CN113307435B - Dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system and method - Google Patents
Dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system and method Download PDFInfo
- Publication number
- CN113307435B CN113307435B CN202110572622.1A CN202110572622A CN113307435B CN 113307435 B CN113307435 B CN 113307435B CN 202110572622 A CN202110572622 A CN 202110572622A CN 113307435 B CN113307435 B CN 113307435B
- Authority
- CN
- China
- Prior art keywords
- materials
- centrifugal separator
- information
- cyclone
- outlet
- 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
- 238000002425 crystallisation Methods 0.000 title claims abstract description 82
- 230000008025 crystallization Effects 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 72
- 239000007788 liquid Substances 0.000 title claims abstract description 55
- 238000000926 separation method Methods 0.000 title claims abstract description 52
- 238000000513 principal component analysis Methods 0.000 title description 71
- 239000000463 material Substances 0.000 claims abstract description 261
- 230000008569 process Effects 0.000 claims abstract description 54
- 238000012544 monitoring process Methods 0.000 claims abstract description 46
- 238000001035 drying Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000001704 evaporation Methods 0.000 claims description 20
- 230000008020 evaporation Effects 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 230000010365 information processing Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000012141 concentrate Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 abstract description 9
- 230000008859 change Effects 0.000 abstract description 4
- 230000003044 adaptive effect Effects 0.000 abstract description 3
- 239000011159 matrix material Substances 0.000 description 22
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000011217 control strategy Methods 0.000 description 3
- 239000010842 industrial wastewater Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000007791 liquid phase Substances 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000012047 saturated solution Substances 0.000 description 1
- 239000007790 solid phase Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/02—Treatment of water, waste water, or sewage by heating
- C02F1/04—Treatment of water, waste water, or sewage by heating by distillation or evaporation
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/38—Treatment of water, waste water, or sewage by centrifugal separation
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2303/00—Specific treatment goals
- C02F2303/14—Maintenance of water treatment installations
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Hydrology & Water Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Organic Chemistry (AREA)
- Analytical Chemistry (AREA)
- Mechanical Engineering (AREA)
- Centrifugal Separators (AREA)
- Cyclones (AREA)
Abstract
The invention provides a solid-liquid separation system and a solid-liquid separation method based on dynamic PCA evaporative crystallization.A controller effectively controls and monitors a solid-liquid separation unit, an image acquisition module respectively acquires material images of a cyclone and a centrifugal separator, and the basic information of the materials of the cyclone and the centrifugal separator can analyze the change of the basic information and the image information of the materials on a time sequence in a data processing module through a dynamic PCA model, so that the output result is fit with the actual situation, the monitoring and control are more accurate and adaptive, unqualified materials can be returned to evaporative crystallization process equipment, the materials with low solid content are prevented from entering drying equipment and agglomerating, the continuous and stable operation of the evaporative crystallization process is ensured, and the operation stability of the evaporative crystallization process is improved.
Description
Technical Field
The invention relates to the field of solid-liquid separation in an evaporative crystallization process, in particular to an evaporative crystallization solid-liquid separation system and method based on dynamic PCA.
Background
One key point in 'zero discharge' of mine water and coal chemical wastewater and resource engineering is the solid-liquid separation process of the saturated solution of the crystallized salt after evaporation and crystallization. Whether this process is unobstructed directly influences the steady operation of whole engineering to and front end reuse water volume and treatment water yield.
At the present stage, zero discharge of mine water and industrial wastewater and resource engineering evaporative crystallization processes often occur, and solid content of materials entering a centrifugal separator is too thin, so that the centrifugal separator cannot separate solid and liquid phases, subsequent drying equipment is agglomerated, the whole crystallization process is forced to stop, and the drying equipment is cleaned. The continuous and stable operation of the whole 'zero emission' and resource engineering is seriously influenced, and the workload is increased. In the 'zero discharge' project of partial mine water and industrial wastewater, the scale of a front cyclone entering the centrifugal separator is enlarged, and the solid content entering the centrifugal separator is ensured, so that the long-period stable operation of the centrifugal separator is ensured. However, the technical route can cause the pipeline between the cyclone and the centrifugal separator to be blocked, the pipeline needs to be cleaned frequently, the whole zero emission and the stable operation of a recycling system are also not facilitated, and the problem of solid-liquid separation in the evaporative crystallization process is not solved fundamentally.
Furthermore, the conventional PCA model does not take into account the variation of variables in time series, resulting in partial information loss.
Disclosure of Invention
The invention provides a dynamic PCA-based evaporative crystallization solid-liquid separation system and method, aiming at solving the problems that the existing mine water and industrial wastewater zero discharge and evaporative crystallization process in the resource technology can not effectively separate solid and liquid, and the conventional PCA model does not consider the change of variables in a time sequence, thereby causing partial information loss.
The invention is realized by the following technical scheme:
a solid-liquid separation system based on dynamic PCA evaporative crystallization comprises a controller and a solid-liquid separation unit;
the solid-liquid separation unit comprises evaporation crystallization process equipment, a cyclone, a centrifugal separator and drying equipment which are arranged from top to bottom; wherein, the input end of the cyclone is also connected with a material device to be separated; the output ends of the cyclone and the centrifugal separator are respectively connected with the input end of the evaporative crystallization process equipment;
the input end of the controller is respectively connected with the image acquisition module and the signal input module, and the output end of the controller is respectively connected with the image preprocessing module and the data processing module; the input end of the image acquisition module is respectively connected with the first high-definition camera and the second high-definition camera; the input end of the signal input module is respectively connected with the first flow meter, the first TDS analysis meter, the first temperature meter, the first pressure meter, the second flow meter, the second TDS analysis meter, the second temperature meter and the second pressure meter;
first high definition digtal camera assembly is on the swirler, and the assembly of second high definition digtal camera is in centrifuge's material export, first flow instrument, first TDS analytical instrument, first temperature instrument, first pressure instrument set up the exit end at the material device that treats to separate, second flow instrument, second TDS analytical instrument, second temperature instrument and second pressure instrument set up the entrance point at centrifuge.
Preferably, a human-computer interaction module is arranged on the controller, and the input end of the human-computer interaction module is connected with the output end of the controller and used for displaying images acquired by the first high-definition camera and the second high-definition camera and displaying signal information of the first flow meter, the first TDS analysis meter, the first temperature meter, the first pressure meter, the second flow meter, the second TDS analysis meter, the second temperature meter, the second pressure meter, the image preprocessing module and the data processing module.
Preferably, the output end of the controller is connected with a monitor through a monitoring module, and the monitors are respectively assembled on the material outlet output ends of the cyclone and the centrifugal separator.
Preferably, the output end of the cyclone is provided with an automatic valve for the materials with unqualified cyclone outlets and an automatic valve for the materials with qualified cyclone outlets; the automatic valve for the unqualified materials at the outlet of the cyclone is connected with evaporative crystallization process equipment; and the automatic valve for qualified materials at the outlet of the cyclone is connected with the input end of the centrifugal separator.
Preferably, the output end of the centrifugal separator is provided with an automatic valve for qualified materials at the outlet of the centrifugal separator and an automatic valve for unqualified materials at the outlet of the centrifugal separator; the automatic valve of the unqualified material at the outlet of the centrifugal separator is connected with evaporative crystallization process equipment; the automatic valve for qualified materials at the outlet of the centrifugal separator is connected with drying equipment.
A solid-liquid separation method based on dynamic PCA evaporative crystallization is based on the solid-liquid separation system based on dynamic PCA evaporative crystallization and comprises the following steps,
step 5, acquiring basic information of materials at an inlet of the centrifugal separator and image information of the materials at an outlet of the centrifugal separator, and performing noise reduction processing on the acquired image information of the materials through an image preprocessing technology;
step 6, constructing dynamic information processing on the basic material information at the inlet of the centrifugal separator and the de-noised image information at the outlet of the centrifugal separator to obtain dynamic information;
the dynamic information is obtained by performing entropy operation on the basic information and the image information of the material.
Preferably, the image pre-processing techniques include gaussian filtering, mean filtering, median filtering, minimum mean square error filtering, gabor filtering.
Preferably, the materials in the cyclone and at the outlet of the centrifugal separator are screened by adopting a dynamic PCA model, and the specific method is as follows:
establishing a first PCA model and a second PCA model
Inputting basic material information of the material device to be separated, image information and dynamic information of materials in the cyclone after noise reduction treatment into a first PCA model, and outputting a monitoring value T by the first PCA model 1 2 Therein monitorMeasured value T 1 2 Corresponding control limit value T 1L 2 ;
When monitoring the value T 1 2 Less than control limit T 1L 2 When the material is in use, the material enters a centrifugal separator;
when monitoring value T 1 2 Greater than the control limit T 1L 2 When the material is cooled, the material returns to the evaporation crystallization process equipment;
inputting the basic information of the centrifuge inlet material, the noise-reduced centrifuge outlet material image information and the dynamic information into a second PCA model, and outputting a monitoring value T by the second PCA model 2 2 Wherein a value T is monitored 2 2 Corresponding control limit value T 2L 2 ;
When monitoring value T 2 2 Value less than control limit T 2L 2 When the material is dried, the material enters drying equipment;
when monitoring value T 2 2 Value greater than control limit T 2L 2 When the material is used, the material returns to the evaporation crystallization process equipment.
Further, the first PCA model and the second PCA model both select principal elements with principal element contribution rate larger than 85% for modeling.
Further, a limit value T is controlled 1L 2 The method is obtained by training a first PCA model by utilizing the basic information of separable materials, the material image information and the dynamic information in a cyclone by the same evaporative crystallization process;
control limit value T 2L 2 The method is obtained by training a second PCA model by utilizing basic information of inlet materials of the centrifugal separator, image information of outlet materials of the centrifugal separator and dynamic information which can be separated by the same evaporative crystallization process.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention provides a solid-liquid separation system based on dynamic PCA evaporative crystallization.A controller effectively controls and monitors a solid-liquid separation unit, an image acquisition module respectively acquires material images of a cyclone and a centrifugal separator, and the basic information of the materials of the cyclone and the centrifugal separator can analyze the change of the basic information and the image information of the materials on a time sequence in a data processing module through a dynamic PCA model, so that the output result is fit with the actual situation, the monitoring and control are more accurate and adaptive, unqualified materials can be returned to evaporative crystallization process equipment, the materials with lower solid content are prevented from entering drying equipment and agglomerating, the continuous and stable operation of the evaporative crystallization process is ensured, and the operation stability of the evaporative crystallization process is improved.
Furthermore, a human-computer interaction module is arranged on the controller, so that an operator can conveniently and effectively observe the image information condition and the material basic condition in the equipment during solid-liquid separation operation.
Furthermore, the output end of the controller is connected with the monitor through the monitoring module, and the output end of the controller is connected with the monitor through the monitoring value T according to the materials to be separated 1 2 And a control limit T 1L 2 Comparing to obtain a control strategy of the material at the outlet of the cyclone; by monitoring value T according to material at the outlet of the centrifugal separator 2 2 And a control limit T 2L 2 And by contrast, a control strategy of the materials at the outlet of the centrifugal separator is obtained, and the material screening efficiency is improved.
Furthermore, the output end of the cyclone is provided with an automatic valve for the materials with unqualified outlet of the cyclone and an automatic valve for the materials with qualified outlet of the cyclone, and the automatic valve for the materials with unqualified outlet of the cyclone is connected with evaporative crystallization process equipment to ensure the continuous and stable operation of the evaporative crystallization process; the automatic valve for qualified materials at the outlet of the cyclone is connected with the input end of the centrifugal separator, so that the separation operation between the cyclone and the centrifugal separator is facilitated.
Furthermore, the output end of the centrifugal separator is provided with an automatic valve for qualified materials at the outlet of the centrifugal separator and an automatic valve for unqualified materials at the outlet of the centrifugal separator, and the automatic valve for unqualified materials at the outlet of the centrifugal separator is connected with evaporative crystallization process equipment to ensure the continuous and stable operation of the evaporative crystallization process; the automatic valve for qualified materials at the outlet of the centrifugal separator is connected with the drying equipment, so that the separation operation between the centrifugal separator and the drying equipment is facilitated.
A solid-liquid separation method based on dynamic PCA evaporative crystallization is characterized in that dynamic changes of entropy variables capturing material original information and image information are added in modeling variables of a PCA model, so that a monitoring control system is more suitable for actual operation. In addition, the cloud computing technology is adopted, so that the reliability and the compatibility of data acquisition are improved, and the computing cost is reduced.
Drawings
FIG. 1 is a schematic structural diagram of a dynamic PCA-based evaporative crystallization solid-liquid separation system according to the present invention;
FIG. 2 is a schematic flow chart of a dynamic PCA-based evaporative crystallization solid-liquid separation method in the present invention;
fig. 3 is a schematic structural diagram of a controller according to the present invention.
In the figure: 1-a swirler; 2-a first high definition camera; 3-an automatic valve for unqualified materials at the outlet of the cyclone; 4-automatic valve for qualified materials at the outlet of the cyclone; 5-centrifugal separator; 6-a second high-definition camera; 7-automatic valve for qualified materials at the outlet of the centrifugal separator; 8-automatic valve for unqualified material at the outlet of the centrifugal separator; 9-a first flow meter; 10-a first TDS analytical meter; 11-a first temperature meter; 12-a first pressure gauge; 13-a second flow meter; 14-a second TDS analytical meter; 15-a second temperature meter; 16-a second pressure gauge; 17-evaporative crystallization process equipment; 18-a drying device; 19-a material device to be separated; and 20, a controller.
Detailed Description
The present invention will now be described in further detail with reference to specific examples, which are intended to be illustrative, but not limiting, of the invention.
The invention provides a dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system, which comprises a controller 20 and a solid-liquid separation unit, as shown in figure 1;
the solid-liquid separation unit comprises evaporation crystallization process equipment 17, a cyclone 1, a centrifugal separator 5 and drying equipment 18 which are arranged from top to bottom; wherein, the input end of the cyclone 1 is also connected with a material device 19 to be separated; the output ends of the cyclone 1 and the centrifugal separator 5 are respectively connected with the input end of the evaporative crystallization process equipment 17;
as shown in fig. 3, the input end of the controller 20 is connected to the image acquisition module and the signal input module, respectively, and the output end of the controller 20 is connected to the image preprocessing module and the data processing module, respectively; the input end of the image acquisition module is respectively connected with the first high-definition camera 2 and the second high-definition camera 6; the input end of the signal input module is respectively connected with a first flow meter 9, a first TDS analysis meter 10, a first temperature meter 11, a first pressure meter 12, a second flow meter 13, a second TDS analysis meter 14, a second temperature meter 15 and a second pressure meter 16;
the first high-definition camera 2 is assembled on the cyclone 1, the second high-definition camera 6 is assembled at the material outlet of the centrifugal separator 5, the first flow meter 9, the first TDS analysis meter 10, the first temperature meter 11 and the first pressure meter 12 are arranged at the outlet end of the material device 19 to be separated, and the second flow meter 13, the second TDS analysis meter 14, the second temperature meter 15 and the second pressure meter 16 are arranged at the inlet end of the centrifugal separator 5.
The controller 20 is provided with a human-computer interaction module, the input end of the human-computer interaction module is connected with the output end of the controller and used for displaying images acquired by the first high-definition camera 2 and the second high-definition camera 6 and displaying signal information of the first flow instrument 9, the first TDS analysis instrument 10, the first temperature instrument 11, the first pressure instrument 12, the second flow instrument 13, the second TDS analysis instrument 14, the second temperature instrument 15, the second pressure instrument 16, the image preprocessing module and the data processing module.
The output of the controller 20 is connected via a monitoring module to monitors which are fitted on the material outlet outputs of the cyclone 1 and the centrifuge 5, respectively.
The output end of the cyclone 1 is provided with an automatic material valve 3 with an unqualified cyclone outlet and an automatic material valve 4 with a qualified cyclone outlet; the automatic valve 3 for the unqualified material at the outlet of the cyclone is connected with evaporative crystallization process equipment 17; and the qualified material automatic valve 4 at the outlet of the cyclone is connected with the input end of a centrifugal separator 5.
The output end of the centrifugal separator is provided with an automatic valve 7 for qualified materials at the outlet of the centrifugal separator and an automatic valve 8 for unqualified materials at the outlet of the centrifugal separator; the automatic valve 8 for unqualified materials at the outlet of the centrifugal separator is connected with evaporative crystallization process equipment 17; and the automatic valve 7 for qualified materials at the outlet of the centrifugal separator is connected with a drying device 18.
Referring to FIG. 2, a solid-liquid separation method based on dynamic PCA evaporative crystallization, based on the above-mentioned solid-liquid separation system based on dynamic PCA evaporative crystallization, comprises the following steps,
step 34, screening the basic material information of the material device 19 to be separated, the preprocessed material image information and dynamic information of the cyclone 1 through data processing, enabling the normal solid-liquid separable material to enter a centrifugal separator 5 to execute step 4, returning the solid-liquid inseparable material to the evaporative crystallization process equipment 10 to evaporate and concentrate, and then executing step 1 again;
step 45, acquiring basic information of the materials at the inlet of the centrifugal separator 5 and image information of the materials at the outlet of the centrifugal separator 5, and performing noise reduction pretreatment on the acquired image information of the materials by using an image pretreatment technology to obtain dynamic information;
step 6, constructing dynamic information processing on the basic information of the material at the inlet of the centrifugal separator 5 and the image information of the outlet of the centrifugal separator 5 after denoising to obtain dynamic information;
step 57, screening the materials at the outlet of the centrifugal separator 5 by data processing on the basic information of the materials at the inlet of the centrifugal separator 5, the image information and the dynamic information of the materials at the outlet of the centrifugal separator after the pre-denoising treatment, feeding the materials with normal solid-liquid separation into the drying equipment 18, and finishing the separation work; returning the solid-liquid inseparable material to the evaporative crystallization process equipment 10 for evaporative concentration, and then executing the step 1 again;
the dynamic information is obtained by performing entropy operation on the basic information and the image information of the material to be separated.
Image preprocessing techniques include gaussian filtering, mean filtering, median filtering, minimum mean square error filtering, gabor filtering.
The materials in the cyclone 1 and at the outlet of the centrifugal separator 5 are screened by adopting a dynamic PCA model, and the specific method comprises the following steps:
establishing a first PCA model and a second PCA model
Inputting the basic material information of the material device 19 to be separated, the image information of the materials in the cyclone after noise reduction and the dynamic information into a first PCA model, and outputting a monitoring value T by the first PCA model 1 2 Wherein a value T is monitored 1 2 Corresponding control limit value T 1L 2 ;
When monitoring value T 1 2 Less than control limit T 1L 2 When the material is in use, the material enters a centrifugal separator 5;
when monitoring value T 1 2 Greater than the control limit T 1L 2 When the material is fed back to the evaporative crystallization process equipment 17;
inputting the basic information of the inlet material of the centrifugal separator 5, the image information and the dynamic information of the outlet material of the centrifugal separator 5 after noise reduction treatment into a second PCA model, and outputting a monitoring value T by the second PCA model 2 2 Wherein a value T is monitored 2 2 Corresponding control limit value T 2L 2 ;
When monitoring value T 2 2 Less than a second control limit T 2L 2 While the material is entering the drying apparatus 18;
when monitoring value T 2 2 Greater than a second control limit T 2L 2 At this point, the material is returned to the evaporative crystallization process equipment 17.
And the first PCA model and the second PCA model are both modeled by selecting principal elements with principal element contribution rate more than 85%.
ControllingLimit value T 1L 2 The method is obtained by training a first PCA model by utilizing the basic information of separable materials, the material image information and the dynamic information in a cyclone by the same evaporative crystallization process;
control limit value T 2L 2 The method is obtained by training a second PCA model by utilizing basic information of inlet materials of the centrifugal separator, image information of outlet materials of the centrifugal separator and dynamic information which can be separated by the same evaporative crystallization process.
Wherein the material basic information includes Total Dissolved Solids (TDS), temperature, pressure and volume flow rate of the material. The material image information in the cyclone 1 is shot and acquired through the first high-definition camera 2. The image information of the material at the outlet of the centrifugal separator 5 is shot by the second high-definition camera 6.
Carrying out evaporative crystallization solid-liquid separation by establishing an image pretreatment model, an entropy change construction model, a first PCA model and a second PCA model based on a dynamic PCA evaporative crystallization solid-liquid separation method;
the control limit value T can be updated by separating basic information, image information and dynamic information of materials 1L 2 And a control limit value T 2L 2 The specific method is that the basic information, the image information and the dynamic information of the latest separable material are substituted for the basic information, the image information and the dynamic information of the separable material with longer time in the original model to obtain the updated control limit value T 1L 2 And a control limit value T 2L 2 ;
The invention relates to an image acquisition module and a signal input module: obtaining basic information of materials to be separated, basic information of inlet materials of the centrifugal separator 5, image information of materials in the cyclone 1, image information and dynamic information of outlet materials of the centrifugal separator 5.
A data processing module: inputting basic information of separable materials, preprocessed image information and dynamic information of materials in the cyclone into a first PCA model to output a control limit value T 1L 2 . Basic information of the inlet separable material of the centrifugal separator, image information and dynamic information of the outlet material of the centrifugal separator after pretreatmentInput to the second PCA model to output a control limit T 2L 2 。
A monitoring module: inputting basic information of materials to be separated, material image information and dynamic information in a cyclone into a first PCA model, and outputting a monitoring value T by the first PCA model 1 2 If the monitored value T of the material to be separated 1 2 Does not exceed the control limit T 1L 2 And (4) feeding the material at the outlet of the cyclone into a centrifugal separator, and returning the material at the outlet of the cyclone to the front-end evaporation crystallization process. Inputting the centrifuge inlet material, centrifuge outlet material image information and dynamic information into a second PCA model, and outputting a monitoring value T by the second PCA model 2 2 If the monitoring value T of the material at the outlet of the centrifugal separator 2 2 Does not exceed the control limit T 2L 2 Then sending to a drying device; otherwise, returning to the evaporation crystallization process.
Examples
The embodiment provides a solid-liquid separation method based on dynamic PCA evaporative crystallization, which comprises the following specific steps:
s101: basic information of x sets of separable materials including dissolved total solids, temperature, pressure and volumetric flow rate of the materials and material image information within the cyclone are obtained. The material image information in the cyclone is shot by a high-definition camera;
s102: the image information is subjected to noise reduction processing by a preprocessing technology, and a X images are output m×n Matrices, the image pre-processing techniques including, but not limited to, gaussian filtering, mean filtering, median filtering, minimum mean square error filtering, gabor filtering;
s103: a pretreated X are treated m×n Conversion of matrix to X a×mn The matrix is combined with the basic information of the material to form X a×(mn+4) And (4) matrix. The basic information of the separable materials and the image information of the materials in the cyclone are uploaded once every 5 minutes, and the information is uploaded 12 times in 1 hour. The 12 times of information uploaded for 1 hour, namely: x 12×(mn+4) Performing entropy operation on the matrix to obtain dynamic information X a×(mn+4) A matrix;
the concrete formula is as follows:
k is the length of the observation time sequence and takes a value of 12; p is a radical of i As observed information at a single time.
S104: basic information of separable materials, image information and dynamic information of materials in the denoised cyclone are combined to generate X a×2(mn+4) And (4) matrix. To the X a×2(mn+4) And (3) carrying out standardization treatment on the matrix:
the specific formula is as follows:
wherein x is i Is the original value of the variable, u i Is the mean value, σ, of the variable i Is the standard deviation of the variables.
Solving the covariance matrix:
where cov (X) is the covariance matrix of X.
Solving the eigenvalues of the covariance matrix and arranging them from large to small:
cov(X)p i =λ i p i ;i=1,2,……,2(mn+4);
λ 1 ≥λ 2 ≥Λ≥λ 2(mn+4) ;
wherein λ is i Is a characteristic value, p i Is a characteristic vector, Λ is a characteristic value matrix, and P is a load matrix.
And selecting principal elements with principal element contribution rate more than 85% to construct a PCA model.
Wherein k is the number of the principal elements with the principal element contribution rate of more than 85 percent.
The original matrix X after principal component transformation can be represented as:
X=t 1 p 1 T +t 2 p 2 T +……+t k p k T +E;
wherein, t i Is a score vector, E is a residual matrix;
generating a control limit T 1L 2 :
Wherein, a is the test level and takes the value of 0.95 k,n-1,a To examine the critical value of F distribution under the conditions of level a, degree of freedom k, n-1.
S105: and acquiring the basic information of the material to be separated and the image information of the material in the cyclone in real time, wherein the basic information of the separable material comprises the total dissolved solids, the temperature, the pressure and the volume flow of the material. The material image information in the cyclone is obtained by shooting through a high-definition camera;
s106: the image information is subjected to noise reduction processing by a preprocessing technology, and Y is output m×n A matrix, wherein the image preprocessing technology is consistent with the preprocessing technology adopted by the training data;
s107: pre-treated Y m×n Conversion of matrix into Y 1×mn The matrix is combined with the basic information of the materials to form Y a×(mn+4) And (4) matrix. The basic information of the separable materials and the image information of the materials in the cyclone are uploaded once every 5 minutes, and the information is uploaded 12 times in 1 hour. Merging the sampled real-time point information and the previous 11 pieces of information into Y 12×(mn+4) Entropy of matrixCalculating to obtain dynamic information Y 1×(mn+4) A matrix;
s108: the basic information of the material to be separated, the image information and the dynamic information of the material in the cyclone after the noise removal are combined to generate Y 1×2(mn+4) And (4) matrix. For the Y 1×2(mn+4) And (3) carrying out standardization treatment on the matrix:
wherein, y i For the original value of the variable to be measured, u Yi To train the mean, σ, of the variables Yi Standard deviation of the training variables.
S109: and generating a score vector t of the information to be separated according to the load matrix P.
S110: generating a monitoring value T of the material to be separated 1 2 :
T 1 2 =tλ -1 t T =YPλ -1 P T Y T ;
S111: comparing the monitored values T 1 2 And a control limit value T 1L 2 . The monitoring value T 1 2 < control Limit T 1L 2 And the material to be separated enters a subsequent centrifugal separator, otherwise, the material returns to the front-end evaporation crystallization process.
S112: the calculation process of the second PCA model is the same as S101-S111, which is not described herein.
According to the technical scheme, the first PCA model outputs the control limit value T 1L 2 Monitoring value T of material to be separated 1 2 Less than control limit T 1L 2 When the materials to be separated can be continuously separated, otherwise, the materials can not be separated and return to the front end. Second PCA model output control Limit T 2L 2 Monitoring value T of material at outlet of centrifugal separator 2 2 Less than control limit T 2L 2 When the centrifugal separator is used, the materials at the outlet of the centrifugal separator can be continuously separated, otherwise, the materials can not be separated, and the materials are returned to the frontAnd (4) an end. At the same time, the limit value T is controlled 1L 2 And a control limit value T 2L 2 The information of the latest separable materials can be updated, the materials are attached to the actual situation, so that the monitoring and the control are more accurate and adaptive, and the stable operation of the evaporative crystallization process is ensured.
In the controller of the present invention, an image acquisition module and a signal input module: obtaining basic information of materials to be separated, basic information of inlet materials of the centrifugal separator 5, image information of materials in the cyclone 1, image information and dynamic information of outlet materials of the centrifugal separator 5. The basic information of the material is that a first flow meter 9, a first TDS analysis meter 10, a first temperature meter 11, a first pressure meter 12, a second flow meter 13, a second TDS analysis meter 14, a second temperature meter 15 and a second pressure meter 16 are uploaded to a signal input module, and the image information of a first high-definition camera 2 and a second high-definition camera 6 is uploaded to an image acquisition module;
a data processing module: and establishing a dynamic variable construction module to construct dynamic information by entropy calculation of the material information and the image information. Establishing a PCA model module, inputting material information, image information and dynamic information into a preset first PCA model or a preset second PCA model, and outputting a monitoring value T by the first PCA model 1 2 (ii) a The second PCA model outputs a monitoring value T 2 2 。
A monitoring module: according to the monitored value T of the material to be separated 1 2 And a control limit value T 1L 2 Comparison and monitoring value T of material at outlet of centrifugal separator 2 2 And a control limit value T 2L 2 And comparing to obtain a control strategy.
In the first PCA model, if the value T is monitored 1 2 < control Limit T 1L 2 Opening an automatic valve 4 for qualified materials at the outlet of the cyclone, and closing an automatic valve 3 for unqualified materials at the outlet of the cyclone; if the monitored value T 1 2 Control limit T 1L 2 And opening the automatic valve 3 for the unqualified materials at the outlet of the cyclone, and closing the automatic valve 4 for the qualified materials at the outlet of the cyclone.
In the second PCA model, if the value T is monitored 2 2 < control Limit T 2L 2 Opening an automatic valve 7 for qualified materials at the outlet of the centrifugal separator, and closing an automatic valve 8 for unqualified materials at the outlet of the centrifugal separator; if the monitored value T 2 2 Control limit T 2L 2 And opening the automatic valve 8 for the unqualified materials at the outlet of the centrifugal separator and closing the automatic valve 7 for the qualified materials at the outlet of the centrifugal separator.
T generated by material to be separated in the invention 2 Value, output monitor value T through first PCA model 1 2 (ii) a T generated by material to be separated 2 The value is output to a monitoring value T through a second PCA model 2 2 。
In a preferred embodiment, a PCA module is constructed that builds the PCA model.
In a preferred embodiment, the principal component contribution of the PCA model is selected to be 85%.
In a preferred embodiment, further comprising:
and updating the PCA model, namely inputting the latest separable material information into the training data to replace the material information with long time, and generating the latest PCA model.
Claims (10)
1. A solid-liquid separation system based on dynamic PCA evaporative crystallization is characterized by comprising a controller (20) and a solid-liquid separation unit;
the solid-liquid separation unit comprises evaporation crystallization process equipment (17), a cyclone (1), a centrifugal separator (5) and drying equipment (18) which are arranged from top to bottom; wherein, the input end of the cyclone (1) is also connected with a material device (19) to be separated; the output ends of the cyclone (1) and the centrifugal separator (5) are respectively connected with the input end of the evaporation crystallization process equipment (17);
the input end of the controller (20) is respectively connected with the image acquisition module and the signal input module, and the output end of the controller (20) is respectively connected with the image preprocessing module and the data processing module; the input end of the image acquisition module is respectively connected with a first high-definition camera (2) and a second high-definition camera (6); the input end of the signal input module is respectively connected with a first flow meter (9), a first TDS analysis meter (10), a first temperature meter (11), a first pressure meter (12), a second flow meter (13), a second TDS analysis meter (14), a second temperature meter (15) and a second pressure meter (16);
the first high-definition camera (2) is assembled on the cyclone (1), the second high-definition camera (6) is assembled at a material outlet of the centrifugal separator (5), the first flow meter (9), the first TDS analysis meter (10), the first temperature meter (11) and the first pressure meter (12) are arranged at an outlet end of a material device (19) to be separated, and the second flow meter (13), the second TDS analysis meter (14), the second temperature meter (15) and the second pressure meter (16) are arranged at an inlet end of the centrifugal separator (5);
materials in the cyclone (1) and at the outlet of the centrifugal separator (5) are screened by adopting a dynamic PCA model and are used for establishing a first PCA model and a second PCA model;
wherein the first PCA model is used for inputting basic material information of a material device (19) to be separated, image information and dynamic information of materials in the cyclone after noise reduction and outputting a monitoring value T 1 2 Wherein a value T is monitored 1 2 Corresponding control limit value T 1L 2 (ii) a When monitoring value T 1 2 Greater than the control limit T 1L 2 When the material is fed back to the evaporation crystallization process equipment (17); the control limit value T 1L 2 The calculation formula is as follows:
wherein,afor the test level, the value is 0.95,F k,n- ,a1 to test the level ofaWith a degree of freedom ofk,n-1, critical value of F distribution;
wherein the second PCA model is used for inputting the material to be input into the centrifugal separator (5)Basic information, image information and dynamic information of the materials at the outlet of the centrifugal separator (5) after noise reduction processing and output a monitoring value T 2 2 Wherein a value T is monitored 2 2 Corresponding control limit value T 2L 2 (ii) a When monitoring value T 2 2 Value less than control limit T 2L 2 When the material is fed into the drying device (18); when monitoring value T 2 2 Value greater than control limit T 2L 2 When the material is fed back to the evaporation crystallization process equipment (17); the control limit value T 2L 2 Is calculated and the control limit value T 1L 2 The calculation formula is the same.
2. The dynamic PCA evaporative crystallization-based solid-liquid separation system as claimed in claim 1, wherein a human-computer interaction module is arranged on the controller (20), and the input end of the human-computer interaction module is connected with the output end of the controller and is used for displaying the images acquired in the first high-definition camera (2) and the second high-definition camera (6) and displaying the signal information of the first flow meter (9), the first TDS analysis meter (10), the first temperature meter (11), the first pressure meter (12), the second flow meter (13), the second TDS analysis meter (14), the second temperature meter (15), the second pressure meter (16), the image preprocessing module and the data processing module.
3. The dynamic PCA evaporative crystallization-based solid-liquid separation system of claim 1, wherein the output of the controller (20) is connected to monitors via monitoring modules, the monitors being respectively mounted on the material outlet outputs of the cyclone (1) and the centrifuge (5).
4. The dynamic PCA evaporative crystallization-based solid-liquid separation system as claimed in claim 1, wherein the output end of the cyclone (1) is provided with an automatic valve (3) for material with unqualified cyclone outlet and an automatic valve (4) for material with qualified cyclone outlet; the automatic valve (3) for the material with unqualified cyclone outlet is connected with evaporation crystallization process equipment (17); and the qualified material automatic valve (4) at the outlet of the cyclone is connected with the input end of the centrifugal separator (5).
5. The dynamic PCA evaporative crystallization-based solid-liquid separation system as claimed in claim 1, wherein the output end of the centrifugal separator is provided with an automatic valve (7) for qualified materials at the outlet of the centrifugal separator and an automatic valve (8) for unqualified materials at the outlet of the centrifugal separator; the automatic valve (8) for unqualified materials at the outlet of the centrifugal separator is connected with evaporative crystallization process equipment (17); the automatic valve (7) for qualified materials at the outlet of the centrifugal separator is connected with a drying device (18).
6. A solid-liquid separation method based on dynamic PCA evaporative crystallization, which is characterized in that the solid-liquid separation system based on dynamic PCA evaporative crystallization as claimed in any one of claims 1 to 5 comprises the following steps,
step 1, obtaining basic material information in a material device (19) to be separated and material image information in a cyclone (1);
step 2, carrying out noise reduction pretreatment on the obtained material image information through an image pretreatment technology;
step 3, constructing dynamic information processing on the basic material information in the material device (19) to be separated and the image information after denoising in the swirler (1) to obtain dynamic information;
step 4, screening the materials in the cyclone (1) by data processing according to the basic information of the materials of the device (19) to be separated, the image information and the dynamic information of the pretreated materials in the cyclone (1), feeding the materials with normal solid-liquid separation into the centrifugal separator (5) to execute the step 4, returning the materials with solid-liquid separation back to the evaporation and crystallization process equipment (17) to evaporate and concentrate, and then executing the step 1 again;
step 5, acquiring basic information of materials at an inlet of the centrifugal separator (5) and image information of the materials at an outlet of the centrifugal separator (5), and performing noise reduction on the acquired image information of the materials by an image preprocessing technology;
step 6, constructing dynamic information processing on the basic material information at the inlet of the centrifugal separator (5) and the de-noised image information at the outlet of the centrifugal separator (5) to obtain dynamic information;
step 7, screening the materials at the outlet of the centrifugal separator (5) by data processing on basic material information at the inlet of the centrifugal separator (5), noise-reduced material image information at the outlet of the centrifugal separator and dynamic information, enabling the normal solid-liquid separable materials to enter drying equipment (18), and finishing the separation work; returning the solid-liquid inseparable material to the evaporation crystallization process equipment (17) for evaporation and concentration, and then re-executing the step 1;
the dynamic information is obtained by performing entropy operation on the basic information and the image information of the material.
7. The dynamic PCA evaporative crystallization-based solid-liquid separation method of claim 6, wherein the image preprocessing technique comprises Gaussian filtering, mean filtering, median filtering, minimum mean square error filtering, and Gabor filtering.
8. The dynamic PCA evaporative crystallization-based solid-liquid separation method as claimed in claim 6, wherein the materials in the cyclone (1) and at the outlet of the centrifugal separator (5) are screened by a dynamic PCA model, and the specific method is as follows:
establishing a first PCA model and a second PCA model
Inputting basic material information of the material device (19) to be separated, image information and dynamic information of materials in the cyclone after noise reduction treatment into a first PCA model, and outputting a monitoring value T by the first PCA model 1 2 Wherein a value T is monitored 1 2 Corresponding control limit value T 1L 2 ;
When monitoring value T 1 2 Less than control limit T 1L 2 When in use, the materials enter a centrifugal separator (5);
when monitoring value T 1 2 Greater than the control limit T 1L 2 When the material is fed back to the evaporation crystallization process equipment (17);
inputting the basic information of the inlet material of the centrifugal separator (5), the image information and the dynamic information of the outlet material of the centrifugal separator (5) after noise reduction treatment into a second PCA model, and outputting a monitoring value T by the second PCA model 2 2 Wherein a value T is monitored 2 2 Corresponding control limit value T 2L 2 ;
When monitoring value T 2 2 Value less than control limit T 2L 2 When the material is fed into the drying device (18);
when monitoring value T 2 2 Value greater than control limit T 2L 2 In this case, the material is returned to the evaporative crystallization process equipment (17).
9. The dynamic PCA evaporative crystallization-based solid-liquid separation method of claim 8, wherein the first PCA model and the second PCA model are modeled by selecting principal components with principal component contribution rate greater than 85%.
10. The dynamic PCA evaporative crystallization-based solid-liquid separation method of claim 8, wherein the control limit T is 1L 2 The method is obtained by training a first PCA model by utilizing the basic information of separable materials, the material image information and the dynamic information in a cyclone by the same evaporative crystallization process;
control limit value T 2L 2 The method is obtained by training a second PCA model by using basic information of inlet materials of a centrifugal separator, image information of outlet materials of the centrifugal separator and dynamic information which can be separated by the same evaporative crystallization process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110572622.1A CN113307435B (en) | 2021-05-25 | 2021-05-25 | Dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110572622.1A CN113307435B (en) | 2021-05-25 | 2021-05-25 | Dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113307435A CN113307435A (en) | 2021-08-27 |
CN113307435B true CN113307435B (en) | 2022-12-13 |
Family
ID=77374705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110572622.1A Active CN113307435B (en) | 2021-05-25 | 2021-05-25 | Dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113307435B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106599902A (en) * | 2016-11-04 | 2017-04-26 | 浙江大学 | Sugar crystal classification and recognition and crystallization quality control method based on image |
CN207899610U (en) * | 2017-12-20 | 2018-09-25 | 上海亭博分离技术有限公司 | A kind of intelligent disconnecting link for horizontal centrifuge solid outlet |
CN108985376A (en) * | 2018-07-17 | 2018-12-11 | 东北大学 | It is a kind of based on convolution-Recognition with Recurrent Neural Network rotary kiln sequence operating mode's switch method |
US10242393B1 (en) * | 2014-06-24 | 2019-03-26 | Amazon Technologies, Inc. | Determine an item and user action in a materials handling facility |
CN210394061U (en) * | 2019-08-13 | 2020-04-24 | 北京中航泰达环保科技股份有限公司 | Treatment system for dry-method activated coke/carbon desulfurization and denitrification gas-rich pretreatment wastewater |
CN112520930A (en) * | 2020-12-18 | 2021-03-19 | 内蒙古蒙维科技有限公司 | Device and method for improving particle size distribution of chemical strong brine byproduct crystalline salt |
-
2021
- 2021-05-25 CN CN202110572622.1A patent/CN113307435B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10242393B1 (en) * | 2014-06-24 | 2019-03-26 | Amazon Technologies, Inc. | Determine an item and user action in a materials handling facility |
CN106599902A (en) * | 2016-11-04 | 2017-04-26 | 浙江大学 | Sugar crystal classification and recognition and crystallization quality control method based on image |
CN207899610U (en) * | 2017-12-20 | 2018-09-25 | 上海亭博分离技术有限公司 | A kind of intelligent disconnecting link for horizontal centrifuge solid outlet |
CN108985376A (en) * | 2018-07-17 | 2018-12-11 | 东北大学 | It is a kind of based on convolution-Recognition with Recurrent Neural Network rotary kiln sequence operating mode's switch method |
CN210394061U (en) * | 2019-08-13 | 2020-04-24 | 北京中航泰达环保科技股份有限公司 | Treatment system for dry-method activated coke/carbon desulfurization and denitrification gas-rich pretreatment wastewater |
CN112520930A (en) * | 2020-12-18 | 2021-03-19 | 内蒙古蒙维科技有限公司 | Device and method for improving particle size distribution of chemical strong brine byproduct crystalline salt |
Also Published As
Publication number | Publication date |
---|---|
CN113307435A (en) | 2021-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106649755A (en) | Threshold self-adaption setting abnormity detection method for multi-dimensional real-time power transformation device data | |
CN113307435B (en) | Dynamic PCA (principal component analysis) -based evaporative crystallization solid-liquid separation system and method | |
CN111695730A (en) | ARIMA and RNN-based vertical mill vibration prediction method and device | |
CN111882006A (en) | Data preprocessing method of desulfurization system based on PCA and correlation function | |
Guo et al. | Fault diagnosis of a semi-batch crystallization process through deep learning method | |
CN115495924A (en) | MOSFET service life prediction method based on ARIMA model | |
Strydom et al. | Fault diagnosis and economic performance evaluation for a simulated base metal leaching operation | |
CN113307436B (en) | HMM model-based evaporative crystallization solid-liquid separation system and method | |
AT522736B1 (en) | Determination device for calculating a humidity value in a fuel cell system | |
EP4209464A1 (en) | Chemical dosing optimization apparatus and method for water treatment plant | |
CN112631258A (en) | Fault early warning method for key indexes of industrial process | |
CN111061257B (en) | Industrial process monitoring method based on dynamic global LPP | |
CN110956308A (en) | Chemical equipment health state prediction method based on time sequence | |
Shaikh et al. | Data-driven based fault diagnosis using principal component analysis | |
Lu et al. | Model-plant mismatch detection with support vector machines | |
Miron et al. | Artificial neural network approach for fault recognition in a wastewater treatment process | |
Ai et al. | Reagent predictive control using joint froth image feature for antimony flotation process | |
CN113705637A (en) | Method, system and equipment for detecting mechanical fault of circuit breaker and readable storage medium | |
Li et al. | Qualitative/quantitative simulation of process temporal behavior using clustered fuzzy digraphs | |
CN117095362B (en) | Liquid drop monitoring method, system and storage medium of cell sorter | |
Pei et al. | Fault detection in chemical processes using discriminant analysis and control chart | |
US20230212033A1 (en) | Apparatus and method for controlling chemical dosing optimization for water treatment plant | |
Mrugalski et al. | Robust fault detection via GMDH neural networks | |
CN109407640B (en) | Dynamic process monitoring method based on dynamic orthogonal component analysis | |
CN114841295B (en) | Industrial process fault detection method and device, electronic equipment and storage medium |
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 |