CN117141783B - Static accurate weighing system and method - Google Patents
Static accurate weighing system and method Download PDFInfo
- Publication number
- CN117141783B CN117141783B CN202311380723.4A CN202311380723A CN117141783B CN 117141783 B CN117141783 B CN 117141783B CN 202311380723 A CN202311380723 A CN 202311380723A CN 117141783 B CN117141783 B CN 117141783B
- Authority
- CN
- China
- Prior art keywords
- weighing
- frame
- data
- gap
- bottle
- 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
- 238000005303 weighing Methods 0.000 title claims abstract description 163
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000003068 static effect Effects 0.000 title claims abstract description 43
- 239000003814 drug Substances 0.000 claims abstract description 44
- 238000011049 filling Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 17
- 239000008187 granular material Substances 0.000 claims abstract description 14
- 230000000670 limiting effect Effects 0.000 claims abstract description 4
- 230000003287 optical effect Effects 0.000 claims description 33
- 238000012937 correction Methods 0.000 claims description 29
- 241000039077 Copula Species 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000005315 distribution function Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 229940079593 drug Drugs 0.000 description 16
- 239000002245 particle Substances 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 4
- 239000000428 dust Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000005429 filling process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 239000002775 capsule Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000004108 freeze drying Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 239000003826 tablet Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B1/00—Packaging fluent solid material, e.g. powders, granular or loose fibrous material, loose masses of small articles, in individual containers or receptacles, e.g. bags, sacks, boxes, cartons, cans, or jars
- B65B1/30—Devices or methods for controlling or determining the quantity or quality or the material fed or filled
- B65B1/32—Devices or methods for controlling or determining the quantity or quality or the material fed or filled by weighing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B43/00—Forming, feeding, opening or setting-up containers or receptacles in association with packaging
- B65B43/42—Feeding or positioning bags, boxes, or cartons in the distended, opened, or set-up state; Feeding preformed rigid containers, e.g. tins, capsules, glass tubes, glasses, to the packaging position; Locating containers or receptacles at the filling position; Supporting containers or receptacles during the filling operation
- B65B43/54—Means for supporting containers or receptacles during the filling operation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B57/00—Automatic control, checking, warning, or safety devices
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Basic Packing Technique (AREA)
Abstract
The invention discloses a static accurate weighing system and a method, which are used for a medicine granule counting filling system, wherein the system comprises a base arranged at a preset position on a granule counting filling line and a weighing unit fixed on the base; the weighing unit comprises a feeding star plate, a guide frame, a weighing level and a collecting unit: the feeding star plate is used for acquiring the bottle bodies from the assembly line and sequentially conveying the bottle bodies to the appointed position; the guide frame is used for limiting the moving position of the bottle body, so that the bottle body can accurately reach the working area of the weighing balance and the working area of the several filling machines; the weighing balance is positioned at two sides of the several filling working areas, and the acquisition unit provides information of the position and the state of the bottle body for the weighing control system. The static high-precision weighing device solves the problem of realizing static high-precision weighing in the dynamic feeding process through the combined design of the mechanical structure and the control algorithm, overcomes the defect of the existing dynamic weighing, and solves the engineering difficult problem which puzzles the industry for a long time.
Description
Technical Field
The invention relates to a medicine granule counting filling technology, in particular to a static accurate weighing system and a method for medicine filling weighing.
Background
The static accurate weighing technology of medicines refers to a technology for accurately, stably and reliably measuring and controlling the weight of medicines in the production process of medicines. The technology has important significance for guaranteeing the quality, safety and effectiveness of medicines. Currently, the static accurate weighing technology of medicines is mainly applied to the production of solid preparations (such as tablets, capsules, granules and the like) and injections (such as liquid, powder, freeze-drying and the like).
The static accurate weighing technology of medicines mainly relies on two core components of a weighing sensor and a weighing controller. The load cell is a device that converts a weight signal of a medicine into an electrical signal. The weighing controller is a device for processing, displaying and outputting the electric signals. According to the different working principles of the weighing sensor, the weighing sensor can be divided into various types such as resistance strain type, capacitance type, electromagnetic force type, piezoelectric type and the like. According to different functions of the weighing controller, the weighing controller can be divided into a plurality of types such as single-way, multi-way, intelligent and the like.
At present, a static accurate weighing technology of medicines has been developed and applied to a certain degree at home and abroad. For example, in solid preparation production, a common particle counter can meet the precision requirement through particle counting detection; in the production of injections, the filling amount of a common filling machine can be adjusted through weighing feedback. However, existing weighing techniques still have some problems and drawbacks. For example: factors such as quality non-uniformity, defective products, dust and the like of the medicines can influence the accuracy of weighing results. Factors such as temperature, humidity, air pressure, electromagnetic interference and the like of the weighing environment can influence the stability of a weighing result. Vibration, noise, abrasion, aging and other factors of the weighing device can influence the reliability of the weighing result. Factors such as the motion state, speed and direction of the medicine in the weighing process can influence the real-time performance of the weighing result. In short, it is difficult to reach a stationary state due to the influence of the equipment. How to realize static weighing in the feeding process and solve the problems existing in dynamic weighing is an unsolved problem in the industry.
Further research innovation is needed to solve the above-mentioned problems of the prior art.
Disclosure of Invention
The invention aims to provide a static accurate weighing system so as to solve the problems in the prior art.
According to one aspect of the application, the static accurate weighing system is used for a medicine granule counting filling system and mainly comprises a base arranged at a preset position on a granule counting filling assembly line and a weighing unit fixed on the base; wherein, the weighing unit includes:
the feeding star plate is provided with at least three feeding grooves which are used for acquiring bottle bodies from a production line and sequentially conveying the bottle bodies to a designated position, and reversing the bottle bodies backwards for a preset distance after each feeding;
the guide frame comprises an outer guide frame and an inner guide frame with notches, and the outer guide frame and the inner guide frame are coaxially arranged with the feeding star plate and are used for limiting the moving position of the bottle body, so that the bottle body accurately reaches a weighing balance working area and a plurality of grain filling working areas;
the weighing scales are respectively positioned at two sides of the grain filling working area, and are provided with an outer guide arc and an inner guide arc which are respectively in clearance fit with the outer guide frame and the inner guide frame to form a guide channel which is integrally circular;
the acquisition unit at least covers the area where the weighing unit is located and provides information of the position and the state of the bottle body for the weighing control system.
According to one aspect of the application, the outer guide arc and the outer guide frame are provided with a second gap, and a first gap is arranged between the inner guide arc and the inner guide frame, and the first gap and the second gap are both larger than a threshold value; a light source or a receiving part is arranged at the inner side of the inner guide arc along the diameter direction of the inner guide arc, so that light can sequentially pass through the inner first gap and the second gap to reach the field of view of the acquisition unit; or the light rays emitted from the acquisition unit pass through the second gap and the first gap in sequence and then enter the receiving part.
According to one aspect of the application, the working surfaces of the inner and outer guide arcs are each provided with a buffer layer extending a distance in the height direction of not less than half the height of the bottle body.
According to one aspect of the application, the weighing control system comprises:
the data preprocessing module is used for receiving the optical information or the image data of at least N frames of the weighing unit area acquired by the acquisition unit, preprocessing the optical information or the image data into a uniform format and forming standard data; n is a natural number greater than 3;
the static window searching module is used for sequentially reading each frame of standard data along the time sequence, judging whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, and if the optical information of the corresponding areas of the first gap or the second gap does not reach the threshold value, continuing to read the next frame of standard data until M frames of continuous standard data in time are obtained; m is a natural number greater than 2; in the continuous M-frame standard data, acquiring time information of first-frame standard data and last-frame standard data and taking an intermediate time value;
and the weight data calculation output module searches weight detection data of the K groups of weighing balances closest to the middle moment value, takes an average value, and outputs the average value after correction.
According to one aspect of the application, the weight data calculation output module further comprises a preconfigured correction database, the correction database is provided with correction data under at least one working condition, and working parameters under each working condition comprise a basic parameter, a feeding parameter, a granule counting parameter, a blanking parameter and a rejecting parameter;
the weight data calculation output module is used for retrieving the current working parameters, searching working conditions corresponding to the working parameters, obtaining the current working conditions, subtracting correction data under the correction current working conditions from the average value of the weight detection data, and outputting the correction data.
According to one aspect of the application, in the weighing process after filling, the weight data calculation output module obtains artificial intelligent residue identification information of the preconfigured intelligent control unit, and the final output result and the confidence coefficient are given according to the Copula combined distribution function module of the preconfigured weighing error and the image identification error.
According to one aspect of the application, the static window searching module further comprises obtaining edge lines of the bottle mouth or the bottle cap from the image acquisition information of the intelligent control unit when searching the continuous M frames of standard data, and judging whether the circle center of the bottle cap or the bottle mouth is located in a designated area or not according to each frame of standard image; if not, deleting the frame and the standard image at the moment before the frame.
According to another aspect of the present application, a static accurate weighing method is provided, which is implemented based on the static accurate weighing system according to any one of the above technical solutions, and the method includes the following steps:
s1, receiving optical information or image data of at least N frames of weighing unit areas acquired by an acquisition unit, and preprocessing the optical information or the image data into a uniform format to form standard data; n is a natural number greater than 3;
step S2, sequentially reading each frame of standard data along the time sequence, judging whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, and if the optical information of the corresponding areas of the first gap or the second gap does not reach the threshold value, continuing to read the next frame of standard data until the M frames of continuous standard data in time are obtained; m is a natural number greater than 2; in the continuous M-frame standard data, acquiring time information of first-frame standard data and last-frame standard data and taking an intermediate time value;
and S3, searching weight detection data of the K groups of weighing balances closest to the middle moment value, taking an average value, correcting the average value and outputting the average value.
According to one aspect of the present application, during the weighing process after filling, further comprising:
and obtaining artificial intelligent residue identification information of a preconfigured intelligent control unit, and giving out a final output result and confidence level according to a Copula joint distribution function module of a preconfigured weighing error and an image identification error.
According to one aspect of the application, when searching continuous M frames of standard data, the method further comprises the steps of acquiring edge lines of the bottle mouth or the bottle cap from image acquisition information of the intelligent control unit, and judging whether the circle center of the bottle cap or the bottle mouth is located in a designated area or not according to each frame of standard image; if not, deleting the frame and the standard image at the moment before the frame.
The dynamic weighing device has the beneficial effects that the problem of realizing static high-precision weighing in the dynamic feeding process is solved, and the defect of the existing dynamic weighing is overcome.
Drawings
Fig. 1 is a schematic diagram of the structure of a weighing cell.
Fig. 2 is a plan view of the weighing cell.
Fig. 3 is a schematic view of a part of the weighing cell.
Fig. 4 is a plan view of a part of the weighing cell.
Fig. 5 is an overall schematic of the precision weighing system.
In the drawings, each reference numeral is:
a weighing unit 1, a feeding star plate 10, a conveying groove 11, a rotating shaft 12, an outer guide frame 13, an inner guide frame 14,
Base 2, tray component 3, medicine bottle 4,
A first weighing scale 5, an outer guide arc 51, an inner guide arc 52, a buffer layer 53, a gap 54,
A second weighing balance 6,
A grain counting machine 7, a conveyor belt 8 and a collecting unit 9.
Detailed Description
In the prior art, the grain counting machine mainly achieves the precision requirement through grain counting detection, but the reality is that: defective products can also appear in the medicine particles, and the medicine particles also have dust and other factors, so that on one hand, the difference is relatively large by visual detection, and for some small dust, the medicine particles are difficult to confirm. To above-mentioned problem, this application adopts static weighing technique to improve the weighing precision and the efficiency of medicine. The static weighing technique is a technique in which a medicine is temporarily stopped or decelerated in some way during the movement of the medicine to a stationary or near stationary state, and then weighing measurement is performed. The technology can effectively avoid dynamic errors of medicines and improve weighing accuracy and stability. In order to balance weighing precision and particle filling efficiency, the weighing device needs to reach a static state as soon as possible, then start as soon as possible and enter the next link.
As shown in fig. 1 to 5, a static accurate weighing system is provided for a medicine granule counting filling system, and mainly comprises a base arranged at a preset position on a granule counting filling line and a weighing unit fixed on the base; wherein, the weighing unit includes:
the feeding star plate is provided with at least three feeding grooves which are used for acquiring bottle bodies from a production line and sequentially conveying the bottle bodies to a designated position, and reversing the bottle bodies backwards for a preset distance after each feeding;
the guide frame comprises an outer guide frame and an inner guide frame with notches, and the outer guide frame and the inner guide frame are coaxially arranged with the feeding star plate and are used for limiting the moving position of the bottle body, so that the bottle body accurately reaches a weighing balance working area and a plurality of grain filling working areas;
the weighing scales are respectively positioned at two sides of the grain filling working area, and are provided with an outer guide arc and an inner guide arc which are respectively in clearance fit with the outer guide frame and the inner guide frame to form a guide channel which is integrally circular;
the acquisition unit at least covers the area where the weighing unit is located and provides information of the position and the state of the bottle body for the weighing control system.
In this embodiment, the friction between the bottle and the guide frame becomes an internal force in a clearance fit manner, so that the influence on the measurement accuracy is avoided, and only the weight of the part is subtracted in a peeling manner, so that the influence on the measurement accuracy caused by the kinetic energy of the bottle and partial vibration is improved in a mechanical design manner. The clearance fit achieves a release from the rest with as little interference as possible. But without this guide or arcuate guide, the travel of the bottle is uncontrolled.
In addition, in the embodiment, the feeding star plate can convey the bottles to the designated positions from the assembly line according to a certain sequence and speed, so that the interval and synchronism among the bottles are ensured, and the collision and blockage among the bottles are reduced. The guide frame can limit the bottle body on a fixed track, so that the bottle body can not deviate or incline in the moving process, and the stability and the alignment of the bottle body are improved. The weighing balance can weigh the bottle body before and after the bottle body reaches the filling work areas to acquire the data of the quality of the bottle body and the quality of the bottle body, so that the quality change in the filling process is monitored. The acquisition unit can acquire the position and state information of the bottle body in the weighing unit area in real time through an optical information or image data acquisition mode, and data support and feedback are provided for a weighing control system. It should be noted that the feeding star plate can reverse a preset distance during feeding, so that the bottle body is separated from the star plate, and the influence on weighing is reduced. This can be achieved by adjusting the operating parameters of the servo motor.
According to one aspect of the application, the outer guide arc and the outer guide frame are provided with a second gap, and a first gap is arranged between the inner guide arc and the inner guide frame, and the first gap and the second gap are both larger than a threshold value; a light source or a receiving part is arranged at the inner side of the inner guide arc along the diameter direction of the inner guide arc, so that light can sequentially pass through the inner first gap and the second gap to reach the field of view of the acquisition unit; or the light rays emitted from the acquisition unit pass through the second gap and the first gap in sequence and then enter the receiving part.
In the present embodiment, the optical image acquisition and processing is performed using the gap. Since the illumination condition in the factory may be complicated, the image quality may be unstable by using only the industrial camera, and more time is spent in identifying the bottle, so that the light source (such as linear structured light, a plurality of point light sources or gratings) is transmitted through the gap by using the gap, and then a very obvious brightness area is formed in the camera, so that the state of the bottle is more easily identified. Of course, the transmission and reception modes can be adopted according to the optical symmetrical design. The first gap and the second gap are located in a certain radial direction to form a radial light path channel. In addition, the drawings are merely examples and not all details are shown.
According to one aspect of the application, the working surfaces of the inner and outer guide arcs are each provided with a buffer layer extending a distance in the height direction of not less than half the height of the bottle body.
The moving bottle body is stopped as soon as possible through the buffer layer, so that a short static time is obtained, and accurate weighing is realized. In this embodiment, the bottle body can be stopped quickly by arranging the buffer layer as long as possible in the height direction and optimizing the friction coefficient of the buffer layer. In further embodiments, other types of cushioning materials or structures, such as springs, rubber, air springs, etc., may be used to improve cushioning and durability.
According to one aspect of the application, the weighing control system comprises:
the data preprocessing module is used for receiving the optical information or the image data of at least N frames of the weighing unit area acquired by the acquisition unit, preprocessing the optical information or the image data into a uniform format and forming standard data; n is a natural number greater than 3;
the static window searching module is used for sequentially reading each frame of standard data along the time sequence, judging whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, and if the optical information of the corresponding areas of the first gap or the second gap does not reach the threshold value, continuing to read the next frame of standard data until M frames of continuous standard data in time are obtained; m is a natural number greater than 2; in the continuous M-frame standard data, acquiring time information of first-frame standard data and last-frame standard data and taking an intermediate time value;
and the weight data calculation output module searches weight detection data of the K groups of weighing balances closest to the middle moment value, takes an average value, and outputs the average value after correction.
In this embodiment, it is first ensured that the stability of the vial after loading can be accurately determined by a precise image processing technique, which is a key part of the overall process. Only after the medicine bottle is completely stable, the weighing accuracy can be ensured. The adoption of the light source and the collection unit ensures that the light can accurately irradiate the medicine bottle and be completely captured by the collection unit. This provides high quality raw data for subsequent image processing. In addition, through the comparison of medicine bottle positions between the continuous frames, the stability of medicine bottles can be effectively analyzed, so that not only can the weighing accuracy be ensured, but also potential impulse caused by unstable medicine bottles can be avoided, and further the weighing accuracy is influenced. In a word, the embodiment can ensure that the star-plate-type feeding medicine bottles can be accurately, quickly and stably fed, and ensure that the medicine bottles are accurately weighed after feeding is completed.
According to one aspect of the application, the weight data calculation output module further comprises a preconfigured correction database, the correction database is provided with correction data under at least one working condition, and working parameters under each working condition comprise a basic parameter, a feeding parameter, a granule counting parameter, a blanking parameter and a rejecting parameter; the weight data calculation output module is used for retrieving the current working parameters, searching working conditions corresponding to the working parameters, obtaining the current working conditions, subtracting correction data under the correction current working conditions from the average value of the weight detection data, and outputting the correction data.
In this embodiment, the rejection parameters include the number of bottles to be rejected when the machine is started, the number of times of continuous rejection and shutdown, the rejection action time, the rejection delay time, the turntable speed, etc. The blanking parameters comprise bottling time, bottle discharging time, material nozzle vibration frequency, buffering time and the like. The parameters include electric eye parameters, door closing time and the like. The feeding parameters comprise vibration delay starting time, bin gate height, vibration speed and frequency of each stage and the like.
In other words, in the present embodiment, in order to reduce the weighing error caused by the background vibration or the like, a correction data database is constructed for each operation state, and then error correction is performed according to the content of the database. During static weighing, factors such as environmental vibration, pipeline vibration and the like can also cause certain influence, so that weight data under the complete ideal condition can be obtained through the correction process, and the accuracy is greatly improved.
According to one aspect of the application, in the weighing process after filling, the weight data calculation output module obtains artificial intelligent residue identification information of the preconfigured intelligent control unit, and the final output result and the confidence coefficient are given according to the Copula combined distribution function module of the preconfigured weighing error and the image identification error. In this step, a joint distribution function construction is performed with respect to the correlation between the weighing error and the image recognition error. Such as in the course of an image recognition process,
the Copula joint distribution function module is constructed specifically as follows:
STEP1. Data are collected from the weighing data and the image data acquisition device, respectively. It is assumed that each drug particle has a unique number that can be used to match the results of weighing and image acquisition. It is assumed that the weighing device gives the mass m of the drug particles and the image acquisition device gives the residue information r of the drug particles, such as the number of residues, size, shape, etc.
STEP2. Pretreatment of the data. This step is to eliminate some outliers or noise and normalize or normalize the data. The specific method may be selected according to the actual situation, for example:
STEP21, detecting and eliminating abnormal values of the weight data. Statistical methods such as box graphs, Z-scores, mahalanobis distances, etc. can be used to identify and delete data points that are far from normal.
STEP22 noise filtering and segmentation is performed on the image acquisition data. Some image processing methods, such as median filtering, edge detection, threshold segmentation, etc., may be used to remove noise from the image and to distinguish between drug particles and debris.
STEP23 data were normalized or normalized. Since the weighing data and the image acquisition data may have different dimensions and distribution characteristics, the data may be standardized or normalized to have the same or similar dimensions and morphology for facilitating subsequent analysis. For example, methods such as maximum-minimum normalization, Z-score normalization, etc. may be used.
STEP3. Copula function fitting was performed on the data. This step is to find a suitable copula function to describe the correlation between the weighing data and the image acquisition data. The specific method may be selected according to the actual situation, for example:
STEP31. Select a copula family of functions. Based on the copula family table, a copula family suitable for the current problem characteristics, such as archimedes family or ellipsoids family, is selected.
STEP32. Estimate copula function parameters. For a particular functional form in each copula family of functions, a maximum likelihood estimation method or other method may be used to estimate its parameter values, such as correlation coefficients, tail correlation coefficients, etc.
STEP33. The copula function fitting effect was evaluated. For each copula function form and parameter value, some evaluation index may be used to measure its fitting effect, such as the red pool information amount criterion (AIC), bayesian information amount criterion (BIC), mean square error (MSTEPE), etc.
STEP34. Select the optimal copula function form and parameter values. According to the result of the evaluation index, an optimal or closest optimal copula function form and parameter value can be selected as a description of the correlation between the weighing data and the image acquisition data.
STEP4, comprehensive judgment is performed by using a copula function. The step is to comprehensively judge the quality and the residue information of the medicine particles by utilizing the result of the copula function and give weighing data and confidence level so as to facilitate the subsequent quality control or optimization. The specific method may be selected according to the actual situation, for example:
step41. Calculate the Cumulative Distribution Function (CDF) and Probability Density Function (PDF) of the copula function. Based on the previously selected copula function form and parameter values, the values or expressions of the CDF and PDF thereof can be calculated to facilitate subsequent calculations or analysis.
STEP42. Calculate the integrated error probability of the drug particles. From the CDF or PDF of the copula function, the probability that the weighing error and the image error of each drug particle fall within a certain interval at the same time, for example, P (m <0.1, r < 0.2), representing the probability that the mass error is less than 0.1 g and the residue information error is less than 0.2, can be calculated. This probability may reflect the overall error level of the drug particles, with larger representations being more accurate and smaller representations being less accurate.
According to the relation between the time when the image identifies the residue, the bottling time and the weighing time, the weighing data confidence degree can be judged, for example, weighing is carried out at a plurality of moments after the residue is identified, and the weight exceeds a threshold value, so that the probability of occurrence of problems in the quality of the bottle of medicine is comprehensively seen to be greatly improved. Thus sending a signal to the bottle kicking mechanism to reject the bottle of medicine. For smaller flakes, their weight and impulse may have an impact on the measurement. Therefore, the confidence is given through joint reasoning, and the judgment accuracy can be greatly improved.
According to one aspect of the application, the static window searching module further comprises obtaining edge lines of the bottle mouth or the bottle cap from the image acquisition information of the intelligent control unit when searching the continuous M frames of standard data, and judging whether the circle center of the bottle cap or the bottle mouth is located in a designated area or not according to each frame of standard image; if not, deleting the frame and the standard image at the moment before the frame.
In this step, it is mainly determined whether the bottle is in a relatively stationary state or at a moment during shaking. In other words, in theory, it can be classified into steady-state rest and unsteady-state rest. Unsteady state is static, a certain kinetic energy or momentum can exist, and the result of the symmetry is influenced. Thus, by way of example, the determination of the edge line may assist in determining whether it is stationary. When the unstable state is static, the circle center can shake to a certain extent, so that the unstable state can be identified.
According to another aspect of the present application, a static accurate weighing method is provided, which is implemented based on the static accurate weighing system according to any one of the above technical solutions, and the method includes the following steps:
s1, receiving optical information or image data of at least N frames of weighing unit areas acquired by an acquisition unit, and preprocessing the optical information or the image data into a uniform format to form standard data; n is a natural number greater than 3;
this step is to acquire optical information or image data of the vial in the weighing cell area, such as using a camera or a photosensor, and acquire information about the position, shape, size, etc. of the vial on the weighing scale. This information can be used to determine if the vial is completely dropped on the weighing scale and if other objects interfere with the weighing process. The preprocessing is to convert data of different devices or different formats into a unified format, such as pixel values, gray values, binarization and the like, so as to facilitate subsequent processing.
Step S2, sequentially reading each frame of standard data along the time sequence, judging whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, and if the optical information of the corresponding areas of the first gap or the second gap does not reach the threshold value, continuing to read the next frame of standard data until the M frames of continuous standard data in time are obtained; m is a natural number greater than 2; and in the continuous M-frame standard data, acquiring the time information of the first-frame standard data and the last-frame standard data and taking an intermediate time value.
Whether the vial is fully landed on the weighing scale can be determined based on whether the optical information of the two regions reaches a threshold (e.g., brightness, color, etc.). If both areas reach the threshold value, the medicine bottle is in a stable state, and weighing can be performed; if one area does not reach the threshold value, the medicine bottle is in a moving state or swaying state, and weighing cannot be performed. In order to guarantee the reliability of the weighing result, it is necessary that at least M consecutive frames (M is greater than 2) satisfy the condition that both areas reach the threshold value. In these successive frames, the time information of the first frame and the last frame is acquired, and their average value is taken as an intermediate time value.
And S3, searching weight detection data of the K groups of weighing balances closest to the middle moment value, taking an average value, correcting the average value and outputting the average value. The weighing balance will constantly detect and record the weight of the vial thereon and correspond to the time of day information. From the intermediate time value, the weight detection data of K groups (K is a natural number) nearest to it can be found, and their average value is taken as the weight of the vial. This can avoid the influence of errors or noise of individual data. The correction is to eliminate errors or deviations of the weighing balance itself, such as zero drift, temperature variations, etc. And then outputting, namely displaying or storing the corrected weight value.
According to one aspect of the present application, during the weighing process after filling, further comprising:
and obtaining artificial intelligent residue identification information of a preconfigured intelligent control unit, and giving out a final output result and confidence level according to a Copula joint distribution function module of a preconfigured weighing error and an image identification error.
The construction process of the joint distribution function module is as described above, and the preconfigured module is called. And judging whether a large error exists in the weighing after filling or not through the given confidence coefficient.
It should be noted that, for the identification of intelligent control units and artificial intelligent fragments, reference may be made to the applicant's patent, and a matrix type intelligent module particle counting system and method (2023112918259) with a fragment detection function will not be described in detail herein to avoid repetition.
According to one aspect of the application, when searching continuous M frames of standard data, the method further comprises the steps of acquiring edge lines of the bottle mouth or the bottle cap from image acquisition information of the intelligent control unit, and judging whether the circle center of the bottle cap or the bottle mouth is located in a designated area or not according to each frame of standard image; if not, deleting the frame and the standard image at the moment before the frame.
Specific actions and effects have been described above and are not described in detail herein.
In further embodiments, bayesian reasoning, fuzzy logic, multi-criterion decision, etc. may also be employed to enhance the overall judgment and confidence.
In a word, in this embodiment, through parts such as pay-off star dish, leading truck, weighing level and collection unit, constitute a stable, high-efficient, accurate weighing unit, can realize the real-time supervision and the control to the bottle quality among the several filling processes of medicine. The matching and coordination among the components ensure that the bottle body can smoothly move, position, fill and weigh on the assembly line, and avoid weighing errors caused by shaking, shifting, tilting and the like of the bottle body.
And secondly, by adopting an optical information or image data acquisition mode and combining a data preprocessing module and a static window searching module, the time when the bottle body reaches a weighing balance working area and a plurality of filling working areas can be effectively identified, so that the optimal weighing time is determined. The way can avoid weighing errors caused by the influence of inertia force, friction force and the like on the bottle body in the movement process, and can also avoid weighing errors caused by the external interference on the bottle body in the stop state.
Specifically, the optical information or image data acquisition mode can realize the judgment of whether the bottle body completely stops on the guide arc through the light source or the receiving part, the first gap, the second gap and other parts, so as to determine whether the bottle body enters a weighing state. The data preprocessing module can perform some processing operations on the optical information or the image data acquired by the acquisition unit, such as removing abnormal values, missing values, noise and the like, so as to improve the data quality. The static window searching module can sequentially read each frame of standard data along the time sequence, judge whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, thereby determining a time window continuously meeting the weighing condition, and taking the middle time value as the optimal weighing time.
And finally, correcting and comprehensively judging the weight detection data according to the correction data and the artificial intelligent residue identification information under different working conditions by using the correction database and the Copula combined distribution function module, so that the accuracy and the reliability of the weighing result are improved. The method can eliminate systematic errors caused by factors such as equipment aging, environmental changes, residue influences and the like, and can also consider the correlation between weighing errors and image recognition errors, so that more reasonable and comprehensive output results and confidence are given. Specifically, the correction database can pre-configure correction data under different working conditions according to different working parameters, such as basic parameters, feeding parameters, granule counting parameters, blanking parameters, rejecting parameters and the like, and is used for carrying out deviation correction on weight detection data so as to improve weighing accuracy. The Copula combined distribution function module can establish a correlation model between weighing errors and image recognition errors according to artificial intelligent residue recognition information, and is used for comprehensively judging weight detection data so as to improve weighing reliability.
The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to the specific details of the above embodiments, and various equivalent changes can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the equivalent changes belong to the protection scope of the present invention.
Claims (7)
1. The static accurate weighing system is used for a medicine granule counting filling system and is characterized by comprising a base arranged at a preset position on a granule counting filling assembly line and a weighing unit fixed on the base; wherein, the weighing unit includes:
the feeding star plate is provided with at least three feeding grooves which are used for acquiring bottle bodies from a production line and sequentially conveying the bottle bodies to a designated position, and reversing the bottle bodies backwards for a preset distance after each feeding;
the guide frame comprises an outer guide frame and an inner guide frame with notches, and the outer guide frame and the inner guide frame are coaxially arranged with the feeding star plate and are used for limiting the moving position of the bottle body, so that the bottle body accurately reaches a weighing balance working area and a plurality of grain filling working areas;
the weighing scales are respectively positioned at two sides of the grain filling working area, and are provided with an outer guide arc and an inner guide arc which are respectively in clearance fit with the outer guide frame and the inner guide frame to form a guide channel which is integrally circular;
the acquisition unit at least covers the area where the weighing unit is positioned and provides information of the position and the state of the bottle body for the weighing control system;
the outer guide arc and the outer guide frame are provided with a second gap, and a first gap is arranged between the inner guide arc and the inner guide frame, and the first gap and the second gap are both larger than a threshold value; a light source or a receiving part is arranged at the inner side of the inner guide arc along the diameter direction of the inner guide arc, so that light can sequentially pass through the inner first gap and the second gap to reach the field of view of the acquisition unit; or the light rays emitted from the acquisition unit pass through the second gap and the first gap in sequence and then enter the receiving part;
the working surfaces of the inner guide arc and the outer guide arc are respectively provided with a buffer layer, and the extending distance of the buffer layers in the height direction is not less than half of the height of the bottle body; stopping the moving bottle body through the buffer layer to obtain a static time, so that accurate weighing is realized;
the weighing control system comprises:
the data preprocessing module is used for receiving the optical information or the image data of at least N frames of the weighing unit area acquired by the acquisition unit, preprocessing the optical information or the image data into a uniform format and forming standard data; n is a natural number greater than 3;
the static window searching module is used for sequentially reading each frame of standard data along the time sequence, judging whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, and if the optical information of the corresponding areas of the first gap or the second gap does not reach the threshold value, continuing to read the next frame of standard data until M frames of continuous standard data in time are obtained; m is a natural number greater than 2; in the continuous M-frame standard data, acquiring time information of first-frame standard data and last-frame standard data and taking an intermediate time value;
and the weight data calculation output module searches weight detection data of the K groups of weighing balances closest to the middle moment value, takes an average value, and outputs the average value after correction.
2. The static precision weighing system of claim 1, wherein said weight data calculation output module further comprises a preconfigured correction database provided with correction data for at least one operating condition, the operating parameters for each operating condition comprising a base parameter, a feed parameter, a granule count parameter, a blanking parameter, and a reject parameter;
the weight data calculation output module is used for retrieving the current working parameters, searching working conditions corresponding to the working parameters, obtaining the current working conditions, subtracting correction data under the correction current working conditions from the average value of the weight detection data, and outputting the correction data.
3. The static accurate weighing system according to claim 1, wherein in the weighing process after filling, the weight data calculation output module obtains artificial intelligent residue identification information of a preconfigured intelligent control unit, and gives a final output result and a confidence level according to a Copula combined distribution function module of a preconfigured weighing error and an image identification error.
4. The static accurate weighing system according to claim 1, wherein the static window searching module further comprises acquiring edge lines of the bottle mouth or the bottle cap from image acquisition information of the intelligent control unit when searching continuous M frames of standard data, and judging whether the circle center of the bottle cap or the bottle mouth is located in a designated area or not according to each frame of standard image; if not, deleting the frame and the standard image at the moment before the frame.
5. Static accurate weighing method, based on the static accurate weighing system of any one of claims 1 to 4, characterized in that it comprises the following steps:
s1, receiving optical information or image data of at least N frames of weighing unit areas acquired by an acquisition unit, and preprocessing the optical information or the image data into a uniform format to form standard data; n is a natural number greater than 3;
step S2, sequentially reading each frame of standard data along the time sequence, judging whether the optical information of the corresponding areas of the first gap and the second gap reaches a threshold value, and if the optical information of the corresponding areas of the first gap or the second gap does not reach the threshold value, continuing to read the next frame of standard data until the M frames of continuous standard data in time are obtained; m is a natural number greater than 2; in the continuous M-frame standard data, acquiring time information of first-frame standard data and last-frame standard data and taking an intermediate time value;
and S3, searching weight detection data of the K groups of weighing balances closest to the middle moment value, taking an average value, correcting the average value and outputting the average value.
6. The static precision weighing method according to claim 5, further comprising, during the weighing process after filling:
and obtaining artificial intelligent residue identification information of a preconfigured intelligent control unit, and giving out a final output result and confidence level according to a Copula joint distribution function module of a preconfigured weighing error and an image identification error.
7. The static accurate weighing method according to claim 5, further comprising acquiring edge lines of the bottle mouth or the bottle cap from image acquisition information of the intelligent control unit when searching continuous M frames of standard data, and judging whether the circle center of the bottle cap or the bottle mouth is located in a designated area or not according to each frame of standard image; if not, deleting the frame and the standard image at the moment before the frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380723.4A CN117141783B (en) | 2023-10-24 | 2023-10-24 | Static accurate weighing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380723.4A CN117141783B (en) | 2023-10-24 | 2023-10-24 | Static accurate weighing system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117141783A CN117141783A (en) | 2023-12-01 |
| CN117141783B true CN117141783B (en) | 2023-12-26 |
Family
ID=88910285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311380723.4A Active CN117141783B (en) | 2023-10-24 | 2023-10-24 | Static accurate weighing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117141783B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07167704A (en) * | 1993-10-22 | 1995-07-04 | Takeda Chem Ind Ltd | Apparatus for weighing filling amount |
| EP0787653A1 (en) * | 1996-02-02 | 1997-08-06 | Food Machinery Espanola S.A. | Automatic bulk fruit package weighing filling machine |
| US6359238B1 (en) * | 1999-12-17 | 2002-03-19 | Siemens Electrocom, L.P. | Apparatus and method for weighing a moving object |
| JP2005265764A (en) * | 2004-03-22 | 2005-09-29 | Yamato Scale Co Ltd | Weighing apparatus and weighing method |
| DE102008027624A1 (en) * | 2008-06-10 | 2009-12-17 | Zill, Siegfried, Dipl.-Ing. | Method for controlling and sorting small articles, involves supplying number of small articles by conveying unit per time unit up to separation unit, and small articles are lined up and transported one behind other in conveying tracks |
| CN101795180A (en) * | 2010-01-28 | 2010-08-04 | 北京邮电大学 | MIMO detection pretreatment method with optimal sequencing feature and device |
| CN102582878A (en) * | 2012-03-06 | 2012-07-18 | 上海恒谊制药设备有限公司 | Device and method capable of automatically and quickly detecting filling quantity of bottles |
| EP2554957A1 (en) * | 2011-08-03 | 2013-02-06 | Libra Weighing Machines Limited | Weighbridge component |
| CN108896143A (en) * | 2018-06-14 | 2018-11-27 | 天地科技股份有限公司 | A kind of rotary three buckets dynamic material feeding meausring apparatus |
| CN109160266A (en) * | 2018-09-03 | 2019-01-08 | 刘强 | A kind of storage old and useless battery size automatic measuring and posture put system |
| CN109433641A (en) * | 2018-09-30 | 2019-03-08 | 南通大学 | The filling omission intelligent detecting method of tablet capsule based on machine vision |
| CN213502985U (en) * | 2020-07-20 | 2021-06-22 | 南京比逊弥特智能科技有限公司 | Lower hopper structure that can remove dust |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080169044A1 (en) * | 2006-10-20 | 2008-07-17 | Forhealth Technologies, Inc. | Automated drug preparation apparatus including syringe loading, preparation and filling |
-
2023
- 2023-10-24 CN CN202311380723.4A patent/CN117141783B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07167704A (en) * | 1993-10-22 | 1995-07-04 | Takeda Chem Ind Ltd | Apparatus for weighing filling amount |
| EP0787653A1 (en) * | 1996-02-02 | 1997-08-06 | Food Machinery Espanola S.A. | Automatic bulk fruit package weighing filling machine |
| US6359238B1 (en) * | 1999-12-17 | 2002-03-19 | Siemens Electrocom, L.P. | Apparatus and method for weighing a moving object |
| JP2005265764A (en) * | 2004-03-22 | 2005-09-29 | Yamato Scale Co Ltd | Weighing apparatus and weighing method |
| DE102008027624A1 (en) * | 2008-06-10 | 2009-12-17 | Zill, Siegfried, Dipl.-Ing. | Method for controlling and sorting small articles, involves supplying number of small articles by conveying unit per time unit up to separation unit, and small articles are lined up and transported one behind other in conveying tracks |
| CN101795180A (en) * | 2010-01-28 | 2010-08-04 | 北京邮电大学 | MIMO detection pretreatment method with optimal sequencing feature and device |
| EP2554957A1 (en) * | 2011-08-03 | 2013-02-06 | Libra Weighing Machines Limited | Weighbridge component |
| CN102582878A (en) * | 2012-03-06 | 2012-07-18 | 上海恒谊制药设备有限公司 | Device and method capable of automatically and quickly detecting filling quantity of bottles |
| CN108896143A (en) * | 2018-06-14 | 2018-11-27 | 天地科技股份有限公司 | A kind of rotary three buckets dynamic material feeding meausring apparatus |
| CN109160266A (en) * | 2018-09-03 | 2019-01-08 | 刘强 | A kind of storage old and useless battery size automatic measuring and posture put system |
| CN109433641A (en) * | 2018-09-30 | 2019-03-08 | 南通大学 | The filling omission intelligent detecting method of tablet capsule based on machine vision |
| CN213502985U (en) * | 2020-07-20 | 2021-06-22 | 南京比逊弥特智能科技有限公司 | Lower hopper structure that can remove dust |
Non-Patent Citations (2)
| Title |
|---|
| 电气测量技术及仪器;中国无线电电子学文摘(03);第160页 * |
| 称重技术在全自动数粒装瓶生产线上的应用;陈旺平;张爱平;;机电信息(35);第36-38页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117141783A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10894686B2 (en) | Systems and methods for loading items into a tray | |
| US10125001B2 (en) | Method for monitoring and controlling a filling system, and device for carrying out said method | |
| US10301122B2 (en) | Device for feeding items to a sorting machine and sorting machine | |
| US7746486B2 (en) | Pellet sorting by diameter measurement | |
| CN101303316B (en) | Method and apparatus for automatic detection on large infusion production line | |
| US5499718A (en) | System and method for seeking and presenting an area for reading with a vision system | |
| US7814939B2 (en) | Method of operating a beverage bottling plant with a beverage filling machine for filling beverage bottles, and a method and apparatus for monitoring beverage bottle or container handling machines in the beverage bottling plant | |
| CN101692056B (en) | Method and device for automatically detecting impurities in health wine | |
| CN207188252U (en) | The intelligent checking system of grain unsound grain | |
| CN101105460A (en) | Multifunctional bottle checker | |
| CN109433641B (en) | Intelligent detection method for tablet capsule filling omission based on machine vision | |
| US20110064266A1 (en) | Device and method for checking container closures | |
| RU2714952C1 (en) | Device for processing fruit-growing products, such as blueberries and similar | |
| CN111389753A (en) | P L C fruit vegetables intelligence sorting system that can long-range wisdom control | |
| CN117141783B (en) | Static accurate weighing system and method | |
| CN102320544A (en) | On-line automatic weighing system for filling and sealing of bottle container | |
| CN111537520A (en) | Beverage bottle defect detection system based on machine vision | |
| CN102608018A (en) | Backlight type particle counting device | |
| JP2006346630A (en) | Sorting apparatus | |
| US4819783A (en) | Automated inspection system and method | |
| CN212159606U (en) | Beverage bottle defect detection system based on machine vision | |
| KR102171867B1 (en) | Sorting apparatus for carrier breakage reduction | |
| CN116871179A (en) | Intelligent logistics sorting device and sorting method thereof | |
| CN115265927B (en) | Container sealing detection method and detection device | |
| WO2012115504A2 (en) | Solar cell sorting conveyor and methodology thereof |
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 |