CN113111854A - Current signal extraction method, current signal extraction device, computer equipment and storage medium - Google Patents
Current signal extraction method, current signal extraction device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113111854A CN113111854A CN202110486155.0A CN202110486155A CN113111854A CN 113111854 A CN113111854 A CN 113111854A CN 202110486155 A CN202110486155 A CN 202110486155A CN 113111854 A CN113111854 A CN 113111854A
- Authority
- CN
- China
- Prior art keywords
- current
- current value
- event block
- discrete
- data
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000013075 data extraction Methods 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 28
- 238000001514 detection method Methods 0.000 claims description 22
- 238000002372 labelling Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000005856 abnormality Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/25—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques
- G01R19/2506—Arrangements for conditioning or analysing measured signals, e.g. for indicating peak values ; Details concerning sampling, digitizing or waveform capturing
- G01R19/2509—Details concerning sampling, digitizing or waveform capturing
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present application relates to the field of data standardization for data processing, and in particular, to a current signal extraction method, apparatus, computer device, and storage medium. According to the method, a state frame extraction method and event block definitions corresponding to discrete current data to be extracted are determined by obtaining the discrete current data to be extracted corresponding to the Internet of things equipment; extracting state frame information corresponding to discrete current data of discrete current data to be extracted by a state frame extraction method; according to the definition of the event block, the current value in the discrete current data corresponding to the state frame information is placed in the event block; and acquiring a current value random signal corresponding to the Internet of things equipment from the event block. The current value random signal is extracted based on the event block, and noise data in the discrete current data are filtered, so that the working details of the Internet of things equipment are effectively reserved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a current signal extraction method and apparatus, a computer device, and a storage medium.
Background
With The development of computer technology and sensing technology, The Internet of Things (IOT) technology has emerged, that is, by various devices and technologies such as various information sensors, radio frequency identification technology, global positioning system, infrared sensor, laser scanner, etc., any object or process needing monitoring, connection and interaction is collected in real time, various information needed by sound, light, heat, electricity, mechanics, chemistry, biology, location, etc. is collected, and by various possible network accesses, The ubiquitous connection between objects and objects, and objects and people is realized, and The intelligent perception, identification and management of objects and processes are realized. The internet of things is an information bearer based on the internet, a traditional telecommunication network and the like, and all common physical objects which can be independently addressed form an interconnected network.
In the internet of things technology, a situation that a certain equipment current value needs to be acquired at a low frequency and a discrete current value is analyzed sometimes occurs. However, in this case, because the acquisition frequency of the current data is low, the working details of the internet of things device may be lost when acquiring the discrete current value in the low-frequency state in the prior art, so that the accuracy of analyzing the internet of things device based on the discrete current data cannot be ensured.
Disclosure of Invention
In view of the above, it is necessary to provide a current signal extraction method, a device, a computer device and a storage medium for processing discrete current data and saving the working details of an electrical appliance.
A current signal extraction method, the method comprising:
acquiring discrete current data corresponding to Internet of things equipment, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
extracting state frame information corresponding to the discrete current data through the state frame extraction method;
according to the event block definition, a current value in discrete current data corresponding to the state frame information is placed in an event block;
and acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
In one embodiment, the extracting, by the state frame extracting method, the state frame information corresponding to the discrete current data includes:
searching a preset data extraction model corresponding to the discrete current data;
inputting the discrete current data into the preset data extraction model, and carrying out state classification and labeling on the current values in the discrete current data through the preset data extraction model to obtain a current value labeling result;
and acquiring state frame information corresponding to the discrete current data according to the current value marking result.
In one embodiment, before searching for the preset data extraction model corresponding to the discrete current data, the method further includes:
acquiring equipment operation historical data corresponding to the Internet of things equipment, and marking discrete current frames in the equipment operation historical data according to the operation state of the Internet of things equipment;
and training the initial convolutional neural network model based on the marked equipment operation historical data to obtain a preset data extraction model.
In one embodiment, the placing, according to the event block definition, a current value in discrete current data corresponding to the status frame information into an event block includes:
searching a standard current value and a standard current value time sequence corresponding to the event block definition;
and based on the current value marked in the state frame information and the current value time sequence, putting the current value in the discrete current data corresponding to the state frame information into an event block.
In one embodiment, the placing the current value in the discrete current data corresponding to the state frame information into the event block based on the current value and the current value timing labeled in the state frame information includes:
determining similarity between a current value in discrete current data corresponding to the state frame information and a standard current value corresponding to event block definition based on the current value marked in the state frame information and a current value time sequence;
and when the similarity is greater than a preset similarity threshold, setting a current value in the discrete current data corresponding to the state frame information into an event block corresponding to the event block definition.
In one embodiment, after obtaining the current value random signal corresponding to the discrete current data from the event block, the method further includes:
extracting a non-stationary current signal in the current value random signal;
carrying out abnormity detection on the non-stationary current signal to obtain an abnormity detection result;
and feeding back the abnormal detection result.
In one embodiment, after obtaining the current value random signal corresponding to the discrete current data from the event block, the method further includes:
extracting a stationary random signal in the current value random signal;
obtaining a device current analysis result corresponding to the stable random signal;
and feeding back the current analysis result of the equipment.
A current signal extraction device, the device comprising:
the data acquisition module is used for acquiring discrete current data corresponding to the Internet of things equipment and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
the information extraction module is used for extracting the state frame information corresponding to the discrete current data by the state frame extraction method;
the information embedding module is used for embedding the current value in the discrete current data corresponding to the state frame information into the event block according to the event block definition;
and the signal extraction module is used for acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring discrete current data corresponding to Internet of things equipment, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
extracting state frame information corresponding to the discrete current data through the state frame extraction method;
according to the event block definition, a current value in discrete current data corresponding to the state frame information is placed in an event block;
and acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
A computer storage medium having a computer program stored thereon, the computer program when executed by a processor implementing the steps of:
acquiring discrete current data corresponding to Internet of things equipment, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
extracting state frame information corresponding to the discrete current data through the state frame extraction method;
according to the event block definition, a current value in discrete current data corresponding to the state frame information is placed in an event block;
and acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
According to the current signal extraction method, the current signal extraction device, the computer equipment and the storage medium, the state frame extraction method and the event block definition corresponding to the discrete current data are determined by acquiring the discrete current data corresponding to the Internet of things equipment; extracting state frame information corresponding to the discrete current data by a state frame extraction method; according to the definition of the event block, the current value in the discrete current data corresponding to the state frame information is placed in the event block; and acquiring a current value random signal corresponding to the Internet of things equipment from the event block. According to the current signal extraction method, the state frame extraction method and the event block definition of the discrete current data corresponding to the Internet of things equipment are determined, then the state frame information is extracted from the data to be extracted based on the state frame extraction method, the current value in the discrete current data corresponding to the state frame information is placed into the event block based on the event block definition, the current value is classified, the current value random signal is extracted based on the event block, the noise data in the discrete current data is filtered, and therefore the working details of the Internet of things equipment are effectively reserved.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a current signal extraction method;
FIG. 2 is a flow diagram illustrating a method for extracting a current signal according to one embodiment;
FIG. 3 is a flowchart illustrating the step of extracting status frame information according to one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating the training steps of the default data extraction model in one embodiment;
FIG. 5 is a flowchart illustrating a step of placing a current value in discrete current data corresponding to status frame information into an event block according to an embodiment;
FIG. 6 is a flowchart illustrating the steps of obtaining and feeding back the results of the anomaly checking in one embodiment;
FIG. 7 is a block diagram showing the structure of a current signal extracting device according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The current signal extraction method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the current signal extraction server 104 over a network. When a worker at the terminal 102 needs to analyze discrete current data corresponding to the internet of things device, a current signal extraction server 104 needs to extract a stabilized current value random signal, at this time, discrete current data generated by the internet of things device in the operation process can be sent to the current signal extraction server 104 through a network, and the discrete current data is acquired by sensing devices such as an intelligent electric meter. The current signal extraction server 104 firstly acquires discrete current data corresponding to the external internet of things equipment submitted by the terminal 102, and then determines a state frame extraction method and event block definition corresponding to the discrete current data; extracting state frame information corresponding to the discrete current data by a state frame extraction method; according to the definition of the event block, the current value in the discrete current data corresponding to the state frame information is placed in the event block; and acquiring a current value random signal corresponding to the Internet of things equipment from the event block. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the current signal extracting server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a current signal extraction method is provided, which is described by taking the method as an example applied to the current signal extraction server 104 in fig. 1, and includes the following steps:
step 201, obtaining discrete current data corresponding to the internet of things device, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, where the event block definition is used to define an operation event of the internet of things device.
Discrete current data generated by the internet of things device is a processing object of the current signal extraction method, and the internet of things device is not related to the current signal extraction server 104 in the application and is opposite to an external device. The discrete current data refers to the device current value acquired by the corresponding sensor at low frequency aiming at the internet of things device, and is specifically discrete current data. The method and the device are mainly used for extracting the current value random signals corresponding to the event information from the discrete current data and performing subsequent data analysis on the Internet of things equipment based on the stable random signals in the current value random signals. The event information specifically comprises two parts, one part is a state frame, the other part is an event block, specifically, the state frame corresponding to the current change rule corresponding to each state in the operation of the equipment is sorted out by summarizing the current rule of the equipment in the operation process in historical data, and the event in the operation process of the equipment is constructed based on the combination of the state frames. An event is assembled from multiple state frames. The state frame is mainly used for filtering noise data which is irrelevant to events, and the event block further clearly defines the analyzed events. The state that satisfies the event definition is the current value that needs to be analyzed. That is, the current data corresponding to the status frame and the event block is extracted from the current data to be extracted. Therefore, after obtaining the extracted current data, it is necessary to further determine the state frame extraction method corresponding to the current data to be extracted. And the state frame extraction method corresponding to the current data to be extracted corresponds to the equipment. Namely, based on the type of the device to be subjected to current data extraction, the corresponding state frame extraction method and event block definition are determined. The state frame extraction method corresponds to the device type of the external internet of things device, for example, a refrigerator corresponds to one state frame extraction method, and a television corresponds to another state frame extraction method. Of course, it is also possible to further subdivide a refrigerator into 100 watts for one status frame extraction method, and a refrigerator of 130 watts for another status frame extraction method. And the event block definition also corresponds to the device type and is used for defining the operation event of the equipment of the Internet of things. For example, the running event of the television set when the television set is turned on, what characteristics should be in the collected current frame, the running event of the television set when the television set is turned off, what characteristics should be in the collected current frame, and the event block definition is used for expressing the characteristics.
Specifically, when extracting the current signal, an object to be analyzed, that is, discrete current data corresponding to the external internet of things device, needs to be obtained from the terminal. And then determining a corresponding state frame extraction method and an event block definition, and processing the discrete current data based on the state frame extraction method and the event block definition.
Step 203, extracting the state frame information corresponding to the discrete current data by a state frame extraction method.
The state frame is used for dividing the state of original current information of external Internet of things equipment; for example, for a device with multi-gear operation function, the corresponding state frame information can be constructed according to the original current information corresponding to the states of shutdown, standby, 1 gear, 2 gear and 3 gear. The current state of one device may be which when the device works, and the collected current data to be extracted is discrete data and belongs to a non-stationary random signal, so that the current data to be extracted in a non-event state related to the device can be removed through a pre-summarized state frame.
Specifically, after the state frame extraction method is determined, the discrete current data may be processed by the state frame extraction method, and the non-event current data of the non-concerned portion in the discrete current data is deleted while the remaining data is retained. And meanwhile, establishing the corresponding relation between the discrete current data of the reserved part and the state frame. For example, for a piece of discrete current data having 16 discrete current values, the internet of things device corresponding to the discrete current value is an electric motor. After the processing is performed by the state frame extraction method, it can be determined that the 1 st current value, the 2 nd current value and the 3 rd current value form a motor startup state frame, the 5 th current value, the 6 th current value and the 7 th current value form a motor first-gear operation state frame, the 9 th current value, the 10 th current value and the 11 th current value form a motor second-gear operation state frame, and the 13 th current value, the 14 th current value and the 15 th current value form a motor shutdown operation state frame. While the remaining current values are non-stationary random signals. In a specific embodiment, the extraction operation of the state frame information can be performed through a pre-trained neural network model, so that the extraction efficiency and accuracy are improved.
Step 205, according to the event block definition, the current value in the discrete current data corresponding to the status frame information is placed in the event block.
In particular, the event block definition may specifically define a specified order of current frames as one event block, such as in one embodiment, a first standby status frame to a second standby status frame may be defined as one machining event. Therefore, according to the definition of the event block, the discrete current value in the state frame information corresponding to the current data to be extracted, which meets the definition requirement, can be placed into the preset event block. Subsequent current data analysis is thus performed based on the event block.
And step 207, acquiring a current value random signal corresponding to the internet of things equipment from the event block.
The current value change of the Internet of things equipment is a random process, and the current value of the Internet of things equipment is a random variable at each time point. Therefore, the current value signal corresponding to the equipment of the internet of things can be represented through the current value random signal, and therefore current data analysis of the equipment of the internet of things is carried out. And the random signal includes stationary random signals and non-stationary random signals. The stationary signal has small information content, and the statistical characteristic of the stationary signal is unchanged along with time, namely, the corresponding signal is the stationary signal when the internet of things equipment is in a normal working state. While a non-stationary signal means that the statistical properties change over time, its information content changes. There will always be "innovation" introduced, which is defined in the stochastic signal analysis as the difference between the current signal value and the predicted signal value. The predicted signal value is inferred from the statistical properties of the past signal, i.e. the innovation is an unpredictable part. Namely, under the abnormal working state of the equipment of the internet of things, an immeasurable part is introduced, and the corresponding current random signal may be a non-stationary random signal.
Specifically, after the current values in the discrete current data corresponding to the state frame information are placed in the event block, the current values can be used as current value random signals of the operation events of the internet of things equipment corresponding to the event block, and the current values can show working details of the internet of things equipment in the operation events. And the current values of all the event blocks are combined, namely the current values of all the operating events of the equipment of the internet of things are random signals, and the current values which are not placed into the event blocks belong to noise data.
For the internet of things equipment, when the current of the equipment is collected in a low-frequency state, the working details of part of the equipment cannot be presented, for example, the current of the internet of things equipment in what state is specifically the working details, because the current is collected in the low-frequency state, the collected current signal interval is long, so the details are not easy to identify, and the current value of a non-event part is filtered out by combining a state frame and an event block, and the current values of other parts are put into the event block, so that the working details of the event block can be clearly identified.
According to the current signal extraction method, the state frame extraction method and the event block definition corresponding to the discrete current data to be extracted are determined by obtaining the discrete current data to be extracted corresponding to the Internet of things equipment; extracting state frame information corresponding to discrete current data of discrete current data to be extracted by a state frame extraction method; according to the definition of the event block, the current value in the discrete current data corresponding to the state frame information is placed in the event block; and acquiring a current value random signal corresponding to the Internet of things equipment from the event block. According to the current signal extraction method, the state frame extraction method and the event block definition of discrete current data to be extracted corresponding to the Internet of things equipment are determined, then state frame information is extracted from the data to be extracted based on the state frame extraction method, the current value in the discrete current data corresponding to the state frame information is placed into the event block based on the event block definition, the current value is classified, the current value random signal is extracted based on the event block, noise data in the discrete current data are filtered, and therefore working details of the Internet of things equipment are effectively reserved.
In one embodiment, as shown in fig. 3, step 201 includes:
step 302, searching a preset data extraction model corresponding to the discrete current data.
Step 304, inputting the discrete current data into a preset data extraction model, and performing state classification labeling on the current values in the discrete current data through the preset data extraction model to obtain a current value labeling result.
And step 306, acquiring the state frame information corresponding to the discrete current data according to the current value marking result.
The preset data extraction model can be a convolutional neural network model and a convolutional neural network, and the convolutional neural network is a feedforward neural network which comprises convolutional calculation and has a deep structure and is one of the representative algorithms of deep learning. Convolutional neural networks have a characteristic learning ability, and can perform translation invariant classification on input information according to a hierarchical structure thereof, and are also called "translation invariant artificial neural networks".
Specifically, the state frame information can be identified by an artificial intelligence method, and the state frame identification operation in the current data to be extracted is performed by a pre-trained convolutional neural network. When the method is used, a corresponding convolution kernel can be defined for each state frame, then the current values acquired by continuous low frequency are subjected to state classification by using a convolution algorithm, and then the classified current values are labeled. Because a single current value is not high in reference value due to interference of a large amount of noise in a real scene, the accuracy of discrete current noise data filtering in the process of extracting a state frame is greatly improved by comprehensively judging the state according to a time sequence historical current value related to the current value by using a convolution algorithm. In this embodiment, the extraction of the state frame information is performed through the preset data extraction model, so that the efficiency and accuracy of the extraction of the state frame information can be ensured.
In one embodiment, before step 302, the method further includes:
step 401, obtaining device operation history data corresponding to the internet of things device, and labeling discrete current frames in the device operation history data according to the operation state of the internet of things device.
And 403, training the initial convolutional neural network model based on the marked equipment operation historical data to obtain a preset data extraction model.
Specifically, the method further comprises a process of presetting a data extraction model, wherein the process is mainly carried out by taking historical data of equipment operation as model training. The method comprises the steps of firstly obtaining historical data of operation of the Internet of things equipment corresponding to discrete current data, labeling discrete current frames corresponding to the historical data according to the operation state of the Internet of things equipment, then carrying out supervised training on an initial convolutional neural network model by taking the labeled historical data as model training data, defining a corresponding convolutional kernel for each state frame in the training process, and then carrying out model training by using a convolutional algorithm. The model training process can also comprise a model checking process, the marked equipment operation historical data are divided into a training group and a testing group, after the initial convolutional neural network model is trained based on the training group, the trained model can be checked through the testing group, and the model passing the checking is taken as a preset data extraction model. In this embodiment, the initial convolutional neural network model is trained based on the labeled device operation historical data to obtain a preset data extraction model, so that the state frame extraction accuracy of the preset data extraction model can be ensured.
In one embodiment, as shown in FIG. 5, step 205 comprises:
step 502, find the standard current value and the standard current value timing sequence corresponding to the event block definition.
Step 504, based on the current value and the current value timing labeled in the status frame information, the current value in the discrete current data corresponding to the status frame information is placed into the event block.
The standard current value and the standard current value time sequence of the equipment of the internet of things are generally corresponding to the operation events of the equipment of the internet of things, so that the standard current value and the standard current value time sequence of the equipment of the internet of things under the corresponding operation time can be measured by a historical data summarization or a pre-measurement method before the current signal extraction method is used.
Specifically, after the corresponding status frame labeling is performed on the current value, the current value added with the status frame label may be placed in the corresponding position of the event block. In the process of matching the state frame with the event block, the current value in the discrete current data corresponding to the state frame information needs to be embedded into the event block by considering the timing between the state frames, that is, based on the magnitude and the timing of the current value. In this embodiment, the current value in the discrete current data corresponding to the state frame information is placed into the event block based on the current value and the current value timing sequence labeled in the state frame information, so that the accuracy of placing the current value can be effectively ensured.
In one embodiment, the step of placing the current value in the discrete current data corresponding to the state frame information into the event block based on the current value labeled in the state frame information and the current value timing sequence includes: determining the similarity between the current value in the discrete current data corresponding to the state frame information and the standard current value corresponding to the event block definition based on the current value marked in the state frame information and the current value time sequence; and when the similarity is greater than a preset similarity threshold, setting the current value in the discrete current data corresponding to the state frame information into an event block corresponding to the event block definition.
Particularly, when the discrete current data is embedded, the problem of partial missing of the state frames is considered, if the defined similarity between the time sequence combination of some current frames and the event block exceeds a certain threshold, the current value in the discrete current data corresponding to the state frame information can be embedded into the event block, so that the identification accuracy is ensured, and the current value in the discrete current data corresponding to the state frame information can be embedded into the event block as much as possible. The similarity threshold may be set according to the accuracy requirement of data extraction, and generally, the greater the similarity, the higher the accuracy of current signal extraction, but the smaller the amount of extracted current signal data will be. In a specific embodiment, the calibration current value at each time sequence in the current frame time sequence combination can be determined directly according to the definition of the event block. And then calculating the similarity according to the actual current value and the calibrated current value corresponding to the current frame. In another embodiment, a current change fitting curve corresponding to the current frame may be generated based on the time sequence combination of the current frames, and then compared with a current change fitting curve corresponding to the event block, and the similarity may be determined by methods such as Frechet or Hausdorff. In this embodiment, the current value in the discrete current data corresponding to the state frame information is placed into the event block by the similarity to define the corresponding event block, so that the accuracy of the current value placement process can be ensured.
In one embodiment, as shown in fig. 6, after step 207, the method further includes:
step 601, extracting a non-stationary current signal in the current value random signal.
Step 603, performing anomaly detection on the non-stationary current signal to obtain an anomaly detection result.
Step 605, an abnormality detection result is fed back.
Specifically, when the data extracted from the event block does not exhibit a stationary random state, it indicates that an abnormality occurs in the real event corresponding to the discrete current data, and at this time, corresponding abnormality detection may be performed on the current data exhibiting the non-stationary random state, and then abnormality analysis result data obtained by the abnormality detection is fed back. In this embodiment, the event block can effectively improve the effect of performing anomaly detection on the discrete current signal.
In one embodiment, after step 207, the method further includes: extracting stable random signals in the current value random signals; obtaining a device current analysis result corresponding to the stable random signal; and feeding back the current analysis result of the equipment.
Specifically, stationary random signal portions can be distinguished at the current value random signal extracted by the event block. After the stationary random signal is determined, the stationary random signal can be analyzed. Because the data acquired based on the sensing data are non-stationary random signals, in order to analyze the non-stationary random signals, part of noise data can be filtered from the current data to be extracted through the current signal extraction method, so that stationary random signals capable of effectively analyzing the equipment current are obtained, and after the stationary random signals are obtained, the stationary random signals can be analyzed, and corresponding equipment current analysis results are obtained.
It should be understood that although the various steps in the flow charts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a current signal extracting apparatus including:
the data obtaining module 702 is configured to obtain discrete current data corresponding to the internet of things device, and determine a state frame extraction method and an event block definition corresponding to the discrete current data, where the event block definition is used to define an operation event of the internet of things device.
And an information extraction module 704, configured to extract, by using a state frame extraction method, state frame information corresponding to the discrete current data.
And an information embedding module 706, configured to embed, according to the event block definition, a current value in the discrete current data corresponding to the state frame information into the event block.
The signal extraction module 708 is configured to obtain a current value random signal corresponding to the internet of things device from the event block.
In one embodiment, the information extraction module 704 is specifically configured to: searching a preset data extraction model corresponding to the discrete current data; inputting discrete current data into a preset data extraction model, and performing state classification and labeling on current values in the discrete current data through the preset data extraction model to obtain a current value labeling result; and acquiring state frame information corresponding to the discrete current data according to the current value marking result.
In one embodiment, the system further includes a model training module, specifically configured to: acquiring equipment operation historical data corresponding to the Internet of things equipment, and labeling discrete current frames in the equipment operation historical data according to the operation state of the Internet of things equipment; and training the initial convolutional neural network model based on the marked equipment operation historical data to obtain a preset data extraction model.
In one embodiment, the information embedding module 706 is specifically configured to: searching an event block to define a corresponding standard current value and a standard current value time sequence; and based on the current value marked in the state frame information and the current value time sequence, putting the current value in the discrete current data corresponding to the state frame information into the event block.
In one embodiment, the information placement module 706 is further configured to: determining the similarity between the current value in the discrete current data corresponding to the state frame information and the standard current value corresponding to the event block definition based on the current value marked in the state frame information and the current value time sequence; and when the similarity is greater than a preset similarity threshold, setting the current value in the discrete current data corresponding to the state frame information into an event block corresponding to the event block definition.
In one embodiment, the system further comprises an anomaly detection module, configured to: extracting a non-stationary current signal in the current value random signal; carrying out anomaly detection on the non-stationary current signal to obtain an anomaly detection result; and feeding back an abnormal detection result.
In one embodiment, the apparatus further comprises a current analysis module for: extracting stable random signals in the current value random signals; obtaining a device current analysis result corresponding to the stable random signal; and feeding back the current analysis result of the equipment.
For specific embodiments of the current signal extraction device, reference may be made to the above embodiments of the current signal extraction method, and details are not described here. The respective modules in the current signal extraction device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing current signal extraction data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a current signal extraction method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
acquiring discrete current data corresponding to the Internet of things equipment, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
extracting state frame information corresponding to the discrete current data by a state frame extraction method;
according to the definition of the event block, the current value in the discrete current data corresponding to the state frame information is placed in the event block;
and acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
In one embodiment, the processor, when executing the computer program, further performs the steps of: searching a preset data extraction model corresponding to the discrete current data; inputting discrete current data into a preset data extraction model, and performing state classification and labeling on current values in the discrete current data through the preset data extraction model to obtain a current value labeling result; and acquiring state frame information corresponding to the discrete current data according to the current value marking result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring equipment operation historical data corresponding to the Internet of things equipment, and labeling discrete current frames in the equipment operation historical data according to the operation state of the Internet of things equipment; and training the initial convolutional neural network model based on the marked equipment operation historical data to obtain a preset data extraction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: searching an event block to define a corresponding standard current value and a standard current value time sequence; and setting the current value in the discrete current data corresponding to the state frame information into the event block according to the current value marked in the state frame information and the current value time sequence.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining the similarity between the current value in the discrete current data corresponding to the state frame information and the standard current value corresponding to the event block definition based on the current value marked in the state frame information and the current value time sequence; and when the similarity is greater than a preset similarity threshold, setting the current value in the discrete current data corresponding to the state frame information into an event block corresponding to the event block definition.
In one embodiment, the processor, when executing the computer program, further performs the steps of: extracting a non-stationary current signal in the current value random signal; carrying out anomaly detection on the non-stationary current signal to obtain an anomaly detection result; and feeding back an abnormal detection result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: extracting stable random signals in the current value random signals; obtaining a device current analysis result corresponding to the stable random signal; and feeding back the current analysis result of the equipment.
In one embodiment, a computer storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of:
acquiring discrete current data corresponding to the Internet of things equipment, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
extracting state frame information corresponding to the discrete current data by a state frame extraction method;
according to the definition of the event block, the current value in the discrete current data corresponding to the state frame information is placed in the event block;
and acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching a preset data extraction model corresponding to the discrete current data; inputting discrete current data into a preset data extraction model, and performing state classification and labeling on current values in the discrete current data through the preset data extraction model to obtain a current value labeling result; and acquiring state frame information corresponding to the discrete current data according to the current value marking result.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring equipment operation historical data corresponding to the Internet of things equipment, and labeling discrete current frames in the equipment operation historical data according to the operation state of the Internet of things equipment; and training the initial convolutional neural network model based on the marked equipment operation historical data to obtain a preset data extraction model.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching an event block to define a corresponding standard current value and a standard current value time sequence; and setting the current value in the discrete current data corresponding to the state frame information into the event block according to the current value marked in the state frame information and the current value time sequence.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining the similarity between the current value in the discrete current data corresponding to the state frame information and the standard current value corresponding to the event block definition based on the current value marked in the state frame information and the current value time sequence; and when the similarity is greater than a preset similarity threshold, setting the current value in the discrete current data corresponding to the state frame information into an event block corresponding to the event block definition.
In one embodiment, the computer program when executed by the processor further performs the steps of: extracting a non-stationary current signal in the current value random signal; carrying out anomaly detection on the non-stationary current signal to obtain an anomaly detection result; and feeding back an abnormal detection result.
In one embodiment, the computer program when executed by the processor further performs the steps of: extracting stable random signals in the current value random signals; obtaining a device current analysis result corresponding to the stable random signal; and feeding back the current analysis result of the equipment.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A current signal extraction method, the method comprising:
acquiring discrete current data corresponding to Internet of things equipment, and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
extracting state frame information corresponding to the discrete current data through the state frame extraction method;
according to the event block definition, a current value in discrete current data corresponding to the state frame information is placed in an event block;
and acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
2. The method of claim 1, wherein the extracting the state frame information corresponding to the discrete current data by the state frame extraction method comprises:
searching a preset data extraction model corresponding to the discrete current data;
inputting the discrete current data into the preset data extraction model, and carrying out state classification and labeling on the current values in the discrete current data through the preset data extraction model to obtain a current value labeling result;
and acquiring state frame information corresponding to the discrete current data according to the current value marking result.
3. The method according to claim 2, wherein before searching for the preset data extraction model corresponding to the discrete current data, the method further comprises:
acquiring equipment operation historical data corresponding to the Internet of things equipment, and marking discrete current frames in the equipment operation historical data according to the operation state of the Internet of things equipment;
and training the initial convolutional neural network model based on the marked equipment operation historical data to obtain a preset data extraction model.
4. The method according to claim 2, wherein the placing the current value in the discrete current data corresponding to the status frame information into the event block according to the event block definition comprises:
searching a standard current value and a standard current value time sequence corresponding to the event block definition;
and based on the current value marked in the state frame information and the current value time sequence, putting the current value in the discrete current data corresponding to the state frame information into an event block.
5. The method of claim 4, wherein the placing the current value in the discrete current data corresponding to the status frame information into the event block based on the current value labeled in the status frame information and the current value timing comprises:
determining similarity between a current value in discrete current data corresponding to the state frame information and a standard current value corresponding to event block definition based on the current value marked in the state frame information and a current value time sequence;
and when the similarity is greater than a preset similarity threshold, setting a current value in the discrete current data corresponding to the state frame information into an event block corresponding to the event block definition.
6. The method of claim 1, wherein after obtaining the random signal of current values corresponding to the discrete current data from the event block, further comprising:
extracting a non-stationary current signal in the current value random signal;
carrying out abnormity detection on the non-stationary current signal to obtain an abnormity detection result;
and feeding back the abnormal detection result.
7. The method of claim 1, wherein after obtaining the random signal of current values corresponding to the discrete current data from the event block, further comprising:
extracting a stationary random signal in the current value random signal;
obtaining a device current analysis result corresponding to the stable random signal;
and feeding back the current analysis result of the equipment.
8. A current signal extraction apparatus, the apparatus comprising:
the data acquisition module is used for acquiring discrete current data corresponding to the Internet of things equipment and determining a state frame extraction method and an event block definition corresponding to the discrete current data, wherein the event block definition is used for defining an operation event of the Internet of things equipment;
the information extraction module is used for extracting the state frame information corresponding to the discrete current data by the state frame extraction method;
the information embedding module is used for embedding the current value in the discrete current data corresponding to the state frame information into the event block according to the event block definition;
and the signal extraction module is used for acquiring a current value random signal corresponding to the Internet of things equipment from the event block.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer storage medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110486155.0A CN113111854A (en) | 2021-04-30 | 2021-04-30 | Current signal extraction method, current signal extraction device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110486155.0A CN113111854A (en) | 2021-04-30 | 2021-04-30 | Current signal extraction method, current signal extraction device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113111854A true CN113111854A (en) | 2021-07-13 |
Family
ID=76720832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110486155.0A Pending CN113111854A (en) | 2021-04-30 | 2021-04-30 | Current signal extraction method, current signal extraction device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111854A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451004A (en) * | 2017-07-01 | 2017-12-08 | 南京理工大学 | A kind of switch breakdown diagnostic method based on qualitiative trends analysis |
| CN109241915A (en) * | 2018-09-11 | 2019-01-18 | 浙江大学 | The intelligent power plant's pump machine method for diagnosing faults screened based on the steady non-stationary differentiation of vibration signal and feature |
| CN111144267A (en) * | 2019-12-23 | 2020-05-12 | 上海联影智能医疗科技有限公司 | Equipment operation state detection method and device, storage medium and computer equipment |
| CN111614491A (en) * | 2020-05-06 | 2020-09-01 | 国网电力科学研究院有限公司 | Power monitoring system oriented safety situation assessment index selection method and system |
| CN111859384A (en) * | 2020-07-23 | 2020-10-30 | 平安证券股份有限公司 | Abnormal event monitoring method and device, computer equipment and storage medium |
| CN112171376A (en) * | 2020-08-21 | 2021-01-05 | 杭州玖欣物联科技有限公司 | Machine tool workpiece real-time statistical method based on current signal segmentation |
| CN112256774A (en) * | 2020-09-27 | 2021-01-22 | 深圳供电局有限公司 | Power data processing method and device, computer equipment and storage medium |
| CN112257610A (en) * | 2020-10-23 | 2021-01-22 | 岭东核电有限公司 | Nuclear power equipment monitoring method and device, computer equipment and storage medium |
-
2021
- 2021-04-30 CN CN202110486155.0A patent/CN113111854A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451004A (en) * | 2017-07-01 | 2017-12-08 | 南京理工大学 | A kind of switch breakdown diagnostic method based on qualitiative trends analysis |
| CN109241915A (en) * | 2018-09-11 | 2019-01-18 | 浙江大学 | The intelligent power plant's pump machine method for diagnosing faults screened based on the steady non-stationary differentiation of vibration signal and feature |
| CN111144267A (en) * | 2019-12-23 | 2020-05-12 | 上海联影智能医疗科技有限公司 | Equipment operation state detection method and device, storage medium and computer equipment |
| CN111614491A (en) * | 2020-05-06 | 2020-09-01 | 国网电力科学研究院有限公司 | Power monitoring system oriented safety situation assessment index selection method and system |
| CN111859384A (en) * | 2020-07-23 | 2020-10-30 | 平安证券股份有限公司 | Abnormal event monitoring method and device, computer equipment and storage medium |
| CN112171376A (en) * | 2020-08-21 | 2021-01-05 | 杭州玖欣物联科技有限公司 | Machine tool workpiece real-time statistical method based on current signal segmentation |
| CN112256774A (en) * | 2020-09-27 | 2021-01-22 | 深圳供电局有限公司 | Power data processing method and device, computer equipment and storage medium |
| CN112257610A (en) * | 2020-10-23 | 2021-01-22 | 岭东核电有限公司 | Nuclear power equipment monitoring method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2997489C (en) | Method and system for health monitoring and fault signature identification | |
| CN111177714B (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
| CN110008082B (en) | Abnormal task intelligent monitoring method, device, equipment and storage medium | |
| CN106294219B (en) | Equipment identification and data processing method, device and system | |
| CN111325159B (en) | Fault diagnosis method, device, computer equipment and storage medium | |
| CN113284002A (en) | Power consumption data anomaly detection method and device, computer equipment and storage medium | |
| CN111694718A (en) | Method and device for identifying abnormal behavior of intranet user, computer equipment and readable storage medium | |
| CN111523683B (en) | Method and system for predicting technological parameters in tobacco processing | |
| CN111738404B (en) | Model training task processing method and device, electronic equipment and storage medium | |
| CN113093985B (en) | Sensor data link abnormity detection method and device and computer equipment | |
| CN108200087B (en) | Web intrusion detection method and device, computer equipment and storage medium | |
| CN110912908A (en) | Network protocol anomaly detection method and device, computer equipment and storage medium | |
| CN112541016A (en) | Power consumption abnormality detection method, device, computer equipment and storage medium | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN111679953B (en) | Fault node identification method, device, equipment and medium based on artificial intelligence | |
| CN111898035A (en) | Data processing strategy configuration method and device based on Internet of things and computer equipment | |
| CN110889357A (en) | Underground cable fault detection method and device based on marked area | |
| CN113111854A (en) | Current signal extraction method, current signal extraction device, computer equipment and storage medium | |
| CN113808727B (en) | Device monitoring method, device, computer device and readable storage medium | |
| CN113222370B (en) | Power system risk early warning method, device, equipment and storage medium | |
| CN110838940A (en) | Underground cable inspection task configuration method and device | |
| CN114756671A (en) | Article recommendation method and device, computer equipment and storage medium | |
| CN113052938A (en) | Method and device for constructing boiler energy efficiency curve | |
| CN110907749A (en) | Method and device for positioning fault underground cable | |
| CN110991473A (en) | Feature selection method and device for image sample, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210713 |
|
| RJ01 | Rejection of invention patent application after publication |