CN116166072A - Electronic grade hexafluoropropylene cracking temperature control system - Google Patents
Electronic grade hexafluoropropylene cracking temperature control system Download PDFInfo
- Publication number
- CN116166072A CN116166072A CN202310313649.8A CN202310313649A CN116166072A CN 116166072 A CN116166072 A CN 116166072A CN 202310313649 A CN202310313649 A CN 202310313649A CN 116166072 A CN116166072 A CN 116166072A
- Authority
- CN
- China
- Prior art keywords
- temperature
- time sequence
- feature
- matrix
- decoding
- 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.)
- Withdrawn
Links
- 238000005336 cracking Methods 0.000 title claims abstract description 96
- HCDGVLDPFQMKDK-UHFFFAOYSA-N hexafluoropropylene Chemical group FC(F)=C(F)C(F)(F)F HCDGVLDPFQMKDK-UHFFFAOYSA-N 0.000 title claims abstract description 59
- 239000013598 vector Substances 0.000 claims abstract description 162
- 238000010438 heat treatment Methods 0.000 claims abstract description 80
- 238000000605 extraction Methods 0.000 claims abstract description 55
- 238000006243 chemical reaction Methods 0.000 claims abstract description 49
- 239000011159 matrix material Substances 0.000 claims description 224
- 230000008859 change Effects 0.000 claims description 64
- 238000009826 distribution Methods 0.000 claims description 56
- 230000004927 fusion Effects 0.000 claims description 40
- 238000005457 optimization Methods 0.000 claims description 20
- 238000010586 diagram Methods 0.000 claims description 17
- 238000000197 pyrolysis Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 description 25
- 238000001514 detection method Methods 0.000 description 11
- 238000011217 control strategy Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- YCKRFDGAMUMZLT-UHFFFAOYSA-N Fluorine atom Chemical compound [F] YCKRFDGAMUMZLT-UHFFFAOYSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 229910052731 fluorine Inorganic materials 0.000 description 2
- 239000011737 fluorine Substances 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003776 cleavage reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- BFKJFAAPBSQJPD-UHFFFAOYSA-N tetrafluoroethene Chemical group FC(F)=C(F)F BFKJFAAPBSQJPD-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D23/00—Control of temperature
- G05D23/19—Control of temperature characterised by the use of electric means
- G05D23/20—Control of temperature characterised by the use of electric means with sensing elements having variation of electric or magnetic properties with change of temperature
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
An electronic grade hexafluoropropylene cracking temperature control system is disclosed. Firstly, arranging temperature values of heating sleeves at a plurality of preset time points into temperature input vectors, wherein the temperature values of every two adjacent positions are different to obtain temperature fluctuation input vectors, then, respectively passing the temperature input vectors and the temperature fluctuation input vectors through a multi-scale neighborhood feature extraction module to obtain temperature time sequence feature vectors and temperature fluctuation time sequence feature vectors, then, carrying out feature enhancement on the temperature time sequence feature vectors and the temperature fluctuation time sequence feature vectors based on a Gaussian density map to obtain decoding feature matrixes, finally, passing the decoding feature matrixes through a decoder to obtain decoding values for representing estimated values of reaction temperatures of a cracking furnace at the current time point, and generating a temperature control instruction based on the decoding values. Thus, the temperature of the cracking reaction can be accurately controlled.
Description
Technical Field
The present application relates to the field of intelligent control, and more particularly, to an electronic grade hexafluoropropylene cracking temperature control system.
Background
Electronic grade hexafluoropropylene is an extremely important perfluorinated intermediate in the organic fluorine industry and has wide application as a monomer of fluorine-containing materials. The industrial production mainly produces electronic grade hexafluoropropylene through tetrafluoroethylene cracking.
In the prior art, a cracking furnace for producing electronic-grade hexafluoropropylene adopts a three-section single-furnace tube cracking furnace, and is matched with three magnetic pressure regulators, and the magnetic pressure regulators are regulated by a temperature controller to act on a heating sleeve outside the cracking furnace, so that the sleeve is heated and then radiates heat to the cracking furnace tube. Thereby providing the heat required for the cleavage reaction. The heat supply mode can avoid the risk of explosion caused by direct contact between materials and electric appliances, but has larger relative heat loss and higher power consumption, and the temperature detection of the cracking furnace is generally realized by arranging a temperature detection point on the outer wall of the heating sleeve. Therefore, the temperature of the cracking furnace is controlled, but the detection mode can only detect the temperature of the heating sleeve, has a larger difference with the actual reaction temperature in the cracking furnace, and cannot accurately control the temperature of the cracking reaction.
Thus, an optimized electronic grade hexafluoropropylene cracking temperature control scheme is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides an electronic-grade hexafluoropropylene cracking temperature control system. Firstly, arranging temperature values of heating sleeves at a plurality of preset time points into temperature input vectors, wherein the temperature values of every two adjacent positions are different to obtain temperature fluctuation input vectors, then, respectively passing the temperature input vectors and the temperature fluctuation input vectors through a multi-scale neighborhood feature extraction module to obtain temperature time sequence feature vectors and temperature fluctuation time sequence feature vectors, then, carrying out feature enhancement on the temperature time sequence feature vectors and the temperature fluctuation time sequence feature vectors based on a Gaussian density map to obtain decoding feature matrixes, finally, passing the decoding feature matrixes through a decoder to obtain decoding values for representing estimated values of reaction temperatures of a cracking furnace at the current time point, and generating a temperature control instruction based on the decoding values. Thus, the temperature of the cracking reaction can be accurately controlled.
According to one aspect of the present application, there is provided an electronic grade hexafluoropropylene cracking temperature control system, comprising: the temperature data acquisition module is used for acquiring temperature values of the heating sleeve at a plurality of preset time points in a preset time period acquired by the temperature sensor; the temperature time sequence distribution module is used for arranging the temperature values of the heating sleeves at a plurality of preset time points into temperature input vectors according to the time dimension; the temperature relative data distribution module is used for calculating the difference value between the temperature values of every two adjacent positions in the temperature input vector to obtain a temperature fluctuation input vector; the temperature time sequence change feature extraction module is used for respectively passing the temperature input vector and the temperature fluctuation input vector through the multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector; the data characteristic enhancement module is used for carrying out characteristic enhancement on the temperature time sequence characteristic vector and the temperature fluctuation time sequence characteristic vector based on a Gaussian density chart so as to obtain a temperature time sequence characteristic matrix and a temperature fluctuation time sequence characteristic matrix; the feature fusion module is used for fusing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix to obtain a decoding feature matrix; the reaction temperature estimation module is used for enabling the decoding feature matrix to pass through a decoder to obtain a decoding value, wherein the decoding value is used for representing an estimated value of the reaction temperature of the cracking furnace at the current time point; and a control module for generating a temperature control instruction based on the decoded value.
In the electronic-grade hexafluoropropylene pyrolysis temperature control system, the multi-scale neighborhood feature extraction module comprises a first convolution layer and a second convolution layer which are parallel, and a multi-scale feature fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer use one-dimensional convolution kernels with different scales.
In the above electronic grade hexafluoropropylene cracking temperature control system, the temperature time sequence variation feature extraction module includes: a first scale temperature feature extraction unit, configured to perform one-dimensional convolutional encoding on the temperature input vector by using a first convolutional layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature feature vector, where the first convolutional layer has a first one-dimensional convolution kernel with a first length; a second scale temperature feature extraction unit, configured to perform one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the temperature multiscale fusion unit is used for cascading the first-scale temperature characteristic vector and the second-scale temperature characteristic vector by using a multiscale characteristic fusion layer of the multiscale neighborhood characteristic extraction module so as to obtain the temperature time sequence characteristic vector.
In the above electronic grade hexafluoropropylene cracking temperature control system, the data characteristic enhancing module is configured to: performing data enhancement on the temperature time sequence feature vector by using a first Gaussian formula to obtain a first Gaussian density diagram; wherein, the first gaussian formula is:
wherein ,/>
Representing the temperature timing feature vector, and +.>
The value of each position of the temperature time sequence characteristic vector represents the variance between the characteristic values of the corresponding two positions; and discretizing the Gaussian distribution of each position of the first Gaussian density map to obtain the temperature time sequence characteristic matrix.
In the above electronic grade hexafluoropropylene cracking temperature control system, the feature fusion module includes: the optimization factor calculation unit is used for calculating the Helmholtz type free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix to obtain a first Helmholtz type free energy factor and a second Helmholtz type free energy factor; the weighting optimization unit is used for weighting the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix by taking the first Helmholtz class free energy factor and the second Helmholtz class free energy factor as weighting weights so as to obtain an optimized temperature time sequence characteristic matrix and an optimized temperature fluctuation time sequence characteristic matrix; and the optimized feature fusion unit is used for fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix to obtain the decoding feature matrix.
In the above electronic grade hexafluoropropylene cracking temperature control system, the optimization factor calculating subunit is configured to: calculating the Helmholtz type free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix according to the following optimization formula to obtain the first Helmholtz type free energy factor and the second Helmholtz type free energy factor; wherein, the optimization formula is:
wherein ,/>
Characteristic values representing respective positions in the temperature time series characteristic matrix, +.>
Characteristic values representing respective positions in the temperature fluctuation time sequence characteristic matrix, < >>
and />
Classification probability values respectively representing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix, and +.>
Is the scale of the feature matrix, +.>
A logarithmic function with a base of 2 is shown,
watch (watch)Index calculation (I/O)>
and />
Representing the first helmholtz-like free energy factor and the second helmholtz-like free energy factor, respectively.
In the above electronic grade hexafluoropropylene cracking temperature control system, the optimizing feature fusion unit is configured to: fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix by using the following fusion formula to obtain the decoding feature matrix; wherein, the fusion formula is: 
wherein ,/>
Representing the optimized temperature time sequence characteristic matrix, < >>
Representing the optimized temperature fluctuation time sequence characteristic matrix, < >>
Representing the decoding feature matrix,/a>
Representing multiplication by location.
In the above electronic grade hexafluoropropylene cracking temperature control system, the reaction temperature estimation module is configured to: performing decoding regression on the decoding feature matrix in the following decoding formula by using a plurality of full connection layers of the decoder to obtain the decoding value; wherein, the decoding formula is:
wherein ,/>
Is the decoding feature matrix,>
is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication.
Compared with the prior art, the electronic-grade hexafluoropropylene cracking temperature control system provided by the application is characterized in that firstly, temperature values of heating sleeves at a plurality of preset time points are arranged into temperature input vectors, the difference value between the temperature values of every two adjacent positions is used for obtaining temperature fluctuation input vectors, then, the temperature input vectors and the temperature fluctuation input vectors are respectively processed through a multi-scale neighborhood feature extraction module to obtain temperature time sequence feature vectors and temperature fluctuation time sequence feature vectors, then, feature enhancement is carried out on the temperature time sequence feature vectors and the temperature fluctuation time sequence feature vectors based on Gaussian density diagrams, then, fusion is carried out to obtain decoding feature matrixes, finally, the decoding feature matrixes are processed through a decoder to obtain decoding values for representing estimated values of reaction temperatures of cracking furnaces at the current time point, and temperature control instructions are generated based on the decoding values. Thus, the temperature of the cracking reaction can be accurately controlled.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. The following drawings are not intended to be drawn to scale, with emphasis instead being placed upon illustrating the principles of the present application.
Fig. 1 is an application scenario diagram of an electronic grade hexafluoropropylene cracking temperature control system according to an embodiment of the present application.
Fig. 2 is a block diagram schematic diagram of an electronic grade hexafluoropropylene cracking temperature control system according to an embodiment of the present application.
Fig. 3 is a schematic block diagram of the temperature time sequence variation feature extraction module in the electronic grade hexafluoropropylene cracking temperature control system according to the embodiment of the present application.
Fig. 4 is a schematic block diagram of the feature fusion module in the electronic grade hexafluoropropylene cracking temperature control system according to an embodiment of the present application.
Fig. 5 is a flow chart of a method for controlling the cracking temperature of electronic grade hexafluoropropylene according to an embodiment of the present application.
Fig. 6 is a schematic diagram of a system architecture of an electronic grade hexafluoropropylene cracking temperature control method according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are also within the scope of the present application.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As described above, the temperature detection of the pyrolysis furnace is generally performed by setting a temperature detection point on the outer wall of the heating sleeve, but the detection mode can only detect the temperature of the heating sleeve, and the temperature of the pyrolysis reaction cannot be accurately controlled because the temperature of the pyrolysis furnace is greatly different from the actual reaction temperature in the pyrolysis furnace. Thus, an optimized electronic grade hexafluoropropylene cracking temperature control scheme is desired.
Accordingly, it is considered that although the temperature detection point is set on the outer wall of the heating sleeve, the temperature of the heating sleeve can only be detected, and the difference between the temperature of the heating sleeve and the actual reaction temperature in the cracking furnace is large, in practice, there is an implicit relation between the temperature of the heating sleeve and the actual reaction temperature in the cracking furnace, and the temperature change between the two is also an implicit relation. Thus, the estimated value of the reaction temperature of the cracking furnace can be obtained by capturing the temperature distribution characteristics of the heating sleeve and performing decoding regression on the temperature distribution characteristics. Furthermore, an appropriate temperature control strategy is adopted based on the estimated value of the reaction temperature, so that accurate temperature control can be realized through software-side optimization without changing hardware conditions or with simple hardware conditions. In the process, the difficulty is how to fully perform accurate expression of time sequence dynamic change characteristics of the temperature value of the heating sleeve, so as to accurately estimate the reaction temperature of the cracking furnace, and ensure stable and normal cracking reaction by adopting a corresponding temperature control strategy.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides new solutions and schemes for mining time sequence dynamic change characteristic information of the temperature value of the heating sleeve.
Specifically, in the technical solution of the present application, first, temperature values of the heating jacket at a plurality of predetermined time points within a predetermined period of time acquired by the temperature sensor are acquired. Next, in order to accurately capture such a time-series change hiding rule, it is necessary to integrate time-series distribution information of the temperature values of the heating jacket by arranging the temperature values of the heating jacket at the plurality of predetermined time points in the time dimension as a temperature input vector, taking into consideration that the temperature values of the heating jacket have a time-series dynamic change rule in the time dimension.
Further, in order to accurately estimate the reaction temperature value of the cracking furnace, it is necessary to perform sufficient expression of the dynamic change characteristics of the temperature value of the heating jacket in the time dimension. Considering that the time-series change information of the temperature value of the heating sleeve is weak, the weak change feature is small-scale change feature information relative to the temperature value of the heating sleeve, if the time-series dynamic change feature extraction of the temperature value of the heating sleeve is performed by using absolute change information, the small-scale weak change feature of the temperature value of the heating sleeve in the time dimension is difficult to be perceived, and the accuracy of subsequent decoding is further affected.
Based on the above, in the technical solution of the present application, the dynamic feature extraction of the temperature value of the heating sleeve is comprehensively performed by adopting the time sequence relative change feature and the absolute change feature of the temperature value of the heating sleeve. Specifically, first, the difference between the temperature values of every adjacent two positions in the temperature input vector is calculated to obtain a temperature fluctuation input vector. Next, it is considered that since there is a correlation between the time series relative change characteristic and the time series absolute change characteristic of the temperature value of the heating jacket with respect to the temperature dynamic time series change of the heating jacket, and since the time series relative change information and the time series absolute change information of the temperature value of the heating jacket have different fluctuation change characteristics at different time period spans within the predetermined period, the time series correlation characteristic information of the two also has a multi-scale fluctuation correlation characteristic. Based on the above, in order to fully capture the dynamic change rule of the temperature value of the heating sleeve in the time dimension so as to accurately estimate the reaction temperature of the cracking furnace, in the technical scheme of the application, the temperature input vector and the temperature fluctuation input vector are firstly encoded in a multi-scale neighborhood feature extraction module respectively so as to extract dynamic multi-scale neighborhood associated features of time sequence relative change information and time sequence absolute change information of the temperature value of the heating sleeve under different time spans, thereby obtaining a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector.
Then, considering that the absolute change amount and the relative fluctuation amount of the temperature value of the heating jacket are not obvious in the actual detection process, it is desirable to further perform feature expression enhancement after obtaining the time-series multi-scale dynamic change feature of the absolute change amount and the relative fluctuation amount of the temperature value of the heating jacket so as to perform sufficient expression of the time-series dynamic change feature of the temperature value of the heating jacket. It should be understood that, as a learning target of the neural network model, the gaussian density map may represent a joint distribution in the case where a plurality of feature values constitute an overall distribution due to probability density thereof, that is, a feature distribution is taken as a priori distribution, and probability density under the influence of correlation with other a priori distribution positions at each a priori distribution position is obtained as a posterior distribution, thereby describing the feature distribution more accurately in a higher dimension. Therefore, in the technical scheme of the application, the data enhancement can be performed on the time sequence multi-scale dynamic implicit association features of the absolute variation of the temperature value and the relative fluctuation amount of the heating sleeve through the prior distribution, namely the Gaussian distribution, of the absolute variation of the temperature value and the relative fluctuation amount of the heating sleeve, namely the time sequence feature vector and the temperature fluctuation time sequence feature vector are subjected to feature enhancement based on a Gaussian density chart so as to obtain a temperature time sequence feature matrix and a temperature fluctuation time sequence feature matrix.
Further, the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix are fused, so that absolute time sequence multi-scale dynamic change feature information of the temperature value of the heating sleeve and relative time sequence multi-scale dynamic change feature information of the temperature value are fused, and a decoding feature matrix with time sequence relative change feature and absolute change feature of the temperature value of the heating sleeve is expressed, and further, time sequence dynamic change feature of the temperature value of the heating sleeve is fully expressed. And then, further carrying out decoding regression on the decoding characteristic matrix through a decoder to obtain an estimated value decoding value for representing the reaction temperature of the cracking furnace at the current time point. That is, the temperature distribution characteristics of the heating sleeve are used for carrying out decoding regression to obtain an estimated value of the reaction temperature of the cracking furnace, and then an appropriate temperature control strategy is adopted based on the estimated value of the reaction temperature to generate a temperature control instruction. In this way, precise temperature control can be realized through optimization of a software end without changing hardware conditions or using simple hardware conditions.
Particularly, in the technical scheme of the application, when the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix are fused to obtain the decoding feature matrix, the fact that the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix are obtained by feature enhancement of the temperature time sequence feature vector and the temperature fluctuation time sequence feature vector through a Gaussian density chart is considered, random features introduced in the Gaussian discretization process inevitably cause feature enhancement of the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix in opposite directions, so that regression weak correlation distribution examples relative to decoding regression of a decoder exist in the overall feature distribution of the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix respectively, namely, the compatibility of the overall feature distribution of the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix under the decoding regression of the decoder is low, and the fusion effect of the decoding feature matrix on the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix is influenced, and the accuracy of decoding values of the decoding feature matrix is influenced.
Based on this, the helmholtz-like free energy factors of the temperature time series characteristic matrix and the temperature fluctuation time series characteristic matrix are preferably calculated, specifically:
and />
Respectively represent the temperature time sequence characteristic matrix +.>
And the temperature fluctuation time sequence characteristic matrix
Is a classification probability value of>
Is the dimension of the feature matrix, i.e. width times height.
Here, the temperature timing characteristic matrix may be based on the helmholtz free energy formula
And the temperature fluctuation time sequence characteristic matrix +.>
The respective feature value sets describe the energy value of the predetermined regression as the regression free energy of the feature vector as a whole by using it to +.>
And the temperature fluctuation time sequenceFeature matrix->
Weighting is performed to obtain the temperature time sequence characteristic matrix +.>
And the temperature fluctuation time sequence characteristic matrix +.>
Focusing on the distribution of regression-related prototype examples (prototype instance) of features overlapping with the distribution of true examples (groundtruth instance) in the regression target domain so as to be +/in the temperature timing feature matrix>
And the temperature fluctuation time sequence characteristic matrix +.>
And under the condition that the integral feature distribution has regression weak correlation distribution examples, incremental learning is realized by carrying out ambiguity labeling on the integral feature distribution, so that the compatibility of the integral feature distribution under decoding regression is improved, the fusion effect of the decoding feature matrix on the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix is improved, and the accuracy of the decoding value of the decoding feature matrix is improved. Therefore, the reaction temperature of the cracking furnace can be accurately estimated, so that the stable and normal operation of the cracking reaction can be ensured by adopting a corresponding temperature control strategy.
Fig. 1 is an application scenario diagram of an electronic grade hexafluoropropylene cracking temperature control system according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, temperature values (e.g., D illustrated in fig. 1) of heating jackets (e.g., M illustrated in fig. 1) at a plurality of predetermined time points within a predetermined period of time acquired by a temperature sensor (e.g., C illustrated in fig. 1) are acquired, then, the temperature values of the heating jackets at the plurality of predetermined time points are input to a server (e.g., S illustrated in fig. 1) in which an electronic-grade hexafluoropropylene cracking temperature control algorithm is deployed, wherein the server is capable of processing the temperature values of the heating jackets at the plurality of predetermined time points using the electronic-grade hexafluoropropylene cracking temperature control algorithm to obtain decoded values representing an estimated value of a reaction temperature of a cracking furnace at a current time point, and then, based on the decoded values, a temperature control instruction is generated.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Fig. 2 is a block diagram schematic diagram of an electronic grade hexafluoropropylene cracking temperature control system according to an embodiment of the present application. As shown in fig. 2, an electronic grade hexafluoropropylene cracking temperature control system 100 according to an embodiment of the present application includes: a temperature data acquisition module 110 for acquiring temperature values of the heating jacket at a plurality of predetermined time points within a predetermined time period acquired by the temperature sensor; a temperature time sequence distribution module 120, configured to arrange temperature values of the heating jackets at the plurality of predetermined time points into a temperature input vector according to a time dimension; a temperature relative data distribution module 130, configured to calculate a difference between temperature values of every two adjacent positions in the temperature input vector to obtain a temperature fluctuation input vector; the temperature time sequence change feature extraction module 140 is configured to pass the temperature input vector and the temperature fluctuation input vector through the multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector; the data characteristic enhancement module 150 is configured to perform characteristic enhancement on the temperature time sequence characteristic vector and the temperature fluctuation time sequence characteristic vector based on a gaussian density map to obtain a temperature time sequence characteristic matrix and a temperature fluctuation time sequence characteristic matrix; the feature fusion module 160 is configured to fuse the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix to obtain a decoded feature matrix; a reaction temperature estimation module 170, configured to pass the decoding feature matrix through a decoder to obtain a decoded value, where the decoded value is used to represent an estimated value of a reaction temperature of the cracking furnace at a current point in time; and a control module 180 for generating a temperature control instruction based on the decoded value.
More specifically, in the embodiment of the present application, the temperature data acquisition module 110 is configured to acquire temperature values of the heating jacket at a plurality of predetermined time points within a predetermined time period acquired by the temperature sensor. In practice there is an implicit relationship between the temperature of the heated sleeve and the actual reaction temperature in the cracking furnace, and there is also an implicit relationship between the temperature changes between the two. Thus, the estimated value of the reaction temperature of the cracking furnace can be obtained by capturing the temperature distribution characteristics of the heating sleeve and performing decoding regression on the temperature distribution characteristics. Furthermore, an appropriate temperature control strategy is adopted based on the estimated value of the reaction temperature, so that accurate temperature control can be realized through software-side optimization without changing hardware conditions or with simple hardware conditions.
More specifically, in the embodiment of the present application, the temperature timing distribution module 120 is configured to arrange the temperature values of the heating jackets at the plurality of predetermined time points into a temperature input vector according to a time dimension. Since the temperature value of the heating sleeve has a time-series dynamic change rule in the time dimension, in order to accurately capture the time-series change hiding rule, the temperature values of the heating sleeve at a plurality of preset time points need to be arranged as temperature input vectors according to the time dimension so as to integrate the time-series distribution information of the temperature values of the heating sleeve.
More specifically, in the embodiment of the present application, the temperature relative data distribution module 130 is configured to calculate a difference between the temperature values of each two adjacent positions in the temperature input vector to obtain a temperature fluctuation input vector. In order to accurately estimate the reaction temperature value of the cracking furnace, the temperature value of the heating sleeve needs to be fully expressed in the dynamic change characteristic of the time dimension. The time sequence change information of the temperature value of the heating sleeve is weak, the weak change characteristic is small-scale change characteristic information relative to the temperature value of the heating sleeve, and if the time sequence dynamic change characteristic extraction of the temperature value of the heating sleeve is carried out by absolute change information, the small-scale weak change characteristic of the temperature value of the heating sleeve in the time dimension is difficult to be perceived, so that the accuracy of subsequent decoding is affected. Therefore, the time sequence relative change characteristic and the absolute change characteristic of the temperature value of the heating sleeve are adopted to comprehensively extract the dynamic characteristic of the temperature value of the heating sleeve.
More specifically, in the embodiment of the present application, the temperature time sequence variation feature extraction module 140 is configured to pass the temperature input vector and the temperature fluctuation input vector through a multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector, respectively. The time sequence related characteristic information of the heating sleeve has a multi-scale fluctuation related characteristic because the time sequence relative change characteristic and the time sequence absolute change characteristic of the temperature value of the heating sleeve have a related relation with the temperature dynamic time sequence change of the heating sleeve, and because the time sequence relative change information and the time sequence absolute change information of the temperature value of the heating sleeve have different fluctuation change characteristics under different time period spans in the preset time period. Therefore, in order to fully capture the dynamic change rule of the temperature value of the heating sleeve in the time dimension so as to accurately estimate the reaction temperature of the cracking furnace, in the technical scheme of the application, the temperature input vector and the temperature fluctuation input vector are respectively encoded in a multi-scale neighborhood feature extraction module so as to respectively extract dynamic multi-scale neighborhood association features of time sequence relative change information and time sequence absolute change information of the temperature value of the heating sleeve under different time spans, thereby obtaining a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector.
More specifically, in an embodiment of the present application, the multi-scale neighborhood feature extraction module includes a first convolution layer and a second convolution layer in parallel, and a multi-scale feature fusion layer connected to the first convolution layer and the second convolution layer, where the first convolution layer and the second convolution layer use one-dimensional convolution kernels having different scales.
It should be appreciated that convolutional neural network (Convolutional Neural Network, CNN) is an artificial neural network and has wide application in the fields of image recognition and the like. The convolutional neural network may include an input layer, a hidden layer, and an output layer, where the hidden layer may include a convolutional layer, a pooling layer, an activation layer, a full connection layer, etc., where the previous layer performs a corresponding operation according to input data, outputs an operation result to the next layer, and obtains a final result after the input initial data is subjected to a multi-layer operation. The convolutional neural network model has excellent performance in the aspect of image local feature extraction by taking a convolutional kernel as a feature filtering factor, and has stronger feature extraction generalization capability and fitting capability compared with the traditional image feature extraction algorithm based on statistics or feature engineering.
More specifically, in the embodiment of the present application, as shown in fig. 3, the temperature time sequence variation feature extraction module 140 includes: a first scale temperature feature extraction unit 141, configured to perform one-dimensional convolutional encoding on the temperature input vector by using a first convolutional layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature feature vector, where the first convolutional layer has a first one-dimensional convolution kernel with a first length; a second scale temperature feature extraction unit 142, configured to perform one-dimensional convolution encoding on the temperature input vector using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and a temperature multi-scale fusion unit 143, configured to cascade the first-scale temperature feature vector and the second-scale temperature feature vector by using a multi-scale feature fusion layer of the multi-scale neighborhood feature extraction module to obtain the temperature time sequence feature vector.
More specifically, in the embodiment of the present application, the temperature time-series variation feature extraction module 140 further includes: the first scale temperature fluctuation feature extraction unit is used for carrying out one-dimensional convolution encoding on the temperature fluctuation input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature fluctuation feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; a second scale temperature fluctuation feature extraction unit, configured to perform one-dimensional convolutional encoding on the temperature fluctuation input vector by using a second convolutional layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature fluctuation feature vector, where the second convolutional layer has a second one-dimensional convolutional kernel with a second length, and the first length is different from the second length; and the temperature fluctuation multiscale fusion unit is used for cascading the first-scale temperature fluctuation feature vector and the second-scale temperature fluctuation feature vector by using a multiscale feature fusion layer of the multiscale neighborhood feature extraction module so as to obtain the temperature fluctuation time sequence feature vector.
More specifically, in the embodiment of the present application, the data feature enhancement module 150 is configured to perform feature enhancement on the temperature time sequence feature vector and the temperature fluctuation time sequence feature vector based on a gaussian density map to obtain a temperature time sequence feature matrix and a temperature fluctuation time sequence feature matrix. The absolute change amount and the relative fluctuation amount of the temperature value of the heating sleeve are not obvious in the actual detection process, so after the time sequence multi-scale dynamic change characteristics of the absolute change amount and the relative fluctuation amount of the temperature value of the heating sleeve are obtained, the characteristic expression enhancement is expected to be further carried out so as to fully express the time sequence dynamic change characteristics of the temperature value of the heating sleeve.
It should be understood that, as a learning target of the neural network model, the gaussian density map may represent a joint distribution in the case where a plurality of feature values constitute an overall distribution due to probability density thereof, that is, a feature distribution is taken as a priori distribution, and probability density under the influence of correlation with other a priori distribution positions at each a priori distribution position is obtained as a posterior distribution, thereby describing the feature distribution more accurately in a higher dimension.
More specifically, in the embodiment of the present application, the data feature enhancement module 150 is configured to: performing data enhancement on the temperature time sequence feature vector by using a first Gaussian formula to obtain a first Gaussian density diagram; wherein, the first gaussian formula is:
wherein ,/>
Representing the temperature timing feature vector, and +.>
The value of each position of the temperature time sequence characteristic vector represents the variance between the characteristic values of the corresponding two positions; and discretizing the Gaussian distribution of each position of the first Gaussian density map to obtain the temperature time sequence characteristic matrix.
More specifically, in the embodiment of the present application, the data feature enhancement module 150 is further configured to: performing data enhancement on the temperature fluctuation time sequence feature vector by using a second Gaussian formula to obtain a second Gaussian density diagram; wherein, the second gaussian formula is:
wherein ,/>
Representing the temperature fluctuation time sequence characteristic vector, and +.>
The value of each position of the temperature fluctuation time sequence characteristic vector represents the variance between the characteristic values of the corresponding two positions; and discretizing the Gaussian distribution of each position of the second Gaussian density map to obtain the temperature fluctuation time sequence characteristic matrix.
More specifically, in the embodiment of the present application, the feature fusion module 160 is configured to fuse the temperature timing feature matrix and the temperature fluctuation timing feature matrix to obtain a decoded feature matrix. The absolute time sequence multi-scale dynamic change characteristic information of the temperature value of the heating sleeve and the relative time sequence multi-scale dynamic change characteristic information of the temperature value are fused, so that a decoding characteristic matrix with time sequence relative change characteristics and absolute change characteristics of the temperature value of the heating sleeve is expressed, and further the time sequence dynamic change characteristics of the temperature value of the heating sleeve are fully expressed.
More specifically, in the embodiment of the present application, as shown in fig. 4, the feature fusion module 160 includes: an optimization factor calculation unit 161, configured to calculate helmholtz type free energy factors of the temperature timing characteristic matrix and the temperature fluctuation timing characteristic matrix to obtain a first helmholtz type free energy factor and a second helmholtz type free energy factor; a weighted optimization unit 162, configured to weight the temperature timing characteristic matrix and the temperature fluctuation timing characteristic matrix with the first helmholtz class free energy factor and the second helmholtz class free energy factor as weighted weights, so as to obtain an optimized temperature timing characteristic matrix and an optimized temperature fluctuation timing characteristic matrix; and an optimized feature fusion unit 163, configured to fuse the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix to obtain the decoding feature matrix.
Particularly, in the technical scheme of the application, when the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix are fused to obtain the decoding feature matrix, the fact that the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix are obtained by feature enhancement of the temperature time sequence feature vector and the temperature fluctuation time sequence feature vector through a Gaussian density chart is considered, random features introduced in the Gaussian discretization process inevitably cause feature enhancement of the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix in opposite directions, so that regression weak correlation distribution examples relative to decoding regression of a decoder exist in the overall feature distribution of the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix respectively, namely, the compatibility of the overall feature distribution of the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix under the decoding regression of the decoder is low, and the fusion effect of the decoding feature matrix on the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix is influenced, and the accuracy of decoding values of the decoding feature matrix is influenced. Based on this, the helmholtz-like free energy factors of the temperature timing characteristic matrix and the temperature fluctuation timing characteristic matrix are preferably calculated.
More specifically, in the embodiment of the present application, the optimization factor calculating subunit 161 is configured to: calculating the Helmholtz type free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix according to the following optimization formula to obtain the first Helmholtz type free energy factor and the second Helmholtz type free energy factor; wherein, the optimization formula is:
wherein ,/>
Characteristic values representing respective positions in the temperature time series characteristic matrix, +.>
Characteristic values representing respective positions in the temperature fluctuation time sequence characteristic matrix, < >>
and />
Classification probability values respectively representing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix, and +.>
Is the scale of the feature matrix, +.>
Represents a logarithmic function with base 2, +.>
Representing an exponential operation, ++>
and />
Representing the first helmholtz-like free energy factor and the second helmholtz-like free energy factor, respectively.
Here, based on the helmholtz free energy formula, the respective feature value sets of the temperature timing feature matrix and the temperature fluctuation timing feature matrix can be described by the regression free energy of the feature vector ensemble for the energy value of the predetermined regression, by weighting the temperature timing feature matrix and the temperature fluctuation timing feature matrix by the feature value sets, the regression correlation prototype instance (prototype instance) distribution of the feature having the overlapping property between the temperature timing feature matrix and the temperature fluctuation timing feature matrix in the regression target domain and the true instance (groundtruth instance) distribution can be focused, so that incremental learning can be realized by carrying out ambiguity labeling on the overall feature distribution of the temperature timing feature matrix and the temperature fluctuation timing feature matrix under the condition that the regression weak correlation distribution instance exists, thereby improving the compatibility of the overall feature distribution under decoding regression, and improving the fusion effect of the decoding feature matrix on the temperature timing feature matrix and the temperature fluctuation timing feature matrix, thereby improving the accuracy of the decoding value of the decoding feature matrix. Therefore, the reaction temperature of the cracking furnace can be accurately estimated, so that the stable and normal operation of the cracking reaction can be ensured by adopting a corresponding temperature control strategy.
More specifically, in the embodiment of the present application, the optimizing feature fusion unit 163 is configured to: fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix by using the following fusion formula to obtain the decoding feature matrix; wherein, the fusion formula is:
wherein ,/>
Representing the optimized temperature time sequence characteristic matrix, < >>
Representing the optimized temperature fluctuation time sequence characteristic matrix, < >>
Representing the decoding feature matrix,/a>
Representing multiplication by location.
More specifically, in the embodiment of the present application, the reaction temperature estimation module 170 is configured to pass the decoding feature matrix through a decoder to obtain a decoded value, where the decoded value is used to represent an estimated value of the reaction temperature of the cracking furnace at the current time point. That is, the temperature distribution characteristic of the heating sleeve is used for decoding regression to obtain an estimated value of the reaction temperature of the cracking furnace, and an appropriate temperature control strategy can be adopted based on the estimated value of the reaction temperature to generate a temperature control instruction.
More specifically, in the embodiment of the present application, the reaction temperature estimation module 170 is configured to: performing decoding regression on the decoding feature matrix in the following decoding formula by using a plurality of full connection layers of the decoder to obtain the decoding value; wherein, the decoding formula is: 
wherein ,/>
Is the decoding feature matrix,>
is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication.
More specifically, in the embodiment of the present application, the control module 180 is configured to generate a temperature control instruction based on the decoded value.
In summary, the electronic hexafluoropropylene cracking temperature control system 100 according to the embodiment of the present application is illustrated, firstly, temperature values of heating jackets at a plurality of predetermined time points are arranged as temperature input vectors, wherein differences between temperature values of every two adjacent positions are obtained to obtain temperature fluctuation input vectors, then, the temperature input vectors and the temperature fluctuation input vectors are respectively passed through a multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector, then, feature enhancement is performed on the temperature time sequence feature vector and the temperature fluctuation time sequence feature vector based on a gaussian density diagram, so as to obtain a decoding feature matrix, finally, the decoding feature matrix is passed through a decoder to obtain a decoding value for representing an estimated value of a reaction temperature of a cracking furnace at a current time point, and a temperature control instruction is generated based on the decoding value. Thus, the temperature of the cracking reaction can be accurately controlled.
As described above, the electronic grade hexafluoropropylene cracking temperature control system 100 according to the embodiment of the present application may be implemented in various terminal devices, for example, a server or the like having the electronic grade hexafluoropropylene cracking temperature control algorithm according to the embodiment of the present application. In one example, electronic grade hexafluoropropylene cracking temperature control system 100 in accordance with embodiments of the present application may be integrated into a terminal device as a software module and/or hardware module. For example, the electronic grade hexafluoropropylene cracking temperature control system 100 according to the embodiments of the present application may be a software module in the operating system of the terminal device, or may be an application program developed for the terminal device; of course, the electronic grade hexafluoropropylene cracking temperature control system 100 according to the embodiments of the present application may also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the electronic grade hexafluoropropylene cracking temperature control system 100 according to the embodiments of the present application and the terminal device may be separate devices, and the electronic grade hexafluoropropylene cracking temperature control system 100 may be connected to the terminal device through a wired and/or wireless network, and transmit the interactive information according to a agreed data format.
Fig. 5 is a flow chart of a method for controlling the cracking temperature of electronic grade hexafluoropropylene according to an embodiment of the present application. As shown in fig. 5, the method for controlling the cracking temperature of electronic grade hexafluoropropylene according to the embodiment of the present application includes: s110, acquiring temperature values of the heating sleeve at a plurality of preset time points in a preset time period acquired by a temperature sensor; s120, arranging the temperature values of the heating sleeves at a plurality of preset time points into temperature input vectors according to a time dimension; s130, calculating the difference value between the temperature values of every two adjacent positions in the temperature input vector to obtain a temperature fluctuation input vector; s140, the temperature input vector and the temperature fluctuation input vector are respectively passed through a multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector; s150, carrying out characteristic enhancement on the temperature time sequence characteristic vector and the temperature fluctuation time sequence characteristic vector based on a Gaussian density chart to obtain a temperature time sequence characteristic matrix and a temperature fluctuation time sequence characteristic matrix; s160, fusing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix to obtain a decoding feature matrix; s170, the decoding characteristic matrix passes through a decoder to obtain a decoding value, wherein the decoding value is used for representing an estimated value of the reaction temperature of the cracking furnace at the current time point; and S180, generating a temperature control instruction based on the decoded value.
Fig. 6 is a schematic diagram of a system architecture of an electronic grade hexafluoropropylene cracking temperature control method according to an embodiment of the present application. As shown in fig. 6, in the system architecture of the electronic-grade hexafluoropropylene cracking temperature control method, first, temperature values of the heating jacket at a plurality of predetermined time points within a predetermined period of time acquired by a temperature sensor are acquired; then, arranging the temperature values of the heating sleeves at a plurality of preset time points into a temperature input vector according to a time dimension; then, calculating the difference value between the temperature values of every two adjacent positions in the temperature input vector to obtain a temperature fluctuation input vector; then, the temperature input vector and the temperature fluctuation input vector are respectively passed through a multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector; then, carrying out characteristic enhancement on the temperature time sequence characteristic vector and the temperature fluctuation time sequence characteristic vector based on a Gaussian density chart to obtain a temperature time sequence characteristic matrix and a temperature fluctuation time sequence characteristic matrix; then, fusing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix to obtain a decoding feature matrix; then, the decoding characteristic matrix passes through a decoder to obtain a decoding value, wherein the decoding value is used for representing an estimated value of the reaction temperature of the cracking furnace at the current time point; finally, based on the decoded value, a temperature control instruction is generated.
In a specific example, in the electronic-level hexafluoropropylene cracking temperature control method, the multi-scale neighborhood feature extraction module includes a first convolution layer and a second convolution layer in parallel, and a multi-scale feature fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer use one-dimensional convolution kernels with different scales.
In a specific example, in the above electronic-grade hexafluoropropylene cracking temperature control method, the step of passing the temperature input vector and the temperature fluctuation input vector through a multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector includes: performing one-dimensional convolution encoding on the temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale temperature feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; performing one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector, wherein the second convolution layer is provided with a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first scale temperature feature vector and the second scale temperature feature vector by using a multi-scale feature fusion layer of the multi-scale neighborhood feature extraction module to obtain the temperature time sequence feature vector.
In a specific example, in the above electronic-grade hexafluoropropylene cracking temperature control method, performing feature enhancement on the temperature time sequence feature vector and the temperature fluctuation time sequence feature vector based on a gaussian density map to obtain a temperature time sequence feature matrix and a temperature fluctuation time sequence feature matrix, including: performing data enhancement on the temperature time sequence feature vector by using a first Gaussian formula to obtain a first Gaussian density diagram; wherein, the first gaussian formula is:
wherein ,/>
Representing the temperature timing feature vector, and +.>
The value of each position of the temperature time sequence characteristic vector represents the variance between the characteristic values of the corresponding two positions; and discretizing the Gaussian distribution of each position of the first Gaussian density map to obtain the temperature time sequence characteristic matrix.
In a specific example, in the above electronic-grade hexafluoropropylene cracking temperature control method, fusing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix to obtain a decoding feature matrix includes: calculating Helmholtz free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix to obtain a first Helmholtz free energy factor and a second Helmholtz free energy factor; the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix are weighted by taking the first Helmholtz class free energy factor and the second Helmholtz class free energy factor as weighting weights so as to obtain an optimized temperature time sequence characteristic matrix and an optimized temperature fluctuation time sequence characteristic matrix; and fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix to obtain the decoding feature matrix.
In a specific example, in the above electronic-grade hexafluoropropylene cracking temperature control method, calculating the helmholtz class free energy factors of the temperature timing characteristic matrix and the temperature fluctuation timing characteristic matrix to obtain a first helmholtz class free energy factor and a second helmholtz class free energy factor, including: calculating the Helmholtz type free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix according to the following optimization formula to obtain the first Helmholtz type free energy factor and the second Helmholtz type free energy factor; wherein, the optimization formula is:
wherein ,/>
Characteristic values representing respective positions in the temperature time series characteristic matrix, +.>
Characteristic values representing respective positions in the temperature fluctuation time sequence characteristic matrix, < >>
and />
Classification probability values respectively representing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix, and +.>
Is the scale of the feature matrix, +.>
Represents a logarithmic function with base 2, +.>
Representing an exponential operation, ++>
And
representing the first helmholtz-like free energy factor and the second helmholtz-like free energy factor, respectively.
In a specific example, in the above electronic-grade hexafluoropropylene cracking temperature control method, fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix to obtain the decoding feature matrix includes: fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix by using the following fusion formula to obtain the decoding feature matrix; wherein, the fusion formula is:
wherein ,/>
Representing the optimized temperature time sequence characteristic matrix, < >>
Representing the optimized temperature fluctuation time sequence characteristic matrix, < >>
Representing the decoding feature matrix,/a>
Representing multiplication by location.
In a specific example, in the above electronic grade hexafluoropropylene cracking temperature control method, the decoding feature matrix is passed through a decoder to obtain a decoding value, where the decoding value is used to represent an estimated value of a reaction temperature of a cracking furnace at a current time point, and the method includes: performing decoding regression on the decoding feature matrix in the following decoding formula by using a plurality of full connection layers of the decoder to obtain the decoding value; wherein, the decoding formula is:
wherein ,/>
Is the decoding feature matrix, >
Is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described electronic grade hexafluoropropylene cracking temperature control method have been described in detail in the above description of the electronic grade hexafluoropropylene cracking temperature control system 100 with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
According to another aspect of the present application, there is also provided a non-volatile computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a computer, can perform a method as described above.
Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.
All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may load software from one computer device or processor to another. For example: a hardware platform loaded from a server or host computer of the video object detection device to a computer environment, or other computer environment implementing the system, or similar functioning system related to providing information needed for object detection. Thus, another medium capable of carrying software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic, etc., propagating through cable, optical cable, air, etc. Physical media used for carrier waves, such as electrical, wireless, or optical, may also be considered to be software-bearing media. Unless limited to a tangible "storage" medium, other terms used herein to refer to a computer or machine "readable medium" mean any medium that participates in the execution of any instructions by a processor.
This application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (8)
1. An electronic grade hexafluoropropylene cracking temperature control system, comprising: the temperature data acquisition module is used for acquiring temperature values of the heating sleeve at a plurality of preset time points in a preset time period acquired by the temperature sensor; the temperature time sequence distribution module is used for arranging the temperature values of the heating sleeves at a plurality of preset time points into temperature input vectors according to the time dimension; the temperature relative data distribution module is used for calculating the difference value between the temperature values of every two adjacent positions in the temperature input vector to obtain a temperature fluctuation input vector; the temperature time sequence change feature extraction module is used for respectively passing the temperature input vector and the temperature fluctuation input vector through the multi-scale neighborhood feature extraction module to obtain a temperature time sequence feature vector and a temperature fluctuation time sequence feature vector; the data characteristic enhancement module is used for carrying out characteristic enhancement on the temperature time sequence characteristic vector and the temperature fluctuation time sequence characteristic vector based on a Gaussian density chart so as to obtain a temperature time sequence characteristic matrix and a temperature fluctuation time sequence characteristic matrix; the feature fusion module is used for fusing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix to obtain a decoding feature matrix; the reaction temperature estimation module is used for enabling the decoding feature matrix to pass through a decoder to obtain a decoding value, wherein the decoding value is used for representing an estimated value of the reaction temperature of the cracking furnace at the current time point; and a control module for generating a temperature control instruction based on the decoded value.
2. The electronic grade hexafluoropropylene pyrolysis temperature control system of claim 1, wherein the multi-scale neighborhood feature extraction module comprises a first convolution layer and a second convolution layer in parallel, and a multi-scale feature fusion layer connected to the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer use one-dimensional convolution kernels having different scales.
3. The electronic grade hexafluoropropylene cracking temperature control system of claim 2, wherein the temperature time series variation feature extraction module comprises: a first scale temperature feature extraction unit, configured to perform one-dimensional convolutional encoding on the temperature input vector by using a first convolutional layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature feature vector, where the first convolutional layer has a first one-dimensional convolution kernel with a first length; a second scale temperature feature extraction unit, configured to perform one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the temperature multiscale fusion unit is used for cascading the first-scale temperature characteristic vector and the second-scale temperature characteristic vector by using a multiscale characteristic fusion layer of the multiscale neighborhood characteristic extraction module so as to obtain the temperature time sequence characteristic vector.
4. An electronic grade hexafluoropropylene cracking temperature control system as in claim 3, wherein the data characteristic enhancement module is configured to: performing data enhancement on the temperature time sequence feature vector by using a first Gaussian formula to obtain a first Gaussian density diagram; wherein, the first gaussian formula is:
wherein ,/>
Representing the temperature timing feature vector, and +.>
The value of each position of the temperature time sequence characteristic vector represents the variance between the characteristic values of the corresponding two positions; and discretizing the Gaussian distribution of each position of the first Gaussian density map to obtain the temperature time sequence characteristic matrix.
5. The electronic grade hexafluoropropylene cracking temperature control system of claim 4, wherein the feature fusion module comprises: the optimization factor calculation unit is used for calculating the Helmholtz type free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix to obtain a first Helmholtz type free energy factor and a second Helmholtz type free energy factor; the weighting optimization unit is used for weighting the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix by taking the first Helmholtz class free energy factor and the second Helmholtz class free energy factor as weighting weights so as to obtain an optimized temperature time sequence characteristic matrix and an optimized temperature fluctuation time sequence characteristic matrix; and the optimized feature fusion unit is used for fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix to obtain the decoding feature matrix.
6. According to claimThe electronic grade hexafluoropropylene cracking temperature control system of claim 5, wherein the optimization factor calculation subunit is configured to: calculating the Helmholtz type free energy factors of the temperature time sequence characteristic matrix and the temperature fluctuation time sequence characteristic matrix according to the following optimization formula to obtain the first Helmholtz type free energy factor and the second Helmholtz type free energy factor; wherein, the optimization formula is:
wherein ,/>
Characteristic values representing respective positions in the temperature time series characteristic matrix, +.>
Characteristic values representing respective positions in the temperature fluctuation time sequence characteristic matrix, < >>
and />
Classification probability values respectively representing the temperature time sequence feature matrix and the temperature fluctuation time sequence feature matrix, and +.>
Is the scale of the feature matrix and,
represents a logarithmic function with base 2, +.>
Representing an exponential operation, ++>
and />
Representing the first helmholtz-like free energy factor and the second helmholtz-like free energy factor, respectively.
7. The electronic grade hexafluoropropylene cracking temperature control system of claim 6, wherein the optimizing feature fusion unit is configured to: fusing the optimized temperature time sequence feature matrix and the optimized temperature fluctuation time sequence feature matrix by using the following fusion formula to obtain the decoding feature matrix; wherein, the fusion formula is: 
wherein ,
representing the optimized temperature time sequence characteristic matrix, < >>
Representing the optimized temperature fluctuation time sequence characteristic matrix, < >>
Representing the decoding feature matrix,/a>
Representing multiplication by location.
8. The electronic grade hexafluoropropylene pyrolysis temperature control system of claim 7, wherein the reaction temperature estimation module is configured to: performing decoding regression on the decoding feature matrix in the following decoding formula by using a plurality of full connection layers of the decoder to obtain the decoding value; wherein, the decoding formula is:
wherein ,/>
Is the decoding feature matrix,>
is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310313649.8A CN116166072A (en) | 2023-03-28 | 2023-03-28 | Electronic grade hexafluoropropylene cracking temperature control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310313649.8A CN116166072A (en) | 2023-03-28 | 2023-03-28 | Electronic grade hexafluoropropylene cracking temperature control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116166072A true CN116166072A (en) | 2023-05-26 |
Family
ID=86420305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310313649.8A Withdrawn CN116166072A (en) | 2023-03-28 | 2023-03-28 | Electronic grade hexafluoropropylene cracking temperature control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116166072A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116688909A (en) * | 2023-08-01 | 2023-09-05 | 福建省杭氟电子材料有限公司 | Intelligent heating reaction method and system for hexafluoroethane preparation |
| CN116861333A (en) * | 2023-07-11 | 2023-10-10 | 科睿特软件集团股份有限公司 | Intelligent public renting room management system and method thereof |
-
2023
- 2023-03-28 CN CN202310313649.8A patent/CN116166072A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116861333A (en) * | 2023-07-11 | 2023-10-10 | 科睿特软件集团股份有限公司 | Intelligent public renting room management system and method thereof |
| CN116688909A (en) * | 2023-08-01 | 2023-09-05 | 福建省杭氟电子材料有限公司 | Intelligent heating reaction method and system for hexafluoroethane preparation |
| CN116688909B (en) * | 2023-08-01 | 2023-10-27 | 福建省杭氟电子材料有限公司 | Intelligent heating reaction method and system for hexafluoroethane preparation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116166072A (en) | Electronic grade hexafluoropropylene cracking temperature control system | |
| Ping et al. | Degradation feature extraction using multi-source monitoring data via logarithmic normal distribution based variational auto-encoder | |
| CN116025319A (en) | Multi-medium thermal fluid operation monitoring system and method thereof | |
| CN115759658B (en) | Enterprise energy consumption data management system suitable for smart city | |
| CN116036639B (en) | Control system and method for ultrasonic wave induced hexafluorophosphate crystallization | |
| Casteleiro-Roca et al. | Bio-inspired model of ground temperature behavior on the horizontal geothermal exchanger of an installation based on a heat pump | |
| CN116321620B (en) | Intelligent lighting switch control system and method thereof | |
| CN116910611A (en) | Intelligent environment monitoring system and method based on big data | |
| Ribeiro et al. | Towards a deep unified framework for nuclear reactor perturbation analysis | |
| CN116150566A (en) | Ship fuel supply safety monitoring system and method thereof | |
| CN116336400B (en) | Baseline detection method for oil and gas gathering and transportation pipeline | |
| CN116820052B (en) | PBT material production equipment and control method thereof | |
| CN116563302B (en) | Intelligent medical information management system and method thereof | |
| CN116149397B (en) | Temperature self-adaptive control system for electronic grade hydrogen peroxide storage | |
| CN115657265A (en) | Zoom control method and system for lens | |
| Kumar et al. | Single sample face recognition in the last decade: a survey | |
| CN115324843A (en) | Wind generating set fault diagnosis system and method based on monitoring data | |
| Mou et al. | A latent representation dual manifold regularization broad learning system with incremental learning capability for fault diagnosis | |
| CN116624977B (en) | Building automatic control system and method based on artificial intelligence | |
| CN116678258A (en) | Cold-heat exchanger for pressure vessel and control method thereof | |
| CN117134958A (en) | Information processing method and system for network technology service | |
| CN116702028A (en) | Intelligent smelting method and system for industrial silicon | |
| CN116468894A (en) | Distance self-adaptive mask generation method for supervised learning of lithium battery pole piece | |
| CN116188847A (en) | Intelligent processing method and system for military toy model | |
| CN105740815A (en) | Human body behavior identification method based on deep recursive and hierarchical condition random fields |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230526 |
|
| WW01 | Invention patent application withdrawn after publication |