CN103630473B - Active sludge on-line computer graphical analysis early warning system and method - Google Patents
Active sludge on-line computer graphical analysis early warning system and method Download PDFInfo
- Publication number
- CN103630473B CN103630473B CN201310713069.4A CN201310713069A CN103630473B CN 103630473 B CN103630473 B CN 103630473B CN 201310713069 A CN201310713069 A CN 201310713069A CN 103630473 B CN103630473 B CN 103630473B
- Authority
- CN
- China
- Prior art keywords
- image
- der pilz
- length
- active sludge
- sludge
- 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.)
- Expired - Fee Related
Links
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
- Activated Sludge Processes (AREA)
Abstract
The present invention relates to a kind of active sludge on-line computer graphical analysis early warning system and method; This system is made up of sample diluting device, peristaltic pump, computing machine, high-speed camera, microscope and sample chamber.The method first obtains sample morphology image, then the image obtained is processed, analyze flco Size Distribution and the der Pilz length distribution of active sludge, mud floc particle Size Distribution and der Pilz length distribution and activated sludge settling property are associated, and then early warning is carried out to active sludge effect of settling.
Description
Technical field
The invention belongs to a kind of sewage disposal process detection technique, be exactly in biological wastewater treatment process specifically, the active sludge der Pilz situation of secondary sedimentation tank (second pond) carries out continuous computer pattern analysis, thus carries out the method for early warning to the mud filamentary discharges that may occur.
Background technology
Activated sludge process is modal sanitary sewage disposal technology.Active sludge realizes mud-water separation through second pond, obtains the water outlet of comparatively clarifying.The quality of activated sludge settling property is the key obtaining better effluent quality, and mud filamentary discharges is the key factor affecting activated sludge settling property.Theoretical according to the skeleton that mud flco is formed, der Pilz can provide attachment skeleton for active pollution index, thus the shear action of opposing waterpower, keep larger volume to be beneficial to sedimentation.But when der Pilz excess growth, the collision that will affect between mud flco combines, and makes active sludge become loose, causes activated sludge bulking.Modern active sludge treatment factory, particularly nitrogen phosphorus ligands reactor, have the long residence time, dissolubility easily biodegradable organics concentration is lower.These factors all can be beneficial to hyphomycetic growth.Therefore, monitoring the hyphomycetic situation of active sludge is in time the important leverage ensureing that activated sludge process sewage disposal system is normally run.
Microscopic examination is a common method of inspection active sludge form and der Pilz content thereof.But this Measures compare is consuming time, can not the precipitated form of reactivity mud timely, and be easily subject to the impact of subjective judgement of operating personnel.These factors all limit the application of microbioscope detection in active sludge at-once monitor.The present invention utilizes the method for on-line computer graphics process to replace traditional microbiological microscopy, obtains the relation between active sludge form and settling property.Computer graphical processing is a kind of method of Extraction and determination information from figure.It has fast, quantitative advantage, and can avoid manually-operated subjectivity.
Phase at the end of the nineties in last century, the method of the method for computer graphics analysis to active pollution index morphological analysis is utilized to start to occur abroad, by analyzing the diameter of active pollution index, fractal constant, the indexs such as der Pilz total length evaluate active sludge form and the impact on active sludge sedimentation thereof.In these existing methods, the size of active pollution index generally represents by mean diameter.And the set that active sludge is generally made up of the floc particle that difference in size is very large.It is obviously not enough for only summarizing its size by an average number.Therefore in the present invention, the concept of flco size distribution and der Pilz length distribution will be introduced.
Existing active sludge computer graphics analysis method is all that off-line completes in addition, is realized by hand sampling, preparation of samples, Image Acquisition and analysis.This limits computer graphics analysis method detects application key in activated sludge bulking.
Summary of the invention
The technical matters that 1, will solve
Existing active sludge image analysis method has come mainly through off-line method, and only can measure mud flco and hyphomycetic mean diameter and total length, cannot as the on-line early warning of second pond effect of settling.The key issue that the present invention will solve, being just to provide one can on-line computer Graph analysis method, carries out real-time analysis to active sludge form.
2, technical scheme
For overcoming the above problems, the present invention, by on-line computer Graph analysis method, analyzes flco Size Distribution and the der Pilz length distribution of active sludge in real time, and associates sludge volume index, thus realizes carrying out on-line early warning to second pond effect of settling.
The invention discloses a kind of active sludge on-line computer image analysis system, this system is made up of sample diluting device, peristaltic pump, computing machine, high-speed camera, microscope and sample chamber, sample diluting device is connected by circulation line with sample chamber, and circulation line is provided with peristaltic pump; Sample chamber is made up of glass, is arranged on below micro objective; One high-speed camera is arranged on above microscope ocular, is taken the sample flowed in sample chamber by microscope; Computing machine, carry out Image Acquisition for controlling high-speed camera and peristaltic pump is controlled automatically, according to flco Size Distribution and the der Pilz length distribution of the graphical analysis active sludge obtained, mud floc particle Size Distribution and der Pilz length distribution and activated sludge settling property are associated, early warning is carried out to active sludge effect of settling.
The invention also discloses the graphical analysis of a kind of active sludge on-line computer and method for early warning, comprise the following steps:
Step one: utilization is arranged on the morphological image information high-speed camera on microscope obtaining sample, sends computing machine to;
Step 2: computing machine carries out image procossing according to the morphological image obtained, analyzes flco Size Distribution and the der Pilz length distribution of active sludge,
Step 3: observe the change with the quantity of institute's analysis chart picture of active pollution index mean diameter and standard deviation thereof, determine the required active sludge amount of images analyzed, graphical analysis number when flco mean diameter and standard deviation thereof are stablized is required amount of images;
Step 4: by measuring the settling property (with sludge volume index SVI) of different activities mud sample and mud floc particle Size Distribution thereof and der Pilz length distribution, find the association between settling property and mud morphological image feature, to be analyzed by inline graphics, draw active sludge morphological feature (the flco Size Distribution of active sludge and der Pilz length distribution), just can its effect of settling of early warning; Measure the linear relationship between der Pilz total length (TEFL) and sludge settling property.
Step 5: setting settling property early warning value, computing machine processes according to the image obtained, analyzes, and is associated with the activated sludge settling property in step 4, carries out early warning to active sludge effect of settling.
Wherein step 2 specifically: active sludge image procossing is mainly divided into two parts, comprises mud floc particle Size Distribution and der Pilz length distribution.
1) mensuration of mud floc particle Size Distribution:
Mud floc particle Size Distribution completes mainly through the following steps:
(1) from the activated sludge sample image obtained, intercept still image, obtain activated sludge sample MIcrosope image;
(2) MIcrosope image is converted into binary picture.The standard transformed is that gray scale is greater than a certain threshold value
Pixel as ' object ', gray scale is less than the pixel of this threshold value as image background, threshold values
Size is generated automatically by image analysis algorithm;
(3) noise reduction process is carried out to binary picture, remove the impurity in image, obtain active pollution index particle figure;
(4) active pollution index Size Distribution measures, and by the pixel quantity of single flco in counting floc particle figure, just can measure the size of flco, the unit of the flco size that this pacing is fixed is pixel, demarcates size after mensuration;
(5) conversion of Pixel Dimensions and international standard long measure: the micro-scale utilizing known length, measures its length in pixels, thus is converted into international standard length.
2) mensuration of der Pilz length distribution:
(1) der Pilz is extracted, and binary picture and floc particle figure is subtracted each other, and just can obtain the binary picture of der Pilz and some granule foreigns;
(2) binary picture of der Pilz and some granule foreigns is carried out noise reduction and extracts skeleton to der Pilz, obtain the der Pilz skeleton image of length direction list pixel;
(3) by the single der Pilz pixel of counting, measure hyphomycetic length in pixels, and change into international standard length.
The required active sludge amount of images analyzed to be determined in step 3, in order to make the data of graphical analysis have representative and reliability widely, preventing the contingency of single analyses, tackling same water sample and carry out repeatedly replication analysis.Active pollution index is complicated three-dimensional structure, it in microscope camera lens towards the size that can affect measurement.The present invention determines required minimum analysis times by observation active pollution index mean diameter and standard deviation thereof with the change of the quantity of institute's analysis chart picture.Amount of images required when standard deviation tends towards stability is minimum amount of images requirement.
3, beneficial effect
Traditional active sludge microscopic detecting method is more consuming time, can not as a kind of real-time monitoring method.And also there is larger operate miss between different operating employee.The present invention utilizes the method for on-line computer pattern analysis to analyze active sludge form, in order to eliminate the subjectivity of artificial microscopic examination.Be a kind of fast, the method for quantitative measurement activated sludge settling property, can as a kind of means of at-once monitor sludge bulking.
Accompanying drawing explanation
Fig. 1 active sludge on-line computer image analysis apparatus.
Fig. 2 activated sludge sample typical microscope image.
Fig. 3 activated sludge sample binary picture.
Fig. 4 active pollution index sample particle.
The mensuration of Fig. 5 active pollution index sample particle Size Distribution.
The conversion of Fig. 6 Pixel Dimensions and national standard long measure.
The extraction of Fig. 7 der Pilz image.
Fig. 8 der Pilz skeletal extraction.
The mensuration of Fig. 9 der Pilz length.
Figure 10 active pollution index Size Distribution.
Figure 11 active sludge der Pilz length distribution.
Figure 12 flco mean diameter and standard deviation thereof are with the change of analyzed amount of images.
The correlationship of Figure 13 TEFL and SVI value.
Figure 14 active sludge inline graphics analysis software interface.
Embodiment
Be below the detailed description of the specific embodiment of the invention:
Step one: configuration active sludge on-line computer image analysis apparatus, as Fig. 1, is formed primarily of sample diluting device 1, peristaltic pump 2, computing machine 3, high-speed camera 4, microscope 5 and sample chamber 6.The effect of sample diluting device is the concentration of dilution primary sample, prevent sample concentration too high, block the sample chamber be arranged on below microscope, also floc particle in sample can be reduced in addition overlapping, cause measuring error, Sample Dilution multiple is 1:9, and activated sludge sample and indoor tap water enter sample diluting device according to 1:9 flow proportional; Sample, after dilution, has peristaltic pump to be transferred to sample chamber, is recycled to sample diluting device as discharging of waste liquid; Sample chamber is placed in below micro objective, it is that the glass cell being 0.4 centimetre by thickness 500 microns, length 1.5 centimetres and width is formed, sample chamber adopts (Ibidi, Germany, μ-Slide I, sequence number 004246) product, when sample flows therethrough, can be taken it by high-speed camera; Microscope is Cai Si ordinary optical microscope, and object lens magnification adopts 50 times; Above microscopical eyepiece, install high-speed camera, video camera shooting frame number is at more than 1000fps (as 2000fps); Be necessary for high-speed camera, because sample is at sample indoor moveable, common low speed video camera can not obtain image clearly; Separately there is one, computing machine, carry out Image Acquisition for controlling high-speed camera and peristaltic pump is controlled automatically, the performance of computing machine must meet the requirement of high-speed camera shooting and later image process, in general need the configuration with cpu2.5G, internal memory 2G and more than hard disk 200G, such as, adopt Dell SIGMATEL STAC92XX C-Major HD desktop computer one.
Step 2: active sludge image processing algorithm is developed, and is mainly divided into two parts, comprises mud floc particle Size Distribution and der Pilz length distribution.
1) mensuration of mud floc particle Size Distribution:
Mud floc particle Size Distribution completes mainly through the following steps:
(1) obtain activated sludge sample image, from the device that step one is built, take active sludge image data by high-speed camera, then intercept still image from image data, obtain as Fig. 2 thus activated sludge sample MIcrosope image;
(2) utilize MATLAB image analysis tool case that figure 2 is converted into binary picture (Fig. 3).Transform standard be gray scale is greater than a certain threshold value pixel as ' object ', gray scale is less than the pixel of this threshold value as image background, the selected MATLAB of the having function of this threshold values is chosen automatically;
(3) carry out process of making an uproar to Fig. 3, remove the impurity in image, obtain active pollution index particle Fig. 4, the object being less than picture size 1% is deleted as noise;
(4) active pollution index Size Distribution measures, and by the pixel quantity of flco single in counting diagram 4, just can measure the size of flco, the unit of the flco size that this pacing is fixed is pixel, and the size of demarcating after measuring is shown in Fig. 5;
(5) conversion of Pixel Dimensions and international standard long measure, utilizes micro-scale of known length, measures its length in pixels, thus be converted into international standard length, and as shown in Figure 6, the length of 100 microns, corresponding to 301 pixels, scale merit is 3.01 pixels/micron.
2) mensuration of der Pilz length distribution:
(1) der Pilz is extracted, and is subtracted each other by Fig. 3 and Fig. 4, just can obtain the binary picture (Fig. 7) of der Pilz and some granule foreigns;
(2) Fig. 7 is carried out noise reduction and skeleton is extracted to der Pilz, obtain the der Pilz skeleton image (Fig. 8) of length direction list pixel;
(3) by the single der Pilz pixel of counting, measure hyphomycetic length in pixels (Fig. 9), and change into international standard length.
Figure 10 and Figure 11 obtains through above pattern analysis algorithm, the floc particle size of different settling property active sludge and der Pilz length distribution.
Step 3: determine the required active sludge amount of images analyzed, in order to make the data of graphical analysis have representative and reliability widely, preventing the contingency once analyzed, tackling same water sample and carry out repeatedly replication analysis.Active pollution index is complicated three-dimensional structure, it in microscope camera lens towards the size that can affect measurement.The present invention determines required minimum analysis times by observation active pollution index mean diameter and standard deviation thereof with the change of the quantity of institute's analysis chart picture.Amount of images required when standard deviation tends towards stability is minimum amount of images requirement.As seen from Figure 12, after analyzing 30 images, standard deviation is reduced to less than 10% of mean value, and when analyzing 50 images, standard deviation tends towards stability.
Step 4: by measuring the settling property (with sludge volume index SVI) of different activities mud sample and mud floc particle Size Distribution thereof and der Pilz length distribution, find the association between settling property and mud morphological image feature, to be analyzed by inline graphics, draw active sludge morphological feature, just can its effect of settling of early warning.Selection SVI value is the active sludge of 76,84,86,90,95,102, the expression settling property that SVI value is lower is good, by measuring their particle size distribution and der Pilz length distribution, can see that der Pilz length distribution associates with SVI closely, the sample (76 and 84) that two SVI values are lower, in comparatively sarconeme shape bacterium length of interval (being less than 60 microns) distribute often.It is more that the sample (90,95 and 102) that SVI value is larger (60-955 micron) in longer der Pilz length of interval distributes.
Calculate der Pilz total length (TEFL) and SVI value between related coefficient, result as shown in figure 13, SVI value and TEFL linearly positive correlation.SVI value, from 76 to 102, creates less change, and reaction is on TEFL, is but the larger change from 680 microns to 2600 microns.The difference of activated sludge settling property, is reflected enlargedly by TEFL index, illustrates that the TEFL index of image procossing can reflect sludge settling property more delicately than traditional SVI index.Image procossing is also one measuring method fast simultaneously, is easy to realize real-time monitoring.
Step 5: by the computing machine in step one to peristaltic pump and the control to high-speed camera Image Acquisition, integrate with the image analysis algorithm of the mud floc particle Size Distribution in step 2 and der Pilz length distribution, utilize MATLAB gui tool, exploitation integrated image analytic function software; And and the activated sludge settling property in step 4 is associated, and carries out early warning to active sludge effect of settling.Software users interactive interface is shown in Figure 14.
Claims (2)
1. the graphical analysis of active sludge on-line computer and a method for early warning, comprises the following steps:
Step one: utilization is arranged on the image information high-speed camera on microscope obtaining sample, sends computing machine to;
Step 2: computing machine carries out image procossing according to the morphological image obtained, analyzes flco Size Distribution and the der Pilz length distribution of active sludge,
Step 3: observe the change with the quantity of institute's analysis chart picture of active pollution index mean diameter and standard deviation thereof, determine the required active sludge amount of images analyzed, graphical analysis number when flco mean diameter and standard deviation thereof are stablized is required amount of images;
Step 4: by measuring the settling property of different activities mud sample and mud floc particle Size Distribution thereof and der Pilz length distribution, find the association between settling property and mud morphological image feature; Measure the linear relationship between der Pilz total length and sludge settling property;
Step 5: setting settling property early warning value, computing machine processes according to the image obtained, analyzes, and is associated with the activated sludge settling property in step 4, carries out early warning to active sludge effect of settling.
2. method according to claim 1, is characterized in that, comprises mud floc particle Size Distribution and der Pilz length distribution in step 2 to active sludge image procossing; Specific as follows:
1) mensuration of mud floc particle Size Distribution:
Mud floc particle Size Distribution completes mainly through the following steps:
(1) from the activated sludge sample image obtained, intercept still image, obtain activated sludge sample MIcrosope image;
(2) MIcrosope image is converted into binary picture;
Transform standard be gray scale is greater than a certain threshold value pixel as ' object ', gray scale is less than the pixel of this threshold value as image background, the size of threshold values is generated automatically by image analysis algorithm;
(3) noise reduction process is carried out to binary picture, remove the impurity in image, obtain active pollution index particle figure;
(4) active pollution index Size Distribution measures, and by the pixel quantity of single flco in counting floc particle figure, just can measure the size of flco, the unit of the flco size that this pacing is fixed is pixel, demarcates size after mensuration;
(5) conversion of Pixel Dimensions and international standard long measure: the micro-scale utilizing known length, measures its length in pixels, thus is converted into international standard length;
2) mensuration of der Pilz length distribution:
(1) der Pilz is extracted, and binary picture and floc particle figure is subtracted each other, and just can obtain the binary picture of der Pilz and some granule foreigns;
(2) binary picture of der Pilz and some granule foreigns is carried out noise reduction and extracts skeleton to der Pilz, obtain the der Pilz skeleton image of length direction list pixel;
(3) by the single der Pilz pixel of counting, measure hyphomycetic length in pixels, and change into international standard length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310713069.4A CN103630473B (en) | 2013-12-20 | 2013-12-20 | Active sludge on-line computer graphical analysis early warning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310713069.4A CN103630473B (en) | 2013-12-20 | 2013-12-20 | Active sludge on-line computer graphical analysis early warning system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103630473A CN103630473A (en) | 2014-03-12 |
| CN103630473B true CN103630473B (en) | 2015-08-05 |
Family
ID=50211750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310713069.4A Expired - Fee Related CN103630473B (en) | 2013-12-20 | 2013-12-20 | Active sludge on-line computer graphical analysis early warning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103630473B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104914213B (en) * | 2015-05-13 | 2016-10-19 | 西安建筑科技大学 | A kind of method of early warning activated sludge filamentary discharges |
| CN105223115A (en) * | 2015-09-29 | 2016-01-06 | 苏州工业园区清源华衍水务有限公司 | A kind of sludge settling ratio observation device and apply the observation procedure of this device |
| CN105261027B (en) * | 2015-10-30 | 2019-01-01 | 北京金控数据技术股份有限公司 | Sludge settling ratio detection method and system based on image procossing |
| CN106814068A (en) * | 2017-01-24 | 2017-06-09 | 英普（北京）环境科技有限公司 | The rapid assay device and method of monitoring sewage treatment plant running status |
| CN107179265A (en) * | 2017-07-06 | 2017-09-19 | 中国矿业大学(北京) | Flco dynamic feature coefficient extraction system and method during Coagulation of Coal Slime Water |
| CN109459354A (en) * | 2019-01-20 | 2019-03-12 | 华东交通大学 | A kind of workshop dust fall amount automatic detection device and method based on machine vision |
| CN110251078A (en) * | 2019-01-30 | 2019-09-20 | 北京大学第三医院（北京大学第三临床医学院） | Microscopical imaging method, imaging system and microscope |
| CN110118771A (en) * | 2019-03-29 | 2019-08-13 | 亳州学院 | A kind of intelligent microscopic examination device and microscopy method for active sludge microorganism |
| CN110160919A (en) * | 2019-07-04 | 2019-08-23 | 中国科学院青岛生物能源与过程研究所 | A kind of on-line measurement device of grain graininess and pattern |
| CN110697874B (en) * | 2019-09-27 | 2021-12-17 | 中国葛洲坝集团水务运营有限公司 | Activated sludge performance index on-line monitoring method |
| CN110702458B (en) * | 2019-10-31 | 2022-02-01 | 黑龙江大学 | Online continuous sampling system of activated sludge |
| CN111707587A (en) * | 2020-06-04 | 2020-09-25 | 核工业北京地质研究院 | Particle size statistical method |
| CN111796552B (en) * | 2020-06-16 | 2021-10-22 | 浙江大学 | Automatic analysis device and method for sludge sedimentation characteristics based on MATLAB image conversion |
| CN111912752A (en) * | 2020-09-07 | 2020-11-10 | 上海易清智觉自动化科技有限公司 | Flocculation detection device and method and sewage treatment system |
| CN116008139B (en) * | 2023-03-27 | 2023-06-23 | 华中科技大学 | Evaluation method and evaluation system for fractal dimension of particles in dispersion system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1793839A (en) * | 2005-12-12 | 2006-06-28 | 苏州科技学院 | Automatic monitoring device of active sludge multiparameter |
| CN1996023A (en) * | 2006-12-22 | 2007-07-11 | 清华大学 | Moving type quick automatic monitoring system for water quality |
-
2013
- 2013-12-20 CN CN201310713069.4A patent/CN103630473B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN103630473A (en) | 2014-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103630473B (en) | Active sludge on-line computer graphical analysis early warning system and method | |
| Amaral et al. | Activated sludge monitoring of a wastewater treatment plant using image analysis and partial least squares regression | |
| CN103471991B (en) | Activated sludge characteristic determination method based on zoogloea microscopical image analysis | |
| CN108507625A (en) | A kind of water body planktonic organism intellectual monitoring platform and method for integrating Internet of Things | |
| CN103708592A (en) | Novel water treatment method based on machine vision and device thereof | |
| CN103278431A (en) | On-line monitoring and analyzing method of lubrication oil wear particles based on video acquisition | |
| CN109919012A (en) | A kind of indicative microorganism image-recognizing method of sewage treatment based on convolutional neural networks | |
| CN109967143B (en) | Cell size detection method based on micro-fluidic microscope system | |
| Mesquita et al. | Correlation between sludge settling ability and image analysis information using partial least squares | |
| CN116665137B (en) | Livestock breeding wastewater treatment method based on machine vision | |
| CN101786675A (en) | Device and method for separating multi-parameter wastewater sources | |
| Shanono et al. | Image processing techniques applicable to wastewater quality detection: towards a hygienic environment | |
| Milferstedt et al. | Analyzing characteristic length scales in biofilm structures | |
| CN101231229A (en) | Non-dyeing automatic counting method for liquid bacterium-containing quantity | |
| CN115950886A (en) | Floc state monitoring method based on textural features | |
| CN112767362B (en) | Activated sludge phase contrast microscopic image-based sludge expansion prediction method | |
| Nisar et al. | Application of imaging techniques for monitoring flocs in activated sludge | |
| Zhao et al. | Segmentation of Activated Sludge Phase Contrast Microscopy Images Using U-Net Deep Learning Model. | |
| Li et al. | A recognition method of urine cast based on deep learning | |
| CN110339938A (en) | A kind of digitlization coal separation system | |
| Cross et al. | Image analysis of low magnification images of fine needle aspirates of the breast produces useful discrimination between benign and malignant cases | |
| Yong et al. | An approach for the segmentation and quantification of activated sludge floc blobs | |
| Zhao et al. | Distributed online sludge volume index prediction model via image analysis and federated broad stochastic configuration network | |
| Huo et al. | Size measurement and prediction for L-glutamic acid crystal growth during stirred crystallization based on imaging analysis | |
| Peng et al. | The coagulation-precipitation turbidity prediction model for precision drug delivery system based on deep learning and machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150805 Termination date: 20171220 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |