CN110378257B - Artificial intelligent model whole process automation system - Google Patents
Artificial intelligent model whole process automation system Download PDFInfo
- Publication number
- CN110378257B CN110378257B CN201910598739.XA CN201910598739A CN110378257B CN 110378257 B CN110378257 B CN 110378257B CN 201910598739 A CN201910598739 A CN 201910598739A CN 110378257 B CN110378257 B CN 110378257B
- Authority
- CN
- China
- Prior art keywords
- module
- scale
- dial
- image
- numerical value
- 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
- 238000004801 process automation Methods 0.000 title claims description 12
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 34
- 230000005540 biological transmission Effects 0.000 claims abstract description 20
- 238000004519 manufacturing process Methods 0.000 abstract description 17
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Abstract
The invention relates to an artificial intelligent model whole-process automatic system which is used for realizing intelligent dial data identification and aims at an instrument dial and has the function of automatically generating a data set. The system comprises: the device comprises a scale module, a transmission module, a scale feedback module and an image acquisition module, wherein the transmission module is connected with the scale module and the scale feedback module, the numerical value indicated by the scale module and the numerical value detected by the scale feedback module can establish a one-to-one correspondence, the image acquisition module is used for obtaining an image of the scale module, and the numerical value detected by the scale feedback module is used for marking the image of the scale module. The system is used for whole-process training education of artificial intelligence, and automatic integrated management of various instrument and meter dial identifications and monitoring data of safety production enterprises.
Description
Technical Field
The invention relates to an artificial intelligent model whole process automation system, in particular to an artificial intelligent model whole process automation system which is used for the whole process training of artificial intelligence aiming at instrument and meter dials and is provided with an automatic generation data set so as to realize intelligent identification of dial data.
Background
In recent years, artificial intelligence learning has been rapidly developed, and is widely used in various industries, and along with this, related education of artificial intelligence learning has become more popular. However, all artificial intelligence learning is based on a large number of data sets, and the effect of artificial intelligence learning is proportional to the size and accuracy of the data sets used for training. At present, a learner after artificial intelligence training can understand a program and debug parameters to improve the accuracy of a model, and can not participate in sampling, processing and establishing of a data set because the existing data set training is directly called, so that a very important loop is lacked, and the learner after training lacks the capability of using artificial intelligence to solve the actual problem, so that the learner cannot learn to use the model. Generating a large and accurate data set often requires a significant amount of time and labor costs that prevent full-chain education for artificial intelligence, so developing a method for quickly and accurately generating data sets is an urgent task for artificial intelligence education.
Meanwhile, a large number of off-line instruments and meters are reserved in many production enterprises at present, the meters cannot collect data remotely and online, and the data must be collected in a mode of taking special person on duty readings, so that great cost is generated when the meters are completely replaced. In addition, various meters collect data online through communication, and great trouble is brought to data integration due to different communication modes. Therefore, the image information collected by the camera is used for universally identifying various meter data, and the method has great value in the current practical production environment, does not need to put in a great deal of capital and technical improvement, and does not need to consider the data format of each meter. However, various gauges are in various forms, and great effort is required to build a data set to train an artificial intelligence model, so that the data set is automatically generated according to different gauges to train an identified artificial intelligence model, and the method has a great effect on actual production.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a method for automatically generating and calibrating a data set. The method for quickly establishing a large number of reliable data sets is beneficial to solving the problem of complex process of generating the data sets before, so that the process of establishing the data sets can be added into popular education of artificial intelligence learning, students are helped to comprehensively know the whole artificial intelligence learning process, a learning chain is more complete and rich in practicability and logicality, learning cost is reduced, and popularization and perfection of the artificial intelligence learning education are facilitated.
On the other hand, for the safety production enterprises, a large number of instrument meters exist, if the readings of the meters are all manually read, a lot of human resources are consumed, and the error rate of workers in processing a large number of meter disk data at the same time is greatly increased; after the enterprises have the way of quickly and accurately generating the data sets, the readings of the instruments can be read and monitored through an artificial intelligent model trained based on the generated data sets, and the human resources in the past are replaced, so that the human cost and errors in production required by the enterprises can be greatly reduced, and the production efficiency is improved. Meanwhile, dial data read by using the artificial intelligent model can be used as online monitoring data, and is convenient to integrate into an automatic management flow.
An artificial intelligence model whole process automation system, comprising: the device comprises a scale module, a transmission module, a scale feedback module and an image acquisition module, wherein the transmission module is connected with the scale module and the scale feedback module, the numerical value indicated by the scale module and the numerical value detected by the scale feedback module can establish a one-to-one correspondence, the image acquisition module is used for obtaining an image of the scale module, and the numerical value detected by the scale feedback module is used for marking the image of the scale module.
The transmission module comprises: the motor control module controls the motor sub-module to move, and the motor sub-module is provided with double output ends and is respectively connected with the scale module and the scale feedback module.
The image acquisition module can adjust the environmental illumination when obtaining the scale module image, can also adjust the angle, the distance with the scale module, obtain and mark the scale module image of different illumination, angle, distance parameter, mark scale module image of scale numerical value and parameter and constitute the dataset of artificial intelligence model training, this dataset divide into: training sets and test sets.
The scale feedback module and the scale module have the same and synchronous operation mode; the scale module is an instrument meter dial; the scale feedback module adopts a potentiometer which rotates or moves linearly, and the resistance value measured by the scale feedback module is used for indicating the scale value of the scale module.
The image acquisition module comprises: the image acquisition program controls the camera to obtain an image, normalizes the image, and converts the detection value transmitted by the scale feedback module into the value of the scale module to mark the image.
The transmission module includes: the motor control module adjusts the resistance of the rotary potentiometer to a state through the motor sub-module, measures the actual resistance of the rotary potentiometer in the state, and obtains the indication value of the gauge dial in the state according to the corresponding relation between the actual resistance and the gauge dial; the image acquisition module starts to shoot a dial of the gauge, processes the size and the light of the image according to the setting to obtain a standard uniform image, and marks the marked dial image of the state according to the dial value corresponding to the measured value of the rotary potentiometer; the marked dial image of the meter becomes one element of a data set required for training the artificial intelligent model, and in this way, an image covering all dial information states is generated and automatically marked, and a complete data set is established.
The transmission module comprises a motor control module and a motor sub-module, the motor control module controls the motor sub-module to move, the motor sub-module of the transmission module drives the scale module and the scale feedback module to move, and the motor control module continuously adjusts the motor sub-module to move according to a comprehensive interval strategy, so that an image of each scale state of the scale module is obtained; measuring the resolution of the motor submodule driving the scale module and the scale feedback module; and a comprehensive interval strategy, wherein the comprehensive interval strategy comprises each scale state of the scale module, and the interval is determined according to parameters of the motor submodule.
The artificial intelligence whole process training method of the artificial intelligence model whole process automation system is characterized by comprising the following steps: manufacturing a data set, constructing an artificial intelligent training model, and adjusting the parameter optimization performance of the training model; as the basis of the data set production of the starting link, a scale module is selected as an image recognition target, the image of the scale module is marked by the numerical value detected by the scale feedback module, and a mode of automatically generating the data set is constructed by utilizing the transmission module; different illumination, distance and angle parameters can be selected to automatically generate different data sets; after the data set is automatically manufactured, an artificial intelligent model training platform is selected, and an artificial intelligent training model is constructed; starting artificial intelligence model training based on the produced data set; and continuously adjusting the parameter optimization performance of the training model according to the training result until the requirement is met.
The method for identifying the scales of the gauges of the whole process automation system of the artificial intelligent model is characterized in that various gauges display production control flows, and the dials of the gauges are used as scale modules for reading; the output forms of various meters are different, the data formats are different, the communication modes are also different, and the communication integration mode of remotely reading data on line is replaced by an image recognition mode; the image identification of the gauge dial adopts a mode of constructing an artificial intelligence training model; the data set required by the artificial intelligence training model is generated in an automated manner; marking an image of a dial of the meter with a numerical value detected by a scale feedback module, and constructing a mode of automatically generating a data set by using a transmission module; different illumination, distance and angle parameters can be selected to automatically generate different data sets; after the data set is automatically manufactured, an artificial intelligent model training platform is selected, and an artificial intelligent training model is constructed; starting artificial intelligence model training based on the produced data set; and continuously adjusting the parameter optimization performance of the training model according to the training result until the numerical value of the gauge dial is correctly identified.
When more than one meter scale is identified, respectively automatically establishing marked data sets according to a meter scale identification method, and respectively training artificial intelligent identification models; in practical application, the acquired image is firstly segmented, each meter is segmented, and then the trained artificial intelligent model is used for identification.
For training education for artificial intelligence learning, there is a need for a system that can generate data sets in a simple, fast, and accurate manner. If the existing data set is selected to be directly used in education, the generation process of the data set required in education is lacked, and a key step is lacked, so that the popular education of artificial intelligence learning is incomplete. This requires a more advanced method to automatically generate the data set, thus making the educational process more complete.
For safety production enterprises, the production process generally needs to monitor various instrument panels to control the production process. If the traditional manual meter reading mode is used, the labor cost required by a factory is increased, errors and misjudgment exist in the manual meter reading process, and the production efficiency is reduced; if the data of the dial of the instrument and meter are read by using an online detection and communication mode, however, the output modes of various meters are different, the data modes are different, the communication integration mode is complex, the realization difficulty is high, and a plurality of meters cannot realize an online reading mode; if the general image recognition is adopted, complex image processing is required to be carried out according to the dial form of each meter, and the implementation method is not general; the artificial intelligence method is used for monitoring the instrument, a huge and accurate database is required to be established for training the identification model, and a great deal of time and manpower are required to be spent for establishing a training data set for manually calibrating different instrument states. An advanced method is required to automatically generate training data sets of instruments and meters, so that time is reduced and production cost is saved.
Aiming at the popularization education of artificial intelligence learning, the market lacks related education kits, which is not beneficial to the popularization of the artificial intelligence learning education. Aiming at dial reading and monitoring in industrial production, a low-cost, high-efficiency and general method for monitoring and managing a large number of different dials is lacking.
Compared with the prior art, the invention has the following beneficial effects: first, in the whole process training education for artificial intelligence learning, from the problem to be solved, include: collecting, processing, establishing and artificial intelligence model training of a data set, and enhancing the learning ability of a learner; secondly, the method solves the difficult problems of on-line reading and data integration of a large number of instruments and meters for production enterprises, and is convenient for establishing the identification and monitoring of an automatic process.
Drawings
FIG. 1 is an artificial intelligence model overall process automation system.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the attached drawings: the embodiment is implemented on the premise of the technical scheme of the invention, and detailed implementation modes and processes are given, but the protection scope of the invention is not limited to the following embodiment. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.
As shown in fig. 1, the artificial intelligence model whole process automation system includes: scale module, transmission module, scale feedback module, image acquisition module, transmission module includes again: the motor sub-module adopts a direct current motor with a speed reduction structure, the double output ends of the transmission module are realized by adopting a gear structure, the motor sub-module in the transmission module is connected with the scale module and the scale feedback module in a gear mode, and the transmission ratio of the scale module to the scale feedback module is 10:1; the dial of the scale module is provided with 60 scales, and each scale represents a numerical value of 1; the scale feedback module adopts a 10-turn rotary potentiometer, the resistance value of the rotary potentiometer is 6k omega plus or minus 5%, the precision is plus or minus 10 omega, and the linearity is plus or minus 0.25%; the resistance value of 6k omega of the rotary potentiometer is in one-to-one correspondence with 60 scales of the dial. The dial and the image acquisition module are at an angle of 45 degrees, and the ambient light is 2lux.
The motor control module of the transmission module controls the movement of the motor sub-module, the motor sub-module of the transmission module drives the scale module and the scale feedback module to move, and the motor control module continuously adjusts the movement of the motor sub-module according to a comprehensive interval strategy, so that the state of each scale indicated by the dial is obtained; taking the dial shown in fig. 1 as an example, 60 scales of the dial correspond to the 6k omega resistance value of the rotary potentiometer, one scale corresponds to the 100 omega resistance value, the precision of the rotary potentiometer is +/-10 omega, so 20 omega is selected as a reference, the identifiable resolution of one scale is set to be 5, five states are selected for each scale to acquire an image, and the dial is set to 300 states in total; the state of the dial is represented by the resistance value of the rotary potentiometer; if the motor control module gives the resistance value of the rotary potentiometer, the resistance values are as follows in sequence: 20. 40, 60, 80, …, 6000; the motor sub-module is used as a power component, and the rotation angle is very small and difficult to be realized accurately, so that the optimal given resistance value embodiment 1 of the motor control module is as follows: 100. 200, …, 6000; 20. 120, 220, …, 5920; 40. 140, 240, …, 5940; 60. 160, 260, …, 5960; 80. 180, 280, …, 5980.
The state of the dial is represented by the resistance value of the rotary potentiometer, the motor control module adjusts the resistance value of the rotary potentiometer to a state through the motor sub-module, the actual resistance value of the state is measured, and the dial indication value of the state is obtained according to the corresponding relation between the actual resistance value and the dial of the scale module; the image acquisition module starts to shoot the dial, processes the size and the light of the photo according to the setting to obtain a standard uniform image, and marks the dial photo in the state according to the dial value corresponding to the measured value of the rotary potentiometer; the marked dial photo becomes one element of a data set required by training the artificial intelligent model, and by the method, an image covering all dial information states is generated and automatically marked, so that a complete data set is established; based on the artificial intelligence training platform PaddlePaddle, the data set is uploaded, the artificial intelligence identification model for identifying the dial can be trained according to the set artificial intelligence model parameters, and the dial identification model with high accuracy can be obtained rapidly and conveniently by debugging the artificial intelligence model parameters and setting the model structure, so that the dial reading of the meter dial can be identified rapidly and accurately.
In example 2, the scale module is divided into two parts, the first part is 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, the second part is a dial with marks of 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, and five scales between 0 and 10 are used, namely each scale represents a value of 2; the scale feedback module adopts 10 circles of high-precision rotary potentiometers with the total resistance value of 10kΩ; each scale corresponds to a resistance value of 20Ω; the dial of the meter has 500 states, the motor control module gives the 500 states according to a comprehensive interval giving method, the image acquisition module obtains the image of the dial of the meter in each state, and marks the image according to the scale value corresponding to the detection resistance value of the scale feedback module.
The whole process automation system of the artificial intelligent model shown in fig. 1, a motor control module adopts NI myRIO and an integrated PID feedback algorithm to control a motor submodule; the high-precision rotary potentiometer adopts a 10-circle measuring range of 6kΩ, and can be matched with most of meter dials, so that the corresponding relation between the resistance and the scale value is established; the motor submodule comprises a direct current motor and a speed reducer, and the parameters of the direct current motor are as follows: rated voltage 5V, rated rotation speed 6000r/m, and the reduction ratio of the reduction gear is 10:1; the rotary output shaft of the motor sub-module can have two ends.
The high precision rotary potentiometer as shown in fig. 1 has three pins: the middle terminal, one end and the other end are connected with 5V voltage, one end is grounded, the middle terminal outputs voltage, the voltage value corresponds to the resistance value one by one, and the dial value can be marked only by collecting the voltage value through the motor control module myRIO; the image acquisition module is realized by using a USB camera and a computer, and a program written in the computer can process and calibrate images acquired by the camera; the control program in the motor control module myRIO is linked with the image acquisition program in the image acquisition module.
The dial image acquisition process comprises the following steps: the motor control module myRIO controls the motor sub-module to move the high-precision rotary potentiometer to a certain position, collects a voltage value output by the middle terminal of the high-precision rotary potentiometer at the moment, converts the voltage value into dial data and transmits the dial data to the image collection module; at the moment, a control program in the motor control module myRIO is suspended, the program in the image acquisition module operates, a dial image at the moment is acquired through the camera, normalization processing is carried out, and the dial image is calibrated according to dial data transmitted by the motor control module myRIO; the program of the image acquisition module is suspended, the control program in the motor control module myRIO is started again, the control program is circulated in sequence, marked dial photos are continuously generated, and a data set is built; in the artificial intelligent training platform AIstudio, the established data set is uploaded, and the PaddlePaddle is called to conveniently establish an artificial intelligent model for training, and the data set and model parameters are finely adjusted according to training results, so that a high-precision identification model can be obtained.
The whole process automation system of the artificial intelligence model is used for whole process training education of artificial intelligence, dial identification of various instruments and meters of safety production enterprises and automatic integrated management of monitoring data.
Claims (1)
1. An artificial intelligence model whole process automation system, comprising: the scale module, transmission module, scale feedback module, image acquisition module, the transmission module is connected scale module and scale feedback module, and the one-to-one correspondence can be established with the numerical value that scale feedback module detected to the numerical value that scale module indicates, and image acquisition module is used for obtaining the image of scale module, and the numerical value that scale feedback module detected is used for marking the image of scale module, characterized by, transmission module includes:
the motor control module adjusts the resistance of the rotary potentiometer to a state through the motor sub-module, measures the actual resistance of the rotary potentiometer in the state, and obtains the indication value of the gauge dial in the state according to the corresponding relation between the actual resistance and the gauge dial; the image acquisition module starts to shoot a dial of the gauge, processes the size and the light of the image according to the setting to obtain a standard uniform image, and marks the marked dial image of the state according to the dial value corresponding to the measured value of the rotary potentiometer; the marked dial image of the meter becomes one element of a data set required for training the artificial intelligent model, and in this way, an image covering all dial information states is generated and automatically marked, and a complete data set is established.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910598739.XA CN110378257B (en) | 2019-07-04 | 2019-07-04 | Artificial intelligent model whole process automation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910598739.XA CN110378257B (en) | 2019-07-04 | 2019-07-04 | Artificial intelligent model whole process automation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378257A CN110378257A (en) | 2019-10-25 |
| CN110378257B true CN110378257B (en) | 2023-12-19 |
Family
ID=68251933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910598739.XA Active CN110378257B (en) | 2019-07-04 | 2019-07-04 | Artificial intelligent model whole process automation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378257B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101614562A (en) * | 2009-08-05 | 2009-12-30 | 钟胜 | Pointer type reading device with digitizing function |
| CN106194167A (en) * | 2016-09-23 | 2016-12-07 | 上海神开石油设备有限公司 | A kind of device and method of rotation status subscript orientation resistivity |
| RU2604116C1 (en) * | 2015-07-21 | 2016-12-10 | Федеральное государственное унитарное предприятие "Российский Федеральный Ядерный Центр - Всероссийский Научно-Исследовательский Институт Технической Физики имени академика Е.И. Забабахина" (ФГУП "РФЯЦ-ВНИИТФ им. академ. Е.И. Забабахина") | Method for automatic reading from pointer-deflecting instruments |
| WO2017084186A1 (en) * | 2015-11-18 | 2017-05-26 | 华南理工大学 | System and method for automatic monitoring and intelligent analysis of flexible circuit board manufacturing process |
| CN107229930A (en) * | 2017-04-28 | 2017-10-03 | 北京化工大学 | A kind of pointer instrument numerical value intelligent identification Method and device |
| CN107729906A (en) * | 2017-10-24 | 2018-02-23 | 国网江苏省电力公司南京供电公司 | A kind of inspection point ammeter technique for partitioning based on intelligent robot |
| CN107944486A (en) * | 2017-11-20 | 2018-04-20 | 中国电子科技集团公司第四十研究所 | Suitable for the test data identifying processing method and system tested automatically |
| CN109871859A (en) * | 2018-09-28 | 2019-06-11 | 北京矩视智能科技有限公司 | One kind automatically generating training set of images system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590498B (en) * | 2017-09-27 | 2020-09-01 | 哈尔滨工业大学 | Self-adaptive automobile instrument detection method based on character segmentation cascade two classifiers |
-
2019
- 2019-07-04 CN CN201910598739.XA patent/CN110378257B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101614562A (en) * | 2009-08-05 | 2009-12-30 | 钟胜 | Pointer type reading device with digitizing function |
| RU2604116C1 (en) * | 2015-07-21 | 2016-12-10 | Федеральное государственное унитарное предприятие "Российский Федеральный Ядерный Центр - Всероссийский Научно-Исследовательский Институт Технической Физики имени академика Е.И. Забабахина" (ФГУП "РФЯЦ-ВНИИТФ им. академ. Е.И. Забабахина") | Method for automatic reading from pointer-deflecting instruments |
| WO2017084186A1 (en) * | 2015-11-18 | 2017-05-26 | 华南理工大学 | System and method for automatic monitoring and intelligent analysis of flexible circuit board manufacturing process |
| CN106194167A (en) * | 2016-09-23 | 2016-12-07 | 上海神开石油设备有限公司 | A kind of device and method of rotation status subscript orientation resistivity |
| CN107229930A (en) * | 2017-04-28 | 2017-10-03 | 北京化工大学 | A kind of pointer instrument numerical value intelligent identification Method and device |
| CN107729906A (en) * | 2017-10-24 | 2018-02-23 | 国网江苏省电力公司南京供电公司 | A kind of inspection point ammeter technique for partitioning based on intelligent robot |
| CN107944486A (en) * | 2017-11-20 | 2018-04-20 | 中国电子科技集团公司第四十研究所 | Suitable for the test data identifying processing method and system tested automatically |
| CN109871859A (en) * | 2018-09-28 | 2019-06-11 | 北京矩视智能科技有限公司 | One kind automatically generating training set of images system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378257A (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107655626A (en) | A kind of automation demarcation of pressure sensor and test equipment and its method of testing | |
| CN107478382B (en) | Automatic detection device and detection method for pressure instrument | |
| CN106168461B (en) | A kind of novel telemeasurement calibration instrument | |
| CN104089574A (en) | New classroom teaching model based on machine vision technology | |
| CN110378257B (en) | Artificial intelligent model whole process automation system | |
| CN108958212A (en) | Calibrating operation auxiliary device, calibrating operation householder method and recording medium | |
| CN111751049A (en) | Automatic detection device and detection method for mechanical pointer instrument | |
| CN107631803A (en) | Surface temperature of concrete accurate measurement method based on thermal sensation imaging | |
| CN104913721B (en) | A kind of experimental provision of industrial vision sensor detection | |
| CN102494743A (en) | Small-flow automatic detection device and detection method for water meters | |
| CN202563724U (en) | DBP semi-continuous production-oriented chemical teaching simulation system | |
| CN207318002U (en) | A kind of automation calibration of pressure sensor and test equipment | |
| CN112781642B (en) | Calibration method of pointer instrument | |
| CN114063518B (en) | Valve position calibration method, device, system and storage medium | |
| CN113970679A (en) | Automatic debugging table and debugging method for angular precision of shaft angle-digital converter | |
| CN109029537A (en) | A kind of pointer-type sync bit indicator test device and its application method | |
| Martín et al. | An electronic instrumentation design project for computer engineering students | |
| CN215450008U (en) | Multi-parameter automatic calibration device of oil level temperature controller for transformer | |
| CN112161647A (en) | Measuring instrument, measuring transmission/tracing method thereof, measuring instrument management system and method | |
| CN203149105U (en) | Digital universal meter automatic calibrating device | |
| Gautam et al. | Web-enabled simulated and remote control virtual laboratory of transducer | |
| CN112560983B (en) | Instrument identification method and device | |
| CN103955010B (en) | Portable Automatic check instrument | |
| CN212513464U (en) | Automatic detection device for mechanical pointer instrument | |
| CN114384340A (en) | Intelligent copying test device of steering engine tester |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231122 Address after: 2-1802, Building 1, Longhu Tianpuyuan, Aoti West Road, Lixia District, Jinan City, Shandong Province, 250000 Applicant after: Shandong Qiaosi Intelligent Technology Co.,Ltd. Address before: Room 403, No. 210 Zhongshan South 1st Road, Huangpu District, Shanghai, 200011 Applicant before: SHANGHAI TULING NEW ENERGY TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |