CN118131678B - Artificial intelligence control system of dietary fiber tester - Google Patents
Artificial intelligence control system of dietary fiber tester Download PDFInfo
- Publication number
- CN118131678B CN118131678B CN202410545818.5A CN202410545818A CN118131678B CN 118131678 B CN118131678 B CN 118131678B CN 202410545818 A CN202410545818 A CN 202410545818A CN 118131678 B CN118131678 B CN 118131678B
- Authority
- CN
- China
- Prior art keywords
- flexible container
- heater
- node
- control
- self
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 26
- 235000013325 dietary fiber Nutrition 0.000 title claims abstract description 24
- 238000010438 heat treatment Methods 0.000 claims abstract description 39
- 238000009529 body temperature measurement Methods 0.000 claims abstract description 11
- 238000012546 transfer Methods 0.000 claims description 43
- 210000002569 neuron Anatomy 0.000 claims description 40
- 238000013528 artificial neural network Methods 0.000 claims description 30
- 230000005855 radiation Effects 0.000 claims description 24
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000004861 thermometry Methods 0.000 claims 2
- 230000004888 barrier function Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 6
- 238000009499 grossing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25257—Microcontroller
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Control Of Temperature (AREA)
Abstract
An artificial intelligence control system of a dietary fiber tester belongs to the technical field of electric control. In the control system, a heating control module provides control signals for a heater group selector and the heater selector according to information provided by a temperature measurement module, and the heater group selector and the heater selector are connected to M heater group control circuits through M heater group selection lines and N multiplied by M heater selection lines respectively; each heater group control circuit comprises N selection switches and N power switches, the control ends of the N selection switches are connected to a heater group selection line, the first terminals of the N selection switches are respectively connected to a heater selection line, the second terminals of the N selection switches are respectively connected to the control ends of the power switches, the first terminals of the N power switches are respectively connected to a power supply, the second terminals of the N power switches are respectively connected to a heater, and M and N are positive integers greater than or equal to 2. The invention saves energy and has higher control flexibility.
Description
Technical Field
The invention relates to an artificial intelligent control system of a dietary fiber tester, and belongs to the technical field of intelligent control.
Background
The Chinese patent application with publication number of CN116036945A discloses a non-contact stirring device and a dietary fiber tester, wherein the dietary fiber tester comprises a fixing frame, a plurality of flexible containers arranged on the fixing frame and a heating plate.
The technical solutions disclosed in the above-mentioned patent applications have the following drawbacks:
1. All the flexible containers arranged on the support are heated by using the same heating plate, and all the nodes of the support are heated even if only part of the flexible containers on the support need to be heated, so that energy waste is caused;
2. the temperature of each flexible container can not be controlled respectively, and the flexibility is poor.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide an artificial intelligent control system of a dietary fiber tester, which can only heat flexible containers on part of heater groups according to the needs, saves energy, and has higher flexibility, wherein the temperature of each heater group can be controlled respectively.
In order to achieve the purpose, the invention aims at an artificial intelligent control system of a dietary fiber tester, which is characterized by comprising a temperature measuring module, a processor, M heater groups, heater group selectors, a heater selector and M heater group control circuits, wherein each heater group is provided with N heaters, the N heaters jointly heat one flexible container arranged on a bracket, the processor comprises a heating control module, the heating control module provides control signals for the heater group selectors and the heater selector in each heater group according to information provided by the temperature measuring module, and the heater group selectors are connected to the M heater group control circuits through M heater group selection lines; the heater selector is connected to M heater group control circuits through N multiplied by M heater select lines, each heater group control circuit comprises N select switches and N power switches, control ends of 1 st to N select switches in the N select switches are all connected to one heater group select line, first terminals of 1 st to N select switches in the N select switches are respectively connected to 1 st to N heater select lines, second terminals are respectively connected to control ends of 1 st to N power switches, first terminals of 1 st to N power switches in the N power switches are all connected to power supplies, second terminals of 1 st to N power switches in the N power switches are respectively connected to 1 st to N heaters, M is a positive integer greater than or equal to 2, and N is a positive integer greater than or equal to 2.
Compared with the prior art, the invention has the following beneficial effects:
the flexible container on part of the heater groups can be heated as required, so that energy sources are saved, the temperature of each heater group can be controlled respectively, and the flexibility is high.
Drawings
FIG. 1 is a block diagram of an artificial intelligence control system for a dietary fiber meter according to a first embodiment of the present invention.
Fig. 2 is a diagram of a heating control model provided in the first embodiment of the present invention.
Fig. 3 is a diagram of a heating control model provided in a second embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
First embodiment
The dietary fiber tester provided by the first embodiment of the invention comprises a bracket, M heater groups are arranged on the bracket, N heaters are arranged on each heater group to heat, N heaters form a heater ring, M is a positive integer greater than or equal to 2, and N is a positive integer greater than or equal to 2. When heating the sample, a flexible container for holding the sample may be provided on one heater group as needed.
FIG. 1 is a block diagram of an artificial intelligence control system for a dietary fiber meter according to a first embodiment of the present invention, and as shown in FIG. 1, the artificial intelligence control system includes: the device comprises a temperature measurement module, a processor, M heater groups, heater group selectors, heater selectors and M heater group control circuits, wherein each heater group is provided with N heaters which heat one flexible container arranged on a bracket together, the processor comprises a heating control module, the heating control module provides control signals for the heater group selectors and the heater selectors in each heater group according to information provided by the temperature measurement module, and the heater group selectors are connected to the M heater group control circuits through M heater group selection lines; the heater selector is connected to M heater group control circuits through N multiplied by M heater select lines, each heater group control circuit comprises N select switches and N power switches, control ends of 1 st to N select switches in the N select switches are all connected to one heater group select line, first terminals of 1 st to N select switches in the N select switches are respectively connected to 1 st to N heater select lines, second terminals are respectively connected to control ends of 1 st to N power switches, first terminals of 1 st to N power switches in the N power switches are all connected to power supplies, second terminals of 1 st to N power switches in the N power switches are respectively connected to 1 st to N heaters, M is a positive integer greater than or equal to 2, and N is a positive integer greater than or equal to 2.
Specifically, the heater group control circuit includes a1 st selection switch T 111, a1 st power switch T 121, and a1 st heater D 111, the control terminal of the selection switch T 111 is connected to a heater group selection line L 1, The first terminal of the selection switch T 111 is connected to the heater selection line A11, the second terminal is connected to the control terminal of the power switch T 121, the first terminal of the power switch T 121 is connected to the power Ec, the second terminal of the power switch T 121 is connected to the heater D 111, …, a heater group control circuit comprising an nth selection switch T 11N, an nth power switch T 12N and an nth heater D 11N, the control terminal of the selection switch T 11N being connected to a heater group selection line L 1, The first terminal of the selection switch T 11N is connected to the heater selection line A 1N, the second terminal is connected to the control terminal of the power switch T 12N, the first terminal of the power switch T 12N is connected to the power Ec, A second terminal of the power switch T 12N is connected to the heater D 11N. For example, the heater group control circuit operates as follows: the heater group selector supplies a high level to the heater group selection line L 1, the control terminals of the 1 st to nth selection switches T 111,…,T11N are high level, the selection switch T 111,…,T11N is turned on, and if the heater D 111 is selected to heat, The heater provides a high signal to the select line a 11, the power switch T 121 is turned on, the power Ec provides a voltage via the power switch T 121, the heater D 111 operates, If the heater D 111 is selected not to heat at this time, the heater supplies a low level signal to the selection line a 11, the power switch T 121 is turned off, the heater D 111 is not operated, And so on, part of heaters of the same heater group can be freely selected to heat, simultaneously heat or simultaneously not heat according to the needs.
The first embodiment provides an artificial intelligence control system of a dietary fiber tester, further comprising a touch display screen, which is a control interface of a control program, wherein a user can select which heater group on the bracket is used for heating the flexible container containing the sample in the interface, and can select heating power according to requirements.
The first embodiment provides an artificial intelligence control system of a dietary fiber meter, further comprising a storage unit for storing data, a control program, and the like, and the processor calls the control program to implement control of the heaters of the M heater groups.
In a first embodiment, a temperature sensor may be designed near each heater group for detecting the temperature value of the heater group and transmitting the temperature value to the heating control module of the processor.
The temperature measurement module of the artificial intelligence control system of the dietary fiber tester provided by the first embodiment comprises a first infrared image sensor and a second infrared image sensor; the processor comprises a control signal generation module; the method comprises the steps that a first infrared image sensor acquires a first sequence of infrared images comprising a flexible container and transmits the first sequence of infrared images to a control signal generation module, a second infrared image sensor acquires a second sequence of infrared images comprising the flexible container and transmits the second sequence of infrared images to the control signal generation module, and the control signal generation module comprises a first convolution neural network, a second convolution neural network and an artificial intelligence module, wherein the first convolution neural network extracts a first feature vector of the flexible container according to the first sequence of infrared images; the second convolutional neural network extracts a second feature vector of the flexible container according to the second sequence of infrared images; the artificial intelligence module comprises a calculation module and an inference module, wherein the calculation module calculates the expansion amount of the flexible container and the infrared radiation energy of the unit area of the flexible container according to a first characteristic vector and a second characteristic vector provided by the first convolutional neural network and the second convolutional neural network, and the inference module infers the air pressure in the flexible container according to the flexible container and calculates the temperature of the flexible container according to the infrared radiation energy of the unit area of the flexible container; the control signal generation module controls the working state of the heaters in each heater group according to the temperature of the flexible container and the air pressure in the flexible container.
In the first embodiment, the computing module processes the first image data and the second image data of the flexible container sequence to obtain the parallax of the same pixel at the same moment, and the volume of the flexible container or the visible part of the flexible container is obtained according to the parallax of the pixel at the edge of the flexible container; obtaining the expansion amount of the flexible container according to the obtained volume of the flexible container or the visible part of the flexible container of the adjacent image data; when the expansion amount of the flexible container obtained by the volume of the flexible container or the visible part of the flexible container obtained by the calculation of the adjacent image data is input to the trained self-competitive neural network of the inference module, the trained self-competitive neural network outputs the air pressure in the flexible container.
In a first embodiment, the inference module comprises a self-competing neural network comprising an input layer and a first self-competing two-dimensional neuron layer, the input layer inputting an amount of expansion of the flexible container; the trained self-competitive neural network learns the expansion amount of the flexible container into a first self-competitive two-dimensional neuron layer along with the internal air pressure change curve in advance, clusters with neurons of the first self-competitive two-dimensional neuron layer when the expansion amount of the flexible container is input into an input layer of the trained first self-competitive neural network, and corrects air pressure represented by the neurons of the first self-competitive two-dimensional neuron layer with the minimum Euler distance by using the first Euler distance to obtain the air pressure in the flexible container.
The self-competitive neural network also comprises a second self-competitive two-dimensional neuron layer, and the input layer inputs infrared radiation energy of the unit area of the flexible container; the trained self-competitive neural network learns the infrared radiation energy of the unit area of the flexible container into a second self-competitive two-dimensional neuron layer along with the temperature change curve of the infrared radiation energy, when the infrared radiation energy of the unit area of the flexible container is input into the input layer of the trained second self-competitive two-dimensional neuron network, the infrared radiation energy is clustered with neurons of the second self-competitive two-dimensional neuron layer, and the temperature represented by the neurons of the second self-competitive two-dimensional neuron layer with the minimum Euclidean distance is corrected by utilizing the second Euclidean distance to obtain the temperature estimated value in the flexible container.
In the first embodiment, when the pressure of the gas in the flexible container is higher than a set threshold value, a sealing piece at the opening of the flexible container is started to release pressure, so that the safety of experimenters is ensured.
Optionally, in the first embodiment, the artificial intelligence module further includes a calculation module and a BP neural network, where the calculation module performs fusion processing on the first sequence of thermal radiation data and the second sequence of thermal radiation data of the flexible container, for example, the thermal radiation data at the same time is averaged, and then the thermal radiation data is input to an input layer of the BP neural network, neurons in an hidden layer of the BP neural network are activated by using an activation function, and an output layer of the BP neural network outputs a temperature estimated value of the flexible container.
In a first embodiment, the heating module includes a heating control model and a thermal circuit network model, the heating control module includes a thermal circuit network model, the thermal circuit network model includes M nodes, each node has a heat capacity, a thermal resistance between adjacent nodes, and each node is at least equivalent to a sample, a flexible container, a support, a first infrared image sensor, a second infrared image sensor, and N heaters. Optionally, each node corresponds to at least a sample, a flexible container, a rack, a temperature sensor, and N heaters. The thermal resistance of each heat transfer path of the thermal circuit network model may be sequentially given according to the size, thermal characteristics of the material, empirical formula, etc., or may be obtained by experiment in advance. When the temperature estimated value of the flexible container and the heat supplied from the heater are known, a state estimation can be performed by using a kalman filter, a particle filter, or the like, and the temperature value of the sample can be deduced.
In the first embodiment, the touch display screen is further configured to display the infrared image information acquired by the first and second infrared image sensors and the analysis result of the control signal generating module.
Fig. 2 is a diagram of a heating control model according to a first embodiment of the present invention, and as shown in fig. 2, the heating control module further includes a feedback heating control model, where the feedback heating control model satisfies the following formula:
，
In the method, in the process of the invention, For z-transformation of flexible container temperature estimates in node X m, m=1, …, M;
，
For the z-transform of the thermal transfer function of node X 1 to node X m, For the z-transform of the thermal transfer function of node X a to node X m,A = 1, …, M for the z-transform of the thermal transfer function of node X M to node X m;
for the z-transform of the flexible container temperature estimate in node X 1, The z-transform value, which is the flexible container temperature estimate in node X a, …,A z-transform value that is an estimate of the temperature of the flexible container in node X M;
Z-transformation of a transfer function for a path from the 1 st heater input control voltage to the temperature estimate of the resulting flexible container; z-transformation of a transfer function for a path from an nth heater input control voltage to obtaining an estimated temperature value of the flexible container; for the z-transform of the transfer function of the path from the nth heater input control voltage to the temperature estimate of the resulting flexible container, n=1, …, N;
For the control voltage z-shift of the 1 st heater in node X m, For the control voltage z-shift of the nth heater in point X m,The control voltage z for the nth heater in node X m is shifted;
Obtaining the z-transformation of a transfer function of a control instruction value of the 1 st heater according to the temperature estimated value of the flexible container in the node X m; Obtaining the z-transformation of the transfer function of the control instruction value of the nth heater according to the temperature estimated value of the flexible container in the node X m; The z-transform of the transfer function of the control command value for the nth heater is obtained from the temperature estimate of the flexible container at node X m.
Temperature measurement or inferred value of each flexible container is a digital signal，…,，…,Their z-transform values are respectivelyFor the purposes of …,，…,; Control voltage value for each heater in the same heater group，…,The z-transform values of (2) are respectively,…,，…,According to
，…,，…,And calculated during the cycle，，…,Estimating a temperature value. Then according to the estimated temperature valueCalculating a control voltage value，…,，…,Control the voltage value，…,，…,The analog signal is converted into analog signal control voltage values through D/A converters respectively, and then the analog signal control voltage values are transmitted to N heaters through amplifiers respectively. Transfer function，…,，…,Respectively to，…,，…,Smoothing; transfer function，…,，…,Respectively to,…,，…,Smoothing; transfer function，…,，…,And a transfer function，…,，…,And a transfer function，…,，…,Pre-stored in memory, and can be called when in use.
According to the first embodiment of the invention, only the flexible containers on part of the heater groups can be heated as required, so that energy sources are saved, the temperature of each heater group can be controlled respectively, and the flexibility is high; the control command value of the heater in each heater group can be accurately obtained through a closed-loop heating control model, so that the flexible container can be heated according to the required temperature.
Second embodiment
The second embodiment of the present invention only describes matters different from those of the first embodiment, and the description is not repeated for the same parts.
In a second embodiment, the control signal generating module includes a heating control model and a thermal circuit network model, the heating control module includes a thermal circuit network model, the thermal circuit network model includes M nodes, each node has a heat capacity, heat is blocked between adjacent nodes, and each node is at least equivalent to a sample, a flexible container, a bracket, a first infrared image sensor, a second infrared image sensor and N heaters. Optionally each node corresponds to at least a sample, a flexible container, a rack, a temperature sensor, and N heaters.
Fig. 3 is a diagram of a heating control model according to a second embodiment of the present invention, where, as shown in fig. 3, the heating control module further includes a heating control model, and the heating control model is:
In the method, in the process of the invention, Z-transform of temperature estimate for flexible container in node X m;
z-transform of the transfer function for node X m;
A z-transform of a transfer function for a path in node X m from the control voltage input by heater 1 to the temperature estimate for the flexible container; Z-transformation of the transfer function for the path between the nth heater in node X m from the input control voltage to the temperature estimate of the flexible container; For the z-transform of the transfer function of the path in node X m between the control voltage input from the nth heater and the temperature estimate of the flexible container, n=1, …, N;
For the control voltage z-shift of the 1 st heater in node X m, For the control voltage z-shift of the nth heater in point X m,The control voltage z of the Nth heater is changed for the node X m;
Obtaining the z-transformation of the transfer function of the 1 st heater control instruction value according to the temperature estimated value of the flexible container in the node X m; Obtaining the z-transformation of the transfer function of the nth heater control instruction value according to the temperature estimated value of the flexible container in the node X m; The z-transform of the transfer function of the nth heater control command value is derived from the temperature estimate of the flexible container at node X m.
Temperature measurement or inferred value of flexible container is digital signalThe z-transform value is; Control voltage for each heater in the same heater group，…,，…,The z-transform values of (2) are respectively，…,，…,According toAnd calculated during the cycle，…,，…,Estimating a temperature value. Then according to the estimated temperature valueCalculating a control voltage value，…,，…,Control the voltage value，…,，…,The analog signal is converted into analog signal control voltage values through D/A converters respectively, and then the analog signal control voltage values are transmitted to N heaters through amplifiers respectively. Transfer functionFor a pair ofSmoothing; transfer function，…,，…,Respectively to，…,，…,Smoothing; transfer functionAnd a transfer function，…,And a transfer function，…,，…,Pre-stored in memory, and can be called when in use.
According to the second embodiment of the invention, only the flexible containers on part of the heater groups can be heated as required, so that energy sources are saved, the temperature of each heater group can be controlled respectively, and the flexibility is high; the control command value of the heater in each heater group can be accurately obtained through a closed-loop heating control model, so that the flexible container can be heated according to the required temperature.
The preferred embodiments of the present invention will be described in detail below with reference to the drawings. The advantages and features of the present invention and the methods of accomplishing the same will become apparent with reference to the accompanying drawings and the detailed description of the embodiments that follow.
However, the present invention is not limited to the embodiments disclosed below, and can be implemented in various forms different from each other, and the embodiments are only for making the disclosure of the present invention more complete and fully informing the person skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims of the present invention.
Although the terms first, second, etc. may be used herein to describe various elements, components and/or sections, these elements, components and/or sections should not be limited by these terms. These terms are only used to distinguish one element, component, or section from another element, component, or section. It is therefore apparent that the first element, or the first part mentioned below may be the second element, or the second part within the technical spirit of the present disclosure, and the terms used in the present specification are only used to describe the embodiments and are not intended to limit the present disclosure.
In the present specification, the singular form also includes the plural form unless specifically mentioned in the sentence. The use of "comprising" and/or "consisting of … …" in the specification does not exclude the presence or addition of more than one other structural element, step, action and/or component as referred to.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. In addition, terms defined in a dictionary generally used are not desirably or excessively interpreted unless specifically defined explicitly.
The same or similar structures are denoted by the same reference numerals, and repetitive description thereof will be omitted.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims.
Claims (10)
1. The artificial intelligence control system of the dietary fiber tester is characterized by comprising a temperature measurement module, a processor, M heater groups, a heater group selector, a heater selector and M heater group control circuits, wherein each heater group is provided with N heaters which heat one flexible container arranged on a bracket together, the processor comprises a heating control module, the heating control module provides control signals for the heater group selector and the heater selector in each heater group according to information provided by the temperature measurement module, and the heater group selector is connected to the M heater group control circuits through M heater group selection lines; the heater selector is connected to M heater group control circuits through N multiplied by M heater selection lines, each heater group control circuit comprises N selection switches and N power switches, the control ends of the 1 st to N selection switches in the N selection switches are all connected to one heater group selection line, the first terminals of the 1 st to N selection switches in the N selection switches are respectively connected to the 1 st to N heater selection lines, the second terminals are respectively connected to the control ends of the 1 st to N power switches, the first terminals of the 1 st to N power switches in the N power switches are all connected to power supplies, the second terminals of the 1 st to N power switches in the N power switches are respectively connected to the 1 st to N heaters, M is a positive integer greater than or equal to 2, and N is a positive integer greater than or equal to 2; the heating control module further includes a feedback heating control model that satisfies the following equation:
in which, in the process, For z-transformation of flexible container temperature estimates in node X m, m=1, …, M;
， For the z-transform of the thermal transfer function of node X 1 to node X m, For the z-transform of the thermal transfer function of node X a to node X m,A = 1, …, M for the z-transform of the thermal transfer function of node X M to node X m;
， for the z-transform of the flexible container temperature estimate in node X 1, The z-transform value, which is the flexible container temperature estimate in node X a, …,A z-transform value that is an estimate of the temperature of the flexible container in node X M;
， Z-transformation of a transfer function for a path from the 1 st heater input control voltage to the temperature estimate of the resulting flexible container; z-transformation of a transfer function for a path from an nth heater input control voltage to obtaining an estimated temperature value of the flexible container; for the z-transform of the transfer function of the path from the nth heater input control voltage to the temperature estimate of the resulting flexible container, n=1, …, N;
， For the control voltage z-shift of the 1 st heater in node X m, For the control voltage z-shift of the n-th heater in node X m,The control voltage z for the nth heater in node X m is shifted;
， Obtaining the z-transformation of a transfer function of a control instruction value of the 1 st heater according to the temperature estimated value of the flexible container in the node X m; Obtaining the z-transformation of the transfer function of the control instruction value of the nth heater according to the temperature estimated value of the flexible container in the node X m; The z-transform of the transfer function of the control command value for the nth heater is obtained from the temperature estimate of the flexible container at node X m.
2. The artificial intelligence control system of a dietary fiber meter of claim 1, wherein the thermometry module comprises a first infrared image sensor and a second infrared image sensor; the processor comprises a control signal generation module; the method comprises the steps that a first infrared image sensor acquires a first sequence of infrared images comprising a flexible container and transmits the first sequence of infrared images to a control signal generation module, a second infrared image sensor acquires a second sequence of infrared images comprising the flexible container and transmits the second sequence of infrared images to the control signal generation module, and the control signal generation module comprises a first convolution neural network, a second convolution neural network and an artificial intelligence module, wherein the first convolution neural network extracts a first feature vector of the flexible container according to the first sequence of infrared images; the second convolutional neural network extracts a second feature vector of the flexible container according to the second sequence of infrared images; the artificial intelligence module comprises a calculation module and an inference module, wherein the calculation module calculates the expansion amount of the flexible container and the infrared radiation energy of the unit area of the flexible container according to a first characteristic vector and a second characteristic vector provided by the first convolutional neural network and the second convolutional neural network, and the inference module infers the air pressure in the flexible container according to the expansion amount of the flexible container and calculates the temperature of the flexible container according to the infrared radiation energy of the unit area of the flexible container; the control signal generation module controls the working state of the heaters in each heater group according to the temperature of the flexible container and the air pressure in the flexible container.
3. The artificial intelligence control system of a dietary fiber meter of claim 2, wherein the inference module comprises a self-competing neural network comprising an input layer and a first self-competing two-dimensional neuron layer, the input layer inputting the amount of expansion of the flexible container; the trained self-competitive neural network learns the expansion amount of the flexible container into a first self-competitive two-dimensional neuron layer along with the change curve of the air pressure in the flexible container in advance, clusters with the neurons of the first self-competitive two-dimensional neuron layer when the expansion amount of the flexible container is input into the trained input layer of the first self-competitive neural network, and corrects the air pressure represented by the neurons of the first self-competitive two-dimensional neuron layer with the minimum Euler distance by utilizing the first Euler distance to obtain the air pressure in the flexible container.
4. The artificial intelligence control system of dietary fiber meter according to claim 3, wherein the self-competing neural network further comprises a second self-competing two-dimensional neuron layer, the input layer inputting infrared radiation energy per unit area of the flexible container; the trained self-competitive neural network learns the infrared radiation energy of the unit area of the flexible container into a second self-competitive two-dimensional neuron layer along with the temperature change curve of the infrared radiation energy, when the infrared radiation energy of the unit area of the flexible container is input into the input layer of the trained second self-competitive two-dimensional neuron layer, the infrared radiation energy is clustered with neurons of the second self-competitive two-dimensional neuron layer, and the temperature represented by the neurons of the second self-competitive two-dimensional neuron layer with the minimum Euclidean distance is corrected by using the second Euclidean distance to obtain the temperature estimated value of the flexible container.
5. The artificial intelligence control system of a dietary fiber meter of claim 4, wherein the heating control module comprises a thermal circuit network model comprising M nodes, each node having a thermal capacity, and thermal resistances between adjacent nodes, each node corresponding to at least a sample, a flexible container, a holder, a first infrared image sensor, a second infrared image sensor, and N heaters.
6. The artificial intelligence control system of the dietary fiber tester is characterized by comprising a temperature measurement module, a processor, M heater groups, a heater group selector, a heater selector and M heater group control circuits, wherein each heater group is provided with N heaters which heat one flexible container arranged on a bracket together, the processor comprises a heating control module, the heating control module provides control signals for the heater group selector and the heater selector in each heater group according to information provided by the temperature measurement module, and the heater group selector is connected to the M heater group control circuits through M heater group selection lines; the heater selector is connected to M heater group control circuits through N multiplied by M heater selection lines, each heater group control circuit comprises N selection switches and N power switches, the control ends of the 1 st to N selection switches in the N selection switches are all connected to one heater group selection line, the first terminals of the 1 st to N selection switches in the N selection switches are respectively connected to the 1 st to N heater selection lines, the second terminals are respectively connected to the control ends of the 1 st to N power switches, the first terminals of the 1 st to N power switches in the N power switches are all connected to power supplies, the second terminals of the 1 st to N power switches in the N power switches are respectively connected to the 1 st to N heaters, M is a positive integer greater than or equal to 2, and N is a positive integer greater than or equal to 2; the heating control module further comprises a heating control model, wherein the heating control model is as follows:
in which, in the process, Z-transform of temperature estimate for flexible container in node X m; α m (z) is the z-transform of the temperature measurement or inferred value of the flexible container in node X m to the digital signal α m; m=1, …, M;
z-transform of the transfer function for node X m;
， A z-transform of a transfer function for a path in node X m from the control voltage input by heater 1 to the temperature estimate for the flexible container; Z-transformation of the transfer function for the path between the nth heater in node X m from the input control voltage to the temperature estimate of the flexible container; For the z-transform of the transfer function of the path in node X m between the control voltage input from the nth heater and the temperature estimate of the flexible container, n=1, …, N;
， For the control voltage z-shift of the 1 st heater in node X m, For the control voltage z-shift of the n-th heater in node X m,The control voltage z for the Nth heater at node X m varies;
， Obtaining the z-transformation of the transfer function of the 1 st heater control instruction value according to the temperature estimated value of the flexible container in the node X m; Obtaining the z-transformation of the transfer function of the nth heater control instruction value according to the temperature estimated value of the flexible container in the node X m; The z-transform of the transfer function of the nth heater control command value is derived from the temperature estimate of the flexible container at node X m.
7. The artificial intelligence control system of a dietary fiber analyzer of claim 6, wherein the thermometry module includes a first infrared image sensor and a second infrared image sensor; the processor comprises a control signal generation module; the method comprises the steps that a first infrared image sensor acquires a first sequence of infrared images comprising a flexible container and transmits the first sequence of infrared images to a control signal generation module, a second infrared image sensor acquires a second sequence of infrared images comprising the flexible container and transmits the second sequence of infrared images to the control signal generation module, and the control signal generation module comprises a first convolution neural network, a second convolution neural network and an artificial intelligence module, wherein the first convolution neural network extracts a first feature vector of the flexible container according to the first sequence of infrared images; the second convolutional neural network extracts a second feature vector of the flexible container according to the second sequence of infrared images; the artificial intelligence module comprises a calculation module and an inference module, wherein the calculation module calculates the expansion amount of the flexible container and the infrared radiation energy of the unit area of the flexible container according to a first characteristic vector and a second characteristic vector provided by the first convolutional neural network and the second convolutional neural network, and the inference module infers the air pressure in the flexible container according to the expansion amount of the flexible container and calculates the temperature of the flexible container according to the infrared radiation energy of the unit area of the flexible container; the control signal generation module controls the working state of the heaters in each heater group according to the temperature of the flexible container and the air pressure in the flexible container.
8. The artificial intelligence control system of a dietary fiber meter of claim 7, wherein the inference module comprises a self-competing neural network comprising an input layer and a first self-competing two-dimensional neuron layer, the input layer inputting an amount of expansion of the flexible container; the trained self-competitive neural network learns the expansion amount of the flexible container into a first self-competitive two-dimensional neuron layer along with the change curve of the air pressure in the flexible container in advance, clusters with the neurons of the first self-competitive two-dimensional neuron layer when the expansion amount of the flexible container is input into the trained input layer of the first self-competitive neural network, and corrects the air pressure represented by the neurons of the first self-competitive two-dimensional neuron layer with the minimum Euler distance by utilizing the first Euler distance to obtain the air pressure in the flexible container.
9. The artificial intelligence control system of dietary fiber meter of claim 8, wherein the self-competing neural network further comprises a second self-competing two-dimensional neuron layer, the input layer inputting infrared-radiation energy per unit area of the flexible container; the trained self-competitive neural network learns the infrared radiation energy of the unit area of the flexible container into a second self-competitive two-dimensional neuron layer along with the temperature change curve of the infrared radiation energy, when the infrared radiation energy of the unit area of the flexible container is input into the input layer of the trained second self-competitive two-dimensional neuron layer, the infrared radiation energy is clustered with neurons of the second self-competitive two-dimensional neuron layer, and the temperature represented by the neurons of the second self-competitive two-dimensional neuron layer with the minimum Euclidean distance is corrected by using the second Euclidean distance to obtain the temperature estimated value of the flexible container.
10. The artificial intelligence control system of a dietary fiber meter of claim 9, wherein the heating control module comprises a thermal circuit network model comprising M nodes, each node having a thermal capacity, thermal barriers between adjacent nodes, each node corresponding to at least a sample, a flexible container, a holder, a first infrared image sensor, a second infrared image sensor, and N heaters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410545818.5A CN118131678B (en) | 2024-05-06 | 2024-05-06 | Artificial intelligence control system of dietary fiber tester |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410545818.5A CN118131678B (en) | 2024-05-06 | 2024-05-06 | Artificial intelligence control system of dietary fiber tester |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118131678A CN118131678A (en) | 2024-06-04 |
| CN118131678B true CN118131678B (en) | 2024-07-09 |
Family
ID=91236231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410545818.5A Active CN118131678B (en) | 2024-05-06 | 2024-05-06 | Artificial intelligence control system of dietary fiber tester |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118131678B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN208435234U (en) * | 2018-02-05 | 2019-01-29 | 广东美的生活电器制造有限公司 | Heating vessel and its heating control circuit |
| CN116036945A (en) * | 2023-02-18 | 2023-05-02 | 海能未来技术集团股份有限公司 | Non-contact stirring device and dietary fiber tester |
| CN117804526A (en) * | 2023-12-13 | 2024-04-02 | 中建新疆建工集团第三建设工程有限公司 | Underground pipe gallery environment detection system and method based on inspection robot |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393884B (en) * | 2011-10-12 | 2015-04-15 | 杭州电子科技大学 | Hot continuous rolling electromagnetic induction heating temperature prediction method based on BP (back-propagation) neural network |
-
2024
- 2024-05-06 CN CN202410545818.5A patent/CN118131678B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN208435234U (en) * | 2018-02-05 | 2019-01-29 | 广东美的生活电器制造有限公司 | Heating vessel and its heating control circuit |
| CN116036945A (en) * | 2023-02-18 | 2023-05-02 | 海能未来技术集团股份有限公司 | Non-contact stirring device and dietary fiber tester |
| CN117804526A (en) * | 2023-12-13 | 2024-04-02 | 中建新疆建工集团第三建设工程有限公司 | Underground pipe gallery environment detection system and method based on inspection robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118131678A (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Nonlinear observer design for PEM fuel cell power systems via second order sliding mode technique | |
| CN113792478B (en) | Heat source layout temperature field reliability analysis method based on integrated depth proxy model | |
| CN118131678B (en) | Artificial intelligence control system of dietary fiber tester | |
| CN104199441A (en) | Blast furnace multiple working condition fault separation method and system based on sparse contribution plot | |
| Zamyad et al. | Behavior identification of IPMC actuators using Laguerre-MLP network with consideration of ambient temperature and humidity effects on their performance | |
| CN112155434A (en) | Temperature control method, temperature control device, control equipment, storage medium and heater | |
| CN114781248A (en) | Off-line reinforcement learning method and device based on state offset correction | |
| Li et al. | Temperature compensation of piezo-resistive pressure sensor utilizing ensemble AMPSO-SVR based on improved AdaBoost. RT | |
| CN109144136A (en) | A kind of temperature control system and method for three sections of heated type heating furnaces | |
| CN110285567B (en) | Method and device for predicting outlet water temperature and water body heating device | |
| CN111442852A (en) | Device and method for detecting surface temperature of heating element in cylindrical cavity | |
| CN110018679B (en) | Closed-loop test system and test method for spacecraft autonomous temperature control system | |
| CN110471474A (en) | A kind of temperature and humidity intelligent control system of power distribution cabinet | |
| CN103397312B (en) | A kind of control method of LPCVD explained hereafter environment and Controlling System thereof | |
| Xu et al. | Dual extreme learning machine based online spatiotemporal modeling with adaptive forgetting factor | |
| CN115332649A (en) | Battery temperature control management method, device, equipment and readable storage medium | |
| CN115062847A (en) | Carbon fiber heating energy consumption prediction method and system based on logistic regression algorithm | |
| CN115309207B (en) | Temperature control method of intelligent closestool | |
| CN118068879B (en) | Control system of electric heating digestion instrument | |
| US11543381B2 (en) | Method and apparatus for operating a gas sensor | |
| EP2550623B1 (en) | Improved control system simulator and simplified interconnection control system | |
| Mojžišová et al. | Model of indirect temperature measurement by neural network | |
| Chen et al. | Self-tuning PID temperature controller based on flexible neural network | |
| JP2711766B2 (en) | Electric carpet control | |
| Neelamengam et al. | Neural network based density measurement |
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 |