CN112653306B - Electric motor dynamic balance process optimization method and system based on industrial AI - Google Patents
Electric motor dynamic balance process optimization method and system based on industrial AI Download PDFInfo
- Publication number
- CN112653306B CN112653306B CN202011510435.2A CN202011510435A CN112653306B CN 112653306 B CN112653306 B CN 112653306B CN 202011510435 A CN202011510435 A CN 202011510435A CN 112653306 B CN112653306 B CN 112653306B
- Authority
- CN
- China
- Prior art keywords
- data
- dynamic balance
- steel sheet
- silicon steel
- model
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02K—DYNAMO-ELECTRIC MACHINES
- H02K15/00—Methods or apparatus specially adapted for manufacturing, assembling, maintaining or repairing of dynamo-electric machines
- H02K15/16—Centering rotors within the stator; Balancing rotors
- H02K15/165—Balancing the rotor
-
- 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
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- Power Engineering (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Control Of Electric Motors In General (AREA)
- Manufacture Of Motors, Generators (AREA)
Abstract
The invention discloses an electric motor dynamic balance process optimization method and system based on industrial AI, which collects process data in the manufacturing process of an electric motor rotor; extracting associated feature data from the process data; inputting the correlation characteristic data into the trained AI model to obtain optimized process parameters; and controlling the production equipment based on the optimized process parameters. The invention utilizes the industrial AI technology, analyzes the process data in the manufacturing process through the trained AI model, and adopts the obtained optimized process parameters to perform feedback control on the production equipment, thereby being capable of controlling the dynamic balance quality of the motor in the manufacturing process and realizing the control on the quality of the motor from the source. Compared with the prior art, the method avoids the remediation after the product is manufactured, optimizes the product manufacturing process and shortens the production cycle of the product.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing, in particular to an electric motor dynamic balance process optimization method and system based on industrial AI.
Background
Machines include a large number of components that perform rotational motion, such as various transmission shafts, spindles, and rotors of electric motors, which are collectively referred to as rotors. In an ideal situation, when the revolving body rotates and does not rotate, the pressure generated on the bearing is the same, and the revolving body is a balanced revolving body, but due to the uneven material or blank defects of the various revolving bodies in the engineering and errors generated in processing and assembling, the centrifugal inertia force generated by each tiny mass point on the revolving body can not be mutually counteracted when the revolving body rotates, and the centrifugal inertia force acts on the machine and the foundation through the bearing to cause vibration, generate noise, accelerate the abrasion of the bearing and shorten the service life of the machine.
Therefore, the dynamic balance parameter of the motor is one of the important technical parameters for measuring the product quality of the motor. In the prior art, the dynamic balance amount is adjusted mainly by adding or removing materials at corresponding positions, and the method can be only carried out after the product is manufactured, and belongs to post-repair of the manufacturing process. The method can increase the manufacturing process of the product and prolong the production cycle of the product.
In summary, how to control the motor dynamic balance in the manufacturing process and further realize the control of the motor quality from the source becomes a problem which needs to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above-mentioned deficiencies of the prior art, the problems actually solved by the present invention include: how to control the motor dynamic balance in the manufacturing process, thereby realizing the control of the motor quality from the source.
The invention adopts the following technical scheme:
the electric motor dynamic balance process optimization method based on the industrial AI comprises the following steps:
s1, collecting process data in the manufacturing process of the motor rotor;
s2, extracting associated characteristic data from the process data;
s3, inputting the associated characteristic data into the trained AI model to obtain optimized process parameters;
and S4, controlling the production equipment based on the optimized process parameters.
Preferably, the process data comprises silicon steel sheet material performance data, silicon steel sheet nominal size processing data, rotor silicon steel sheet assembly data, silicon steel sheet press-fitting data and environment variables.
Preferably, the training method of the AI model in step S3 is as follows:
s100, acquiring historical process data and historical dynamic balance data;
s200, determining correlation factors influencing dynamic balance data and weights corresponding to the correlation factors based on historical process data and historical dynamic balance data;
s300, screening historical dynamic balance data meeting dynamic balance requirements as qualified dynamic balance data, and extracting training process data corresponding to the qualified dynamic balance data from the historical process data on the basis of the correlation factors;
s400, generating a training sample based on the training process data and the weight corresponding to the correlation factor;
s500, reducing the dimension of the training sample;
s600, training the AI model by using the data after dimension reduction until the output result meets the preset requirement.
Preferably, the AI model comprises a short-term dependent neural network and/or a long-term dependent neural network, and the parameters of the AI model are optimized by a genetic algorithm in the training process.
Electric motor dynamic balance process optimization system based on industry AI includes data acquisition module, data processing module, technology optimization module and control execution module, wherein:
the data acquisition module is used for acquiring process data in the manufacturing process of the motor rotor;
the data processing module is used for extracting associated characteristic data from the process data;
the process optimization module is used for inputting the associated characteristic data into the trained AI model to obtain optimized process parameters;
and the control execution module is used for controlling the production equipment based on the optimized process parameters.
Preferably, the process data comprises silicon steel sheet material performance data, silicon steel sheet nominal size processing data, rotor silicon steel sheet assembly data, silicon steel sheet press-fitting data and environment variables.
Preferably, the training system further comprises an AI model training module, the AI model training module is used for training the AI model, and the training method of the AI model is as follows:
acquiring historical process data and historical dynamic balance data;
determining a correlation factor influencing the dynamic balance data and a weight corresponding to the correlation factor based on the historical process data and the historical dynamic balance data;
screening historical dynamic balance data meeting dynamic balance requirements as qualified dynamic balance data, and extracting training process data corresponding to the qualified dynamic balance data from the historical process data based on the correlation factors;
generating a training sample based on the training process data and the weight corresponding to the association factor;
reducing the dimension of the training sample;
and training the AI model by using the data after dimension reduction until the output result meets the preset requirement.
Preferably, the AI model comprises a short-term dependent neural network and/or a long-term dependent neural network, and the parameters of the AI model are optimized by a genetic algorithm in the training process.
In summary, the invention utilizes the industrial AI technology, analyzes the process data in the manufacturing process through the trained AI model, and performs feedback control on the production equipment by using the obtained optimized process parameters, so that the dynamic balance quality of the motor can be controlled in the manufacturing process, and the control on the quality of the motor from the source is realized. Compared with the prior art, the method avoids the remedy after the product is manufactured, optimizes the product manufacturing process and shortens the production cycle of the product.
Drawings
For purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made in detail to the present invention as illustrated in the accompanying drawings, in which:
FIG. 1 is a flow chart of a method for optimizing an industrial AI-based motorized balancing process;
FIG. 2 is a flow chart of AI model training in the industrial AI-based electric motor dynamic balance process optimization method disclosed by the invention.
Fig. 3 is a schematic diagram of the industrial AI-based electric motorized balancing process optimization system disclosed herein.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, the invention discloses an electric dynamic balance process optimization method based on industrial AI, comprising the following steps:
s1, collecting process data in the manufacturing process of the motor rotor;
through the IOT transformation to the silicon steel sheet production process of the motor, the corresponding data acquisition device can be deployed. After data is acquired, due to the dispersibility of the information acquisition nodes and the size of information flow, data transmission mainly takes 5G + Ethernet as a transmission form. By the form, the scattered node data are completely, safely and timely transmitted to the Internet of things end and are connected to the Internet of things platform under the industrial Internet system architecture for subsequent data model processing.
S2, extracting associated characteristic data from the process data;
in the invention, for the process data acquired in real time, the way of subsequently generating the training sample can be adopted, and the correlation characteristic data can be extracted by utilizing the correlation factor.
S3, inputting the associated characteristic data into the trained AI model (neural network) to obtain optimized process parameters;
the input of the trained AI model is the process data acquired in real time, and the output is the optimized process parameters which can ensure the motor dynamic balance parameters to be qualified.
And S4, controlling the production equipment based on the optimized process parameters.
The production equipment comprises a punch press, a silicon steel sheet stacking machine, a glue filling machine, a rotating shaft pressing machine and the like.
When the revolving body rotates, the mass center is not coincident with the axis, so that the rotor is influenced by asymmetric force when rotating, periodic vibration is generated, and the magnitude of the asymmetric force is the dynamic unbalance.
The main structure of the motor rotor is composed of silicon steel sheets, and due to the existing processing technique and equipment conditions, the processing quality space distribution of the silicon steel sheets is different, and the processing error is the main reason of dynamic unbalance.
The production data of the dynamic unbalance of the motor rotor influenced by the silicon steel sheets are collected and processed, then the correlation analysis is carried out on the dynamic unbalance and the dynamic unbalance detection result, a corresponding mathematical model is established, and the correlation of the data is found by using a model algorithm, so that the production process is guided to be optimized, and the production process control method with the minimum unbalance is found.
The invention utilizes the industrial AI technology, analyzes the process data in the manufacturing process through the trained AI model, and adopts the obtained optimized process parameters to perform feedback control on the production equipment, thereby being capable of controlling the dynamic balance quality of the motor in the manufacturing process and realizing the control on the quality of the motor from the source. Compared with the prior art, the method avoids the remedy after the product is manufactured, optimizes the product manufacturing process and shortens the production cycle of the product.
In specific implementation, the process data comprises silicon steel sheet material performance data, silicon steel sheet nominal size processing data, rotor silicon steel sheet assembly data, silicon steel sheet press-mounting data and environment variables.
In the invention, the performance data of the silicon steel sheet material comprises material components and mechanical indexes; the nominal size processing data of the silicon steel sheet comprises the position, the directionality and the processed weight of the silicon steel sheet in the stamping process; the rotor silicon steel sheet assembly data comprises an assembly overlapping mode, a mutual overlapping assembly angle and a positive side and a negative side during silicon steel sheet assembly; the process data of the silicon steel sheet press-mounting equipment comprise glue injection pressure, glue injection temperature, glue injection amount and environment variables comprising temperature, humidity and voltage.
As shown in fig. 2, in implementation, the AI model training method in step S3 is as follows:
s100, acquiring historical process data and historical dynamic balance data;
the invention uses the historical process data of the motor which is manufactured and the historical dynamic balance data (amplitude, frequency, phase and the like) of the motor which is manufactured and collected by a dynamic balance machine for the training of the AI model.
S200, determining correlation factors influencing dynamic balance data and weights corresponding to the correlation factors based on historical process data and historical dynamic balance data;
the correlation factor and the weight relationship can be obtained by combing these data and performing mathematical model mapping of the industrial mechanism by the machining process of the electrodynamic rotor. In the invention, the determined motor rotor processing industrial mechanism model can be subjected to industrial internet PaaS component packaging based on a micro-service frame and a container technology; and encapsulated and embedded in the industrial internet platform. According to the motor dynamic balance industrial mechanism control, aiming at different processing technologies, industrial mechanism components of various motor rotor processing procedures are packaged.
In addition, since the data in the motor manufacturing process is various, in order to facilitate training and subsequent use of the model, the data may be classified, a pre-constructed clustering model is called to perform clustering processing on the data (for example, data having an influence on amplitude, data having an influence on frequency, data having an influence on phase, and the like), and abnormal information is discarded.
S300, screening historical dynamic balance data meeting dynamic balance requirements as qualified dynamic balance data, and extracting training process data corresponding to the qualified dynamic balance data from the historical process data based on the correlation factors;
s400, generating a training sample based on the training process data and the weight corresponding to the correlation factor;
s500, reducing the dimension of the training sample;
due to the complexity of the production condition, the acquired original data has high dimensionality, which affects subsequent processing. The sample data after dimensionality reduction is Z (i) ∈R M ' ×T The dimension of the data is reduced from M to M'. The Z sample data belongs to a real number set of M multiplied by T, R represents the real number set, and M' multiplied by T represents the number of rows and columns of the matrix.
S600, training the AI model by using the data after dimension reduction until the output result meets the preset requirement.
In specific implementation, the AI model comprises a short-term dependence neural network and/or a long-term dependence neural network, and parameters of the AI model are optimized by adopting a genetic algorithm in a training process.
In terms of AI models, the present invention selects three different models to address different production scenarios. For the short-term dependence problem, an RNN model is adopted to facilitate implementation, and for the long-term dependence problem, an algorithm adopts LSTM or GRU to adapt to different numbers of parameters to be optimized. In the aspect of network hyper-parameter selection, a proper Genetic Algorithm (GA) is selected, the output error of the model is taken as an optimization target, the preset requirement is met until the error is smaller than a preset threshold value, and crossing and variation parameters are adjusted to select more optimal hyper-parameters, so that a better training effect is achieved. The calculation of the training session is as follows.
Wherein F (-) is a network model, θ is a network weight, Loss (-) is a Loss function, and Y (-) is a network model (i) For model output, the GA continuously adjusts the hyper-parameters according to the training result of each model, so that the model evolves to achieve a better result.
As shown in fig. 3, the invention also discloses an electric motor dynamic balance process optimization system based on industrial AI, which comprises a data acquisition module, a data processing module, a process optimization module and a control execution module, wherein:
the data acquisition module is used for acquiring process data in the manufacturing process of the motor rotor;
the data processing module is used for extracting associated characteristic data from the process data;
the process optimization module is used for inputting the associated characteristic data into the trained AI model to obtain optimized process parameters;
and the control execution module is used for controlling the production equipment based on the optimized process parameters.
In specific implementation, the process data comprises silicon steel sheet material performance data, silicon steel sheet nominal size processing data, rotor silicon steel sheet assembly data, silicon steel sheet press-mounting data and environment variables.
When the method is specifically implemented, the method further comprises an AI model training module, wherein the AI model training module is used for training an AI model, and the AI model training method comprises the following steps:
acquiring historical process data and historical dynamic balance data;
determining a correlation factor influencing the dynamic balance data and a weight corresponding to the correlation factor based on the historical process data and the historical dynamic balance data;
screening historical dynamic balance data meeting dynamic balance requirements as qualified dynamic balance data, and extracting training process data corresponding to the qualified dynamic balance data from the historical process data based on the correlation factors;
generating a training sample based on the training process data and the weight corresponding to the association factor;
reducing the dimension of the training sample;
and training the AI model by using the data after dimension reduction until the output result meets the preset requirement.
In specific implementation, the AI model comprises a short-term dependence neural network and/or a long-term dependence neural network, and parameters of the AI model are optimized by adopting a genetic algorithm in a training process.
In conclusion, the invention adopts the artificial intelligence AI technology and the edge control technology to solve the manufacturing control problem of the motor dynamic balance. The method overcomes the defect of a traditional mechanical control mode with a single process point, and is digital control over the whole production process based on a 5G technology and an IOT (Internet of things).
The traditional dynamic unbalance control is a control mode of passive existing fact. The invention is a dynamic control process for the equipment parameters causing dynamic unbalance in the production process, and is an active control mode.
The invention can dynamically pre-judge the quality index of the dynamic balance mass in the production process of the motor and can avoid the quality problem of the product batch.
Finally, it is noted that the above-mentioned embodiments illustrate rather than limit the invention, and that, while the invention has been described with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (4)
1. The electric motor dynamic balance process optimization method based on the industrial AI is characterized by comprising the following steps of:
s1, collecting process data in the manufacturing process of the motor rotor; after the process data are collected, according to the dispersity of the information collection nodes and the size of information flow, the data transmission takes 5G and Ethernet as transmission forms, and the scattered node data are completely, safely and timely transmitted to an Internet of things end through the transmission forms and are connected to an Internet of things platform under an industrial Internet system architecture for subsequent data model processing; the process data comprises silicon steel sheet material performance data, silicon steel sheet nominal size processing data, rotor silicon steel sheet assembly data, silicon steel sheet press-mounting data and environment variables; wherein, the performance data of the silicon steel sheet material comprises material components and mechanical indexes; the nominal size processing data of the silicon steel sheet comprises the position, the directionality and the processed weight of the silicon steel sheet in the stamping process; the rotor silicon steel sheet assembly data comprises an assembly overlapping mode, an overlapping assembly angle and a positive side and a negative side during silicon steel sheet assembly; the press mounting data of the silicon steel sheet comprises glue injection pressure, glue injection temperature and glue injection amount, and the environmental variables comprise temperature, humidity and voltage;
s2, extracting associated characteristic data from the process data; for the process data acquired in real time, a mode of subsequently generating a training sample is adopted, and correlation characteristic data are extracted by using a correlation factor;
s3, inputting the associated characteristic data into the trained AI model to obtain optimized process parameters; the input of the trained AI model is process data acquired in real time, and the output is optimized process parameters which can ensure that motor dynamic balance parameters are qualified; the AI model training method comprises the following steps:
s100, acquiring historical process data and historical dynamic balance data;
s200, determining correlation factors influencing dynamic balance data and weights corresponding to the correlation factors based on historical process data and historical dynamic balance data;
s300, screening historical dynamic balance data meeting dynamic balance requirements as qualified dynamic balance data, and extracting training process data corresponding to the qualified dynamic balance data from the historical process data based on the correlation factors;
s400, generating a training sample based on the training process data and the weight corresponding to the correlation factor;
s500, reducing the dimension of the training sample;
s600, training the AI model by using the data after dimension reduction until an output result meets a preset requirement;
and S4, controlling the production equipment based on the optimized process parameters, namely, performing feedback control on the production equipment by using the obtained optimized process parameters.
2. The industrial AI-based electric motorized balancing process optimization method according to claim 1, characterized in that the AI model comprises a short-term dependent neural network and/or a long-term dependent neural network, and a genetic algorithm is used to optimize AI model parameters during the training process.
3. Electric motor dynamic balance process optimization system based on industry AI, characterized in that, including data acquisition module, data processing module, technology optimization module and control execution module, wherein:
the data acquisition module is used for acquiring process data in the manufacturing process of the motor rotor; after the process data are collected, according to the dispersity of the information collection nodes and the size of information flow, the data transmission takes 5G and Ethernet as transmission forms, and the scattered node data are completely, safely and timely transmitted to an Internet of things end through the transmission forms and are connected to an Internet of things platform under an industrial Internet system architecture for subsequent data model processing; the process data comprises silicon steel sheet material performance data, silicon steel sheet nominal size processing data, rotor silicon steel sheet assembly data, silicon steel sheet press-mounting data and environment variables; wherein, the performance data of the silicon steel sheet material comprises material components and mechanical indexes; the nominal size processing data of the silicon steel sheet comprises the position, the directionality and the processed weight of the silicon steel sheet in the stamping process; the rotor silicon steel sheet assembly data comprises an assembly overlapping mode, an overlapping assembly angle and a positive side and a negative side during silicon steel sheet assembly; the press mounting data of the silicon steel sheet comprises glue injection pressure, glue injection temperature and glue injection amount, and the environmental variables comprise temperature, humidity and voltage;
the data processing module is used for extracting associated characteristic data from the process data; for the process data acquired in real time, a mode of subsequently generating a training sample is adopted, and correlation characteristic data are extracted by using a correlation factor;
the process optimization module is used for inputting the associated characteristic data into the trained AI model to obtain optimized process parameters; the input of the trained AI model is process data acquired in real time, and the output is optimized process parameters which can ensure that motor dynamic balance parameters are qualified;
the control execution module is used for controlling the production equipment based on the optimized process parameters, namely, the obtained optimized process parameters are adopted to perform feedback control on the production equipment;
the training system further comprises an AI model training module, wherein the AI model training module is used for training an AI model, and the training method of the AI model comprises the following steps:
acquiring historical process data and historical dynamic balance data;
determining a correlation factor influencing the dynamic balance data and a weight corresponding to the correlation factor based on the historical process data and the historical dynamic balance data;
screening historical dynamic balance data meeting dynamic balance requirements as qualified dynamic balance data, and extracting training process data corresponding to the qualified dynamic balance data from the historical process data on the basis of the correlation factors;
generating a training sample based on the training process data and the weight corresponding to the association factor;
reducing the dimension of the training sample;
and training the AI model by using the data after dimension reduction until the output result meets the preset requirement.
4. The industrial AI-based motorized balancing process optimization system according to claim 3, wherein the AI model includes a short-term dependent neural network and/or a long-term dependent neural network, and wherein genetic algorithms are used during the training process to optimize the AI model parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011510435.2A CN112653306B (en) | 2020-12-18 | 2020-12-18 | Electric motor dynamic balance process optimization method and system based on industrial AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011510435.2A CN112653306B (en) | 2020-12-18 | 2020-12-18 | Electric motor dynamic balance process optimization method and system based on industrial AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112653306A CN112653306A (en) | 2021-04-13 |
| CN112653306B true CN112653306B (en) | 2022-08-23 |
Family
ID=75355257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011510435.2A Active CN112653306B (en) | 2020-12-18 | 2020-12-18 | Electric motor dynamic balance process optimization method and system based on industrial AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112653306B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117389209A (en) * | 2023-09-06 | 2024-01-12 | 苏州数设科技有限公司 | Target compensation value determining method and device, electronic equipment and readable storage medium |
| CN117519042B (en) * | 2023-11-30 | 2024-04-26 | 天瑞集团信息科技有限公司 | Intelligent control method, system and storage medium for cement production based on AI technology |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103931099A (en) * | 2011-09-15 | 2014-07-16 | 赛乐姆知识产权控股有限责任公司 | Motor regulation for a synchronous motor |
| DE202019106180U1 (en) * | 2019-11-06 | 2019-12-02 | Yin-Shen Hsiung | Expandable AI power artificial intelligence, multi-function motor with multiple stators and system device for power generation |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100436050C (en) * | 2007-06-07 | 2008-11-26 | 浙江大学 | Automatic positioning device for full automatic balancing machine cutting point |
| CN104215395B (en) * | 2014-09-09 | 2016-11-23 | 中国石油大学(北京) | The detection method of a kind of rotor unbalance fault and device |
| CN105678404B (en) * | 2015-12-30 | 2019-07-23 | 东北大学 | Based on online shopping electricity and dynamically associate the micro-grid load forecasting system and method for the factor |
| US11031009B2 (en) * | 2019-04-10 | 2021-06-08 | Hitachi, Ltd. | Method for creating a knowledge base of components and their problems from short text utterances |
| CN110826617A (en) * | 2019-10-31 | 2020-02-21 | 中国人民公安大学 | Situation element classification method and training method and device of model thereof, and server |
| CN111665761B (en) * | 2020-06-23 | 2023-05-26 | 上海一旻成锋电子科技有限公司 | Industrial control system and control method |
-
2020
- 2020-12-18 CN CN202011510435.2A patent/CN112653306B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103931099A (en) * | 2011-09-15 | 2014-07-16 | 赛乐姆知识产权控股有限责任公司 | Motor regulation for a synchronous motor |
| DE202019106180U1 (en) * | 2019-11-06 | 2019-12-02 | Yin-Shen Hsiung | Expandable AI power artificial intelligence, multi-function motor with multiple stators and system device for power generation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112653306A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112653306B (en) | Electric motor dynamic balance process optimization method and system based on industrial AI | |
| Tran et al. | Milling chatter detection using scalogram and deep convolutional neural network | |
| CN108918137B (en) | Gear box fault diagnosis device and method based on improved WPA-BP neural network | |
| CN106980822A (en) | A kind of rotary machinery fault diagnosis method learnt based on selective ensemble | |
| CN109116811A (en) | Machine learning device and method, Servocontrol device, servo-control system | |
| Pinheiro et al. | Vibration analysis in turbomachines using machine learning techniques | |
| CN112883994A (en) | Rotating machinery variable working condition fault diagnosis method with balanced distribution adaptation | |
| CN109190270A (en) | A kind of double balancing disk balance Control Scheme methods based on APSO-BP | |
| CN112445181A (en) | Machine learning device, servo control system, and machine learning method | |
| CN113485123A (en) | Frequency domain adaptive iterative learning control method for small-stroke nanoscale motion platform | |
| Rathore et al. | Framework for imbalanced fault diagnosis of rolling bearing using autoencoding generative adversarial learning | |
| CN114390085B (en) | Grain processing industry internet structure and edge controller thereof | |
| CN112464526B (en) | Intelligent optimization method for loading path of spinning roller for mandrel-free spinning forming | |
| CN117234165A (en) | Automatic pipeline control system and control method based on computer vision | |
| CN117345527A (en) | AI-based wind driven generator rotating speed optimization system, AI-based wind driven generator rotating speed optimization method and electronic equipment | |
| CN117348558A (en) | Filter pressing production closed-loop modeling and optimizing control method based on big data analysis | |
| CN115081330A (en) | Virtual and real data mirror image updating method for digital twin model of gear transmission system | |
| Lu et al. | An automated bearing fault diagnosis using a self-normalizing convolutional neural network | |
| CN115434870A (en) | Method, device and equipment for processing vibration data of wind power generation set and storage medium | |
| Liu et al. | Research on predictive maintenance technology of stepping motor based on load value analysis | |
| Tseng et al. | Intelligent Motor Fault Diagnosis Using Dynamic Structural Neural Networks with Bat-Algorithm Based Terminal Attractor Learning | |
| CN115446244B (en) | Control method and system for forging stacker crane of electric automobile motor spindle | |
| CN118224111A (en) | Axial flow fan design and verification method | |
| CN117896384B (en) | Internet of things communication method, device, equipment and storage medium | |
| CN115310498B (en) | Neural network-based rotating machine fault classification method under variable rotating speed working condition |
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 |