CN116091623A - Development system of artificial intelligence calibration algorithm - Google Patents
Development system of artificial intelligence calibration algorithm Download PDFInfo
- Publication number
- CN116091623A CN116091623A CN202310003844.0A CN202310003844A CN116091623A CN 116091623 A CN116091623 A CN 116091623A CN 202310003844 A CN202310003844 A CN 202310003844A CN 116091623 A CN116091623 A CN 116091623A
- Authority
- CN
- China
- Prior art keywords
- data
- moving average
- processing
- artificial intelligence
- processing module
- 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.)
- Pending
Links
- 238000011161 development Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 5
- 238000013500 data storage Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000009499 grossing Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 4
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000005538 encapsulation Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims 1
- 230000026676 system process Effects 0.000 claims 1
- 230000002452 interceptive effect Effects 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000010363 phase shift Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M1/00—Analogue/digital conversion; Digital/analogue conversion
- H03M1/12—Analogue/digital converters
- H03M1/124—Sampling or signal conditioning arrangements specially adapted for A/D converters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a development system of an artificial intelligence calibration algorithm, which comprises a sensor body, wherein a processing module, a data acquisition circuit, a bridge type conversion circuit and a filter are arranged in the sensor body, the processing module is in interactive connection with the data acquisition circuit, the processing module is in interactive connection with the filter, the data acquisition circuit is in interactive connection with the filter, and the bridge type conversion circuit is in interactive connection with the processing module; the processing module comprises a central processing unit, a data storage unit and a network communication unit; the invention can process the data with larger data quantity and make the data stable, thereby meeting the use requirement of processing a large amount of data.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a development system of an artificial intelligence calibration algorithm.
Background
Usually, a development system of an artificial intelligent calibration algorithm needs to use a high-end chip in an image sensor to realize a trigger mode graph, so that the cost is high; at present, for calibration equipment which does not support a trigger mode picture, after an image sensor finishes initialization configuration in an ERS mode, image data starts to be continuously output line by line, when the rear end needs to take pictures, a register of the image sensor is modified through driving software of an image acquisition device, so that the image sensor outputs pictures corresponding to a current frame, the effect of the trigger mode picture is simulated, and along with development of a sensing technology, a communication technology and a computer technology, the traditional calibration algorithm has the main defects that the data volume required by the algorithm is large, non-stable sensor measurement data cannot be processed, the measurement data is large, and meanwhile, the data are required to be stable, obviously contradicted, so that the use requirement on large amount of data processing cannot be met.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a development system of an artificial intelligent calibration algorithm.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the development system comprises an artificial intelligent server and a data center, wherein a processing module, a data acquisition circuit, a bridge type conversion circuit and a filter are arranged in the artificial intelligent server, the data center is in interactive connection with the processing module, the processing module is in interactive connection with the data acquisition circuit, the processing module is in interactive connection with the filter, the data acquisition circuit is in interactive connection with the filter, and the bridge type conversion circuit is in interactive connection with the processing module;
the processing module comprises a central processing unit, a data storage unit and a network communication unit.
As a further preferred aspect of the present invention: the processing module is used for comprehensive data processing, the data acquisition circuit is used for preprocessing data and converting signals, and the filter is used for filtering and reducing nonlinear errors.
As a further preferred aspect of the present invention: the development system processing calibration algorithm comprises the following steps:
the method comprises the following steps:
step one, creating a data acquisition circuit, wherein the data acquisition circuit is used for realizing a circuit system for converting an analog signal into a digital signal, and the most important device in the data acquisition circuit is an analog-to-digital converter, namely an A/D converter;
step two, preprocessing, namely preprocessing through a data acquisition circuit;
step three, creating a bridge type conversion circuit, and utilizing the sum and difference characteristics of the bridge type circuit, adopting a differential structure to output so as to reduce nonlinear errors;
fourth, system encapsulation;
step five, digital filtering, namely filtering by adopting a zero phase shift digital filter;
step six, data processing is carried out by a primary average method, wherein the primary moving average method is to calculate the average value of each piece of data by adopting a gradual transition method according to the sequence of original data points;
step seven, data processing by a secondary moving average method is performed, in order to improve the tracking capacity of the primary moving average method, particularly when the measured data of the processing sensor has a linear trend, the increment of each piece of data is approximately equal, and the algorithm tracking capacity can be improved by adopting the secondary moving average method;
step eight, data testing, which is to process stable sensor signals and non-stable sensor signals to compare their smoothing and tracking capabilities.
As a further preferred aspect of the present invention: in the fifth step, the output function of the filter:
Y(z)＝X(z)H(1/z)H(z).
where X (z) is the variation of the wireless signal sequence without edge z and H (z) is the system function of the filter.
As a further preferred aspect of the present invention: in the sixth step, the calculation formula of the primary moving average method is as follows:
in mk (1) The result of the k-th moving average is that k is the sampling number, xk is the original sampling data of the k-th moving average, and n is the segment data length of the one-time moving average.
As a further preferred aspect of the present invention: in the seventh step, the calculation formula of the second moving average method is as follows:
in mk (2) Is the result of the quadratic moving average, mk (1) The result of the k-th moving average is that k is a sampling sequence number, n is the segment data length of the moving average method, and similarly, when the sensor data is a stable signal, the algorithm is unbiased, so that the method is suitable for processing the stable sensor data and the non-stable sensor data.
As a further preferred aspect of the present invention: the primary moving average method adopts a method of gradually moving and then averages, so that the change dynamics of future data can be tracked relatively quickly, namely, a non-stationary sensor signal can be processed, and if the sensor signal is stationary, the result of unbiased estimation of the measured value can be easily proved by a calculation formula of the primary moving average method.
As a further preferred aspect of the present invention: in the eighth step, the processing is performed by adopting the methods of primary moving average, secondary moving average, primary exponential smoothing, secondary exponential smoothing and the like with n=10, the processing results are shown in fig. 4, the curves 1 and 4 are original data curves, the curves 2 and 3 are respectively primary and secondary exponential smoothing processing result curves, the curves 5 and 6 are respectively primary and secondary moving average result curves, and according to the above two types of sensor data processing results, it can be seen that the above algorithm has smoothing capability and tracking capability on signals.
Compared with the prior art, the invention has the beneficial effects that:
the invention can process the data with larger data quantity and make the data stable, thereby meeting the use requirement of processing a large amount of data.
Drawings
FIG. 1 is a schematic flow chart of a development system of an artificial intelligence calibration algorithm according to the present invention;
FIG. 2 is a schematic diagram of a processing module in a development system of an artificial intelligence calibration algorithm according to the present invention;
FIG. 3 is a diagram showing steps for implementing a filter in a development system of an artificial intelligence calibration algorithm according to the present invention;
FIG. 4 is a data test chart of step eight of a processing method in a development system of an artificial intelligence calibration algorithm according to the present invention;
FIG. 5 is a block diagram of a development system for an artificial intelligence calibration algorithm according to the present invention;
FIG. 6 is a circuit diagram of a bridge type conversion circuit in a development system of an artificial intelligence calibration algorithm according to the present invention;
FIG. 7 is a block diagram showing the connection of a data acquisition circuit in a development system of an artificial intelligence calibration algorithm according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Referring to fig. 2, 3, 5, 6 and 7, a development system of an artificial intelligence calibration algorithm comprises an artificial intelligence server and a data center, wherein a processing module, a data acquisition circuit, a bridge type conversion circuit and a filter are arranged in the artificial intelligence server, the data center is in interactive connection with the processing module, the processing module is in interactive connection with the data acquisition circuit, the processing module is in interactive connection with the filter, the data acquisition circuit is in interactive connection with the filter, and the bridge type conversion circuit is in interactive connection with the processing module;
the processing module comprises a central processing unit, a data storage unit and a network communication unit, the processing module is used for comprehensive data processing, the data acquisition circuit is used for preprocessing data and converting signals, and the filter is used for filtering and reducing nonlinear errors.
Referring to fig. 1-7, in this embodiment, a specific processing method of a development system of an artificial intelligence calibration algorithm includes the following steps:
step one, creating a data acquisition circuit, wherein the data acquisition circuit is used for realizing a circuit system for converting an analog signal into a digital signal, and the most important device in the data acquisition circuit is an analog-to-digital converter, namely an A/D converter;
step two, preprocessing, namely preprocessing through a data acquisition circuit;
step three, creating a bridge type conversion circuit, and utilizing the sum and difference characteristics of the bridge type circuit, adopting a differential structure to output so as to reduce nonlinear errors;
fourth, system encapsulation;
step five, digital filtering, filtering by adopting a zero phase shift digital filter, and outputting functions of the filter:
Y(z)＝X(z)H(1/z)H(z).
wherein X (z) is the variation of the wireless signal sequence without edge z, and H (z) is the system function of the filter;
step six, data processing is carried out by a primary moving average method, wherein the primary moving average method adopts a gradual transition method according to the sequence of original data points to calculate the average value of each piece of data, and the calculation formula of the primary moving average method is as follows:
in mk (1) The result of the k-th moving average is the sampling sequence number, xk is the original sampling data of the k-th time, n is the segment data length of the one-time moving average method, and the one-time moving average method adopts a step-by-step moving method and then averages, so that the change dynamics of future data can be tracked faster, i.e. a non-stable sensor signal can be processed, if the sensor signal is stable, the result can be easily proved to be unbiased estimation of a measured value by a calculation formula of the one-time moving average method;
in order to improve the tracking capability of the primary moving average method, particularly when the measured data of the processing sensor has a linear trend, the increment of each piece of data is approximately equal, the algorithm tracking capability can be improved by adopting the secondary moving average method, and the calculation formula of the secondary moving average method is as follows:
in mk (2) Is the result of the quadratic moving average, mk (1) The result of the k-th moving average is that k is a sampling sequence number, n is the segment data length of the one-time moving average method, and similarly, when the sensor data are stationary signals, the algorithm is unbiased, so that the method is suitable for processing stationary sensor data and non-stationary sensor data;
step eight, data testing, namely processing stable sensor signals, processing non-stable sensor signals to compare the smoothing capacity and tracking capacity of the stable sensor signals, processing the stable sensor signals by adopting methods of primary moving average, secondary moving average, primary exponential smoothing, secondary exponential smoothing and the like of n=10, wherein the processing results are shown in fig. 4, curves 1 and 4 are original data curves, curves 2 and 3 are respectively a primary exponential smoothing processing result curve and a secondary exponential smoothing processing result curve, curves 5 and 6 are respectively a primary moving average result curve and a secondary moving average result curve, and according to the processing results of the two types of sensor data, the algorithm has the smoothing capacity and tracking capacity of the signals.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (8)
1. The development system of the artificial intelligence calibration algorithm comprises an artificial intelligence server and a data center, and is characterized in that a processing module, a data acquisition circuit, a bridge type conversion circuit and a filter are arranged in the artificial intelligence server, the data center is interactively connected with the processing module, the processing module is interactively connected with the data acquisition circuit, the processing module is interactively connected with the filter, the data acquisition circuit is interactively connected with the filter, and the bridge type conversion circuit is interactively connected with the processing module;
the processing module comprises a central processing unit, a data storage unit and a network communication unit.
2. The system of claim 1, wherein the processing module is configured to perform integrated data processing, the data acquisition circuit is configured to perform preprocessing and signal conversion on the data, and the filter is configured to perform filtering and reduce nonlinear errors.
3. The development system of an artificial intelligence calibration algorithm according to claim 1, wherein the development system processes the calibration algorithm comprising the steps of:
step one, creating a data acquisition circuit, wherein the data acquisition circuit is used for realizing a circuit system for converting an analog signal into a digital signal, and the most important device in the data acquisition circuit is an analog-to-digital converter, namely an A/D converter;
step two, preprocessing, namely preprocessing through a data acquisition circuit;
step three, creating a bridge type conversion circuit, and utilizing the sum and difference characteristics of the bridge type circuit, adopting a differential structure to output so as to reduce nonlinear errors;
fourth, system encapsulation;
step five, digital filtering, filtering by using a filter;
step six, data processing is carried out by a primary average method, wherein the primary moving average method is to calculate the average value of each piece of data by adopting a gradual transition method according to the sequence of original data points;
step seven, data processing by a secondary moving average method is performed, in order to improve the tracking capacity of the primary moving average method, particularly when the measured data of the processing sensor has a linear trend, the increment of each piece of data is approximately equal, and the algorithm tracking capacity can be improved by adopting the secondary moving average method;
step eight, data testing, which is to process stable sensor signals and non-stable sensor signals to compare their smoothing and tracking capabilities.
4. A development system for an artificial intelligence calibration algorithm according to claim 3, wherein in step five, the output function of the filter:
Y(z)＝X(z)H(1/z)H(z).
where X (z) is the variation of the wireless signal sequence without edge z and H (z) is the system function of the filter.
5. A development system for an artificial intelligence calibration algorithm according to claim 3, wherein in the sixth step, a calculation formula of a one-time moving average method is:
in mk (1) The result of the k-th moving average is that k is the sampling number, xk is the original sampling data of the k-th moving average, and n is the segment data length of the one-time moving average.
6. A development system for an artificial intelligence calibration algorithm according to claim 3, wherein in the seventh step, the formula of the second moving average is:
in mk (2) Is the result of the quadratic moving average, mk (1) The result of the k-th moving average is that k is a sampling sequence number, n is the segment data length of the moving average method, and similarly, when the sensor data is a stable signal, the algorithm is unbiased, so that the method is suitable for processing the stable sensor data and the non-stable sensor data.
7. The system of claim 5, wherein the one-time moving average method is capable of tracking the change dynamics of future data faster, i.e. processing non-stationary sensor signals, if the sensor signals are stationary, by using a calculation formula of the one-time moving average method, the result of which can be easily demonstrated as an unbiased estimate of the measured value, due to the stepwise moving method and the averaging.
8. A development system for an artificial intelligence calibration algorithm according to claim 3, wherein in the eighth step, the processing is performed by a method such as a first moving average, a second moving average, a first exponential smoothing, and a second exponential smoothing, where n=10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310003844.0A CN116091623A (en) | 2023-01-03 | 2023-01-03 | Development system of artificial intelligence calibration algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310003844.0A CN116091623A (en) | 2023-01-03 | 2023-01-03 | Development system of artificial intelligence calibration algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116091623A true CN116091623A (en) | 2023-05-09 |
Family
ID=86203896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310003844.0A Pending CN116091623A (en) | 2023-01-03 | 2023-01-03 | Development system of artificial intelligence calibration algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116091623A (en) |
-
2023
- 2023-01-03 CN CN202310003844.0A patent/CN116091623A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN202196119U (en) | Single-phase multifunctional electric energy metering circuit | |
| CN107966638B (en) | Method and apparatus for correcting error, storage medium, and processor | |
| Savkin et al. | Model validation and state estimation for uncertain continuous-time systems with missing discrete-continuous data | |
| CN109327258A (en) | Calibration method, device and the readable storage medium storing program for executing of optical module receiving end optical power | |
| CN108693400B (en) | Double-slope fractional order integral type analog-to-digital converter | |
| CN217506534U (en) | Readout circuit and processor | |
| CN110335219B (en) | Correction method and correction device for pixel distortion and terminal | |
| CN109683524B (en) | Processing method for sampling and synchronizing sampling signals without sampling and holding | |
| CN116091623A (en) | Development system of artificial intelligence calibration algorithm | |
| CN108132383B (en) | Time-interleaved multi-harmonic signal undersampling method | |
| CN113791240A (en) | Acceleration estimation method, system, device and medium based on high-order synovial membrane tracking differentiator | |
| CN116805882B (en) | Processing method for signal amplitude exceeding AD range of receiver | |
| CN110033030B (en) | Method for solving compressed sensing problem of 0-1 measurement matrix based on neural network | |
| CN114113843B (en) | Image recognition-based automatic detection system and method for direct current charging pile | |
| CN113687289B (en) | Measurement and self-calibration method and system of non-contact miniature voltage sensor | |
| CN213149093U (en) | Direct current fills electric pile error calibrating installation based on image recognition | |
| CN115291158A (en) | Automatic electric quantity calibration method and device of settlement metering device | |
| CN210720628U (en) | Direct current insulation monitoring circuit | |
| CN113777394A (en) | Software integration method, device, equipment and storage medium independent of external circuit | |
| CN113702890A (en) | Charging pile error calibration method and device based on image recognition | |
| CN114092503A (en) | Detection circuit, chip and electronic equipment | |
| CN207114471U (en) | A kind of numeral output potentiostat | |
| CN116067433B (en) | Vibration wire data acquisition method and acquisition instrument thereof | |
| CN109001278B (en) | Automatic negative capacitance compensation method for microelectrode amplifier | |
| CN115266708B (en) | Embedded sand content measuring method based on cyclic neural network |
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 |