CN113469246A - Instrument operation state analysis method and system based on neural network - Google Patents
Instrument operation state analysis method and system based on neural network Download PDFInfo
- Publication number
- CN113469246A CN113469246A CN202110736859.9A CN202110736859A CN113469246A CN 113469246 A CN113469246 A CN 113469246A CN 202110736859 A CN202110736859 A CN 202110736859A CN 113469246 A CN113469246 A CN 113469246A
- Authority
- CN
- China
- Prior art keywords
- neural network
- working
- data
- classification result
- convolutional neural
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 58
- 238000004458 analytical method Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 41
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001737 promoting effect Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003860 storage Methods 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
- G06F18/21—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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an instrument running state analysis method and system based on a neural network, which reconstructs an array after preprocessing current data sampled every 10 seconds of equipment; then inputting training set data into the designed convolutional neural network, and modifying neural network parameters; and finally, predicting by using the trained convolutional neural network to obtain a final classification result, so that the running state of the instrument can be automatically monitored when the instrument runs, and further, the instrument equipment is prevented from being damaged under the condition of no monitoring.
Description
Technical Field
The invention relates to the field of instrument operation monitoring, in particular to an instrument operation state analysis method and system based on a neural network.
Background
The existing instrument is a production instrument containing a microprocessor or a microprocessor and is used for the functions of storage operation logic judgment, automation operation and the like of data.
When the existing instrument runs, the existing instrument is inconvenient to automatically monitor, the running state of the existing instrument cannot be timely known, and further the existing instrument is easily damaged under the condition of no monitoring.
Disclosure of Invention
The invention aims to provide an instrument running state analysis method and system based on a neural network, and aims to solve the technical problems that in the prior art, when an instrument runs, the instrument is inconvenient to automatically monitor, the running state of the instrument cannot be known in time, and further, instrument equipment is easy to damage under the condition of no monitoring.
In order to achieve the above object, the present invention provides a method for analyzing an operation state of an instrument based on a neural network, comprising the following steps:
preprocessing current data sampled every 10 seconds by equipment and then reconstructing an array;
inputting training set data into the designed convolutional neural network, and modifying neural network parameters;
and predicting by using the trained convolutional neural network to obtain a final classification result.
Wherein, in the step of reconstructing the array after preprocessing the current data sampled every 10 seconds of the equipment, the method further comprises the steps of,
each time point and the 89 current data after the time point are arranged in sequence to be used as the time point signal;
associating the operating state with the current signal over the time period at each point in time;
and lifting the two-dimensional m by 90 matrix formed by each time point and the preprocessed current signal into a four-dimensional m by 90 by 1 matrix.
Wherein in inputting training set data into the designed convolutional neural network, modifying neural network parameters, the method further comprises,
designing a convolutional neural network;
the full connection layer is set to be three, corresponding to the states of shutdown, standby and working;
respectively taking sample data of three working states as a training set and a verification set;
inputting training set data into a convolutional neural network for training;
inputting the data of the verification set into a trained convolutional neural network for classification;
and obtaining a classification result.
Wherein, after the classification result is obtained,
and comparing the obtained classification result with the real working state, and modifying the parameters in the convolutional neural network.
Wherein, in the step of predicting by using the trained convolutional neural network to obtain the final classification result, the method also comprises the following steps,
carrying out the same pretreatment on the current data of the sample to be detected;
inputting the training convolutional neural network for classification to obtain a classification result;
finding out all working intervals in the classified results;
keeping all the points of the shutdown state in the classification result;
and smoothing all the other points except the working interval and the shutdown state into a standby state to obtain a final classification result.
Wherein, in the step of inputting the trained convolutional neural network for classification to obtain a classification result, the method also comprises the steps of,
and (4) performing smooth optimization by using an algorithm when the classification result has obvious problems.
In the step of finding out all working intervals in the classified results, the method further comprises the step of respectively corresponding 0, 1 and 2 in the classified results to shutdown, standby and working;
traversing all the points in the classification result, and judging that at least 50 points in 100 points behind one working point are in working states, and then the point is the working point;
combining continuous points which are the same as the judgment points after the current working point into a working interval;
combining two working intervals with the interval not larger than 300 into one interval, and not combining the intervals with the interval larger than 300;
and finding out all working intervals.
An instrument running state analysis system based on a neural network comprises a current data processing module, a data training module and a neural network prediction module;
the data training module is connected with the current data processing module, and the neural network prediction module is connected with the data training module;
the current data processing module is used for arranging current data and associating the working state of each time point with a current signal in a time period;
the data training module is used for designing a convolutional neural network, training sample data, and modifying parameters in the neural network after comparing the sample data;
and the neural network prediction module is used for classifying the current data of the sample to be detected and sorting the current data to obtain a classification result.
The current data processing module comprises a preprocessing unit and a preprocessed reconstructed array unit, and the preprocessed reconstructed array unit is connected with the preprocessing unit and the data training module;
the preprocessing unit is used for arranging the current data as time point signals and associating the working state of each time point with the current signals in a time period;
and the preprocessed reconstruction array unit is used for promoting a two-dimensional m × 90 matrix formed by each time point and the preprocessed current signal into a four-dimensional m × 90 × 1 matrix so as to perform convolution neural network.
According to the method and the system for analyzing the running state of the instrument based on the neural network, an array is reconstructed after current data sampled every 10 seconds of equipment is preprocessed; then inputting training set data into the designed convolutional neural network, and modifying neural network parameters; and finally, predicting by using the trained convolutional neural network to obtain a final classification result, so that the running state of the instrument can be automatically monitored when the instrument runs, and further, the instrument equipment is prevented from being damaged under the condition of no monitoring.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an apparatus operation state analyzing method based on a neural network according to the present invention.
FIG. 2 is a flow chart of the present invention for reconstructing an array after pre-processing current data sampled every 10 seconds of the device.
FIG. 3 is a flow chart of the present invention for inputting training set data into a designed convolutional neural network to modify neural network parameters.
FIG. 4 is a flow chart of the present invention for using a trained convolutional neural network for prediction to obtain a final classification result.
FIG. 5 is a flow chart of the present invention for finding all of the work intervals in the sorted results.
FIG. 6 is a graph of a current signal simulation of the present invention before and after preconditioning.
FIG. 7 is a graph of the error of the convolutional neural network training results of the present invention.
FIG. 8 is the classification result of the prediction with the trained neural network of the present invention.
FIG. 9 is a flow chart of the present invention for finding all work intervals.
FIG. 10 is a system diagram of the neural network based instrument operating condition analysis system of the present invention.
In the figure: the device comprises a 1-current data processing module, a 2-data training module, a 3-neural network prediction module, an 11-preprocessing unit and a 12-preprocessed reconstruction array unit.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the description of the present invention, it is to be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships illustrated in the drawings, and are used merely for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention. Further, in the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Referring to fig. 1 to 5, the present invention provides an apparatus operation state analysis method based on a neural network, including the following steps:
s101: preprocessing current data sampled every 10 seconds by equipment and then reconstructing an array;
s1011: each time point and the 89 current data after the time point are arranged in sequence to be used as the time point signal;
s1012: associating the operating state with the current signal over the time period at each point in time;
s1013: lifting a two-dimensional m × 90 matrix formed by each time point and the preprocessed current signals into a four-dimensional m × 90 × 1 matrix;
s102: inputting training set data into the designed convolutional neural network, and modifying neural network parameters;
s1021: designing a convolutional neural network;
s1022: the full connection layer is set to be three, corresponding to the states of shutdown, standby and working;
s1023: respectively taking sample data of three working states as a training set and a verification set;
s1024: inputting training set data into a convolutional neural network for training;
s1025: inputting the data of the verification set into a trained convolutional neural network for classification;
s1026: obtaining a classification result;
s1027: comparing the obtained classification result with the real working state, and modifying parameters in the convolutional neural network;
s103: predicting by using the trained convolutional neural network to obtain a final classification result;
s1031: carrying out the same pretreatment on the current data of the sample to be detected;
s1032: inputting the training convolutional neural network for classification to obtain a classification result, performing smooth optimization by using an algorithm when the classification result has an obvious problem;
s1033: finding out all working intervals in the classified results;
s10331: respectively corresponding 0, 1 and 2 in the classified results to shutdown, standby and work;
s10332: traversing all the points in the classification result, and judging that at least 50 points in 100 points behind one working point are in working states, and then the point is the working point;
s10333: combining continuous points which are the same as the judgment points after the current working point into a working interval;
s10334: combining two working intervals with the interval not larger than 300 into one interval, and not combining the intervals with the interval larger than 300;
s10335: finding out all working intervals;
s1034: keeping all the points of the shutdown state in the classification result;
s1035: smoothing all other points except the working interval and the shutdown state into a standby state to obtain a final classification result;
in the present embodiment, it is preferred that,
1. current data processing:
the current data is the current magnitude of the current at the current time point sampled every 10 seconds by the device.
Pretreatment: each time point and the 89 current data after the time point are arranged in sequence to be used as the time point signal, and the working state of each time point is related to the current signal in the time period, as shown in figure 6, wherein each time point and the 3 following time points are taken in the figure.
The tail in preprocessing the data requires 89 data points to be replenished.
(2) And reconstructing an array after preprocessing, and promoting a two-dimensional m × 90 matrix formed by each time point and the preprocessed current signal into a four-dimensional m × 90 × 1 matrix so as to enable the matrix to perform convolution neural network.
2. Training data
Designing a convolutional neural network:
the full connection layer is set to 3, corresponding to the "off", "standby" and "working" states.
% convolutional neural network architecture
% deep learning neural network training scheme
And respectively taking 70 percent of sample data of the three working states as a training set, and taking the remaining 30 percent as a verification set. Inputting training set data into a neural network for training, inputting verification set data into the trained neural network for classification, and comparing the obtained classification result with the real working state to modify parameters in the neural network so as to prevent over-fitting or under-fitting.
When the error is stable and low, the trained neural network is stored, and the error graph of the convolution neural network training result is shown in FIG. 7.
3. And (3) predicting by using the trained neural network:
the current data of the sample to be tested is input into the trained neural network for classification after the same pretreatment, and the obtained classification result is shown in fig. 8:
and (4) carrying out smooth optimization by using an algorithm, wherein a small part of classification results have obvious problems.
When the working interval algorithm is found, 100 points behind one working point are determined, so that all working states of the point to be measured can be accurately determined only by adding 100 points behind the point to be measured, as shown in fig. 9.
And after all the working intervals are found, keeping all the points in the shutdown state (the fitting accuracy of the shutdown state is 100), smoothing all the other points except the working intervals and the shutdown state into the standby state, and sorting to obtain a final classification result.
Referring to fig. 10, an instrument operation state analysis system based on a neural network includes a current data processing module, a data training module, and a neural network prediction module;
the data training module is connected with the current data processing module, and the neural network prediction module is connected with the data training module;
the current data processing module is used for arranging current data and associating the working state of each time point with a current signal in a time period;
the data training module is used for designing a convolutional neural network, training sample data, and modifying parameters in the neural network after comparing the sample data;
and the neural network prediction module is used for classifying the current data of the sample to be detected and sorting the current data to obtain a classification result.
Further, referring to fig. 10, the current data processing module includes a preprocessing unit and a preprocessed reconstructed array unit, and the preprocessed reconstructed array unit is connected to the preprocessing unit and the data training module;
the preprocessing unit is used for arranging the current data as time point signals and associating the working state of each time point with the current signals in a time period;
and the preprocessed reconstruction array unit is used for promoting a two-dimensional m × 90 matrix formed by each time point and the preprocessed current signal into a four-dimensional m × 90 × 1 matrix so as to perform convolution neural network.
In the embodiment, the current data processing module is used for preprocessing the current data sampled every 10 seconds of the equipment and then reconstructing an array; then the data training module inputs training set data into the designed convolutional neural network and modifies neural network parameters; finally, the neural network prediction module predicts by using the trained convolutional neural network to obtain a final classification result; the preprocessing unit arranges the current data as time point signals, associates the working state of each time point with the current signals in a time period, and promotes a two-dimensional m 90 matrix formed by each time point of the preprocessing reconstructed array unit and the preprocessed current signals into a four-dimensional m 90 1 matrix so as to enable the matrix to be capable of performing convolution neural network.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. An instrument operation state analysis method based on a neural network is characterized by comprising the following steps,
preprocessing current data sampled every 10 seconds by equipment and then reconstructing an array;
inputting training set data into the designed convolutional neural network, and modifying neural network parameters;
and predicting by using the trained convolutional neural network to obtain a final classification result.
2. The neural network-based instrument operation state analyzing method of claim 1, wherein in "reconstructing the array after preprocessing the current data sampled every 10 seconds for the device", the method further comprises,
each time point and the 89 current data after the time point are arranged in sequence to be used as the time point signal;
associating the operating state with the current signal over the time period at each point in time;
and lifting the two-dimensional m by 90 matrix formed by each time point and the preprocessed current signal into a four-dimensional m by 90 by 1 matrix.
3. The neural network-based instrument operating state analyzing method of claim 2, wherein in inputting training set data into the designed convolutional neural network, modifying neural network parameters, the method further comprises,
designing a convolutional neural network;
the full connection layer is set to be three, corresponding to the states of shutdown, standby and working;
respectively taking sample data of three working states as a training set and a verification set;
inputting training set data into a convolutional neural network for training;
inputting the data of the verification set into a trained convolutional neural network for classification;
and obtaining a classification result.
4. The neural network-based instrument operation state analyzing method of claim 1, wherein, after "deriving the classification result",
and comparing the obtained classification result with the real working state, and modifying the parameters in the convolutional neural network.
5. The method of analyzing the operational status of an instrument based on a neural network as claimed in claim 1, wherein in the step of predicting with the trained convolutional neural network to obtain the final classification result, the method further comprises,
carrying out the same pretreatment on the current data of the sample to be detected;
inputting the training convolutional neural network for classification to obtain a classification result;
finding out all working intervals in the classified results;
keeping all the points of the shutdown state in the classification result;
and smoothing all the other points except the working interval and the shutdown state into a standby state to obtain a final classification result.
6. The method of analyzing the operation status of an instrument based on a neural network as claimed in claim 1, wherein in the step of classifying the input trained convolutional neural network to obtain a classification result, the method further comprises,
and (4) performing smooth optimization by using an algorithm when the classification result has obvious problems.
7. The neural network-based instrument operation state analyzing method of claim 1, wherein in "find all working intervals in the classified results", the method further comprises,
respectively corresponding 0, 1 and 2 in the classified results to shutdown, standby and work;
traversing all the points in the classification result, and judging that at least 50 points in 100 points behind one working point are in working states, and then the point is the working point;
combining continuous points which are the same as the judgment points after the current working point into a working interval;
combining two working intervals with the interval not larger than 300 into one interval, and not combining the intervals with the interval larger than 300;
and finding out all working intervals.
8. An instrument running state analysis system based on a neural network is characterized by comprising a current data processing module, a data training module and a neural network prediction module;
the data training module is connected with the current data processing module, and the neural network prediction module is connected with the data training module;
the current data processing module is used for arranging current data and associating the working state of each time point with a current signal in a time period;
the data training module is used for designing a convolutional neural network, training sample data, and modifying parameters in the neural network after comparing the sample data;
and the neural network prediction module is used for classifying the current data of the sample to be detected and sorting the current data to obtain a classification result.
9. The neural network-based instrument operational state analysis system of claim 8,
the current data processing module comprises a preprocessing unit and a preprocessed reconstructed array unit, and the preprocessed reconstructed array unit is connected with the preprocessing unit and the data training module;
the preprocessing unit is used for arranging the current data as time point signals and associating the working state of each time point with the current signals in a time period;
and the preprocessed reconstruction array unit is used for promoting a two-dimensional m × 90 matrix formed by each time point and the preprocessed current signal into a four-dimensional m × 90 × 1 matrix so as to perform convolution neural network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110736859.9A CN113469246A (en) | 2021-06-30 | 2021-06-30 | Instrument operation state analysis method and system based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110736859.9A CN113469246A (en) | 2021-06-30 | 2021-06-30 | Instrument operation state analysis method and system based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113469246A true CN113469246A (en) | 2021-10-01 |
Family
ID=77876502
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110736859.9A Pending CN113469246A (en) | 2021-06-30 | 2021-06-30 | Instrument operation state analysis method and system based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113469246A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116126945A (en) * | 2023-03-30 | 2023-05-16 | 创域智能(常熟)网联科技有限公司 | Sensor running state analysis method and system based on data analysis |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107844859A (en) * | 2017-10-31 | 2018-03-27 | 深圳达实智能股份有限公司 | Large medical equipment energy consumption Forecasting Methodology and terminal device based on artificial intelligence |
CN108892014A (en) * | 2018-09-19 | 2018-11-27 | 歌拉瑞电梯股份有限公司 | A kind of elevator internal contracting brake fault early warning method based on Elman neural network |
CN110224673A (en) * | 2019-05-14 | 2019-09-10 | 太原理工大学 | A kind of solar photovoltaic cell panel fault detection method based on deep learning |
CN110991818A (en) * | 2019-11-14 | 2020-04-10 | 广西电网有限责任公司电力科学研究院 | Load identification method integrating event detection and neural network |
US20200364563A1 (en) * | 2019-05-13 | 2020-11-19 | Nec Laboratories America, Inc. | Landmark-based classification model updating |
CN112345956A (en) * | 2020-11-24 | 2021-02-09 | 广州橙行智动汽车科技有限公司 | Battery pack charge state detection method and device |
CN112580784A (en) * | 2020-12-16 | 2021-03-30 | 哈尔滨电站设备成套设计研究所有限公司 | Intelligent early warning method for equipment based on multi-input multi-output convolutional neural network |
-
2021
- 2021-06-30 CN CN202110736859.9A patent/CN113469246A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107844859A (en) * | 2017-10-31 | 2018-03-27 | 深圳达实智能股份有限公司 | Large medical equipment energy consumption Forecasting Methodology and terminal device based on artificial intelligence |
CN108892014A (en) * | 2018-09-19 | 2018-11-27 | 歌拉瑞电梯股份有限公司 | A kind of elevator internal contracting brake fault early warning method based on Elman neural network |
US20200364563A1 (en) * | 2019-05-13 | 2020-11-19 | Nec Laboratories America, Inc. | Landmark-based classification model updating |
CN110224673A (en) * | 2019-05-14 | 2019-09-10 | 太原理工大学 | A kind of solar photovoltaic cell panel fault detection method based on deep learning |
CN110991818A (en) * | 2019-11-14 | 2020-04-10 | 广西电网有限责任公司电力科学研究院 | Load identification method integrating event detection and neural network |
CN112345956A (en) * | 2020-11-24 | 2021-02-09 | 广州橙行智动汽车科技有限公司 | Battery pack charge state detection method and device |
CN112580784A (en) * | 2020-12-16 | 2021-03-30 | 哈尔滨电站设备成套设计研究所有限公司 | Intelligent early warning method for equipment based on multi-input multi-output convolutional neural network |
Non-Patent Citations (2)
Title |
---|
游晓霞;党志胜;: "基于RBF的船用污水处理装置运行状态在线监测研究", 自动化与仪器仪表, no. 03, pages 1 * |
赵艳平;姜子运;李元成;: "基于神经网络的静电除尘器放电信号预测研究", 计算机工程与设计, no. 21 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116126945A (en) * | 2023-03-30 | 2023-05-16 | 创域智能(常熟)网联科技有限公司 | Sensor running state analysis method and system based on data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111178456A (en) | Abnormal index detection method and device, computer equipment and storage medium | |
CN110543903B (en) | Data cleaning method and system for GIS partial discharge big data system | |
CN113887616B (en) | Real-time abnormality detection method for EPG connection number | |
US7716152B2 (en) | Use of sequential nearest neighbor clustering for instance selection in machine condition monitoring | |
CN106383916B (en) | Data processing method based on predictive maintenance of industrial equipment | |
CN114118224A (en) | Neural network-based system-wide remote measurement parameter anomaly detection system | |
CN111506729B (en) | Information processing method, device and computer readable storage medium | |
US11443168B2 (en) | Log analysis system employing long short-term memory recurrent neural net works | |
CN106537423A (en) | Adaptive featurization as service | |
CN113505537A (en) | Building energy consumption detection method and device, computer equipment and storage medium | |
CN115184193B (en) | Automatic testing method, device, equipment and storage medium for cable | |
CN111860981A (en) | Enterprise national industry category prediction method and system based on LSTM deep learning | |
CN113469246A (en) | Instrument operation state analysis method and system based on neural network | |
CN112966957A (en) | Data link abnormity positioning method and device, electronic equipment and storage medium | |
CN116089218A (en) | Dynamic baseline alarm method and system based on Kubernetes historical data and trend analysis | |
CN111352820A (en) | Method, equipment and device for predicting and monitoring running state of high-performance application | |
Schlegl et al. | Scalable anomaly detection in manufacturing systems using an interpretable deep learning approach | |
CN111209158B (en) | Mining monitoring method and cluster monitoring system for server cluster | |
CN114203268A (en) | Machine learning-based geochemical data classification method and device | |
CN113469090A (en) | Water quality pollution early warning method and device and storage medium | |
CN113254428A (en) | Missing data filling method and system based on decision tree | |
CN117973566B (en) | Training data processing method and device and related equipment | |
KR102497585B1 (en) | OHT anomaly detection system using artificial intelligence | |
CN117668584A (en) | Rapid preparation method and system of oil well working condition diagnosis data set | |
He et al. | An Integrated Long Short-Term Memory Based Online Log Anomaly Detection |
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 |