CN112597630B - Discrete integral-based nonlinear remote parameter conversion method and system - Google Patents
Discrete integral-based nonlinear remote parameter conversion method and system Download PDFInfo
- Publication number
- CN112597630B CN112597630B CN202011394604.0A CN202011394604A CN112597630B CN 112597630 B CN112597630 B CN 112597630B CN 202011394604 A CN202011394604 A CN 202011394604A CN 112597630 B CN112597630 B CN 112597630B
- Authority
- CN
- China
- Prior art keywords
- remote
- sequence
- nonlinear
- binary
- time interval
- 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
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
-
- 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]
-
- 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
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention provides a discrete integration based nonlinear remote parameter conversion method and a system, comprising the following steps: step 1: according to the analysis of the internal working mechanism of the satellite and the analysis of actual data, binary original remote parameters with a nonlinear integral relation are selected from the satellite remote parameters, the binary original remote parameters are aligned and matched on a time axis, and a binary remote parameter sequence with strictly matched time point positions is obtained; step 2: carrying out time difference processing on the binary remote reference sequence to obtain an original remote reference time interval sequence; and step 3: according to a nonlinear conversion formula, carrying out discrete integral conversion on the original remote parameter time interval sequence to generate a remote parameter integral sequence; and 4, step 4: and performing linear representation on the remote reference integral sequence to generate a new remote reference sequence combination with a linear mathematical relationship. The invention utilizes a mathematical transformation method to carry out linearization processing on the nonlinear telemetry parameter sequence which is not easy to carry out incidence relation modeling, thereby realizing the conversion from the nonlinear telemetry incidence relation to the linear incidence relation.
Description
Technical Field
The invention relates to the technical field of satellite health state monitoring, in particular to a discrete integration-based nonlinear remote parameter conversion method and system.
Background
The navigation satellite system has a complex structure, monitoring parameters contain rich correlation relations, and the real-time operation state of the satellite is described by the correlation relations. The traditional single-parameter satellite state monitoring method mainly alarms the telemetering parameters with the amplitude or the change rate exceeding the limit through a fixed threshold. However, in the initial failure and slight failure period of the satellite system, the single-remote parameter changes weakly according to itself, which means that the remote parameter amplitude is still stable within the monitoring threshold range, so that the single-remote parameter state monitoring based on the fixed threshold cannot effectively represent the real-time health state of the system. For this reason, it is often necessary to jointly characterize the health status of the satellites using binary telemetry.
Through observation of satellite real telemetry data, it can be found that binary telemetry representing satellite health states generally obeys two forms from the mathematical relationship between the two: linear and non-linear integral relationships. The binary satellite remote parameter with the linear relation has a plurality of good properties, and can support qualitative analysis, quantitative analysis and batch data mining. In qualitative analysis, the binary remote parameters in a linear relationship have synchronous variation trend, are visual and easy to observe, and can be directly combined with expert experience to carry out analysis from the binary remote parameter trend relationship. On quantitative analysis, the binary remote parameters in a linear relation have a definite mathematical model and can support accurate mathematical relation measurement. Meanwhile, due to the existence of linear correlation quantitative indexes such as Pearson coefficients and the like, binary remote parameter combinations with potential linear relations can be automatically mined from massive satellite remote parameters. However, since the binary remote parameters with non-linear integral relationship do not have the obvious advantages and the non-linear relationship with regular period is difficult to accurately and quantitatively describe, the non-linear integral relationship remote parameters are often ignored in the actual health monitoring work, so that the health information represented behind the remote parameters is lost.
Patent document CN110274660A (application number: CN201910688144.3) discloses a liquid amount detection method, device, system, and household appliance, in which capacitance acquisition is performed by each capacitance detector provided on a liquid container, and when the liquid amount in the liquid container changes, the liquid amount can be sensed by the capacitance detector, and corresponding capacitance acquisition is performed. When each capacitance detector acquires capacitance values with corresponding sizes, the sum of the corresponding capacitance values is obtained through calculation, and then the sum of the capacitance values and a preset fitting curve are analyzed, so that liquid level data in the liquid container can be visually obtained.
Patent document CN110110365A (application number: CN201910258427.4) discloses a battery RUL prediction method based on battery capacity fading trajectory linearization transformation, which includes the steps of: s1, reading historical capacity data of the power battery, linearizing a nonlinear capacity data track through Box-Cox transformation, and obtaining Box-Cox transformation coefficients and historical capacity data after Box-Cox transformation; s2, fitting the historical capacity data after Box-Cox transformation and the corresponding cycle number by a first-order polynomial model; s3, identifying model parameters of the first-order polynomial model through a Parameter Estimation tool in Matlab/Simulink; and S4, inputting the set capacity threshold, predicting the cycle number reaching the capacity threshold through the first-order polynomial model after the parameters are updated, and outputting the cycle number.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a discrete integration-based nonlinear remote parameter conversion method and system.
The invention provides a discrete integration-based nonlinear remote parameter conversion method, which comprises the following steps:
step 1: according to the analysis of the internal working mechanism of the satellite and the analysis of actual data, binary original remote parameters with a nonlinear integral relation are selected from the satellite remote parameters, and the binary original remote parameters are aligned and matched on a time axis by adopting a fuzzy matching-based time calibration algorithm to obtain a binary remote parameter sequence with strictly matched time point positions;
step 2: carrying out time difference processing on the binary remote reference sequence to obtain an original remote reference time interval sequence;
and step 3: according to a nonlinear conversion formula, carrying out discrete integral conversion on the original remote parameter time interval sequence to generate a remote parameter integral sequence;
and 4, step 4: and performing linear representation on the remote reference integral sequence to generate a new remote reference sequence combination with a linear mathematical relationship.
Preferably, the step 1 comprises:
-performing an alignment process on missing data;
-aligning the non-uniform sampling frequency data;
aligning the satellite multi-dimensional remote reference sequence with time offset.
Preferably, the step 2 comprises:
and acquiring a time tag set of the binary remote reference sequence to be processed, and carrying out differential processing on the time tag set to obtain a remote reference time interval set.
Preferably, the step 3 comprises:
step 3.1: performing point multiplication on the time interval set and the satellite independent variable remote parameter sequence to obtain a unit time interval remote parameter increase set;
step 3.2: and accumulating the remote parameter growth set to obtain a unit time interval accumulation set.
Preferably, the step 4 comprises: and performing linear representation on the unit time interval accumulation set to complete the mapping conversion from the nonlinear remote reference sequence to the linear remote reference sequence and complete the conversion processing.
The invention provides a discrete integration based nonlinear remote parameter conversion system, which comprises:
module M1: according to the analysis of the internal working mechanism of the satellite and the analysis of actual data, binary original remote parameters with a nonlinear integral relation are selected from the satellite remote parameters, and the binary original remote parameters are aligned and matched on a time axis by adopting a fuzzy matching-based time calibration algorithm to obtain a binary remote parameter sequence with strictly matched time point positions;
module M2: carrying out time difference processing on the binary remote reference sequence to obtain an original remote reference time interval sequence;
module M3: according to a nonlinear conversion formula, carrying out discrete integral conversion on the original remote parameter time interval sequence to generate a remote parameter integral sequence;
module M4: and performing linear representation on the remote reference integral sequence to generate a new remote reference sequence combination with a linear mathematical relationship.
Preferably, the module M1 includes:
-performing an alignment process on missing data;
-aligning the non-uniform sampling frequency data;
aligning the satellite multi-dimensional remote reference sequence with time offset.
Preferably, the module M2 includes:
and acquiring a time tag set of the binary remote reference sequence to be processed, and carrying out differential processing on the time tag set to obtain a remote reference time interval set.
Preferably, the module M3 includes:
module M3.1: performing point multiplication on the time interval set and the satellite independent variable remote parameter sequence to obtain a unit time interval remote parameter increase set;
module M3.2: and accumulating the remote parameter growth set to obtain a unit time interval accumulation set.
Preferably, the module M4 includes: and performing linear representation on the unit time interval accumulation set to complete the mapping conversion from the nonlinear remote reference sequence to the linear remote reference sequence and complete the conversion processing.
Compared with the prior art, the invention has the following beneficial effects: the invention utilizes a mathematical transformation method to carry out linearization processing on the nonlinear telemetry parameter sequence which is not easy to carry out incidence relation modeling, realizes the conversion from the nonlinear telemetry incidence relation to the linear incidence relation, and can effectively represent the real-time health state of the system.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a general flow chart of a nonlinear remote parameter conversion method;
FIG. 2 is a diagram illustrating the effect of time calibration processing of a two-dimensional remote reference set of a satellite;
fig. 3 is a diagram illustrating the effect of the linearization process of the two-dimensional remote reference set of the satellite.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
Example (b):
referring to fig. 1, a discrete integral nonlinear remote parameter data conversion method is provided for solving the problems of poor visibility and difficulty in quantitative description of binary remote parameters in a nonlinear integral relationship, and the nonlinear integral relationship is converted into a linear relationship to support development of qualitative analysis, quantitative analysis and data mining.
Telemetry parameter selection: combining the analysis of the internal working mechanism of the satellite and the analysis of actual data, selecting binary original remote parameters with potential nonlinear integral relation from the satellite remote parameters, and forming a binary remote parameter set in K periods:
time calibration processing steps: because inconsistent sampling frequencies may exist among different remote parameters, a time calibration algorithm based on fuzzy matching is adopted to carry out alignment matching on a time axis, and a binary remote parameter sequence with strictly matched time point positions is obtained:
a time difference processing step: by analyzing the working mechanism of the internal components of the satelliteAnd data observation shows that the binary remote parameters with the nonlinear integral relationship generally represent that: the dependent variable set Y and the independent variable set X show periodic integral rules. I.e. in each cycle, the sequence of dependent variables yiThe first value of each point
For the initial value of the integral, the sequence of independent variables xiThe points in the table are change rates, and show monotone cumulative change trend in time. Therefore, the time difference processing steps are as follows:
a time tag obtaining step: extracting a time label set corresponding to the binary remote parameter after time calibration:
a time difference processing step: for each sequence T of the time tag set TiPerforming point-to-point differential processing on the adjacent elements to obtain a time interval sequence
Repeating the above operations to obtain a time interval set:
discrete integral conversion step: multiplying the sequence in the time interval set delta T obtained in the last step with the sequence in the independent variable remote reference set X point by point
And obtaining a unit interval growth set:
on the basis, each sequence in the growing set is subjected to point-by-point accumulation processing
Obtaining a unit interval accumulation set:
thereby, the conversion of the binary nonlinear integral relationship into the binary linear relationship is completed.
A mathematical relationship representation generation step: through the above nonlinear transformation process, the binary nonlinear integral relationship can be linearly expressed as follows:
wherein a is the intercept, b is the slope,
to factor the ith value in the ith sequence of the variable set,
the ith point value in the ith sequence is cumulatively assembled for the interval,
the first value in the ith sequence, i.e. the starting point of integration, is collected by the dependent variables. Therefore, the linear transformation of the nonlinear integral binary remote parameter is completed, and qualitative and quantitative analysis and related data mining work can be carried out on the nonlinear integral binary remote parameter.
Fig. 2 is a binary telemetry curve obtained by performing time calibration processing on the integral binary telemetry set and unifying a time axis. And selecting the charging current of the storage battery as an independent variable, selecting the capacity of the storage battery as a dependent variable, and establishing an integral binary remote parameter set to be converted. As can be seen from the graph, the battery capacity as a dependent variable and the charging current independent variable show a periodic integral relationship.
Fig. 3 is a linear transformed satellite binary telemetry sequence curve. According to the time difference processing method, the binary remote parameter set after step time calibration is processed to obtain a time interval set. Then, the discrete integral conversion method mentioned in the summary of the invention is used for carrying out nonlinear conversion on the obtained time interval set to obtain a first value-removed dependent variable and a unit interval accumulation set. Finally, through discrete integral processing, the remote reference set of the binary nonlinear integral relation completes linear transformation, and can support subsequent qualitative and quantitative analysis and related data mining work.
The invention provides a discrete integration based nonlinear remote parameter conversion system, which comprises:
module M1: according to the analysis of the internal working mechanism of the satellite and the analysis of actual data, binary original remote parameters with a nonlinear integral relation are selected from the satellite remote parameters, and the binary original remote parameters are aligned and matched on a time axis by adopting a fuzzy matching-based time calibration algorithm to obtain a binary remote parameter sequence with strictly matched time point positions;
module M2: carrying out time difference processing on the binary remote reference sequence to obtain an original remote reference time interval sequence;
module M3: according to a nonlinear conversion formula, carrying out discrete integral conversion on the original remote parameter time interval sequence to generate a remote parameter integral sequence;
module M4: and performing linear representation on the remote reference integral sequence to generate a new remote reference sequence combination with a linear mathematical relationship.
Preferably, the module M1 includes:
-performing an alignment process on missing data;
-aligning the non-uniform sampling frequency data;
aligning the satellite multi-dimensional remote reference sequence with time offset.
Preferably, the module M2 includes:
and acquiring a time tag set of the binary remote reference sequence to be processed, and carrying out differential processing on the time tag set to obtain a remote reference time interval set.
Preferably, the module M3 includes:
module M3.1: performing point multiplication on the time interval set and the satellite independent variable remote parameter sequence to obtain a unit time interval remote parameter increase set;
module M3.2: and accumulating the remote parameter growth set to obtain a unit time interval accumulation set.
Preferably, the module M4 includes: and performing linear representation on the unit time interval accumulation set to complete the mapping conversion from the nonlinear remote reference sequence to the linear remote reference sequence and complete the conversion processing.
Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. A non-linear remote parameter conversion method based on discrete integration is characterized by comprising the following steps:
step 1: according to the analysis of the internal working mechanism of the satellite and the analysis of actual data, binary original remote parameters with a nonlinear integral relation are selected from the satellite remote parameters, and the binary original remote parameters are aligned and matched on a time axis by adopting a fuzzy matching-based time calibration algorithm to obtain a binary remote parameter sequence with strictly matched time point positions;
step 2: carrying out time difference processing on the binary remote reference sequence to obtain an original remote reference time interval sequence;
and step 3: according to a nonlinear conversion formula, carrying out discrete integral conversion on the original remote parameter time interval sequence to generate a remote parameter integral sequence;
and 4, step 4: and performing linear representation on the remote reference integral sequence to generate a new remote reference sequence combination with a linear mathematical relationship.
2. The discrete integration-based nonlinear telemetry method according to claim 1, wherein the step 1 comprises:
-performing an alignment process on missing data;
-aligning the non-uniform sampling frequency data;
aligning the satellite multi-dimensional remote reference sequence with time offset.
3. The discrete integration-based nonlinear telemetry method of claim 1, wherein the step 2 comprises:
and acquiring a time tag set of the binary remote reference sequence to be processed, and carrying out differential processing on the time tag set to obtain a remote reference time interval set.
4. The discrete integration-based nonlinear telemetry method according to claim 3, wherein the step 3 comprises:
step 3.1: performing point multiplication on the time interval set and the satellite independent variable remote parameter sequence to obtain a unit time interval remote parameter increase set;
step 3.2: and accumulating the remote parameter growth set to obtain a unit time interval accumulation set.
5. The discrete integration-based nonlinear telemetry method according to claim 4, wherein the step 4 comprises: and performing linear representation on the unit time interval accumulation set to complete the mapping conversion from the nonlinear remote reference sequence to the linear remote reference sequence and complete the conversion processing.
6. A discrete integration based non-linear telemetry conversion system, comprising:
module M1: according to the analysis of the internal working mechanism of the satellite and the analysis of actual data, binary original remote parameters with a nonlinear integral relation are selected from the satellite remote parameters, and the binary original remote parameters are aligned and matched on a time axis by adopting a fuzzy matching-based time calibration algorithm to obtain a binary remote parameter sequence with strictly matched time point positions;
module M2: carrying out time difference processing on the binary remote reference sequence to obtain an original remote reference time interval sequence;
module M3: according to a nonlinear conversion formula, carrying out discrete integral conversion on the original remote parameter time interval sequence to generate a remote parameter integral sequence;
module M4: and performing linear representation on the remote reference integral sequence to generate a new remote reference sequence combination with a linear mathematical relationship.
7. The discrete integration based nonlinear telemetry system of claim 6, wherein the module M1 comprises:
-performing an alignment process on missing data;
-aligning the non-uniform sampling frequency data;
aligning the satellite multi-dimensional remote reference sequence with time offset.
8. The discrete integration based nonlinear telemetry system of claim 6, wherein the module M2 comprises:
and acquiring a time tag set of the binary remote reference sequence to be processed, and carrying out differential processing on the time tag set to obtain a remote reference time interval set.
9. The discrete integration based nonlinear telemetry system of claim 8, wherein the module M3 comprises:
module M3.1: performing point multiplication on the time interval set and the satellite independent variable remote parameter sequence to obtain a unit time interval remote parameter increase set;
module M3.2: and accumulating the remote parameter growth set to obtain a unit time interval accumulation set.
10. The discrete integration based nonlinear telemetry system of claim 9, wherein the module M4 comprises: and performing linear representation on the unit time interval accumulation set to complete the mapping conversion from the nonlinear remote reference sequence to the linear remote reference sequence and complete the conversion processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011394604.0A CN112597630B (en) | 2020-12-03 | 2020-12-03 | Discrete integral-based nonlinear remote parameter conversion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011394604.0A CN112597630B (en) | 2020-12-03 | 2020-12-03 | Discrete integral-based nonlinear remote parameter conversion method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112597630A CN112597630A (en) | 2021-04-02 |
| CN112597630B true CN112597630B (en) | 2022-03-18 |
Family
ID=75187765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011394604.0A Active CN112597630B (en) | 2020-12-03 | 2020-12-03 | Discrete integral-based nonlinear remote parameter conversion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112597630B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5792062A (en) * | 1996-05-14 | 1998-08-11 | Massachusetts Institute Of Technology | Method and apparatus for detecting nonlinearity in an electrocardiographic signal |
| CN105677937A (en) * | 2015-07-16 | 2016-06-15 | 同济大学 | Method for remodeling medium objects by electromagnetic inverse scattering |
| CN110297258A (en) * | 2019-06-18 | 2019-10-01 | 中国科学院国家空间科学中心 | A kind of monotonic increase counts class telemetry parameter exception automatic distinguishing method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ZA965340B (en) * | 1995-06-30 | 1997-01-27 | Interdigital Tech Corp | Code division multiple access (cdma) communication system |
-
2020
- 2020-12-03 CN CN202011394604.0A patent/CN112597630B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5792062A (en) * | 1996-05-14 | 1998-08-11 | Massachusetts Institute Of Technology | Method and apparatus for detecting nonlinearity in an electrocardiographic signal |
| CN105677937A (en) * | 2015-07-16 | 2016-06-15 | 同济大学 | Method for remodeling medium objects by electromagnetic inverse scattering |
| CN110297258A (en) * | 2019-06-18 | 2019-10-01 | 中国科学院国家空间科学中心 | A kind of monotonic increase counts class telemetry parameter exception automatic distinguishing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112597630A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Nonlinear-drifted Brownian motion with multiple hidden states for remaining useful life prediction of rechargeable batteries | |
| CN102282552B (en) | Based Intelligent Control based on pattern, monitoring and the system of automatization, method and computer program | |
| Grzesiek et al. | Long term belt conveyor gearbox temperature data analysis–Statistical tests for anomaly detection | |
| CN101436057A (en) | Numerical control machining tool heat error Bayes network compensation method | |
| CN102884486A (en) | Malfunction analysis apparatus, malfunction analysis method, and recording medium | |
| EP3696693A1 (en) | Method and apparatus for monitoring state of device in process industry and medium | |
| Juraev et al. | Nonlinear control object identification problems: Methods and approaches | |
| CN115514679B (en) | Abnormal source monitoring method and system based on communication module | |
| Chakour et al. | Diagnosis of uncertain nonlinear systems using interval kernel principal components analysis: Application to a weather station | |
| CN117556366B (en) | Data abnormality detection system and method based on data screening | |
| CN116597939A (en) | Medicine quality control management analysis system and method based on big data | |
| CN102722603A (en) | Reliability measuring method for mechanical and electrical products | |
| Pulikottil et al. | Big data life cycle in shop-floor–trends and challenges | |
| CN112597630B (en) | Discrete integral-based nonlinear remote parameter conversion method and system | |
| CN1996192A (en) | Industrial soft measuring instrument based on bionic intelligence and soft measuring method therefor | |
| Lee et al. | Deep neural network and meta-learning-based reactive sputtering with small data sample counts | |
| Cardot et al. | Comparison of different sample designs and construction of confidence bands to estimate the mean of functional data: An illustration on electricity consumption | |
| Xue et al. | A nonparametric adaptive EWMA control chart for monitoring mixed continuous and categorical data using self-starting strategy | |
| CN117694070A (en) | Nutrient element inversion evaluation and intelligent variable accurate fertilization decision system | |
| Hasan | WyNDA: A method to discover mathematical models of dynamical systems from data | |
| CN103390103A (en) | Melt index online detection method based on subspace independent component regression model | |
| CN113554106B (en) | Collaborative completion method for power missing data | |
| Marufuzzaman et al. | Hardware simulation of pattern matching and reinforcement learning to predict the user next action of smart home device usage | |
| dos Santos et al. | Simulation-based digital twins monitoring: an approach focused on models’ accreditation | |
| CN106919755A (en) | A kind of cloud manufacture system uncertainty quantitative analysis method and device based on data |
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 |