CN113297792A - Centrifugal pump energy efficiency evaluation method based on vibration data - Google Patents
Centrifugal pump energy efficiency evaluation method based on vibration data Download PDFInfo
- Publication number
- CN113297792A CN113297792A CN202110575005.7A CN202110575005A CN113297792A CN 113297792 A CN113297792 A CN 113297792A CN 202110575005 A CN202110575005 A CN 202110575005A CN 113297792 A CN113297792 A CN 113297792A
- Authority
- CN
- China
- Prior art keywords
- centrifugal pump
- energy efficiency
- vibration data
- matrix
- method based
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000013210 evaluation model Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 48
- 230000008569 process Effects 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000001595 flow curve Methods 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 2
- 238000012854 evaluation process Methods 0.000 abstract description 2
- 230000009545 invasion Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000003973 irrigation 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
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
The invention discloses a centrifugal pump energy efficiency evaluation method based on vibration data, which comprises the following steps: (1) collecting vibration data of the centrifugal pump under different working conditions by using a vibration sensor; (2) dividing an energy efficiency area of the centrifugal pump and classifying the collected vibration data by category according to a performance curve of the centrifugal pump; (3) extracting the characteristics of the collected vibration data based on a PCA method; (4) training an RNN (neural network) by taking the extracted characteristic data as input to obtain a centrifugal pump energy efficiency evaluation model; (5) and (4) using a centrifugal pump energy efficiency evaluation model to evaluate the energy efficiency of the centrifugal pump. The invention adopts a non-invasive measuring means, does not generate invasion influence on the equipment, and has the advantages of rapidness, convenience and the like; meanwhile, the collected data are subjected to feature extraction, the calculated amount of the model training and evaluation process is greatly reduced, whether the centrifugal pump runs in a deviated working condition or not can be efficiently and accurately evaluated, and the method has an important effect on judging whether the centrifugal pump needs to implement energy-saving reconstruction or not.
Description
Technical Field
The invention belongs to the field of centrifugal pump energy efficiency assessment, and particularly relates to a centrifugal pump energy efficiency assessment method based on vibration data.
Background
The centrifugal pump is used as a typical fluid conveying and energy conversion device and is widely applied to the fields of electric power, chemical industry, agricultural irrigation and the like. The global water pump power consumption accounts for about 25% of the total consumption of industrial equipment, and the centrifugal pump power demand in China is as high as 80% of the water pump power consumption. Therefore, it is imperative to improve the operating efficiency of centrifugal pumps and reduce energy consumption. To carry out energy-saving transformation work, firstly, whether the water pump operates in a high-efficiency area or not needs to be accurately evaluated. At present, there are two mature methods for testing pump efficiency: hydraulics and thermodynamics.
For example, chinese patent publication No. CN109322819A discloses an on-line energy efficiency testing and energy consumption analyzing system and method for pump systems, which analyze the energy efficiency of a pump by measuring performance parameters such as pressure and flow rate by using a hydraulic method. The publication number CN110425154A discloses a method and a device for online energy efficiency and state monitoring and fault prediction of a water pump, which integrate two methods of hydraulics and thermodynamics to monitor the energy efficiency of the water pump.
Although the hydraulics and thermodynamics methods can achieve quantitative measurement, the process is complex, and the two methods are invasive, and a non-invasive qualitative assessment method for the energy efficiency of the centrifugal pump is lacked in an industrial field.
Disclosure of Invention
The invention provides a centrifugal pump energy efficiency evaluation method based on vibration data, which is characterized in that non-invasive measurement means are used for obtaining the vibration data in the operation of a centrifugal pump, the characteristics of the vibration data are further extracted, and finally the classification and evaluation of the energy efficiency are completed by combining an RNN method.
A centrifugal pump energy efficiency evaluation method based on vibration data comprises the following steps:
(1) collecting vibration data of the centrifugal pump under different working conditions by using a vibration sensor;
(2) dividing an energy efficiency area of the centrifugal pump by combining a performance curve of the centrifugal pump, and classifying the vibration data acquired in the step (1);
(3) extracting the characteristics of the collected vibration data based on a PCA method;
(4) training an RNN (neural network) by taking the extracted characteristic data as input to obtain a centrifugal pump energy efficiency evaluation model;
(5) and (4) using a centrifugal pump energy efficiency evaluation model to evaluate the energy efficiency of the centrifugal pump.
In the step (1), when vibration data are collected, the centrifugal pump is provided with collecting measuring points in the axial direction and the radial direction.
In the step (2), the specific process of dividing the energy efficiency area of the centrifugal pump is as follows:
and dividing a load low-efficiency area, a high-efficiency area and an overload low-efficiency area in sequence by taking the downward floating of the efficiency of the highest efficiency point as a limit in an efficiency-flow curve of the centrifugal pump.
The specific process of the step (3) is as follows:
(3-1) arranging the acquired N-channel vibration data into an N-row matrix form X to obtain a data matrix, and solving a covariance matrix U of the X; namely:
and N is the number of channels for sampling the vibration data, and N is the number of sampling points of the single-channel vibration data.
Wherein x isi＝[xi1,xi2,…,xin]I is 1,2, …, N. Cov is an operator to find covariance, defined as follows:
(3-2) solving an eigenvalue matrix W and an eigenvector matrix V from the covariance matrix U, and obtaining a new eigenvalue matrix W 'and a correspondingly sorted eigenvector matrix V' according to a principle that eigenvalues are sorted from large to small, namely:
wherein λ isiI is 1,2, …, and N is the corresponding characteristic value.
Wherein v isi＝[vi1 vi2 … viN]And i is 1,2, …, and N is a feature value corresponding to the feature vector.
The ordered eigenvalue matrix and eigenvector matrix are as follows:
wherein λ ismax、λminMaximum and minimum eigenvalues. The feature vector matrix V' after corresponding sorting is as follows:
wherein v ismax、vminThe feature vectors corresponding to the maximum and minimum feature values are respectively.
(3-3) retaining only those of W' that are greater than
Wherein M is the sum of the values of the eigenvalues, to form a new eigenvalue matrix WkSimilarly, only the first k corresponding eigenvectors are retained to form a new eigenvector matrix VkNamely:
wherein λ iskIs the k-th characteristic value after sorting.
Wherein, VkIs equal to WkThe corresponding feature vector.
(3-4) Using the New eigenvector matrix VkMultiplying with X to obtain a new feature matrix X', namely:
in the step (4), the extracted feature data is a feature matrix X', the RNN has two hidden layers, the learning rate is 0.001 during training, the loss function is cross entropy loss, and three classified recurrent neural networks are finally obtained by adopting an Adam optimization method.
In the step (5), the specific process for evaluating the energy efficiency of the centrifugal pump comprises the following steps:
using the trained three-classification cyclic neural network to obtain vibration data X of the centrifugal pump under the condition to be evaluated0And as an input, calculating the energy efficiency classification condition output by the model to obtain the final energy efficiency evaluation result of the centrifugal pump under the condition to be evaluated.
Compared with the prior art, the invention has the following beneficial effects:
the method uses the vibration sensor to acquire vibration data in the operation of the centrifugal pump, performs characteristic extraction based on the vibration data, and further completes energy efficiency evaluation of the centrifugal pump based on the recurrent neural network. Compared with the traditional hydraulics and thermodynamics method in centrifugal pump energy efficiency evaluation, the method adopts a non-invasive measuring means, is faster and more convenient, does not have invasive influence on equipment, and simultaneously, combines features through a feature extraction means, thereby greatly reducing the calculated amount of the model training and evaluation process. Finally, the effects of quickly, efficiently and accurately evaluating the energy efficiency of the centrifugal pump are achieved.
Drawings
FIG. 1 is a flow chart of a method for evaluating the energy efficiency of a centrifugal pump based on vibration data according to the present invention;
FIG. 2 is a time domain plot of the 5 th channel data of the vibration sensor in an embodiment of the present invention;
FIG. 3 is a result graph of energy efficiency area division according to a centrifugal pump performance curve in the embodiment of the invention;
FIG. 4 is a diagram illustrating the sorting and selecting of eigenvalues in an embodiment of the present invention;
FIG. 5 is a time domain diagram of data of the 5 th channel after feature extraction in an embodiment of the present invention;
FIG. 6 is a diagram of an RNN network according to an embodiment of the present invention;
FIG. 7 is a graph illustrating average accuracy variation of a model training process according to an embodiment of the present invention.
Detailed Description
The invention will be described in further detail below with reference to the drawings and examples, which are intended to facilitate the understanding of the invention without limiting it in any way.
As shown in fig. 1, a method for evaluating energy efficiency of a centrifugal pump based on vibration data includes:
and S01, acquiring vibration data of the centrifugal pump under different working conditions by using a vibration sensor, wherein the number of measuring points of the vibration sensor can be determined according to the situation, but the axial and radial measuring points of the centrifugal pump must be ensured. In this embodiment, in the test process, the vibration data of the centrifugal pump under different working conditions are acquired by using 9 measuring points, and finally, the vibration data with the channel number N being 9 is obtained. FIG. 2 is a time domain diagram of vibration raw data of a test group 5 th channel under a certain working condition.
And S02, dividing an energy efficiency area by combining a performance curve of the centrifugal pump, and marking the working condition of the vibration data of each working condition. As shown in fig. 3, the load low-efficiency area, the high-efficiency area and the overload low-efficiency area are divided by taking the maximum efficiency point efficiency floating downward by 5%, and it can be seen from the figure that 5 of the 14 sets of vibration data are low-efficiency load working conditions, 7 are high-efficiency working conditions, and 2 are overload low-efficiency working conditions.
And S03, performing feature extraction on the vibration data based on the PCA method. Firstly, a covariance matrix of the vibration data of 9 channels is obtained, as shown in formula (2), a matrix with the dimensionality of 9 times 9 is obtained, and then a characteristic value matrix of the covariance matrix is obtained, as shown in formula (3), and a diagonal matrix is obtained. Then sorting the eigenvalues according to the numerical value, as shown in fig. 4, calculating according to the sorting result to obtain
Therefore, K is 5, i.e. only the first five eigenvalues and their corresponding eigenvectors V are retainedk. End use VkAnd X to obtain a feature matrix X'. FIG. 5 is a time domain diagram of data of the 5 th channel after feature extraction.
S04, using an RNN network with two hidden layers, setting the learning rate to be 0.001, selecting cross entropy loss as a loss function, adopting an Adam optimization method, and taking a feature matrix X' as an input training model, wherein FIG. 6 is a schematic diagram of the RNN network.
The RNN network consists of an input layer, a hidden layer, and an output layer, with outputs at each time step, and with cyclic connections between hidden units. RNN maps the input sequence of x values to the corresponding sequence of output values o, defining the loss L as the distance between each o and the corresponding training label y, since o is an unnormalized log probability, and output by using a softmax function, the loss L is internally calculated
And compared to tag y. The total loss of y paired with the x sequence is the sum of the losses at all time steps. For example,
is given as x1,x2,…,xtRear ytNegative log-likelihood of (d), then:
wherein p ismodel(yt|{x1,x2,…,xt}) need to read the model output vector
In (1) corresponds to ytThe item (1).
RNN input layer to hidden layer are connected by weight matrix U, hide between the unit by weight matrix W circulation connection, hide layer to output layer by weight matrix V connection. Equations (12) - (15) define the forward propagation of the RNN model:
at＝b+Wst-1+Uxt (12)
st＝tanh(at) (13)
ot＝c+Vst (14)
and b and c are offset vectors, tanh and softmax functions are activation functions, and the introduction of the activation functions increases the nonlinearity of the neural network model.
Fig. 7 shows the average accuracy in the training process, and it can be seen that the accuracy of the model has reached 99.2% after 15 rounds of training.
And S05, using the trained model and taking the vibration data of the centrifugal pump to be evaluated as input, so as to evaluate the energy efficiency.
Table 1 below shows the evaluation results of 90 sets of data, and it can be found that the average accuracy reaches 96.7%. Therefore, the centrifugal pump energy efficiency evaluation method based on the vibration data disclosed by the invention realizes non-invasive efficient and accurate centrifugal pump energy efficiency evaluation.
TABLE 1
| Data label | Load inefficient regime | High efficiency regime | Overload inefficient regime |
| Number to be evaluated | 30 | 30 | 30 |
| The correct amount | 29 | 30 | 28 |
The embodiments described above are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only specific embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions and equivalents made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A centrifugal pump energy efficiency evaluation method based on vibration data is characterized by comprising the following steps:
(1) collecting vibration data of the centrifugal pump under different working conditions by using a vibration sensor;
(2) dividing an energy efficiency area of the centrifugal pump by combining a performance curve of the centrifugal pump, and classifying the vibration data acquired in the step (1);
(3) extracting the characteristics of the collected vibration data based on a PCA method;
(4) training an RNN (neural network) by taking the extracted characteristic data as input to obtain a centrifugal pump energy efficiency evaluation model;
(5) and (4) using a centrifugal pump energy efficiency evaluation model to evaluate the energy efficiency of the centrifugal pump.
2. The centrifugal pump energy efficiency evaluation method based on vibration data as claimed in claim 1, wherein in the step (1), when the vibration data is collected, the centrifugal pump has collection measuring points in both axial and radial directions.
3. The centrifugal pump energy efficiency evaluation method based on vibration data as claimed in claim 1, wherein in the step (2), the specific process of dividing the energy efficiency area of the centrifugal pump is as follows:
and dividing a load low-efficiency area, a high-efficiency area and an overload low-efficiency area in sequence by taking the downward floating of the efficiency of the highest efficiency point as a limit in an efficiency-flow curve of the centrifugal pump.
4. The centrifugal pump energy efficiency evaluation method based on vibration data as claimed in claim 1, wherein the specific process of step (3) is as follows:
(3-1) arranging the acquired N-channel vibration data into an N-row matrix form X to obtain a data matrix, and solving a covariance matrix U of the X;
(3-2) solving an eigenvalue matrix W and an eigenvector matrix V from the covariance matrix U, and obtaining a new eigenvalue matrix W 'and a correspondingly sequenced eigenvector matrix V' according to a principle that eigenvalues are sequenced from large to small;
(3-3) retaining only those of W' that are greater than
Wherein M is the sum of the values of the eigenvalues, to form a new eigenvalue matrix WkSimilarly, only the first k corresponding eigenvectors are retained to form a new eigenvector matrix Vk；
(3-4) Using the New eigenvector matrix VkMultiplying with X to obtain a new feature matrix X'.
5. The centrifugal pump energy efficiency evaluation method based on vibration data as set forth in claim 4, wherein in the step (3-1), the data matrix X is represented as:
wherein, N is the number of channels for sampling the vibration data, and N is the number of sampling points of the single-channel vibration data; the covariance matrix U is expressed as:
wherein x isi＝[xi1,xi2,…,xin]I 1,2, …, N, Cov is an operator to find the covariance.
6. The centrifugal pump energy efficiency evaluation method based on vibration data according to claim 5, wherein in step (3-2), the eigenvalue matrix W is represented as:
wherein λ isiI is 1,2, …, N is the corresponding eigenvalue; the eigenvector matrix V is represented as:
wherein v isi＝[vi1 vi2…viN]I is 1,2, …, N is a feature value corresponding to the feature vector; the sorted eigenvalue matrix W' is represented as:
wherein λ ismax、λminMaximum and minimum eigenvalues; the ordered eigenvector matrix V' is:
wherein v ismax、vminThe feature vectors corresponding to the maximum and minimum feature values are respectively.
7. The centrifugal pump energy efficiency assessment method based on vibration data according to claim 6, characterized in that in step (3-3), the new eigenvalue matrix WkExpressed as:
wherein λ iskThe k characteristic value after sorting; novel eigenvector matrix VkExpressed as:
wherein, VkIs equal to WkThe corresponding feature vector.
8. The centrifugal pump energy efficiency evaluation method based on vibration data according to claim 7, wherein in step (3-4), the new feature matrix X' is represented as:
9. the centrifugal pump energy efficiency evaluation method based on vibration data as claimed in claim 1, wherein in the step (4), the extracted feature data is a feature matrix X', the RNN has two hidden layers, the learning rate is 0.001 during training, the loss function is cross entropy loss, and three kinds of classified recurrent neural networks are finally obtained by adopting an Adam optimization method.
10. The centrifugal pump energy efficiency evaluation method based on vibration data as claimed in claim 9, wherein in the step (5), the specific process of performing centrifugal pump energy efficiency evaluation is as follows:
using the trained three-classification cyclic neural network to obtain vibration data X of the centrifugal pump under the condition to be evaluated0And as an input, calculating the energy efficiency classification condition output by the model to obtain the final energy efficiency evaluation result of the centrifugal pump under the condition to be evaluated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110575005.7A CN113297792A (en) | 2021-05-26 | 2021-05-26 | Centrifugal pump energy efficiency evaluation method based on vibration data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110575005.7A CN113297792A (en) | 2021-05-26 | 2021-05-26 | Centrifugal pump energy efficiency evaluation method based on vibration data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113297792A true CN113297792A (en) | 2021-08-24 |
Family
ID=77324993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110575005.7A Pending CN113297792A (en) | 2021-05-26 | 2021-05-26 | Centrifugal pump energy efficiency evaluation method based on vibration data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113297792A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150039250A1 (en) * | 2013-07-31 | 2015-02-05 | General Electric Company | Vibration condition monitoring system and methods |
| CN110044602A (en) * | 2019-03-15 | 2019-07-23 | 昆明理工大学 | A kind of high-pressure diaphragm pump one-way valve fault diagnostic method based on analysis of vibration signal |
| CN111120348A (en) * | 2019-12-25 | 2020-05-08 | 中国石化销售股份有限公司华南分公司 | Centrifugal pump fault early warning method based on support vector machine probability density estimation |
| CN111767521A (en) * | 2020-06-22 | 2020-10-13 | 中国石油化工股份有限公司 | Oil transfer pump rolling bearing state evaluation method based on convolutional neural network and long-short term memory network |
| CN112101142A (en) * | 2020-08-27 | 2020-12-18 | 深圳市行健自动化股份有限公司 | Slurry pump running state evaluation method, monitoring terminal and computer readable storage medium |
-
2021
- 2021-05-26 CN CN202110575005.7A patent/CN113297792A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150039250A1 (en) * | 2013-07-31 | 2015-02-05 | General Electric Company | Vibration condition monitoring system and methods |
| CN110044602A (en) * | 2019-03-15 | 2019-07-23 | 昆明理工大学 | A kind of high-pressure diaphragm pump one-way valve fault diagnostic method based on analysis of vibration signal |
| CN111120348A (en) * | 2019-12-25 | 2020-05-08 | 中国石化销售股份有限公司华南分公司 | Centrifugal pump fault early warning method based on support vector machine probability density estimation |
| CN111767521A (en) * | 2020-06-22 | 2020-10-13 | 中国石油化工股份有限公司 | Oil transfer pump rolling bearing state evaluation method based on convolutional neural network and long-short term memory network |
| CN112101142A (en) * | 2020-08-27 | 2020-12-18 | 深圳市行健自动化股份有限公司 | Slurry pump running state evaluation method, monitoring terminal and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600140B (en) | Gas pipeline fault prediction early warning system and method based on improved support vector machine | |
| CN112257530B (en) | Rolling bearing fault diagnosis method based on blind signal separation and support vector machine | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN113255848B (en) | Water turbine cavitation sound signal identification method based on big data learning | |
| CN113569742B (en) | Broadband electromagnetic interference source identification method based on convolutional neural network | |
| CN113607325B (en) | Intelligent monitoring method and system for looseness positioning of steel structure bolt group | |
| CN108090515B (en) | Data fusion-based environment grade evaluation method | |
| CN110647911A (en) | Bearing fault diagnosis method based on principal component analysis and deep belief network | |
| CN114755745A (en) | Hail weather identification and classification method based on multi-channel depth residual shrinkage network | |
| CN114429152A (en) | Rolling bearing fault diagnosis method based on dynamic index antagonism self-adaption | |
| CN112287980B (en) | Power battery screening method based on typical feature vector | |
| CN112504682A (en) | Chassis engine fault diagnosis method and system based on particle swarm optimization algorithm | |
| CN113887342A (en) | Equipment fault diagnosis method based on multi-source signals and deep learning | |
| CN113177577A (en) | Bearing fault diagnosis method based on improved convolutional neural network | |
| CN116204831A (en) | Road-to-ground analysis method based on neural network | |
| CN114974306A (en) | Transformer abnormal voiceprint detection and identification method and device based on deep learning | |
| CN114354184A (en) | Deep learning-based method and device for establishing health early warning model of main shaft of large-scale rotating equipment | |
| CN113297792A (en) | Centrifugal pump energy efficiency evaluation method based on vibration data | |
| CN106599391B (en) | Association vector machine soft measurement modeling method based on dynamic weighting of triangle angle values | |
| CN117272230A (en) | Non-invasive load monitoring method and system based on multi-task learning model | |
| CN110020680B (en) | PMU data classification method based on random matrix theory and fuzzy C-means clustering algorithm | |
| CN110930012A (en) | Energy consumption abnormity positioning method based on sensitivity analysis and improved negative selection method | |
| CN112257773B (en) | Mechanical equipment fault diagnosis method based on multiple measurement vectors of wireless sensor network | |
| CN115797804A (en) | Abnormity detection method based on unbalanced time sequence aviation flight data | |
| Bishwas et al. | Relative comparison of k-means clustering segmented rice leaves image based nitrogen, phosphorus, and potassium nutrient deficiency classification using convolutional 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: 20210824 |
|
| RJ01 | Rejection of invention patent application after publication |