CN112859977A - Dryer control method and system based on artificial intelligence and computer equipment - Google Patents
Dryer control method and system based on artificial intelligence and computer equipment Download PDFInfo
- Publication number
- CN112859977A CN112859977A CN202110388021.5A CN202110388021A CN112859977A CN 112859977 A CN112859977 A CN 112859977A CN 202110388021 A CN202110388021 A CN 202110388021A CN 112859977 A CN112859977 A CN 112859977A
- Authority
- CN
- China
- Prior art keywords
- data
- dryer
- artificial intelligence
- product
- drying
- 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.)
- Withdrawn
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 152
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000001035 drying Methods 0.000 claims abstract description 133
- 239000000463 material Substances 0.000 claims abstract description 105
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 78
- 238000012544 monitoring process Methods 0.000 claims description 36
- 239000000523 sample Substances 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 25
- 238000004140 cleaning Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 21
- 238000006243 chemical reaction Methods 0.000 claims description 20
- 230000010354 integration Effects 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 238000012805 post-processing Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000010365 information processing Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 11
- 210000002569 neuron Anatomy 0.000 description 11
- 235000013305 food Nutrition 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000007791 dehumidification Methods 0.000 description 6
- 238000011144 upstream manufacturing Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000007580 dry-mixing Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 238000002329 infrared spectrum Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 235000019629 palatability Nutrition 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000013330 chicken meat Nutrition 0.000 description 1
- 238000002939 conjugate gradient method Methods 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009834 vaporization Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F26—DRYING
- F26B—DRYING SOLID MATERIALS OR OBJECTS BY REMOVING LIQUID THEREFROM
- F26B25/00—Details of general application not covered by group F26B21/00 or F26B23/00
- F26B25/22—Controlling the drying process in dependence on liquid content of solid materials or objects
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F26—DRYING
- F26B—DRYING SOLID MATERIALS OR OBJECTS BY REMOVING LIQUID THEREFROM
- F26B21/00—Arrangements or duct systems, e.g. in combination with pallet boxes, for supplying and controlling air or gases for drying solid materials or objects
- F26B21/06—Controlling, e.g. regulating, parameters of gas supply
- F26B21/08—Humidity
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F26—DRYING
- F26B—DRYING SOLID MATERIALS OR OBJECTS BY REMOVING LIQUID THEREFROM
- F26B21/00—Arrangements or duct systems, e.g. in combination with pallet boxes, for supplying and controlling air or gases for drying solid materials or objects
- F26B21/06—Controlling, e.g. regulating, parameters of gas supply
- F26B21/12—Velocity of flow; Quantity of flow, e.g. by varying fan speed, by modifying cross flow area
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Drying Of Solid Materials (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to a dryer control method, a dryer control system and a computer device based on artificial intelligence, by acquiring the operation data of the dryer, acquiring the state parameter data of the product before and after drying, acquiring the target parameter data of the dried product, and calculates the control target parameter of the dryer according to the acquired data and by an artificial intelligence algorithm, further controlling and adjusting the operation parameters of each temperature zone in the dryer to achieve the control target parameters according to the control target parameters of the dryer, thereby the dried product can reach the target parameter data, the problems that the water content of the product is estimated by a spot check in the traditional technology, a large amount of time and labor are consumed, and materials are wasted are avoided, and the dryer is controlled in an intelligent manner, so that the operation complexity of the dryer and the degree of dependence on experienced operators are reduced.
Description
Technical Field
The application relates to a material drying technology, in particular to a dryer control method, a dryer control system and computer equipment based on artificial intelligence.
Background
Currently, the moisture requirements of commercial drying products generally need to be less than a specified value. Taking pet food and feed as an example, if the moisture value of the material is too large, the material is easy to go moldy in the storage and transportation processes; conversely, if the moisture value of the material is too low, the palatability of the material is reduced (animals do not like to eat) and also the production cost is increased.
In the continuous dryer for drying feed and food in the market, an operator needs to set parameters such as target temperature of each subarea in the dryer, rotating speed of a fan, rotating speed of a moisture exhausting fan, opening and closing degree of a moisture exhausting air door, rotating speed of a conveyor belt and the like according to experience. These parameters all affect the drying rate of the product and ultimately the moisture content of the finished product. In order to operate the dryer in the best condition, the operator needs to adjust all parameters according to experience, which makes it extremely complicated to operate the dryer.
Disclosure of Invention
In view of the above, it is necessary to provide a dryer control method, a control device and a computer device based on artificial intelligence to solve the above-mentioned problem that the operation of the dryer is complicated due to the adjustment of parameters by an operator according to experience.
An artificial intelligence based dryer control method, the method comprising:
acquiring operation data of a dryer, wherein the operation data of the dryer is used for representing the drying performance of the dryer;
acquiring state parameter data of products before and after drying;
acquiring target parameter data of a dried product;
calculating to obtain control target parameters of the dryer through an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data;
and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the control target parameters according to the control target parameters of the dryer.
In one embodiment, the pre-drying and post-drying product state parameter data includes post-drying product moisture content data, and the drying product target parameter data includes drying product target moisture content data; the step of obtaining control target parameters of the dryer through calculation by an artificial intelligence algorithm according to the obtained operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data comprises the following steps: calculating the deviation between the dried product moisture content data and the dried product target moisture content data; if the deviation is within the set threshold value, the operation parameters of each temperature zone in the dryer are unchanged, and the operation parameters of each temperature zone in the dryer are used as the control target parameters of the dryer; if the deviation is not within the set threshold, acquiring updated product state parameter data before and after drying, operation data of the dryer and target moisture content data of the dried product through an artificial intelligence unit, and calculating to obtain a new control target parameter of the dryer through an artificial intelligence algorithm according to the acquired data; and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the new control target parameters according to the new control target parameters of the dryer.
In one embodiment, the calculating, by an artificial intelligence algorithm, to obtain the control target parameter of the dryer specifically includes: performing data cleaning and integration on the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data; carrying out standardization processing on the integrated data; carrying out artificial intelligence analysis on the data after the standardization processing; carrying out data conversion on the data subjected to the artificial intelligence analysis to obtain control target parameters of the dryer; the data cleaning is to delete invalid data and data with noise larger than a preset value from original data; the data integration is to combine the operation data of the dryer and the product state parameter data of the time sequence into a data structure with the material unit as an index.
In one embodiment, the transformation function for normalizing the integrated data is as follows:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*To normalize the processed data, μ is the mean of the historical data used for artificial intelligence model training and σ is the standard deviation of the historical data used for artificial intelligence model training.
In one embodiment, the conversion function for data conversion is:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
x is a maximum and minimum; x is the number ofMax，xMinThe maximum value and the minimum value of the output command are corresponding to the control device for controlling and adjusting the dryer.
In one embodiment, the artificial intelligence algorithm is implemented by using an artificial intelligence model, and the artificial intelligence model is obtained by the following method: acquiring training data sets of sample materials corresponding to the material units respectively, wherein the training data sets of the sample materials comprise state parameter data of the sample materials before and after drying, target parameter data of the dried sample materials and operation data of the dryer; carrying out data cleaning, integration and standardization processing on a training data set of the sample material corresponding to each material unit to obtain standardized training data corresponding to the material units; and training the deep neural network by back propagation by adopting the standardized training data corresponding to the material units until the loss function reaches the minimum value, and obtaining the artificial intelligence model corresponding to the material units.
In one embodiment, the calculating, according to the acquired operation data of the dryer, the product state parameter data before and after drying, and the target parameter data of the dried product, a control target parameter of the dryer by an artificial intelligence algorithm includes: and inputting the acquired operating data of the dryer, the product state parameter data before and after drying and the dried product target parameter data into the artificial intelligence model to obtain the control target parameters of the dryer output by the artificial intelligence model.
An artificial intelligence based dryer control system, the system comprising:
the dryer state monitoring unit is arranged in the dryer and used for acquiring the operation data of the dryer, and the operation data of the dryer is used for representing the drying performance of the dryer;
the information input unit is used for inputting the target parameter data of the dried product;
the product state monitoring unit is arranged in the dryer and used for acquiring the product state parameter data before and after drying and judging whether the dried product state parameter data reaches the target parameter data of the dried product;
the artificial intelligence unit is used for receiving the data acquired by the dryer state monitoring unit, the information input unit and the product state monitoring unit and calculating to acquire a control target parameter of the operation of the dryer through an artificial intelligence algorithm;
and the dryer control unit is used for receiving the control target parameters of the dryer output by the artificial intelligence unit and controlling and adjusting the operation parameters of each temperature zone in the dryer to achieve the control target parameters.
In one embodiment, the artificial intelligence unit comprises: the information receiving module is used for receiving data acquired by the dryer state monitoring unit, the information input unit and the product state monitoring unit; the information processing module comprises a data preprocessing module, an artificial intelligence model and a data post-processing module, the data preprocessing module carries out data cleaning and integration on the data received by the information receiving module, the integrated data is subjected to standardization processing and then is sent to the artificial intelligence model, the data analyzed by the artificial intelligence model is sent to the data post-processing module for data conversion, and control target parameters of the dryer are obtained; and the instruction sending module is used for receiving the control target parameters obtained after the data post-processing module converts the control target parameters, generating corresponding control instructions and sending the control instructions to the dryer control unit.
In one embodiment, the function of the normalization process of the data pre-processing module is:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*Mu is the mean value of historical data used for artificial intelligence model training, and sigma is the standard deviation of the historical data used for artificial intelligence model training;
the data post-processing module performs data conversion with a conversion function of:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
x is a maximum and minimum; x is the number ofMax，xMinThe maximum value and the minimum value of the output command are corresponding to the control device for controlling and adjusting the dryer.
In one embodiment, the dryer control unit includes an actuator, the actuator including: the PID temperature controller is used for receiving the control instruction and outputting a control signal to the steam valve so as to control the temperature in the dryer; the fan rotating speed controller is used for receiving the control instruction and outputting a control signal to the fan motor so as to control the rotating speed of the fan; the opening controller of the dehumidifying air door is used for receiving the control instruction and controlling the opening and closing degree of the dehumidifying air door so as to control the humidity of the circulating air in the dryer; the moisture exhausting fan rotating speed controller is used for receiving the control instruction and outputting a control signal to the moisture exhausting fan motor so as to control the rotating speed of the moisture exhausting fan; and the conveyor belt rotating speed controller is used for receiving the control instruction and outputting a control signal to the conveyor belt motor so as to control the rotating speed of the conveyor belt.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as set forth above.
The dryer control method, the dryer control system and the computer device based on artificial intelligence acquire the state parameter data of the products before and after drying and the target parameter data of the dried products by acquiring the operating data of the dryer, and calculates the control target parameter of the dryer according to the acquired data and by an artificial intelligence algorithm, further controlling and adjusting the operation parameters of each temperature zone in the dryer to achieve the control target parameters according to the control target parameters of the dryer, thereby the dried product can reach the target parameter data, the problems that the water content of the product is estimated by a spot check in the traditional technology, a large amount of time and labor are consumed, and materials are wasted are avoided, and the dryer is controlled in an intelligent manner, so that the operation complexity of the dryer and the degree of dependence on experienced operators are reduced.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of an application environment of an artificial intelligence-based dryer control method;
FIG. 2 is a schematic flow chart illustrating an embodiment of a dryer control method based on artificial intelligence;
FIG. 3 is a schematic flow chart diagram illustrating the steps for obtaining an artificial intelligence model in one embodiment;
FIG. 4 is a block diagram of an embodiment of an artificial intelligence based dryer control system;
FIG. 5 is a block diagram of an artificial intelligence based dryer control system in another embodiment;
FIG. 6 is a block diagram of an artificial intelligence based dryer control system in yet another embodiment;
FIG. 7 is a block diagram of the information processing module of FIG. 5;
FIG. 8 is a schematic view illustrating an operation of a dryer according to an embodiment;
FIG. 9 is a diagram of an artificial intelligence model in one embodiment;
FIG. 10 is a graph of moisture content of the material at the outlet of the dryer in one embodiment;
FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The application relates to a dryer which is mechanical equipment used for drying products such as feed and food so as to achieve the purpose of removing moisture in the products. The moisture requirement of the dried product is typically within a specified range to meet storage requirements. Taking pet food and feed as an example, if the moisture value of the material is too large, the material is easy to go moldy in the storage and transportation processes; conversely, if the moisture value of the material is too low, the palatability of the material is reduced (animals do not like to eat), and excessive drying leads to increased production costs. In order to ensure that the produced product meets the moisture requirement of the product, quality testing staff need to regularly measure and evaluate the moisture content of the product. If the product after the drying is finished through sampling inspection, whether the moisture reaches the standard is detected, however, the whole process needs about 1 hour from the product drying to the detection, and if the product is detected to be unqualified, the material in the 1 hour is changed into unqualified product. Therefore, the current method of estimating the moisture content of the product by spot inspection not only consumes a lot of time and labor, but also causes a lot of material waste.
And the thickness of the material entering the dryer is not uniform due to the unstable output of the equipment (such as the bulking machine, the granulator and the like) upstream of the dryer, while the current dryers are generally based on the assumption that the output of the machines is constant, and once the output of the machines changes, the total amount of moisture to be removed also changes, and the moisture content of the dried material also has large difference due to the fact that the dryers cannot recognize the change. At present, the continuous dryer for drying feed and food in the market needs an operator to set parameters such as target temperature of each subarea in the dryer, rotating speed of a fan, rotating speed of a moisture exhausting fan, opening and closing degree of a moisture exhausting air door, rotating speed of a conveyor belt and the like according to experience. And these parameters all affect the drying rate of the product and ultimately the moisture content of the finished product. Therefore, in order to ensure that the produced product meets the moisture requirement of the product and the dryer can work in the best state, the operator needs to adjust all parameters according to experience, thereby making the operation of the dryer extremely complicated.
Based on this, the present application proposes a dryer control method based on artificial intelligence, which can be applied to the application environment shown in fig. 1. Wherein terminal 102 is in communication with dryer 104. The terminal 102 obtains the control target parameter of the dryer by obtaining the operation data of the dryer 104, the product state parameter data before and after drying and the drying product target parameter data, and according to the obtained operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data, calculating by an artificial intelligence algorithm to obtain the control target parameter of the dryer, and then according to the control target parameter of the dryer, controlling and adjusting the operation parameter of each temperature zone in the dryer to reach the control target parameter, so that the final drying product can reach the requirement of the drying product target parameter data. The terminal 102 may be, but is not limited to, various servers, personal computers, notebook computers, smart phones, tablet computers, portable wearable devices, and the like.
In one embodiment, as shown in fig. 2, there is provided an artificial intelligence-based dryer control method, which is described by taking the method as an example of being applied to the terminal in fig. 1, and includes the following steps:
The operation data of the dryer is used for representing the drying performance of the dryer, and includes but is not limited to the temperature and humidity of air at the air supply port of each temperature zone in the dryer, the temperature and humidity of air in the moisture exhaust pipeline of each temperature zone, the temperature and humidity of air before and after the heat exchanger, the temperature and humidity of air in the main air exhaust pipe, the rotating speed of a fan motor of each temperature zone, the rotating speed of a moisture exhaust motor, the rotating speed of a conveyor belt motor and the like. The operation data of the dryer is obtained by detecting air temperature and humidity sensors arranged at air supply ports of various temperature zones, air temperature and humidity sensors in humidity exhaust pipelines of various temperature zones, air temperature and humidity sensors in front and at back of a heat exchanger, air temperature and humidity sensors in a main exhaust pipe, fan motor frequency converters of various temperature zones, humidity exhaust motor frequency converters, conveyor motor frequency converters and the like.
And step 204, acquiring the state parameter data of the product before and after drying.
The product state parameter data before and after drying comprises the moisture content of the product to be dried before entering the dryer and after drying, the moisture content before drying can be analyzed and collected by arranging a near infrared spectrum analyzer at the inlet end of the dryer so as to analyze and collect the moisture content and the proportion of main components of the product before entering the dryer, and the moisture content before drying can also be obtained by calculating related data of upstream equipment, for example, if the upstream equipment is a bulking machine, the moisture content can be obtained by indirectly calculating the data of the mass flow of materials of the bulking machine, the water adding amount of a modulator, the steam adding amount of the bulking machine and the like by combining with a corresponding calculation formula; the moisture content of the dried product can be analyzed by arranging a microwave moisture meter at the outlet end of the dryer. The product state parameter data before and after drying may further include a material mass flow rate of the drying zone, and specifically, the material mass flow rate refers to a material mass of a material passing through an effective cross section of the dryer in a unit time, and may be directly or indirectly obtained through operation data of an upstream device, for example, if the upstream device is a bulking machine, the mass flow rate may be obtained by converting a frequency of a feeder of a modulator of the bulking machine, or may be obtained by detecting a flow sensor installed at an outlet of the bulking machine or an inlet of the dryer.
The following specific process for indirectly calculating the moisture value and mass flow of the material at the feeding port of the dryer by using a calculation formula, for example, specifically, firstly, collecting the parameters of the upstream equipment as follows: for the adjuster part, the maximum dry mixing ratio MR, the dry mixing humidity M and the steam quantity S are collectedPWater amount WPAnd the amount of injected FatPThe units are percentages; for the expander section, the steam quantity S is collectedEAnd water amount WEThe units are all percentages; for other parts, the acquisition of melting point data T is also neededmeltEvaporation temperature TevaVaporization heat dissipation HvaAnd a specific heat adjustment coefficient delta. And then the moisture value of the material at the feeding port of the dryer is obtained by indirect calculation of the parameters as follows:
wherein,
for the calculated result, defined as the moisture value of the material at the feeding port of the dryer, MM is the melting moisture,
the water evaporation per kg was estimated. Specifically, MM ═ TWR/TMR, where TWR is the total water amount, calculated by the following formula: TWR ═ MR × (M + S)P+WP+SE+WE) TMR is the total mass flow rate of the material to be expanded, and is represented by the following formulaAnd calculating to obtain: TMR + MR × (S)P+WP+FatP+SE+WE)。
Then it is calculated by the following formula:
wherein HlossThe heat loss per kg of extrudate is calculated by the following formula:
while
As an estimate of the specific heat in the extruder barrel,
estimation value of material mass flow
Then it is calculated by the following formula:
and step 206, acquiring target parameter data of the dried product.
The drying product target parameter data includes, but is not limited to, target moisture content data of the drying product, which may be obtained by manual input or automatic acquisition.
And step 208, calculating to obtain control target parameters of the dryer through an artificial intelligence algorithm according to the acquired data.
The control target parameters comprise temperature parameters for controlling each temperature zone, fan rotating speed parameters, moisture exhaust air door opening degree parameters, moisture exhaust fan rotating speed parameters, conveying belt rotating speed parameters and the like. Specifically, the temperature parameters of each temperature zone can be realized by controlling the steam valve of the corresponding temperature zone, the fan rotating speed parameters can be realized by controlling the fan motor of the corresponding temperature zone, the opening degree parameters of the moisture exhaust air door can be realized by controlling the opening degree of the moisture exhaust air door of the corresponding temperature zone, the rotating speed parameters of the moisture exhaust air door can be realized by controlling the motor of the moisture exhaust air door of the corresponding temperature zone, and the rotating speed parameters of the conveying belt can be realized by controlling the motor of the conveying belt of the corresponding temperature zone. The control target parameter is used for controlling and adjusting the operation parameters of each temperature zone in the dryer, so that the dried product can reach the target parameter data. And the artificial intelligence algorithm is realized based on a deep neural network. In the embodiment, the control target parameter of the dryer is calculated through an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data, so that the dependence on experience operators in the operation of the dryer is reduced.
And step 210, controlling and adjusting the operation parameters of each temperature zone in the dryer to reach the control target parameters according to the control target parameters of the dryer.
Specifically, based on the calculated control target parameters of the dryer, the operation parameters of each temperature zone in the dryer are controlled and adjusted to reach the control target parameters, and then the dryer is controlled based on the control target parameters, so that the dried product can reach the target parameter data.
According to the dryer control method based on artificial intelligence, the operating data of the dryer are obtained, the product state parameter data before and after drying are obtained, the dried product target parameter data are obtained, the control target parameter of the dryer is obtained through calculation according to the obtained data and an artificial intelligence algorithm, and then the operating parameters of each temperature zone in the dryer are controlled and adjusted to reach the control target parameter according to the control target parameter of the dryer, so that the dried product can reach the target parameter data.
In one embodiment, the pre-drying and post-drying product state parameter data comprises post-drying product moisture content data, and the drying product target parameter data comprises drying product target moisture content data; the step of obtaining control target parameters of the dryer through calculation by an artificial intelligence algorithm according to the obtained operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data comprises the following steps: calculating the deviation between the dried product moisture content data and the dried product target moisture content data; if the deviation is within the set threshold value, the operation parameters of each temperature zone in the dryer are unchanged, namely the current operation parameters of each temperature zone in the dryer are used as the control target parameters of the dryer; if the deviation is not within the set threshold, acquiring updated product state parameter data before and after drying, operation data of the dryer and target moisture content data of the dried product through an artificial intelligence unit, calculating to obtain a new control target parameter of the dryer through an artificial intelligence algorithm according to the acquired data, and controlling and adjusting operation parameters of each temperature zone in the dryer to achieve the new control target parameter according to the new control target parameter of the dryer.
In one embodiment, the calculating the control target parameter of the dryer through an artificial intelligence algorithm specifically includes: performing data cleaning and integration on the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data; carrying out standardization processing on the integrated data; carrying out artificial intelligence analysis on the data after the standardization processing; and carrying out data conversion on the data subjected to the artificial intelligence analysis to obtain control target parameters of the dryer. The data cleaning is to delete invalid data and data with noise larger than a preset value from original data; the data integration is to combine the operation data of the dryer and the product state parameter data of the time series into a data structure with the material unit as an index. The material unit is material classification information which is obtained by classifying different material formulas and is used for expressing the material formulas and the material types.
In one embodiment, as shown in FIG. 3, the artificial intelligence algorithm is implemented using an artificial intelligence model obtained by:
The training data set of the sample materials comprises state parameter data of the sample materials before and after drying, target parameter data of the dried sample materials and operation data of the dryer. It can be understood that the training data set of the sample material may be real data acquired during the process of drying the material, and is mainly used for training the neural network, so that the neural network can learn corresponding characteristics from a large amount of training data, and then the control target parameters of the dryer can be obtained based on certain input data. It should be noted that, when training the neural network, in order to make the output accuracy of the model obtained after training higher, the training data set may further include more training data, for example, in addition to the above training data, the training data may further include the air temperature after the heat exchanger in the drying zone, the air temperature in the dehumidifying air duct in the drying zone, the fan speed in the drying zone, the motor speed of the material conveyor belt, the set temperature in the drying zone, the material thickness at different positions (such as the left side, the middle portion, and the right side of the conveyor belt) on the drying zone conveyor belt, and the like.
And because the combination ratio of the various raw materials corresponding to different material units may be different, the drying degree corresponding to the same drying condition may also be different. Based on the method, corresponding training data sets can be respectively constructed for different material units, and the training data sets are used for training and obtaining the artificial intelligence model corresponding to the material units, so that the output of the model is more accurate.
And 304, performing data cleaning, integration and standardization on the training data set of the sample material corresponding to each material unit to obtain standardized training data corresponding to the material units.
The data cleaning is to delete the invalid data and the data with noise larger than a preset value from the original data. The data integration is to combine the operation data of the dryer and the product state parameter data of the time series into a data structure with the material unit as an index. The transformation function for normalizing the data is:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*To normalize the processed data, μ is the mean of the historical data used for artificial intelligence model training and σ is the standard deviation of the historical data used for artificial intelligence model training.
Specifically, in this embodiment, the training data set of the sample material corresponding to each material unit is subjected to data cleaning, integration, and standardization, so as to obtain the standardized training data corresponding to the material unit.
And step 306, training the deep neural network by back propagation by adopting the standardized training data corresponding to the material units until the loss function reaches the minimum value, and obtaining the artificial intelligence model corresponding to the material units.
The neural network is composed of an input layer, a hidden layer and an output layer. The input layer and the hidden layer, the hidden layer and the hidden layer, and the hidden layer and the output layer are all connected. The neural network used in this embodiment is a deep neural network, which has 3 hidden layers, 1 input layer, and 1 output layer. Each layer in the neural network is composed of a plurality of neurons, wherein the number of neurons in the input layer is determined by the number of the model input characteristic data, and the neurons in the output layer output control target parameters of the dryer, and the output number of the neurons is determined based on the number of the control target parameters.
Specifically, in this embodiment, the normalized training data corresponding to the material unit is used, forward propagation is performed first, any input training data is calculated from left to right, and then the result vector is propagated in reverse to train the deep neural network, and the loss function is iteratively solved by combining a gradient descent method or a higher-level conjugate gradient method or a quasi-newton method (BFGS), until the loss function reaches a minimum value, the training process is ended, so as to obtain the artificial intelligence model corresponding to the material unit. Wherein, the loss function can be realized by a mean square error loss function or an absolute error loss function.
In the above embodiment, the training data sets of the sample materials corresponding to the material units are obtained, the training data sets of the sample materials corresponding to each material unit are subjected to data cleaning, integration and standardization processing to obtain the standardized training data corresponding to the material units, the standardized training data corresponding to the material units are adopted, the deep neural network is trained through back propagation until the loss function reaches the minimum value, the artificial intelligence model corresponding to the material units is obtained, and therefore the corresponding artificial intelligence model is selected based on the material units of the drying product in actual application, and the output of the model is more accurate.
In one embodiment, the method for obtaining the control target parameter of the dryer through calculation by an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data specifically includes: and inputting the acquired operating data of the dryer, the product state parameter data before and after drying and the dried product target parameter data into the acquired artificial intelligence model to obtain the control target parameters of the dryer output by the artificial intelligence model. Specifically, the corresponding artificial intelligence model can be selected based on the material unit of the drying product, so that the output of the model is more accurate.
It should be understood that although the various steps in the flowcharts of fig. 1-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-3 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps or stages.
In one embodiment, as shown in fig. 4, there is provided an artificial intelligence based dryer control system, including: dryer state monitoring unit 1, product state monitoring unit 2, information input unit 3, artificial intelligence unit 4 and dryer control unit 5, wherein:
the dryer state monitoring unit 1 is arranged in the dryer and used for acquiring operation data of the dryer, wherein the operation data of the dryer is used for representing the drying performance of the dryer;
the product state monitoring unit 2 is arranged in the dryer and used for acquiring the product state parameter data before and after drying and judging whether the dried product state parameter data reaches the target parameter data of the dried product;
the information input unit 3 is used for inputting the target parameter data of the drying product;
the artificial intelligence unit 4 is used for receiving the data acquired by the dryer state monitoring unit, the information input unit and the product state monitoring unit and calculating to obtain a control target parameter of the operation of the dryer through an artificial intelligence algorithm;
and the dryer control unit 5 is used for receiving the control target parameters of the dryer output by the artificial intelligence unit and controlling and adjusting the operation parameters of each temperature zone in the dryer to achieve the control target parameters.
For specific limitations of the artificial intelligence based dryer control system, reference may be made to the above limitations of the artificial intelligence based dryer control method, which are not described herein again. All or part of each module in the artificial intelligence-based dryer control system can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In order to further explain the principle of the present application, the present application is further explained with reference to fig. 4 to 10, specifically, a dryer state monitoring unit 1, a product state monitoring unit 2, and an information input unit 3 are disposed in the dryer, and the dryer state monitoring unit 1 is configured to monitor information such as air temperature and humidity, motor rotation speed, and air door opening and closing degree of each area of the dryer.
Dryer state monitoring unit 1 is mainly through setting up air temperature and humidity sensor and converter in the dryer, and temperature and humidity sensor includes: air temperature and humidity sensors at air supply ports of various temperature zones, air temperature and humidity sensors in dehumidification pipelines of various temperature zones, air temperature and humidity sensors before heat exchangers, air temperature and humidity sensors before and after heat exchangers and air temperature and humidity sensors in main exhaust ducts, wherein the air temperature and humidity state monitoring inside the dryer is realized through the temperature and humidity sensors; the frequency converter comprises a fan motor frequency converter, a dehumidifying motor frequency converter and a conveyor belt motor frequency converter in each temperature zone, the monitoring of the moving speed and the air flowing state of products in the dryer is realized through the frequency converters, and the output of the unit is represented by the following code numbers:
·
represents the temperature of the air in the air supply port of the dryer "#" zone at the time t;
·
represents the humidity of the air in the air supply opening of the dryer "#" area at the time t;
·
represents the temperature of the air in the dehumidification duct of the "#" section of the dryer at time t;
·
represents the humidity of the air in the dehumidifying pipe of the dryer "#" zone at the time t;
·
represents the temperature of the air before the heat exchanger in the "#" section of the dryer at time t;
·
represents the humidity of the air before the heat exchanger in the "#" section of the dryer at time t;
·
represents the temperature of the air after the heat exchanger in the "#" section of the dryer at time t;
·
represents the humidity of the air after the heat exchanger in the "#" section of the dryer at time t;
·
showing the temperature of the air in the main exhaust duct of the dryer at the time t;
·
showing the humidity of the air in the main exhaust duct of the dryer at the time t;
·
indicating the fan motor speed in dryer "#" zone at time t;
·
the rotating speed of a conveyor belt motor on the upper layer of the dryer at the time t is shown;
·
indicating the rotating speed of a conveyor belt motor at the lower layer of the dryer at the time t;
·
represents the opening and closing degree of a dehumidifying air door in a "#" area of the dryer at the time t;
the product state monitoring unit 2 is used for monitoring the moisture content of the product to be dried before entering the dryer and after drying, and the moisture content before drying can be analyzed and collected by arranging a near infrared spectrum analyzer at the inlet end of the dryer to analyze and collect the moisture content and the main component proportion of the product before entering the dryer; the moisture content of the dried product can be analyzed by arranging a microwave moisture meter at the outlet end of the dryer. The output code of the unit is:
·
indicating the thickness of the material at the inlet of the dryer at time t;
·
representing the moisture content of the material at the feeding port of the dryer at the time t;
·
representing the moisture content of the material at the discharge hole of the dryer at the time t;
the information input unit 3 can adopt a manual input or automatic acquisition mode, mainly acquires the moisture value of a target, and the output code number of the information input unit is as follows:
·MTargetrepresenting a target moisture value of the product being dried;
as shown in fig. 4, the dryer state monitoring unit 1, the product state monitoring unit 2, and the information input unit 3 transmit the collected data to the artificial intelligence element 4.
As shown in fig. 5, the artificial intelligence unit 4 includes an information receiving module 6, an information processing module 7, and an instruction transmitting module 8, wherein the information receiving module 6 is configured to receive data collected by the dryer state monitoring unit 1, the product state monitoring unit 2, and the information input unit 3, and the information receiving module 6 transmits the collected information to the information processing module 7.
As shown in fig. 7, the information processing module 7 includes a data preprocessing module 14, an artificial intelligence model 15, and a data post-processing module 16, wherein the data preprocessing module 14 cleans and recombines the information received by the information receiving module 6, the data cleaning deletes invalid data and data with excessive noise from the original data center, the data recombination combines time-series dryer state data and product state data into a data structure using material units as indexes, the combined data is standardized, and the conversion function of the standardized processing is:
wherein y is the original data, y*To normalize the processed data, μ is the mean of the historical data used for model training and σ is the standard deviation of the historical data used for model training.
Upper conveyer motor speed at time t
For example, assuming that there are N sets of data for model training, the transformed data is:
wherein:
the data processed by the data preprocessing module 14 is input into the artificial intelligence model 15, it should be understood that the artificial intelligence model 15 may be a deep neural network, or an artificial intelligence model such as a bayesian network, and it is within the scope of the present patent that the artificial intelligence model is put into the above-mentioned process method for performing the drying calculation.
The data processed by the artificial intelligence model 15 is sent to the data post-processing module 16, the data post-processing module 16 converts the analyzed data, and the conversion function is:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
training data x maximum and minimum; x is the number ofMax，xMinAnd outputting the maximum value and the minimum value of the command to the corresponding control mechanism.
The data converted by the data post-processing module 16 is sent to the instruction sending module 8, and the instruction sending module 8 sends the control instruction to the dryer control unit 5 according to the analysis result.
As shown in fig. 6, the dryer control unit 5 further includes an actuator including: PID temperature controller 9, fan rotational speed controller 10, hydrofuge air door aperture controller 11, hydrofuge fan rotational speed controller 12, conveyer belt rotational speed controller 13, PID temperature controller 9 output control signal to the steam valve thereby the temperature in the control drying-machine, fan rotational speed controller 10, hydrofuge fan rotational speed controller 12, conveyer belt rotational speed controller 13 output the control command received to each motor thereby control the fan, the hydrofuge fan, the rotational speed of conveyer belt, the hydrofuge air door aperture controller 11 controls the degree of opening and closing of the hydrofuge air door thereby control the humidity of the inside circulating air of drying-machine according to the control command.
FIG. 8 shows a control principle of a dryer, after the dryer is started, a dryer state monitoring unit monitors operation information of the dryer through sensors and frequency converters installed at each part, a product monitoring unit can monitor product states of product input and output, an information input unit can manually or automatically input a target moisture value and other key information of a product, an artificial intelligence unit integrates the received information and outputs the information to a dryer control unit through analysis of an artificial intelligence model, the dryer control unit can control temperature and fan rotation speed in the dryer, opening degree of a moisture exhaust air door, rotation speed of a moisture exhaust fan and rotation speed of a conveyor belt through input control instructions, a discharge outlet product moisture detection device is further arranged at a dryer outlet, the outlet moisture value is compared with the target moisture value, and if the deviation is too large, the artificial intelligence is driven to analyze again, and directly carries out real-time parameter adjustment on the dryer.
The following description of specific example 1 is made:
as shown in fig. 9, the present embodiment uses a certain brand of natural gas dryer, and the dryer is a continuous double-layer dryer for the drying test of dog food mainly made of corn, wheat and chicken, wherein each zone has a heat exchanger, a fan, a moisture-removing pipeline, a moisture-removing air door, a moisture-removing blower and other devices. The dehumidifying pipelines of the three areas are all connected with the main exhaust duct of the dryer, and the dryer control system based on artificial intelligence is arranged on the dryer.
Dryer starts, and dryer state monitoring unit 1 monitors out dryer key operation data, includes: air temperature and humidity before heat exchange of each temperature zone
Air temperature and humidity after heat exchange of each temperature zone
Air temperature and humidity in dehumidification pipeline of each temperature zone
Air temperature and humidity in main exhaust duct
Fan speed of each zone
Rotational speed of conveyor belt motor
And the opening degree of the moisture exhaust air door of each temperature zone
The product state monitoring unit 2 monitors the moisture content value of the product to be dried and the dried product in real time
And the thickness of the product to be dried on the conveyor belt
Information that the drying product cannot be acquired by the sensor, for example: product target moisture value (M)Target) The product surface area (S), etc., are acquired by the information input unit 3. The information in the information input unit can be input manually or can be automatically acquired according to the product information.
The artificial intelligence unit 4 collects information in the dryer state monitoring unit 1, the product state monitoring unit 2, and the information input unit 3 through the information collection module 6, and transmits the information to the data preprocessing module 14 following a data structure shown in the following table.
Where t is the Unix timestamp.
The data preprocessing module 14 cleans up the received data and performs standardized data preprocessing,
rotational speed of upper layer conveyor belt
For example, based on historical data, an average of data used for model training is obtained
Standard deviation of
Normalized conveyor speed
Comprises the following steps:
the normalized data is sent to the artificial intelligence model 15, which in this embodiment uses a deep neural network with 3 hidden layers. The input layer comprises 34 neurons, the first and second hidden layers respectively comprise 150 neurons, the third hidden layer comprises 100 neurons, and the output layer comprises 14 neurons. Sequentially corresponding region 1 target temperature T by neuron of output layer1Zone 2 target temperature T2Zone 3 target temperature T3Zone 1 fan target speed ωFan1Zone 2 fan target speed ωFan2Zone 3 fan target speed ωFan3Zone 1 target opening O of the dehumidification damper1Zone 2 target opening O of the dehumidification damper2Zone 3 target opening O of the dehumidification damper3Zone 1 rowTarget rotating speed omega of wet fanExhaust1Target rotation speed omega of moisture-removing fan in region 2Exhaust2 Zone 3 dehumidifier target speed ωExhaust3Upper conveyor motor target speed omegaCT1And target rotation speed omega of lower layer conveyor belt motorCT2. The activation equation for each neuron in the deep neural network uses the Sigmoid equation shown below.
Where S is the single neuron output value and x is the input value.
The normalized data finally reaches the output layer through the input layer and the three hidden layers, and is sent to the data post-processing module 16.
The data post-processing module 16 converts the data output by the artificial intelligence model 15 into values that can be used directly to control the corresponding actuators. Target opening degree O of moisture exhaust damper in region 11For example, 0.72, the extreme value of the damper opening of the training data is
The control extreme value of the damper control mechanism is OMin＝0，OMax100. So that the converted target opening degree of the dehumidifying air door
Comprises the following steps:
the post-processed data are shown in the following table:
the data post-processing module 16 sends the data of the table above to the instruction sending module 8.
The instruction sending module 8 forwards the control parameters to the corresponding executing mechanism in the dryer control unit 5. Wherein, the target temperature control instruction of each temperature zone is sent to the PID temperature controller 9 of the corresponding temperature zone; the fan speed control instructions of each temperature zone are sent to the corresponding fan speed controllers 10; the opening control instructions of the dehumidifying air doors of each temperature zone are sent to the corresponding opening controllers 11 of the dehumidifying air doors; the dehumidifying fan rotational speed control instruction is sent to the dehumidifying fan rotational speed controller 12; the respective layer conveyor speed control instructions are sent to the corresponding conveyor speed controllers 13. And each control unit adjusts the operation parameters of the dryer according to the received control instruction.
After the set time, the moisture value of the dried product is detected at the discharge port of the dryer, and if the deviation of the moisture value of the product at the discharge port and the target moisture value of the product meets the product quality requirement, namely the deviation is within the range of the set threshold value, the operation parameters of the dryer do not need to be changed.
Fig. 10 is a schematic diagram showing the moisture content of dog food during the drying process in the dryer.
If the deviation of the moisture value is too large, namely the deviation is larger than the set threshold range, the artificial intelligence unit 4 starts to collect the updated product state information (including the inlet product state information and the outlet product state information), the dryer operation information, the product target moisture value and other key information, and predicts new dryer control parameters according to the data.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 11. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an artificial intelligence based dryer control method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring operation data of a dryer, wherein the operation data of the dryer is used for representing the drying performance of the dryer;
acquiring state parameter data of products before and after drying;
acquiring target parameter data of a dried product;
calculating to obtain control target parameters of the dryer through an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data;
and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the control target parameters according to the control target parameters of the dryer.
In one embodiment, the pre-drying and post-drying product state parameter data comprises post-drying product moisture content data, and the drying product target parameter data comprises drying product target moisture content data; the processor when executing the computer program further realizes the following steps: calculating the deviation between the dried product moisture content data and the dried product target moisture content data; if the deviation is within the set threshold value, the operation parameters of each temperature zone in the dryer are unchanged, and the operation parameters of each temperature zone in the dryer are used as the control target parameters of the dryer; if the deviation is not within the set threshold, acquiring updated product state parameter data before and after drying, operation data of the dryer and target moisture content data of the dried product through an artificial intelligence unit, and calculating to obtain a new control target parameter of the dryer through an artificial intelligence algorithm according to the acquired data; and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the new control target parameters according to the new control target parameters of the dryer.
In one embodiment, the processor, when executing the computer program, further performs the steps of: performing data cleaning and integration on the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data; carrying out standardization processing on the integrated data; carrying out artificial intelligence analysis on the data after the standardization processing; carrying out data conversion on the data subjected to the artificial intelligence analysis to obtain control target parameters of the dryer; the data cleaning is to delete invalid data and data with noise larger than a preset value from original data; the data integration is to combine the operation data of the dryer and the product state parameter data of the time sequence into a data structure with the material unit as an index.
In one embodiment, the transformation function for normalizing the integrated data is as follows:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*For the normalized data, μ is the mean of the historical data for artificial intelligence model training and σ is the mean for artificial intelligence model trainingStandard deviation of historical data for type training.
In one embodiment, the conversion function for data conversion is:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
x is a maximum and minimum; x is the number ofMax，xMinThe maximum value and the minimum value of the output command are corresponding to the control device for controlling and adjusting the dryer.
In one embodiment, the artificial intelligence algorithm is implemented by an artificial intelligence model, and the processor executes the computer program to further implement the following steps: acquiring training data sets of sample materials corresponding to the material units respectively, wherein the training data sets of the sample materials comprise state parameter data of the sample materials before and after drying, target parameter data of the dried sample materials and operation data of the dryer; carrying out data cleaning, integration and standardization processing on a training data set of the sample material corresponding to each material unit to obtain standardized training data corresponding to the material units; and training the deep neural network by back propagation by adopting the standardized training data corresponding to the material units until the loss function reaches the minimum value, and obtaining the artificial intelligence model corresponding to the material units.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and inputting the acquired operating data of the dryer, the product state parameter data before and after drying and the dried product target parameter data into the artificial intelligence model to obtain the control target parameters of the dryer output by the artificial intelligence model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring operation data of a dryer, wherein the operation data of the dryer is used for representing the drying performance of the dryer;
acquiring state parameter data of products before and after drying;
acquiring target parameter data of a dried product;
calculating to obtain control target parameters of the dryer through an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data;
and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the control target parameters according to the control target parameters of the dryer.
In one embodiment, the pre-drying and post-drying product state parameter data comprises post-drying product moisture content data, and the drying product target parameter data comprises drying product target moisture content data; the computer program when executed by the processor further realizes the steps of: calculating the deviation between the dried product moisture content data and the dried product target moisture content data; if the deviation is within the set threshold value, the operation parameters of each temperature zone in the dryer are unchanged, and the operation parameters of each temperature zone in the dryer are used as the control target parameters of the dryer; if the deviation is not within the set threshold, acquiring updated product state parameter data before and after drying, operation data of the dryer and target moisture content data of the dried product through an artificial intelligence unit, and calculating to obtain a new control target parameter of the dryer through an artificial intelligence algorithm according to the acquired data; and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the new control target parameters according to the new control target parameters of the dryer.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing data cleaning and integration on the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data; carrying out standardization processing on the integrated data; carrying out artificial intelligence analysis on the data after the standardization processing; carrying out data conversion on the data subjected to the artificial intelligence analysis to obtain control target parameters of the dryer; the data cleaning is to delete invalid data and data with noise larger than a preset value from original data; the data integration is to combine the operation data of the dryer and the product state parameter data of the time sequence into a data structure with the material unit as an index.
In one embodiment, the transformation function for normalizing the integrated data is as follows:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*To normalize the processed data, μ is the mean of the historical data used for artificial intelligence model training and σ is the standard deviation of the historical data used for artificial intelligence model training.
In one embodiment, the conversion function for data conversion is:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
x is a maximum and minimum; x is the number ofMax，xMinThe maximum value and the minimum value of the output command are corresponding to the control device for controlling and adjusting the dryer.
In one embodiment, the artificial intelligence algorithm is implemented using an artificial intelligence model, and the computer program when executed by the processor further performs the steps of: acquiring training data sets of sample materials corresponding to the material units respectively, wherein the training data sets of the sample materials comprise state parameter data of the sample materials before and after drying, target parameter data of the dried sample materials and operation data of the dryer; carrying out data cleaning, integration and standardization processing on a training data set of the sample material corresponding to each material unit to obtain standardized training data corresponding to the material units; and training the deep neural network by back propagation by adopting the standardized training data corresponding to the material units until the loss function reaches the minimum value, and obtaining the artificial intelligence model corresponding to the material units.
In one embodiment, the computer program when executed by the processor further performs the steps of: and inputting the acquired operating data of the dryer, the product state parameter data before and after drying and the dried product target parameter data into the artificial intelligence model to obtain the control target parameters of the dryer output by the artificial intelligence model.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (13)
1. A dryer control method based on artificial intelligence is characterized by comprising the following steps:
acquiring operation data of a dryer, wherein the operation data of the dryer is used for representing the drying performance of the dryer;
acquiring state parameter data of products before and after drying;
acquiring target parameter data of a dried product;
calculating to obtain control target parameters of the dryer through an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data;
and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the control target parameters according to the control target parameters of the dryer.
2. The method of claim 1, wherein the pre-oven, post-oven product condition parameter data comprises post-oven product moisture content data, and the oven product target parameter data comprises oven product target moisture content data; the step of obtaining control target parameters of the dryer through calculation by an artificial intelligence algorithm according to the obtained operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data comprises the following steps:
calculating the deviation between the dried product moisture content data and the dried product target moisture content data;
if the deviation is within the set threshold value, the operation parameters of each temperature zone in the dryer are unchanged, and the operation parameters of each temperature zone in the dryer are used as the control target parameters of the dryer;
if the deviation is not within the set threshold, acquiring updated product state parameter data before and after drying, operation data of the dryer and target moisture content data of the dried product through an artificial intelligence unit, and calculating to obtain a new control target parameter of the dryer through an artificial intelligence algorithm according to the acquired data; and controlling and adjusting the operating parameters of each temperature zone in the dryer to achieve the new control target parameters according to the new control target parameters of the dryer.
3. The method of claim 1, wherein the control target parameters of the dryer are calculated by an artificial intelligence algorithm, specifically:
performing data cleaning and integration on the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data;
carrying out standardization processing on the integrated data;
carrying out artificial intelligence analysis on the data after the standardization processing;
carrying out data conversion on the data subjected to the artificial intelligence analysis to obtain control target parameters of the dryer;
the data cleaning is to delete invalid data and data with noise larger than a preset value from original data;
the data integration is to combine the operation data of the dryer and the product state parameter data of the time sequence into a data structure with the material unit as an index.
4. The method of claim 3, wherein the transformation function for normalizing the integrated data is:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*To normalize the processed data, μ is the mean of the historical data used for artificial intelligence model training and σ is the standard deviation of the historical data used for artificial intelligence model training.
5. The method of claim 4, wherein the transfer function for data conversion is:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
x is a maximum and minimum; x is the number ofMax，xMinThe maximum value and the minimum value of the output command are corresponding to the control device for controlling and adjusting the dryer.
6. The method of claim 1, wherein the artificial intelligence algorithm is implemented using an artificial intelligence model, the artificial intelligence model being obtained by:
acquiring training data sets of sample materials corresponding to the material units respectively, wherein the training data sets of the sample materials comprise state parameter data of the sample materials before and after drying, target parameter data of the dried sample materials and operation data of the dryer;
carrying out data cleaning, integration and standardization processing on a training data set of the sample material corresponding to each material unit to obtain standardized training data corresponding to the material units;
and training the deep neural network by back propagation by adopting the standardized training data corresponding to the material units until the loss function reaches the minimum value, and obtaining the artificial intelligence model corresponding to the material units.
7. The method of claim 6, wherein calculating the control target parameter of the dryer through an artificial intelligence algorithm according to the acquired operation data of the dryer, the product state parameter data before and after drying and the drying product target parameter data comprises:
and inputting the acquired operating data of the dryer, the product state parameter data before and after drying and the dried product target parameter data into the artificial intelligence model to obtain the control target parameters of the dryer output by the artificial intelligence model.
8. The utility model provides a drying-machine control system based on artificial intelligence which characterized in that includes:
the dryer state monitoring unit is arranged in the dryer and used for acquiring the operation data of the dryer, and the operation data of the dryer is used for representing the drying performance of the dryer;
the information input unit is used for inputting the target parameter data of the dried product;
the product state monitoring unit is arranged in the dryer and used for acquiring the product state parameter data before and after drying and judging whether the dried product state parameter data reaches the target parameter data of the dried product;
the artificial intelligence unit is used for receiving the data acquired by the dryer state monitoring unit, the information input unit and the product state monitoring unit and calculating to acquire a control target parameter of the operation of the dryer through an artificial intelligence algorithm;
and the dryer control unit is used for receiving the control target parameters of the dryer output by the artificial intelligence unit and controlling and adjusting the operation parameters of each temperature zone in the dryer to achieve the control target parameters.
9. The system of claim 8, wherein the artificial intelligence unit comprises:
the information receiving module is used for receiving data acquired by the dryer state monitoring unit, the information input unit and the product state monitoring unit;
the information processing module comprises a data preprocessing module, an artificial intelligence model and a data post-processing module, the data preprocessing module carries out data cleaning and integration on the data received by the information receiving module, the integrated data is subjected to standardization processing and then is sent to the artificial intelligence model, the data analyzed by the artificial intelligence model is sent to the data post-processing module for data conversion, and control target parameters of the dryer are obtained;
and the instruction sending module is used for receiving the control target parameters obtained after the data post-processing module converts the control target parameters, generating corresponding control instructions and sending the control instructions to the dryer control unit.
10. The system of claim 9, wherein the function of the normalization process of the data pre-processing module is:
wherein y is original data including operation data of the dryer, and state parameter data of the product before and after drying, and y*Mu is the mean value of historical data used for artificial intelligence model training, and sigma is the standard deviation of the historical data used for artificial intelligence model training;
the data post-processing module performs data conversion with a conversion function of:
wherein x is*Is a control target parameter of the dryer; x is training data obtained by analyzing the data y subjected to the standardization processing through an artificial intelligence model;
x is a maximum and minimum; x is the number ofMax，xMinThe maximum value and the minimum value of the output command are corresponding to the control device for controlling and adjusting the dryer.
11. The system of claim 8, wherein the dryer control unit comprises an actuator comprising:
the PID temperature controller is used for receiving the control instruction and outputting a control signal to the steam valve so as to control the temperature in the dryer;
the fan rotating speed controller is used for receiving the control instruction and outputting a control signal to the fan motor so as to control the rotating speed of the fan;
the opening controller of the dehumidifying air door is used for receiving the control instruction and controlling the opening and closing degree of the dehumidifying air door so as to control the humidity of the circulating air in the dryer;
the moisture exhausting fan rotating speed controller is used for receiving the control instruction and outputting a control signal to the moisture exhausting fan motor so as to control the rotating speed of the moisture exhausting fan;
and the conveyor belt rotating speed controller is used for receiving the control instruction and outputting a control signal to the conveyor belt motor so as to control the rotating speed of the conveyor belt.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010640981.1A CN111766910A (en) | 2020-07-06 | 2020-07-06 | Dryer control method and system based on artificial intelligence |
| CN2020106409811 | 2020-07-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112859977A true CN112859977A (en) | 2021-05-28 |
Family
ID=72724695
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010640981.1A Pending CN111766910A (en) | 2020-07-06 | 2020-07-06 | Dryer control method and system based on artificial intelligence |
| CN202110388021.5A Withdrawn CN112859977A (en) | 2020-07-06 | 2021-04-12 | Dryer control method and system based on artificial intelligence and computer equipment |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010640981.1A Pending CN111766910A (en) | 2020-07-06 | 2020-07-06 | Dryer control method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111766910A (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110324A (en) * | 2021-04-12 | 2021-07-13 | 江苏丰尚智能科技有限公司 | Training method and device for dryer parameter optimization model and computer equipment |
| CN113048777A (en) * | 2021-04-12 | 2021-06-29 | 江苏丰尚智能科技有限公司 | Dryer control method and device based on discharged water content and computer equipment |
| CN113157018B (en) * | 2021-04-12 | 2022-06-21 | 江苏丰尚智能科技有限公司 | Method and device for controlling temperature of dryer, computer equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103760312A (en) * | 2014-01-25 | 2014-04-30 | 安徽大洋自动化科技有限公司 | High-efficiency online drying system for grain moisture |
| CN105767165B (en) * | 2016-04-14 | 2019-09-13 | 吉林大学 | A kind of method for drying cereal based on Kalman filtering |
| CN106227038A (en) * | 2016-07-29 | 2016-12-14 | 中国人民解放军信息工程大学 | Grain drying tower intelligent control method based on neutral net and fuzzy control |
| CN107577257B (en) * | 2017-09-11 | 2019-07-12 | 吉林大学 | A kind of investigating method that the grain based on temperature zone is continuous drying |
| US11268729B2 (en) * | 2018-05-07 | 2022-03-08 | Johnson Controls Tyco IP Holdings LLP | Building management system with apparent indoor temperature and comfort mapping |
-
2020
- 2020-07-06 CN CN202010640981.1A patent/CN111766910A/en active Pending
-
2021
- 2021-04-12 CN CN202110388021.5A patent/CN112859977A/en not_active Withdrawn
Also Published As
| Publication number | Publication date |
|---|---|
| CN111766910A (en) | 2020-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112859977A (en) | Dryer control method and system based on artificial intelligence and computer equipment | |
| CN113048777A (en) | Dryer control method and device based on discharged water content and computer equipment | |
| Batuwatta-Gamage et al. | A physics-informed neural network-based surrogate framework to predict moisture concentration and shrinkage of a plant cell during drying | |
| CN113157018B (en) | Method and device for controlling temperature of dryer, computer equipment and storage medium | |
| CN113048780A (en) | Control method and device of dryer, computer equipment and storage medium | |
| Li et al. | A neural-network-based model predictive control scheme for grain dryers | |
| Lawrence et al. | Modeling in-bin rice drying using natural air and controlled air drying strategies | |
| Alam et al. | Neural network modeling of drying of rice in BAU-STR dryer | |
| CN118066807B (en) | Control system of intelligent drying cabin | |
| CN113156807A (en) | Control method and device of dryer, computer equipment and storage medium | |
| Ahmad et al. | Machine learning based grain moisture estimation for real-time monitoring of high-temperature paddy drying silo | |
| CN113566557B (en) | Grain dryer intelligent control method based on deep neural network | |
| CN113110324A (en) | Training method and device for dryer parameter optimization model and computer equipment | |
| Barriga et al. | Advanced data modeling for industrial drying machine energy optimization | |
| CN113053469B (en) | Method and device for predicting moisture of drying material, computer equipment and storage medium | |
| CN108158028A (en) | Cigarette cut tobacco process multistage distributed monitoring and diagnostic method based on tile and hierarchy thought | |
| CN116624971A (en) | Air conditioner monitoring system | |
| Thant et al. | ANN modelling for prediction of moisture content and drying characteristics of paddy in fluidized bed | |
| CN113096747A (en) | Method and device for predicting moisture content of discharged material of dryer and computer equipment | |
| da Silva Rodrigues et al. | Thermal signature: A method to extract characteristics from infrared thermography data applied to the development of animal heat stress classifier models | |
| Białobrzewski | Neural modeling of relative air humidity | |
| Mellmann et al. | Experiments on hot-air drying of wheat in a semi-technical mixed-flow dryer | |
| KR101657137B1 (en) | Intelligent Pigsty Air Vent Method Of Control | |
| Norouzian et al. | Prediction of feed abrasive value by artificial neural networks and multiple linear regression | |
| Molano-Jimenez et al. | Temperature and relative humidity prediction in swine livestock buildings |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210528 |
|
| WW01 | Invention patent application withdrawn after publication |