CN114117900B - Method for solving U-tube spraying problem about support vector machine - Google Patents
Method for solving U-tube spraying problem about support vector machine Download PDFInfo
- Publication number
- CN114117900B CN114117900B CN202111371816.1A CN202111371816A CN114117900B CN 114117900 B CN114117900 B CN 114117900B CN 202111371816 A CN202111371816 A CN 202111371816A CN 114117900 B CN114117900 B CN 114117900B
- Authority
- CN
- China
- Prior art keywords
- hyperplane
- drying
- support vector
- vector machine
- spraying
- 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
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 45
- 238000005507 spraying Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001035 drying Methods 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 39
- 239000013598 vector Substances 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 25
- 230000001105 regulatory effect Effects 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims description 9
- 230000001276 controlling effect Effects 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 4
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 4
- 239000003973 paint Substances 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 230000003064 anti-oxidating effect Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 4
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 5
- 229910052802 copper Inorganic materials 0.000 description 5
- 239000010949 copper Substances 0.000 description 5
- 230000033228 biological regulation Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000000576 coating method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05D—PROCESSES FOR APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05D1/00—Processes for applying liquids or other fluent materials
- B05D1/02—Processes for applying liquids or other fluent materials performed by spraying
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05D—PROCESSES FOR APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05D3/00—Pretreatment of surfaces to which liquids or other fluent materials are to be applied; After-treatment of applied coatings, e.g. intermediate treating of an applied coating preparatory to subsequent applications of liquids or other fluent materials
- B05D3/04—Pretreatment of surfaces to which liquids or other fluent materials are to be applied; After-treatment of applied coatings, e.g. intermediate treating of an applied coating preparatory to subsequent applications of liquids or other fluent materials by exposure to gases
- B05D3/0406—Pretreatment of surfaces to which liquids or other fluent materials are to be applied; After-treatment of applied coatings, e.g. intermediate treating of an applied coating preparatory to subsequent applications of liquids or other fluent materials by exposure to gases the gas being air
- B05D3/0413—Heating with air
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
- Drying Of Solid Materials (AREA)
Abstract
The invention provides a method for solving the problem of U-tube spraying with respect to a support vector machine, which relates to the technical field of spraying and curing and comprises the following steps: processing devices, collecting factors, creating experimental sample data, giving training sample sets, linear equation descriptions, calculating distances, setting conditions and obtaining intervals; according to the invention, in the process of processing a device, various motion parameters of a drying part are macroscopically regulated and controlled according to the types of multiple factors, so that influence factors are determined, experimental sample data are established, a training sample set is generated, data are called and classified by using a support vector machine, a partitioned hyperplane is found in a sample space based on the training sample set, and is described by a linear equation, calculation is performed according to the set condition, a support vector is obtained from a training sample point nearest to the hyperplane, an interval is obtained according to the sum of distances from the support vector to the hyperplane, and a partitioned hyperplane with the largest interval is found, so that the optimal value of the influence factors is obtained, thereby improving production efficiency.
Description
Technical Field
The invention relates to the technical field of spraying and curing, in particular to a method for solving U-tube spraying with respect to a support vector machine.
Background
The spraying and curing are common processing procedures in the production process, taking a heat exchange U pipe of an evaporator and a condenser in an air conditioner as an example, most of heat dissipation of the air conditioner can be covered by aluminum fins, but a part of copper pipe heads can leak outside, oxidation corrosion and water leakage can occur after the pipe heads are contacted with air for a long time, in order to prevent the copper pipe heads from being contacted with the air, a layer of coating is required to cover the copper pipe heads, the copper pipe heads are directly used after being dried and cured, but the artificial coating process is slower and harmful to human bodies, and then the copper pipe heads are put into design and use in a U pipe spraying machine;
In the actual use process of equipment factories, the temperature difference between summer and winter is found to be large, the room temperature during summer processing is up to 40 ℃, the drying efficiency is greatly improved after the workpiece is sprayed with paint, the drying time can be reduced, the workpiece can be in a drying state, and the aim of improving the working efficiency is fulfilled; however, the room temperature is as low as 10 ℃ in winter processing, the air humidity is high, the original working state can be achieved only by increasing the drying temperature and lengthening the drying time in the processing process, the wind speed of the air heater, the distance between the air heater and the two devices and the like are found to be main influencing factors in the actual use process, in most cases, the temperature and speed range area of the U-tube spraying machine can be obtained only by estimating the U-tube spraying machine through experiments and experiences, but the final feedback result is only whether the U-tube is dried or not, and the optimal processing efficiency cannot be achieved.
Disclosure of Invention
In view of the above problems, the present invention provides a method for solving U-tube spraying by using a support vector machine, wherein in the process of processing a device, the method for solving U-tube spraying by using a support vector machine is characterized in that a plurality of motion parameters of a drying part are macroscopically regulated and controlled according to a plurality of factors, so as to determine influencing factors and establish experimental sample data, a training sample set is generated, data is called and classified by using a Support Vector Machine (SVM), support vectors are obtained by describing a linear equation, an interval is obtained according to the sum of distances from the support vectors to the hyperplane, and the most-spaced division hyperplanes are found, so that an optimal value of the influencing factors is obtained, thereby achieving a function of improving production efficiency.
In order to achieve the purpose of the invention, the invention is realized by the following technical scheme: a method for solving U-tube spraying with respect to a support vector machine, comprising the steps of:
step one: processing device
Dividing a U-pipe spraying machine into a spraying part and a drying part, spraying the prepared water paint on a required anti-oxidation device in the spraying part, conveying the sprayed device to the drying part through a plate chain line, and drying the device by controlling the output temperature of an input dryer;
Step two: collecting factors
Judging whether the device is dried or not, analyzing multi-factor influence according to multiple times of drying and non-drying, carrying out dimension lifting treatment on the device by utilizing a hyperplane idea in a Support Vector Machine (SVM), and mapping two dimensions of drying and non-drying into multi-factor high-dimensional mapping;
Step three: creation of experimental sample data
Collecting experimental sample data according to multiple factors under the condition of multiple times of drying and non-drying, and dividing the high-dimensional mapping under the experimental sample data to obtain an equation for dividing the hyperplane;
step four: given training sample set
In a given training sample set D= { (x 1,y1),(x2,y2),...,(xm,ym)},yi epsilon-1, +1), x represents a vector coordinate, refers to a characteristic value of one of multiple factors, and y refers to the condition of whether the device is successfully dried;
Step five: description of the Linear equation
Based on the training set D, a partitioned hyperplane is found in the sample space, and samples of different categories are classified, wherein the partitioned hyperplane is described by the following linear equation:
wTx+b＝0(0.1)
wherein w= (w 1;w2;w3;…;wd) represents a normal vector; b is a displacement term;
Step six: calculating distance
Determining a partition hyperplane quilt by using w and b, marking the partition hyperplane quilt as (w, b), and writing the distance from any point x in a sample space to the hyperplane (w, b) as;
Step seven: setting conditions
Setting the hyperplane (w, b) enables the training sample set to be correctly classified, for { (x i,yi) } i=1 to N,
Make the following stepsWhen y i = +1, then w Txi +b > 0; when y i = -1, w Txi +b < 0, let
Step eight: obtaining the interval
The nearest training sample point to the hyperplane satisfies the equal sign of equation (0.3), which is called the support vector, and the sum of the distances from the two support vectors to the hyperplane is
I.e., the interval, thereby calculating the maximum interval.
The further improvement is that: in the second step, the multiple factors include: drying temperature, drying time, drying wind speed, indoor temperature and indoor humidity.
The further improvement is that: in the second step, the support vector machine is an SVM, and the support vector machine is utilized to call data and classify the data to obtain the function relation of the influence of the data, so as to perform the dimension lifting processing.
The further improvement is that: in the second step, the multi-factor influence is analyzed according to multiple times of drying and non-drying, and the method specifically comprises the following steps: and (3) macroscopically regulating and controlling various motion parameters of the drying part according to the types of the multiple factors, so as to draw conclusions of the influencing factors.
The further improvement is that: in the fourth step, +1 represents a successful drying, and-1 represents a failed drying.
The further improvement is that: in the fifth step, w= (w 1;w2;w3;…;wd) represents a normal vector, determines the direction of the hyperplane, and b is a displacement term, and determines the distance between the hyperplane and the origin.
The further improvement is that: in the fifth step, w T x is a constant, and b is present so that w T x+b=0 is satisfied.
The further improvement is that: in the seventh step, for samples in the training sample set, when the device is dried successfully y i = +1, w and b exist, and w Txi +b >0 is satisfied; when the device fails to dry y i = -1, w and b exist, and w Txi +b < 0 is satisfied, which is the constraint condition of the equation.
The further improvement is that: in the step eight, the purpose of calculating the interval is to find the dividing hyperplane of the maximum interval, with this satisfying the parameters w and b of the constraint in equation (0.3), maximizing γ maximizes β, maximizing β -1, equating to minimizing γ 2.
The beneficial effects of the invention are as follows:
1. According to the invention, in the process of processing a device, various motion parameters of a drying part are macroscopically regulated and controlled according to the types of multiple factors, so that influence factors are determined, experimental sample data are established, a training sample set is generated, data are called by a Support Vector Machine (SVM) and classified, a divided hyperplane is found in a sample space based on the training sample set, and is described by a linear equation, calculation is performed according to the set condition, a training sample point closest to the hyperplane obtains a support vector, an interval is obtained according to the sum of distances from the support vector to the hyperplane, and the divided hyperplane with the maximum interval is found, so that an optimal value of the influence factors is obtained, and therefore, the function of improving production efficiency is achieved.
2. According to the invention, through statistics and collection of a large number of training samples, the most accurate parameters of influencing factors are obtained, and the high-efficiency macroscopic regulation and control of various motion parameters of the drying part are matched, so that the working efficiency of the U-tube spraying machine is accurately improved, and the error is small.
3. According to the invention, the latest support vector machine algorithm is used for calculating the functional relation between the drying completion condition and a plurality of processing factors according to the measurement data of different processing factories, so that the processing efficiency is improved, and the application range is wide.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of two classes of training samples separated by the existence of multiple partitioning hyperplanes in accordance with the present invention;
FIG. 3 is a schematic diagram of support vectors and intervals according to the present invention.
Detailed Description
The present invention will be further described in detail with reference to the following examples, which are only for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Example 1
According to fig. 1, 2 and 3, the present embodiment provides a method for solving U-tube spraying with respect to a support vector machine, including the following steps:
step one: processing device
Dividing a U-pipe spraying machine into a spraying part and a drying part, spraying the prepared water paint on a required anti-oxidation device in the spraying part, conveying the sprayed device to the drying part through a plate chain line, and drying the device by controlling the output temperature of an input dryer;
Step two: collecting factors
Judging whether the device is dried or not, and analyzing multi-factor influence according to repeated drying and non-drying, wherein the method specifically comprises the following steps: and macroscopically regulating and controlling various motion parameters of the drying part according to the types of multiple factors so as to draw conclusions of influencing factors, wherein the multiple factors comprise: the method comprises the steps of carrying out dimension lifting treatment on the drying temperature, the drying time, the drying wind speed, the indoor temperature and the indoor humidity by utilizing a hyperplane thought in a Support Vector Machine (SVM), wherein the support vector machine is the SVM, calling data by utilizing the support vector machine and classifying the data to obtain the functional relation of influence of the data, carrying out dimension lifting treatment on the data, and carrying out dimension lifting treatment, wherein the two-dimensional mapping of the drying and the non-drying is carried out to multi-factor high-dimensional mapping; according to the invention, the latest support vector machine algorithm is used for calculating the functional relation between the drying completion condition and a plurality of processing factors according to the measurement data of different processing factories, so that the processing efficiency is improved, and the application range is wide;
Step three: creation of experimental sample data
Collecting experimental sample data according to multiple factors under the condition of multiple times of drying and non-drying, and dividing the high-dimensional mapping under the experimental sample data to obtain an equation for dividing the hyperplane; according to the invention, through statistics and collection of a large number of training samples, the most accurate parameters of influencing factors are obtained, and the high-efficiency macroscopic regulation and control of various motion parameters of the drying part are matched, so that the working efficiency of the U-tube spraying machine is accurately improved, and the error is small;
step four: given training sample set
In a given training sample set D= { (x 1,y1),(x2,y2),...,(xm,ym)},yi E { -1, +1}, x represents a vector coordinate, refers to a characteristic value of one of multiple factors, y refers to whether the device is successfully dried or not, wherein +1 represents drying success, and-1 represents drying failure;
Step five: description of the Linear equation
Based on the training set D, a partitioned hyperplane is found in the sample space, and samples of different classes are classified, but the possibility of separating the training samples from the hyperplane is high, as shown in fig. 2, but it is required to select an optimal plane, and in the sample space, the partitioned hyperplane is described by the following linear equation:
wTx+b＝0(0.1)
Wherein w= (w 1;w2;w3;…;wd) represents a normal vector, determining the direction of the hyperplane; b is a displacement term, and the distance between the hyperplane and the origin is determined; w T x is a constant, b is present, such that w T x+b=0 is satisfied.
Step six: calculating distance
Determining a partition hyperplane quilt by using w and b, marking the partition hyperplane quilt as (w, b), and writing the distance from any point x in a sample space to the hyperplane (w, b) as;
Step seven: setting conditions
Setting the hyperplane (w, b) enables the training sample set to be correctly classified, for { (x i,yi) } i=1 to N,
Make the following stepsWhen y i = +1, then w Txi +b > 0; when y i = -1, w Txi +b < 0, let
For samples in the training sample set, when the device is dried successfully y i = +1, w and b exist, and w Txi +b >0 is satisfied; when the device fails to dry y i = -1, w and b exist, and w Txi +b <0 is satisfied, and the constraint condition of the equation is adopted;
Step eight: obtaining the interval
As shown in FIG. 3, the nearest training sample point to the hyperplane satisfies the equal sign of equation (0.3), which is called the support vector, and the sum of the distances from the hyperplane to the two support vectors is
I.e. interval, the object of calculating the interval is to find the dividing hyperplane of the maximum interval, thereby satisfying the parameters w and b constrained in the formula (0.3), maximizing gamma, maximizing the value of w -1, equivalent to minimize w 2 then the final optimization problem is:
This is the basic type of support vector machine (Support Vector Machine). According to the invention, in the process of processing a device, various motion parameters of a drying part are macroscopically regulated and controlled according to the types of multiple factors, so that influence factors are determined, experimental sample data are established, a training sample set is generated, data are called by a Support Vector Machine (SVM) and classified, a divided hyperplane is found in a sample space based on the training sample set, and is described by a linear equation, calculation is performed according to the set condition, a training sample point closest to the hyperplane obtains a support vector, an interval is obtained according to the sum of distances from the support vector to the hyperplane, and the divided hyperplane with the maximum interval is found, so that an optimal value of the influence factors is obtained, and therefore, the function of improving production efficiency is achieved.
Example two
The embodiment provides a method for solving the problem of U-tube spraying about a support vector machine, which comprises the following steps:
Step one: in a given training sample set D= { (x 1,y1),(x2,y2),...,(xm,ym)},yi epsilon-1, +1), x represents a vector coordinate, and represents characteristic values such as drying temperature, drying time, drying wind speed, indoor temperature, indoor humidity and the like, y represents the condition of two-device drying, wherein +1 represents drying success, and-1 represents drying failure;
Step two: let x be a vector of m rows and 1 columns, let w be the normal vector of m rows and 1 columns perpendicular thereto, multiply the two, let w T x be a constant, have b, let w T x+b=0;
step three: for { (x i,yi) } i=1 to N, Make the following stepsWhen y i = +1, then w Txi +b > 0; when y i = -1, w Txi +b <0, for samples in the training sample set, when two-ware drying is successful y i = +1, w and b exist, satisfying w Txi +b > 0; when the two-device drying failure y i = -1, w and b exist, and w Txi +b <0 is satisfied, then this is the constraint condition of the equation.
Step four: assuming plane equations
w1x+w2y+b＝0(0.10)
Assuming the point is (x 0,y0), then to this equation:
The distance of vector x0 to hyperplane w T x + b=0 is then
Step five: given that w T x+b=0 is in the same plane as aw T x+ab=0, when (w, b) satisfies equation (0.3), then (aw, ab) also satisfies equation (0.3), so w T x+b is scaled by constant a to satisfy w T x+b=1, and then the distance between the support vector and the plane is:
According to the invention, in the process of processing a device, various motion parameters of a drying part are macroscopically regulated and controlled according to the types of multiple factors, so that influence factors are determined, experimental sample data are established, a training sample set is generated, data are called by a Support Vector Machine (SVM) and classified, a divided hyperplane is found in a sample space based on the training sample set, and is described by a linear equation, calculation is performed according to the set condition, a training sample point closest to the hyperplane obtains a support vector, an interval is obtained according to the sum of distances from the support vector to the hyperplane, and the divided hyperplane with the maximum interval is found, so that an optimal value of the influence factors is obtained, and therefore, the function of improving production efficiency is achieved. And the most accurate parameters of influencing factors are obtained through statistics and collection of a large number of training samples, and the working efficiency of the U-tube spraying machine is accurately improved by matching with various motion parameters of the high-efficiency macroscopic regulation and control drying part, so that the error is small. Meanwhile, the invention calculates the functional relation between the drying completion condition and a plurality of processing factors according to the measurement data of different processing factories by the latest support vector machine algorithm, thereby improving the processing efficiency and having wide application range.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. The method for solving the problem of U-pipe spraying with respect to the support vector machine is characterized by comprising the following steps:
step one: processing device
Dividing a U-pipe spraying machine into a spraying part and a drying part, spraying the prepared water paint on a required anti-oxidation device in the spraying part, conveying the sprayed device to the drying part through a plate chain line, and drying the device by controlling the output temperature of an input dryer;
Step two: collecting factors
Judging whether the device is dried or not, analyzing the multi-factor influence according to multiple times of drying and non-drying, carrying out dimension lifting treatment on the device by utilizing a hyperplane idea in a support vector machine, and mapping two dimensions of drying and non-drying into multi-factor high-dimension mapping;
Step three: creation of experimental sample data
Collecting experimental sample data according to multiple factors under the condition of multiple times of drying and non-drying, and dividing the high-dimensional mapping under the experimental sample data to obtain an equation for dividing the hyperplane;
step four: given training sample set
In a given training sample set D= { (x 1,y1),(x2,y2),...,(xm,ym)},yi epsilon-1, +1), x represents a vector coordinate, refers to a characteristic value of one of multiple factors, and y refers to the condition of whether the device is successfully dried;
Step five: description of the Linear equation
Based on the training set D, a partitioned hyperplane is found in the sample space, and samples of different categories are classified, wherein the partitioned hyperplane is described by the following linear equation:
wTx+b＝0 (0.1)
wherein w= (w 1;w2;w3;…;wd) represents a normal vector; b is a displacement term;
Step six: calculating distance
Determining a partition hyperplane quilt by using w and b, marking the partition hyperplane quilt as (w, b), and writing the distance from any point x in a sample space to the hyperplane (w, b) as;
Step seven: setting conditions
Setting the hyperplane (w, b) enables the training sample set to be correctly classified, for { (x i,yi) } i=1 to N,Make the following stepsWhen y i = +1, then w Txi +b > 0; when y i = -1, w Txi +b < 0, let
Step eight: obtaining the interval
The nearest training sample point to the hyperplane satisfies the equal sign of equation (0.3), which is called the support vector, and the sum of the distances from the two support vectors to the hyperplane is
I.e., the interval, thereby calculating the maximum interval.
2. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 1, wherein: in the second step, the multiple factors include: drying temperature, drying time, drying wind speed, indoor temperature and indoor humidity.
3. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 2, wherein: in the second step, the support vector machine is an SVM, and the support vector machine is utilized to call data and classify the data to obtain the function relation of the influence of the data, so as to perform the dimension lifting processing.
4. A method for solving U-tube spraying with respect to a support vector machine according to claim 3, wherein: in the second step, the multi-factor influence is analyzed according to multiple times of drying and non-drying, and the method specifically comprises the following steps: and (3) macroscopically regulating and controlling various motion parameters of the drying part according to the types of the multiple factors, so as to draw conclusions of the influencing factors.
5. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 4, wherein: in the fourth step, +1 represents a successful drying, and-1 represents a failed drying.
6. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 5, wherein: in the fifth step, w= (w 1;w2;w3;…;wd) represents a normal vector, determines the direction of the hyperplane, and b is a displacement term, and determines the distance between the hyperplane and the origin.
7. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 6, wherein: in the fifth step, w T x is a constant, and b is present so that w T x+b=0 is satisfied.
8. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 7, wherein: in the seventh step, for samples in the training sample set, when the device is dried successfully y i = +1, w and b exist, and w Txi +b >0 is satisfied; when the device fails to dry y i = -1, w and b exist, and w Txi +b <0 is satisfied, which is the constraint condition of the equation.
9. The method for solving the problem of U-tube spraying with respect to the support vector machine according to claim 8, wherein: in the step eight, the purpose of calculating the interval is to find the dividing hyperplane of the maximum interval, with this satisfying the parameters w and b of the constraint in equation (0.3), maximizing γ maximizes β, maximizing β -1, equating to minimizing γ 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111371816.1A CN114117900B (en) | 2021-11-18 | 2021-11-18 | Method for solving U-tube spraying problem about support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111371816.1A CN114117900B (en) | 2021-11-18 | 2021-11-18 | Method for solving U-tube spraying problem about support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114117900A CN114117900A (en) | 2022-03-01 |
| CN114117900B true CN114117900B (en) | 2024-08-02 |
Family
ID=80397772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111371816.1A Active CN114117900B (en) | 2021-11-18 | 2021-11-18 | Method for solving U-tube spraying problem about support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114117900B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909852B (en) * | 2024-03-19 | 2024-05-24 | 山东省地矿工程勘察院(山东省地质矿产勘查开发局八〇一水文地质工程地质大队) | Monitoring data state division method for hydraulic loop ecological data analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108345965A (en) * | 2018-04-13 | 2018-07-31 | 魔金真彩网络科技（长沙）有限公司 | A kind of Paint Color Matching method and system based on big data study |
| CN112149760A (en) * | 2020-10-28 | 2020-12-29 | 哈尔滨工业大学 | Heterogeneous inner hyperplane-based fuzzy support vector machine design method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AR118333A1 (en) * | 2019-03-18 | 2021-09-29 | Evonik Operations Gmbh | METHOD OF GENERATING A COMPOSITION FOR PAINTS, VARNISHES, PRINTING INKS, GRINDING RESINS, PIGMENT CONCENTRATES OR OTHER COATING MATERIALS |
-
2021
- 2021-11-18 CN CN202111371816.1A patent/CN114117900B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108345965A (en) * | 2018-04-13 | 2018-07-31 | 魔金真彩网络科技（长沙）有限公司 | A kind of Paint Color Matching method and system based on big data study |
| CN112149760A (en) * | 2020-10-28 | 2020-12-29 | 哈尔滨工业大学 | Heterogeneous inner hyperplane-based fuzzy support vector machine design method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114117900A (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108317670B (en) | Refrigeration system energy-saving control method and system based on machine learning | |
| CN111199016A (en) | DTW-based improved K-means daily load curve clustering method | |
| CN114117900B (en) | Method for solving U-tube spraying problem about support vector machine | |
| CN111427750B (en) | GPU power consumption estimation method, system and medium of computer platform | |
| CN111442489A (en) | Control method and system of air conditioner, air conditioner and readable storage medium | |
| CN111008504A (en) | Wind power prediction error modeling method based on meteorological pattern recognition | |
| CN116820214B (en) | Intelligent regulation and control method and system for ventilation and heat dissipation of server | |
| CN111898725A (en) | Air conditioning system sensor fault detection method and device and electronic equipment | |
| CN104700147A (en) | Cooling tower water outlet temperature predicating method | |
| CN113703506B (en) | Building material production workshop environment control and regulation method and system | |
| CN115472233B (en) | Semi-supervised integrated industrial process soft measurement modeling method and system based on thermal diffusion label propagation | |
| CN116595383A (en) | Intelligent cooling method for storage unit of data center | |
| CN109886462B (en) | Rectifying tower fault diagnosis method for improving particle swarm optimization support vector machine | |
| CN115013949A (en) | Indoor temperature control system and method based on image recognition | |
| Yaro et al. | Enhancing Fingerprint Localization Accuracy With Inverse Weight-Normalized Context Similarity Coefficient-Based Fingerprint Similarity Metric | |
| CN107544447A (en) | A kind of chemical process Fault Classification based on core study | |
| CN116963482A (en) | Intelligent energy-saving method and related equipment based on data center heating and ventilation system | |
| CN113074575B (en) | Cooling tower control method and cooling tower control system | |
| CN116403375A (en) | Biological laboratory danger monitoring and early warning system based on data analysis | |
| CN118466375B (en) | Environment control method, device and system applied to GIS control cabinet | |
| CN114548294A (en) | Power grid abnormal data detection method and device, mobile terminal and storage medium | |
| Xiao et al. | Improved ALOHA-based RFID Tag Anti-collision Algorithm | |
| CN116089860B (en) | Multi-stage distribution correction guided equipment fault diagnosis method and device | |
| CN111967150A (en) | Cooling capacity calculation method and device, computer equipment and storage medium | |
| CN118348942B (en) | Servo driver control system and method based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |