CN110749337A - MIMU error compensation method based on deep neural network - Google Patents
MIMU error compensation method based on deep neural network Download PDFInfo
- Publication number
- CN110749337A CN110749337A CN201910961889.2A CN201910961889A CN110749337A CN 110749337 A CN110749337 A CN 110749337A CN 201910961889 A CN201910961889 A CN 201910961889A CN 110749337 A CN110749337 A CN 110749337A
- Authority
- CN
- China
- Prior art keywords
- mimu
- output
- neural network
- error
- mems
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000006403 short-term memory Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000007787 long-term memory Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 4
- 238000001816 cooling Methods 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims 1
- 238000003062 neural network model Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 229940050561 matrix product Drugs 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C25/00—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
- G01C25/005—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass initial alignment, calibration or starting-up of inertial devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Manufacturing & Machinery (AREA)
- Gyroscopes (AREA)
Abstract
The invention discloses a MIMU error compensation method based on a deep neural network. And then, carrying out MIMU data acquisition aiming at the MIMU error model, and making a MIMU error data set. Finally, establishing an LSTM neural network model, training the neural network by adopting the manufactured data set, and continuously probing and adjusting the network structure; and predicting the MIMU error through the trained neural network, and using the network prediction value for MIMU error compensation. The invention adopts the LSTM neural network to carry out error compensation on the MIMU, replaces the traditional multi-position calibration method, and improves the precision and the efficiency of the MIMU error compensation.
Description
Technical Field
The invention relates to a MIMU error compensation method based on a deep neural network, and belongs to the technical field of MIMU output error compensation.
Background
MEMS inertial sensors are increasingly used in aerospace, defense, and consumer electronics applications because of their small size, low power consumption, low cost, and mass producibility. The MEMS accelerometer and the gyroscope respectively measure the acceleration and the angular velocity in the direction of a sensitive axis of the sensor, and the accelerometer and the gyroscope are three-dimensionally configured to form a Micro Inertial Measurement Unit (MIMU). The MEMS inertial device has large measurement error and is easily influenced by environmental factors, and in addition, non-orthogonal error and temperature drift caused by an integration process in three-dimensional orthogonal configuration form an important error source of the MIMU, a corresponding error model must be established to compensate the error so as to improve the precision of the MIMU.
The traditional MIMU calibration method needs to perform position test, speed test and temperature test, and performs independent calibration on all inertial sensors according to the processes of firstly normal temperature and then high and low temperature, so that the method is extremely tedious and consumes a lot of time. And the MEMS device has low precision and low zero-bias repeatability, and the performance of the MEMS device is reduced along with the increase and decrease of time, so that a large error exists between an error model and laboratory calibration.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the MIMU error compensation method based on the deep neural network is provided, features hidden in time sequence data are mined, the deep neural network is constructed, and strong nonlinear errors output by the MIMU are compensated.
The invention adopts the following technical scheme for solving the technical problems:
a MIMU error compensation method based on a deep neural network comprises the following steps:
step 2, acquiring specific data of the input variable and the output variable in the MIMU working state according to the input variable and the output variable determined in the step 1, and constructing a data set;
step 3, establishing a depth long-term and short-term memory neural network prediction model, and training the depth long-term and short-term memory neural network prediction model by using the data set established in the step 2 to obtain a trained prediction model;
and 4, acquiring the MIMU output data in real time, calculating an output error prediction value by using the trained prediction model, and performing error compensation on the MIMU output data by using the output error prediction value.
As a preferred embodiment of the present invention, the step 1 specifically comprises:
respectively establishing angular rate errors epsilon of three orthogonal MEMS gyroscopesaAnd acceleration error ▽ of three orthogonal MEMS accelerometersaThe model analyzes influence factors causing output errors of the MEMS gyroscope and the MEMS accelerometer according to respective error models, so as to determine input variables and output variables of the depth long-time memory neural network;
the error models of the MEMS gyroscope and the MEMS accelerometer are as follows:
wherein epsilon0aAnd Δ0aConstant zero offset vectors, ε, for gyroscopes and accelerometers, respectivelyTaAnd ΔTaRespectively the drift vectors of the gyroscope and accelerometer zero offset with temperature,
is a coefficient matrix
Coefficient of (1), ωaIs the angular velocity vector of the gyroscope output,
is a coefficient matrix
Coefficient of (1), faIs the acceleration vector output by the accelerometer,is a coefficient matrix
The coefficient of (a) to (b),
is a coefficient matrix
Coefficient of (1), eraAnd ΔraFor random error, a ═ x, y, z.
As a preferred embodiment of the present invention, the input variables and the output variables of the deep long-term and short-term memory neural network specifically include:
the input variables of the depth long-time memory neural network comprise the output of the MEMS gyroscope, the output of the MEMS accelerometer, the temperature of the MEMS gyroscope and the temperature of the MEMS accelerometer;
the output variables of the depth long-time memory neural network comprise an output error prediction value of the MEMS gyroscope and an output error prediction value of the MEMS accelerometer.
As a preferred scheme of the present invention, the specific data of the input variable and the output variable in the MIMU operating state is collected by the following specific method:
fixing the MIMU on a rotary table with a temperature control box; starting the rotary table, controlling the inner ring of the rotary table to accelerate to 200 ℃ per second, and simultaneously starting the temperature control box to heat the MIMU; when the speed of the inner ring of the turntable reaches 200 ℃ per second, the outer ring of the turntable is controlled to be accelerated to 200 ℃ per second uniformly, and the heating is stopped when the temperature of the MIMU reaches 80 ℃; keeping the turntable in the current motion state for a preset time; controlling the outer ring of the turntable to uniformly decelerate to 0, and controlling the temperature control box to cool the MIMU; when the speed of the outer ring of the turntable reaches 0, controlling the inner ring of the turntable to uniformly decelerate to 0, and stopping cooling when the temperature of the MIMU reaches-45 ℃; and collecting the data of the MIMU in the whole process, and repeatedly collecting the data until the data volume meets the requirement of the data set.
As a preferable scheme of the invention, the loss function of the depth long-term and short-term memory neural network is a cross entropy function, and the Optimizer is an Optimizer.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
the method comprises the steps of firstly carrying out error modeling on the MIMU, analyzing possible factors causing the MIMU output error, determining the input and output quantity of the LSTM network, then carrying out data acquisition on the MIMU, making a data set, and then using the data set for training of a depth Short-Term Memory (LSTM) neural network, wherein the data set is a model for better predicting the MIMU error, and finally improving the MIMU error compensation precision.
Drawings
Fig. 1 is a flowchart of a MIMU error compensation method based on a deep neural network according to the present invention.
FIG. 2 is a flow chart of data acquisition according to the present invention.
FIG. 3 is a block diagram of an LSTM neural network element of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As shown in fig. 1, a flowchart of a MIMU error compensation method based on a deep neural network according to the present invention includes the following steps:
step 2, acquiring multiple groups of time sequence historical data of the MIMU, wherein each group of time sequence data comprises inertial sensor output data, MIMU output error data and MIMU working environment data, the inertial sensor output data comprises triaxial accelerometer output and triaxial gyroscope output, the MIMU output error data comprises triaxial accelerometer error and triaxial gyroscope error, and the MIMU working environment data comprises temperature and time;
step 3, constructing the time sequence data into a data set;
step 4, establishing an LSTM neural network prediction model, training the LSTM neural network by using the data set, adjusting, optimizing and determining the number of input layers, hidden layers and output layers;
step 5, acquiring real-time MIMU output data, and calculating a predicted MIMU output error;
and 6, compensating the MIMU output error in real time by using the predicted data.
wherein the first term ε0And ▽0Constant zero offset vectors, second term epsilon, for gyros and accelerometers, respectivelyTAnd ΔTRespectively, the drift vectors of zero offset with temperature, and the third terms respectively are coefficient matrixes
Product and of angular velocity vector ω with gyro outputThe product of the output f of the accelerometer represents the nonlinear error related to angular motion and linear acceleration, and the fourth term is a coefficient matrix
Product and coefficient matrix with accelerometer output f
The first formula represents the mechanically sensitive error term of the angular velocity of the gyro in relation to the linear motion acceleration (vibration/shock acceleration) and the second formula represents the dimension effect error of the MEMS accelerometer, the first four terms of the two formulas being functionally regular and belonging to the deterministic error, epsilonrAnd ΔrIs a random error.
Step 2, acquiring historical time sequence data, specifically:
a set of data acquisition system is designed by using the single chip microcomputer STM32F407 as a processor, and a plurality of serial ports of the single chip microcomputer are used for simultaneously acquiring MIMU and turntable output data, so that the problem of time synchronization between the MIMU and the turntable is solved, the data synchronization between the MIMU and the turntable is realized, and the data acquisition flow is shown in figure 2. Design one set of revolving stage motion trail for MIMU data under the operating condition is more closely to the time series data of acquireing:
① starting the turntable to control the inner ring of the turntable to accelerate to 200 (deg)/s, and simultaneously starting the temperature control box to heat the MIMU;
② controlling the outer ring of the turntable to accelerate to 200 (deg)/s, and stopping heating when the temperature reaches 80 deg.C;
③ keeping the turntable moving for a certain time;
④ controlling the outer ring of the turntable to uniformly decelerate to 0, and controlling the incubator to cool the MIMU;
⑤ controlling the inner ring of the turntable to uniformly decelerate to 0, and stopping cooling when the temperature reaches-45 ℃;
and repeatedly acquiring data until the data volume meets the requirement of the data set.
Step 4, an LSTM neural network prediction model is built, the LSTM neural network unit is shown in fig. 3, the LSTM neural network unit controls the updating and the loss of the cell state through an input gate, a forgetting gate and an output gate, and the specific formula is as follows:
it＝σ(Wxixt+Whiht-1+d)
Ot＝σ(Wxoxt+Whoht-1+d)
ft＝σ(Wxfxt+Whfht-1+d)
wherein it、Ot、ftThe input gate output, the output gate output and the forgetting gate output at the moment t are respectively; h ist-1、ct-1Hidden layer output and memory unit state values at the time of t-1 respectively; sigma is an activation function; d is an offset value; the rest are corresponding weight coefficient matrixes.
The input gate and the forgetting gate determine the current memory state ct＝ftct-1+ittanh(Wxcxt+Whcht-1+ d) and the final output value h is obtained under the action of the output gatet＝ottanh(ct)。
Searching a hidden layer structure with the best performance by adopting a heuristic method, establishing a plurality of different models for training, and taking the mean square error (mse) of an error vector of an output layer as a measurement index of the precision of a network training result:
as can be seen from the above table, when the number of hidden layers is 4 and the number of nodes in each layer is 50, the LSTM network model has the best training effect, and the complexity of the network structure is considered comprehensively, so that the network structure is determined to be 3 hidden layers, and the number of nodes in each layer is 50. The LSTM network loss function selects a cross entropy function, the Optimizer selects an Optimizer, and the learning rate is designed to be exponentially and dynamically reduced along with the training times. And finally, acquiring real-time MIMU output data, calculating a predicted MIMU output error through the prediction model, and using the predicted data for compensating the MIMU output error in real time.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention.
Claims (5)
1. A MIMU error compensation method based on a deep neural network is characterized by comprising the following steps:
step 1, establishing an error model of the MIMU, and determining an input variable and an output variable of a memory neural network at long and short depths according to influence factors of MIMU output errors caused by the analysis of the error model;
step 2, acquiring specific data of the input variable and the output variable in the MIMU working state according to the input variable and the output variable determined in the step 1, and constructing a data set;
step 3, establishing a depth long-term and short-term memory neural network prediction model, and training the depth long-term and short-term memory neural network prediction model by using the data set established in the step 2 to obtain a trained prediction model;
and 4, acquiring the MIMU output data in real time, calculating an output error prediction value by using the trained prediction model, and performing error compensation on the MIMU output data by using the output error prediction value.
2. The MIMU error compensation method based on the deep neural network of claim 1, wherein the step 1 specifically comprises:
respectively establishing angular rate errors epsilon of three orthogonal MEMS gyroscopesaAnd acceleration error ▽ of three orthogonal MEMS accelerometersaThe model analyzes influence factors causing output errors of the MEMS gyroscope and the MEMS accelerometer according to respective error models, so as to determine input variables and output variables of the depth long-time memory neural network;
the error models of the MEMS gyroscope and the MEMS accelerometer are as follows:
wherein epsilon0aAnd Δ0aConstant zero offset vectors, ε, for gyroscopes and accelerometers, respectivelyTaAnd ΔTaRespectively the drift vectors of the gyroscope and accelerometer zero offset with temperature,is a coefficient matrix
Coefficient of (1), ωaIs the angular velocity vector of the gyroscope output,
is a coefficient matrix
Coefficient of (1), faIs the acceleration vector output by the accelerometer,
is a coefficient matrix
The coefficient of (a) to (b),
is a coefficient matrix
Coefficient of (1), eraAnd ΔraFor random error, a ═ x, y, z.
3. The MIMU error compensation method according to claim 1, wherein the input variables and the output variables of the deep long-term and short-term memory neural network are specifically:
the input variables of the depth long-time memory neural network comprise the output of the MEMS gyroscope, the output of the MEMS accelerometer, the temperature of the MEMS gyroscope and the temperature of the MEMS accelerometer;
the output variables of the depth long-time memory neural network comprise an output error prediction value of the MEMS gyroscope and an output error prediction value of the MEMS accelerometer.
4. The MIMU error compensation method based on the deep neural network of claim 1, wherein the specific data of the input variable and the output variable in the MIMU working state is collected by the following specific method:
fixing the MIMU on a rotary table with a temperature control box; starting the rotary table, controlling the inner ring of the rotary table to accelerate to 200 ℃ per second, and simultaneously starting the temperature control box to heat the MIMU; when the speed of the inner ring of the turntable reaches 200 ℃ per second, the outer ring of the turntable is controlled to be accelerated to 200 ℃ per second uniformly, and the heating is stopped when the temperature of the MIMU reaches 80 ℃; keeping the turntable in the current motion state for a preset time; controlling the outer ring of the turntable to uniformly decelerate to 0, and controlling the temperature control box to cool the MIMU; when the speed of the outer ring of the turntable reaches 0, controlling the inner ring of the turntable to uniformly decelerate to 0, and stopping cooling when the temperature of the MIMU reaches-45 ℃; and collecting the data of the MIMU in the whole process, and repeatedly collecting the data until the data volume meets the requirement of the data set.
5. The MIMU error compensation method based on the deep neural network of claim 1, wherein the loss function of the deep temporal memory neural network is a cross entropy function, and the Optimizer is an Optimizer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910961889.2A CN110749337B (en) | 2019-10-11 | 2019-10-11 | MIMU error compensation method based on deep neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910961889.2A CN110749337B (en) | 2019-10-11 | 2019-10-11 | MIMU error compensation method based on deep neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110749337A true CN110749337A (en) | 2020-02-04 |
| CN110749337B CN110749337B (en) | 2023-10-31 |
Family
ID=69277975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910961889.2A Active CN110749337B (en) | 2019-10-11 | 2019-10-11 | MIMU error compensation method based on deep neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110749337B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505543A (en) * | 2020-03-18 | 2020-08-07 | 中国电力科学研究院有限公司 | Method and system for compensating dynamic hysteresis based on recurrent neural network |
| CN111561929A (en) * | 2020-04-26 | 2020-08-21 | 南京工业大学 | Time delay and noise reduction method for vehicle-mounted MEMS inertial sensor |
| CN112580257A (en) * | 2020-12-10 | 2021-03-30 | 东北大学 | Method, device and equipment for constructing prediction model of complex industrial system based on deep learning and storage medium |
| CN113008291A (en) * | 2021-03-15 | 2021-06-22 | 北京信息科技大学 | Data generation method and device, storage medium and electronic device |
| CN113091768A (en) * | 2021-03-12 | 2021-07-09 | 南京理工大学 | MIMU integral dynamic intelligent calibration compensation method |
| CN113503899A (en) * | 2021-07-12 | 2021-10-15 | 清华大学 | Nonlinear error suppression system and sensor based on neural network |
| US11205112B2 (en) | 2019-04-01 | 2021-12-21 | Honeywell International Inc. | Deep neural network-based inertial measurement unit (IMU) sensor compensation method |
| CN113932842A (en) * | 2020-07-13 | 2022-01-14 | 西门子股份公司 | Measuring device |
| CN113984043A (en) * | 2021-09-14 | 2022-01-28 | 哈尔滨工程大学 | Dynamic error correction method for mining inertial navigation system |
| CN115326063A (en) * | 2022-07-07 | 2022-11-11 | 江苏大块头智驾科技有限公司 | Inertial device signal filtering method based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101158588A (en) * | 2007-11-16 | 2008-04-09 | 北京航空航天大学 | MEMS gyroscopes error compensation method for micro satellite based on integration nerval net |
| CN107330149A (en) * | 2017-05-27 | 2017-11-07 | 哈尔滨工业大学 | MIMU Modelling of Random Drift of Gyroscopes Forecasting Methodologies based on ARMA and BPNN built-up patterns |
| CN109188026A (en) * | 2018-10-25 | 2019-01-11 | 北京航空航天大学 | The deep learning method of automatic Calibration suitable for mems accelerometer |
| US20190122373A1 (en) * | 2018-12-10 | 2019-04-25 | Intel Corporation | Depth and motion estimations in machine learning environments |
-
2019
- 2019-10-11 CN CN201910961889.2A patent/CN110749337B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101158588A (en) * | 2007-11-16 | 2008-04-09 | 北京航空航天大学 | MEMS gyroscopes error compensation method for micro satellite based on integration nerval net |
| CN107330149A (en) * | 2017-05-27 | 2017-11-07 | 哈尔滨工业大学 | MIMU Modelling of Random Drift of Gyroscopes Forecasting Methodologies based on ARMA and BPNN built-up patterns |
| CN109188026A (en) * | 2018-10-25 | 2019-01-11 | 北京航空航天大学 | The deep learning method of automatic Calibration suitable for mems accelerometer |
| US20190122373A1 (en) * | 2018-12-10 | 2019-04-25 | Intel Corporation | Depth and motion estimations in machine learning environments |
Non-Patent Citations (2)
| Title |
|---|
| CHANGHUI JIANG等: "A MEMS IMU De-Noising Method Using Long Short Term Memory Recurrent Neural Networks (LSTM-RNN)" * |
| 许德新等: "MEMS 惯性测量组件的温度误差补偿模型研究" * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11205112B2 (en) | 2019-04-01 | 2021-12-21 | Honeywell International Inc. | Deep neural network-based inertial measurement unit (IMU) sensor compensation method |
| CN111505543B (en) * | 2020-03-18 | 2023-02-28 | 中国电力科学研究院有限公司 | Method and system for compensating dynamic hysteresis based on recurrent neural network |
| CN111505543A (en) * | 2020-03-18 | 2020-08-07 | 中国电力科学研究院有限公司 | Method and system for compensating dynamic hysteresis based on recurrent neural network |
| CN111561929A (en) * | 2020-04-26 | 2020-08-21 | 南京工业大学 | Time delay and noise reduction method for vehicle-mounted MEMS inertial sensor |
| CN111561929B (en) * | 2020-04-26 | 2022-05-03 | 南京工业大学 | Time delay and noise reduction method for vehicle-mounted MEMS inertial sensor |
| CN113932842A (en) * | 2020-07-13 | 2022-01-14 | 西门子股份公司 | Measuring device |
| US11668675B2 (en) | 2020-07-13 | 2023-06-06 | Siemens Aktiengesellschaft | Measuring device |
| CN112580257B (en) * | 2020-12-10 | 2022-03-29 | 东北大学 | Method, device and equipment for constructing prediction model of complex industrial system based on deep learning and storage medium |
| WO2022121956A1 (en) * | 2020-12-10 | 2022-06-16 | 东北大学 | Deep-learning-based forecasting model construction method, apparatus and device for complex industrial system, and storage medium |
| CN112580257A (en) * | 2020-12-10 | 2021-03-30 | 东北大学 | Method, device and equipment for constructing prediction model of complex industrial system based on deep learning and storage medium |
| CN113091768A (en) * | 2021-03-12 | 2021-07-09 | 南京理工大学 | MIMU integral dynamic intelligent calibration compensation method |
| CN113091768B (en) * | 2021-03-12 | 2024-04-12 | 南京理工大学 | MIMU integral dynamic intelligent calibration compensation method |
| CN113008291A (en) * | 2021-03-15 | 2021-06-22 | 北京信息科技大学 | Data generation method and device, storage medium and electronic device |
| CN113503899A (en) * | 2021-07-12 | 2021-10-15 | 清华大学 | Nonlinear error suppression system and sensor based on neural network |
| CN113984043A (en) * | 2021-09-14 | 2022-01-28 | 哈尔滨工程大学 | Dynamic error correction method for mining inertial navigation system |
| CN113984043B (en) * | 2021-09-14 | 2024-05-10 | 哈尔滨工程大学 | Dynamic error correction method of mining inertial navigation system |
| CN115326063A (en) * | 2022-07-07 | 2022-11-11 | 江苏大块头智驾科技有限公司 | Inertial device signal filtering method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110749337B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110749337B (en) | MIMU error compensation method based on deep neural network | |
| Abdulshahed et al. | The application of ANFIS prediction models for thermal error compensation on CNC machine tools | |
| CN110039373B (en) | Method and system for predicting thermal deformation of spindle of numerical control machine tool | |
| CN109188026B (en) | Automatic calibration deep learning method suitable for MEMS accelerometer | |
| CN108645427A (en) | The used system-level temperature-compensation method of group of laser based on spline interpolation iterated revision | |
| CN108120451A (en) | Based on silicon micro accerometer temperature-compensation method, the system for improving PSO optimization neural networks | |
| CN113091768B (en) | MIMU integral dynamic intelligent calibration compensation method | |
| CN112596533B (en) | MEMS gyroscope data driving high-precision active disturbance rejection control method | |
| Zhang et al. | Design and implementation of novel fractional-order controllers for stabilized platforms | |
| CN107919813A (en) | Ultrasound electric machine rotating speed control based on fuzzy neural network | |
| CN106092138A (en) | A kind of silicon micro-gyroscope temperature compensation based on microprocessor | |
| CN103954304A (en) | Zero offset short and long-term change value testing method applied to MEMS (Micro-electromechanical Systems) inertia unit | |
| Khan et al. | Analysis and time-delay synchronisation of chaotic satellite systems | |
| Gang-Qiang et al. | Real-time temperature drift compensation method of a MEMS accelerometer based on deep GRU and optimized monarch butterfly algorithm | |
| Vertzberger et al. | Adaptive attitude estimation using a hybrid model-learning approach | |
| Cui et al. | A new calibration method for MEMS accelerometers with genetic algorithm | |
| CN110262242B (en) | Micro gyroscope self-adaptive fractional order sliding mode control method | |
| Xing et al. | Offline calibration for MEMS gyroscope G-sensitivity error coefficients based on the newton iteration and least square methods | |
| Shi et al. | Tilt angle on-line prognosis by using improved sparse LSSVR and dynamic sliding window | |
| Zhou et al. | Parameter Optimization on FNN/PID Compound Controller for a Three‐Axis Inertially Stabilized Platform for Aerial Remote Sensing Applications | |
| Liang et al. | System‐Level Temperature Compensation Method for the RLG‐IMU Based on HHO‐RVR | |
| CN112180122B (en) | MEMS accelerometer turntable-free calibration method based on improved drosophila optimization algorithm | |
| CN117325149B (en) | Gesture adjustment method and system based on Kalman filtering | |
| CN103196446B (en) | Intelligent gyro signal filtering method of trapdown inertial navigation system in high overload environment | |
| Wang et al. | MEMS-IMU automatic calibration system design and implementation |
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 |