CN114861810A - Coal gasification device process diagnosis method and system - Google Patents
Coal gasification device process diagnosis method and system Download PDFInfo
- Publication number
- CN114861810A CN114861810A CN202210554979.1A CN202210554979A CN114861810A CN 114861810 A CN114861810 A CN 114861810A CN 202210554979 A CN202210554979 A CN 202210554979A CN 114861810 A CN114861810 A CN 114861810A
- Authority
- CN
- China
- Prior art keywords
- coal gasification
- data
- gasification device
- operation data
- value
- 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
Links
- 239000003245 coal Substances 0.000 title claims abstract description 210
- 238000002309 gasification Methods 0.000 title claims abstract description 207
- 238000000034 method Methods 0.000 title claims abstract description 133
- 230000008569 process Effects 0.000 title claims abstract description 96
- 238000003745 diagnosis Methods 0.000 title claims abstract description 90
- 238000001914 filtration Methods 0.000 claims description 32
- 238000007781 pre-processing Methods 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 9
- 238000002405 diagnostic procedure Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000004989 laser desorption mass spectroscopy Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004148 unit process Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to a coal gasification device process diagnosis method and a coal gasification device process diagnosis system. The coal gasification device process diagnosis model library in the method covers various working conditions of the coal gasification device, the model has high robustness, a user use interface of a coal gasification device process diagnosis system is easy and convenient to operate, the use difficulty of the model is greatly reduced, continuous normalized process diagnosis can be carried out on the coal gasification device, and the coal gasification device is guided to carry out refined operation optimization.
Description
Technical Field
The invention relates to the field of coal gasification devices, in particular to a coal gasification device process diagnosis method and a coal gasification device process diagnosis system.
Background
Coal gasification is an important means for clean and efficient utilization of coal, is a core device of modern coal chemical industry, but has the characteristics of large fluctuation of raw material properties, harsh reaction conditions, complex process and the like, so that the coal gasification has high energy consumption and high emission, and compared with the energy consumption of natural gas and petrochemical industry, the high energy consumption of the coal chemical industry becomes a main factor for restricting the development of the coal gasification. In order to reduce carbon emission, a coal gasification device needs a reliable means to guide the device to perform process optimization, and reduce the energy consumption of the device.
Currently, there are several methods for diagnosing the coal gasification device: a process diagnosis method is that related experts and technicians judge and diagnose the running state of a device according to experience, but the method has great limitation due to serious dependence on the experience of the personnel, can only carry out qualitative diagnosis on the device, cannot carry out quantitative diagnosis, and is difficult to guide the device to carry out fine operation; another process diagnosis method is to use flow simulation software to establish an off-line model of the typical working conditions of the device, and to perform simulation diagnosis on the device to obtain a device optimization scheme to guide device optimization. However, because coal gasification is a typical flow chemical industry, the production process is continuous and dynamic, and complicated chemical and physical changes are involved, the model developed by the method has poor robustness, continuous normalized diagnosis on the device cannot be performed, and because the flow simulation software has strong specialty, technical barriers exist on modeling personnel and users, and the method is difficult to popularize and apply.
Disclosure of Invention
The first technical problem to be solved by the present invention is to provide a coal gasification apparatus process diagnosis method in view of the above prior art.
The second technical problem to be solved by the present invention is to provide a coal gasification apparatus process diagnostic system for implementing the coal gasification apparatus process diagnostic method.
The technical scheme adopted by the invention for solving the first technical problem is as follows: the coal gasification device process diagnosis method is characterized by comprising the following steps:
step S1, acquiring an operation data set in the operation process of the coal gasification device, and preprocessing the operation data in the operation data set to obtain a preprocessed operation data set;
step S2, adopting the operation data in the operation data set after pretreatment to pre-construct a coal gasification device initialization model base for simulating the operation of the coal gasification device; the coal gasification device initialization model library comprises subunit initialization models corresponding to W different subunits, the different subunit initialization models comprise M feeding types, each feeding type comprises N working condition types, each subunit initialization model respectively corresponds to a subunit operation condition in a simulated coal gasification device, and W is the total number of the subunit operation units actually included in the coal gasification device;
s3, setting examination technical parameters and constraint conditions corresponding to the examination technical parameters based on the process diagnosis requirements, and developing and forming a process diagnosis model library based on the initialization model, the examination technical parameters and the constraint conditions in the coal gasification device initialization model library;
and step S4, acquiring the actual operation data of the coal gasification device again, and inputting the acquired actual operation data into the process diagnosis model base for diagnosis to obtain a process diagnosis result of the coal gasification device.
Alternatively, in the coal gasification plant process diagnosis method, the actual operation data in step S4 is real-time operation data of a called coal gasification plant or operation data of a coal gasification plant inputted manually.
Further, in the coal gasification apparatus process diagnosis method, the model in the process diagnosis model library is a diagnosis model having a simulation analysis for a key technical parameter of the coal gasification apparatus, the key technical parameter is an independent technical parameter relative to other technical parameters in the coal gasification apparatus, and the other technical parameters in the coal gasification apparatus are dependent technical parameters relative to the key technical parameter.
In a further improvement, the coal gasification device process diagnosis method further comprises the process of displaying the called real-time operation data in a visual mode; or/and displaying the coal gasification device process diagnosis result in a visual mode.
In the coal gasification apparatus process diagnosis method, in step S2, the coal gasification apparatus initialization model is constructed by the following steps a1 to a 3:
step a1, acquiring operation data of a coal gasification device, and performing validity processing on the operation data of the coal gasification device to form a basic database; the coal gasification device operation data comprises a coal gasification device real-time database and historical data collected by LIMS;
a2, based on basic database data, adopting a clustering algorithm to perform feed clustering and working condition clustering in sequence to form a sample data set library;
step a3, constructing an initialization model of the coal gasification device based on the formed sample number set database.
Further, in the coal gasification apparatus process diagnosis method, in step a2, the parameter data are gathered into M feed categories according to the feed characteristic parameter set, and then the parameter data are gathered into N working condition categories according to the working condition characteristic parameter set for each of the M feed categories; the clustering distance is calculated in the following manner:
where n, m are the numbers of the feature parameter set Y, Y n ＝(x n1 ,x n2 ,…,x nJ )，Y m ＝(x m1 ,x m2 ,…,x mJ )，cosθ nm For the feature parameter set Y n And a feature parameter set Y m Cosine distance between, x nj For the feature parameter set Y n Data of the jth characteristic parameter in (1), corresponding to, x mj For the feature parameter set Y m J is the feature parameter set Y n The total number of characteristic parameters; feature parameter set Y n And a feature parameter set Y m With the same total number of characteristic parameters.
Optionally, in the coal gasification plant process diagnosis method, the clustering algorithm is a mean shift clustering or a self-organizing neural network clustering algorithm.
Still further, in the coal gasification apparatus process diagnosis method, the validity processing in step a1 includes preprocessing, steady-state detection and data correction, and the preprocessing includes invalid data elimination, interpolation fitting and filling, filtering and denoising, and data normalization processing.
Further, in the coal gasification device process diagnosis method, in step a1, the invalid data is removed to remove the operation data meeting the large error condition in the collected coal gasification device operation data, and the operation data meeting the large error condition is the operation data with the fluctuation coefficient value larger than the preset fluctuation coefficient threshold value in the collected coal gasification device operation data; the collected coal gasification device operation data is operation data collected in a preset time interval, and the fluctuation coefficient value of the kth operation data collected in the preset time interval is marked as tau k The preset fluctuation coefficient threshold corresponding to the preset time interval is marked as tau th ：
a k Is the kth operation data value a in the operation data of the coal gasification device collected in the preset time interval k-1 The k-1 operating data value mu in the operating data of the coal gasification device collected in the preset time interval a The average value of all operation data values of the operation data of the coal gasification device collected in the preset time interval is obtained; and K is the total amount of the operation data of the coal gasification device collected in the preset time interval.
In the coal gasification device process diagnosis method, the steady-state detection is heuristic steady-state detection; the steady state detection process comprises the following steps b 1-b 4:
b1, calculating a light filtering value and a heavy filtering value corresponding to each effective data in the coal gasification device operation data acquired in the step a 1; effective data in the collected coal gasification device operation data are residual data after invalid data are removed;
(Y L ) t ＝f L ·y t +(1-f L )·(Y L ) t-1 ；
(Y H ) t ＝f H ·y t +(1-f H )· (Y H ) t-1 ；
(Y L ) 0 ＝y t1 ，(Y H ) 0 ＝y t1 ；
t 1 ≤t≤t Q ；
wherein, the time period (t) 1 ,t Q ) For the period of time for collecting the operation data of the coal gasification apparatus collected in the step a1, (Y) L ) t In a time period (t) 1 ,t Q ) The light filtering value (Y) of effective data corresponding to the t-th moment in the operation data of the coal gasification device is acquired internally H ) t In a time period (t) 1 ,t Q ) The operation data of the coal gasification device is internally collected, and the refiltered value of the effective data corresponding to the t moment in the operation data of the coal gasification device is acquired; (Y) L ) t-1 In a time period (t) 1 ,t Q ) The light filtering value (Y) of effective data corresponding to t-1 th time in the operation data of the coal gasification device is acquired H ) t-1 In a time period (t) 1 ,t Q ) The re-filtering value f of effective data corresponding to t-1 th time in the operation data of the coal gasification device collected internally L Is a light filter coefficient, f H Is a re-filtering coefficient; y is t The actual value of the valid data corresponding to the t-th moment; q is in the time period (t) 1 ,t Q ) The total number of moments corresponding to all effective data in the operation data of the coal gasification device collected internally;
b2, respectively calculating absolute values of light and heavy filtering value differences corresponding to effective data in the collected operation data of the coal gasification device, and acquiring the maximum value of the absolute values in all the obtained absolute values; wherein, the absolute value of the difference of the light and heavy filtering values of the effective data corresponding to the t-th moment in the collected operation data of the coal gasification device is marked as
The maximum absolute value among all the obtained absolute values is marked as
Step b3, making parameter steady state judgment according to the maximum value of the obtained absolute value:
when the maximum value of the obtained absolute value is obtained
When the steady-state tolerance value x is smaller than the preset parameter, the factory value of the effective data corresponding to the moment t is judged to be a steady-state value; otherwise, judging that the factory value of the effective data corresponding to the moment t is an unsteady state value;
step b4, making device steady state judgment according to the obtained re-filtering value of the effective data corresponding to the last moment and the re-filtering value of the effective data corresponding to the first moment:
when the absolute value of the difference between the two is less than the preset trend tolerance value, that is
Determining the time period t 1 ,t Q The coal gasification device state corresponding to the effective data in the system is a steady state; otherwise, the time period t is judged 1 ,t Q The coal gasification device state corresponding to the effective data in the system is unstable.
In the coal gasification plant process diagnosis method, the data correction includes the steps of: on the basis of original measurement data, determining a correction condition based on the minimum square sum of the deviation between a correction value and a corresponding measurement value by utilizing a material balance relation or an energy balance relation in the production process of a coal gasification device, and establishing a correction mathematical expression solved based on a least square method; wherein the corrected mathematical expression is as follows:
wherein X is a vector formed by measured values of measured variables, U is a vector formed by parameters which are not measured or to be estimated,
the vector is formed by corrected values of measured variables, P is a variance-covariance matrix of measurement errors, and F is a constraint equation of a coal gasification device model; wherein the constraint equation comprises a material balance equation, an energy balance equation, a chemical reaction rate equation, a chemical balance equation, a heat mass and momentum transfer equation; p determines the weight to adjust for each variable and gives higher weight to meters with higher accuracy.
The technical scheme adopted by the invention for solving the second technical problem is as follows: a coal gasification apparatus process diagnosis system for implementing the coal gasification apparatus process diagnosis method is characterized by comprising:
the data acquisition module is used for acquiring an operation data set in the operation process of the coal gasification device;
the data preprocessing module is used for preprocessing the operation data in the operation data set acquired by the data acquisition module to obtain a preprocessed operation data set and performing category processing on the preprocessed operation data set data;
the device model management module is used for managing a coal gasification device initial model and a process diagnosis model which are constructed in advance and used for simulating the operation of the coal gasification device;
and the process diagnosis module is responsible for setting the assessment technical parameters, calling the diagnosis model corresponding to the category of the preprocessed operation data set determined by the data preprocessing module, inputting the preprocessed operation data set into the process diagnosis model for diagnosis, and outputting a process diagnosis result.
Compared with the prior art, the invention has the advantages that: the coal gas device process diagnosis method comprises the steps of preprocessing operation data of a coal gasification device to form a sample database, pre-constructing an initialization model base of the coal gasification device for simulating the operation of the coal gasification device based on the data in the sample database, developing and forming a process diagnosis model base based on an initialization model, examination technical parameters and constraint conditions of the coal gasification device in the initialization model base, automatically matching and calling current operation data of the coal gasification device and a diagnosis model in the process diagnosis model base through a developed process diagnosis system of the coal gasification device, and realizing on-line diagnosis of the coal gasification device. The process diagnosis models in the process diagnosis model library of the coal gasification device developed by the method cover various working conditions of the coal gasification device, the robustness of the models is high, the user interface of the developed process diagnosis system of the coal gasification device is easy and convenient to operate, the difficulty in using the models is greatly reduced, continuous normalized process diagnosis can be performed on the coal gasification device, and the coal gasification device is guided to perform refined operation optimization.
Drawings
FIG. 1 is a schematic flow diagram of a coal gasification unit process diagnostic method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a coal gasification unit process diagnostic system in an embodiment of the invention.
Detailed Description
The invention is described in further detail below with reference to the following examples of the drawings.
The embodiment provides a coal gasification device process diagnosis method. Specifically, referring to fig. 1, the coal gasification apparatus process diagnosis method of the embodiment includes the following steps:
step S1, acquiring an operation data set in the operation process of the coal gasification device, and preprocessing the operation data in the operation data set to obtain a preprocessed operation data set;
step S2, adopting the operation data in the operation data set after pretreatment to pre-construct a coal gasification device initialization model base for simulating the operation of the coal gasification device; the coal gasification device initialization model library comprises subunit initialization models corresponding to W different subunits, the different subunit initialization models comprise M feeding types, each feeding type comprises N working condition types, each subunit initialization model respectively corresponds to a subunit operation condition in a simulated coal gasification device, and W is the total number of the subunit operation units actually included in the coal gasification device;
that is, if the coal gasification apparatus is formed by 10 sub-units, a sub-unit initialization model for simulating the operation condition of each sub-unit is constructed, that is, 10 sub-unit initialization models need to be constructed in advance; of course, each subunit initialization model includes input data and output data, for example, the input data is the operation data of a subunit, and the output data is the performance parameter corresponding to the subunit;
specifically, in this embodiment, the process for constructing the coal gasification apparatus initialization model includes the following steps a1 to a 3:
step a1, acquiring operation data of a coal gasification device, and performing validity processing on the operation data of the coal gasification device to form a basic database; the coal gasification device operation data comprises a coal gasification device real-time database and historical data collected by LIMS; the effectiveness processing comprises preprocessing, steady-state detection and data correction, wherein the preprocessing comprises invalid data elimination, interpolation fitting filling, filtering denoising and data normalization processing;
a2, based on basic database data, adopting a clustering algorithm to perform feed clustering and working condition clustering in sequence to form a sample data set library;
step a3, constructing an initialization model of the coal gasification device based on the formed sample number set database data;
s3, setting examination technical parameters and constraint conditions corresponding to the examination technical parameters based on the process diagnosis requirements, and developing and forming a process diagnosis model library based on the initialization model, the examination technical parameters and the constraint conditions in the coal gasification device initialization model library; the model in the process diagnosis model library is a diagnosis model for performing simulation analysis on key technical parameters of the coal gasification device, the key technical parameters are independent technical parameters relative to other technical parameters in the coal gasification device, and the other technical parameters in the coal gasification device are dependent technical parameters relative to the key technical parameters;
and step S4, acquiring the actual operation data of the coal gasification device again, inputting the acquired actual operation data into the process diagnosis model base for diagnosis, and obtaining the process diagnosis result of the coal gasification device. For example, the actual operating data may be real-time operating data of the called-up coal gasification plant or operating data of the coal gasification plant entered manually.
It should be noted that, in step a2 of this embodiment, the parameter data in the feeding characteristic parameter set are firstly grouped into M feeding categories, and then each feeding category in the M feeding categories is grouped into N working condition categories according to the parameter data in the working condition characteristic parameter set; the clustering distance is calculated in the following manner:
where n, m are the numbers of the feature parameter set Y, Y n ＝(x n1 ,x n2 ,…,x nJ )，Y m ＝(x m1 ,x m2 ,…,x mJ )，cosθ nm For the feature parameter set Y n And a feature parameter set Y m Cosine distance between, x nj For the feature parameter set Y n Data of the jth characteristic parameter in (1), corresponding to, x mj For the feature parameter set Y m J is a feature parameter set Y n The total number of characteristic parameters; feature parameter set Y n And a feature parameter set Y m With the same total number of characteristic parameters. In particular to this embodiment, the feed characteristic parameter set is a set formed by feed-related characteristic parameters such as feed composition and feed properties; the process characteristic parameter set is a set formed by aiming at parameters related to process parameters such as processing capacity, operating temperature and the like; and the clustering distance calculation mode adopted by the formula is adopted when clustering is carried out on the parameter data in the feeding characteristic parameter set and the parameter data in the working condition characteristic parameter set.
In addition, in step a1 of this embodiment, the invalid data elimination is to eliminate the operation data meeting the large error condition in the collected operation data of the coal gasification device, and the operation data meeting the large error condition is the operation data with the fluctuation coefficient value larger than the preset fluctuation coefficient threshold value in the collected operation data of the coal gasification device; the collected coal gasification device operation data is operation data collected in a preset time interval, and the fluctuation coefficient value of the kth operation data collected in the preset time interval is marked as tau k The preset fluctuation coefficient threshold corresponding to the preset time interval is marked as tau th ：
a k Is the kth operation data value a in the operation data of the coal gasification device collected in the preset time interval k-1 The k-1 operating data value mu in the operating data of the coal gasification device collected in the preset time interval a The average value of all operation data values of the operation data of the coal gasification device collected in the preset time interval is obtained; and K is the total amount of the operation data of the coal gasification device collected in the preset time interval.
Specifically, in this embodiment, the steady-state detection in step a1 is a heuristic steady-state detection; the steady state detection process comprises the following steps b 1-b 4:
b1, calculating a light filtering value and a heavy filtering value corresponding to each effective data in the coal gasification device operation data acquired in the step a 1; effective data in the collected coal gasification device operation data are residual data after invalid data are removed;
(Y L ) t ＝f L ·y t +(1-f L )·(Y L ) t-1 ；
(Y H ) t ＝f H ·y t +(1-f H )·(Y H ) t-1 ；
(Y L ) 0 ＝y t1 ，(Y H ) 0 ＝y t1 ；
t 1 ≤t≤t Q ；
wherein, the time period (t) 1 ,t Q ) For the period of time for collecting the operation data of the coal gasification apparatus collected in the step a1, (Y) L ) t In a time period (t) 1 ,t Q ) The light filtering value (Y) of effective data corresponding to the t-th moment in the operation data of the coal gasification device is acquired internally H ) t In a time period (t) 1 ,t Q ) The operation data of the coal gasification device is internally collected, and the refiltered value of the effective data corresponding to the t moment in the operation data of the coal gasification device is acquired; (Y) L ) t-1 In a time period (t) 1 ,t Q ) The light filtering value (Y) of effective data corresponding to t-1 th time in the operation data of the coal gasification device is acquired H ) t-1 In a time period (t) 1 ,t Q ) The re-filtering value f of effective data corresponding to t-1 th time in the operation data of the coal gasification device collected internally L Is a light filter coefficient, f H Is a re-filtering coefficient; y is t The actual value of the valid data corresponding to the t-th moment; q is in the time period (t) 1 ,t Q ) The total number of moments corresponding to all effective data in the operation data of the coal gasification device collected internally;
b2, respectively calculating absolute values of light and heavy filtering value differences corresponding to effective data in the collected operation data of the coal gasification device, and acquiring the maximum value of the absolute values in all the obtained absolute values; wherein, the absolute value of the difference of the light and heavy filtering values of the effective data corresponding to the t-th moment in the collected operation data of the coal gasification device is marked as
The maximum absolute value among all the obtained absolute values is marked as
Step b3, making parameter steady state judgment according to the maximum value of the obtained absolute value:
when the maximum value of the obtained absolute value is obtained
When the steady-state tolerance value x is smaller than the preset parameter, the factory value of the effective data corresponding to the moment t is judged to be a steady-state value; otherwise, judging that the factory value of the effective data corresponding to the moment t is an unsteady state value;
it should be noted that, in this embodiment, the preset parameter steady-state tolerance value χ is calculated as follows:
χ＝(2±b)·σ，b>0，
wherein, a k Is a preset time interval (t) 1 ,t Q ) The K operation data value in the operation data of the coal gasification device is acquired, and K is the preset time interval (t) 1 ,t Q ) Total amount of operating data of the coal gasification device collected in the coal gasification system;
step b4, making device steady state judgment according to the obtained re-filtering value of the effective data corresponding to the last moment and the re-filtering value of the effective data corresponding to the first moment:
when the absolute value of the difference between the two is less than the preset trend tolerance value epsilon, that is
Determining the time period t 1 ,t Q ]The coal gasification device state corresponding to the internal effective data is a steady state; otherwise, the time period t is judged 1 ,t Q ]The coal gasification device state corresponding to the internal effective data is unstable. In this embodiment, the preset tendency tolerance value ε is calculated as follows:
0<ε<5％·μ a ，
wherein, a k Is a preset time interval (t) 1 ,t Q ) A kth operation data value in the operation data of the coal gasification device collected in the coal gasification device; k is the predetermined time interval (t) 1 ,t Q ) Total amount of coal gasification device operation data collected in the coal gasification device.
In addition, in step a1, the data correction process includes the steps of: on the basis of original measurement data, determining a correction condition based on the minimum square sum of the deviation between a correction value and a corresponding measurement value by utilizing a material balance relation or an energy balance relation in the production process of a coal gasification device, and establishing a correction mathematical expression solved based on a least square method; wherein the corrected mathematical expression is as follows:
wherein X is a vector formed by measured values of measured variables, U is a vector formed by parameters which are not measured or to be estimated,
the vector is formed by corrected values of measured variables, P is a variance-covariance matrix of measurement errors, and F is a constraint equation of a coal gasification device model; wherein the constraint equation comprises a material balance equation, an energy balance equation, a chemical reaction rate equation, a chemical balance equation, a heat mass and momentum transfer equation; p determines the weight to adjust for each variable and gives higher weight to meters with higher accuracy.
The embodiment also provides a coal gasification device process diagnosis system for realizing the coal gasification device process diagnosis method. Specifically, the coal gasification apparatus process diagnosis system of the embodiment includes:
the data acquisition module 1 is used for acquiring an operation data set in the operation process of the coal gasification device;
the data preprocessing module 2 is used for preprocessing the operation data in the operation data set acquired by the data acquisition module 1 to obtain a preprocessed operation data set and performing classification processing on the preprocessed operation data set data;
a device model management module 3 for managing a coal gasification device initial model and a process diagnosis model which are constructed in advance and simulate the operation of a coal gasification device;
and the process diagnosis module 4 is responsible for setting the assessment technical parameters and calling the diagnosis model corresponding to the category to which the preprocessed operation data set determined by the data preprocessing module belongs, inputting the preprocessed operation data set into the process diagnosis model for diagnosis and outputting a process diagnosis result.
Although preferred embodiments of the present invention have been described in detail hereinabove, it should be clearly understood that modifications and variations of the present invention are possible to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The coal gasification device process diagnosis method is characterized by comprising the following steps:
step S1, acquiring an operation data set in the operation process of the coal gasification device, and preprocessing the operation data in the operation data set to obtain a preprocessed operation data set;
step S2, adopting the operation data in the operation data set after pretreatment to pre-construct a coal gasification device initialization model base for simulating the operation of the coal gasification device; the coal gasification device initialization model library comprises subunit initialization models corresponding to W different subunits, the different subunit initialization models comprise M feeding types, each feeding type comprises N working condition types, each subunit initialization model respectively corresponds to a subunit operation condition in a simulated coal gasification device, and W is the total number of the subunit operation units actually included in the coal gasification device;
s3, setting examination technical parameters and constraint conditions corresponding to the examination technical parameters based on the process diagnosis requirements, and developing and forming a process diagnosis model library based on the initialization model, the examination technical parameters and the constraint conditions in the coal gasification device initialization model library;
and step S4, acquiring the actual operation data of the coal gasification device again, and inputting the acquired actual operation data into the process diagnosis model base for diagnosis to obtain the process diagnosis result of the coal gasification device.
2. The coal gasification apparatus process diagnosis method according to claim 1, wherein the model in the process diagnosis model library is a diagnosis model having a simulation analysis for a key technical parameter of the coal gasification apparatus, the key technical parameter is an independent technical parameter with respect to other technical parameters in the coal gasification apparatus, and the other technical parameters in the coal gasification apparatus are dependent technical parameters with respect to the key technical parameter.
3. The coal gasification apparatus process diagnosis method according to claim 1, further comprising a process of displaying the retrieved real-time operation data in a visual manner; or/and displaying the coal gasification device process diagnosis result in a visual mode.
4. The coal gasification apparatus process diagnosis method according to any one of claims 1 to 3, wherein in step S2, the coal gasification apparatus initialization model is constructed by the following steps a1 to a 3:
step a1, acquiring operation data of a coal gasification device, and performing validity processing on the operation data of the coal gasification device to form a basic database; the coal gasification device operation data comprises a coal gasification device real-time database and historical data collected by LIMS;
a2, based on basic database data, adopting a clustering algorithm to perform feed clustering and working condition clustering in sequence to form a sample data set library;
step a3, constructing an initialization model of the coal gasification device based on the formed sample number set database.
5. The coal gasification apparatus process diagnostic method according to claim 4, wherein in step a2, the parameter data are grouped into M feed categories according to the feed characteristic parameter set, and each of the M feed categories is grouped into N working condition categories according to the working condition characteristic parameter set; the clustering distance is calculated in the following manner:
where n, m are the numbers of the feature parameter set Y, Y n ＝(x n1 ,x n2 ,…,x nJ )，Y m ＝(x m1 ,x m2 ,…,x mJ )，cosθ nm For the feature parameter set Y n And a feature parameter set Y m Cosine distance between, x nj For the feature parameter set Y n Data of the jth characteristic parameter in (1), corresponding to, x mj Set of parameters Y for the features m J is a feature parameter set Y n The total number of characteristic parameters; feature parameter set Y n And a feature parameter set Y m With the same total number of characteristic parameters.
6. The coal gasification plant process diagnostic method according to claim 5, wherein the validity processing in step a1 comprises preprocessing, steady state detection and data correction, and the preprocessing comprises invalid data elimination, interpolation fitting filling, filtering denoising and data normalization processing.
7. The coal gasification device process diagnosis method according to claim 6, wherein in step a1, the invalid data is removed to remove the operation data satisfying the large error condition from the collected operation data of the coal gasification device, and the operation data satisfying the large error condition is the operation data having a coefficient of fluctuation value greater than a preset threshold value of fluctuation coefficient from the collected operation data of the coal gasification device; the collected coal gasification device operation data is operation data collected in a preset time interval, and the fluctuation coefficient value of the kth operation data collected in the preset time interval is marked as tau k The preset fluctuation coefficient threshold corresponding to the preset time interval is marked as tau th ：
a k Operating data of the coal gasification device collected in the preset time intervalOf the kth operational data value, a k-1 The k-1 operating data value mu in the operating data of the coal gasification device collected in the preset time interval a The average value of all the operation data values of the operation data of the coal gasification device collected in the preset time interval is obtained; and K is the total amount of the operation data of the coal gasification device collected in the preset time interval.
8. The coal gasification plant process diagnostic method of claim 6, wherein the steady state detection is a heuristic steady state detection; the steady state detection process comprises the following steps b 1-b 4:
b1, calculating a light filtering value and a heavy filtering value corresponding to each effective data in the coal gasification device operation data collected in the step a 1; effective data in the collected coal gasification device operation data are residual data after invalid data are removed;
(Y L ) t ＝f L ·y t +(1-f L )·(Y L ) t-1 ；
(Y H ) t ＝f H ·y t +(1-f H )·(Y H ) t-1 ；
t 1 ≤t≤t Q ；
wherein, the time period (t) 1 ,t Q ) For the period of time for collecting the operation data of the coal gasification apparatus collected in the step a1, (Y) L ) t In a time period (t) 1 ,t Q ) The light filtering value (Y) of effective data corresponding to the t-th moment in the operation data of the coal gasification device is acquired internally H ) t In a time period (t) 1 ,t Q ) The operation data of the coal gasification device is internally collected, and the refiltered value of the effective data corresponding to the t moment in the operation data of the coal gasification device is acquired; (Y) L ) t-1 In a time period (t) 1 ,t Q ) Internally collected operating data of the coal gasification deviceThe value of the light filter of the valid data corresponding to the internal t-1 time, (Y) H ) t-1 In a time period (t) 1 ,t Q ) The re-filtering value f of effective data corresponding to t-1 th time in the operation data of the coal gasification device collected internally L Is a light filter coefficient, f H Is a re-filtering coefficient; y is t The actual value of the valid data corresponding to the t-th moment; q is in the time period (t) 1 ,t Q ) The total number of moments corresponding to all effective data in the operation data of the coal gasification device collected internally;
b2, respectively calculating absolute values of light and heavy filtering value differences corresponding to effective data in the collected operation data of the coal gasification device, and acquiring the maximum value of the absolute values in all the obtained absolute values; wherein, the absolute value of the difference of the light and heavy filtering values of the effective data corresponding to the t-th moment in the collected operation data of the coal gasification device is marked as
The maximum absolute value among all the obtained absolute values is marked as
Step b3, making parameter steady state judgment according to the maximum value of the obtained absolute value:
when the maximum value of the obtained absolute value is obtained
When the steady-state tolerance value x is smaller than the preset parameter, the factory value of the effective data corresponding to the moment t is judged to be a steady-state value; otherwise, judging that the factory value of the effective data corresponding to the moment t is an unsteady state value;
step b4, making device steady state judgment according to the obtained re-filtering value of the effective data corresponding to the last moment and the re-filtering value of the effective data corresponding to the first moment:
when the absolute value of the difference between the two is less than the preset trend tolerance value, that is
Determining the time period t 1 ,t Q ]The coal gasification device state corresponding to the internal effective data is a steady state; otherwise, the time period t is judged 1 ,t Q ]The coal gasification device state corresponding to the internal effective data is unstable.
9. The coal gasification apparatus process diagnostic method of claim 6, wherein the data correction comprises the steps of: on the basis of original measurement data, determining a correction condition based on the minimum square sum of the deviation between a correction value and a corresponding measurement value by utilizing a material balance relation or an energy balance relation in the production process of a coal gasification device, and establishing a correction mathematical expression solved based on a least square method; wherein the corrected mathematical expression is as follows:
wherein X is a vector formed by measured values of measured variables, U is a vector formed by parameters which are not measured or to be estimated,
the vector is formed by corrected values of measured variables, P is a variance-covariance matrix of measurement errors, and F is a constraint equation of a coal gasification device model; wherein the constraint equation comprises a material balance equation, an energy balance equation, a chemical reaction rate equation, a chemical balance equation, a heat mass and momentum transfer equation; p determines the weight of each variable to be adjusted, andhigher precision meters are given higher weight.
10. A coal gasification apparatus process diagnostic system for implementing the coal gasification apparatus process diagnostic method according to claim 1, characterized by comprising:
the data acquisition module is used for acquiring an operation data set in the operation process of the coal gasification device;
the data preprocessing module is used for preprocessing the operation data in the operation data set acquired by the data acquisition module to obtain a preprocessed operation data set and performing category processing on the preprocessed operation data set data;
the device model management module is used for managing a coal gasification device initial model and a process diagnosis model which are constructed in advance and used for simulating the operation of the coal gasification device;
and the process diagnosis module is responsible for setting the assessment technical parameters, calling the diagnosis model corresponding to the category of the preprocessed operation data set determined by the data preprocessing module, inputting the preprocessed operation data set into the process diagnosis model for diagnosis, and outputting a process diagnosis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210554979.1A CN114861810A (en) | 2022-05-20 | 2022-05-20 | Coal gasification device process diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210554979.1A CN114861810A (en) | 2022-05-20 | 2022-05-20 | Coal gasification device process diagnosis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114861810A true CN114861810A (en) | 2022-08-05 |
Family
ID=82638534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210554979.1A Pending CN114861810A (en) | 2022-05-20 | 2022-05-20 | Coal gasification device process diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114861810A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075498A (en) * | 2023-10-16 | 2023-11-17 | 三峡科技有限责任公司 | Water electrolysis hydrogen production energy consumption monitoring and bionic optimizing system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764626A (en) * | 2018-04-19 | 2018-11-06 | 武汉钢铁有限公司 | A kind of diagnosis of energy saving method and apparatus |
| CN111898976A (en) * | 2020-07-20 | 2020-11-06 | 中国石油化工股份有限公司 | Online monitoring and intelligent operation system of steam power system |
| US20210065021A1 (en) * | 2018-12-17 | 2021-03-04 | Shenyang Institute Of Automation, Chinese Academy Of Sciences | Working condition state modeling and model correcting method |
| CN113050548A (en) * | 2019-12-26 | 2021-06-29 | 上海异工同智信息科技有限公司 | Auxiliary decision making system and method based on field production experience and chemical mechanism model, electronic device and storage medium |
-
2022
- 2022-05-20 CN CN202210554979.1A patent/CN114861810A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764626A (en) * | 2018-04-19 | 2018-11-06 | 武汉钢铁有限公司 | A kind of diagnosis of energy saving method and apparatus |
| US20210065021A1 (en) * | 2018-12-17 | 2021-03-04 | Shenyang Institute Of Automation, Chinese Academy Of Sciences | Working condition state modeling and model correcting method |
| CN113050548A (en) * | 2019-12-26 | 2021-06-29 | 上海异工同智信息科技有限公司 | Auxiliary decision making system and method based on field production experience and chemical mechanism model, electronic device and storage medium |
| CN111898976A (en) * | 2020-07-20 | 2020-11-06 | 中国石油化工股份有限公司 | Online monitoring and intelligent operation system of steam power system |
Non-Patent Citations (1)
| Title |
|---|
| 谭章禄;张丽娜;吕明;: "基于人工神经网络和模糊诊断技术的煤矿安全预测系统", 矿业安全与环保, no. 05, 10 October 2012 (2012-10-10) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075498A (en) * | 2023-10-16 | 2023-11-17 | 三峡科技有限责任公司 | Water electrolysis hydrogen production energy consumption monitoring and bionic optimizing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN107273924B (en) | Multi-data fusion power plant fault diagnosis method based on fuzzy clustering analysis | |
| CN102880905B (en) | Online soft measurement method for normal oil dry point | |
| CN102736558A (en) | Numerical control machine tool thermal error real-time compensation modeling method based on time series algorithm | |
| CN101436057A (en) | Numerical control machining tool heat error Bayes network compensation method | |
| CN108053110A (en) | A kind of transformer state inline diagnosis method based on PMU data | |
| CN105868164B (en) | A kind of soft-measuring modeling method based on the linear dynamic system model for having supervision | |
| CN117574780B (en) | Intelligent thermal power plant load online modeling method and system | |
| CN110852496A (en) | Natural gas load prediction method based on LSTM recurrent neural network | |
| CN114881374B (en) | Multi-element heterogeneous energy consumption data fusion method and system for building energy consumption prediction | |
| CN114861810A (en) | Coal gasification device process diagnosis method and system | |
| CN114548494B (en) | Visual cost data prediction intelligent analysis system | |
| CN112547807A (en) | Decision tree algorithm-based hot rolled strip quality accurate judgment method | |
| CN117029968A (en) | Traffic data diagnosis method, system, storage medium and electronic equipment | |
| CN117709555B (en) | Carbon emission prediction and evaluation method and system based on transformer carbon accounting model | |
| CN108204997A (en) | Normal line oil flash point on-line soft measurement method | |
| CN117553840A (en) | Instrument based on intelligent management and system thereof | |
| CN103389360A (en) | Probabilistic principal component regression model-based method for soft sensing of butane content of debutanizer | |
| CN101598754B (en) | System and method for automatic virtual metrology | |
| CN102289718A (en) | Method for softly measuring height of mud layer in settlement process of red mud | |
| CN112949816A (en) | ANN-based method and system for identifying abnormal data of hydrostatic level | |
| CN115985411A (en) | Soft measurement method for polymer melt index based on Gaussian process regression model | |
| CN113537759A (en) | User experience measurement model based on weight self-adaptation | |
| CN117113886B (en) | Pressure prediction method and device | |
| CN115952853B (en) | Method and device for constructing ore pulp density detection model and ore pulp density detection system |
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 |