CN113076694A - Fan fault evaluation equipment based on Internet of things - Google Patents
Fan fault evaluation equipment based on Internet of things Download PDFInfo
- Publication number
- CN113076694A CN113076694A CN202110377986.4A CN202110377986A CN113076694A CN 113076694 A CN113076694 A CN 113076694A CN 202110377986 A CN202110377986 A CN 202110377986A CN 113076694 A CN113076694 A CN 113076694A
- Authority
- CN
- China
- Prior art keywords
- data
- fan
- fault
- evaluation
- information 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.)
- Granted
Links
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Abstract
The embodiment of the invention provides fan fault evaluation equipment based on the Internet of things. According to the method, firstly, collected state information data are preprocessed, a data set capable of being matched with a classifier is obtained, then fault classification is carried out on the data set through machine learning, the fault degree is evaluated through an established fan fault degree evaluation model after classification, and finally a fault degree value is calculated. The method is carried out based on the Internet of things, and from data acquisition and processing to fault evaluation and calculation, a large amount of manpower is saved, and meanwhile, the evaluation result is accurate. According to the technical scheme, the fan faults can be classified, and the fault degree can be quantitatively displayed, so that the fault assessment is more visual.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of fans, in particular to fan fault evaluation equipment based on the Internet of things.
[ background of the invention ]
In the process of acquiring the data of the wind turbine, due to the reasons of uneven sample sampling, complex data generation process and the like, the subsequent data mining processing process is difficult, the wind power operation mechanism of the wind turbine is complex, various variables may have many nonlinear correlations, the automatic fault evaluation is generally low in accuracy, and therefore maintenance personnel are generally required to go to the site to perform fault detection and evaluation.
[ summary of the invention ]
In view of this, the embodiment of the invention provides a fan fault evaluation method, system and device based on the internet of things.
In a first aspect, an embodiment of the present invention provides a fan fault evaluation method based on the internet of things, where the method includes:
s1, collecting state information data of the fan equipment in a specified time period, and preprocessing the state information data to obtain a data set capable of being matched with the classifier;
s2, obtaining the feature weight of each feature of the data set through the XGboost model, and selecting the feature meeting the preset feature weight condition;
s3, randomly dividing the data set with the selected features into K sub-data with the same size through K-fold cross validation, taking K-1 sub-data as a training set and 1 sub-data as a test set, and respectively inputting the sub-data into corresponding classifiers;
s4, based on TPE algorithm, predicting all classifiers in a weighted voting mode, wherein the voting weight of the classifier e
ξeE and f are the total number of the types of the classifiers, the TPE algorithm is operated for J times, and the number of the classifiers with the smallest verification error is selected as the optimal number of the classifiers through J times of cross validation;
s5, inputting the number of the optimal classifiers into a deep cascading forest model, and performing successive operation on the deep cascading forest model until preset precision is met to obtain a classification result of the fan fault;
s66, establishing a fan fault degree evaluation model, wherein the model comprises a numerical value group and a numerical value group weight vector, which correspond to power consumption loss, maintenance cost, parking cost and service life loss respectively;
and S7, calculating a gray weight evaluation matrix of each fault for each numerical value, multiplying the gray weight evaluation matrix by the corresponding numerical value weight vector to obtain a fault degree evaluation vector, and calculating a fault degree value through the fault degree evaluation vector.
As for the above-mentioned aspect and any possible implementation manner, further providing an implementation manner, S1 specifically includes:
s11, collecting state information data of the fan equipment in the appointed time period T;
s12, after the lengths of the sampling points of the state information data are unified to 13 dimensions, Min-Max standardization is carried out to be normalized to (0, 1), and the normalization conversion formula is as follows:
wherein x is original data, x is normalized data, max is the maximum value of each piece of data in the original sample, and min is the minimum value of each piece of data in the original sample;
s13, classifying the state information data according to the data type;
s14, performing a screening process for each category of status information data, the screening process including: sequentially selecting two adjacent data as one group according to the acquisition time and judging the size value of the two adjacent data in each round, randomly sampling 5-dimensional data in each group of data to compare the sizes, wherein the winner of the number of the dimensions is a large value, and the loser of the number of the dimensions is a small value; if the x group takes a larger value, the x +1 group takes a smaller value, the data which is not grouped directly takes a value corresponding to the data, and the process is a round of screening treatment; after y-round screening processing is carried out, screened data are obtained;
s15, passing formula uz＝{λ1+uz1(1-τ1),λ2+uz2(1-τ2),...,λd+uzd(1-τd) Amending each screened data, wherein uzFor the z-th data, λ, in the state information data type UdCorrection parameter for d-th dimension, uzdFor the component of the z-th data in the d-th dimension, τdIs uzdFrequency of occurrence in the status information data type U, U ═ U1,u1,...,uz,...,uZZ is the data quantity in the state information data type U;
and S16, processing the format of the corrected data into a format required by the classifier.
The above-described aspects and any possible implementations further provide an implementation in which the state information data includes blade state information data, motor state information data, temperature state information data, fan current information data, and fan voltage information data.
The above-described aspects and any possible implementations further provide an implementation, where the classifier includes: RF classifier, ET classifier, AdaBoost classifier, and GBDT classifier.
As for the above-mentioned aspect and any possible implementation manner, further providing an implementation manner, S7 specifically includes:
s71, establishing a sample matrix X, amnSet of values u for mth faultnThe numerical value of (1):
s72, setting k to 4 grey classes, the variable u representing 1, 10, 40, 100 in turn representing the value amnCorresponding fault degree is divided into 4 grades from light to heavy, and whitening weight functions f of k gray classes are determinedk(amn)；
S73, calculating the gray statistics S of k gray classes according to the sample matrix, the whitening weight function and the value groupmnAnd gray weight gmnEstablishing an evaluation weight matrix:
s74, multiplying the gray weight evaluation matrix with the corresponding numerical weight vector to obtain a fault degree evaluation vector, wherein E is (epsilon)1,ε1,...,εm) Psi is a numerical weight vector;
s75, calculating the fault degree value through the fault degree evaluation vector,
m is the number of fault types.
In a second aspect, an embodiment of the present invention provides a fan fault evaluation system based on the internet of things, where the system includes:
the preprocessing module is used for acquiring state information data of the fan equipment in a specified time period, and preprocessing the state information data to obtain a data set which can be matched with the classifier;
the acquisition module is used for acquiring the feature weight of each feature of the data set through the XGboost model and selecting the feature meeting the preset feature weight condition;
the distribution module is used for randomly dividing the data set with the selected characteristics into K sub-data with the same size through K-fold cross validation, taking K-1 sub-data as a training set and 1 sub-data as a test set, and respectively inputting the sub-data into corresponding classifiers;
a selection module used for predicting all classifiers in a weighted voting mode based on a TPE algorithm, wherein the voting weight of the classifier e
ξeE, operating a TPE algorithm for K times, and selecting the number of classifiers with the smallest verification error as the optimal number of classifiers by K times of cross validation;
the classification module is used for inputting the number of the optimal classifiers into the deep cascading forest model, and the deep cascading forest model is operated successively until the preset precision is met to obtain a classification result of the fan fault;
the system comprises an establishing module, a judging module and a judging module, wherein the establishing module is used for establishing a fan fault degree evaluation model, and the model comprises a numerical value group and a numerical value group weight vector which respectively correspond to power consumption loss, maintenance cost, parking cost and service life loss;
and the evaluation module is used for calculating a gray weight evaluation matrix of each fault for each numerical value, multiplying the gray weight evaluation matrix with the corresponding numerical value weight vector to obtain a fault degree evaluation vector, and calculating a fault degree value through the fault degree evaluation vector.
In a third aspect, the present invention provides a wind turbine fault evaluation device based on the internet of things, including:
the fan system is provided with a vibration sensor, a rotating speed sensor and a temperature sensor which are used for acquiring state data, and a buffer assembly is also arranged between the fan equipment and the base assembly;
the gateway system is used for receiving the state data acquired by the sensor, converting the state data into cellular data and transmitting the cellular data to the terminal system;
and the terminal system comprises a fan manufacturer terminal and a fan user terminal, a fan fault evaluation system based on the Internet of things is arranged in the terminal system, and the terminal system is used for receiving the honeycomb data of the gateway system and displaying the honeycomb data after fault evaluation.
The above aspects, and any possible implementations, further provide an implementation,
the fan system comprises a fan assembly, a buffer assembly and a base assembly; the fan assembly comprises a fan main body and a bottom plate, the fan main body is at least internally provided with a motor assembly, a blade assembly and a microprocessor, the root of a rotating shaft of the blade assembly is provided with a vibration sensor, a rotating speed sensor and a temperature sensor, an input shaft and an output shaft of the motor assembly are also provided with the vibration sensor, the rotating speed sensor and the temperature sensor, and the output end of the microprocessor is connected with a collecting sensor for collecting current and voltage data information;
the fan device is fixedly connected with the buffer assembly through the bottom plate; the buffer assembly comprises an upper seat, a lower seat, axial buffer parts and radial buffer parts, wherein a raised platform is arranged in the middle of the upper surface of the upper seat, a containing groove and two first mounting grooves are formed in the lower surface of the upper seat, a lug matched with the containing groove in a tenon-mortise manner is arranged on the upper surface of the lower seat, two second mounting grooves capable of forming two complete mounting grooves corresponding to the two first mounting grooves are formed in the lug, the two radial buffer parts are symmetrically arranged and are respectively arranged in the corresponding complete mounting grooves, the shapes of the radial buffer parts are matched with the shapes of the complete mounting grooves, the two axial buffer parts are respectively arranged on two sides of the lug, and vibration sensors are also arranged on two sides of the raised platform; the base assembly is fixedly connected with the buffering assembly, the base assembly is in a round table shape, a plurality of reinforcing ribs are arranged on the side face of the base assembly, and a guide pile is arranged on the upper surface of the base assembly in the middle.
In a fourth aspect, the invention provides a readable medium comprising executable instructions which, when executed by a processor of an electronic device, cause the electronic device to perform the method according to any one of the first aspect.
In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a bus;
the memory is used for storing execution instructions, the processor is connected with the memory through the bus, and when the electronic device runs, the processor executes the execution instructions stored in the memory to enable the processor to execute the method according to any one of the first aspect.
One of the above technical solutions has the following beneficial effects:
according to the method provided by the embodiment of the invention, firstly, collected state information data are preprocessed to obtain a data set which can be matched with a classifier, then the data set is classified through machine learning, the fault degree is evaluated through an established fan fault degree evaluation model after classification, and finally, a fault degree value is calculated. The method is carried out based on the Internet of things, and from data acquisition and processing to fault evaluation and calculation, a large amount of manpower is saved, and meanwhile, the evaluation result is accurate.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic flow chart of a fan fault evaluation method based on the internet of things according to an embodiment of the invention;
fig. 2 is a functional block of a fan fault evaluation system based on the internet of things according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a fan fault evaluation device based on the Internet of things;
FIG. 4 is a schematic structural diagram of a blower system according to the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail and completely with reference to the following embodiments and accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, which is a schematic flow chart of a fan fault evaluation method based on the internet of things according to an embodiment of the present invention, as shown in the figure, the method includes the following steps:
s1, collecting state information data of the fan equipment in a specified time period, and preprocessing the state information data to obtain a data set capable of being matched with the classifier;
s2, obtaining the feature weight of each feature of the data set through the XGboost model, and selecting the feature meeting the preset feature weight condition;
s3, randomly dividing the data set with the selected features into K sub-data with the same size through K-fold cross validation, taking K-1 sub-data as a training set and 1 sub-data as a test set, and respectively inputting the sub-data into corresponding classifiers;
s4, based on TPE algorithm, predicting all classifiers in a weighted voting mode, wherein the voting weight of the classifier e
ξeE and f are the total number of the types of the classifiers, the TPE algorithm is operated for J times, and the number of the classifiers with the smallest verification error is selected as the optimal number of the classifiers through J times of cross validation;
s5, inputting the number of the optimal classifiers into a deep cascading forest model, and performing successive operation on the deep cascading forest model until preset precision is met to obtain a classification result of the fan fault;
s7, establishing a fan fault degree evaluation model, wherein the model comprises a numerical value group and a numerical value group weight vector, which correspond to power consumption loss, maintenance cost, parking cost and service life loss respectively;
and S8, calculating a gray weight evaluation matrix of each fault for each numerical value, multiplying the gray weight evaluation matrix by the corresponding numerical value weight vector to obtain a fault degree evaluation vector, and calculating a fault degree value through the fault degree evaluation vector.
S1 specifically includes:
and S11, collecting the state information data of the fan equipment in the designated time period T.
S12, after the lengths of the sampling points of the state information data are unified to 13 dimensions, Min-Max standardization is carried out to be normalized to (0, 1), and the normalization conversion formula is as follows:
wherein x is the original data, x is the normalized data, max is the maximum value of each piece of data in the original sample, and min is the minimum value of each piece of data in the original sample.
Wherein, the purpose of unifying dimensionality is to ensure the format of data to be regular and reduce the processing amount, Min-Max standardization is also called dispersion standardization, and is linear transformation of original data, so that a result value is mapped between (Min, Max), and the (Min, Max) is obtained by mapping
And (6) performing conversion.
S13, classifying the state information data according to the data type.
It should be noted that the category of the status information data includes blade status information data, motor status information data, temperature status information data, fan current information data, and fan voltage information data. In addition, each category also comprises a plurality of sub-categories, for example, the blade state information data comprises fan outlet pressure, fan vibration, fan rotating speed, wind direction deviation, variable pitch angle and the like; the motor state information data comprises motor rotating speed and the like; the temperature state information data comprises motor coil temperature, motor bearing temperature, fan outlet air temperature, fan inlet air temperature, fan oil tank temperature and the like; the fan current information data comprise fan hard wiring current, variable pitch motor current, yaw motor current and the like; the fan voltage information data packet includes a fan starting voltage, a fan operating voltage and the like. The above is only a little explanation and explanation of the content of the status information data, and does not limit the protection scope of the present invention.
S14, performing a screening process for each category of status information data, the screening process including: sequentially selecting two adjacent data as one group according to the acquisition time and judging the size value of the two adjacent data in each round, randomly sampling 5-dimensional data in each group of data to compare the sizes, wherein the winner of the number of the dimensions is a large value, and the loser of the number of the dimensions is a small value; if the x group takes a larger value, the x +1 group takes a smaller value, the data which is not grouped directly takes a value corresponding to the data, and the process is a round of screening treatment; and after y-round screening treatment, screening data are obtained.
It should be noted that the data processing amount can be further reduced by S14, and the degree of reduction depends on the number of rounds of the screening process. The method comprises the following steps that an a group and a b group of data are assumed to sample 5 dimensions for comparison, if the larger dimension quantity of the a group of data exceeds the b group of data, the a group of data is a dimension quantity winner, namely a larger value, and the b group of data is a dimension quantity loser, namely a smaller value.
S15, passing formula uz＝{λ1+uz1(1-τ1),λ2+uz2(1-τ2),...,λd+uzd(1-τd) Amending each screened data, wherein uzFor the z-th data, λ, in the state information data type UdCorrection parameter for d-th dimension, uzdFor the component of the z-th data in the d-th dimension, τdIs uzdFrequency of occurrence in the status information data type U, U ═ U1,u1,...,uz,...,uZAnd Z is the data quantity in the state information data type U.
And S16, processing the format of the corrected data into a format required by the classifier.
Specifically, the modified state information data is preprocessed as required by the classifier to obtain a data set without missing values and error values, and a correct format capable of being input into the classifier is generated, and the format is generally: d { (p)1,q1),(p2,q2),...,(pt,qt) In which p istIndicating the type of status information data items relating to time t, qtIndicating whether the fan has a certain fault at the moment t, q t1 represents that a certain fault occurs in the fan at the moment t, and qtAnd 0 represents that the fan has no fault at the moment t.
It should be noted that in S2, the feature weights of the features of the data set are obtained through the XGBoost model, and the features meeting the preset feature weight condition are selected. That is, the XGBoost model removes unimportant features, so that the data processing amount can be reduced. The XGboost is the efficient implementation of a GB algorithm, and a base learning device in the XGboost can be a decision tree classifier or a sex classifier.
It should be noted that the TPE (Tree-structured park Estimator) is mainly used for hyper-parameter optimization of the deep neural network, and during the optimization, each classifier i generates the class distribution piIs estimated. In the binary classification problem, piContaining two values, i.e. ci0And ci1Which represent probabilities of classes 0 and 1, respectively. Optimizing basic ensemble by minimizing the loss function given by the average output of all classifiersThe number of the learning devices. The number of classifiers e is ξeAnd xi iseE.n ═ {0,1,0, 3. }, when ξeWhen the value of (d) is 0, the classifier e is not selected. Determining the optimized number n of each classifier through a TPE (thermal plastic elastomer) optimization methodiAll classifiers in the classifier pool are predicted in a weighted voting mode, and the voting weight of the classifier e
ξeAnd e and f are the total number of the types of the classifiers, the TPE algorithm is operated for K times, the number of the classifiers with the minimum verification error is selected as the optimal number of the classifiers through K times of cross validation, and K can be 10.
Here we select four basic classifiers, respectively RF (Random Forest) classifier, ET (extreme Random Tree) classifier, AdaBoost classifier and GBDT (Gradient Boosting Tree) classifier, for example, a set of ξ classifierseEach of the two classifiers is a {0, 2,1,2}, and represents that 0 RF classifier (i.e., an unselected RF classifier), 2 ET classifiers, 1 AdaBoost classifier, and 2 GBDT classifiers are combined into an integrated model. The type and number of base classifiers used in each layer of the deep integration model, namely the structure of the initial layer and the intermediate hidden layer of the deep integration model.
In addition, the fan failure degree evaluation model in S6 includes a value group and a value group weight vector corresponding to the power consumption loss, the maintenance cost, the parking cost, and the life loss, and is calculated by the following formulas:
(1) power consumption loss is estimated as power consumption wattage multiplied by power cost per watt
(2) Maintenance cost is equal to maintenance cost of the fan plus maintenance cost of the line
(3) Parking cost is parking time multiplied by productivity loss per unit time and parking time multiplied by worker cost per unit time
(4) Life loss is defined as failure coefficient x failure time
Wherein, the weight of the severe influence of the power consumption loss, the maintenance cost, the parking cost and the life loss on the accident consequence is respectively as follows:ψ＝(ψ1,ψ2,ψ3,ψ4)。
s7 specifically includes:
s71, establishing a sample matrix X, amnSet of values u for mth faultnThe numerical values in (1).
S72, setting k to 4 grey classes, the variable u representing 1, 10, 40, 100 in turn representing the value amnCorresponding fault degree is divided into 4 grades from light to heavy, and whitening weight functions f of k gray classes are determinedk(amn)。
The invention sets k to 4 grey classes, because the loss is larger as the severity of the result is higher, and the increasing trend is exponential, 1, 10, 40 and 100 are expressed by variable u, the severity of the result corresponding to the index value is expressed from light to heavy 4, and k whitening weight functions f for evaluating the grey classes are determinedk(xij)，fk(xij) Is a weight belonging to the k-th class of evaluation criteria. Function parameters A, B, C, D are obtained empirically based on the gray scale and mathematical expressions corresponding to the typical whitening weight function, the medium measure whitening weight function, the lower limit measure whitening weight function, and the upper limit measure whitening weight function of table 1 below.
TABLE 1 four types of whitening weight function
S73, calculating the gray statistics S of k gray classes according to the sample matrix, the whitening weight function and the value groupmnAnd gray weight gmnEstablishing an evaluation weight matrix:
s74, evaluating the gray weight matrix and the corresponding numerical weightMultiplying the vectors to obtain a fault degree evaluation vector, wherein E is (epsilon)1,ε1,...,εm) Psi is a numerical weight vector;
s75, calculating the fault degree value through the fault degree evaluation vector,
m is the number of fault types.
According to the method provided by the embodiment of the invention, firstly, collected state information data are preprocessed to obtain a data set which can be matched with a classifier, then, fault classification is carried out on the data set through machine learning, the fault degree is evaluated through an established fan fault degree evaluation model after classification, and finally, a fault degree value is calculated. The method is carried out based on the Internet of things, and from data acquisition and processing to fault evaluation and calculation, a large amount of manpower is saved, and meanwhile, the evaluation result is accurate. According to the technical scheme, the fan faults can be classified, and the fault degree can be quantitatively displayed, so that the fault assessment is more visual.
The embodiment of the invention further provides an embodiment of a device for realizing the steps and the method in the embodiment of the method.
Please refer to fig. 2, which is a functional block diagram of a wind turbine fault evaluation system based on the internet of things according to an embodiment of the present invention, as shown in the figure, the system includes:
the preprocessing module 210 is configured to collect state information data of the fan device in a specified time period, and preprocess the state information data to obtain a data set that can be matched with the classifier;
the obtaining module 220 is configured to obtain feature weights of the features of the data set through the XGBoost model, and select features that meet a preset feature weight condition;
the distribution module 230 is configured to randomly divide the data set with the selected features into K pieces of sub data with the same size through K-fold cross validation, where K-1 pieces of sub data are used as a training set, and 1 piece of sub data is used as a test set, and the K pieces of sub data are input into corresponding classifiers respectively;
a selection module 240, configured to predict all classifiers in a weighted voting manner based on the TPE algorithm, where the voting weight of the classifier e
ξeE, operating a TPE algorithm for K times, and selecting the number of classifiers with the smallest verification error as the optimal number of classifiers by K times of cross validation;
the classification module 250 is used for inputting the number of the optimal classifiers into the deep cascading forest model, and the deep cascading forest model is operated successively until the preset precision is met to obtain the classification result of the fan fault;
the establishing module 260 is used for establishing a fan fault degree evaluation model, and the model comprises a numerical value group and a numerical value group weight vector, wherein the numerical value group and the numerical value group weight vector respectively correspond to power consumption loss, maintenance cost, parking cost and service life loss;
and the evaluation module 270 is configured to calculate a gray weight evaluation matrix for each numerical value for each fault, multiply the gray weight evaluation matrix by the corresponding numerical weight vector to obtain a fault degree evaluation vector, and calculate a fault degree value according to the fault degree evaluation vector.
The above-described aspect and any possible implementation further provide an implementation, where the preprocessing module is specifically configured to perform:
s11, collecting state information data of the fan equipment in the appointed time period T;
s12, after the lengths of the sampling points of the state information data are unified to 13 dimensions, Min-Max standardization is carried out to be normalized to (0, 1), and the normalization conversion formula is as follows:
wherein x is original data, x is normalized data, max is the maximum value of each piece of data in the original sample, and min is the minimum value of each piece of data in the original sample;
s13, classifying the state information data according to the data type;
s14, performing a screening process for each category of status information data, the screening process including: sequentially selecting two adjacent data as one group according to the acquisition time and judging the size value of the two adjacent data in each round, randomly sampling 5-dimensional data in each group of data to compare the sizes, wherein the winner of the number of the dimensions is a large value, and the loser of the number of the dimensions is a small value; if the x group takes a larger value, the x +1 group takes a smaller value, the data which is not grouped directly takes a value corresponding to the data, and the process is a round of screening treatment; after y-round screening processing is carried out, screened data are obtained;
s15, passing formula uz＝{λ1+uz1(1-τ1),λ2+uz2(1-τ2),...,λd+uzd(1-τd) Amending each screened data, wherein uzFor the z-th data, λ, in the state information data type UdCorrection parameter for d-th dimension, uzdFor the component of the z-th data in the d-th dimension, τdIs uzdFrequency of occurrence in the status information data type U, U ═ U1,u1,...,uz,...,uZZ is the data quantity in the state information data type U;
and S16, processing the format of the corrected data into a format required by the classifier.
The above aspects, and any possible implementations, further provide an implementation,
the state information data comprises blade state information data, motor state information data, temperature state information data, fan current information data and fan voltage information data.
The above-described aspects and any possible implementations further provide an implementation, where the classifier includes: RF classifier, ET classifier, AdaBoost classifier, and GBDT classifier.
The above-described aspects and any possible implementations further provide an implementation, where the evaluation module is specifically configured to perform:
s71, establishing a sample matrix X, amnSet of values u for mth faultnThe numerical value of (1):
s72, setting k to 4 grey classes, the variable u representing 1, 10, 40, 100 in turn representing the value amnCorresponding fault degree is divided into 4 grades from light to heavy, and whitening weight functions f of k gray classes are determinedk(amn)；
S73, calculating the gray statistics S of k gray classes according to the sample matrix, the whitening weight function and the value groupmnAnd gray weight gmnEstablishing an evaluation weight matrix:
s74, multiplying the gray weight evaluation matrix with the corresponding numerical weight vector to obtain a fault degree evaluation vector, wherein E is (epsilon)1,ε1,...,εm) Psi is a numerical weight vector;
s75, calculating the fault degree value through the fault degree evaluation vector,
m is the number of fault types.
Since each unit module in the embodiment can execute the method shown in fig. 1, reference may be made to the related description of fig. 1 for a part of the embodiment that is not described in detail.
Fig. 3 is a schematic structural diagram of a fan fault evaluation device based on the internet of things, and as shown in fig. 3, the fan fault evaluation device includes:
the fan system 100 is provided with a vibration sensor, a rotating speed sensor and a temperature sensor which are used for acquiring state data, and a buffer assembly is also arranged between the fan equipment and the base assembly;
the gateway system 200 is used for receiving the state data acquired by the sensors, converting the state data into cellular data and transmitting the cellular data to the terminal system;
the terminal system 300 comprises a fan manufacturer terminal and a fan user terminal, wherein a fan fault evaluation system based on the internet of things is built in the terminal system, and the terminal system is used for receiving the honeycomb data of the gateway system and displaying the honeycomb data after fault evaluation.
Fig. 4 is a schematic structural diagram of a fan system provided by the present invention, and as shown in fig. 4, the fan system includes a fan assembly 1, a buffer assembly 2, and a base assembly 3.
Two fixing plates 121 are arranged on the bottom plate 12, the two fixing plates 121 are located on two opposite sides of the fan main body 11 and fixedly connected with the fan main body 11, and the fan assembly 1 is fixedly connected with the buffer assembly 2 through the bottom plate 12.
The damping assembly 2 comprises an upper seat 21, a lower seat 22, an axial damping member 24 and a radial damping member 23. The middle of the upper surface of the upper seat 21 is provided with a raised platform 211, and the lower surface of the upper seat 21 is provided with a receiving groove 212 and two first mounting grooves 213. The first mounting grooves 213 are formed at the top of the receiving groove 212, and the two first mounting grooves 213 are not communicated with each other. Vibration sensor 4 is still installed to the both sides of protruding platform 211, and vibration sensor 4's height is no longer than protruding platform 211's height, and the both sides of protruding platform 211 are equipped with the screw.
The upper surface of the lower seat 22 is provided with a convex block 221 matched with the accommodating groove 212 in a mortise-tenon manner, the convex block 21 is provided with two second installation grooves 222 which can form two complete installation grooves corresponding to the two first installation grooves 213, and the two second installation grooves 222 are not communicated with each other. The projection 221 is further provided with a guide hole matched with the guide pile, and screw holes are formed in two sides of the projection 221.
The radial buffer 23 includes a buffer spring 231, a spring seat 232, an anti-falling block 233 and a filling block 234, the buffer spring 231 is mounted on the spring seat 232, the anti-falling block 233 and the filling block 234 are of an integrated structure, the spring seat 232 and the filling block 233 are of a cubic structure, and the anti-falling block 234 is of a cylindrical structure. The two radial buffering parts 23 are arranged in the corresponding complete mounting grooves respectively, the two radial buffering parts 23 are symmetrically arranged, and the shapes of the radial buffering parts 23 are matched with the shapes of the complete mounting grooves.
The axial buffers 24 are two and respectively installed at both sides of the protrusion 221, and the axial buffers 24 are dampers or damping cylinders. The height of the axial buffer 24 does not exceed the height of the projection 221.
The screw holes of the bottom plate 12, the screw holes of the upper seat 21, the screw holes of the lower seat 22 and the screw holes of the base component 3 are in one-to-one correspondence in number and position, and the integral fixation of the equipment can be realized through screws or pins.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Referring to fig. 5, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 3, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
In a possible implementation manner, the processor reads a corresponding computer program from the nonvolatile memory to the memory and then runs the computer program, and may also obtain the corresponding computer program from other devices, so as to form the wind turbine fault detection system based on the internet of things on a logic level. And the processor executes the program stored in the memory so as to realize the fan fault evaluation method based on the Internet of things provided by any embodiment of the invention through the executed program.
Embodiments of the present invention also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method for evaluating a fault of a wind turbine based on the internet of things provided in any embodiment of the present invention.
The method executed by the wind turbine fault evaluation system based on the internet of things according to the embodiment of the invention shown in fig. 2 can be applied to a processor or implemented by the processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
Embodiments of the present invention also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method for evaluating a fault of a wind turbine based on the internet of things provided in any embodiment of the present invention.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units or modules by function, respectively. Of course, the functionality of the units or modules may be implemented in the same one or more software and/or hardware when implementing the invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (7)
1. The utility model provides a fan fault evaluation equipment based on thing networking which characterized in that includes:
the fan system is provided with a vibration sensor, a rotating speed sensor and a temperature sensor which are used for acquiring state data, and a buffer assembly is also arranged between the fan equipment and the base assembly;
the gateway system is used for receiving the state data acquired by the sensor, converting the state data into cellular data and transmitting the cellular data to the terminal system;
and the terminal system comprises a fan manufacturer terminal and a fan user terminal, a fan fault evaluation system based on the Internet of things is arranged in the terminal system, and the terminal system is used for receiving the honeycomb data of the gateway system and displaying the honeycomb data after fault evaluation.
2. The blower fault evaluation device based on the Internet of things of claim 1,
the fan system comprises a fan assembly, a buffer assembly and a base assembly; the fan assembly comprises a fan main body and a bottom plate, the fan main body is at least internally provided with a motor assembly, a blade assembly and a microprocessor, the root of a rotating shaft of the blade assembly is provided with a vibration sensor, a rotating speed sensor and a temperature sensor, an input shaft and an output shaft of the motor assembly are also provided with the vibration sensor, the rotating speed sensor and the temperature sensor, and the output end of the microprocessor is connected with a collecting sensor for collecting current and voltage data information;
the fan assembly is fixedly connected with the buffer assembly through the bottom plate; the buffer assembly comprises an upper seat, a lower seat, axial buffer parts and radial buffer parts, wherein a raised platform is arranged in the middle of the upper surface of the upper seat, a containing groove and two first mounting grooves are formed in the lower surface of the upper seat, a lug matched with the containing groove in a tenon-mortise manner is arranged on the upper surface of the lower seat, two second mounting grooves capable of forming two complete mounting grooves corresponding to the two first mounting grooves are formed in the lug, the two radial buffer parts are symmetrically arranged and are respectively arranged in the corresponding complete mounting grooves, the shapes of the radial buffer parts are matched with the shapes of the complete mounting grooves, the two axial buffer parts are respectively arranged on two sides of the lug, and vibration sensors are also arranged on two sides of the raised platform; the base assembly is fixedly connected with the buffering assembly, the base assembly is in a round table shape, a plurality of reinforcing ribs are arranged on the side face of the base assembly, and a guide pile is arranged on the upper surface of the base assembly in the middle.
3. The blower fault evaluation device based on the internet of things of claim 2, wherein the blower fault evaluation system based on the internet of things comprises:
the preprocessing module is used for acquiring state information data of the fan equipment in a specified time period, and preprocessing the state information data to obtain a data set which can be matched with the classifier;
the acquisition module is used for acquiring the feature weight of each feature of the data set through the XGboost model and selecting the feature meeting the preset feature weight condition;
the distribution module is used for randomly dividing the data set with the selected characteristics into K sub-data with the same size through K-fold cross validation, taking K-1 sub-data as a training set and 1 sub-data as a test set, and respectively inputting the sub-data into corresponding classifiers;
a selection module used for predicting all classifiers in a weighted voting mode based on a TPE algorithm, wherein the voting weight of the classifier e
ξeE and f are the total number of the types of the classifiers, the TPE algorithm is operated for J times, and the number of the classifiers with the smallest verification error is selected as the optimal number of the classifiers through J times of cross validation;
the classification module is used for inputting the number of the optimal classifiers into the deep cascading forest model, and the deep cascading forest model is operated successively until the preset precision is met to obtain a classification result of the fan fault;
the system comprises an establishing module, a judging module and a judging module, wherein the establishing module is used for establishing a fan fault degree evaluation model, and the model comprises a numerical value group and a numerical value group weight vector which respectively correspond to power consumption loss, maintenance cost, parking cost and service life loss;
and the evaluation module is used for calculating a gray weight evaluation matrix of each fault for each numerical value, multiplying the gray weight evaluation matrix with the corresponding numerical value weight vector to obtain a fault degree evaluation vector, and calculating a fault degree value through the fault degree evaluation vector.
4. The blower fault evaluation device based on the internet of things of claim 3, wherein the preprocessing module is specifically configured to perform the following steps:
s11, collecting state information data of the fan equipment in the appointed time period T;
s12, after the lengths of the sampling points of the state information data are unified to 13 dimensions, Min-Max standardization is carried out to be normalized to (0, 1), and the normalization conversion formula is as follows:
wherein x is original data, x is normalized data, max is the maximum value of each piece of data in the original sample, and min is the minimum value of each piece of data in the original sample;
s13, classifying the state information data according to the data type;
s14, performing a screening process for each category of status information data, the screening process including: sequentially selecting two adjacent data as one group according to the acquisition time and judging the size value of the two adjacent data in each round, randomly sampling 5-dimensional data in each group of data to compare the sizes, wherein the winner of the number of the dimensions is a large value, and the loser of the number of the dimensions is a small value; if the x group takes a larger value, the x +1 group takes a smaller value, the data which is not grouped directly takes a value corresponding to the data, and the process is a round of screening treatment; after y-round screening processing is carried out, screened data are obtained;
s15, passing formula uz＝{λ1+uz1(1-τ1),λ2+uz2(1-τ2),...,λd+uzd(1-τd) Amending each screened data, wherein uzFor the z-th data, λ, in the state information data type UdCorrection parameter for d-th dimension, uzdFor the component of the z-th data in the d-th dimension, τdIs uzdFrequency of occurrence in the status information data type U, U ═ U1,u1,...,uz,...,uZZ is the data quantity in the state information data type U;
and S16, processing the format of the corrected data into a format required by the classifier.
5. The Internet of things-based fan fault evaluation device of claim 4, wherein the status information data comprises blade status information data, motor status information data, temperature status information data, fan current information data, and fan voltage information data.
6. The blower fault evaluation device based on the internet of things of claim 5, wherein the classifier comprises: RF classifier, ET classifier, AdaBoost classifier, and GBDT classifier.
7. The blower fault evaluation device based on the internet of things of claim 6, wherein the evaluation module is specifically configured to execute the following steps:
s71, establishing a sample matrix X, amnSet of values u for mth faultnThe numerical value of (1):
s72, setting k to 4 grey classes, the variable u representing 1, 10, 40, 100 in turn representing the value amnCorresponding fault degree is divided into 4 grades from light to heavy, and whitening weight functions f of k gray classes are determinedk(amn)；
S73 whitening weight function according to sample matrixAnd a value group for calculating the gray statistics s of k gray classesmnAnd gray weight gmnEstablishing an evaluation weight matrix:
s74, multiplying the gray weight evaluation matrix with the corresponding numerical weight vector to obtain a fault degree evaluation vector, wherein E is (epsilon)1,ε1,...,εm) Psi is a numerical weight vector;
s75, calculating the fault degree value through the fault degree evaluation vector,
m is the number of fault types.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110377986.4A CN113076694B (en) | 2019-06-20 | 2019-06-20 | Fan fault evaluation equipment based on thing networking |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110377986.4A CN113076694B (en) | 2019-06-20 | 2019-06-20 | Fan fault evaluation equipment based on thing networking |
| CN201910538887.2A CN110263856B (en) | 2019-06-20 | 2019-06-20 | Blower fault evaluation method, system and equipment based on Internet of things |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910538887.2A Division CN110263856B (en) | 2019-06-20 | 2019-06-20 | Blower fault evaluation method, system and equipment based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113076694A true CN113076694A (en) | 2021-07-06 |
| CN113076694B CN113076694B (en) | 2023-10-20 |
Family
ID=67920058
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910538887.2A Active CN110263856B (en) | 2019-06-20 | 2019-06-20 | Blower fault evaluation method, system and equipment based on Internet of things |
| CN202110377986.4A Active CN113076694B (en) | 2019-06-20 | 2019-06-20 | Fan fault evaluation equipment based on thing networking |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910538887.2A Active CN110263856B (en) | 2019-06-20 | 2019-06-20 | Blower fault evaluation method, system and equipment based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110263856B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115559928A (en) * | 2022-11-18 | 2023-01-03 | 淄博博睿机电科技有限公司 | Direct current brushless fan controller fault monitoring system based on big data |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347617B (en) * | 2020-10-20 | 2024-05-03 | 北京空间飞行器总体设计部 | Multi-factor-based fault troubleshooting strategy evaluation method and device |
| CN113111568B (en) * | 2021-03-05 | 2023-05-30 | 苏州热工研究院有限公司 | Nickel-based alloy stress corrosion crack growth rate prediction method |
| CN113888526B (en) * | 2021-10-21 | 2022-09-23 | 北京实力伟业环保科技有限公司 | Waste gas treatment method and system based on microorganisms |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205569A (en) * | 2015-10-15 | 2015-12-30 | 华侨大学 | Draught fan gear box state on-line evaluation model building method and on-line evaluation method |
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
| CN107992880A (en) * | 2017-11-13 | 2018-05-04 | 山东斯博科特电气技术有限公司 | A kind of optimal lump classification method for diagnosing faults of power transformer |
| US20180322958A1 (en) * | 2017-05-04 | 2018-11-08 | Efthymios Kalafatis | Machine learning, natural language processing and network analysis-guided discovery related to medical research |
| CN109459235A (en) * | 2018-12-13 | 2019-03-12 | 中国航空工业集团公司上海航空测控技术研究所 | Based on the enhanced gear single fault classification diagnostic method of integrated study |
| CN109492790A (en) * | 2018-09-18 | 2019-03-19 | 北京光耀电力科技股份有限公司 | Wind turbines health control method based on neural network and data mining |
| CN109543210A (en) * | 2018-09-28 | 2019-03-29 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
| CN109826818A (en) * | 2019-02-26 | 2019-05-31 | 北京工业大学 | A kind of method for diagnosing faults of mine ventilator |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484678B (en) * | 2015-01-07 | 2017-06-16 | 青岛理工大学 | Multiple Classifiers Combination method for diagnosing faults based on fault type differential ability rating matrix |
| CN105184316B (en) * | 2015-08-28 | 2019-05-14 | 国网智能电网研究院 | A kind of support vector machines electrical network business classification method based on feature power study |
| CN107449603A (en) * | 2016-05-31 | 2017-12-08 | 华北电力大学（保定） | Fault Diagnosis of Fan method based on SVMs |
| CN106779087B (en) * | 2016-11-30 | 2019-02-22 | 福建亿榕信息技术有限公司 | A kind of general-purpose machinery learning data analysis platform |
| CN107220469B (en) * | 2017-07-14 | 2020-10-30 | 华北电力大学（保定） | Method and system for estimating state of fan |
| CN108062571B (en) * | 2017-12-27 | 2021-04-27 | 福州大学 | Photovoltaic array fault diagnosis method based on differential evolution random forest classifier |
| CN108734192B (en) * | 2018-01-31 | 2021-10-15 | 国家电网公司 | Voting mechanism-based support vector machine mechanical fault diagnosis method |
| CN109026563B (en) * | 2018-07-24 | 2019-12-27 | 上海电力学院 | Fan blade icing prediction method based on feature selection and XGboost |
| CN109857861A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | File classification method, device, server and medium based on convolutional neural networks |
| CN109858564B (en) * | 2019-02-21 | 2023-05-05 | 上海电力学院 | Improved Adaboost-SVM model generation method suitable for wind power converter fault diagnosis |
-
2019
- 2019-06-20 CN CN201910538887.2A patent/CN110263856B/en active Active
- 2019-06-20 CN CN202110377986.4A patent/CN113076694B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205569A (en) * | 2015-10-15 | 2015-12-30 | 华侨大学 | Draught fan gear box state on-line evaluation model building method and on-line evaluation method |
| US20180322958A1 (en) * | 2017-05-04 | 2018-11-08 | Efthymios Kalafatis | Machine learning, natural language processing and network analysis-guided discovery related to medical research |
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
| CN107992880A (en) * | 2017-11-13 | 2018-05-04 | 山东斯博科特电气技术有限公司 | A kind of optimal lump classification method for diagnosing faults of power transformer |
| CN109492790A (en) * | 2018-09-18 | 2019-03-19 | 北京光耀电力科技股份有限公司 | Wind turbines health control method based on neural network and data mining |
| CN109543210A (en) * | 2018-09-28 | 2019-03-29 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
| CN109459235A (en) * | 2018-12-13 | 2019-03-12 | 中国航空工业集团公司上海航空测控技术研究所 | Based on the enhanced gear single fault classification diagnostic method of integrated study |
| CN109826818A (en) * | 2019-02-26 | 2019-05-31 | 北京工业大学 | A kind of method for diagnosing faults of mine ventilator |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115559928A (en) * | 2022-11-18 | 2023-01-03 | 淄博博睿机电科技有限公司 | Direct current brushless fan controller fault monitoring system based on big data |
| CN115559928B (en) * | 2022-11-18 | 2023-03-21 | 淄博博睿机电科技有限公司 | Direct current brushless fan controller fault monitoring system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110263856A (en) | 2019-09-20 |
| CN110263856B (en) | 2021-04-27 |
| CN113076694B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110263856B (en) | Blower fault evaluation method, system and equipment based on Internet of things | |
| US20180046902A1 (en) | Enhanced restricted boltzmann machine with prognosibility regularization for prognostics and health assessment | |
| CN108920863B (en) | Method for establishing energy consumption estimation model of robot servo system | |
| CN109993652A (en) | A kind of debt-credit assessing credit risks method and device | |
| JP2018092445A5 (en) | ||
| CN111523084A (en) | Service data prediction method and device, electronic equipment and computer readable storage medium | |
| Gong et al. | Bottom-up load forecasting with Markov-based error reduction method for aggregated domestic electric water heaters | |
| CN105956722A (en) | Short-term wind power prediction method and apparatus | |
| CN108320112B (en) | Method and device for determining health state of equipment | |
| CN113468157A (en) | Similar building selection method and device based on energy consumption analysis | |
| CN117076869A (en) | Time-frequency domain fusion fault diagnosis method and system for rotary machine | |
| CN117272145A (en) | Health state evaluation method and device of switch machine and electronic equipment | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN114637620B (en) | Database system abnormal classification prediction method based on SVM algorithm | |
| WO2022222230A1 (en) | Indicator prediction method and apparatus based on machine learning, and device and storage medium | |
| CN114065430A (en) | State data processing method and system for planetary gear box | |
| CN114595525A (en) | Rolling bearing degradation trend prediction method based on linear regression and TCN | |
| CN114970657A (en) | Abnormality degree calculation system and method | |
| CN113869601A (en) | Power consumer load prediction method, device and equipment | |
| CN113503232A (en) | Early warning method and system for running health state of fan | |
| CN111026661A (en) | Method and system for comprehensively testing usability of software | |
| CN117726240B (en) | Quality evaluation classification method and system based on convolutional neural network | |
| CN111160419B (en) | Deep learning-based electronic transformer data classification prediction method and device | |
| CN115658371B (en) | Diagnosis algorithm quantitative recommendation method based on case learning and diagnosability analysis | |
| CN116562990B (en) | Electricity selling transaction service recommendation method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |