CN116821632A - Household garbage incineration facility stability assessment and control method - Google Patents
Household garbage incineration facility stability assessment and control method Download PDFInfo
- Publication number
- CN116821632A CN116821632A CN202310964950.5A CN202310964950A CN116821632A CN 116821632 A CN116821632 A CN 116821632A CN 202310964950 A CN202310964950 A CN 202310964950A CN 116821632 A CN116821632 A CN 116821632A
- Authority
- CN
- China
- Prior art keywords
- data
- household garbage
- garbage incineration
- stability
- evaluating
- 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
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013097 stability assessment Methods 0.000 title description 2
- 238000011156 evaluation Methods 0.000 claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 5
- 239000003546 flue gas Substances 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 2
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 239000000428 dust Substances 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000013179 statistical model Methods 0.000 claims description 2
- 238000005406 washing Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000007704 transition Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- HGUFODBRKLSHSI-UHFFFAOYSA-N 2,3,7,8-tetrachloro-dibenzo-p-dioxin Chemical compound O1C2=CC(Cl)=C(Cl)C=C2OC2=C1C=C(Cl)C(Cl)=C2 HGUFODBRKLSHSI-UHFFFAOYSA-N 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000002910 solid waste Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses a method for evaluating and controlling the stability of a household garbage incineration facility, which belongs to the technical field of the method for evaluating and controlling the stability of the garbage incineration, adopts a neural network to carry out evaluation on the data of a subsystem, can extract characteristics of a cross subsystem, solves the problem of weight distribution in classification, adopts a self-coding framework to extract the characteristics of the data, avoids the influence of subjective factors to the maximum extent, can directly map an evaluation result to control parameters, adopts a visual evaluation interface to display, and is beneficial to operators to adjust in real time according to control targets during field application.
Description
Technical Field
The invention relates to a method for evaluating and controlling the stability of garbage incineration, in particular to a method for evaluating and controlling the stability of household garbage incineration facilities, and belongs to the technical field of methods for evaluating and controlling the stability of garbage incineration.
Background
According to the statistical publication, the incineration disposal of household garbage is the main disposal mode in China at present.
The correct evaluation of the household garbage incineration disposal industry is an effective means for promoting the development of the industry.
At present, the operation evaluation standard of the household garbage incineration power plant is mainly "household garbage incineration plant evaluation standard" issued by the construction department of housing and urban and rural areas (CJJ/T137-2019), and part of group evaluation standards are also required. The standards are mainly hierarchical models, and standard evaluation is carried out by comparing the different subsystems with corresponding execution standards.
With the gradual perfection of the technical development of the household garbage incineration industry, the problems of green low carbon, improved efficiency and the like are replaced by the problems reaching standards, and the problems are the problems to be solved urgently.
Developing an assessment of operational stability below standard to facilitate industry fine management is highly desirable.
Along with the increasing capacity of the household garbage incineration facilities, more and more general industrial solid wastes, town sludge and the like enter the household garbage incinerator for cooperative treatment, so that the heat value of the household garbage is frequently changed.
The generation of dioxin in a household garbage incineration facility is related to the incineration states such as physical and chemical reactions, combustion conditions and the like in the incineration process, and the fluctuation of the incineration states can cause unstable dioxin emission, so that stability evaluation below the standard is carried out, and stable dioxin emission is necessary.
The state space of the incineration system is formed by the combination of various parameters and variables of the incineration system, and belongs to the high latitude space.
Because of the difficulty in sampling and representing parameters and variables, numerical analysis cannot be used to accurately describe them.
The analytic hierarchy process can complete stability evaluation to a certain extent, but has the defects of weight subjectivity and incapability of tracing control parameters to guide the scene.
The standard evaluation is aimed at evaluating a single index, and the index fluctuation evaluation cannot be realized, so that the stability evaluation and control method of the household garbage incineration facility is designed to solve the problems.
Disclosure of Invention
The invention mainly aims to provide a method for evaluating and controlling the stability of a household garbage incineration facility, which adopts a neural network to evaluate the data of a subsystem, can extract characteristics of a cross subsystem and solves the problem of weight distribution in classification.
The self-coding framework is adopted to extract the characteristics of the data, so that the characteristics of the data are furthest explored, and the influence of subjective factors is avoided.
The evaluation result can be directly mapped to the control parameter, and is displayed by adopting a visual evaluation interface, so that the real-time adjustment of operators according to actual requirements is facilitated during field application.
The aim of the invention can be achieved by adopting the following technical scheme:
a method for evaluating and controlling the stability of a household garbage incineration facility is characterized by comprising the following steps of: the method comprises the following steps:
constructing a database for storing time sequence data of each subsystem of the household garbage incineration system;
a data acquisition module is constructed and used for acquiring the data from each subsystem or DCS system;
the data processing module is used for processing and standardizing the acquired data;
constructing an encoder for data feature compression;
constructing a decoder, and training a self-encoder for decoding and restoring data into original data;
establishing an unsupervised classification model for classifying the compressed features;
constructing a data classification statistical model for statistical analysis of the classified raw data;
and constructing a data visual evaluation interface for displaying an evaluation result.
Preferably, each subsystem comprises a steam-water system, a flue gas system, a fan system, a hydraulic system, a deacidification system, a bag-type dust remover, a GGH, a wet-type washing tower, an SGH, an SCR and a flue gas on-line monitoring system.
Preferably, in the data acquisition module, the instantaneous data transmitted from the equipment are averaged for a plurality of different periods of 30s, 1min, 5min and 1 h.
Preferably, the values are normalized by Z-Score, and different amounts of data are converted into uniform metric data.
Preferably, the target from the encoder encodes the acquired data X into h of lower dimension to discard unimportant information and then restores h to X'.
Preferably, the normalization method is as follows:
wherein x is ij For the jth feature of the ith sample, mean (x j ) Mean value of jth feature, std (x j ) Is the standard deviation of the j-th feature.
Preferably, the encoder is constructed from an encoder having the mathematical expression:
h i ＝g(x i )；
wherein:
h i representing potential features of the incineration system as an output of the encoder;
g(x i ) Constructing g with a neural network for an encoder, and compressing 32 feature codes into 7 features;
a decoder is constructed, and the mathematical expression of the decoder is as follows:
wherein:
x i a reconstructed output for the decoder;
f(h i ) For the decoder, f was constructed with a neural network, recovering from 7 features to 32 features.
The beneficial technical effects of the invention are as follows:
according to the method for evaluating and controlling the stability of the household garbage incineration facility, disclosed by the invention, the data of the subsystem is evaluated by adopting the neural network, so that characteristics can be extracted from the cross-subsystem, and the problem of weight distribution in classification is solved.
The self-coding framework is adopted to extract the characteristics of the data, so that the characteristics of the data are furthest explored, and the influence of subjective factors is avoided.
The evaluation result can be directly mapped to the control parameter, and is displayed by adopting a visual evaluation interface, so that the real-time adjustment of operators according to actual requirements is facilitated during field application.
Drawings
Fig. 1 is a flowchart of a preferred embodiment of a method for evaluating and controlling the stability of a household garbage incineration facility according to the present invention.
Detailed Description
In order to make the technical solution of the present invention more clear and obvious to those skilled in the art, the present invention will be described in further detail with reference to examples and drawings, but the embodiments of the present invention are not limited thereto.
The instantaneous data of all subsystems of the household garbage incineration system such as the steam-water system, the air-smoke system, the fan system and the like are collected from the original equipment or the DCS central control system through the data collection module.
The index selected in this example is shown in the following table, and is a total of 32 features:
the data preprocessing module is used for marking the acquired instantaneous data according to the normal and abnormal conditions of the sensor and the running facilities, calculating an arithmetic mean value of the data of the normal sensor according to the time periods of 30s, 1min, 5min, 1h and the like, and storing the arithmetic mean value to the database.
This example uses a 2h mean calculation.
Taking out and standardizing original data marked as normal stored in a database by adopting a data preprocessing module;
the standardized method comprises the following steps:
wherein x is ij For the jth feature of the ith sample, mean (x j ) Mean value of jth feature, std (x j ) Is the standard deviation of the j-th feature.
Constructing a self-encoder, wherein the mathematical expression of the encoder is as follows:
h i ＝g(x i )；
wherein: h is a i Representing potential features of the incineration system as an output of the encoder; g (x) i ) For the encoder, the present example constructs g with a neural network, compressing 32 feature codes into 7 features.
A decoder is constructed, and the mathematical expression of the decoder is as follows:
x i a reconstructed output for the decoder; f (h) i ) For the decoder, the present example constructs f with a neural network, recovering from 7 features to 32 features.
The loss function (reconstruction error), in this example with Mean Square Error (MSE) as the loss function (reconstruction error), is constructed as follows.
Training the self-encoder, and stopping training after the loss functions (reconstruction errors) of the training set and the verification set are smaller than 0.6 to obtain the self-encoder.
The data in 2 are encoded by an encoder to obtain an encoding result h i 。
By k-means for h i And carrying out unsupervised classification, storing cluster centers, and determining the number of the cluster centers by adopting a contour coefficient method.
The present example employs k-means clustering, which is 4 classes.
And calculating the incineration state change condition of the statistic period by adopting shannon entropy or a coefficient of kene. This example uses shannon entropy calculation, as follows:
Entropy＝-∑p(x)logp(p(x))；
entropy represents shannon Entropy and p (x) represents the probability that a symbol x in the sequence will occur.
The shannon entropy calculated in this example is 1.86, and the shannon entropy has a value range of [0, log2 (n) ], where n is the number of clusters. The larger the shannon entropy is, the more frequently the incineration state changes are, and the value range of the shannon entropy in the example is [0,2].
Calculating the transition frequency of each category to obtain a transition probability matrix, wherein a 1-step transition probability calculation formula is as follows:
wherein: p { X m+1 ＝a j |X m ＝a i The state of m time is a i The state at time m+1 is a j Is a probability of (2).
The shannon entropy of the transition probability matrix is calculated, and the calculation formula is as follows:
Entropy＝-∑p i，j logp(p i，j )；
p i，j representing the transition probability from state i to state j.
The 1-step transition probability of this example is shown in the following table, the shannon entropy is 6.78, the value range is [0,8], and the larger the shannon entropy, the more dispersed the 1-step transition representing the incineration state, the more random and uncontrollable the incineration state change.
| Class 0 | Class 1 | Class 2 | Class 3 | |
| Class 0 | 0.36 | 0.40 | 0.20 | 0.04 |
| Class 1 | 0.14 | 0.55 | 0.10 | 0.22 |
| Class 2 | 0.17 | 0.26 | 0.48 | 0.10 |
| Class 3 | 0.13 | 0.40 | 0.04 | 0.42 |
The clustering radius of the target state and the statistical result thereof are calculated, the clustering radius of the example and the statistical result thereof are shown in the following table, the comprehensive variation coefficient is calculated to be 0.8 by adopting a weighted average method, the value range of the comprehensive variation coefficient is generally [0,1], when the comprehensive variation coefficient is larger than 1, abnormal values need to be considered to be removed, and the larger the comprehensive variation coefficient is, the more unstable the operation of the household garbage factory is.
| Project | Class 0 | Class 1 | Class 2 | Class 3 |
| count | 46 | 111 | 42 | 52 |
| mean | 5339 | 5267 | 2971 | 4192 |
| std | 4166 | 3801 | 2558 | 3376 |
| Coefficient of variation | 0.8 | 0.7 | 0.9 | 0.8 |
And calculating the comprehensive stability of the incineration state. The overall stability index is calculated using the following formula:
according to the classification result, drawing a frequency distribution diagram of each parameter of each category, taking the mean value of each parameter plus or minus 2 times of standard deviation as the upper limit and the lower limit of the value range of the parameter of the category, and taking the mean value of each parameter plus or minus 2 times of standard deviation as the control range of each parameter of the category. Class 2 in this example is characterized by high steam flow and low polluting emissions and is therefore considered as an optimal control objective.
/>
And according to the real-time parameters, evaluating the attribution of the real-time category, taking the category 2 high main steam flow and low emission category as control targets, implementing the adjustment of the working conditions and the flue gas treatment facilities, and realizing the fine management and control.
The above is merely a further embodiment of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art will be able to apply equivalents and modifications according to the technical solution and the concept of the present invention within the scope of the present invention disclosed in the present invention.
Claims (7)
1. A method for evaluating and controlling the stability of a household garbage incineration facility is characterized by comprising the following steps of: the method comprises the following steps:
constructing a database for storing time sequence data of each subsystem of the household garbage incineration system;
a data acquisition module is constructed and used for acquiring the data from each subsystem or DCS system;
the data processing module is used for processing and standardizing the acquired data;
constructing an encoder for data feature compression;
constructing a decoder, and training a self-encoder for decoding and restoring data into original data;
establishing an unsupervised classification model for classifying the compressed features;
constructing a data classification statistical model for statistical analysis of the classified raw data;
and constructing a data visual evaluation interface for displaying an evaluation result.
2. A method for evaluating and controlling the stability of a household garbage incineration facility according to claim 1, comprising the steps of: each subsystem comprises a steam-water system, a flue gas system, a fan system, a hydraulic system, a deacidification system, a bag-type dust remover, a GGH, a wet-type washing tower, an SGH, an SCR and a flue gas on-line monitoring system.
3. A method for evaluating and controlling the stability of a household garbage incineration facility according to claim 1, comprising the steps of: and in the data acquisition module, the instantaneous data transmitted from the equipment are averaged according to a plurality of different periods of 30s, 1min, 5min and 1 h.
4. A method for evaluating and controlling the stability of a household garbage incineration facility according to claim 2, comprising the steps of: the values are normalized by Z-Score, and different amounts of data are converted into unified metric data.
5. A method for evaluating and controlling the stability of a household garbage incineration facility according to claim 1, comprising the steps of: the target from the encoder encodes the acquired data X into h of lower dimension to discard unimportant information and then restores h to X'.
6. A method for evaluating and controlling the stability of a household garbage incineration facility according to claim 2, comprising the steps of: the standardized method comprises the following steps:
wherein x is ij For the jth feature of the ith sample, mean (x j ) Mean value of jth feature, std (x j ) Is the j-th featureStandard deviation.
7. A method for evaluating and controlling the stability of a household garbage incineration facility according to claim 1, comprising the steps of: constructing a self-encoder, wherein the mathematical expression of the encoder is as follows:
h i ＝g(x i )；
wherein:
h i representing potential features of the incineration system as an output of the encoder;
g(x i ) Constructing g for an encoder by using a neural network, and compressing the selected feature codes into fewer features;
a decoder is constructed, and the mathematical expression of the decoder is as follows:
wherein:
x i a reconstructed output for the decoder;
f(h i ) For the decoder, f is constructed with a neural network, recovering from the smaller features to the selected features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310964950.5A CN116821632A (en) | 2023-08-02 | 2023-08-02 | Household garbage incineration facility stability assessment and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310964950.5A CN116821632A (en) | 2023-08-02 | 2023-08-02 | Household garbage incineration facility stability assessment and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116821632A true CN116821632A (en) | 2023-09-29 |
Family
ID=88114713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310964950.5A Pending CN116821632A (en) | 2023-08-02 | 2023-08-02 | Household garbage incineration facility stability assessment and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116821632A (en) |
-
2023
- 2023-08-02 CN CN202310964950.5A patent/CN116821632A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110518880B (en) | Photovoltaic power station state diagnosis method and device | |
| CN110927654B (en) | Batch running state evaluation method for intelligent electric energy meters | |
| CN111077869A (en) | Optimization control method and system for big data intelligent control bag-type dust collector | |
| CN108282026A (en) | A kind of high-tension switch gear novel maintenance system | |
| CN110889088A (en) | Enterprise pollution discharge supervision method assisted by electric model | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN113494939A (en) | Distributed monitoring method for rural domestic sewage | |
| CN114912787A (en) | Intelligent assessment method for enterprise dangerous waste concealing, reporting and missing reporting risks | |
| CN114580291A (en) | LSTM-VAE-based mobile equipment health condition assessment method | |
| CN110426996B (en) | Environmental pollution monitoring method based on big data and artificial intelligence | |
| CN115453267A (en) | Fault diagnosis system for electric power information system | |
| CN117151701B (en) | Industrial waste heat recycling system for cogeneration | |
| CN116821610B (en) | Method for optimizing wind power generation efficiency by utilizing big data | |
| CN116821632A (en) | Household garbage incineration facility stability assessment and control method | |
| CN116167659B (en) | Carbon market carbon emission data quality evaluation method | |
| CN117056688A (en) | New material production data management system and method based on data analysis | |
| CN109615239B (en) | Urban air quality assessment method based on social network media data | |
| CN110889495A (en) | State maintenance analysis method for silk making equipment based on active parameters | |
| JP4341950B2 (en) | Remote monitoring system | |
| CN113431800A (en) | Method for distinguishing running state of fan in real time | |
| CN112328707A (en) | Operation action recognition method based on real-time data of power plant | |
| CN117152355B (en) | Visual supervision system based on factory data | |
| CN117311295B (en) | Production quality improving method and system based on wireless network equipment | |
| CN116629642B (en) | Carbon emission assessment method, device and equipment | |
| CN117234785B (en) | Centralized control platform error analysis system based on artificial intelligence self-query |
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 |