CN117454290A - Intelligent data real-time acquisition and analysis system for boiler heat supply - Google Patents

Intelligent data real-time acquisition and analysis system for boiler heat supply Download PDF

Info

Publication number
CN117454290A
CN117454290A CN202311396342.5A CN202311396342A CN117454290A CN 117454290 A CN117454290 A CN 117454290A CN 202311396342 A CN202311396342 A CN 202311396342A CN 117454290 A CN117454290 A CN 117454290A
Authority
CN
China
Prior art keywords
main steam
time sequence
temperature
steam pressure
training
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.)
Pending
Application number
CN202311396342.5A
Other languages
Chinese (zh)
Inventor
姜顺民
蒋甲丁
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.)
Xinjiang Institute of Engineering
Original Assignee
Xinjiang Institute of Engineering
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 Xinjiang Institute of Engineering filed Critical Xinjiang Institute of Engineering
Priority to CN202311396342.5A priority Critical patent/CN117454290A/en
Publication of CN117454290A publication Critical patent/CN117454290A/en
Pending legal-status Critical Current

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F22—STEAM GENERATION
    • F22B—METHODS OF STEAM GENERATION; STEAM BOILERS
    • F22B35/00—Control systems for steam boilers
    • F22B35/18—Applications of computers to steam boiler control
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
    • F24H9/00—Details
    • F24H9/20—Arrangement or mounting of control or safety devices
    • F24H9/2007—Arrangement or mounting of control or safety devices for water heaters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data
    • 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
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

An intelligent data real-time acquisition and analysis system for boiler heat supply is characterized in that a main steam pressure value and a main steam temperature value of a heat control device are acquired in real time, a data processing and analysis algorithm is introduced into the rear end to perform time sequence collaborative analysis of the main steam pressure value and the main steam temperature value, so that whether the working state of a boiler is normal or not is judged according to the time sequence collaborative change condition of the main steam pressure and the main steam temperature parameter of the boiler, and corresponding treatment suggestions are given. Therefore, the real-time abnormal detection of the working state of the boiler heating system can be realized, so that abnormal conditions can be processed in time, the large fluctuation of parameters such as main steam pressure, main steam temperature and the like of the heat control equipment is avoided, and the safety and stability of the heating system are improved.

Description

Intelligent data real-time acquisition and analysis system for boiler heat supply
Technical Field
The present application relates to the field of intelligent data processing technology, and more particularly, to an intelligent data real-time acquisition and analysis system for boiler heating.
Background
Boiler heating is a common heating mode, which generates heat energy by burning fuel, transfers the heat energy to water or steam, and then conveys the water or steam to a place needing heating through a pipeline. However, various faults may occur in the operation process of the boiler, and heat supply efficiency and safety are affected. In order to timely find and process abnormal conditions of the boiler, real-time monitoring and analysis of working parameters of the boiler are required.
However, conventional boiler heating systems are typically manually operated and monitored, but this approach presents some problems. First, manual operations are susceptible to subjective factors, which may lead to inaccurate operations or delay handling of anomalies. Secondly, manual monitoring requires a large amount of human resources, and is high in cost and low in efficiency.
In addition, some existing boiler heating systems monitor each working parameter of the boiler in real time by adopting a threshold monitoring method, so as to judge whether the boiler heating system is abnormal or not. However, the operating state of the boiler heating system may vary with time, season and load, and thus the statically set threshold may not be adaptable to the actual situation under different conditions. Moreover, since the threshold monitoring method can only judge according to a preset threshold, false alarm may be caused when the parameter fluctuation is large or an instantaneous peak exists. On the other hand, if the parameter changes slowly or fluctuates within a threshold, an abnormal situation may be missed.
Accordingly, an intelligent data real-time acquisition and analysis system for boiler heating 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 intelligent data real-time acquisition and analysis system for boiler heat supply, which is used for acquiring a main steam pressure value and a main steam temperature value of heat control equipment in real time, introducing a data processing and analysis algorithm at the rear end to perform time sequence collaborative analysis of the main steam pressure value and the main steam temperature value, judging whether the working state of a boiler is normal according to the time sequence collaborative change condition of the main steam pressure and the main steam temperature parameter of the boiler, and providing corresponding processing suggestions. Therefore, the real-time abnormal detection of the working state of the boiler heating system can be realized, so that abnormal conditions can be processed in time, the large fluctuation of parameters such as main steam pressure, main steam temperature and the like of the heat control equipment is avoided, and the safety and stability of the heating system are improved.
In a first aspect, there is provided an intelligent data real-time acquisition and analysis system for boiler heating, comprising:
the data acquisition module is used for acquiring main steam pressure values and main steam temperature values of the thermal control equipment at a plurality of preset time points in a preset time period;
the data time sequence arrangement module is used for arranging the main steam pressure value and the main steam temperature value of the plurality of preset time points into a main steam temperature time sequence input vector and a main steam pressure time sequence input vector respectively according to the time dimension;
the data local time sequence correlation analysis module is used for carrying out local time sequence correlation analysis on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector so as to obtain a sequence of main steam pressure-temperature local time sequence correlation characteristic vectors;
the main steam pressure-temperature time sequence global context correlation coding module is used for carrying out context correlation mode feature analysis on each main steam pressure-temperature local time sequence correlation feature vector in the sequence of the main steam pressure-temperature local time sequence correlation feature vectors so as to obtain main steam pressure-temperature time sequence context correlation mode features;
and the thermal control equipment working state detection module is used for determining whether the working state of the thermal control equipment is abnormal or not based on the main steam pressure-temperature time sequence context correlation mode characteristics.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art 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.
FIG. 1 is a block diagram of an intelligent data real-time acquisition analysis system for boiler heating according to an embodiment of the present application.
Fig. 2 is a flow chart of an intelligent data real-time acquisition and analysis method for boiler heating according to an embodiment of the present application.
Fig. 3 is a schematic diagram of an architecture of an intelligent data real-time acquisition and analysis method for boiler heating according to an embodiment of the present application.
Fig. 4 is an application scenario diagram of an intelligent data real-time acquisition and analysis system for boiler heating according to an embodiment of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Unless defined otherwise, all technical and scientific terms used in the examples of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
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.
In one embodiment of the present application, FIG. 1 is a block diagram of an intelligent data real-time acquisition analysis system for boiler heating according to an embodiment of the present application. As shown in fig. 1, an intelligent data real-time acquisition and analysis system 100 for boiler heating according to an embodiment of the present application includes: a data acquisition module 110, configured to acquire main steam pressure values and main steam temperature values of the thermal control device at a plurality of predetermined time points within a predetermined time period; the data timing arrangement module 120 is configured to arrange the main steam pressure value and the main steam temperature value at the plurality of predetermined time points into a main steam temperature timing input vector and a main steam pressure timing input vector according to a time dimension, respectively; the data local time sequence correlation analysis module 130 is configured to perform local time sequence correlation analysis on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector to obtain a sequence of main steam pressure-temperature local time sequence correlation feature vectors; the main steam pressure-temperature time sequence global context correlation encoding module 140 is configured to perform context correlation pattern feature analysis on each main steam pressure-temperature local time sequence correlation feature vector in the sequence of the main steam pressure-temperature local time sequence correlation feature vectors to obtain a main steam pressure-temperature time sequence context correlation pattern feature; and the thermal control equipment working state detection module 150 is used for determining whether the working state of the thermal control equipment is abnormal or not based on the main steam pressure-temperature time sequence context correlation mode characteristics.
In view of the above technical problems, it is considered that in a boiler heating system, the main steam pressure and the main steam temperature are two important parameters, which are directly related to the stability and safety of the heating system. Therefore, the technical conception of the method is that the main steam pressure value and the main steam temperature value of the thermal control equipment are collected in real time, and a data processing and analyzing algorithm is introduced into the rear end to carry out time sequence collaborative analysis of the main steam pressure value and the main steam temperature value, so that whether the working state of the boiler is normal or not is judged according to the time sequence collaborative change condition of the main steam pressure and the main steam temperature parameter of the boiler, and corresponding processing suggestions are given. Therefore, the real-time abnormal detection of the working state of the boiler heating system can be realized, so that abnormal conditions can be processed in time, the large fluctuation of parameters such as main steam pressure, main steam temperature and the like of the heat control equipment is avoided, and the safety and stability of the heating system are improved.
Specifically, in the technical scheme of the application, first, main steam pressure values and main steam temperature values of the thermal control device at a plurality of preset time points in a preset time period are obtained.
Then, considering that the main steam pressure value and the main steam temperature value have volatility in the time dimension, the time sequence of the main steam pressure value and the main steam temperature value not only have dynamic change rules, but also have time sequence cooperative association relation, and time sequence cooperative association characteristic information of the two data has important significance for detecting the working state of the thermal control equipment. Therefore, in the technical solution of the present application, in order to better analyze the time sequence cooperative variation between the main steam pressure value and the main steam temperature value, it is necessary to further arrange the main steam pressure value and the main steam temperature value at the plurality of predetermined time points into a main steam temperature time sequence input vector and a main steam pressure time sequence input vector according to a time dimension, so as to integrate the time sequence distribution information of the main steam pressure value and the main steam temperature value respectively.
In one embodiment of the present application, the data local timing correlation analysis module includes: the vector segmentation unit is used for respectively carrying out vector segmentation on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector so as to obtain a sequence of main steam temperature local time sequence input vectors and a sequence of main steam pressure local time sequence input vectors; a local time sequence incidence matrix construction unit, configured to construct a main steam pressure-temperature local time sequence incidence matrix between the main steam temperature local time sequence input vector and the main steam pressure local time sequence input vector of each group of corresponding local time periods in the sequence of the main steam temperature local time sequence input vector so as to obtain a sequence of the main steam pressure-temperature local time sequence incidence matrix; and the main steam pressure-temperature local time sequence feature extraction unit is used for carrying out feature extraction on the sequence of the main steam pressure-temperature local time sequence correlation matrix through a temperature-pressure correlation feature extractor based on a deep neural network model so as to obtain the sequence of the main steam pressure-temperature local time sequence correlation feature vector.
The deep neural network model is a convolutional neural network model.
The main steam temperature and main steam pressure in a boiler heating system typically change over time. In order to better capture time sequence characteristic distribution information of main steam temperature and main steam pressure in a boiler heating system, in the technical scheme of the application, vector segmentation is further carried out on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector respectively so as to obtain a sequence of main steam temperature local time sequence input vectors and a sequence of main steam pressure local time sequence input vectors. By vector slicing the time series input vector, the entire time series can be divided into a sequence of a plurality of local time series input vectors, each local time series input vector representing a change in the main steam temperature or the main steam pressure over a period of time. In this way, the change trend of the main steam temperature and the main steam pressure can be observed and analyzed more carefully. That is, by analyzing the sequence of local time series input vectors, finer patterns of changes and features, such as transient peaks in temperature and pressure, periodic fluctuations, etc., can be captured. The method is helpful for more accurately judging the working state of the boiler heating system, detecting abnormal conditions in time and taking corresponding treatment measures.
Then, considering that the main steam pressure and the main steam temperature are usually closely related in the boiler heating system, the variation trend and fluctuation situation of the main steam pressure and the main steam temperature may affect each other, and reflect the operation state of the system. Therefore, in order to analyze the correlation between the main steam pressure and the main steam temperature to further understand the working state of the boiler heating system, in the technical scheme of the application, a main steam pressure-temperature local time sequence correlation matrix between the main steam temperature local time sequence input vector and the main steam pressure local time sequence input vector of each group of corresponding local time periods in the sequence of the main steam temperature local time sequence input vector is further constructed to obtain the sequence of the main steam pressure-temperature local time sequence correlation matrix. It should be appreciated that by constructing the main steam pressure-temperature local time series correlation matrix, the degree of correlation between main steam pressure and main steam temperature may be quantified. That is, by constructing the sequence of the main steam pressure-temperature local time series correlation matrix, the time-dependent change of the correlation pattern between the main steam pressure and the main steam temperature can be observed. The method is helpful for more comprehensively understanding the working state of the boiler heating system, finding abnormal conditions or abnormal association modes and taking corresponding measures for processing.
Further, the sequence of the main steam pressure-temperature local time sequence correlation matrix is subjected to feature mining in a temperature-pressure correlation feature extractor based on a convolutional neural network model so as to extract local time sequence cooperative correlation feature distribution information between the main steam pressure and the main steam temperature respectively, and thus a sequence of main steam pressure-temperature local time sequence correlation feature vectors is obtained. Particularly, the sequence of the main steam pressure-temperature local time sequence correlation characteristic vector can better represent the correlation mode and the change trend between the main steam pressure and the main steam temperature, and is beneficial to judging whether the working state of the thermal control equipment is abnormal.
In one embodiment of the present application, the main steam pressure-temperature timing global context-related encoding module is configured to: and the sequence of the main steam pressure-temperature local time sequence correlation characteristic vector is used for obtaining a main steam pressure-temperature time sequence context correlation mode characteristic vector as the main steam pressure-temperature time sequence context correlation mode characteristic through a time sequence context encoder based on a gating circulation unit.
Next, it is also considered that the correlation pattern between the main steam pressure and the main steam temperature exists not only in each local time sequence but also in the overall time dimension, that is, the correlation relationship between the local time sequence correlation characteristic information about the main steam pressure-temperature in each local time period has the overall time sequence. Therefore, in order to fully and effectively describe the correlation characteristic between the main steam pressure and the main steam temperature, so as to more accurately detect the working state of the thermal control device, in the technical scheme of the application, the sequence of the main steam pressure-temperature local time sequence correlation characteristic vector needs to be further processed by a time sequence context encoder based on a gating circulation unit to obtain the main steam pressure-temperature time sequence context correlation mode characteristic vector. It should be appreciated that the sequential context encoder based on the gating loop may interact and integrate each of the main vapor pressure-temperature local time sequence-related feature vectors with the main vapor pressure-temperature local time sequence-related feature vectors at the time before and after the main vapor pressure-temperature local time sequence-related feature vectors by learning the time dependency relationship and the context information in the sequence. Therefore, the characteristic vector of the time sequence context correlation mode of the main steam pressure and the temperature can be obtained, so that the time sequence correlation condition between the main steam pressure and the main steam temperature can be more comprehensively described, and the working state of the boiler heating system can be more accurately described.
In one embodiment of the present application, the thermal control device working state detection module is configured to: and the main steam pressure-temperature time sequence context association mode feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the thermal control equipment is abnormal or not.
And then, the main steam pressure-temperature time sequence context correlation mode feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the thermal control equipment is abnormal or not. Therefore, whether the working state of the boiler is normal or not can be judged according to the time sequence cooperative change condition of the main steam pressure and the main steam temperature parameter of the boiler, and corresponding treatment suggestions are given, so that the large fluctuation of the main steam pressure, the main steam temperature and other parameters of the heat control equipment is avoided, and the safety and the stability of a heating system are improved.
In one embodiment of the present application, the intelligent data real-time acquisition and analysis system for boiler heating further comprises a training module for training the temperature-pressure correlation feature extractor based on the convolutional neural network model, the time sequence context encoder based on the gating loop unit, and the classifier. The training module comprises: the training data acquisition unit is used for acquiring training data, wherein the training data comprises training main steam pressure values and training main steam temperature values of the thermal control equipment at a plurality of preset time points in a preset time period, and a true value of whether the working state of the thermal control equipment is abnormal or not; the training data time sequence arrangement unit is used for arranging the training main steam pressure values and the training main steam temperature values of the plurality of preset time points into training main steam temperature time sequence input vectors and training main steam pressure time sequence input vectors respectively according to the time dimension; the training data time sequence vector segmentation unit is used for respectively carrying out vector segmentation on the training main steam temperature time sequence input vector and the training main steam pressure time sequence input vector so as to obtain a sequence of training main steam temperature local time sequence input vectors and a sequence of training main steam pressure local time sequence input vectors; the training data local time sequence correlation construction unit is used for constructing a training main steam pressure-temperature local time sequence correlation matrix between each group of training main steam temperature local time sequence input vectors and training main steam pressure local time sequence input vectors corresponding to the local time period in the training main steam temperature local time sequence input vector sequence and the training main steam pressure local time sequence input vector sequence so as to obtain a training main steam pressure-temperature local time sequence correlation matrix sequence; the training temperature-pressure local time sequence correlation feature extraction unit is used for enabling the sequence of the training main steam pressure-temperature local time sequence correlation matrix to pass through the temperature-pressure correlation feature extractor based on the convolutional neural network model so as to obtain a sequence of training main steam pressure-temperature local time sequence correlation feature vectors; the training main steam pressure-temperature global time sequence associated coding unit is used for enabling the sequence of the training main steam pressure-temperature local time sequence associated characteristic vectors to pass through the time sequence context coder based on the gating circulating unit to obtain training main steam pressure-temperature time sequence context associated mode characteristic vectors; the characteristic distribution optimizing unit is used for carrying out Hilbert orthogonal space domain representation decoupling on the training main steam pressure-temperature time sequence context correlation mode characteristic vector so as to obtain an optimized training main steam pressure-temperature time sequence context correlation mode characteristic vector; the classification loss unit is used for enabling the optimized training main steam pressure-temperature time sequence context correlation mode feature vector to pass through the classifier to obtain a classification loss function value; and the model training unit is used for training the temperature-pressure correlation feature extractor based on the convolutional neural network model, the time sequence context encoder based on the gating circulating unit and the classifier based on the classification loss function value and through gradient descent direction propagation.
In particular, in the technical solution of the present application, each training main vapor pressure-temperature local time sequence correlation feature vector in the sequence of training main vapor pressure-temperature local time sequence correlation feature vectors is used to express a local neighborhood semantic correlation feature based on a convolution kernel and represented by a cooperative correlation between main vapor pressure and main vapor temperature in a local time domain, so when the sequence of training main vapor pressure-temperature local time sequence correlation feature vectors passes through a time sequence context encoder based on a gating cycle unit, a time sequence context correlation of main vapor pressure and main vapor temperature semantic correlation features between local time domains in a global time domain can be extracted, so that the training main vapor pressure-temperature time sequence context correlation pattern feature vectors have diversified feature representations corresponding to main vapor pressure and main vapor temperature semantic correlation features in different time domain spatial dimensions, and when the training main vapor pressure-temperature time sequence context correlation pattern feature vectors pass through a classifier, the training main vapor pressure-temperature time sequence context correlation pattern feature vectors are affected as a whole, that is, the effect of classification regression is accurate.
Based on this, the applicant of the present application, when classifying the training main steam pressure-temperature time series context-associated mode feature vector, preferably turns off the training main steam pressure-temperature time series contextThe joint model feature vector, e.g. denoted asThe hilbert orthogonal spatial domain representation decoupling is performed, expressed as: performing Hilbert orthogonal space domain representation decoupling on the training main steam pressure-temperature time sequence context correlation mode feature vector by using the following optimization formula; wherein, the optimization formula is: />Wherein (1)>Is the training main steam pressure-temperature time sequence context associated mode characteristic vector +.>Global feature mean,/, of>Is the training main steam pressure-temperature time sequence context associated mode characteristic vector +.>Is>Is the training main steam pressure-temperature time sequence context associated mode characteristic vector +.>Length of (2), and->Is a unit vector, +.>Is an optimized training main steam pressure-temperature time sequence context correlation mode characteristic vector,representing one-dimensional convolution processing, ">Representing per-position subtraction.
Here, the hilbert orthogonal spatial domain representation decouples pattern feature vectors for temporal correlation by emphasizing the training main steam pressure-temperature Intrinsic domain-specific (domain-specific) information within the diversified feature expression of (i) is derived from the training main steam pressure-temperature temporal associated pattern feature vector by a hilbert spatial metric based on a vector self-spatial metric and a vector self-inner product representation>Orthogonal spatial domain decoupling of domain-invariant (domain-invariant) representation within the global domain representation to promote the training main vapor pressure-temperature temporal context-dependent mode feature vector ≡>And the domain self-adaptive generalization performance in the classification regression domain is improved, so that the accuracy of the classification result obtained by the training main steam pressure-temperature time sequence context correlation mode feature vector through the classifier is improved. Therefore, the real-time abnormal detection of the working state of the boiler heating system can be realized, so that abnormal conditions can be processed in time, the large fluctuation of parameters such as main steam pressure, main steam temperature and the like of the heat control equipment is avoided, and the safety and stability of the heating system are improved.
In one embodiment of the present application, the classification loss unit includes: a classification result generation subunit, configured to process the optimized training main steam pressure-temperature time sequence context correlation mode feature vector by using the classifier according to the following classification formula to generate a training classification result, where the classification formula is: WhereinRepresenting the saidOptimizing training main steam pressure-temperature time sequence context associated mode feature vector,/for>Weight matrix for full connection layer, +.>A bias matrix representing the fully connected layer; and a loss measurement subunit, configured to calculate, as the classification loss function value, a cross entropy value between the training classification result and a true value of whether the working state of the thermal control device is abnormal.
It should be understood that in the present application, the rated water outlet pressure of the heat supply engineering boiler is 1.6MPa, the rated water outlet temperature is 130 degrees, and the exhaust gas temperature is 142 ℃. The heat efficiency of the rated working condition of the boiler is more than 86%, and the boiler is matched with a main body soot blower, an instrument, an automatic control and a safety valve hoisting point). The intelligent configuration system of the boiler process is developed to mainly complete intelligent PID control algorithms for logic configuration, combustion, water supply, air supply, and the like of a heat supply engineering FSSS system, an SCS system, an MCS and the like. The intelligent data real-time acquisition configuration monitoring system is developed by utilizing advanced control strategies, data analysis and other new technologies, comprehensive optimization of the boiler heating process configuration system is completed, relevant process index data of a production line are analyzed, and the boiler heating control configuration monitoring management system integrating acquisition, analysis and control functions is developed.
The intelligent configuration system development work of the heat supply engineering boiler process is a work which can be carried out after the completion of the power supply work, the software recovery work and the I/O channel test work of the boiler computer system, and the intelligent configuration monitoring system of the heat supply engineering boiler process is researched and developed, so that the digitization, visualization and intellectualization of the heat supply process of the boiler are realized, the problem of unstable control in the traditional heat supply process is solved, the heating efficiency is improved to the maximum extent, the product quality is ensured, the operating cost of a production line is reduced, and the economic benefit and market competitiveness are improved.
In one embodiment of the present application, there is provided a development scope of the intelligent data real-time acquisition and analysis system for boiler heating, which includes:
checking whether the addresses of the DCS controller and the I/O module of the heat supply engineering boiler are consistent with the final data provided by manufacturers, and after checking that the addresses are correct, respectively downloading the configuration of the controllers of all control cabinets of the DCS;
program loading is carried out on the heating engineering boiler controller at an engineer station, a module state monitoring picture is called out, and the display states of all modules in the operation controller can be observed; calling out a typical configuration diagram and confirming an online monitoring function; performing experiments of modifying configuration, downloading part of programs and downloading all programs, and setting the downloading function to be normal; the alarm information is set correctly, and the trend function is normal;
Setting a multi-window system operation function in a configuration picture and an operation condition of an operator station of a heat supply engineering boiler; setting the peripheral functions of a mouse and a keyboard lamp to be normal; setting functions such as screen refreshing time, function key setting, alarm setting, trend display and the like;
setting whether the content, the storage capacity and the time resolution capability of the stored data can meet the contract requirements at the history station; whether the method for retrieving the data can meet the contract requirement or not;
setting printing functions, including functions of unit start-stop parameter printing, measuring point list printing, CRT picture copy printing, configuration diagram printing, logic diagram printing and the like, report printing, picture printing, trend diagram printing and the like;
and setting an audible and visual alarm system of the heat supply engineering boiler DCS and testing the normal function.
The soft control, sequence control, MCS function set, FSSS system and other system logic configuration, burning, water supply, air supply, etc. intelligent PID control algorithm and interlocking protection function set of each single equipment controlled in the heat supply engineering boiler DCS system, and the sequence control of various motors, fans, pumps, switch doors and other primary equipment controlled by using the switch value belong to the development range of the system.
The main development control objects are: the system comprises a smoke and wind system baffle door, an induced draft fan, an exhaust fan, an air preheater, a blower, a sealing fan, a slag remover, a deoxidizing water pump, a back flushing pump, a water supplementing pump, a circulating water pump, a belt type coal conveyor, a high-low voltage frequency converter, a heat supply and water supply process water system, a heat supply boiler combustion process system, a boiler coal supply control system, air quantity control, fuel quantity control, furnace pressure control, steam temperature control, water supply control, boiler soot blowing control, other MCS systems and the like. The control system is divided into monitoring and functional level control of equipment level, site pressure, temperature, flow and the like, the equipment level logic realizes the interlocking protection and soft manual operation functions of equipment, and the functional level logic realizes the sequential start and stop of auxiliary equipment.
More specifically, in one embodiment of the present application, there is also provided a boiler process intelligent configuration and control development:
operator station, engineer station software recovery. The method specifically comprises the following steps: developing the control configuration and process picture in the engineer station as the latest configuration and picture of the boiler process; setting a boiler DCS controller and an I/O module address to respectively configure and download the controllers of all control cabinets of the boiler DCS; program loading is carried out on the controller at an engineer station, a module state monitoring picture is set, and the display states of all modules in the running controller can be observed; calling out a typical configuration diagram and setting an online monitoring function; and carrying out experiments of modifying configuration, downloading part of programs and downloading all programs, and confirming that the setting function is normal, the setting alarm information is correct and the trend function is normal.
According to the design yard data, the system schematic diagram, sequential control logic diagram and configuration diagram are developed, and if the design yard data is inconsistent with the site, the design side is provided with a modification notice. Checking the terminal wiring diagram is also to confirm that the terminal wiring diagram is consistent with the drawing of the design institute, and each signal wire taken from the site or other systems by the system needs to be carefully checked to ensure no errors.
Checking internal connection of the boiler process DCS system.
And checking the cable connection from the cabinet to the local equipment (including a junction terminal box passing through the middle, a coupling relay cabinet and the like) according to the wiring diagram.
And performing field recovery of the boiler process DCS system, including recovery of hardware and software.
In-situ equipment control checks. And the function and control of the controlled equipment meet the design requirements by comparing with the design drawing.
And transmitting and setting the I/O template.
After all the joints in the same template are checked without errors and the problems of grounding, short circuit and the like, the template can be inserted into power transmission, and whether the operation of the template is normal is confirmed according to the state of the fault lamp of the template.
Whether the input signal is normal is set by the engineer station and a test check can be performed by inputting an analog signal in the field.
The output signal part of the module is set and tested by an engineer station after field test of field control equipment (including fans, pumps, electric/pneumatic valves, other execution mechanisms and the like) is complete.
The cold state test is carried out to the combustion engine, specifically includes:
(1) Inspection of field control devices (including fans, pumps, electro/pneumatic valves, and other actuators, etc.): and checking and accepting by construction units, installation units and the like.
(2) Inspection of on-site electric control equipment: the "manual/automatic" or "remote/on-site" switching should be flexible and correct. The action direction of the fan, the pump and the valve should be correct; the device start/stop should be correct. The actions of the fan, the pump and the valve are stable and flexible; the equipment should run smoothly without abnormality. The action strokes and the action time of the fan, the pump and the valve meet the process requirements. The travel switch, the moment switch and the fault contact point act normally. Fans, pumps, valves/equipment are blocked inside and protected from normal.
(3) The field function module transmits power and checks: confirm that the functional module is not directly connected to the site. Taking the confirmed DCS cabinet wiring construction diagram as a basis, taking interphones, universal meters or signal generators and the like as test tools, carefully checking and checking each signal wire from each controller, I/O control cabinet, relay cabinet to field equipment and between each controller and I/O control cabinet, and ensuring that all wiring is correct.
All input signal lines related to the card to be put into operation are tested in the DCS terminal cabinet, so that no strong electric signals and induced potentials are led into the DCS terminal cabinet. And inputting related clamping pieces such as a controller and an I/O clamping piece, and performing static test.
Setting the setting values of the deviation alarm modules of all the systems according to the related specifications and operation rules, and not only considering the allowable variation range of the parameters during the operation of the unit, but also avoiding the automatic control system from being easily cut manually. Preliminary checks are made on the cut-to-hand logic and override logic of the respective dynamic adjustment system, checking the direction of the adjustment system. Checking the incomplete items on the DCS picture to perform unified correction.
(4) Inspection of field primary element: check whether the in-situ pressure, temperature, flow and switch check report meets the requirements. It is checked whether the in-situ pressure switch setpoint is the same as the protection setpoint. Checking whether the fixed values and the channels of the in-situ liquid level switch, the flow switch, the electric contact meter and other devices are correct. Comparing the real set range of the transmitter, and modifying the range of the corresponding measuring point in the configuration to ensure that the parameter is displayed correctly; and modifying and perfecting a flow calculation formula in the configuration according to the flow orifice plate data provided by the manufacturer, so as to ensure that flow signals are displayed correctly.
(5) And setting the software configuration of each system of the heat supply engineering boiler process according to the logic diagram, and modifying and backing up according to the field requirement when the software configuration is not consistent with the logic diagram. And writing the protection fixed value of the analog quantity signal into a heat supply engineering boiler process DCS system according to a protection fixed value list provided by a production unit, and rechecking. And setting and changing the process flow chart, the logic diagram and the configuration diagram of the hot engineering boiler.
(6) And (3) comparing the checking logic diagram, the configuration diagram and the internal configuration of the system, and providing written comments or suggestions for the parts which do not meet the requirements of the process control.
(7) According to the logic diagram and the configuration diagram, the functions of the function group level, the sub-function group level and the driving level are respectively set and tested, and the discovered problems are solved in time by related parties. Before the sequential control equipment is put into operation for the first time, the driving stage, the sub-function group stage and the function group stage of the centralized control room experiment are correctly set. Each device or a group of devices is set and checked to see whether the control loop is unobstructed, the control function is correct, and each interlocking function can be realized. The DCS is used for forcedly simulating field signals, checking whether the acting direction of each regulator accords with the process requirement of a control system, and whether the action direction and the position of an actuator correspond to the output of the regulator; checking the correct and correct actions of each amplitude limiting and alarming function and each logic; and (5) performing manual and automatic switching tests on each main regulating system, and checking whether the main regulating system has disturbance. According to the engineering progress, the investment of the related control system is timely ensured, the equipment is timely adjusted and solved when abnormal, and the discovered problems are timely proposed and solved by related parties.
The hot debugging method specifically comprises the following steps: and setting and checking soft operation control, sequence control, MCS function set and picture configuration of FSSS system of the single equipment, and timely modifying and perfecting.
The subsystem carries out joint debugging on external equipment, confirms that the action of the actuating mechanism is correct, the state feedback is correct, and the static characteristic of the adjusting mechanism meets the requirement of adjusting characteristics.
And the controller parameters are set and adjusted according to the system operation, so that the control system meets the quality regulation requirement, and the control function is safe and reliable.
And checking whether the logic design is reasonable, mainly whether the reference point is reliable and accurate. The device state quantity points should be strictly distinguished according to the reference requirements.
The on-site side signal generator, the resistor box, the potentiometer and other devices send out corresponding analog quantity signals: after the common DAS measuring points are respectively sent out, checking whether the display of the DAS measuring points is normal or not on a monitoring picture of an operator station; if there is a high/low limit alarm, it should also check if the corresponding color change and the associated alarm display are normal.
On the DCS engineer station, the start/stop signals of fans, motors and other devices are "forced" out, and on the site side check is made as to whether the signals or the corresponding contactors are operating correctly.
And checking and inputting analog quantity signals such as a motor, a fan coil, a bearing temperature, a motor current and the like entering the DCS, and setting high/low limit alarms.
And (3) feeding power sources of the motor and related equipment, performing remote sequential starting operation on a monitoring picture of a DCS operator station, checking whether the feedback of the sequential operation steps is normal or not on the monitoring picture, checking whether the operation feedback of the motor and related valves and executing mechanisms is normal or not, and simultaneously monitoring the change conditions of operating parameters such as motor coils, bearing temperatures, motor currents, related temperatures and pressures and the like, and checking whether the operation conditions of the electric power equipment and the related equipment are normal or not on the spot.
And (3) performing CRT soft operation and backup hard manual operation on the single equipment, and setting whether the equipment acts and operates normally. The operation is performed by an operator, the operation of the equipment is monitored, and the confirmation is performed.
And performing grouping operation of the equipment, and checking and monitoring the operation of the auxiliary machine and the linkage equipment thereof.
And (5) putting the interlocking into the equipment or group of equipment to perform interlocking test. And finally, performing a boiler auxiliary machine interlocking test. All of the above operations, monitoring and confirmation are performed by the operator.
The boiler control optimization of the heat supply engineering specifically comprises the following steps: checking signals: the method is mainly used for checking on-site signals and control configuration to ensure the accuracy of signal measurement. And (3) checking remote manual operation of an executing mechanism: the correctness of the action of the field actuator is checked by performing a remote manual operation test after the field actuator is ensured to be in a good state through the check.
Carrying out a static test of a heating engineering boiler control system, and specifically comprising the following steps: setting the correctness of the PID action direction; setting a tracking state and undisturbed switching of the adjusting module; deviation alarm function setting test: the automatic cutting off mode comprises the steps of measuring signal deviation, quality, actuator deviation and the like; simulating logic conditions, and setting the correctness of the logic of the control system; the correctness of the feedforward control direction is set.
Setting whether the control logic is correct or not, sending the switching value signal output by alarming to the corresponding alarm display and control protection loop or not, and recording the checking result.
Carrying out dynamic setting of a boiler control system of a heat supply engineering, and specifically comprising the following steps: when the regulating system is in manual operation, the actuator is manually increased by a certain opening degree, and relevant parameters such as a regulating door command, feedback and the like are recorded. And obtaining the preliminary PID parameters through data calculation. The resulting parameters are compared with the field parameters, and the data is suitably modified and recorded. After automatic stabilization is put into, a constant value disturbance test is carried out, the response condition of an automatic regulating system is observed, and parameter setting is further carried out through analysis; repeating the above process to further optimize the setting of the parameters. And when the unit operation working condition is stable and the control quality of the heat supply engineering boiler is good, recording each relevant parameter change in parameter setting.
In summary, the intelligent data real-time acquisition and analysis system 100 for boiler heat supply according to the embodiment of the present application is illustrated, and can implement real-time abnormal detection on the working state of the boiler heat supply system, so as to facilitate timely handling of abnormal situations, avoid large fluctuation of parameters such as main steam pressure, main steam temperature and the like of the heat control device, and thereby improve safety and stability of the heat supply system.
As described above, the intelligent data real-time collection and analysis system 100 for boiler heating according to the embodiment of the present application may be implemented in various terminal devices, for example, a server or the like for intelligent data real-time collection and analysis for boiler heating. In one example, the intelligent data real-time acquisition and analysis system 100 for boiler heating according to embodiments of the present application may be integrated into the terminal device as a software module and/or hardware module. For example, the intelligent data real-time acquisition and analysis system 100 for boiler heating may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the intelligent data real-time acquisition and analysis system 100 for boiler heating can also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the intelligent data real-time acquisition and analysis system 100 for boiler heating and the terminal device may be separate devices, and the intelligent data real-time acquisition and analysis system 100 for boiler heating may be connected to the terminal device through a wired and/or wireless network, and transmit interactive information according to a agreed data format.
In one embodiment of the present application, FIG. 2 is a flow chart of a method for real-time collection and analysis of intelligent data regarding boiler heating according to an embodiment of the present application. Fig. 3 is a schematic diagram of an architecture of an intelligent data real-time acquisition and analysis method for boiler heating according to an embodiment of the present application. As shown in fig. 2 and 3, the method for collecting and analyzing intelligent data about boiler heat supply in real time comprises the following steps: 210, configured to obtain a main steam pressure value and a main steam temperature value of the thermal control device at a plurality of predetermined time points in a predetermined time period; 220, configured to arrange the main steam pressure values and the main steam temperature values at the plurality of predetermined time points into a main steam temperature time sequence input vector and a main steam pressure time sequence input vector according to a time dimension, respectively; 230, performing local time sequence correlation analysis on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector to obtain a sequence of main steam pressure-temperature local time sequence correlation characteristic vectors; 240, performing context correlation pattern feature analysis on each main steam pressure-temperature local time sequence correlation feature vector in the sequence of main steam pressure-temperature local time sequence correlation feature vectors to obtain main steam pressure-temperature time sequence context correlation pattern features; 250 for determining whether the operating state of the thermal control device is abnormal based on the main vapor pressure-temperature time sequence context correlation mode feature.
It will be appreciated by those skilled in the art that the specific operation of the respective steps in the above-described intelligent data real-time acquisition and analysis method for boiler heat supply has been described in detail above with reference to the description of the intelligent data real-time acquisition and analysis system for boiler heat supply of fig. 1, and thus, repetitive descriptions thereof will be omitted.
Fig. 4 is an application scenario diagram of an intelligent data real-time acquisition and analysis system for boiler heating according to an embodiment of the present application. As shown in fig. 4, in this application scenario, first, main steam pressure values (e.g., C1 as illustrated in fig. 4) and main steam temperature values (e.g., C2 as illustrated in fig. 4) of a thermal control device at a plurality of predetermined time points within a predetermined period of time are acquired; the obtained main steam pressure value and main steam temperature value are then input to a server (e.g., S as illustrated in fig. 4) deployed with an intelligent data real-time acquisition and analysis algorithm for boiler heating, wherein the server is capable of processing the main steam pressure value and the main steam temperature value based on the intelligent data real-time acquisition and analysis algorithm for boiler heating to determine whether the operating state of the thermal control apparatus is abnormal.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims (8)

1. An intelligent data real-time acquisition and analysis system for boiler heat supply, comprising:
the data acquisition module is used for acquiring main steam pressure values and main steam temperature values of the thermal control equipment at a plurality of preset time points in a preset time period;
the data time sequence arrangement module is used for arranging the main steam pressure value and the main steam temperature value of the plurality of preset time points into a main steam temperature time sequence input vector and a main steam pressure time sequence input vector respectively according to the time dimension;
the data local time sequence correlation analysis module is used for carrying out local time sequence correlation analysis on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector so as to obtain a sequence of main steam pressure-temperature local time sequence correlation characteristic vectors;
the main steam pressure-temperature time sequence global context correlation coding module is used for carrying out context correlation mode feature analysis on each main steam pressure-temperature local time sequence correlation feature vector in the sequence of the main steam pressure-temperature local time sequence correlation feature vectors so as to obtain main steam pressure-temperature time sequence context correlation mode features;
And the thermal control equipment working state detection module is used for determining whether the working state of the thermal control equipment is abnormal or not based on the main steam pressure-temperature time sequence context correlation mode characteristics.
2. The intelligent data real-time acquisition and analysis system for boiler heating according to claim 1, wherein the data local time sequence correlation analysis module comprises:
the vector segmentation unit is used for respectively carrying out vector segmentation on the main steam temperature time sequence input vector and the main steam pressure time sequence input vector so as to obtain a sequence of main steam temperature local time sequence input vectors and a sequence of main steam pressure local time sequence input vectors;
a local time sequence incidence matrix construction unit, configured to construct a main steam pressure-temperature local time sequence incidence matrix between the main steam temperature local time sequence input vector and the main steam pressure local time sequence input vector of each group of corresponding local time periods in the sequence of the main steam temperature local time sequence input vector so as to obtain a sequence of the main steam pressure-temperature local time sequence incidence matrix;
and the main steam pressure-temperature local time sequence feature extraction unit is used for carrying out feature extraction on the sequence of the main steam pressure-temperature local time sequence correlation matrix through a temperature-pressure correlation feature extractor based on a deep neural network model so as to obtain the sequence of the main steam pressure-temperature local time sequence correlation feature vector.
3. The intelligent data real-time acquisition and analysis system for boiler heating according to claim 2, wherein the deep neural network model is a convolutional neural network model.
4. The intelligent data real-time collection and analysis system for boiler heating according to claim 3, wherein the main steam pressure-temperature time sequence global context correlation coding module is used for: and the sequence of the main steam pressure-temperature local time sequence correlation characteristic vector is used for obtaining a main steam pressure-temperature time sequence context correlation mode characteristic vector as the main steam pressure-temperature time sequence context correlation mode characteristic through a time sequence context encoder based on a gating circulation unit.
5. The intelligent data real-time acquisition and analysis system for boiler heating according to claim 4, wherein the thermal control device working state detection module is configured to: and the main steam pressure-temperature time sequence context association mode feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the thermal control equipment is abnormal or not.
6. The intelligent data real-time collection and analysis system for boiler heating according to claim 5, further comprising a training module for training the convolutional neural network model-based temperature-pressure correlation feature extractor, the gating loop-based time sequence context encoder, and the classifier.
7. The intelligent data real-time acquisition and analysis system for boiler heating according to claim 6, wherein the training module comprises:
the training data acquisition unit is used for acquiring training data, wherein the training data comprises training main steam pressure values and training main steam temperature values of the thermal control equipment at a plurality of preset time points in a preset time period, and a true value of whether the working state of the thermal control equipment is abnormal or not;
the training data time sequence arrangement unit is used for arranging the training main steam pressure values and the training main steam temperature values of the plurality of preset time points into training main steam temperature time sequence input vectors and training main steam pressure time sequence input vectors respectively according to the time dimension;
the training data time sequence vector segmentation unit is used for respectively carrying out vector segmentation on the training main steam temperature time sequence input vector and the training main steam pressure time sequence input vector so as to obtain a sequence of training main steam temperature local time sequence input vectors and a sequence of training main steam pressure local time sequence input vectors;
the training data local time sequence correlation construction unit is used for constructing a training main steam pressure-temperature local time sequence correlation matrix between each group of training main steam temperature local time sequence input vectors and training main steam pressure local time sequence input vectors corresponding to the local time period in the training main steam temperature local time sequence input vector sequence and the training main steam pressure local time sequence input vector sequence so as to obtain a training main steam pressure-temperature local time sequence correlation matrix sequence;
The training temperature-pressure local time sequence correlation feature extraction unit is used for enabling the sequence of the training main steam pressure-temperature local time sequence correlation matrix to pass through the temperature-pressure correlation feature extractor based on the convolutional neural network model so as to obtain a sequence of training main steam pressure-temperature local time sequence correlation feature vectors;
the training main steam pressure-temperature global time sequence associated coding unit is used for enabling the sequence of the training main steam pressure-temperature local time sequence associated characteristic vectors to pass through the time sequence context coder based on the gating circulating unit to obtain training main steam pressure-temperature time sequence context associated mode characteristic vectors;
the characteristic distribution optimizing unit is used for carrying out Hilbert orthogonal space domain representation decoupling on the training main steam pressure-temperature time sequence context correlation mode characteristic vector so as to obtain an optimized training main steam pressure-temperature time sequence context correlation mode characteristic vector;
the classification loss unit is used for enabling the optimized training main steam pressure-temperature time sequence context correlation mode feature vector to pass through the classifier to obtain a classification loss function value;
and the model training unit is used for training the temperature-pressure correlation feature extractor based on the convolutional neural network model, the time sequence context encoder based on the gating circulating unit and the classifier based on the classification loss function value and through gradient descent direction propagation.
8. The intelligent data real-time acquisition and analysis system for boiler heating according to claim 7, wherein the classification loss unit comprises: a classification result generation subunit, configured to process the optimized training main steam pressure-temperature time sequence context correlation mode feature vector by using the classifier according to the following classification formula to generate a training classification result, where the classification formula is:wherein->Representing the optimized training main steam pressure-temperature time sequence context associated mode characteristic vector, +.>Weight matrix for full connection layer, +.>A bias matrix representing the fully connected layer; and a loss measurement subunit, configured to calculate, as the classification loss function value, a cross entropy value between the training classification result and a true value of whether the working state of the thermal control device is abnormal.
CN202311396342.5A 2023-10-26 2023-10-26 Intelligent data real-time acquisition and analysis system for boiler heat supply Pending CN117454290A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311396342.5A CN117454290A (en) 2023-10-26 2023-10-26 Intelligent data real-time acquisition and analysis system for boiler heat supply

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311396342.5A CN117454290A (en) 2023-10-26 2023-10-26 Intelligent data real-time acquisition and analysis system for boiler heat supply

Publications (1)

Publication Number Publication Date
CN117454290A true CN117454290A (en) 2024-01-26

Family

ID=89588595

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311396342.5A Pending CN117454290A (en) 2023-10-26 2023-10-26 Intelligent data real-time acquisition and analysis system for boiler heat supply

Country Status (1)

Country Link
CN (1) CN117454290A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117803946A (en) * 2024-02-29 2024-04-02 山西漳电科学技术研究院(有限公司) Safety control system and method for low-calorific-value coal burning boiler

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117803946A (en) * 2024-02-29 2024-04-02 山西漳电科学技术研究院(有限公司) Safety control system and method for low-calorific-value coal burning boiler

Similar Documents

Publication Publication Date Title
JP5469131B2 (en) Plant diagnostic method and apparatus.
JP6116466B2 (en) Plant diagnostic apparatus and diagnostic method
US8532795B2 (en) Method and system for offline code validation
CN117454290A (en) Intelligent data real-time acquisition and analysis system for boiler heat supply
CN116772944B (en) Intelligent monitoring system and method for gas distribution station
CN114757380B (en) Fault early warning system and method for thermal power plant, electronic equipment and storage medium
JP2002155708A (en) System and method of providing guidance for power- generating plant
CN116658492B (en) Intelligent power catwalk and method thereof
TW201841087A (en) Diagnostic device and diagnostic method for plant
CN103498706A (en) Turboset performance monitoring and diagnosing method based on general logic table
CN111898794B (en) Abnormal monitoring method for thermal efficiency of large coal-fired boiler
CN108594782B (en) Intelligent self-diagnosis system of periodic aluminum coiled material nitrogen annealing furnace
CN110531742A (en) A kind of generator current collecting equipment real time monitoring and method for diagnosing faults
Bres et al. Coupled building and system simulations for detection and diagnosis of high district heating return temperatures
CN207112772U (en) Boiler hearth temperature on-line prediction system based on core offset minimum binary
CN103105205B (en) Combustion gas, hot water, heating comprehensive detection system and method
CN117451246A (en) Intelligent monitoring system and method for flue gas desulfurization
CN113485262B (en) SVM-based fault analysis method for fuel system of thermal power plant
KR102561073B1 (en) Smart Performance Monitoring System Using Real-time Efficiency Control Limit for Industrial Boilers
CN115167371B (en) Reverse verification-based thermal protection fault diagnosis method and system and self-checking method
CN102918471A (en) Plang diagnostic device and diagnostic method using same
Wu et al. Applications of Data Mining in Conventional Island of Nuclear Power Plant
Athanasopoulou et al. Utilizing data mining algorithms for identification and reconstruction of sensor faults: a Thermal Power Plant case study
CN115628131A (en) Diesel engine electronic speed regulator monitoring system and method
Wang et al. Operation Monitoring and Optimization of Industrial Boiler Based on Improved PCA

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