CN111346688B - Wheat dampening control method and device - Google Patents
Wheat dampening control method and device Download PDFInfo
- Publication number
- CN111346688B CN111346688B CN201811585126.4A CN201811585126A CN111346688B CN 111346688 B CN111346688 B CN 111346688B CN 201811585126 A CN201811585126 A CN 201811585126A CN 111346688 B CN111346688 B CN 111346688B
- Authority
- CN
- China
- Prior art keywords
- wheat
- humidity
- neural network
- environmental
- parameter information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02B—PREPARING GRAIN FOR MILLING; REFINING GRANULAR FRUIT TO COMMERCIAL PRODUCTS BY WORKING THE SURFACE
- B02B1/00—Preparing grain for milling or like processes
- B02B1/04—Wet treatment, e.g. washing, wetting, softening
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02B—PREPARING GRAIN FOR MILLING; REFINING GRANULAR FRUIT TO COMMERCIAL PRODUCTS BY WORKING THE SURFACE
- B02B7/00—Auxiliary devices
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Bakery Products And Manufacturing Methods Therefor (AREA)
Abstract
The invention relates to the technical field of flour processing, in particular to a wheat dampening control method and device, which are used for acquiring the environmental temperature and the environmental humidity within a preset time period and acquiring wheat parameter information; inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network; processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine a target water attachment; according to the determined target water attachment amount, the wheat is attached with water, so that the water attachment amount can be automatically adjusted in a self-adaptive manner according to the change of the environmental temperature, the environmental humidity and the parameter information of the wheat, the intelligent control is realized, and the efficiency and the accuracy are improved.
Description
Technical Field
The invention relates to the technical field of flour processing, in particular to a wheat dampening control method and device.
Background
In the process of flour processing, wheat needs to be watered and moistened firstly, the wheat with water is processed after being stored for a certain time in a moistening storage, the quality and the flour yield of the wheat can be improved, and in the process of moistening, wheat grains and air media continuously exchange heat and moisture and can influence the moistening effect of the wheat, so that the control of the moistening amount of the wheat is necessary for the moistening effect of the wheat and the production quality of flour.
In the prior art, wheat dampening control is realized by mainly designing hardware components and structures of wheat dampening equipment and dampening wheat based on the designed wheat dampening equipment, the water demand of the wheat dampening equipment is mainly manually adjusted based on manual experience, the efficiency is low, the dampening amount is possibly inaccurate, and the wheat moistening effect and the flour production quality are reduced.
Disclosure of Invention
The embodiment of the invention provides a wheat dampening control method and device, and aims to solve the problems that wheat dampening control is inaccurate and efficiency is low in the prior art.
The embodiment of the invention provides the following specific technical scheme:
a wheat dampening control method comprises the following steps:
acquiring the environmental temperature and the environmental humidity within a preset time period, and acquiring wheat parameter information;
inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network;
processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine a target water attachment;
and (5) dampening the wheat according to the determined target dampening amount.
Optionally, the obtaining of the ambient temperature and the ambient humidity within the preset time period specifically includes: respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period; wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
Optionally, before inputting into the pre-trained neural network, further comprising: and respectively normalizing the environmental temperature, the environmental humidity and the wheat parameter information to preset intervals.
Optionally, based on the pre-trained neural network, processing the ambient temperature, ambient humidity, and wheat parameter information to determine a target water application amount, specifically including:
determining a weighted ambient temperature according to the ambient temperatures corresponding to a plurality of update cycles based on the pre-trained neural network;
determining weighted ambient humidity according to the ambient humidity corresponding to the plurality of update periods;
determining target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information; wherein the wheat parameter information includes but is not limited to: wheat temperature, wheat moisture and wheat volume weight.
Optionally, the training mode of the neural network is as follows:
acquiring a training sample set; each training sample in the training sample set at least comprises environmental temperature, environmental humidity and wheat parameter information in a preset time period;
respectively acquiring the moisture content of the wheat flour corresponding to each training sample aiming at each training sample in the training sample set;
and training the neural network according to the training sample set, wherein the input of the neural network is the training sample set, the output of the neural network is the determined target water content, and the target function of the neural network is the minimization of the error value between the determined target water content and the corresponding moisture content of the wheat flour.
A wheat dampening control device comprising:
the acquisition module is used for acquiring the ambient temperature and the ambient humidity within a preset time period and acquiring the parameter information of the wheat;
the input module is used for inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network;
the determining module is used for processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine the target water attachment;
and the dampening module is used for dampening the wheat according to the determined target dampening amount.
Optionally, when the ambient temperature and the ambient humidity within the preset time period are obtained, the obtaining module is specifically configured to: respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period; wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
Optionally, based on the pre-trained neural network, the environmental temperature, the environmental humidity and the wheat parameter information are processed, and when the target water attachment is determined, the determining module is specifically configured to:
determining a weighted ambient temperature according to the ambient temperatures corresponding to a plurality of update cycles based on the pre-trained neural network;
determining weighted ambient humidity according to the ambient humidity corresponding to the plurality of update periods;
determining target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information; wherein the wheat parameter information includes but is not limited to: wheat temperature, wheat moisture and wheat volume weight.
An electronic device, comprising:
at least one memory for storing a computer program;
at least one processor for implementing the steps of any one of the above wheat watering control methods when executing a computer program stored in a memory.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the above-described wheat watering control methods.
In the embodiment of the invention, the environmental temperature and the environmental humidity within a preset time period are obtained, and the parameter information of wheat is obtained; inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network; processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine a target water attachment; according to the method, the wheat is watered according to the determined target watering amount, so that the environmental temperature, the environmental humidity and the wheat parameter information are processed based on the pre-trained neural network, the target watering amount is determined, the watering amount can be automatically adjusted according to the change of the environmental temperature, the environmental humidity and the wheat parameter information in a self-adaptive manner, manual adjustment according to experience is not needed, the efficiency is improved, the processing precision of the moisture content of the flour of the wheat is greatly improved, and intelligent control is realized based on the pre-trained neural network, so that the method is simpler and more accurate.
Drawings
FIG. 1 is a flow chart of a wheat dampening control method in an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a principle of neural network training in the wheat watering control method according to an embodiment of the present invention;
FIG. 3 is a schematic structural view of a wheat dampening control device in an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In practice, in the process of processing wheat into flour, wheat needs to be wetted and moistened firstly, and then is processed into flour after standing for a period of time after being wetted, because moistening means that the wetted wheat or the wheat after being heated and moisture-regulated is put into a bin and stored for a certain time, so that moisture is distributed more uniformly in wheat grains, and a series of physical and biochemical changes are generated, and finally the process of the water regulation process is completed, after free water in the wheat is increased through moisture regulation, the toughness of the cortex of the wheat is enhanced, the structure of starch granules in endosperm becomes loose, the structural force is reduced, the changes are very beneficial to grinding and screening, the endosperm is easy to break and has low energy consumption, the cortex is not easy to break, so that the cortex is not easy to mix with the flour in grinding and screening, therefore, after moisture regulation is performed on the wheat, the color and quality of the flour are good, the flour yield is high, and therefore, wetting and moistening the wheat are very important for the wheat, however, the excessive water absorption may be wasted, and the insufficient water absorption may not achieve the wheat wetting effect, and finally, the production quality of the flour and the moisture content of the flour are affected.
In the prior art, the wheat dampening device based on design usually damps water, the dampening amount is mainly manually adjusted according to experience, the efficiency is low, and the dampening amount is not easy to control and may be inaccurate.
Based on the problems, in the embodiment of the invention, the influence of the environmental temperature and the environmental humidity on the wheat dampening process is considered, the neural network is trained according to the environmental temperature and the environmental humidity and the wheat parameter information, such as the wheat temperature, the wheat humidity, the wheat volume weight and the like, and the value of each weight in the neural network is finally determined, so that the dampening amount of the wheat can be automatically adjusted and controlled according to the trained neural network and based on the environmental temperature, the environmental humidity and the wheat parameter information, the stability of the moisture content of the flour is realized, and the flour quality is improved.
Referring to fig. 1, in the embodiment of the present invention, a specific process of a wheat watering control method is as follows:
step 100: and acquiring the ambient temperature and the ambient humidity within a preset time period, and acquiring the parameter information of the wheat.
In the embodiment of the invention, the environmental temperature and the environmental humidity are considered when the moisture content is determined, because the wheat grains and the air medium continuously exchange heat and moisture when the wheat is processed to absorb moisture. When the atmospheric temperature rises, the molecular motion is intensified, the hydrothermal conduction effect is enhanced, the inward movement and the outward conduction of the moisture of wheat grains are facilitated, the permeation speed is accelerated, the moisture transfer in the wheat is accelerated, and the time required for the moisture transfer to reach the balance can be effectively shortened. When the air humidity is higher, the balance moisture of the wheat is higher, the water absorption speed is higher, meanwhile, the humidity increase is not beneficial to the inter-powder operation, so that the time required by wheat wetting treatment is shorter and the water absorption amount is correspondingly reduced when the wheat is high in temperature and humidity; and when the weather is dry and the air temperature is low, the water attachment amount is increased, and the wheat wetting time is prolonged, so that in order to ensure the stability of the flour production quality, the water attachment amount of the wheat is controlled in real time according to the change of the environmental temperature and the environmental humidity.
In addition, in the embodiment of the invention, the influence of the wheat parameter information on the water retention and the final flour of the wheat is also considered, and other factors influencing the quality of the water retention and the flour of the wheat can be combined, so that the embodiment of the invention is not limited.
When step 100 is executed, the following two parts can be divided:
a first part: and acquiring the ambient temperature and the ambient humidity within a preset time period.
The method specifically comprises the following steps: and respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period.
Wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
That is, the wheat dampening amount is controlled by considering the ambient temperature and the ambient humidity during the period of time when the wheat dampening is still, because the wheat dampening system is a large hysteresis control system, generally not less than 24 hours, and therefore the preset time period is a period of time after the beginning of the wheat dampening.
Moreover, according to practical experience, after wheat is soaked in water, the wheat is usually kept still for 24 hours, and the wheat wetting effect and the flour quality are better, so that the soaking time of the wheat is preferably set to be 24 hours, of course, the soaking time can also be set according to practical situations, and the embodiment of the invention is not limited.
The preset time period includes a plurality of update cycles, that is, in the embodiment of the present invention, the preset time period is divided into a plurality of update cycles, and the ambient temperature and the ambient humidity in each update cycle are respectively obtained.
In the embodiment of the invention, the ambient temperature and the ambient humidity are the atmospheric temperature and the atmospheric humidity, and in the concrete implementation, the weather forecast data can be introduced through a network, and the ambient temperature and the ambient humidity corresponding to each updating period can be obtained from the weather forecast data. Since the atmospheric ambient temperature and the ambient humidity are usually updated every two hours, the update cycle may be set to 2 hours, that is, for example, the duration of the preset time period is 24 hours, and the update cycle is 2 hours, the preset time period may be divided into 12 update cycles, and then the ambient temperature and the ambient humidity corresponding to 12 sets of different update cycles may be obtained.
A second part: and acquiring wheat parameter information.
Wherein the wheat parameter information includes but is not limited to: wheat temperature, wheat humidity, wheat volume weight and the like, and the embodiments of the present invention are not limited.
Specifically, in the embodiment of the invention, probe channels for detecting moisture can be arranged at the inlet and the outlet of the dampening machine, and a moisture detector is added after wheat wetting and flour forming to detect the humidity of wheat. In addition, corresponding sensors can be arranged to detect the wheat temperature, the wheat volume weight and the like, so that various parameter information such as the wheat temperature, the wheat humidity, the production process and the like which influence the moisture content of the wheat flour can be comprehensively sensed.
Step 110: and inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network.
Further, before inputting into the neural network trained in advance, the method further comprises: and respectively normalizing the environmental temperature, the environmental humidity and the wheat parameter information into preset intervals.
In the embodiment of the present invention, the normalization process is performed, which is mainly because, when the neural network is trained, normalization is performed within a preset interval, which can reduce the range of various input data, shorten the learning time, and improve the efficiency and accuracy, therefore, when the neural network is trained to perform actual application of wheat watering control, the input data also needs to be normalized.
For example, the input range for ambient temperature is typically: [ -40 °,40 ° ], the input range of ambient humidity is: [ 0%, 100% ], the input range of the wheat temperature is: -40 °,40 ° ], the input range of the wheat volume weight is [0,1000], and the wheat volume weight can be normalized to a preset interval according to a preset normalization processing algorithm, for example, to the [ -1,1] and [0,1] intervals, respectively.
It should be noted that, for the wheat humidity, since the actual value range is also [0,1], the normalization process may not be performed.
Step 120: and processing the environmental temperature, the environmental humidity and the wheat parameter information based on a pre-trained neural network to determine the target water attachment.
In the embodiment of the invention, the environmental temperature, the environmental humidity and the wheat parameter information are comprehensively considered based on the pre-trained neural network, so that more accurate and reliable target water attachment is determined.
When the step 120 is executed, the method specifically includes:
1) and determining the weighted ambient temperature according to the ambient temperatures corresponding to the plurality of updating periods based on the pre-trained neural network.
2) And determining the weighted ambient humidity according to the ambient humidity corresponding to the plurality of updating periods.
If a plurality of groups of average values of the environmental temperature and the environmental humidity are directly used as input values, the temperature and humidity conditions of the environment cannot be accurately reflected due to great discreteness in the actual watering control, so that in the embodiment of the invention, the influence of the environmental temperature and the environmental humidity on the moisture content of the wheat flour at different moments is considered to be not equivalent, the influence of the environmental humidity and the environmental temperature at a certain moment on the moisture content of the final flour is probably large, and the influence of the environmental humidity and the environmental temperature at other moments on the moisture content of the final flour is small.
However, if the environmental temperature and the environmental humidity are divided on the time axis and are calculated in a statistical manner, the divided intervals are too many, the workload is too large, and the realization of the engineering algorithm is difficult, so in the embodiment of the invention, an artificial intelligence control algorithm is introduced, namely, a neural network is trained in advance, the final network weight is fitted to the actual control parameter through supervised learning, the complexity is simplified, the intelligence of the wheat watering control is improved, after a plurality of groups of environmental temperatures and environmental humidities in a preset time period are obtained, the weight of each group of environmental temperature and environmental humidity is determined based on the neural network trained in advance, so that the weighted environmental temperature and the weighted environmental humidity are calculated, the weighted environmental temperature and the weighted environmental humidity are not obtained through simply averaging the environmental temperatures and the environmental humidities of each group but are learned through training, the influence weights of the environmental temperatures and the environmental humidities at different moments on the final flour quality, resulting in a weighted ambient temperature and a weighted ambient humidity.
3) And determining the target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information.
Step 130: and (5) dampening the wheat according to the determined target dampening amount.
Namely, the wheat is added with the determined target water adding amount to realize the wheat wetting by adding water.
In the embodiment of the invention, the environmental temperature, the environmental humidity and the wheat parameter information are processed based on the pre-trained neural network, the target water-absorbing amount is determined, and the wheat is absorbed according to the determined target water-absorbing amount, so that the water-absorbing amount can be automatically adjusted according to the change of the environmental temperature, the environmental humidity and the wheat parameter information in a self-adaptive manner when the wheat absorbs water, manual adjustment according to experience is not needed, the efficiency is improved, the processing precision of the moisture content of the flour of the wheat is greatly improved, the uniformity and consistency of the moisture content of the flour can be ensured, for example, the moisture content of the flour can be improved from 0.15% to 0.0365% through testing, and the economic benefit and the product quality of a flour mill are improved. And moreover, the artificial intelligence algorithm based on the neural network can also reduce the complexity of wheat dampening control and improve the intelligence.
The following briefly explains the training mode of the neural network in the embodiment of the present invention, and the training mode of the neural network is as follows:
1) acquiring a training sample set; wherein, each training sample in the training sample set at least comprises the environmental temperature, the environmental humidity and the wheat parameter information in a preset time period.
Further, still include: and preprocessing the environmental temperature, the environmental humidity and the wheat parameter information in each training sample, and respectively normalizing the environmental temperature, the environmental humidity and the wheat parameter information to preset intervals.
2) And respectively acquiring the moisture content of the wheat flour corresponding to each training sample aiming at each training sample in the training sample set.
Wherein, the moisture content of the wheat flour is the true value actually detected, namely the theoretical value of supervised learning.
3) And training a neural network according to the training sample set, wherein the input of the neural network is the training sample set, the output is the determined target water uptake, and the target function of the neural network is the minimum of the error value between the determined target water uptake and the corresponding moisture content of the wheat flour.
The neural network may be a feedforward neural network, and the like, and the embodiment of the present invention is not limited.
The method is characterized in that a difference value is calculated according to a true value of the moisture content of actual wheat flour and a result output by a neural network, a supervised learning error value can be obtained, then, the weight value of each network and the like can be reversely updated, the error value is minimized through repeated iteration for a plurality of times, is gradually close to 0 and is stable, and the expected requirement of an algorithm is met.
Based on the above embodiment, specifically referring to fig. 2, a schematic diagram of a principle of training a neural network in a wheat watering control method according to an embodiment of the present invention is shown, and as can be seen from fig. 2, a training process can be divided into the following parts:
a first part: and (4) inputting.
1) Taking the duration of the preset time period as 24 hours and the update period as 2 hours as an example, 12 sets of ambient temperatures and ambient humidity can be respectively obtained, where the ambient humidity is respectively the ambient humidity at 24 moments, the ambient humidity at 22 moments … …, and the ambient humidity at 2 moments, and the ambient temperatures are respectively the ambient temperature at 24 moments, the ambient temperature at 22 moments … …, and the ambient temperature at 2 moments.
2) Taking the wheat parameter information as the wheat temperature, the wheat humidity and the wheat volume weight as an example, the wheat humidity and the wheat volume weight are obtained.
Then the acquired 12 groups of environmental humidity and environmental humidity, wheat temperature, wheat humidity and wheat volume weight are subjected to normalization pretreatment and then input into a neural network.
A second part: and (6) processing.
Referring to fig. 2, the feedforward neural network includes a plurality of neurons, each two neurons have a connection weight therebetween, and when data is input to a current neuron, the output of the current neuron is determined by calculating an activation function of the current neuron, and is output through multi-layer calculation until a final output result is obtained.
Initial values of each connection weight, activation function and offset vector in the feedforward neural network can be generated by adopting a random generation function, and the value range of the initial values is set to be [ -1,1], so that overfitting and local convergence of the initial state of the algorithm can be prevented.
In the embodiment of the invention, when the wheat controls input data in the water-landing process, the output result of each layer can be calculated between each layer of the feedforward neural network according to the connection weight, the deflection vector, the activation function and the like, then the output result is transmitted in the forward direction until the output result is output, as shown in fig. 2, the weighted environment temperature is output through the weighted calculation of a plurality of neurons according to 12 groups of environment temperatures, and the weighted environment humidity is output through the weighted calculation of a plurality of neurons according to 12 groups of environment humidity; and then, outputting the target water attachment of the wheat through the weighted calculation of a plurality of neurons according to the weighted environment temperature and the weighted environment humidity, as well as the wheat humidity, the wheat temperature and the wheat volume weight.
And a third part: and (6) outputting.
Namely, the target water attachment of wheat is output through a feedforward neural network.
The fourth part: and (5) backward propagation and updating iteration.
In the embodiment of the invention, the moisture content of the corresponding wheat flour is taken as expected output with guidance for learning, the expected output is a theoretical value of supervised learning, an error value of the supervised learning is obtained according to the value and an output value of a feedforward neural network, and then the weight and the deflection are updated reversely, so that a large number of training samples can be used for training the feedforward neural network, and the feedforward neural network has reasoning information of wheat soaking when the error value is gradually close to 0 and stable through repeated iteration.
Thus, in the embodiment of the invention, environmental data and wheat parameter information are considered, a neural network is trained, and a wheat watering control method based on the neural network is provided, which is more intelligent and simpler for a wheat watering control system, because the wheat watering control system is a large-lag control system, factors influencing the moisture content precision of final flour are related to production process, season, environmental temperature and environmental humidity besides the condition of wheat, the factors are more, the influence mechanism is complex, the uncertainty is high, and the wheat watering is not accurately controlled, so that the final watering is determined by continuously learning and updating the neural network based on an artificial intelligence control algorithm and comprehensively considering various factors, and the method is simpler and more accurate.
Based on the above embodiment, referring to fig. 3, in the embodiment of the present invention, the wheat watering control device specifically includes:
the acquisition module 30 is used for acquiring the ambient temperature and the ambient humidity within a preset time period and acquiring the parameter information of the wheat;
the input module 31 is used for inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network;
a determining module 32, configured to process the ambient temperature, the ambient humidity, and the wheat parameter information based on the pre-trained neural network, and determine a target water attachment;
and the dampening module 33 is used for dampening the wheat according to the determined target dampening amount.
Optionally, when the ambient temperature and the ambient humidity within the preset time period are obtained, the obtaining module 30 is specifically configured to: respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period; wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
Optionally, based on the pre-trained neural network, the environmental temperature, the environmental humidity, and the wheat parameter information are processed, and when the target water application amount is determined, the determining module 32 is specifically configured to:
determining a weighted ambient temperature according to the ambient temperatures corresponding to a plurality of update cycles based on the pre-trained neural network;
determining weighted ambient humidity according to the ambient humidity corresponding to the plurality of update periods;
determining target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information; wherein the wheat parameter information includes but is not limited to: wheat temperature, wheat moisture and wheat volume weight.
Optionally, before inputting into the pre-trained neural network, further comprising:
and the preprocessing module 34 is configured to normalize the environmental temperature, the environmental humidity, and the wheat parameter information to preset intervals respectively.
Optionally, the training mode for the neural network further includes a training module 35, configured to:
acquiring a training sample set; each training sample in the training sample set at least comprises environmental temperature, environmental humidity and wheat parameter information in a preset time period;
respectively acquiring the moisture content of the wheat flour corresponding to each training sample aiming at each training sample in the training sample set;
and training the neural network according to the training sample set, wherein the input of the neural network is the training sample set, the output of the neural network is the determined target water content, and the target function of the neural network is the minimization of the error value between the determined target water content and the corresponding moisture content of the wheat flour.
Referring to fig. 4, in an embodiment of the invention, a structural diagram of an electronic device is shown.
An embodiment of the present invention provides an electronic device, which may include a processor 410 (CPU), a memory 420, an input device 430, an output device 440, and the like, wherein the input device 430 may include a keyboard, a mouse, a touch screen, and the like, and the output device 440 may include a Display device, such as a Liquid Crystal Display (LCD), a Cathode Ray Tube (CRT), and the like.
By calling the program instructions stored in the memory 420, the processor 410 is configured to perform the following steps according to the obtained program instructions:
acquiring the environmental temperature and the environmental humidity within a preset time period, and acquiring wheat parameter information;
inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network;
processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine a target water attachment;
and (5) dampening the wheat according to the determined target dampening amount.
Optionally, when the ambient temperature and the ambient humidity within the preset time period are obtained, the processor 410 is specifically configured to: respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period; wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
Optionally, before inputting into the pre-trained neural network, the processor 410 is further configured to: and respectively normalizing the environmental temperature, the environmental humidity and the wheat parameter information to preset intervals.
Optionally, based on the pre-trained neural network, the environmental temperature, the environmental humidity, and the wheat parameter information are processed, and when the target water uptake is determined, the processor 410 is specifically configured to:
determining a weighted ambient temperature according to the ambient temperatures corresponding to a plurality of update cycles based on the pre-trained neural network;
determining weighted ambient humidity according to the ambient humidity corresponding to the plurality of update periods;
determining target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information; wherein the wheat parameter information includes but is not limited to: wheat temperature, wheat moisture and wheat volume weight.
Optionally, for the training mode of the neural network, the processor 410 is further configured to:
acquiring a training sample set; each training sample in the training sample set at least comprises environmental temperature, environmental humidity and wheat parameter information in a preset time period;
respectively acquiring the moisture content of the wheat flour corresponding to each training sample aiming at each training sample in the training sample set;
and training the neural network according to the training sample set, wherein the input of the neural network is the training sample set, the output of the neural network is the determined target water content, and the target function of the neural network is the minimization of the error value between the determined target water content and the corresponding moisture content of the wheat flour.
Based on the above embodiments, in the embodiments of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the wheat watering control method in any of the above method embodiments.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (8)
1. A wheat dampening control method is characterized by comprising the following steps:
acquiring the environmental temperature and the environmental humidity within a preset time period, and acquiring wheat parameter information;
inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network;
processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine a target water attachment;
according to the determined target water attachment amount, attaching water to the wheat;
wherein, acquire ambient temperature and ambient humidity in the preset time quantum, specifically include:
respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period; wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
2. The method of claim 1, prior to inputting into the pre-trained neural network, further comprising:
and respectively normalizing the environmental temperature, the environmental humidity and the wheat parameter information to preset intervals.
3. The method of claim 1, wherein processing the ambient temperature, ambient humidity, and wheat parameter information based on the pre-trained neural network to determine a target water uptake comprises:
determining a weighted ambient temperature according to the ambient temperatures corresponding to a plurality of update cycles based on the pre-trained neural network;
determining weighted ambient humidity according to the ambient humidity corresponding to the plurality of update periods;
determining target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information; wherein the wheat parameter information comprises: wheat temperature, wheat moisture and wheat volume weight.
4. The method of any one of claims 1-3, wherein the neural network is trained by:
acquiring a training sample set; each training sample in the training sample set at least comprises environmental temperature, environmental humidity and wheat parameter information in a preset time period;
respectively acquiring the actually detected moisture content of the wheat corresponding to each training sample aiming at each training sample in the training sample set;
and training the neural network according to the training sample set, wherein the input of the neural network is the training sample set, the output of the neural network is the determined target water content, and the target function of the neural network is the minimization of the error value between the determined target water content and the corresponding actually detected moisture content of the wheat.
5. A wheat dampening control device, comprising:
the acquisition module is used for acquiring the ambient temperature and the ambient humidity within a preset time period and acquiring the parameter information of the wheat;
the input module is used for inputting the environmental temperature, the environmental humidity and the wheat parameter information into a pre-trained neural network;
the determining module is used for processing the environmental temperature, the environmental humidity and the wheat parameter information based on the pre-trained neural network to determine the target water attachment;
the dampening module is used for dampening the wheat according to the determined target dampening amount;
wherein, when obtaining ambient temperature and ambient humidity in the predetermined time quantum, the acquisition module is specifically used for:
respectively acquiring the environmental temperature and the environmental humidity corresponding to a plurality of updating cycles pre-divided in a preset time period; wherein the starting time of the preset time period is the determined wheat watering starting time, and the ending time is the sum of the wheat watering starting time and the preset wheat watering duration.
6. The apparatus of claim 5, wherein the pre-trained neural network is based on processing the ambient temperature, ambient humidity, and wheat parameter information, and wherein the determination module is specifically configured to, when determining the target water uptake:
determining a weighted ambient temperature according to the ambient temperatures corresponding to a plurality of update cycles based on the pre-trained neural network;
determining weighted ambient humidity according to the ambient humidity corresponding to the plurality of update periods;
determining target water attachment according to the weighted environment temperature, the weighted environment humidity and the wheat parameter information; wherein the wheat parameter information comprises: wheat temperature, wheat moisture and wheat volume weight.
7. An electronic device, comprising:
at least one memory for storing a computer program;
at least one processor adapted to implement the steps of the method according to any of claims 1-4 when executing a computer program stored in a memory.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program realizing the steps of the method according to any one of claims 1-4 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811585126.4A CN111346688B (en) | 2018-12-24 | 2018-12-24 | Wheat dampening control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811585126.4A CN111346688B (en) | 2018-12-24 | 2018-12-24 | Wheat dampening control method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111346688A CN111346688A (en) | 2020-06-30 |
| CN111346688B true CN111346688B (en) | 2021-08-24 |
Family
ID=71190370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811585126.4A Active CN111346688B (en) | 2018-12-24 | 2018-12-24 | Wheat dampening control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111346688B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105588930A (en) * | 2015-12-17 | 2016-05-18 | 镇江市高等专科学校 | Method for measuring parameters of soil in greenhouse |
| CN105892287A (en) * | 2016-05-09 | 2016-08-24 | 河海大学常州校区 | Crop irrigation strategy based on fuzzy judgment and decision making system |
| CN107944552A (en) * | 2017-12-19 | 2018-04-20 | 电子科技大学 | A kind of industrial Internet of Things parameter prediction method based on Elman neutral nets |
| CN108107716A (en) * | 2017-12-19 | 2018-06-01 | 电子科技大学 | A kind of Parameter Measuring method based on improved BP neural network |
| CN108319134A (en) * | 2018-01-15 | 2018-07-24 | 沈阳大学 | A kind of greenhouse environment intelligent control method based on extreme learning machine network |
| CN108507700A (en) * | 2018-03-20 | 2018-09-07 | 中国农业大学 | A kind of pig house multi-point temperature prediction technique and system |
| CN108983849A (en) * | 2018-07-12 | 2018-12-11 | 沈阳大学 | It is a kind of to utilize compound extreme learning machine ANN Control greenhouse method |
-
2018
- 2018-12-24 CN CN201811585126.4A patent/CN111346688B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105588930A (en) * | 2015-12-17 | 2016-05-18 | 镇江市高等专科学校 | Method for measuring parameters of soil in greenhouse |
| CN105892287A (en) * | 2016-05-09 | 2016-08-24 | 河海大学常州校区 | Crop irrigation strategy based on fuzzy judgment and decision making system |
| CN107944552A (en) * | 2017-12-19 | 2018-04-20 | 电子科技大学 | A kind of industrial Internet of Things parameter prediction method based on Elman neutral nets |
| CN108107716A (en) * | 2017-12-19 | 2018-06-01 | 电子科技大学 | A kind of Parameter Measuring method based on improved BP neural network |
| CN108319134A (en) * | 2018-01-15 | 2018-07-24 | 沈阳大学 | A kind of greenhouse environment intelligent control method based on extreme learning machine network |
| CN108507700A (en) * | 2018-03-20 | 2018-09-07 | 中国农业大学 | A kind of pig house multi-point temperature prediction technique and system |
| CN108983849A (en) * | 2018-07-12 | 2018-12-11 | 沈阳大学 | It is a kind of to utilize compound extreme learning machine ANN Control greenhouse method |
Non-Patent Citations (1)
| Title |
|---|
| 小麦着水机智能水分测量系统研究;易启伟等;《粮油加工与食品机械》;20050930(第9期);第71-73页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111346688A (en) | 2020-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022166919A1 (en) | Breeding environment temperature prediction and control system for livestock and poultry house, and adjustment and control method therefor | |
| CN110515411B (en) | Water treatment chemical adding amount control method and system | |
| CN112418498B (en) | Temperature prediction method and system for intelligent greenhouse | |
| CN102072922A (en) | Particle swarm optimization neural network model-based method for detecting moisture content of wood | |
| CN110889085A (en) | Intelligent wastewater monitoring method and system based on complex network multiple online regression | |
| CN103674778A (en) | Industrial melt index soft measuring meter and method based on RBF (radial basis function) particle swarm optimization | |
| CN108615097A (en) | A kind of wind speed forecasting method, system, equipment and computer readable storage medium | |
| CN103489034A (en) | Method and device for predicting and diagnosing online ocean current monitoring data | |
| CN108595892A (en) | Soft-measuring modeling method based on time difference model | |
| CN110999766A (en) | Irrigation decision method, device, computer equipment and storage medium | |
| CN103675006B (en) | The industrial melt index soft measurement instrument of least square and method | |
| Wang et al. | Modeling of soft sensor based on DBN-ELM and its application in measurement of nutrient solution composition for soilless culture | |
| CN114216256A (en) | Ventilation system air volume control method of off-line pre-training-on-line learning | |
| CN103675011A (en) | Soft industrial melt index measurement instrument and method of optimal support vector machine | |
| CN111346688B (en) | Wheat dampening control method and device | |
| JP2021049841A (en) | Control device, learning device, control method, learning method, and program | |
| CN116865343B (en) | Model-free self-adaptive control method, device and medium for distributed photovoltaic power distribution network | |
| CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment | |
| CN107168066A (en) | A kind of greenhouse self-adaptation control method | |
| CN107766880A (en) | The flexible measurement method of Fermentation by Photosynthetic Bacteria process key parameter based on BA LSSVM | |
| CN103675012B (en) | The industrial melt index soft measurement instrument of BP particle group optimizing and method | |
| CN115829099A (en) | Yellow wine fermentation prediction method and system based on ANFIS and random fractal search algorithm | |
| CN115358375A (en) | Pulse neural network reserve pool calculation model construction method and device | |
| CN112879220B (en) | Fan control method and system and readable storage medium | |
| CN113991752A (en) | Power grid quasi-real-time intelligent control method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |