CN105427016A - Locomotive vehicle data processing method and system - Google Patents
Locomotive vehicle data processing method and system Download PDFInfo
- Publication number
- CN105427016A CN105427016A CN201510711968.XA CN201510711968A CN105427016A CN 105427016 A CN105427016 A CN 105427016A CN 201510711968 A CN201510711968 A CN 201510711968A CN 105427016 A CN105427016 A CN 105427016A
- Authority
- CN
- China
- Prior art keywords
- locomotive vehicle
- mounted data
- locomotive
- data
- noise reduction
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Abstract
The invention provides a locomotive vehicle data processing method and a system. The method includes: pre-processing acquired locomotive vehicle data and obtaining the locomotive vehicle data after noise reduction; and performing information mining of the locomotive vehicle data after noise reduction, thereby analyzing locomotive energy consumption or locomotive faults. According to the processing method, the train energy consumption of a lot of complicated vehicle data can be analyzed, the locomotive vehicle data is effectively analyzed, valuable information is mined, and the performance of energy saving of trains is improved.
Description
Technical field
The present invention relates to locomotive vehicle-mounted data processing field, particularly relate to a kind of locomotive vehicle-mounted data processing method and system.
Background technology
Along with the development of infotech, each business data is collected and data storage technology fast development, have accumulated mass data.But, to go out from these extracting data numerous and diverse in a large number the challenge that useful information become huge.Usually because cause data inconsistent data from different classes, natural variation and DATA REASONING or collection error, it is necessary for therefore before carrying out data mining, carrying out pre-service to data.
For locomotive vehicle-mounted data, first due to the complicacy of locomotive operation environment, result in and there is certain error in the process of measuring and collecting locomotive vehicle-mounted data, as: the error in data that the process that shortage of data, Data duplication or even data pass ground back from locomotive causes, therefore, these outlier are filtered out most important to the raising quality of data.Secondly, along with a large amount of use of locomotive and the raising of locomotive speed, create a large amount of locomotive datas, people urgently wish to excavate valuable information from these mass datas, to improve energy saving and the security of locomotive.
Summary of the invention
In field of track traffic, owing to being difficult to effectively to analyze locomotive vehicle-mounted data and excavate valuable information, therefore the present invention proposes a kind of locomotive vehicle-mounted data processing method.
In order to solve the problems of the technologies described above, the embodiment of the application provide firstly a kind of locomotive vehicle-mounted data processing method, comprising: carry out pre-service to the locomotive vehicle-mounted data collected and obtain the locomotive vehicle-mounted data after noise reduction; Carry out information excavating in the locomotive vehicle-mounted data after described noise reduction, and then analyze locomotive energy consumption or locomotive failure.
Preferably, the locomotive vehicle-mounted data collected are carried out pre-service obtain noise reduction after locomotive vehicle-mounted data step in, the method based on the K average in the method for mahalanobis distance, least-squares estimation matching or cluster detects noisy locomotive vehicle-mounted data.
Preferably, detect in the method based on mahalanobis distance in the step of noisy locomotive vehicle-mounted data, comprise further: the average calculating described locomotive vehicle-mounted data, determine mean vector; Calculate the mahalanobis distance of each locomotive vehicle-mounted data to mean vector successively; Differentiate noisy locomotive vehicle-mounted data according to described mahalanobis distance, and removed the locomotive vehicle-mounted data after obtaining noise reduction.
Preferably, utilize Lay mattress to reach criterion, Grubbs inspection or the Dixon method of inspection carry out outlier differentiation to described mahalanobis distance and then determine noisy locomotive vehicle-mounted data.
Preferably, based on SVM algorithm, carry out information excavating by the distributed variable-frequencypump of large data platform in the locomotive vehicle-mounted data after described noise reduction.
According to a further aspect in the invention, additionally provide a kind of locomotive vehicle-mounted data handling system, comprising: pretreatment module, it carries out pre-service to the locomotive vehicle-mounted data collected and obtains the locomotive vehicle-mounted data after noise reduction; Data processing module, it carries out information excavating in the locomotive vehicle-mounted data after described noise reduction, and then analyzes locomotive energy consumption or locomotive failure.
Preferably, described pretreatment module detects noisy locomotive vehicle-mounted data based on the method for the K average in the method for mahalanobis distance, least-squares estimation matching or cluster.
Preferably, described pretreatment module is further used for: the average calculating described locomotive vehicle-mounted data, determines mean vector; Calculate the mahalanobis distance of each locomotive vehicle-mounted data to mean vector successively; Differentiate noisy locomotive vehicle-mounted data according to described mahalanobis distance, and removed the locomotive vehicle-mounted data after obtaining noise reduction.
Preferably, described pretreatment module utilize Lay mattress reach criterion, Grubbs inspection or the Dixon method of inspection outlier differentiation is carried out to described mahalanobis distance and then determines noisy locomotive vehicle-mounted data.
Preferably, described data processing module, based on SVM algorithm, carries out information excavating by the distributed variable-frequencypump of large data platform in the locomotive vehicle-mounted data after described noise reduction.
Compared with prior art, the one or more embodiments in such scheme can have the following advantages or beneficial effect by tool.
The embodiment of the present invention proposes a kind of locomotive vehicle-mounted data processing method, although locomotive vehicle-mounted data volume is large, this data processing method can be adopted to carry out distributed variable-frequencypump to improve efficiency of algorithm by large data platform on each node.This disposal route can carry out the analysis of train energy consumption to vehicle-mounted data numerous and diverse in a large number, improve the energy saving of train.In addition, the method can also be used for fault detect, predict the contingent fault of train in advance, improve the security of train.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing technical scheme of the present invention.Object of the present invention and other advantages realize by structure specifically noted in instructions, claims and accompanying drawing and/or flow process and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide the further understanding of technical scheme to the application or prior art, and forms a part for instructions.Wherein, the expression accompanying drawing of the embodiment of the present application and the embodiment one of the application are used from the technical scheme explaining the application, but do not form the restriction to technical scheme.
Fig. 1 is the schematic flow sheet of the locomotive vehicle-mounted data processing method of the embodiment of the present application.
Fig. 2 is the idiographic flow schematic diagram of the step S110 of the embodiment of the present application.
Fig. 3 is the idiographic flow schematic diagram of the step S120 of the embodiment of the present application.
Fig. 4 is the structural representation of the locomotive vehicle-mounted data handling system of the embodiment of the present application.
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, to the present invention, how application technology means solve technical matters whereby, and the implementation procedure reaching relevant art effect can fully understand and implement according to this.Each feature in the embodiment of the present application and embodiment, can be combined with each other under prerequisite of not conflicting mutually, the technical scheme formed is all within protection scope of the present invention.
In addition, the step shown in process flow diagram of accompanying drawing can perform in the computer system of such as one group of computer executable instructions.Further, although show logical order in flow charts, in some cases, can be different from the step shown or described by order execution herein.
(embodiment one)
Embodiments provide a kind of locomotive vehicle-mounted data processing method, the method can filter out valuable locomotive vehicle-mounted data from the locomotive vehicle-mounted data of acquired original.First the method uses the method based on Mahalanobis distance (mahalanobis distance) that polynary outlier detection Task Switching is become unitary outlier detection problem, and adopts Lai Yinda criterion to carry out the differentiation of data outlier.And then adopt SVM algorithm to classify or regretional analysis to data.This data processing method can be applicable to locomotive energy consumption analysis and locomotive failure analysis (as sensor temperature fault detect).
Fig. 1 is the schematic flow sheet of the locomotive vehicle-mounted data processing method of the embodiment of the present application.Each step of process in detail is carried out below with reference to Fig. 1.
In step s 110, pre-service is carried out to the locomotive vehicle-mounted data collected and obtain the locomotive vehicle-mounted data after noise reduction.
Particularly, the method in the present embodiment based on Mahalanobis distance detects outlier, namely detects noisy locomotive vehicle-mounted data.
For a multivariate data collection, if
it is corresponding average.For the object o in data set D, from o to
mahalanobis distance definition as follows, wherein S is covariance matrix.
Fig. 2 is the idiographic flow schematic diagram of the step S110 of the embodiment of the present application, and concrete pre-treatment step comprises following sub-step.
In sub-step S110a, calculate the average of each property value in data set D, determine mean vector
In sub-step S110b, for each object o, calculate from object o to
mahalanobis distance
In sub-step S110c, in a metadata set
middle employing Lai Yinda criterion differentiates outlier.This step can also adopt Grubbs inspection or the Dixon method of inspection to differentiate outlier, does not repeat them here.
In sub-step S110d, if
be defined as outlier, then o is also outlier, and it rejected from data set D, noise reduction completes.
The present embodiment adopts the method based on Mahalanobis distance to detect outlier, and reduce the noise existed in locomotive vehicle-mounted data, the data that place one's entire reliance upon itself do not need extraneous information, and method is simple and clear.In addition, detecting based on Mahalanobis distance the object that outlier reaches noise reduction except adopting, also can also can reach this object by adopting the methods such as the K average in least-squares estimation matching or cluster, repeating no more herein.
In the step s 120, carry out information excavating in the locomotive vehicle-mounted data after noise reduction, and then analyze locomotive energy consumption or locomotive failure.
Particularly, carry out information excavating based on SVM algorithm in the locomotive vehicle-mounted data after noise reduction, and then analyze locomotive energy consumption or locomotive failure.
It should be noted that, the much good effect that the theoretical frame complete due to SVM algorithm and practical application obtain, different kernel functions can be constructed to adapt to the data analysis of different characteristic based on different applications, therefore no matter be in theoretical or application, transverse direction or longitudinal direction, had and developed on a large scale very much.SVM algorithm is a learning model having supervision, take structural risk minimization as target, dimension disaster problem can be solved, be mainly used in pattern-recognition, such as: Text region, speech recognition etc., classification and regretional analysis, in oil well logging, well-log information is utilized to use SVM algorithm predicts bottom factor of porosity and the work such as clay content, weather forecast.
In addition, this step adopts carries out on large data platform based on the locomotive vehicle-mounted data processing method of SVM, effectively can improve counting yield by the distributed variable-frequencypump of large data platform.Because calculating is that distributed parallel carries out, therefore calculate individual node hardware performance requirements not high.
Below for two classification situations and data are Nonlinear separabilities, concrete step following (see Fig. 3).
In sub-step S120a, according to data characteristics and class object, choose suitable kernel function K (x, y) and former data are mapped to High-dimensional Linear separable space from low-dimensional non-linear space.Wherein conventional kernel function has:
K(x,y)＝(x·y+1)
2
K(x,y)＝tanh(kx·y-δ)
In this sub-step, adopt the kernel function of SVM algorithm effectively can avoid problem in locomotive vehicle-mounted data numerous and diverse in a large number, the problem includes: " dimension disaster problem ".
In sub-step S120b, determine decision boundary in space after exchange: wx+b=0, adopt the value of method of Lagrange multipliers determination parameter w and b.Namely the convex optimization problem of secondary is solved:
Be limited to y
i(wx
i+ b)>=1, i=1,2 ..., N
Wherein, x
ithe property value of object o, y
ibe the desired value of object o, N is object number, w and b is parameter.
In sub-step S120c, training set determines after study parameter value w and b of decision boundary, the object's property value on test set is substituted in sign function f (x)=sign (wx+b), according to classification of sign.
Can adopt one-to-many method to many classification situation, namely during training, the sample of certain classification is classified as a class, remaining sample is classified as another kind of, has so just constructed multiple two classification SVM, and then carries out SVM according to above-mentioned steps and learn.
It should be noted that, the embodiment of the present invention is except adopting except SVM algorithm processes locomotive vehicle-mounted data, can also adopt other sorting technique, such as: artificial neural network, Bayes classifier nearest neighbor classifier, they also can reach the object of classification.
Enumerate a concrete example below so that the validity of the inventive method to be described.
Example (relevant locomotive energy consumption analysis)
1, with the mode record train operating data of fixed step size, such as: train running speed, train operation distance, Train Schedule, tractive force of train, braking force of train, friction force, air resistance, train operation road conditions (only considering the gradient of running route) and train energy consumption etc., first can collect the data of returning to these and carry out pre-service, reduce noise and improve the quality of data.
2, the data will trained sort according to energy consumption height in unit distance, and before choosing energy consumption, 20% is divided into 3 classes, is respectively high energy consumption, normal, energy-conservation.
3, create 3 two sorters, be respectively:
Sorter A: high energy consumption, normal
Sorter B: high energy consumption, energy-conservation
Sorter C: normal, energy-conservation
Be described as follows for sorter B.
First, choosing classification in the data collected is that high energy consumption and energy-conservation record are as sample; Secondly, definite kernel function K (x, y).Kernel function can adopt the one in the kernel function such as approximation by polynomi-als, Bayes classifier, radial basis function, multilayer perceptron of current widespread use, and chooses training set to confirm parameter by the method for cross-certification.
Then, make wx+b=0, wherein w and b is the parameter needing to solve,
X=(x
1, x
2, x
3, x
4, x
5, x
6, x
7, x
8) represent the gradient of train running speed, train operation distance, Train Schedule, tractive force of train, braking force of train, friction force, air resistance, running route respectively; Then, the value of method of Lagrange multipliers determination parameter w and b is adopted.Namely the convex optimization problem of secondary is solved:
Be limited to y
i(wx
i+ b)>=1, i=1,2 ..., N
Y
irepresent i-th sample generic, y
iget 1 (high energy consumption) or-1 (energy-conservation).X
irepresent the value of the attribute (gradient of train running speed, train operation distance, Train Schedule, tractive force of train, braking force of train, friction force, air resistance, running route) of i-th sample;
That is ask parameter w, b, λ
ivalue, make antithesis LagrangianL
dmaximum
To function L
dabout w, b, λ
idifferentiate, can determine the value of these three parameters.Finally, classify to test samples Z by following formula: if f (z) is >0, sample Z belongs to high energy consumption, illustrates that train operation consumes the energy too much, driver need be reminded to adjust mode of operation; If f (z) is <0, then belong to energy-conservation, illustrate that train operation state is good, save the energy.
Sorter A, sorter C are identical with the principle of work of sorter B.Equally, need test samples Z to classify in sorter A and sorter C, finally determine the classification of test samples Z according to high energy consumption, these 3 classification numbers of votes obtained normal, energy-conservation.
Finally these information feed back can be compared to the energy saving optimizing operating system of train, as judging that whether train is the foundation of energy-saving run.
(embodiment two)
Fig. 4 is the structural representation of the locomotive vehicle-mounted data handling system of the embodiment of the present application.The 26S Proteasome Structure and Function of native system is described referring to Fig. 4.
As shown in Figure 4, this system comprises pretreatment module 41 and data processing module 42, and they perform step S110 in embodiment one and step S120 respectively, repeat no more herein.
Those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on network that multiple calculation element forms, alternatively, they can realize with the executable program code of calculation element, thus, they can be stored and be performed by calculation element in the storage device, or they are made into each integrated circuit modules respectively, or the multiple module in them or step are made into single integrated circuit module to realize.Like this, the present invention is not restricted to any specific hardware and software combination.
Although the embodiment disclosed by the present invention is as above, the embodiment that described content just adopts for the ease of understanding the present invention, and be not used to limit the present invention.Technician in any the technical field of the invention; under the prerequisite not departing from the spirit and scope disclosed by the present invention; any amendment and change can be done what implement in form and in details; but scope of patent protection of the present invention, the scope that still must define with appending claims is as the criterion.
Claims (10)
1. a locomotive vehicle-mounted data processing method, comprising:
Pre-service is carried out to the locomotive vehicle-mounted data collected and obtains the locomotive vehicle-mounted data after noise reduction;
Carry out information excavating in the locomotive vehicle-mounted data after described noise reduction, and then analyze locomotive energy consumption or locomotive failure.
2. method according to claim 1, is characterized in that, the locomotive vehicle-mounted data collected are carried out pre-service obtain noise reduction after locomotive vehicle-mounted data step in,
Method based on the K average in the method for mahalanobis distance, least-squares estimation matching or cluster detects noisy locomotive vehicle-mounted data.
3. method according to claim 2, is characterized in that, detects in the step of noisy locomotive vehicle-mounted data, comprise further in the method based on mahalanobis distance:
Calculate the average of described locomotive vehicle-mounted data, determine mean vector;
Calculate the mahalanobis distance of each locomotive vehicle-mounted data to mean vector successively;
Differentiate noisy locomotive vehicle-mounted data according to described mahalanobis distance, and removed the locomotive vehicle-mounted data after obtaining noise reduction.
4. method according to claim 3, is characterized in that,
Utilize Lay mattress to reach criterion, Grubbs inspection or the Dixon method of inspection carry out outlier differentiation to described mahalanobis distance and then determine noisy locomotive vehicle-mounted data.
5. method according to claim 1, is characterized in that,
Based on SVM algorithm, carry out information excavating by the distributed variable-frequencypump of large data platform in the locomotive vehicle-mounted data after described noise reduction.
6. a locomotive vehicle-mounted data handling system, comprising:
Pretreatment module, it carries out pre-service to the locomotive vehicle-mounted data collected and obtains the locomotive vehicle-mounted data after noise reduction;
Data processing module, it carries out information excavating in the locomotive vehicle-mounted data after described noise reduction, and then analyzes locomotive energy consumption or locomotive failure.
7. system according to claim 6, is characterized in that,
Described pretreatment module detects noisy locomotive vehicle-mounted data based on the method for the K average in the method for mahalanobis distance, least-squares estimation matching or cluster.
8. system according to claim 7, is characterized in that, described pretreatment module is further used for:
Calculate the average of described locomotive vehicle-mounted data, determine mean vector;
Calculate the mahalanobis distance of each locomotive vehicle-mounted data to mean vector successively;
Differentiate noisy locomotive vehicle-mounted data according to described mahalanobis distance, and removed the locomotive vehicle-mounted data after obtaining noise reduction.
9. system according to claim 8, is characterized in that,
Described pretreatment module utilize Lay mattress reach criterion, Grubbs inspection or the Dixon method of inspection outlier differentiation is carried out to described mahalanobis distance and then determines noisy locomotive vehicle-mounted data.
10. system according to claim 6, is characterized in that,
Described data processing module, based on SVM algorithm, carries out information excavating by the distributed variable-frequencypump of large data platform in the locomotive vehicle-mounted data after described noise reduction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510711968.XA CN105427016A (en) | 2015-10-28 | 2015-10-28 | Locomotive vehicle data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510711968.XA CN105427016A (en) | 2015-10-28 | 2015-10-28 | Locomotive vehicle data processing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105427016A true CN105427016A (en) | 2016-03-23 |
Family
ID=55505209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510711968.XA Pending CN105427016A (en) | 2015-10-28 | 2015-10-28 | Locomotive vehicle data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105427016A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106842925A (en) * | 2017-01-20 | 2017-06-13 | 清华大学 | A kind of locomotive smart steering method and system based on deeply study |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794296A (en) * | 2010-01-13 | 2010-08-04 | 中国电子科技集团公司第五十四研究所 | Excavating method based on air activity target data |
| KR20140039380A (en) * | 2012-09-20 | 2014-04-02 | 국립대학법인 울산과학기술대학교 산학협력단 | Apparatus and method for quality control using datamining in manufacturing process |
| CN104461551A (en) * | 2014-12-16 | 2015-03-25 | 芜湖乐锐思信息咨询有限公司 | Parallel data processing based big data processing system |
-
2015
- 2015-10-28 CN CN201510711968.XA patent/CN105427016A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794296A (en) * | 2010-01-13 | 2010-08-04 | 中国电子科技集团公司第五十四研究所 | Excavating method based on air activity target data |
| KR20140039380A (en) * | 2012-09-20 | 2014-04-02 | 국립대학법인 울산과학기술대학교 산학협력단 | Apparatus and method for quality control using datamining in manufacturing process |
| CN104461551A (en) * | 2014-12-16 | 2015-03-25 | 芜湖乐锐思信息咨询有限公司 | Parallel data processing based big data processing system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106842925A (en) * | 2017-01-20 | 2017-06-13 | 清华大学 | A kind of locomotive smart steering method and system based on deeply study |
| CN106842925B (en) * | 2017-01-20 | 2019-10-11 | 清华大学 | A kind of locomotive smart steering method and system based on deeply study |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378869B (en) | Steel rail fastener abnormity detection method with automatic sample marking function | |
| CN102944418B (en) | Wind turbine generator group blade fault diagnosis method | |
| CN102682601B (en) | Expressway traffic incident detection method based on optimized support vector machine (SVM) | |
| CN102855638B (en) | Detection method for abnormal behavior of vehicle based on spectrum clustering | |
| CN102778355B (en) | Rolling bearing state identification method based on empirical mode decomposition (EMD) and principal component analysis (PCA) | |
| CN102063109B (en) | Neural network-based subway train fault diagnosis device and method | |
| CN104598813A (en) | Computer intrusion detection method based on integrated study and semi-supervised SVM | |
| CN107944472B (en) | A kind of airspace operation situation calculation method based on transfer learning | |
| CN104636449A (en) | Distributed type big data system risk recognition method based on LSA-GCC | |
| CN101271625A (en) | Method for detecting freeway traffic event by integration supporting vector machine | |
| CN104749334A (en) | Mode-recognition-based design method for biological abnormal water quality evaluation system | |
| CN102842043B (en) | Particle swarm classifying method based on automatic clustering | |
| CN104050361A (en) | Intelligent analysis early warning method for dangerousness tendency of prison persons serving sentences | |
| CN109947898B (en) | Equipment fault testing method based on intellectualization | |
| CN106991049A (en) | A kind of Software Defects Predict Methods and forecasting system | |
| CN101251896B (en) | Object detecting system and method based on multiple classifiers | |
| CN109376247A (en) | A kind of software defect automatic classification method based on correlation rule | |
| CN104951787A (en) | Power quality disturbance identification method for distinguishing dictionary learning under SRC framework | |
| CN113431635B (en) | Semi-supervised shield tunnel face geological type estimation method and system | |
| CN104832418A (en) | Hydraulic pump fault diagnosis method based on local mean conversion and Softmax | |
| You et al. | An efficient lightweight neural network using BiLSTM-SCN-CBAM with PCA-ICEEMDAN for diagnosing rolling bearing faults | |
| CN114298679A (en) | Industrial AI platform based on big data, application method, medium and electronic equipment thereof | |
| CN106384507A (en) | Travel time real-time estimation method based on sparse detector | |
| Yang et al. | Multipoint acceleration information acquisition of the impact experiments between coal gangue and the metal plate and coal gangue recognition based on SVM and serial splicing data | |
| CN105427016A (en) | Locomotive vehicle data processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160323 |