference value N and measured control parameter data in a mixed quality training set as input data of the first regression network, taking a mixed quality coefficient in the mixed quality training set as output data of the first regression network, and training the first regression network to obtain an initial first regression network;
performing model verification on the initial first regression network by using the mixed quality test set, and outputting the initial first regression network with the test error less than or equal to the preset test error as a first machine learning model for predicting the mixed quality;
it should be noted that: the first regression network is specifically one of model algorithms such as decision tree regression, support vector machine regression, random forest regression, long-short-term memory network or cyclic neural network;
Step 3: judging whether the sticky raw materials are mixed within a preset mixing time length M according to the mixing quality coefficient to obtain a sticky finished product which accords with the mixing quality standard, and if so, continuously controlling the mixing and stirring device according to the actually measured control parameter data; if the data do not accord with the preset data, inputting the mixed quality coefficient, the time difference value N and the actually measured control parameter data into a second machine learning model which is preconfigured for feeding back the correction control parameter to obtain the correction control parameter data, wherein K is an integer larger than zero;
Specifically, the correction control parameter data comprises first correction control parameter data, second correction control parameter data and third correction control parameter data, wherein the first correction control parameter data is a correction stirring speed value, the second correction control parameter data is a correction pressure value, and the third correction control parameter data is a correction temperature value;
in the implementation, judging whether the sticky raw materials are mixed within a preset mixing time M to obtain a sticky finished product accords with a mixing quality standard or not comprises the following steps:
Comparing the mixed quality coefficient with the mixed quality coefficient interval;
if the mixing quality coefficient belongs to the mixing quality coefficient interval, judging that the raw materials of the sticky matters are mixed within a preset mixing time length M to obtain a finished sticky matter product which meets the mixing quality standard;
If the mixing quality coefficient does not belong to the mixing quality coefficient interval, judging that the mixture of the raw materials of the sticky matters in the preset mixing time length M to obtain a finished sticky matter product which does not accord with the mixing quality standard;
It should be noted that: when the mixing processing is completed within the predetermined mixing time period M, the mixing quality coefficient of the corresponding mixed raw materials (i.e. finished products of the sticky materials) should belong to the mixing quality coefficient interval, and the mixed raw materials of the sticky materials (i.e. finished products of the sticky materials) can be considered to meet the quality standard of factory delivery;
specifically, the second machine learning model includes a speed control parameter correction model for feedback correction of a speed control parameter, a pressure control parameter correction model for feedback correction of a pressure control parameter, and a temperature control parameter correction model for feedback correction of a temperature control parameter;
in one specific embodiment, the generation logic of the speed control parameter correction model for feedback correction of the speed control parameter is as follows:
Acquiring control parameter historical data, and dividing the control parameter historical data into a control parameter training set and a control parameter testing set; the control parameter history data comprises a mixing quality coefficient, a time difference value N, measured control parameter data and corresponding first correction control parameter data;
Constructing a second regression network, taking the mixed quality coefficient, the time difference value N and the actually measured control parameter data in the control parameter training set as input data of the second regression network, taking the first corrected control parameter data in the control parameter training set as output data of the second regression network, and training the second regression network to obtain an initial second regression network;
Performing model verification on the initial second regression network by using the control parameter test set, and outputting the initial second regression network with the test error less than or equal to the preset test error as a speed control parameter correction model for feedback correction of the speed control parameter;
It should be noted that: the second regression network is a specific one of model algorithms such as decision tree regression, support vector machine regression, random forest regression, long-short-time memory network or cyclic neural network;
Also to be described is: the generating logic of the pressure control parameter correction model for feedback correction of the pressure control parameter and the temperature control parameter correction model for feedback correction of the temperature control parameter is the same as the generating process of the speed control parameter correction model for feedback correction of the speed control parameter, and detailed description thereof will not be repeated in detail with reference to the above; it should be understood that the output data of the pressure control parameter correction model for feedback correction of the pressure control parameter and the temperature control parameter correction model for feedback correction of the temperature control parameter are different from the output data of the speed control parameter correction model for feedback correction of the speed control parameter, further explaining that the output data of the speed control parameter correction model for feedback correction of the speed control parameter is the first correction control parameter data and the output data of the pressure control parameter correction model for feedback correction of the pressure control parameter is the second correction control parameter data, and the output data of the generation logic of the temperature control parameter correction model for feedback correction of the temperature control parameter is the third correction control parameter data;
Step 4: controlling a mixing device to continuously stir and mix the raw materials of the sticky matters according to the actually measured control parameter data or the corrected control parameter data, enabling T=T+K, and returning to the step 1;
It should be noted that: further exemplary explanation is that, assuming that the actually measured control parameter data at time T is a pressure of 101,325 pascals, a temperature of 60 ℃ and a stirring speed of 200 revolutions, respectively, then assuming that according to the above process, the system may assume that the actually measured control parameter data at time T is used for controlling the mixing device, so that the raw materials of the sticky materials can be mixed within a preset mixing duration M to obtain a finished sticky product which meets the mixing quality standard, the process is always controlled by the actually measured control parameter data, and the process is a single continuous process; however, if at time t+k, the internal condition of the mixing and stirring device changes due to the influence of internal and external factors, the system may determine that the mixing and stirring device is controlled by the actually measured control parameter data at time T, and the viscous material raw material cannot be mixed within the predetermined mixing duration M to obtain a viscous material finished product which meets the mixing quality standard, so that the corrected control parameter data needs to be obtained, and if the corrected control parameter data are respectively the pressure of 101,530 pascals, the temperature of 70 ℃ and the stirring speed of 230 revolutions, the mixing and stirring device is controlled by the corrected control parameter data, so that the viscous material raw material is mixed within the predetermined mixing duration M to obtain the viscous material finished product which meets the mixing quality standard, and the process is a continuous conversion process; it should be further appreciated that in the actual process, the modified control parameter data may also change in real time as the mixing time continues to advance and the internal and external factors continue to affect;
Step 5: repeating the steps 1-4 until T=M, ending the circulation, and completing stirring and mixing of the raw materials of the sticky matters to obtain a sticky matter finished product;
it should be appreciated that: through the continuous lapse of mixing time, the system can continuously carry out self-adaptive parameter adjustment and control in the process, so that the finished sticky product prepared in the set time accords with the factory quality standard, and further, excessive mixing of mixed substances is avoided in the set time, or the mixing quality of the mixed substances is prevented from not reaching standards.
The above formulas are all formulas with dimensionality removed and numerical value calculated, the formulas are formulas with the latest real situation obtained by software simulation by collecting a large amount of data, and preset parameters, weights and threshold selection in the formulas are set by those skilled in the art according to the actual situation.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. Raw material mixing and stirring equipment control system for transdermal drug delivery product production, characterized in that the system comprises:
the data acquisition module is used for acquiring component proportion data of the raw materials of the sticky matters and acquiring internal monitoring data and actually measured control parameter data of the mixing and stirring device at the moment T in the mixing process of the raw materials of the sticky matters; the internal monitoring data comprise density ratio and viscosity ratio of the raw materials of the sticky matters, the control parameters comprise pressure, temperature and stirring speed, and T is an integer larger than zero;
the coefficient prediction module is used for extracting a preset mixing duration M of the sticky material and a mixing quality coefficient interval under the preset mixing duration M, calculating a time difference value N between a mixing time Q and a time T obtained according to the preset mixing duration M, inputting component proportion data, internal monitoring data, the time difference value N and actually measured control parameter data into a first machine learning model which is preconfigured for predicting mixing quality, and predicting the mixing quality coefficient under the mixing time Q, wherein M, Q and N are integers larger than zero;
the logic for acquiring the mixing quality coefficient in the mixing quality historical data is as follows:
acquiring a real shooting mixed image of a viscous material in a mixing process, and acquiring a standard mixed image;
respectively carrying out gray processing on the actual shooting mixed image and the standard mixed image to obtain an actual shooting gray image and a standard gray image;
dividing the real shot gray level image and the standard gray level image into Z areas according to the same dividing rule;
Carrying out formulated calculation according to pixel values in Z areas in the real shot gray image and the standard gray image to obtain a mixed quality coefficient; the calculation formula is as follows:
；
Wherein: is a mixed quality coefficient,/> Is the pixel value of the v pixel in the i-th area in the standard gray level image,/>For the pixel value of the (r) th pixel in the (j) th region in the real shot gray image, D is the total number of pixels in the (i) th region in the standard gray image,/>For the total number of pixels in the j-th region in the real shot gray image,/>The total number of areas in the real shot gray image and the standard gray image is calculated;
The quality judging module is used for judging whether the sticky raw materials are mixed within a preset mixing time length M according to the mixing quality coefficient to obtain a sticky finished product which accords with the mixing quality standard, and if so, the mixing stirring device is continuously controlled according to the actually measured control parameter data; if the mixed quality coefficient, the time difference value N and the actually measured control parameter data are input into a second machine learning model which is preconfigured for feeding back the correction control parameter, and the correction control parameter data are obtained;
The parameter control module is used for controlling the mixing device to continuously stir and mix the raw materials of the sticky matters according to the actually measured control parameter data or the corrected control parameter data, enabling T=T+K, triggering the data acquisition module, and enabling K to be an integer larger than zero;
and the self-adaptive adjustment module is used for repeating the data acquisition module to the parameter control module until T=M, ending the circulation, and completing stirring and mixing of the raw materials of the sticky matters to obtain the finished sticky matters.
2. The raw material mixing and stirring apparatus control system for transdermal drug delivery product production according to claim 1, wherein the measured control parameter data includes a measured pressure value, a measured temperature value, and a measured stirring speed value;
the internal monitoring data acquisition logic includes:
acquiring an actual measurement density value of the viscous material in the mixing process at the time T, and acquiring a standard density value;
And calculating the ratio of the measured density value to the standard density value to obtain the density ratio of the raw materials of the sticky matters.
3. The transdermal drug delivery product manufacturing raw mix agitation device control system of claim 2, wherein the internal monitoring data acquisition logic further comprises:
Acquiring an actually measured viscosity value of the raw materials of the viscous matters in the mixing process at the moment T, and acquiring a standard viscosity value;
and calculating the ratio of the measured viscosity value to the standard viscosity value to obtain the viscosity ratio of the raw materials of the sticky matters.
4. A raw material mixing and stirring apparatus control system for transdermal drug delivery product production according to claim 3, wherein the predetermined mixing time period M for extracting the dope comprises:
acquiring finished product identification data of the sticky material raw material;
And determining the preset mixing duration M of the corresponding sticky object according to the preset relation between the finished product identification data and the preset mixing duration M.
5. The system for controlling a raw material mixing and stirring apparatus for transdermal drug delivery product production according to claim 4, wherein the acquisition logic of the mixing quality coefficient interval for a given mixing period M is as follows:
acquiring finished product identification data of the sticky material raw material;
and determining a mixing quality coefficient interval of the corresponding sticky material under the preset mixing duration M according to the preset relation between the finished product identification data and the mixing quality coefficient interval.
6. The transdermal drug delivery product production raw material mixing and stirring device control system of claim 5, wherein the first machine learning model generation logic is as follows:
Acquiring mixed quality historical data, and dividing the mixed quality historical data into a mixed quality training set and a mixed quality testing set; the mixing quality historical data comprises component proportioning data, internal monitoring data, a time difference value N, actual measurement control parameter data and corresponding mixing quality coefficients thereof;
Constructing a first regression network, taking component proportion data, internal monitoring data, a time difference value N and measured control parameter data in a mixed quality training set as input data of the first regression network, taking a mixed quality coefficient in the mixed quality training set as output data of the first regression network, and training the first regression network to obtain an initial first regression network;
and performing model verification on the initial first regression network by using the mixed quality test set, and outputting the initial first regression network with the test error less than or equal to the preset test error as a first machine learning model for predicting the mixed quality.
7. The raw material mixing and stirring apparatus control system for transdermal drug delivery product production according to claim 6, wherein the correction control parameter data includes first correction control parameter data, second correction control parameter data, and third correction control parameter data, the first correction control parameter data being a correction stirring speed value, the second correction control parameter data being a correction pressure value, the third correction control parameter data being a correction temperature value.
8. The system for controlling a raw material mixing and stirring device for transdermal drug delivery product production according to claim 7, wherein the step of determining whether the finished product of the dope obtained by mixing the raw materials for the given mixing time period M meets the mixing quality standard comprises:
Comparing the mixed quality coefficient with the mixed quality coefficient interval;
if the mixing quality coefficient belongs to the mixing quality coefficient interval, judging that the raw materials of the sticky matters are mixed within a preset mixing time length M to obtain a finished sticky matter product which meets the mixing quality standard;
If the mixing quality coefficient does not belong to the mixing quality coefficient interval, judging that the mixture of the raw materials of the sticky matters in the preset mixing time length M to obtain a finished sticky matter product does not accord with the mixing quality standard.
9. The system of claim 8, wherein the second machine learning model includes a speed control parameter correction model for feedback correction of a speed control parameter, a pressure control parameter correction model for feedback correction of a pressure control parameter, and a temperature control parameter correction model for feedback correction of a temperature control parameter.
10. The raw material mixing and stirring apparatus control system for transdermal drug delivery product production according to claim 9, wherein the generation logic of the speed control parameter correction model for feedback correction of the speed control parameter is as follows:
Acquiring control parameter historical data, and dividing the control parameter historical data into a control parameter training set and a control parameter testing set; the control parameter history data comprises a mixing quality coefficient, a time difference value N, measured control parameter data and corresponding first correction control parameter data;
Constructing a second regression network, taking the mixed quality coefficient, the time difference value N and the actually measured control parameter data in the control parameter training set as input data of the second regression network, taking the first corrected control parameter data in the control parameter training set as output data of the second regression network, and training the second regression network to obtain an initial second regression network;
And performing model verification on the initial second regression network by using the control parameter test set, and outputting the initial second regression network with the test error less than or equal to the preset test error as a speed control parameter correction model for feedback correction of the speed control parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410428183.0A CN118011991B (en) | 2024-04-10 | 2024-04-10 | Raw material mixing and stirring equipment control system for transdermal drug delivery product production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410428183.0A CN118011991B (en) | 2024-04-10 | 2024-04-10 | Raw material mixing and stirring equipment control system for transdermal drug delivery product production |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118011991A CN118011991A (en) | 2024-05-10 |
| CN118011991B true CN118011991B (en) | 2024-06-04 |
Family
ID=90944932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410428183.0A Active CN118011991B (en) | 2024-04-10 | 2024-04-10 | Raw material mixing and stirring equipment control system for transdermal drug delivery product production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118011991B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118896863A (en) * | 2024-07-18 | 2024-11-05 | 湖州盟泰智能科技有限公司 | A roller hardness detection method and system |
| CN118700337B (en) * | 2024-08-24 | 2024-12-31 | 山东天意装配式建筑装备研究院有限公司 | Automatic control system of foaming mixer |
| CN119328921B (en) * | 2024-12-02 | 2025-03-18 | 甘肃海纳塑业有限公司 | An automatic mixing control system used in plastic manufacturing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102258811A (en) * | 2006-07-03 | 2011-11-30 | 汉莫堤克股份有限公司 | Manufacture, method and use of active substance-releasing medical products for permanently keeping blood vessels open |
| CN104168781A (en) * | 2012-03-09 | 2014-11-26 | 卡夫食品集团品牌有限责任公司 | Beverage concentrates with increased viscosity and shelf life and methods of making the same |
| CN110927029A (en) * | 2019-12-16 | 2020-03-27 | 陕西住院帮医疗科技有限公司 | Powder mixing uniformity detection method based on particle size analysis |
| CN112638446A (en) * | 2018-07-09 | 2021-04-09 | V·K·沙玛 | Multi-volume drug delivery system with vacuum assisted mixing and/or delivery |
-
2024
- 2024-04-10 CN CN202410428183.0A patent/CN118011991B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102258811A (en) * | 2006-07-03 | 2011-11-30 | 汉莫堤克股份有限公司 | Manufacture, method and use of active substance-releasing medical products for permanently keeping blood vessels open |
| CN104168781A (en) * | 2012-03-09 | 2014-11-26 | 卡夫食品集团品牌有限责任公司 | Beverage concentrates with increased viscosity and shelf life and methods of making the same |
| CN112638446A (en) * | 2018-07-09 | 2021-04-09 | V·K·沙玛 | Multi-volume drug delivery system with vacuum assisted mixing and/or delivery |
| CN110927029A (en) * | 2019-12-16 | 2020-03-27 | 陕西住院帮医疗科技有限公司 | Powder mixing uniformity detection method based on particle size analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118011991A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118011991B (en) | Raw material mixing and stirring equipment control system for transdermal drug delivery product production | |
| CN103135455B (en) | Systems and methods for process control including process-initiated workflow | |
| JP2023507906A (en) | Method and control system for controlling polymer viscosity quality | |
| CN118486386A (en) | Automatic control system for preparation process of amphiphilic polyaminohexadecanol ester with high salt resistance | |
| RU2020115425A (en) | QUALITY CONTROL IN BATCH PRODUCTION OF BEVERAGE IN REAL TIME USING DENSITOMETRY | |
| CN118080280A (en) | Monitoring system for film processing based on Internet of things | |
| CN108922486B (en) | Gamma adjustment method, device and computer readable storage medium | |
| AU770819B2 (en) | Method and apparatus for rheometry, and its application to control of polymer manufacture | |
| CN110935646A (en) | Full-automatic crab grading system based on image recognition | |
| CN110084379A (en) | Method for calibrating instrument to be calibrated by applying artificial intelligence cloud computing | |
| CN118171965B (en) | Bread production quality management method, system, equipment and readable storage medium | |
| CN118124106A (en) | Injection molding optimization control system and method based on neural network | |
| CN116700189A (en) | Control method, device, equipment and storage medium for butter kneader | |
| CN118558219B (en) | Method, device and system for detecting mixing uniformity of stirring equipment | |
| CN114474523B (en) | Method and system for adjusting performance of modified plastic | |
| CN114872196B (en) | Intelligent regulating and controlling method for current of stirrer | |
| CN118884812B (en) | Control system and method for automatic mixing of materials for premix production | |
| CN106950933B (en) | Quality conformance control method and device, computer storage medium | |
| CN119328921B (en) | An automatic mixing control system used in plastic manufacturing | |
| CN119116188A (en) | Automatic feeding and stirring time control method and system for polymer materials | |
| EP4216002B1 (en) | Control device and control method | |
| US20220079170A1 (en) | Method for determining a kneading state of a dough, system for monitoring the kneading state and kneading machine | |
| CN116272618A (en) | Stirrer regulation and control method and related device based on tackifier viscosity analysis | |
| CN114121188B (en) | Application and correction method and system of monoglyceride | |
| JP2024018449A (en) | Kneading condition derivation device and method, method for producing kneaded product |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |