CN112083707A - Industrial control physical signal processing method, controller and processing system - Google Patents
Industrial control physical signal processing method, controller and processing system Download PDFInfo
- Publication number
- CN112083707A CN112083707A CN202010778395.3A CN202010778395A CN112083707A CN 112083707 A CN112083707 A CN 112083707A CN 202010778395 A CN202010778395 A CN 202010778395A CN 112083707 A CN112083707 A CN 112083707A
- Authority
- CN
- China
- Prior art keywords
- industrial control
- control physical
- deep learning
- physical signals
- processing
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Abstract
The invention discloses a processing method, a controller and a processing system of industrial control physical signals, which comprises the steps of acquiring signals and collecting industrial control physical signals; a signal distribution step, namely distributing industrial control physical signals to a plurality of computing nodes; signal decoding, each computing node performs parallel decoding computation on the distributed industrial control physical signals; a combination step, namely combining decoding signals obtained by decoding and calculating of each calculation node to obtain plaintext characters; and in the deep learning identification step, plaintext characters are identified and classified based on a deep learning model to obtain industrial control behavior information.
Description
Technical Field
The invention relates to the field of industrial control, in particular to a processing method, a controller and a processing system of industrial control physical signals.
Background
The technical development in the fields of industrial control automation and intelligent manufacturing provides technical support for intelligent manufacturing, industrial 4.0, industrial internet of things, IIoT, cloud manufacturing, industrial robots and automatic control. The industrial control industry gradually enters the internet era, however, the industrial control security vulnerability problem also becomes more prominent, and the number of industrial control security problem events gradually rises. On the other hand, the rise of the artificial intelligence technology brings fundamental changes to various industries.
The prior art is in the bud state in the aspect of intelligent detection, and the industrial control field segmentation trade is many, and the information security protection degree of difficulty is great, unable intellectual detection system and universalization. The industrial control has numerous subdivision fields, industrial control safety events relate to key manufacturing, energy, communication and other important industries, but the market aiming at the industrial control safety only covers some attention points at present, and comprehensive and intelligent detection cannot be achieved. In the face of the industry distribution with high subdivision degree, the industrial comprehensive detection is not difficult, and the comprehensive protection of industrial control network information safety is not easy to realize.
Specifically, the physical electrical signals of the general transmitted industrial control equipment are level signal sequences, and are presented by bit digital signals of 0 and 1 after sampling and conversion, and due to the fact that related industries are more, the industrial control physical signals become complicated, interference and errors exist in the processes of triggering, transmission and the like, the processing method of the conventional industrial control physical signals is slow in speed, meanwhile, the conversion accuracy is low, and when the method is applied to different fields, the method cannot be well compatible, the operation condition of the industrial control equipment cannot be accurately judged, and subsequent control misoperation can be possibly caused.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a processing method of industrial control physical signals, which accelerates the processing speed, improves the identification precision and has strong compatibility.
The invention also provides a controller which can quickly process the industrial control physical signal and accurately output industrial control behavior information.
The invention also provides a processing system which can process the collected industrial control physical signals and accurately output industrial control behavior information to know the operation condition of the industrial control equipment.
According to the embodiment of the first aspect of the invention, the method for processing the industrial control physical signal comprises the following steps: acquiring a signal, namely acquiring an industrial control physical signal; a signal distribution step, namely distributing industrial control physical signals to a plurality of computing nodes; signal decoding, each computing node performs parallel decoding computation on the distributed industrial control physical signals; a combination step, namely combining decoding signals obtained by decoding and calculating of each calculation node to obtain plaintext characters; and a deep learning identification step, namely identifying and classifying plaintext characters based on a deep learning model to obtain industrial control behavior information.
The method for processing the industrial control physical signal, provided by the embodiment of the invention, has at least the following beneficial effects:
the invention relates to a processing method of industrial control physical signals, which collects the industrial control physical signals, distributes the working condition physical signals to each computing node, decodes each segment of the industrial control physical signals distributed by each computing node in parallel, can decode the industrial control physical signals quickly, and combines the signals to form plaintext characters, the plaintext characters in the stage still have large noise interference, the plaintext characters are input into a deep learning model for identification and classification, and corresponding industrial control behavior information can be obtained by accurate matching.
According to some embodiments of the invention, in the deep learning identification step, a plaintext character is identified based on a training library of a deep learning model, and corresponding industrial control behavior information is obtained through classification by a classifier.
According to some embodiments of the invention, in the deep learning identification step, plaintext characters are distributed and sent to a plurality of deep learning identification models for identification and classification, and then classification results of the deep learning identification models are combined to form industrial control behavior information.
According to some embodiments of the invention, the deep learning model is a cnn framework model or an rnn framework model.
According to some embodiments of the invention, in the combining step, the decoded signals decoded and calculated by the computing nodes are combined in time sequence to obtain plaintext characters.
According to some embodiments of the present invention, in the signal decoding step, the industrial control physical signal is descrambled and restored to be a character code, and the character code is searched for a plaintext character.
According to some embodiments of the invention, in the signal distribution step, bandwidth is allocated to each computing node according to the flow of the industrial control physical signal and the load capacity of the computing node according to the requirement based on the software defined network.
According to some embodiments of the invention, after the deep learning identification step, the method further comprises: and a data storage step, namely matching and storing the collected industrial control physical signals and the industrial control behavior information obtained by processing in a database.
A controller according to an embodiment of the second aspect of the invention comprises at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor is enabled to implement the method for processing the industrial control physical signal disclosed in any of the above embodiments.
The controller according to the embodiment of the invention has at least the following beneficial effects:
the controller can quickly process industrial control physical signals and accurately output industrial control behavior information.
The processing system according to the third aspect of the present invention includes an acquisition module, an output module, and a processing module respectively connected to the acquisition module and the output module, where the acquisition module is used to connect to an external industrial control device, and the processing module can run the processing method for the industrial control physical signal disclosed in any of the above embodiments and output industrial control behavior information through the output module.
The processing system provided by the embodiment of the invention has at least the following beneficial effects:
the processing system can process the collected industrial control physical signals and accurately output industrial control behavior information to know the operation condition of the industrial control equipment.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a main flow chart of a method for processing industrial control physical signals according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for processing industrial control physical signals according to an embodiment of the present invention;
FIG. 3 is a block diagram of the schematic structure of one embodiment of the processing system of the present invention.
Reference numerals:
the system comprises an acquisition module 100, industrial control equipment 200, a processing module 300 and an output module 400.
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 accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the positional or orientational descriptions referred to, for example, the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., are based on the positional or orientational relationships shown in the drawings and are for convenience of description and simplicity of description only, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1 to 3, a method for processing an industrial control physical signal according to an embodiment of the present invention includes: acquiring a signal, namely acquiring an industrial control physical signal; a signal distribution step, namely distributing industrial control physical signals to a plurality of computing nodes; signal decoding, each computing node performs parallel decoding computation on the distributed industrial control physical signals; a combination step, namely combining decoding signals obtained by decoding and calculating of each calculation node to obtain plaintext characters; and a deep learning identification step, namely identifying and classifying plaintext characters based on a deep learning model to obtain industrial control behavior information.
The invention relates to a processing method of industrial control physical signals, which collects the industrial control physical signals, distributes the working condition physical signals to each computing node, decodes each distributed section of industrial control physical signals in parallel by each computing node, can decode the industrial control physical signals quickly, and combines to form plaintext characters, the plaintext characters in the stage still have larger noise interference, the plaintext characters are input into a deep learning model for identification and classification, corresponding industrial control behavior information can be obtained by accurate matching, and the method can deal with the control of processing more industrial control devices 200 due to the improvement of the accuracy, and has the advantages of accelerated processing speed, improved identification accuracy and strong compatibility.
In the signal acquiring step, the NI acquisition device may be used to acquire the industrial control physical signal from the acquisition point, so as to obtain the physical electrical signal of the industrial control device 200, the physical electrical signal of the industrial control device 200 is a level signal sequence, the sampling frequency may be in a physical signal range of 100M-1000M, the physical signal range is suitable for the signal frequency of most industrial control devices 200, and the sampled physical signal is converted into bits of digital signals 0 and 1.
In some embodiments of the present invention, the acquired data is abnormally large due to large bandwidth of acquired signal frequency, while unreasonable allocation may cause large load on part of computing nodes and slow processing rate, and in the signal distribution step, bandwidth is allocated to each computing node as needed according to the flow of industrial control physical signals and the load capacity of the computing node based on a Software Defined Network (SDN), so as to implement reasonable allocation and balance the processing rate of each computing node.
In some embodiments of the present invention, the signal decoding step descrambles the industrial control physical signal to restore to a character code, and searches for a plaintext character by matching the character code.
Specifically, according to actual conditions, a corresponding industrial signal standard coding algorithm and an inverse coding algorithm are adopted, and the distributed collected industrial control physical signals are cracked by the computing node. And restoring by adopting a corresponding descrambling mode, and performing algorithm matching by character coding search to obtain plaintext characters, wherein a distributed algorithm is required due to a large matching search space, and each computing node is performed in parallel according to a cracking algorithm.
In some embodiments of the present invention, as shown in fig. 2, in the deep learning identification step, a plaintext character is identified based on a training library of a deep learning model, and corresponding industrial control behavior information is obtained through classification by a classifier.
Specifically, the deep learning model is a cnn frame model or an rnn frame model, and the cnn frame model or the rnn frame model can identify and classify the industrial control signals at the character level; before, a cnn frame model or an rnn frame model is required to be modeled, specifically, a large number of industrial control physical signals and corresponding industrial control behavior information data are added to be trained in a conventional cnn frame model or a rnn frame model, the operation rule of the data is observed, and a data behavior library is built; and a full data analysis strategy is adopted to realize omnibearing and deep recognition from physical layer data to application layer data.
In some embodiments of the present invention, in the deep learning identification step, plaintext characters are distributed and sent to a plurality of deep learning identification models for identification and classification, and then classification results of the deep learning identification models are combined to form industrial control behavior information, so as to accelerate the rate of deep learning identification.
In some embodiments of the present invention, the combining step combines the decoded signals decoded and calculated by the respective computing nodes in time sequence to obtain the plaintext character.
And combining the plaintext characters decoded by each computing node according to a time sequence to finally obtain complete control information corresponding to the industrial control physical signal. The control information is used for industrial control behavior recognition, such as air conditioner control, manipulator attitude adjustment and other industrial control behaviors.
In some embodiments of the present invention, after the deep learning identification step, the method further includes a data storage step, in which the collected industrial control physical signals and the processed industrial control behavior information are stored in a database in a matching manner, where the database may adopt a time sequence database or use a memory database in combination with the time sequence database to accelerate the response of the data, which is beneficial to monitoring, checking and analyzing the collected real-time industrial control physical signals, and the data has the advantages of fast generation frequency, severe dependence on the collection time, large information amount of multiple measurement points, and generation of hundreds of megabits to gigabytes of data per second at a single monitoring point.
A controller according to an embodiment of the second aspect of the invention, as shown in fig. 1-3, comprises at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor is enabled to implement the method for processing the industrial control physical signal disclosed in any of the above embodiments.
The controller can quickly process industrial control physical signals and accurately output industrial control behavior information.
The processing system according to the third embodiment of the present invention, as shown in fig. 1 to 3, includes an acquisition module 100, an output module 400, and a processing module 300 connected to the acquisition module 100 and the output module 400, where the acquisition module 100 is used to connect to an external industrial control device 200, the processing module 300 is capable of operating the processing method of the industrial control physical signal disclosed in any of the above embodiments and outputting industrial control behavior information through the output module 400, the processing module may be a CPU, the output module may be a display screen, the industrial control device may be an air conditioner, a robot arm, and the like, and the acquisition module may be a detection circuit matched with the industrial control device.
The processing system can distinguish more industrial control physical signals and can rapidly process the industrial control physical signals due to the improvement of the accuracy, and the industrial control equipment 200 can relate to more fields.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. A method for processing industrial control physical signals is characterized by comprising the following steps:
acquiring a signal, namely acquiring an industrial control physical signal;
a signal distribution step, namely distributing industrial control physical signals to a plurality of computing nodes;
signal decoding, each computing node performs parallel decoding computation on the distributed industrial control physical signals;
a combination step, namely combining decoding signals obtained by decoding and calculating of each calculation node to obtain plaintext characters;
and a deep learning identification step, namely identifying and classifying plaintext characters based on a deep learning model to obtain industrial control behavior information.
2. The industrial control physical signal processing method according to claim 1, wherein in the deep learning identification step, plaintext characters are identified based on a training library of a deep learning model, and corresponding industrial control behavior information is obtained through classification by a classifier.
3. The industrial control physical signal processing method according to claim 1, wherein in the deep learning identification step, plaintext characters are distributed and sent to a plurality of deep learning identification models for identification and classification, and classification results of the deep learning identification models are combined to form industrial control behavior information.
4. The method for processing industrial control physical signals according to claim 2 or 3, wherein the deep learning model is a cnn frame model or an rnn frame model.
5. The industrial control physical signal processing method according to claim 1, wherein in the combining step, the decoded signals decoded and calculated by the computing nodes are combined in time sequence to obtain plaintext characters.
6. The method as claimed in claim 1, wherein in the signal decoding step, the industrial control physical signal is descrambled and restored to be a character code, and the character code is matched and searched to obtain a plaintext character.
7. The method for processing industrial control physical signals according to claim 1, wherein in the signal distribution step, bandwidth is allocated to each computing node according to the flow of industrial control physical signals and the load capacity of the computing node according to the requirement based on a software defined network.
8. The industrial control physical signal processing method according to claim 1, further comprising, after the deep learning identification step:
and a data storage step, namely matching and storing the collected industrial control physical signals and the industrial control behavior information obtained by processing in a database.
9. A controller, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, the at least one program causes the at least one processor to implement the method for processing industrial control physical signals according to any one of claims 1-8.
10. A processing system, comprising an acquisition module, an output module and a processing module respectively connected with the acquisition module and the output module, wherein the acquisition module is used for being connected with external industrial control equipment, and the processing module can operate the processing method of industrial control physical signals according to any one of claims 1 to 8 and output industrial control behavior information through the output module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010778395.3A CN112083707A (en) | 2020-08-05 | 2020-08-05 | Industrial control physical signal processing method, controller and processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010778395.3A CN112083707A (en) | 2020-08-05 | 2020-08-05 | Industrial control physical signal processing method, controller and processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112083707A true CN112083707A (en) | 2020-12-15 |
Family
ID=73735517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010778395.3A Pending CN112083707A (en) | 2020-08-05 | 2020-08-05 | Industrial control physical signal processing method, controller and processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112083707A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114035679A (en) * | 2021-10-26 | 2022-02-11 | 浙江大学 | Dynamically-reconfigurable parallel decoding method and device for cranial nerve signals |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1121754A (en) * | 1993-05-05 | 1996-05-01 | 刘尊全 | A repertoire of mappings for a cryptosystem |
| CN102238001A (en) * | 2010-05-07 | 2011-11-09 | 腾讯数码（深圳）有限公司 | Method and device for enhancing data security |
| CN109302501A (en) * | 2018-12-10 | 2019-02-01 | 北京八分量信息科技有限公司 | A kind of industrial control data storage method based on block chain technology, apparatus and system |
| CN110334886A (en) * | 2018-03-29 | 2019-10-15 | 三星电子株式会社 | Device diagnostic system and method based on deep learning |
| CN110430219A (en) * | 2019-08-24 | 2019-11-08 | 深圳旦倍科技有限公司 | Method and system of the various protocols internet of things equipment from adaptation |
-
2020
- 2020-08-05 CN CN202010778395.3A patent/CN112083707A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1121754A (en) * | 1993-05-05 | 1996-05-01 | 刘尊全 | A repertoire of mappings for a cryptosystem |
| CN102238001A (en) * | 2010-05-07 | 2011-11-09 | 腾讯数码（深圳）有限公司 | Method and device for enhancing data security |
| CN110334886A (en) * | 2018-03-29 | 2019-10-15 | 三星电子株式会社 | Device diagnostic system and method based on deep learning |
| CN109302501A (en) * | 2018-12-10 | 2019-02-01 | 北京八分量信息科技有限公司 | A kind of industrial control data storage method based on block chain technology, apparatus and system |
| CN110430219A (en) * | 2019-08-24 | 2019-11-08 | 深圳旦倍科技有限公司 | Method and system of the various protocols internet of things equipment from adaptation |
Non-Patent Citations (1)
| Title |
|---|
| 赵晓光: "并行计算在网络安全中的应用", 《网络安全技术与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114035679A (en) * | 2021-10-26 | 2022-02-11 | 浙江大学 | Dynamically-reconfigurable parallel decoding method and device for cranial nerve signals |
| CN114035679B (en) * | 2021-10-26 | 2023-11-17 | 浙江大学 | Brain nerve signal parallel decoding method and device capable of dynamically recombining |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10970186B2 (en) | Correlation-based analytic for time-series data | |
| US20230300159A1 (en) | Network traffic anomaly detection method and apparatus, and electronic apparatus and storage medium | |
| JP7116103B2 (en) | Method, Apparatus, and Device for Predicting Optical Module Failure | |
| CN108460397B (en) | Method and device for analyzing equipment fault type, storage medium and electronic equipment | |
| CN112911627B (en) | Wireless network performance detection method, device and storage medium | |
| CN112183758A (en) | Method and device for realizing model training and computer storage medium | |
| WO2018180197A1 (en) | Data analysis device, data analysis method and data analysis program | |
| CN111397902A (en) | Rolling bearing fault diagnosis method based on feature alignment convolutional neural network | |
| CN110825545A (en) | Cloud service platform anomaly detection method and system | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN112101765A (en) | Abnormal data processing method and system for operation index data of power distribution network | |
| CN114861788A (en) | Load abnormity detection method and system based on DBSCAN clustering | |
| CN114511026A (en) | Fault diagnosis method and device, terminal equipment and storage medium | |
| CN117041017A (en) | Intelligent operation and maintenance management method and system for data center | |
| CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
| CN113487223B (en) | Risk assessment method and system based on information fusion | |
| CN112083707A (en) | Industrial control physical signal processing method, controller and processing system | |
| CN114564345A (en) | Server abnormity detection method, device, equipment and storage medium | |
| CN116719831B (en) | Standard database establishment and update method for health monitoring | |
| CN111860598B (en) | Data analysis method and electronic equipment for identifying sports behaviors and relationships | |
| CN117368651A (en) | Comprehensive analysis system and method for faults of power distribution network | |
| CN117034123A (en) | Fault monitoring system and method for fitness equipment | |
| CN115270983A (en) | Switch cabinet fault prediction method based on AdaBoost-RBF algorithm | |
| CN112559589A (en) | Remote surveying and mapping data processing method and system | |
| CN114418036B (en) | Method, device and storage medium for testing and training performance of neural network |
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: 20201215 |
|
| RJ01 | Rejection of invention patent application after publication |