CN113962081B - Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information - Google Patents

Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information Download PDF

Info

Publication number
CN113962081B
CN113962081B CN202111222841.3A CN202111222841A CN113962081B CN 113962081 B CN113962081 B CN 113962081B CN 202111222841 A CN202111222841 A CN 202111222841A CN 113962081 B CN113962081 B CN 113962081B
Authority
CN
China
Prior art keywords
energy consumption
ton
rectifying tower
variance
auxiliary measurement
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111222841.3A
Other languages
Chinese (zh)
Other versions
CN113962081A (en
Inventor
栾小丽
高爽
赵顺毅
倪雨青
刘飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangnan University
Original Assignee
Jiangnan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangnan University filed Critical Jiangnan University
Priority to CN202111222841.3A priority Critical patent/CN113962081B/en
Publication of CN113962081A publication Critical patent/CN113962081A/en
Application granted granted Critical
Publication of CN113962081B publication Critical patent/CN113962081B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P80/00—Climate change mitigation technologies for sector-wide applications
    • Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Air Conditioning Control Device (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method and a system for estimating the energy consumption of a rectifying tower per ton based on auxiliary measurement information, wherein the method comprises the following steps: s1, constructing a single-ton energy consumption state space model of the rectifying tower, and calculating Bayes posterior distribution of introduced reboiler heat load data and auxiliary measurement data by using Bayes state estimation; s2, solving the optimal prediction distribution of the single-ton energy consumption of the rectifying tower; s3, updating the corrected predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower; s4, updating the modal probability; and S5, fusing the updated mean value and variance with the modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the single-ton energy consumption of the rectifying tower to be estimated. According to the method for estimating the energy consumption of the single ton of the rectifying tower based on the auxiliary measurement information, the auxiliary measurement distribution with higher value is fully utilized from the Bayesian state estimation angle by means of high-quality auxiliary measurement data, and the accuracy of estimating the energy consumption of the single ton of the rectifying tower is greatly improved.

Description

Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information
Technical Field
The invention relates to the technical field of signal processing of system engineering, in particular to a rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information.
Background
The rectifying tower in the petrochemical industry is important energy consumption equipment which can not replace strategic materials in the country, and the key for realizing energy conservation and emission reduction of the manufacturing industry is to realize the energy conservation of the important energy consumption equipment. The single-ton energy consumption of the rectifying tower can only be obtained after the production process is finished, and online detection is difficult, so that how to estimate the single-ton energy consumption of the rectifying tower by a state estimation means is particularly important on the basis of the existing detection information. The existing state estimation methods are various, from Bayesian state estimation, Kalman state estimation and finite pulse state estimation, a lot of excellent results are produced, and the method plays a role which cannot be ignored by people in various industries.
In recent years, in order to obtain a more accurate estimated value of the energy consumption of a single ton of a rectifying tower, various fusion strategies are proposed in succession, wherein a track to track method utilizes correlation to fuse the estimated values of the energy consumption estimators of the single ton of different rectifying towers, and is widely applied to the fusion field. Later, various extended fusion estimation methods were proposed in succession. Although the various fusion strategies proposed can improve the accuracy of the energy consumption estimation by means of additional information, the essence is the compromise and weighting of the estimation results, i.e. the utilization of the additional information does not change the essential structure of the single-ton energy consumption estimator, thereby resulting in lower accuracy of the single-ton energy consumption estimation.
Disclosure of Invention
The invention aims to provide a rectifying tower single-ton energy consumption estimation method and a rectifying tower single-ton energy consumption estimation system based on auxiliary measurement information, which improve the rectifying tower single-ton energy consumption estimation precision by means of auxiliary measurement data.
In order to solve the above problems, the present invention provides a method for estimating energy consumption per ton of a rectifying tower based on auxiliary measurement information, which comprises the following steps:
s1, constructing a single-ton energy consumption state space model of the rectifying tower, and calculating Bayes posterior distribution of introduced reboiler heat load data and auxiliary measurement data by utilizing Bayes state estimation based on the constructed single-ton energy consumption state space model of the rectifying tower;
s2, calculating objective similarity between Bayes posterior distribution of reboiler heat load data and auxiliary measurement data and ideal Bayes posterior distribution by using similarity measurement, and solving optimal rectification tower single-ton energy consumption prediction distribution with the objective similarity as a maximum target;
s3, carrying out mixed interaction on the mean value and the variance of the single-ton energy consumption of the rectifying tower, calculating the predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower after the mixed interaction, correcting the predicted values, and updating the corrected predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower;
s4, calculating posterior distribution of the modes by using a Bayesian formula to update the mode probability;
and S5, fusing the updated mean value and variance with the modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the single-ton energy consumption of the rectifying tower to be estimated.
As a further improvement of the method, the mixed interaction of the mean value and the variance of the single-ton energy consumption of the rectifying tower is solved by adopting an interactive multi-model method, an n-order generalized pseudo-Bayes algorithm or a variable structure multi-model algorithm.
As a further improvement of the present invention, the objective similarity is a distance measure, a similarity measure or a matching measure.
As a further improvement of the present invention, in step S1, the single-ton energy consumption state space model of the rectifying tower is constructed as follows:
xk＝F(rk)xk-1+G(rk)wk,
Figure BDA0003313261950000021
Figure BDA0003313261950000022
in the formula (I), the compound is shown in the specification,
Figure BDA0003313261950000023
the energy consumption per ton of the rectifying tower is variable,
Figure BDA0003313261950000024
and
Figure BDA0003313261950000025
respectively representing reboiler heat duty data and auxiliary measurement data, defining
Figure BDA0003313261950000026
And
Figure BDA0003313261950000027
respectively representing a reboiler heat duty sequence set and an auxiliary measurement sequence set, rkA discrete homogeneous Markov chain representing values in a finite space M {1,2, …, M }, for any i, j ∈ M transition probability defined as
Figure BDA0003313261950000028
F(rk),G(rk) And H (r)k) Is represented by rkCorrelated model matrix, noise term wk～N(wk；0,Qk)，
Figure BDA0003313261950000029
And
Figure BDA00033132619500000210
is independent and identically distributed Gaussian noise, QkIn order to be the process noise variance,
Figure BDA00033132619500000211
and
Figure BDA00033132619500000212
are divided into reboiler heat duty noise variance and auxiliary measurement variance, respectively, assuming an initial distribution of
Figure BDA00033132619500000213
Wherein
Figure BDA00033132619500000214
Represents a mean value of
Figure BDA00033132619500000215
A Gaussian distribution with variance P, defined for symbolic simplification
Figure BDA00033132619500000216
Is rkThe (j) th modality of (a),
Figure BDA00033132619500000217
and
Figure BDA00033132619500000218
as a further improvement of the present invention, a bayesian posterior distribution is calculated using bayesian state estimation, including reboiler heat load data and aiding measurement data, as follows:
Figure BDA0003313261950000031
in the formula
Figure BDA0003313261950000032
Representing the total set of reboiler heat duty sequences and auxiliary measurement sequences.
As a further improvement of the present invention, in step S2, the ideal bayesian posterior distribution is as follows:
Figure BDA0003313261950000033
wherein
Figure BDA0003313261950000034
In order to be a likelihood distribution,
Figure BDA0003313261950000035
for the single ton energy consumption of the rectifying towerMeasuring distribution;
bayesian posterior distribution of the introduced reboiler heat duty data and ancillary measurement data is as follows:
Figure BDA0003313261950000036
wherein
Figure BDA0003313261950000037
Defined as the likelihood distribution after introduction of the helper data,
Figure BDA0003313261950000038
the method comprises the following steps of (1) predicting distribution of single-ton energy consumption of a rectifying tower needing to be optimized and solved after auxiliary data is introduced;
using the similarity measure, calculating an objective similarity between the bayesian posterior distribution of the introduced reboiler heat load data and the auxiliary measurement data and the ideal bayesian posterior distribution as follows:
Figure BDA0003313261950000039
and solving the optimal single-ton energy consumption prediction distribution of the rectifying tower by taking the objective similarity as the maximum target as follows:
Figure BDA00033132619500000310
wherein exp (. cndot.) represents an exponential function, Ef(·)[g(·)]Representing the expectation of computing the g (-) distribution with respect to the f (-) distribution.
As a further improvement of the present invention, step S3 includes:
s31, solving the mixed interaction of the mean value and the variance of the single-ton energy consumption of the rectifying tower:
Figure BDA00033132619500000311
Figure BDA00033132619500000312
in which the symbol (…) represents the same term, π, as the preceding termijRepresenting the probability of a transition from modality i at time k-1 to modality j at time k,
Figure BDA0003313261950000041
the probability of the ith mode at time k-1,
Figure BDA0003313261950000042
for the predicted probability of the modality j,
Figure BDA0003313261950000043
is the average value of the energy consumption of a single ton of the rectifying tower in the ith mode at the moment of k-1,
Figure BDA0003313261950000044
the energy consumption of a single ton of the mixed rectifying tower in the j mode after mixed interaction is the average value,
Figure BDA0003313261950000045
is the variance of the single ton energy consumption of the rectifying tower under the ith mode at the moment of k-1,
Figure BDA0003313261950000046
the energy consumption variance of the mixed rectifying tower in the j mode after mixed interaction is single ton;
s32, calculating the predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower according to the prediction step formula:
Figure BDA0003313261950000047
Figure BDA0003313261950000048
s33, correcting the predicted value according to the solved predicted distribution of the single-ton energy consumption of the optimal rectifying tower:
Figure BDA0003313261950000049
Figure BDA00033132619500000410
wherein
Figure BDA00033132619500000411
In order to obtain an estimate using the secondary measurement data,
Figure BDA00033132619500000412
s34, updating the corrected predicted value of the energy consumption of the rectifying tower per ton by using the following formula:
Figure BDA00033132619500000413
Figure BDA00033132619500000414
wherein
Figure BDA00033132619500000415
As a further improvement of the present invention, step S4 includes:
and calculating the Bayesian posterior distribution of the modes by using a Bayesian formula:
Figure BDA00033132619500000416
wherein
Figure BDA00033132619500000417
As a further improvement of the present invention, in step S5, the final estimated mean and variance of the energy consumption per ton of the rectifying tower are as follows:
Figure BDA00033132619500000418
Figure BDA0003313261950000051
wherein
Figure BDA0003313261950000052
For the final estimated mean value of energy consumption per ton of rectifying tower, PkRepresenting the final estimated energy consumption variance of the rectifying tower per ton.
The invention also provides a rectification tower single-ton energy consumption estimation system based on auxiliary measurement information, which comprises the following steps:
the model building module is used for building a single-ton energy consumption state space model of the rectifying tower, and based on the built single-ton energy consumption state space model of the rectifying tower, Bayesian posterior distribution of introduced reboiler heat load data and auxiliary measurement data is calculated by utilizing Bayesian state estimation;
the optimal rectification tower single-ton energy consumption prediction distribution solving module is used for calculating objective similarity between Bayesian posterior distribution introducing reboiler heat load data and auxiliary measurement data and ideal Bayesian posterior distribution by utilizing similarity measurement, and solving optimal rectification tower single-ton energy consumption prediction distribution by taking the objective similarity as a maximum target;
the predicted value updating module is used for carrying out mixed interaction on the mean value and the variance of the single-ton energy consumption of the rectifying tower, calculating the predicted value of the mean value and the variance of the single-ton energy consumption of the rectifying tower after mixed interaction, correcting the predicted value and updating the corrected predicted value of the mean value and the variance of the single-ton energy consumption of the rectifying tower;
the modal probability updating module is used for calculating posterior distribution of the modal by utilizing a Bayesian formula so as to update the modal probability;
and the rectifying tower single-ton energy consumption estimation result output module is used for fusing the updated mean value and variance and modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the rectifying tower single-ton energy consumption to be estimated.
The invention has the beneficial effects that:
according to the method and the system for estimating the single-ton energy consumption of the rectifying tower based on the auxiliary measurement information, the valuable auxiliary measurement distribution is fully utilized from the Bayesian state estimation angle by means of high-quality auxiliary measurement data, and the accuracy of estimating the single-ton energy consumption of the rectifying tower is greatly improved.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a method for estimating the energy consumption of a rectifying tower per ton based on auxiliary measurement information according to a preferred embodiment of the present invention;
fig. 2 is a diagram of the root mean square error for different estimation methods.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
As shown in fig. 1, the method for estimating the energy consumption of a rectifying tower per ton based on auxiliary measurement information in the preferred embodiment of the present invention includes the following steps:
s1, constructing a single-ton energy consumption state space model of the rectifying tower, and calculating Bayes posterior distribution of introduced reboiler heat load data and auxiliary measurement data by utilizing Bayes state estimation based on the constructed single-ton energy consumption state space model of the rectifying tower;
optionally, the constructed single-ton energy consumption state space model of the rectifying tower can be a linear (non-linear) time invariant system or a random multi-modal system.
Specifically, the reboiler heat load data is a reboiler heat load value obtained by using the output of the model, and the auxiliary measurement data is accurate heat load data calculated according to the flow rate of the heat transfer oil, the temperature difference between an inlet and an outlet, and the like.
Optionally, the constructed single-ton energy consumption state space model of the rectifying tower is as follows:
xk＝F(rk)xk-1+G(rk)wk,
Figure BDA0003313261950000061
Figure BDA0003313261950000062
in the formula (I), the compound is shown in the specification,
Figure BDA0003313261950000063
the energy consumption per ton of the rectifying tower is variable,
Figure BDA0003313261950000064
and
Figure BDA0003313261950000065
respectively representing reboiler heat duty data and auxiliary measurement data, defining
Figure BDA0003313261950000066
And
Figure BDA0003313261950000067
respectively representing a reboiler heat duty sequence set and an auxiliary measurement sequence set, rkA discrete homogeneous Markov chain representing values in a finite space M {1,2, …, M }, for any i, j ∈ M transition probability defined as
Figure BDA0003313261950000068
F(rk),G(rk) And H (r)k) Is represented by rkCorrelated model matrix, noise term wk～N(wk；0,Qk)，
Figure BDA0003313261950000069
And
Figure BDA0003313261950000071
is independent and identically distributed Gaussian noise, QkIn order to be the process noise variance,
Figure BDA0003313261950000072
and
Figure BDA0003313261950000073
are divided into reboiler heat duty noise variance and auxiliary measurement variance, respectively, assuming an initial distribution of
Figure BDA0003313261950000074
Wherein
Figure BDA0003313261950000075
Represents a mean value of
Figure BDA0003313261950000076
A Gaussian distribution with variance P, defined for symbolic simplification
Figure BDA0003313261950000077
Is rkThe (j) th modality of (a),
Figure BDA0003313261950000078
and
Figure BDA0003313261950000079
further, a bayesian posterior distribution including reboiler heat load data and auxiliary measurement data is calculated using bayesian state estimation as follows:
Figure BDA00033132619500000710
in the formula
Figure BDA00033132619500000711
Representing the total set of reboiler heat duty sequences and auxiliary measurement sequences.
S2, calculating objective similarity between Bayes posterior distribution of reboiler heat load data and auxiliary measurement data and ideal Bayes posterior distribution by using similarity measurement, and solving optimal rectification tower single-ton energy consumption prediction distribution with the objective similarity as a maximum target;
optionally, the objective similarity is a distance measure, a similarity measure or a matching measure.
The similarity measurement is to calculate the distance between the ideal Bayesian posterior distribution and the Bayesian posterior distribution with the introduced auxiliary data, and can be measured by using distance measures such as Euclidean distance, absolute value distance, Mahalanobis distance, KL divergence and JS divergence; similarity measures such as angle similarity coefficients, correlation coefficients, exponential similarity coefficients, Pearson coefficients; matching measures such as Tanimoto measures, Rao measures, simple matching coefficients, Dice coefficients, Kulzinsky coefficients may also be used.
Optionally, the ideal bayesian posterior distribution is as follows:
Figure BDA00033132619500000712
wherein
Figure BDA00033132619500000713
In order to be a likelihood distribution,
Figure BDA00033132619500000714
the distribution of the single ton energy consumption of the rectifying tower is predicted;
bayesian posterior distribution of the introduced reboiler heat duty data and ancillary measurement data is as follows:
Figure BDA00033132619500000715
wherein
Figure BDA00033132619500000716
Defined as the likelihood distribution after introduction of the helper data,
Figure BDA00033132619500000717
the method comprises the following steps of (1) predicting distribution of single-ton energy consumption of a rectifying tower needing to be optimized and solved after auxiliary data is introduced;
using the similarity measure, calculating an objective similarity between the bayesian posterior distribution of the introduced reboiler heat load data and the auxiliary measurement data and the ideal bayesian posterior distribution as follows:
Figure BDA0003313261950000081
and solving the optimal single-ton energy consumption prediction distribution of the rectifying tower by taking the objective similarity as the maximum target as follows:
Figure BDA0003313261950000082
wherein exp (. cndot.) represents an exponential function, Ef(·)[g(·)]Representing the expectation of computing the g (-) distribution with respect to the f (-) distribution.
S3, carrying out mixed interaction on the mean value and the variance of the single-ton energy consumption of the rectifying tower, calculating the predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower after the mixed interaction, correcting the predicted values, and updating the corrected predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower;
optionally, the mixed interaction of the mean value and the variance of the energy consumption of a single ton of the rectifying tower can be solved by using an interactive multi-model method, an n-order generalized pseudo-bayes algorithm or a variable structure multi-model algorithm and the like.
Illustratively, the prediction and updating of the mean and variance may be by kalman filtering, maximum likelihood, maximum prior, particle filtering, distributed kalman filtering, distributed particle filtering, or covariance consistency.
Optionally, step S3 includes:
s31, solving the mixed interaction of the mean value and the variance of the single-ton energy consumption of the rectifying tower:
Figure BDA0003313261950000083
Figure BDA0003313261950000084
in which the symbol (…) represents the same term, π, as the preceding termijRepresenting the probability of a transition from modality i at time k-1 to modality j at time k,
Figure BDA0003313261950000085
the probability of the ith mode at time k-1,
Figure BDA0003313261950000086
for the predicted probability of the modality j,
Figure BDA0003313261950000087
is the average value of the energy consumption of a single ton of the rectifying tower in the ith mode at the moment of k-1,
Figure BDA0003313261950000088
the energy consumption of a single ton of the mixed rectifying tower in the j mode after mixed interaction is the average value,
Figure BDA0003313261950000089
is the variance of the single ton energy consumption of the rectifying tower under the ith mode at the moment of k-1,
Figure BDA00033132619500000810
the energy consumption variance of the mixed rectifying tower in the j mode after mixed interaction is single ton;
s32, calculating the predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower according to the prediction step formula:
Figure BDA00033132619500000811
Figure BDA0003313261950000091
s33, correcting the predicted value according to the solved predicted distribution of the single-ton energy consumption of the optimal rectifying tower:
Figure BDA0003313261950000092
Figure BDA0003313261950000093
wherein
Figure BDA0003313261950000094
In order to obtain an estimate using the secondary measurement data,
Figure BDA0003313261950000095
s34, updating the corrected predicted value of the energy consumption of the rectifying tower per ton by using the following formula:
Figure BDA0003313261950000096
Figure BDA0003313261950000097
wherein
Figure BDA0003313261950000098
S4, calculating posterior distribution of the modes by using a Bayesian formula to update the mode probability;
optionally, step S4 includes:
and calculating the Bayesian posterior distribution of the modes by using a Bayesian formula:
Figure BDA0003313261950000099
wherein
Figure BDA00033132619500000910
And S5, fusing the updated mean value and variance with the modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the single-ton energy consumption of the rectifying tower to be estimated.
Optionally, the final estimated mean and variance of the energy consumption per ton of the rectifying tower are as follows:
Figure BDA00033132619500000911
Figure BDA00033132619500000912
wherein
Figure BDA00033132619500000913
For the final estimated mean value of energy consumption per ton of rectifying tower, PkRepresenting the final estimated energy consumption variance of the rectifying tower per ton.
As shown in fig. 2, the sampling time is 1 second, and the initial values of the energy consumption variables of the rectifying tower per ton are set to be 100 respectively. The traditional method a is an interactive multi-model algorithm without auxiliary measurement information, the traditional method b is a variable-structure interactive multi-model algorithm, and the traditional method c is an interactive multi-model fusion algorithm. By comparing the root mean square errors of different estimation methods, the method for estimating the energy consumption of the single ton of the rectifying tower based on the auxiliary measurement information has smaller error and higher precision.
The preferred embodiment of the present invention also discloses a rectification tower single-ton energy consumption estimation system based on auxiliary measurement information, which comprises:
the model building module is used for building a single-ton energy consumption state space model of the rectifying tower, and based on the built single-ton energy consumption state space model of the rectifying tower, Bayesian posterior distribution of introduced reboiler heat load data and auxiliary measurement data is calculated by utilizing Bayesian state estimation;
the optimal rectification tower single-ton energy consumption prediction distribution solving module is used for calculating objective similarity between Bayesian posterior distribution introducing reboiler heat load data and auxiliary measurement data and ideal Bayesian posterior distribution by utilizing similarity measurement, and solving optimal rectification tower single-ton energy consumption prediction distribution by taking the objective similarity as a maximum target;
the predicted value updating module is used for carrying out mixed interaction on the mean value and the variance of the single-ton energy consumption of the rectifying tower, calculating the predicted value of the mean value and the variance of the single-ton energy consumption of the rectifying tower after the mixed interaction, correcting the predicted value and updating the corrected predicted value of the mean value and the variance of the single-ton energy consumption of the rectifying tower;
the modal probability updating module is used for calculating posterior distribution of the modal by utilizing a Bayesian formula so as to update the modal probability;
and the rectifying tower single-ton energy consumption estimation result output module is used for fusing the updated mean value and variance and modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the rectifying tower single-ton energy consumption to be estimated.
The rectifying tower single-ton energy consumption estimation system based on the auxiliary measurement information in the embodiment of the invention is used for realizing the rectifying tower single-ton energy consumption estimation method based on the auxiliary measurement information, so the specific implementation of the system can be seen in the embodiment of the rectifying tower single-ton energy consumption estimation method based on the auxiliary measurement information in the foregoing, and therefore, the specific implementation can refer to the description of the corresponding partial embodiments, and the description is not repeated here.
In addition, since the system for estimating energy consumption of a single ton of a rectifying tower based on auxiliary measurement information of this embodiment is used to implement the method for estimating energy consumption of a single ton of a rectifying tower based on auxiliary measurement information, the function corresponds to the function of the method, and details are not described here.
According to the method and the system for estimating the single-ton energy consumption of the rectifying tower based on the auxiliary measurement information, the valuable auxiliary measurement distribution is fully utilized from the Bayesian state estimation angle by means of high-quality auxiliary measurement data, and the accuracy of estimating the single-ton energy consumption of the rectifying tower is greatly improved.
The above embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.

Claims (8)

1. A rectifying tower single-ton energy consumption estimation method based on auxiliary measurement information is characterized by comprising the following steps:
s1, constructing a single-ton energy consumption state space model of the rectifying tower, and calculating Bayes posterior distribution of introduced reboiler heat load data and auxiliary measurement data by utilizing Bayes state estimation based on the constructed single-ton energy consumption state space model of the rectifying tower;
s2, calculating objective similarity between Bayes posterior distribution of reboiler heat load data and auxiliary measurement data and ideal Bayes posterior distribution by using similarity measurement, and solving optimal rectification tower single-ton energy consumption prediction distribution with the objective similarity as a maximum target;
s3, carrying out mixed interaction on the mean value and the variance of the single-ton energy consumption of the rectifying tower, calculating the predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower after the mixed interaction, correcting the predicted values, and updating the corrected predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower;
s4, calculating posterior distribution of the modes by using a Bayesian formula to update the mode probability;
s5, fusing the updated mean value and variance with the modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the single-ton energy consumption of the rectifying tower to be estimated;
the constructed single-ton energy consumption state space model of the rectifying tower is as follows:
xk＝F(rk)xk-1+G(rk)wk,
Figure FDA0003601973230000011
Figure FDA0003601973230000012
in the formula (I), the compound is shown in the specification,
Figure FDA0003601973230000013
the energy consumption per ton of the rectifying tower is variable,
Figure FDA0003601973230000014
and
Figure FDA0003601973230000015
respectively representing reboiler heat duty data and auxiliary measurement data, defining
Figure FDA0003601973230000016
And
Figure FDA0003601973230000017
respectively represents a reboiler heat duty sequence set and an auxiliary measurement sequence set, rkRepresented in a finite space
Figure FDA0003601973230000018
Discrete homogeneous Markov chains of medium value, for arbitrary
Figure FDA0003601973230000019
The transition probability is defined as
Figure FDA00036019732300000110
F(rk),G(rk) And H (r)k) Is represented by rkCorrelated model matrix, noise term
Figure FDA00036019732300000111
Figure FDA00036019732300000112
And
Figure FDA00036019732300000113
is independent and identically distributed Gaussian noise, QkIn order to be the process noise variance,
Figure FDA00036019732300000114
and
Figure FDA00036019732300000115
are divided into reboiler heat duty noise variance and auxiliary measurement variance, respectively, assuming an initial distribution of
Figure FDA00036019732300000116
Wherein
Figure FDA00036019732300000117
Represents a mean value of
Figure FDA00036019732300000118
A Gaussian distribution with variance P, defined for symbolic simplification
Figure FDA00036019732300000119
Is rkThe (j) th modality of (a),
Figure FDA00036019732300000120
and
Figure FDA00036019732300000121
a bayesian posterior distribution including reboiler heat load data and auxiliary measurement data is calculated using bayesian state estimation as follows:
Figure FDA0003601973230000021
in the formula
Figure FDA0003601973230000022
Representing the total set of reboiler heat duty sequences and auxiliary measurement sequences.
2. The method for estimating the energy consumption of a single ton of a rectifying tower based on auxiliary measurement information as claimed in claim 1, wherein a mixed interaction of a mean value and a variance of the energy consumption of the single ton of the rectifying tower is solved by adopting an interactive multi-model method, an n-order generalized pseudo-Bayesian algorithm or a variable structure multi-model algorithm.
3. The method as claimed in claim 1, wherein the objective similarity is a distance measure, a similarity measure or a matching measure.
4. The method as claimed in claim 1, wherein in step S2, the ideal bayesian posterior distribution is as follows:
Figure FDA0003601973230000023
wherein
Figure FDA0003601973230000024
In order to be a likelihood distribution,
Figure FDA0003601973230000025
for predicting the single-ton energy consumption of the rectifying towerDistributing;
the bayesian posterior distribution of the reboiler heat duty data and the auxiliary measurement data was introduced as follows:
Figure FDA0003601973230000026
wherein
Figure FDA0003601973230000027
Defined as the likelihood distribution after introduction of the helper data,
Figure FDA0003601973230000028
the method comprises the following steps of (1) predicting distribution of single-ton energy consumption of a rectifying tower needing to be optimized and solved after auxiliary data is introduced;
using the similarity measure, calculating an objective similarity between the bayesian posterior distribution of the introduced reboiler heat load data and the auxiliary measurement data and the ideal bayesian posterior distribution as follows:
Figure FDA0003601973230000029
and solving the optimal single-ton energy consumption prediction distribution of the rectifying tower by taking the objective similarity as the maximum target as follows:
Figure FDA00036019732300000210
where exp (-) represents an exponential function,
Figure FDA00036019732300000211
representing the expectation of computing the g (-) distribution with respect to the f (-) distribution.
5. The method for estimating energy consumption per ton of a rectifying tower based on auxiliary measurement information as claimed in claim 4, wherein the step S3 comprises:
s31, solving the mixed interaction of the mean value and the variance of the single-ton energy consumption of the rectifying tower:
Figure FDA0003601973230000031
Figure FDA0003601973230000032
where the symbol () represents the same term, pi, as the previous oneijRepresenting the probability of a transition from modality i at time k-1 to modality j at time k,
Figure FDA0003601973230000033
the probability of the ith mode at time k-1,
Figure FDA0003601973230000034
for the predicted probability of the modality j,
Figure FDA0003601973230000035
is the average value of the energy consumption of a single ton of the rectifying tower in the ith mode at the moment of k-1,
Figure FDA0003601973230000036
the energy consumption of a single ton of the mixed rectifying tower in the j mode after mixed interaction is the average value,
Figure FDA0003601973230000037
is the variance of the single ton energy consumption of the rectifying tower under the ith mode at the moment of k-1,
Figure FDA0003601973230000038
the energy consumption variance of the mixed rectifying tower in the j mode after mixed interaction is single ton;
s32, calculating the predicted values of the mean value and the variance of the single-ton energy consumption of the rectifying tower according to the prediction step formula:
Figure FDA0003601973230000039
Figure FDA00036019732300000310
s33, correcting the predicted value according to the solved predicted distribution of the single-ton energy consumption of the optimal rectifying tower:
Figure FDA00036019732300000311
Figure FDA00036019732300000312
wherein
Figure FDA00036019732300000313
In order to obtain an estimate using the secondary measurement data,
Figure FDA00036019732300000314
s34, updating the corrected predicted value of the energy consumption of the rectifying tower per ton by using the following formula:
Figure FDA00036019732300000315
Figure FDA00036019732300000316
wherein
Figure FDA00036019732300000317
6. The method for estimating energy consumption per ton of a rectifying tower based on auxiliary measurement information as claimed in claim 5, wherein the step S4 comprises:
and calculating the Bayesian posterior distribution of the modes by using a Bayesian formula:
Figure FDA0003601973230000041
wherein
Figure FDA0003601973230000042
7. The method as claimed in claim 6, wherein the mean and variance of the final estimated energy consumption per ton of the distillation tower are as follows in step S5:
Figure FDA0003601973230000043
Figure FDA0003601973230000044
wherein
Figure FDA0003601973230000045
For the final estimated mean value of energy consumption per ton of rectifying tower, PkRepresenting the final estimated energy consumption variance of the rectifying tower per ton.
8. A rectifying tower single-ton energy consumption estimation system based on auxiliary measurement information is characterized by comprising:
the model building module is used for building a single-ton energy consumption state space model of the rectifying tower, and based on the built single-ton energy consumption state space model of the rectifying tower, Bayesian posterior distribution of introduced reboiler heat load data and auxiliary measurement data is calculated by utilizing Bayesian state estimation;
the optimal rectification tower single-ton energy consumption prediction distribution solving module is used for calculating objective similarity between Bayesian posterior distribution introducing reboiler heat load data and auxiliary measurement data and ideal Bayesian posterior distribution by utilizing similarity measurement, and solving optimal rectification tower single-ton energy consumption prediction distribution by taking the objective similarity as a target;
the predicted value updating module is used for carrying out mixed interaction on the mean value and the variance of the single-ton energy consumption of the rectifying tower, calculating the predicted value of the mean value and the variance of the single-ton energy consumption of the rectifying tower after mixed interaction, correcting the predicted value and updating the corrected predicted value of the mean value and the variance of the single-ton energy consumption of the rectifying tower;
the modal probability updating module is used for calculating posterior distribution of the modal by utilizing a Bayesian formula so as to update the modal probability;
the rectification tower single-ton energy consumption estimation result output module is used for fusing the updated mean value, variance and modal probability to obtain a final Bayesian estimation value, namely the mean value and variance of the rectification tower single-ton energy consumption to be estimated;
the constructed single-ton energy consumption state space model of the rectifying tower is as follows:
xk＝F(rk)xk-1+G(rk)wk,
Figure FDA0003601973230000051
Figure FDA0003601973230000052
in the formula (I), the compound is shown in the specification,
Figure FDA0003601973230000053
the energy consumption per ton of the rectifying tower is variable,
Figure FDA0003601973230000054
and
Figure FDA0003601973230000055
representing reboiler Heat load data and auxiliary measurement data, respectively, definition
Figure FDA0003601973230000056
And
Figure FDA0003601973230000057
respectively representing a reboiler heat duty sequence set and an auxiliary measurement sequence set, rkRepresented in a finite space
Figure FDA0003601973230000058
Discrete homogeneous Markov chains of medium value, for arbitrary
Figure FDA0003601973230000059
The transition probability is defined as
Figure FDA00036019732300000510
F(rk),G(rk) And H (r)k) Is represented by rkCorrelated model matrix, noise term
Figure FDA00036019732300000511
Figure FDA00036019732300000512
And
Figure FDA00036019732300000513
is independent and identically distributed Gaussian noise, QkIn order to be the process noise variance,
Figure FDA00036019732300000514
and
Figure FDA00036019732300000515
divided into reboiler heat duty noise variance and auxiliary measurement variance, assuming initial distribution as
Figure FDA00036019732300000516
Wherein
Figure FDA00036019732300000517
Represents a mean value of
Figure FDA00036019732300000518
A Gaussian distribution with variance P, defined for symbolic simplification
Figure FDA00036019732300000519
Is rkThe (j) th modality of (a),
Figure FDA00036019732300000520
and
Figure FDA00036019732300000521
a bayesian posterior distribution including reboiler heat load data and auxiliary measurement data is calculated using bayesian state estimation as follows:
Figure FDA00036019732300000522
in the formula
Figure FDA00036019732300000523
Representing the total set of reboiler heat duty sequences and auxiliary measurement sequences.
CN202111222841.3A 2021-10-20 2021-10-20 Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information Active CN113962081B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111222841.3A CN113962081B (en) 2021-10-20 2021-10-20 Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111222841.3A CN113962081B (en) 2021-10-20 2021-10-20 Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information

Publications (2)

Publication Number Publication Date
CN113962081A CN113962081A (en) 2022-01-21
CN113962081B true CN113962081B (en) 2022-05-31

Family

ID=79465024

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111222841.3A Active CN113962081B (en) 2021-10-20 2021-10-20 Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information

Country Status (1)

Country Link
CN (1) CN113962081B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115169721B (en) * 2022-07-25 2023-07-04 江南大学 Method and system for predicting single ton energy consumption in rectification process based on migration identification

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108804784A (en) * 2018-05-25 2018-11-13 江南大学 A kind of instant learning soft-measuring modeling method based on Bayes's gauss hybrid models
CN112116138A (en) * 2020-09-09 2020-12-22 山东科技大学 Power system prediction state estimation method and system based on data driving
CN112562797A (en) * 2020-11-30 2021-03-26 中南大学 Method and system for predicting outlet ions in iron precipitation process

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7289906B2 (en) * 2004-04-05 2007-10-30 Oregon Health & Science University Navigation system applications of sigma-point Kalman filters for nonlinear estimation and sensor fusion
US11966840B2 (en) * 2019-08-15 2024-04-23 Noodle Analytics, Inc. Deep probabilistic decision machines

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108804784A (en) * 2018-05-25 2018-11-13 江南大学 A kind of instant learning soft-measuring modeling method based on Bayes's gauss hybrid models
CN112116138A (en) * 2020-09-09 2020-12-22 山东科技大学 Power system prediction state estimation method and system based on data driving
CN112562797A (en) * 2020-11-30 2021-03-26 中南大学 Method and system for predicting outlet ions in iron precipitation process

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
Intelligent State Estimation for Continuous Fermenters Using Variational Bayesian Learning;S. Gao, S. Zhao, X. Luan and F. Liu;《IEEE Transactions on Industrial Informatics》;20210205;第8429-8437页 *
一种基于自适应模糊高斯核聚类的软测量建模方法;夏源等;《上海交通大学学报》;20170628(第06期);第722-726页 *
基于贝叶斯学习的关联向量机及其在软测量中的应用;陈佳等;《华东理工大学学报(自然科学版)》;20070130(第01期);第1-5页 *
基于贝叶斯网络的软测量建模方法;李雅芹等;《计算机与应用化学》;20101028(第10期);第1391-1394页 *
复合高斯噪声中知识辅助的贝叶斯Rao检测方法;高永婵等;《西安电子科技大学学报》;20130710(第06期);第46-51、173页 *
聚合过程贝叶斯统计学习质量模式监测;高爽，郑年年，栾小丽，刘飞;《化工进展》;20181231;第37卷(第12期);第4558-4564页 *

Also Published As

Publication number Publication date
CN113962081A (en) 2022-01-21

Similar Documents

Publication Publication Date Title
CN106487358B (en) A kind of maneuvering target turning tracking
US20230297642A1 (en) Bearings-only target tracking method based on pseudo-linear maximum correlation entropy kalman filtering
CN107451102B (en) Method for predicting concentration of butane at bottom of debutanizer tower based on improved self-training algorithm semi-supervised Gaussian process regression soft measurement modeling
CN108647272B (en) Method for predicting concentration of butane at bottom of debutanizer by expanding small samples based on data distribution
CN109163720A (en) Kalman filter tracking method based on fading memory exponent
CN112115419B (en) System state estimation method and system state estimation device
CN111080675A (en) Target tracking method based on space-time constraint correlation filtering
CN106599368A (en) FastSLAM method based on particle proposal distribution improvement and adaptive particle resampling
CN113962081B (en) Rectifying tower single-ton energy consumption estimation method and system based on auxiliary measurement information
CN109635245A (en) A kind of robust width learning system
CN106022340A (en) Improved Gaussian mixed potential probability hypothesis density filtering method
CN107861492A (en) A kind of broad sense Non-negative Matrix Factorization fault monitoring method based on nargin statistic
CN111638707A (en) Intermittent process fault monitoring method based on SOM clustering and MPCA
CN114089363A (en) Heterogeneous sensor information fusion and multi-target tracking method based on random finite set
CN110572779A (en) System error estimation method of base station based on ToF model
CN108226887B (en) Water surface target rescue state estimation method under condition of transient observation loss
CN110084301B (en) Hidden Markov model-based multi-working-condition process working condition identification method
Klein et al. Uncertainty in data-driven Kalman filtering for partially known state-space models
CN112381145A (en) Gaussian process regression multi-model fusion modeling method based on nearest correlation spectral clustering
CN109375160B (en) Angle measurement error estimation method in pure-azimuth passive positioning
CN116520311A (en) GLMB-based adaptive track initiation method
CN108804588A (en) A kind of mixed data flow data label method
CN106934124B (en) Adaptive variable window method based on measurement change detection
CN111460974B (en) Scattered point cloud data global feature extraction method based on optimization
Lee et al. Online process monitoring scheme for fault detection based on independent component analysis (ICA) and local outlier factor (LOF)

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant