CN113719269A - On-line monitoring method for circuit working state of logging-while-drilling instrument - Google Patents
On-line monitoring method for circuit working state of logging-while-drilling instrument Download PDFInfo
- Publication number
- CN113719269A CN113719269A CN202110773330.4A CN202110773330A CN113719269A CN 113719269 A CN113719269 A CN 113719269A CN 202110773330 A CN202110773330 A CN 202110773330A CN 113719269 A CN113719269 A CN 113719269A
- Authority
- CN
- China
- Prior art keywords
- emi
- circuit
- logging
- signal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 title claims abstract description 26
- 238000005553 drilling Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000010248 power generation Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 239000002002 slurry Substances 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 6
- 230000007547 defect Effects 0.000 abstract description 2
- 230000001052 transient effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000009781 safety test method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000013585 weight reducing agent Substances 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B2200/00—Special features related to earth drilling for obtaining oil, gas or water
- E21B2200/22—Fuzzy logic, artificial intelligence, neural networks or the like
Landscapes
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses an on-line monitoring method for the working state of a circuit of a logging-while-drilling instrument, which comprises the following steps: the signal acquisition and data processing circuit based on the embedded processor is designed to acquire and calculate EMI signals of the logging-while-drilling instrument, the EMI signals generated by different circuit interfaces are different, and the EMI signals can be used as key characteristics for monitoring the circuit state. The existing instrument and equipment working state detection mode consumes more chips, and occupies a large amount of bus bandwidth during data uploading. The invention is based on power supply EMI signal detection, only one circuit board is arranged on a main line of a vortex power generation source of the logging instrument to collect EMI signals of a plurality of underground digital circuit boards, transient change of the power supply EMI signal of the logging-while-drilling instrument can be effectively detected and identified, the identification of the working state of the circuit board of the logging-while-drilling instrument is realized, and the defects are avoided.
Description
Technical Field
The invention relates to an online monitoring method for a circuit working state of a logging-while-drilling instrument, belonging to the field of power supply quality monitoring.
Background
The petroleum is used as an important energy basis of modern industrial development and is closely related to the development of technology and times, and the logging while drilling technology simultaneously completes logging tasks in the process of drilling. With the increase of the well depth, the working environment of the electric equipment of the logging instrument is diversified and complicated, and the reliable operation of the electronic equipment is more and more difficult to guarantee.
The power supply quality of the power supply of the logging instrument is directly related to the safety of underground operation and the normal work of logging instrument equipment. When the power supply equipment of the logging instrument has an emergency or continuously operates abnormally, the real-time working state of a circuit is influenced, and abnormal positioning analysis cannot be carried out on the situations.
However, in the conventional method for monitoring the working state of the instrument and equipment, the voltage and current sensors are deployed on a plurality of digital circuit boards of the instrument, and then monitoring data are transmitted to a ground system for subsequent processing. The method is easy to realize, but the method consumes more chips and increases the cost, and each circuit board needs to reserve the compact PCB area for placing the voltage and current sensor chips. Meanwhile, the acquired real-time data also occupies a large amount of bus bandwidth. This method is not suitable because of the small bandwidth of the logging instrument data transmission.
The application field of the existing instrument and equipment monitoring and identifying technology mainly comprises: (1) the power supply quality of the aerospace airborne power supply is monitored on line; (2) carrying out online detection and abnormal positioning on a power supply system of the medical equipment; (3) and monitoring the electric energy output of the electric power system in real time. By applying the technology of (1), airborne voltage and current can be acquired and recorded in real time by building an airborne power monitoring system; the application (2) carries out on-line detection and abnormal alarm on the quality of the power supply of the medical equipment through remote control and monitoring; the application (3) can be based on an embedded system, and power quality monitoring hardware is installed to monitor the power output in real time.
In the aspect of logging-while-drilling instruments, technical research on monitoring and management of working states of related circuits does not exist, and safety testing requirements in actual scientific research or production processes are greatly influenced.
Disclosure of Invention
Aiming at the defects and improvement requirements of the prior art, the invention provides an online monitoring method for the working state of a circuit of a logging-while-drilling instrument, which is based on power EMI signal detection and combines a non-invasive single-point analysis method, arranges a learning algorithm on an embedded processor, realizes high-speed data processing and classification, can effectively solve the problem of working state monitoring and identification loss of an underground circuit board, and has certain popularization.
The invention provides an on-line monitoring method for the working state of a circuit of a logging-while-drilling instrument based on power EMI signal characteristic analysis, which comprises the following steps:
s1, an EMI signal acquisition and data processing circuit based on FPGA and STM32 is deployed on an underground vortex power generation source trunk line to acquire EMI signal data and process the EMI signal data in real time;
s2, carrying out denoising and feature enhancement operation on the acquired EMI signal by using a digital signal processing method and a feature extraction algorithm such as a Kalman filtering algorithm and fast Fourier transform;
s3, converting the frequency spectrum component into a dimensionless expression by using direct current removal and normalization processing;
and S4, collecting data by using power EMI signals of different circuit board types to form a training data set and a testing data set, and labeling the data according to whether the circuit board is on line or not. Training a training data set as the input of a lightweight convolutional neural network model to obtain a power supply identification model; the neural network model is compressed and can be loaded into RAM and FLASH inside an STM32 chip.
S5, deploying the lightweight deep learning model by using an embedded processor, for example, deploying a trained lightweight convolutional neural network classification model on an STM32 embedded platform by using STM32Cube.AI;
s6, inputting actual data into a power classification model to classify the state of the circuit boards, wherein the output of the model is whether each circuit board is on line or not; and the classification result is uploaded to a central control system through a 485 bus, the central control system sends the classification result to a ground system by using slurry pulse, and an alarm is given when an offline condition occurs to the underground circuit board.
Furthermore, the EMI signal acquisition and data processing circuit comprises a signal acquisition part and a signal processing part, wherein the signal acquisition part is used for filtering and analog-to-digital conversion processing of the EMI signals, and the signal processing part comprises a time sequence control module and an operation processing module and is used for carrying out data preprocessing and classification on the EMI signals.
Further, taking kalman filtering and fast fourier transform methods as examples: based on EMI signalsThe kalman filtering process is represented as: computing Kalman gainFrom the observed value y (t)kUpdating an estimate Calculating an estimated error covariance matrixTransferring the estimation state to the next moment, and performing filtering iteration; the fast fourier transform process is represented as: for discrete EMI signals x (n), FFT transform X (k) is obtained,
further, the process of removing the dc signal from the denoised EMI signal is represented as: the normalization process is represented as:
further, the pre-trained convolutional neural network model is subjected to model compression and operation acceleration processing by adopting Tensorflow full integer quantization, and is converted into an optimized code of STM32 MCU.
In summary, the technical effects of the technical solution conceived by the present invention are as follows:
(1) compared with the prior art, the invention does not need to install a voltage sensor and a current sensor on each underground circuit board, thereby saving the chip cost and reducing the PCB area of the underground circuit board. The EMI signal acquisition circuit is deployed on a main line of a vortex power generation source, only a very small amount of underground data transmission bus bandwidth is occupied, and the method has the advantages of non-intrusive mode, single-point measurement and the like.
(2) The inherent characteristics of the EMI signal frequency spectrum characteristics of each circuit board in the well are utilized, and the classification precision of the working state of the circuit board is improved by using a convolutional neural network classification algorithm based on big data driving.
(3) The lightweight model is deployed to STM32, and preprocessing operations such as fast Fourier transform and normalization are realized on an FPGA, so that the whole processing process has strong real-time performance.
Drawings
FIG. 1 is a schematic diagram of a single point monitoring location for power EMI signals in accordance with the present invention;
FIG. 2 is a block diagram of a power EMI signal acquisition and data processing circuit system according to the present invention;
FIG. 3 is a partial frequency spectrum diagram of a power EMI signal according to the present invention;
FIG. 4 is a flow chart of the circuit EMI signal data acquisition according to the present invention;
FIG. 5 is a diagram of a circuit board status recognition result according to the present invention;
FIG. 6 is a diagram of a downhole circuit board state identification test result before and after the model weight reduction process of the present invention;
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. Although the scope of practice of the invention is not limited in this respect.
The following are examples.
Example 1:
the schematic diagram of the underground single-point EMI signal monitoring position is shown in FIG. 1, the EMI signal detection point is located on a trunk line behind the power supply switching control circuit, and EMI mixed signals reflected to the trunk line by each circuit board in the well are collected.
The system block diagram of the EMI signal acquisition and data processing circuit based on the FPGA and the STM32 is shown in FIG. 2. The signal acquisition and data processing circuit mainly comprises a signal acquisition part and a signal processing part. In order to prevent EMI signals from being submerged in large direct-current voltage generated by a power supply system and remove useless high-frequency signals, the signal acquisition part is provided with a first-order RC high-pass filter and an eighth-order Butterworth low-pass filter. Weak EMI signals were amplified 100 times to mV level using a homodyne amplifier. An analog-to-digital conversion module in the circuit completes conversion from a 12-bit analog signal to a parallel digital signal output, and an input port of an AD converter is provided with a differential driving circuit for suppressing common-mode interference. Through the design, the original EMI signal with higher signal-to-noise ratio can be acquired.
The EMI signal presents a plurality of wave crests with different frequencies and amplitudes on a frequency domain, and experiments show that the frequency spectrum of the underground circuit board is distributed within 10MHz, the sampling rate is twice of the highest frequency of the signal in consideration of the Nyquist theorem, and the ADC sampling rate is set to be 25 MHz. 4096 points are sampled each time to form a set of time series t in consideration of data amount and subsequent data processing requirementss。
Denoising the EMI time sequence signal by using a Kalman filtering algorithm, and then converting a time domain signal t by using fast Fourier transformsConversion to frequency domain signal xsThe characteristics of the EMI signal may be enhanced. The actually collected local frequency spectrums of the three circuit boards are shown in fig. 3, and the positions and the numbers of the frequency spectrum peaks of the circuit boards show obvious differences. Both the kalman filtering algorithm and the fast fourier transform are done in the FPGA, where an IP core of the fast fourier transform inside the FPGA can be used.
Since EMI signals are amplified during the acquisition process, the input bias of the amplifier is inevitably mixedVoltage, which occupies a large component in the frequency spectrum. For spectrum data xsPerforming a de-DC operation, denoted as
In the convolutional neural network, data needs to be subjected to normalization processing, so that the data distribution of an input layer is approximately the same, the problem of numerical value explosion caused by initialization, unstable training and the like can be avoided, and the convergence rate of the model is increased. The normalization process is represented as:wherein, x [ n ]]scaleFor the normalized data vector, x [ n ]]minIs the minimum value of the sample data vector, x [ n ]]maxIs the maximum value of the sample data vector.
After three high-speed digital-analog mixed circuit boards of the test circuit 1, the test circuit 2 and the test circuit 3 are hung on the transformation circuit shown in fig. 1, by switching on and off the circuit boards, EMI signals mixed by different circuits can be obtained. The circuit arrangement is shown in fig. 5, and the circuit states are classified into 8 types in total. The circuit EMI signal data acquisition flow chart is shown in FIG. 4. 400 groups of data are collected for each type of circuit state, 3200 groups of power supply EMI signal sample data are collected in total, and each group of data contains 4096 frequency point measurement values. 70% of the total number of power EMI samples were used as the training set and the remaining 30% as the test set. And identifying and verifying the test set by using the power state monitoring and identifying model, and judging the working state type of the circuit board.
The method is characterized in that a prestrained convolutional neural network model is subjected to model compression and operation acceleration processing by adopting Tensorflow full-integer quantization, an STM32Cube-AI library is converted into an optimized code of an STM32 MCU, only about dozens of kB exist, and then the optimized code can be deployed on STM32, so that online monitoring can be carried out, as shown in FIG. 6.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (5)
1. An on-line monitoring method for the working state of a circuit of a logging-while-drilling instrument is characterized by comprising the following steps:
s1, an EMI signal acquisition and data processing circuit based on FPGA and STM32 is deployed on an underground vortex power generation source trunk line to acquire EMI signal data and process the EMI signal data in real time;
s2, carrying out denoising and feature enhancement operation on the acquired EMI signal by using a digital signal processing method and a feature extraction algorithm such as a Kalman filtering algorithm and fast Fourier transform;
s3, converting the frequency spectrum component into a dimensionless expression by using direct current removal and normalization processing;
and S4, collecting data by using power EMI signals of different circuit board types to form a training data set and a testing data set, and labeling the data according to whether the circuit board is on line or not. Training a training data set as the input of a lightweight convolutional neural network model to obtain a power supply identification model; the neural network model is compressed and can be loaded into RAM and FLASH inside an STM32 chip.
S5, deploying the lightweight deep learning model by using an embedded processor, for example, deploying a trained lightweight convolutional neural network classification model on an STM32 embedded platform by using STM32Cube.AI;
s6, inputting actual data into a power classification model to identify the state of the circuit board, wherein the output of the model is whether each circuit board is on-line or not; and the classification result is uploaded to a central control system through a 485 bus, the central control system sends the classification result to a ground system by using slurry pulse, and an alarm is given when an offline condition occurs to the underground circuit board.
2. The method for on-line monitoring of the operational status of the LWD instrument as recited in claim 1, wherein said signal acquisition and data processing circuit of step S1 includes two parts, namely signal acquisition and signal processing, the signal acquisition part is used for filtering and analog-to-digital conversion processing of the EMI signal, and the signal processing part includes a timing control module and an operation processing module, and is used for performing data preprocessing and classification on the EMI signal.
3. The method for online monitoring of the circuit operating state of the logging-while-drilling instrument according to claim 1, wherein the step S2 specifically includes, for example, kalman filtering and fast fourier transform methods:
5. The method for on-line monitoring of the circuit working state of the logging-while-drilling instrument as recited in claim 1, wherein the step S5 is specifically to perform model compression and operation acceleration processing on a pre-trained convolutional neural network model by using tenserflow full-integer quantization, and convert the model into an optimized code of STM32 MCU.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110773330.4A CN113719269A (en) | 2021-07-08 | 2021-07-08 | On-line monitoring method for circuit working state of logging-while-drilling instrument |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110773330.4A CN113719269A (en) | 2021-07-08 | 2021-07-08 | On-line monitoring method for circuit working state of logging-while-drilling instrument |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113719269A true CN113719269A (en) | 2021-11-30 |
Family
ID=78673099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110773330.4A Pending CN113719269A (en) | 2021-07-08 | 2021-07-08 | On-line monitoring method for circuit working state of logging-while-drilling instrument |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113719269A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115749734A (en) * | 2022-12-08 | 2023-03-07 | 电子科技大学 | Method for learning geological structure on line by ultrasonic imaging logging instrument while drilling |
CN117054229A (en) * | 2023-10-12 | 2023-11-14 | 中海油田服务股份有限公司 | Fixing device and method for testing reliability of circuit board of logging while drilling instrument |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101971453A (en) * | 2007-05-08 | 2011-02-09 | 莫琼移动股份有限公司 | System and method for inductive charging of portable devices |
CN102749572A (en) * | 2012-06-26 | 2012-10-24 | 南京航空航天大学 | IECMAC parameter identification-based power electronic circuit failure predicting method |
CN204630594U (en) * | 2015-05-11 | 2015-09-09 | 华中科技大学 | A kind of data-adjustable harvester |
CN205422701U (en) * | 2016-03-16 | 2016-08-03 | 北京波特光盛石油技术有限公司 | Multifrequency is along with boring electromagnetic wave resistivity logging appearance circuit system |
US20160245075A1 (en) * | 2013-10-31 | 2016-08-25 | Halliburton Energy Services, Inc. | Cross talk noise reduction technique for downhole instrumentation |
CN106385196A (en) * | 2016-09-27 | 2017-02-08 | 华中科技大学 | Current ripple real-time prediction model-based three-level voltage source variable switching frequency control method |
CN110325929A (en) * | 2016-12-07 | 2019-10-11 | 阿瑞路资讯安全科技股份有限公司 | System and method for detecting the waveform analysis of cable network variation |
-
2021
- 2021-07-08 CN CN202110773330.4A patent/CN113719269A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101971453A (en) * | 2007-05-08 | 2011-02-09 | 莫琼移动股份有限公司 | System and method for inductive charging of portable devices |
CN102749572A (en) * | 2012-06-26 | 2012-10-24 | 南京航空航天大学 | IECMAC parameter identification-based power electronic circuit failure predicting method |
US20160245075A1 (en) * | 2013-10-31 | 2016-08-25 | Halliburton Energy Services, Inc. | Cross talk noise reduction technique for downhole instrumentation |
CN204630594U (en) * | 2015-05-11 | 2015-09-09 | 华中科技大学 | A kind of data-adjustable harvester |
CN205422701U (en) * | 2016-03-16 | 2016-08-03 | 北京波特光盛石油技术有限公司 | Multifrequency is along with boring electromagnetic wave resistivity logging appearance circuit system |
CN106385196A (en) * | 2016-09-27 | 2017-02-08 | 华中科技大学 | Current ripple real-time prediction model-based three-level voltage source variable switching frequency control method |
CN110325929A (en) * | 2016-12-07 | 2019-10-11 | 阿瑞路资讯安全科技股份有限公司 | System and method for detecting the waveform analysis of cable network variation |
Non-Patent Citations (1)
Title |
---|
孔力等: "交直流混合配电系统形态、控制与稳定性研究", 《电工电能新技术》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115749734A (en) * | 2022-12-08 | 2023-03-07 | 电子科技大学 | Method for learning geological structure on line by ultrasonic imaging logging instrument while drilling |
CN115749734B (en) * | 2022-12-08 | 2023-08-08 | 电子科技大学 | Method for learning geological structure on line by ultrasonic imaging logging while drilling instrument |
CN117054229A (en) * | 2023-10-12 | 2023-11-14 | 中海油田服务股份有限公司 | Fixing device and method for testing reliability of circuit board of logging while drilling instrument |
CN117054229B (en) * | 2023-10-12 | 2023-12-19 | 中海油田服务股份有限公司 | Fixing device and method for testing reliability of circuit board of logging while drilling instrument |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yang et al. | The intelligent fault diagnosis of wind turbine gearbox based on artificial neural network | |
Xiang et al. | Fault diagnosis of rolling bearing under fluctuating speed and variable load based on TCO spectrum and stacking auto-encoder | |
CN113719269A (en) | On-line monitoring method for circuit working state of logging-while-drilling instrument | |
CN110501631B (en) | Online intermittent fault detection and diagnosis method | |
CN108982107B (en) | It is a kind of based on morphology and it is multiple dimensioned arrangement entropy mean value bearing fault quantify trend diagnosis method | |
CN112182490B (en) | Reactor state diagnosis method and system | |
CN112098088B (en) | Rolling bearing fault diagnosis method based on KICA-fractal theory | |
CN110991295A (en) | Self-adaptive fault diagnosis method based on one-dimensional convolutional neural network | |
CN112069962B (en) | Method for identifying vibration spectrum under strong noise background based on image | |
CN111077386A (en) | Early fault signal noise reduction method for electrical equipment | |
CN110632484A (en) | ELM-based GIS partial discharge defect diagnosis and classification system and method | |
CN113567162A (en) | Fan fault intelligent diagnosis device and method based on acoustic sensor | |
CN109630449B (en) | Three-proofing ventilation equipment fault prediction system based on RBF algorithm | |
CN110701087A (en) | Axial flow compressor pneumatic instability detection method based on single-classification overrun learning machine | |
CN112945546A (en) | Accurate diagnosis method for complex fault of gear box | |
CN117056849A (en) | Unsupervised method and system for monitoring abnormal state of complex mechanical equipment | |
CN111881594A (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
Zhao et al. | Research on constructing a degradation index and predicting the remaining useful life for rolling element bearings of complex equipment | |
Chen et al. | Gearbox fault diagnosis based on VMD and acoustic emission technology | |
CN117009870A (en) | Pump cavitation state identification method for frequency domain improved SDP diagram | |
CN114200232B (en) | Method and system for detecting fault traveling wave head of power transmission line | |
CN115753107A (en) | Weak rolling bearing fault diagnosis method based on nonlinear quantum information entropy | |
CN113686577B (en) | Bearing fault diagnosis method based on rapid nonlinear sparse spectrum | |
CN112858977B (en) | Hall current sensor chip fault detection circuit and detection method | |
CN114398922A (en) | CNN-BilSTM-based fault diagnosis method for looseness of high-voltage shunt reactor winding |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211130 |
|
WD01 | Invention patent application deemed withdrawn after publication |