CN117668481A - Non-invasive coal chemical industry carbon capture efficiency evaluation method and system - Google Patents
Non-invasive coal chemical industry carbon capture efficiency evaluation method and system Download PDFInfo
- Publication number
- CN117668481A CN117668481A CN202311612086.9A CN202311612086A CN117668481A CN 117668481 A CN117668481 A CN 117668481A CN 202311612086 A CN202311612086 A CN 202311612086A CN 117668481 A CN117668481 A CN 117668481A
- Authority
- CN
- China
- Prior art keywords
- data
- carbon capture
- capture efficiency
- coal chemical
- chemical industry
- 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
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 77
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 77
- 239000003245 coal Substances 0.000 title claims abstract description 51
- 238000011156 evaluation Methods 0.000 title claims abstract description 28
- 239000000126 substance Substances 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 26
- 238000001311 chemical methods and process Methods 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 11
- 230000015654 memory Effects 0.000 claims abstract description 9
- 238000013136 deep learning model Methods 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of environmental monitoring, in particular to a non-invasive coal chemical industry carbon capture efficiency evaluation method and system. The method comprises the steps of obtaining sensing data of a coal chemical process; according to the acquired sensing data, analyzing the sensing data by using a deep learning model; the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result. Through the technical scheme, the method and the device can provide comprehensive data analysis and decision support for the user, help the user to better know and manage the carbon capture process, optimize the operation efficiency and improve the business result.
Description
Technical Field
The invention relates to the technical field of environmental monitoring, in particular to a non-invasive coal chemical industry carbon capture efficiency evaluation method and system.
Background
With the increasing severity of climate change problems, the coal industry is faced with a pressure to reduce greenhouse gas emissions. Carbon capture, utilization and storage (CCUS) technology is one of the key technologies to reduce these emissions. However, the existing carbon capture efficiency evaluation method has the problems of incomplete monitoring, untimely reaction and the like, and the optimization and the efficiency improvement of the carbon capture technology are limited.
Specific disadvantages of the existing carbon capture efficiency evaluation method are that: 1. the monitoring range is limited: traditional methods may only be able to monitor specific parameters or be effective under specific operating conditions and may not be able to fully evaluate the entire carbon capture process. 2. Reaction time lag: the prior art may not be able to respond in real time or rapidly to changes in the environment or operating conditions, resulting in an evaluation result that lags behind the actual situation. 3. The data processing is insufficient: lack of advanced data analysis and processing capabilities and the inability to fully utilize the collected data for in-depth analysis. 4. Accuracy and reliability issues: the accuracy of the monitoring device or method may be limited, affecting the reliability of the assessment. 5. Operational complexity some processes may require complex operations and advanced technical knowledge, which are disadvantageous for widespread use.
Disclosure of Invention
In order to solve the problems, the invention provides a non-invasive coal chemical industry carbon capture efficiency evaluation method and system. Through a non-invasive detection technology and an artificial intelligent analysis algorithm, accurate and real-time evaluation of carbon capture efficiency in the coal chemical process is realized
In a first aspect, the invention provides a non-invasive coal chemical industry carbon capture efficiency evaluation method, which adopts the following technical scheme:
a non-invasive coal chemical industry carbon capture efficiency evaluation method comprises the following steps:
acquiring sensing data of a coal chemical process;
according to the acquired sensing data, analyzing the sensing data by using a deep learning model;
the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result.
Further, the acquiring of the sensing data of the coal chemical process includes monitoring the concentration of CO2 in the carbon capture medium with a spectroscopic sensor; obtaining the saturation of the medium through an acoustic wave sensor; the thickness and the distribution uniformity of the material layer are monitored by an electromagnetic wave sensor.
Further, the classification of the sensing data of the coal chemical process into image map data and time series data includes classifying the data into image map data and time series data according to the nature of the sensing data, wherein the spectrum data and some electromagnetic wave data are classified into the image map data, and the changes of the data collected by the acoustic wave sensor and some electromagnetic wave sensor show sequence characteristics with time and are classified into the time series data.
Further, the analysis of the image map data by using the convolutional neural network to obtain abnormal data in the carbon capture efficiency includes feature extraction of the image data in the sensor data by using a convolutional layer of the convolutional neural network to obtain a feature map, which is expressed as:wherein->For one element in the feature map of layer l, σ is a nonlinear activation function, W is the weight of the convolution kernel, b is the bias term, and X is the input data.
Further, the method includes analyzing the image map data by using the convolutional neural network to obtain abnormal data in the carbon capture efficiency, and further includes reducing the dimension of the feature map by using a pooling layer of the convolutional neural network and outputting the feature map through an output layer connected with a full-connection layer.
Further, the method comprises the steps of analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency, and judging differences between the characteristic map output by the output layer and the input data based on the classification, so as to obtain the abnormal data.
Further, the method comprises the steps of predicting the carbon capture efficiency of time series data by using a long-term and short-term memory network to obtain a prediction result, wherein the prediction result comprises a structure for constructing an LSTM model, and comprises an input layer, an LSTM layer and an output layer, and preparing model training parameters, including a learning rate, a loss function and an optimizer; training the model, and outputting a carbon capture efficiency predicted value of a corresponding time point by the LSTM model according to the learned time dependency.
In a second aspect, a non-invasive coal chemical industry carbon capture efficiency evaluation system comprises:
the data acquisition module is configured to acquire sensing data of the coal chemical process;
the analysis module is configured to analyze the sensing data by using a deep learning model according to the acquired sensing data;
the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result.
In a third aspect, the present invention provides a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded and executed by a processor of a terminal device for the non-invasive coal chemical industry carbon capture efficiency evaluation method.
In a fourth aspect, the present invention provides a terminal device, including a processor and a computer readable storage medium, where the processor is configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the method of non-invasive based assessment of carbon capture efficiency of coal chemical industry.
In summary, the invention has the following beneficial technical effects:
through the technical scheme, the method and the device can provide comprehensive data analysis and decision support for the user, help the user to better know and manage the carbon capture process, optimize the operation efficiency and improve the business result.
Through the cooperation of the two models, the invention can realize the accurate monitoring and efficiency evaluation of the coal chemical carbon capturing process. The sensor module provides real-time and high-precision data, and the data processing unit utilizes an advanced algorithm to carry out deep analysis on the data, so that scientific basis is provided for optimization of the carbon capture system.
Drawings
FIG. 1 is a schematic diagram of a non-invasive coal chemical industry carbon capture efficiency evaluation method according to example 1 of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example 1
Referring to fig. 1, a non-invasive coal chemical industry carbon capture efficiency evaluation method according to the present embodiment includes:
acquiring sensing data of a coal chemical process;
according to the acquired sensing data, analyzing the sensing data by using a deep learning model;
the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result.
Specifically, the method comprises the following steps:
s1, acquiring sensing data of a coal chemical process, wherein the sensing data comprise monitoring the concentration of CO2 in a carbon capture medium by utilizing a spectrum analysis sensor; obtaining the saturation of the medium through an acoustic wave sensor; the thickness and the distribution uniformity of the material layer are monitored by an electromagnetic wave sensor.
S2, dividing sensing data of the coal chemical process into image spectrum data and time sequence data, wherein the data are divided into the image spectrum data and the time sequence data according to the property of the sensing data, the spectrum data and certain electromagnetic wave data are classified into the image spectrum data, the sound wave sensor and the data collected by certain electromagnetic wave sensors, and the change of the data shows sequence characteristics along with time and is classified into the time sequence data.
In particular, the method comprises the steps of,
and (3) data acquisition:
firstly, data are collected in real time in the coal chemical process through different types of sensors. For example, spectroscopic sensors are used to monitor CO2 concentration in carbon capture media, acoustic wave sensors are used to detect media saturation, and electromagnetic wave sensors are used to monitor material layer thickness and distribution uniformity.
Preliminary classification:
data are primarily divided into two main categories according to the nature of the sensor and the characteristics of the acquired data: image map data and time series data. The spectral data and some electromagnetic wave data are naturally classified as image spectrum data, whereas the data collected by the acoustic wave sensor and some electromagnetic wave sensors are classified as time series data because their changes exhibit a series characteristic with time.
Acquisition of image map data and time-series data:
image map data:
provided by a spectroscopic analysis sensor and an electromagnetic wave sensor (in a mode suitable for image analysis). These data are typically presented in the form of images or maps reflecting the CO2 concentration distribution of the medium, the thickness and uniformity of the material layer, etc. Such data is suitable for image processing and feature extraction.
Time series data:
provided by acoustic wave sensors and electromagnetic wave sensors (in a mode suitable for time series analysis). These data record the changes over time of media saturation, material layer characteristics, etc., and are suitable for time series analysis such as trend prediction, pattern recognition, etc.
In this way, the system can effectively separate the collected complex data into image-map data and time-series data for analysis using different deep learning models (e.g., convolutional neural networks and long-term memory networks) to more accurately assess carbon capture efficiency.
S3, analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency, wherein the method comprises the steps of extracting features of the image data in the sensor data by using a convolutional layer of the convolutional neural network to obtain a feature map, wherein the feature map is expressed as follows:wherein->For one element in the feature map of layer l, σ is a nonlinear activation function, W is the weight of the convolution kernel, b is the bias term, and X is the input data.
Application of CNN model in carbon capture efficiency anomaly detection:
feature extraction:
CNN can extract key features from image map data through its convolution layer. These characteristics include the distribution pattern of the CO2 concentration, the thickness variation of the material layer, the distribution uniformity, etc., which are important indicators for evaluating the carbon capturing efficiency.
Dimension reduction and feature mapping:
the pooling layer is used for reducing the dimension of the feature map, so that the complexity of the model is simplified, and the calculation efficiency is improved. During the pooling process, the most important characteristic information is preserved.
The full connection layer further maps the feature map after dimension reduction to the output layer, and necessary feature combinations are provided for final decision.
Abnormality detection logic:
at the output end of the full-connection layer, the CNN model learns the characteristic mode of the carbon capture efficiency in the normal state through training. Thus, when there are significant differences in the characteristics of the input data from the learned normal mode, the model can recognize these differences as anomalies.
Specific decision logic may include setting thresholds, an anomaly scoring mechanism, or using a classification algorithm (e.g., two classifications, classifying data into normal and anomaly) or the like.
Model training and verification:
the CNN model is trained and verified through historical data (including data of normal and known abnormal conditions), so that the CNN model can accurately identify abnormal states.
This training process involves continually adjusting model parameters to minimize the differences between the predicted and actual data while verifying the generalization ability of the model over new data.
Through the flow, the CNN model can effectively judge abnormal data in the carbon capture efficiency after processing and outputting, and provides important basis for further decision and optimization.
S4, predicting the carbon capture efficiency of the time series data by utilizing a long-period memory network to obtain a prediction result, wherein the prediction result comprises a structure for constructing an LSTM model, including an input layer, an LSTM layer and an output layer, and preparing model training parameters, including a learning rate, a loss function and an optimizer; training the model, and outputting a carbon capture efficiency predicted value of a corresponding time point by the LSTM model according to the learned time dependency.
Specifically, the method comprises the following steps:
data preprocessing:
and (3) data collection: relevant time series data such as CO2 concentration, medium saturation, etc. are collected from the coal chemical process.
Characteristic engineering: features directly related to carbon capture efficiency, such as temperature, pressure, flow, etc., are selected.
Data cleaning: the missing values, outliers are processed and the necessary data transformations, such as time-series decomposition, are performed.
Data normalization: converting the data into a form that can be better processed by the model, such as scaling the data to a particular range by a maximum-minimum normalization method.
Model training:
constructing an LSTM model: the structure of the LSTM model is designed, and the LSTM model comprises an input layer, an LSTM layer, an output layer and the like.
Model configuration: training parameters such as learning rate, loss function, optimizer, etc. are configured.
Training a model: and training the LSTM model by using the normalized training data set, and learning the time dependence of the data by adjusting the internal parameters of the model.
The prediction process comprises the following steps:
data preparation: the newly collected or future data is subjected to the same preprocessing steps as the training phase.
Model input: and inputting the processed data into a trained LSTM model.
And (3) predicting: and outputting a carbon capture efficiency predicted value of a corresponding time point by the LSTM model according to the learned time dependence.
Analysis of results: the prediction results are converted back to the scale of the original data (if normalized) for ease of understanding and application.
Prediction principle:
principle of operation of LSTM: the LSTM unit can memorize long-term information and make predictions based on the information. It controls the retention and forgetting of information through gating mechanisms (forget gate, input gate, output gate).
Time sequence learning: LSTM understands patterns and trends in data by learning past time series data.
Prediction based on historical data: using the learned pattern, the LSTM is able to predict future data points, such as carbon capture efficiency.
Results application:
based on the predicted results, optimization and adjustment of the carbon capture process may be performed, such as changing operating parameters or taking preventive maintenance measures.
In summary, the LSTM model can accurately predict future carbon capture efficiency by learning historical patterns and trends of time series data, which provides important decision support for carbon capture efficiency optimization in the coal chemical process.
Example 2
The embodiment provides a coal industry carbon entrapment efficiency evaluation system based on non-invasive, includes:
the data acquisition module is configured to acquire sensing data of the coal chemical process;
the analysis module is configured to analyze the sensing data by using a deep learning model according to the acquired sensing data;
the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded and executed by a processor of a terminal device to perform the method of non-invasive coal chemical industry carbon capture efficiency evaluation.
A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the method of non-invasive based assessment of carbon capture efficiency of coal chemical industry.
The above embodiments are not intended to limit the scope of the present invention, so: all equivalent changes in structure, shape and principle of the invention should be covered in the scope of protection of the invention.
Claims (10)
1. The non-invasive coal chemical industry carbon capture efficiency evaluation method is characterized by comprising the following steps of:
acquiring sensing data of a coal chemical process;
according to the acquired sensing data, analyzing the sensing data by using a deep learning model;
the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result.
2. The non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 1, wherein the acquiring of the sensing data of the coal chemical industry process comprises monitoring the CO2 concentration in the carbon capture medium with a spectroscopic sensor; obtaining the saturation of the medium through an acoustic wave sensor; the thickness and the distribution uniformity of the material layer are monitored by an electromagnetic wave sensor.
3. The non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 2, wherein the classifying the sensing data of the coal chemical industry process into image spectrum data and time series data includes classifying the data into the image spectrum data and the time series data according to the property of the sensing data, wherein the spectrum data and some electromagnetic wave data are classified into the image spectrum data, the data collected by the acoustic wave sensor and some electromagnetic wave sensor, and the change thereof shows a sequence characteristic with time and is classified into the time series data.
4. The non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 3, wherein the analysis of the image map data by using the convolutional neural network to obtain abnormal data in the carbon capture efficiency comprises the feature extraction of the image data in the sensor data by using a convolutional layer of the convolutional neural network to obtain a feature map, which is expressed as:wherein->For one element in the feature map of layer l, σ is a nonlinear activation function, W is the weight of the convolution kernel, b is the bias term, and X is the input data.
5. The non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 4, wherein the analysis of the image map data by using the convolutional neural network to obtain abnormal data in the carbon capture efficiency further comprises the steps of reducing the dimension of a feature map by using a pooling layer of the convolutional neural network and outputting the feature map through an output layer connected by a full-connection layer.
6. The non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 5, wherein the analysis of the image map data by using the convolutional neural network to obtain abnormal data in the carbon capture efficiency, further comprises judging differences between the feature map output by the output layer and the input data based on classification, and obtaining the abnormal data.
7. The non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 6, wherein the predicting of the carbon capture efficiency of the time series data by using the long-short-term memory network is performed to obtain a prediction result, and the predicting result comprises the steps of constructing a structure of an LSTM model, including an input layer, an LSTM layer and an output layer, and preparing model training parameters, including a learning rate, a loss function and an optimizer; training the model, and outputting a carbon capture efficiency predicted value of a corresponding time point by the LSTM model according to the learned time dependency.
8. A non-invasive coal chemical industry carbon capture efficiency evaluation system, comprising:
the data acquisition module is configured to acquire sensing data of the coal chemical process;
the analysis module is configured to analyze the sensing data by using a deep learning model according to the acquired sensing data;
the method comprises the steps of dividing sensing data of a coal chemical process into image map data and time sequence data, and analyzing the image map data by using a convolutional neural network to obtain abnormal data in carbon capture efficiency; and predicting the carbon capture efficiency of the time series data by using the long-short-period memory network to obtain a prediction result.
9. A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded and executed by a processor of a terminal device to a non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 1.
10. A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform a non-invasive coal chemical industry carbon capture efficiency evaluation method according to claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311612086.9A CN117668481A (en) | 2023-11-29 | 2023-11-29 | Non-invasive coal chemical industry carbon capture efficiency evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311612086.9A CN117668481A (en) | 2023-11-29 | 2023-11-29 | Non-invasive coal chemical industry carbon capture efficiency evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117668481A true CN117668481A (en) | 2024-03-08 |
Family
ID=90070628
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311612086.9A Pending CN117668481A (en) | 2023-11-29 | 2023-11-29 | Non-invasive coal chemical industry carbon capture efficiency evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117668481A (en) |
-
2023
- 2023-11-29 CN CN202311612086.9A patent/CN117668481A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112655004B (en) | Computer-implemented method for anomaly detection and/or predictive maintenance | |
CN110441065B (en) | Gas turbine on-line detection method and device based on LSTM | |
CN116625438B (en) | Gas pipe network safety on-line monitoring system and method thereof | |
Lindemann et al. | Anomaly detection and prediction in discrete manufacturing based on cooperative LSTM networks | |
CN113076975A (en) | Dam safety monitoring data anomaly detection method based on unsupervised learning | |
CN116772944A (en) | Intelligent monitoring system and method for gas distribution station | |
Wang et al. | Online Incipient Fault Detection Method Based on Improved ℓ 1 Trend Filtering and Support Vector Data Description | |
CN116597939A (en) | Medicine quality control management analysis system and method based on big data | |
CN116861369A (en) | Air compressor health assessment method and system for industrial internet heterogeneous data fusion | |
CN114217025B (en) | Analysis method for evaluating influence of meteorological data on air quality concentration prediction | |
Zhou et al. | Automatic feature selection for unsupervised clustering of cycle-based signals in manufacturing processes | |
KR102366787B1 (en) | Real-time sliding window based anomaly detection system for multivariate data generated by manufacturing equipment | |
CN117521912A (en) | Carbon emission measuring and calculating model, comparison and evaluation method and application thereof | |
CN116842323A (en) | Abnormal detection method for operation data of water supply pipeline | |
Yu et al. | A hybrid learning-based model for on-line monitoring and diagnosis of out-of-control signals in multivariate manufacturing processes | |
CN113836813B (en) | Blast furnace tuyere water leakage detection method based on data analysis | |
Li et al. | Knowledge enhanced ensemble method for remaining useful life prediction under variable working conditions | |
CN117668481A (en) | Non-invasive coal chemical industry carbon capture efficiency evaluation method and system | |
CN116244596A (en) | Industrial time sequence data anomaly detection method based on TCN and attention mechanism | |
CN116415128A (en) | Method, system and medium for lubrication evaluation | |
CN112862180A (en) | Denitration system inlet NOx concentration prediction method | |
Yang et al. | Prediction of pollutant diffusion trend using CNN-GRU hybrid network in IoT air monitoring system | |
CN111753876A (en) | Product quality detection method based on deep neural network | |
CN113705547B (en) | Dynamic management and control method and device for recognizing false behavior of environment blurring | |
CN117419828B (en) | New energy battery temperature monitoring method based on optical fiber sensor |
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 |