CN103473439B - A kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information - Google Patents
A kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information Download PDFInfo
- Publication number
- CN103473439B CN103473439B CN201310359750.3A CN201310359750A CN103473439B CN 103473439 B CN103473439 B CN 103473439B CN 201310359750 A CN201310359750 A CN 201310359750A CN 103473439 B CN103473439 B CN 103473439B
- Authority
- CN
- China
- Prior art keywords
- data
- forecast
- rough
- electromechanical equipment
- noise ratio
- 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.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information, the steps include: 1) obtain vibration data, acoustic emission data, cutting force data, noise data and temperature data; 2) utilize hierarchical clustering algorithm that serial correlation data are carried out sliding-model control respectively, obtain N group discrete data; 3) the often group discrete data after discretize is formed decision table DT, as the input layer X of rough function adaptive approach
i(t); 4) utilize rough function adaptive approach to carry out forecast analysis to decision table DT, obtain optimal objective forecast model; 5) according to the accurate prediction models of the optimal objective forecast model obtained as this moment, and by monitoring equipment display subsequent time predicted value, the fault forecast to complicated electromechanical equipment low signal-to-noise ratio information is realized.The present invention can realize the fault forecast to low signal-to-noise ratio information, can extensively apply in complicated electromechanical equipment.
Description
Technical field
The present invention relates to a kind of failure prediction method of complicated electromechanical equipment, particularly about a kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information.
Background technology
High-grade turning center is as typical complicated electromechanical equipment, become one of manufacturing main production equipments of modernization, the disposable clamping of processing work can be realized, and be equipped with automatic tool changer, decrease positioning error and lay time, the machining precision of workpiece and working (machining) efficiency are improved greatly.Along with coming into operation of high-grade turning center, the research of machine failure forecasting techniques starts to come into one's own.At present, failure prediction technology is mainly used in the aspect such as power equipment, large rotating machinery, relates to less for numerical control device.Because high-grade turning center has maximization, integrated, the feature such as precise treatment and intellectuality in mechanism, function etc.; make in process, usually can run into full accuracy index not enough; precision can not be guaranteed for a long time; the problems such as failure rate is high, seriously constrain the numerically-controlled machine effect of bringing into normal play.Carrying out the research of diagnosing faults of numerical control machine forecasting techniques is one of the state-of-the-art technology and core technology that ensure numerically-controlled machine reliability service, improve lathe military service performance, is also the focal issue of research both at home and abroad.The extensive application of current high-grade, digitally controlled machine tools and the deficiency of diagnosis and maintenance technology have caused huge lathe early warning and diagnostic requirements, become one of bottleneck of current machine tool technology development.
Linear prediction method, non-linear Forecasting Methodology and neural network prediction is mainly contained in traditional failure prediction method.Mainly by adopting correct signal processing method to extract different fault signatures, then carry out state recognition to these features, this is the key element improving fault pre-alarming and performance evaluation accuracy.Such as numerically-controlled machine adds and carries out slice the dint to monitor man-hour, and utilizes off-line data to train BP neural network, makes tool wear prediction accuracy reach more than 97%.Such Forecasting Methodology achieves satisfied effect to a certain extent.But profit is carried out the electromechanical equipment that high-grade turning center etc. has a highly flexible mechanism in this way and is carried out monitoring, diagnosing, often runs into the situation that quantity of information is few, noise is large in collection signal process, has had a strong impact on the precision of Fault diagnosis and forecast.Simultaneously, because the signal gathered often has the features such as intermittence, ambiguity, time variation, the uncertain factor of causing trouble prediction increases, and processing operating mode variation makes random factors impact in process very greatly, cause the accuracy of failure prediction and the confidence level of conclusion to decline all to some extent.
Summary of the invention
For the problems referred to above, the object of this invention is to provide a kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information, the method can realize the fault forecast to low signal-to-noise ratio information.
For achieving the above object, the present invention takes following technical scheme: a kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information, and it comprises the following steps: 1) obtained vibration data, acoustic emission data, cutting force data, noise data and the temperature data that can represent the continuous print of a series of long course of equipment operation condition and equipment operation condition by on-line monitoring center; 2) utilize hierarchical clustering algorithm that the whole continuous datas obtained in step 1) are carried out sliding-model control respectively, obtain N group discrete data; Wherein, N is natural number; 3) the often group discrete data after discretize is formed decision table DT, and using the input layer X of decision table DT as rough function adaptive approach
i(t), i=1,2,3 ... n; Wherein n represents number of probes; 4) utilize rough function adaptive approach to carry out forecast analysis to decision table DT, obtain the optimal objective forecast model that can characterize complicated electromechanical equipment running status development trend in future; 5) according to the accurate prediction models of the optimal objective forecast model obtained as this moment, and by monitoring equipment display subsequent time predicted value, the fault forecast to complicated electromechanical equipment low signal-to-noise ratio information is realized.
In described step 4), when carrying out forecast analysis to told decision table DT, the rough function adaptive approach step of utilization is as follows: (1) objective definition rough function F (M) is:
F(M)＝f(m,w,θ)＝R[f(m|θ)×f(ω|θ)]，
Wherein, M is optimal objective forecast model; M is prediction rough function model, is the list entries after discretize; R represents the coarse relation of f (m) × f (ω), under difference connects weights θ, calculate corresponding rough function value; (2) input amendment is: X
i(t)=(X
1(t), X
2(t) ..., X
n(t)), X
it () is the often group data after discretize, and according to the definition of rough set upper bound and lower bound to X
it () carries out upper bound and lower bound calculating, obtain approximate data
with lower aprons data
t is the sampling time; (3) approximate data is taken off
calculate rough function, and suppose two tolerance
with
and real function f:R
t→ R
m, wherein R
t=[0t,
then real function f is f for the rough function of tolerance d and e
*(n)=e
*(f (x)),
(4) any given connection weights θ
it (), its scope is 0 < θ
i(t) < 1, by with rough function f
*n () is multiplied and obtains output layer
j=0,1,2 ..., n; (5) connection weights θ is revised
it () makes prediction accuracy w reach more than 85%, namely
=0,1,2 ..., n; Wherein, prediction accuracy is
Y={X
i(t) | i=1,2 ..., n} is the list entries after discretize;
for predicted data; η ∈ (0,1) is learning rate; (6) return step (2), repeat, utilize input amendment data constantly to regulate and connect weights θ
it the size of (), standard prediction accuracy w being reached preset, until connect weights θ
i(t) to all sample standard deviations stablize constant till, finally obtain target rough function F (M)=f (m, w, θ), and then obtain optimal objective forecast model M.
The present invention is owing to taking above technical scheme, it has the following advantages: 1, the present invention analyzes the rough function adaptive forecasting method of Low SNR signal owing to adopting a kind of being suitable for, and avoids because the generation of the unsteady phenomenas such as quantity of information lacks, noise is large appears in process status.2, the present invention is owing to connecting weights θ by adjustment rough function
it () can adapt to the variation of equipment processing operating mode, decrease some uncertain factors impact of failure prediction, improve the precision of failure prediction and the confidence level of conclusion.3, the failure prediction method based on rough function provided by the invention, the signal solved owing to gathering has ambiguity and time variation feature causes implicit data to be difficult to characterize the problem of failure symptom information.The present invention can extensively apply in complicated electromechanical equipment.
Accompanying drawing explanation
Fig. 1 is overall flow schematic diagram of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in detail.
As shown in Figure 1, the present invention is carry out failure prediction based on rough function towards the fault forecast method of complicated electromechanical equipment low signal-to-noise ratio information, and it comprises the following steps:
1) continuous print and the equipment operation condition related data that can represent a series of long course of the equipment operation condition of axis system, tooling system, kinematic train, feed system and electrical system is obtained by existing on-line monitoring center, such as vibration data, acoustic emission data, cutting force data, noise data and temperature data etc.;
2) utilize hierarchical clustering algorithm that the whole serial correlation data obtained in step 1) are carried out sliding-model control respectively, obtain N group discrete data; Wherein, N is natural number;
3) the often group discrete data after discretize is formed decision table DT, and using the input layer X of decision table DT as rough function adaptive approach
i(t), i=1,2,3 ... n; Wherein n represents number of probes;
4) utilize rough function adaptive approach to carry out forecast analysis to decision table DT, obtain the optimal objective forecast model that can characterize complicated electromechanical equipment (such as high-grade turning center) running status development trend in future;
Wherein, when carrying out forecast analysis to decision table DT, the rough function adaptive approach step of utilization is as follows:
(1) objective definition rough function F (M) is: F (M)=f (m, w, θ)=R [f (m| θ) × f (ω | θ)], wherein, M is optimal objective forecast model; M is prediction rough function model, is the list entries after discretize; R represents the coarse relation of f (m) × f (ω), under difference connects weights θ, calculate corresponding rough function value.
(2) input amendment is: X
i(t)=(X
1(t), X
2(t) ..., X
n(t)), X
it () is the often group data after discretize, and according to the definition of rough set upper bound and lower bound to X
it () carries out upper bound and lower bound calculating, obtain approximate data
with lower aprons data
t is the sampling time;
(3) approximate data is taken off
calculate rough function, and suppose two tolerance
with
and real function f:R
t→ R
m, wherein R
t=[0, t],
then real function f is f for the rough function of tolerance d and e
*(n)=e
*(f (x)),
(4) any given connection weights θ
it (), its scope is 0 < θ
i(t) < 1.By with rough function f
*n () is multiplied and can obtains output layer
j=0,1,2 ..., n;
(5) connection weights θ is revised
it () makes prediction accuracy w reach more than 85%, namely
i=0,1,2,…,n。
Wherein, prediction accuracy
y={X
i(t) | i=1,2 ..., n} is the list entries after discretize;
for predicted data; η ∈ (0,1) is learning rate, also referred to as Learning Step, for controlling erection rate, if η too conference affect θ
it stablizing of (), the too little meeting of η makes θ
it the speed of convergence of () is too slow.
(6) return step (2), repeat, utilize input amendment data constantly to regulate and connect weights θ
it the size of (), standard prediction accuracy w being reached preset, until connect weights θ
i(t) to all sample standard deviations stablize constant till, namely prediction accuracy w meets within the scope of specified value, finally obtains target rough function F (M) to be: F (M)=f (m, w, θ), and then obtain optimal objective forecast model M.Wherein, M is optimal objective forecast model; M is prediction rough function model.
5) according to the accurate prediction models of the optimal objective forecast model M obtained as this moment, and by existing monitoring equipment display subsequent time predicted value, the fault forecast to complicated electromechanical equipment low signal-to-noise ratio information is realized.
The various embodiments described above are only for illustration of the present invention; the connection of each parts and structure all can change to some extent; on the basis of technical solution of the present invention; all improvement of carrying out the connection of individual part and structure according to the principle of the invention and equivalents, all should not get rid of outside protection scope of the present invention.
Claims (1)
1., towards a fault forecast method for complicated electromechanical equipment low signal-to-noise ratio information, it comprises the following steps:
1) vibration data, acoustic emission data, cutting force data, noise data and the temperature data that can represent the continuous print of a series of long course of equipment operation condition and equipment operation condition is obtained by on-line monitoring center;
2) utilize hierarchical clustering algorithm by step 1) in obtain whole continuous datas carry out sliding-model control respectively, obtain N group discrete data; Wherein, N is natural number;
3) the often group discrete data after discretize is formed decision table DT, and using the input layer X of decision table DT as rough function adaptive approach
i(t), i=1,2,3 ... n; Wherein n represents number of probes;
4) utilize rough function adaptive approach to carry out forecast analysis to decision table DT, obtain the optimal objective forecast model that can characterize complicated electromechanical equipment running status development trend in future;
Described step 4) in, when carrying out forecast analysis to described decision table DT, the rough function adaptive approach step of utilization is as follows:
(1) objective definition rough function F (M) is: F (M)=f (m, w, θ)=R [f (m| θ) × f (ω | θ)], wherein, M is optimal objective forecast model; M is prediction rough function model, is the list entries after discretize; R represents the coarse relation of f (m) × f (ω), under difference connects weights θ, calculate corresponding rough function value;
(2) input amendment is: X
i(t)=(X
1(t), X
2(t) ..., X
n(t)), X
it () is the often group data after discretize, and according to the definition of rough set upper bound and lower bound to X
it () carries out upper bound and lower bound calculating, obtain approximate data
with lower aprons data
x i (t), t is the sampling time;
(3) approximate data is taken off
x i t () calculates rough function, and suppose two tolerance
with
and real function f:R
t→ R
m, wherein R
t=[0, t], R
m=[
x i (0),
x i (m)], then real function f is f for the rough function of tolerance d and e
*(n)=e
*(f (x)),
(4) any given connection weights θ
it (), its scope is 0< θ
i(t) <1, by with rough function f
*n () is multiplied and obtains output layer
(5) connection weights θ is revised
it () makes prediction accuracy w reach more than 85%, namely
Wherein, prediction accuracy
Y={X
i(t) | i=1,2 ..., n} is the list entries after discretize;
for predicted data; η ∈ (0,1) is learning rate;
(6) return step (2), repeat, utilize input amendment data constantly to regulate and connect weights θ
it the size of (), standard prediction accuracy w being reached preset, until connect weights θ
i(t) to all sample standard deviations stablize constant till, finally obtain target rough function F (M)=f (m, w, θ), and then obtain optimal objective forecast model M;
5) according to the accurate prediction models of the optimal objective forecast model obtained as this moment, and by monitoring equipment display subsequent time predicted value, the fault forecast to complicated electromechanical equipment low signal-to-noise ratio information is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310359750.3A CN103473439B (en) | 2013-08-17 | 2013-08-17 | A kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310359750.3A CN103473439B (en) | 2013-08-17 | 2013-08-17 | A kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103473439A CN103473439A (en) | 2013-12-25 |
| CN103473439B true CN103473439B (en) | 2016-04-06 |
Family
ID=49798286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310359750.3A Active CN103473439B (en) | 2013-08-17 | 2013-08-17 | A kind of fault forecast method towards complicated electromechanical equipment low signal-to-noise ratio information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473439B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117168865B (en) * | 2023-11-03 | 2024-04-12 | 南通宝佳精密机械有限公司 | Electromechanical device protection system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770219A (en) * | 2010-01-29 | 2010-07-07 | 北京信息科技大学 | Knowledge acquisition method of fault diagnosis knowledge base of turn-milling combined machine tool |
| CN102736562A (en) * | 2012-07-10 | 2012-10-17 | 北京信息科技大学 | Knowledge base construction method oriented to fault diagnosis and fault prediction of numerical control machine tool |
-
2013
- 2013-08-17 CN CN201310359750.3A patent/CN103473439B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770219A (en) * | 2010-01-29 | 2010-07-07 | 北京信息科技大学 | Knowledge acquisition method of fault diagnosis knowledge base of turn-milling combined machine tool |
| CN102736562A (en) * | 2012-07-10 | 2012-10-17 | 北京信息科技大学 | Knowledge base construction method oriented to fault diagnosis and fault prediction of numerical control machine tool |
Non-Patent Citations (4)
| Title |
|---|
| Tree structure for efficient data mining using rough sets;Ananthanarayana V S，et al.;《Pattern Recognition Letters》;20031231;第24卷(第6期);851-862 * |
| 基于粗糙集和决策树的自适应神经网络短期负荷预测方法;牛东晓，等.;《电力自动化设备》;20091031;第29卷(第10期);30-34 * |
| 基于粗糙集理论的数控机床智能故障诊断研究;姚鑫骅，等.;《浙江大学学报（工学版）》;20081031;第42卷(第10期);1719-1724 * |
| 融合粗糙集和模糊聚类的连续数据知识发现;于达仁，等.;《中国电机工程学报》;20040630;第24卷(第6期);205-210 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103473439A (en) | 2013-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108107841B (en) | Numerical twin modeling method of numerical control machine tool | |
| CN104808585B (en) | A kind of quick inspection method of lathe health status | |
| CN101520651B (en) | Analysis method for reliability of numerical control equipment based on hidden Markov chain | |
| CN101870075B (en) | Method for predicting service life of screw pair of numerical control machine on basis of performance degradation model | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN102819239B (en) | Intelligent fault diagnosis method of numerical control machine tool | |
| CN107016235B (en) | Equipment running state health degree evaluation method based on multi-feature adaptive fusion | |
| CN104503399B (en) | The regimental Wind turbines status monitoring of one kind collection and fault diagnosis platform | |
| CN104791187B (en) | The Adaptive System of Water-Turbine Engine and method of health status prediction can be realized | |
| CN105718876B (en) | A kind of appraisal procedure of ball-screw health status | |
| CN103064340B (en) | Failure prediction method facing to numerically-controlled machine tool | |
| CN111639921B (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
| CN105204436A (en) | Graded-early-warning-based fault diagnosis method of numerically-controlled machine tool | |
| CN101799674B (en) | Method for analyzing service state of numerical control equipment | |
| CN111812427A (en) | Health state assessment method and system for power electronic device | |
| CN102848266B (en) | Machine tool spindle accuracy prediction method | |
| CN106662072A (en) | Wind turbine condition monitoring method and system | |
| CN104808587A (en) | Utilization statistical approach based on operation states of machining equipment | |
| CN103901882A (en) | Online monitoring fault diagnosis system and method of train power system | |
| CN103499921A (en) | Fault diagnosis method for variable structure fuzzy system sensor and application thereof in flight control system | |
| CN108196525B (en) | The operational safety risk dynamic analysing method of Train Running Control System for High Speed | |
| CN102176217A (en) | Method for estimating reliability of numerical control machine tool cutting tool based on logistic model | |
| CN105243393A (en) | Characteristic-based fault forecasting method for complex electromechanical system | |
| US20220179394A1 (en) | Machine tool management method, machine tool management system and medium | |
| CN104794492A (en) | Online machine tool equipment machining and running state recognizing method based on power feature models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |