CN117609736A - Grain temperature prediction method and device, electronic equipment and storage medium - Google Patents

Grain temperature prediction method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117609736A
CN117609736A CN202311774771.1A CN202311774771A CN117609736A CN 117609736 A CN117609736 A CN 117609736A CN 202311774771 A CN202311774771 A CN 202311774771A CN 117609736 A CN117609736 A CN 117609736A
Authority
CN
China
Prior art keywords
period
data set
periods
data sets
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311774771.1A
Other languages
Chinese (zh)
Inventor
刘芬
刘振宇
李宏伟
王亚平
王志刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aisino Corp
Original Assignee
Aisino Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aisino Corp filed Critical Aisino Corp
Priority to CN202311774771.1A priority Critical patent/CN117609736A/en
Publication of CN117609736A publication Critical patent/CN117609736A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the application provides a grain temperature prediction method, a grain temperature prediction device, electronic equipment and a storage medium, wherein the grain temperature prediction method comprises the following steps: acquiring a plurality of original data sets, wherein the original data sets comprise measured temperature values corresponding to a plurality of temperature measuring points in a target granary in corresponding periods, and the periods corresponding to different original data sets are different; taking an original data set of a target granary in a non-empty granary state in a corresponding period as a first data set; and determining at least one second data set according to the first data sets, wherein the second data set comprises predicted temperature values corresponding to a plurality of temperature measuring points in the target granary in corresponding periods, periods corresponding to different second data sets are different, and the starting time of the first period in the periods corresponding to the second data sets is the ending time of the last period in the periods corresponding to the original data sets or is before the ending time. The scheme can make grain temperature prediction more reliable and more accurate.

Description

Grain temperature prediction method and device, electronic equipment and storage medium
Technical Field
The embodiment of the application relates to the field of data processing, in particular to a grain temperature prediction method, a grain temperature prediction device, electronic equipment and a storage medium.
Background
During the storage process of the grains, heating, mildew and the like are easy to occur, so that economic loss is caused, and even the stable life of partial people can be influenced, therefore, the grain temperature prediction is indispensable during the storage process of the grains.
At present, when actual grain temperature prediction is carried out, grain temperature monitoring is usually carried out through a sensor in a grain bin, and future temperature of grains in the grain bin is predicted according to manual experience so as to determine whether heating risks exist in the grains in the grain bin, and if the heating risks exist, disposal measures are taken so as to avoid the temperature rise of the grains to be too high as much as possible.
However, predicting future temperatures of grain in the grain bin according to human experience is relatively subjective, and further, the reliability and accuracy of grain temperature prediction are poor.
Disclosure of Invention
In view of the foregoing, embodiments of the present application provide a grain temperature prediction method, apparatus, electronic device, and storage medium, so as to at least partially solve the foregoing problems.
According to a first aspect of embodiments of the present application, there is provided a grain temperature prediction method, including: acquiring a plurality of original data sets, wherein the original data sets comprise measured temperature values corresponding to a plurality of temperature measuring points in a target granary in corresponding periods, and the periods corresponding to different original data sets are different; taking an original data set of which the target granary is in a non-empty granary state in a corresponding period as a first data set; and determining at least one second data set according to the first data sets, wherein the second data set comprises predicted temperature values corresponding to a plurality of temperature measuring points in the target granary in corresponding periods, different periods corresponding to the second data sets are different, and the starting time of the first period in the periods corresponding to the second data sets is the ending time of the last period in the periods corresponding to the original data sets or is before the ending time.
According to a second aspect of embodiments of the present application, there is provided a grain temperature prediction apparatus, comprising: the acquisition unit is used for acquiring a plurality of original data sets, wherein the original data sets comprise measured temperature values corresponding to a plurality of temperature measuring points in a target granary in a corresponding period, and the periods corresponding to different original data sets are different; the screening unit is used for taking an original data set of which the target granary is in a non-empty granary state in a corresponding period as a first data set; and the determining unit is used for determining at least one second data set according to the plurality of first data sets, wherein the second data set comprises predicted temperature values corresponding to a plurality of temperature measuring points in the target granary in corresponding periods, periods corresponding to different second data sets are different, and the starting time of the first period in the periods corresponding to the plurality of second data sets is the ending time of the last period in the periods corresponding to the plurality of original data sets or is before the ending time.
According to a third aspect of embodiments of the present application, there is provided an electronic device, including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus; the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the method of the first aspect.
According to a fourth aspect of embodiments of the present application, there is provided a computer storage medium having stored thereon a computer program for execution by a processor of the method of the first aspect described above.
According to a fifth aspect of embodiments of the present application, there is provided a computer program product comprising computer instructions for instructing a computing device to execute the method of the first aspect described above.
According to the grain temperature prediction scheme provided by the embodiment of the application, a plurality of original data sets are firstly obtained, then the original data sets of which the target granary is in a non-empty state in the corresponding period are used as the first data sets, and then at least one second data set is determined according to the plurality of first data sets, wherein the starting time of the first period in the periods corresponding to the plurality of second data sets is the ending time of the last period in the periods corresponding to the plurality of original data sets or is before the ending time. Therefore, the embodiment of the application can automatically predict the second data set, namely, automatically predict the grain temperature, so that the grain temperature is predicted more objectively, and the scheme predicts the second data set according to the original data set of the target grain bin in a non-empty state in a corresponding period, so that the interference of the temperature in the grain bin to the grain temperature prediction in the empty state can be reduced, and the grain temperature prediction can be more reliable and more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings may also be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a flow chart of a grain temperature prediction method according to one embodiment of the present application;
FIG. 2 is a schematic diagram of a grain temperature prediction apparatus according to one embodiment of the present application;
fig. 3 is a schematic diagram of an electronic device according to one embodiment of the present application.
Detailed Description
Application environment of the present application
The embodiment of the application provides a scheme for predicting grain temperature. The whole grain temperature prediction scheme is relatively universal, and can be used for predicting the grain temperature of grains stored in a plurality of grain bins. The grain temperature prediction method may be performed by a data center, a server, a personal computer, an internet of things (Internet of Things, ioT) device, an embedded device, or the like. The grain temperature prediction scheme is independent of the hardware deployed by the computing device executing the scheme.
Grain temperature prediction method
The embodiment of the application provides a grain temperature prediction method, and the grain temperature prediction method is described in detail through a plurality of embodiments.
FIG. 1 is a flow chart of a grain temperature prediction method according to one embodiment of the present application. As shown in fig. 1, the grain temperature prediction method comprises the following steps:
step 101, obtaining a plurality of original data sets.
Wherein the raw data set comprises measured temperature values corresponding to a plurality of temperature measuring points in the target granary in a corresponding period.
For the above-mentioned a plurality of granaries, be provided with a plurality of temperature measurement points in every granary, preferably, a plurality of temperature measurement points in same granary are comparatively dispersed and even that generally set up, and a temperature sensor can be placed to every temperature measurement point for measure the corresponding measurement temperature value of this temperature measurement point department, the target granary is any granary in above-mentioned a plurality of granaries.
The periods corresponding to the different original data sets are different, and the periods corresponding to the plurality of original data sets can be continuous or discontinuous. For example, a single cycle is one day, and the cycles corresponding to the plurality of raw data sets are 2023, 1 month 1 day, 2023, 1 month 2 days, … …, 2023, 4 month 30 days, and 2023, 5 month 1 day, respectively. The duration of a single cycle may be five days, one day, 10 hours, etc., which is not limited in this embodiment, and a single cycle will be exemplified as one day in this embodiment.
The grain temperature prediction may be to predict grain temperature data of future time according to grain temperature data of historical time, or may be to predict grain temperature data of historical time according to grain temperature data of historical time, which is not limited in this embodiment of the present application, specifically as follows:
the grain temperature prediction may be to predict grain temperature data of future time according to grain temperature data of historical time, in a specific implementation manner of step 101, firstly, for each day before the current time and after the preset historical time, a plurality of temperature values corresponding to each temperature measuring point in the target granary in the day are obtained, then, an average value of the plurality of temperature values of each temperature measuring point in the day is used as a measured temperature value corresponding to the temperature measuring point, and further, an original data set corresponding to the day can be obtained to obtain a plurality of original data sets, wherein the specific preset historical time can be preset according to actual conditions, and the embodiment of the application is not limited to this.
In another specific implementation manner, the grain temperature prediction may be to predict the grain temperature data of the historical time according to the grain temperature data of the historical time, in step 101, first a first preset historical time and a second preset historical time are determined, the first preset historical time is after the second preset historical time and the first preset historical time is before the current time, then for each day before the first preset historical time and after the second preset historical time, a plurality of temperature values corresponding to each temperature measuring point in the target grain bin in the day are obtained, then an average value of the plurality of temperature values of each temperature measuring point in the day is used as a measured temperature value corresponding to the temperature measuring point, and then an original data set corresponding to the day can be obtained, so as to obtain a plurality of original data sets, where the specific first preset historical time and the second preset historical time can be preset according to actual conditions.
Step 102, taking an original data set of which the target granary is in a non-empty granary state in a corresponding period as a first data set.
In the process of determining the first data set, the original data set with the target granary in the empty state in the corresponding period can be deleted from all the acquired original data sets, and each remaining original data set is determined to be the first data set, so that the original data set with the target granary in the non-empty state in the corresponding period is determined to be the first data set.
Step 103, determining at least one second data set according to the plurality of first data sets.
The second data sets comprise predicted temperature values corresponding to a plurality of temperature measuring points in the target granary in corresponding periods, periods corresponding to different second data sets are different, and the starting time of the first period in the periods corresponding to the second data sets is the ending time of the last period in the periods corresponding to the original data sets or is before the ending time.
The grain temperature prediction may be to predict grain temperature data of a future time according to grain temperature data of a historical time, and one specific embodiment of step 103 may be that, based on the first specific embodiment of step 101, at least a part of the first data set may be input into a prediction model, then the prediction model may output predicted temperature values corresponding to a plurality of temperature measurement points in a target grain bin in each day of the first period, where the first period may be a day from a day of the current time to a preset future time, and then at least one second data set may be obtained, where a specific number of second data sets is the same as a number of days included in the first period, and the specific preset future time may be preset according to an actual situation.
Furthermore, after the second data set is obtained, corresponding treatment measures can be carried out according to the predicted temperature value in the second data set, so as to avoid the condition that grains in the granary are mildewed and deteriorated due to overhigh grain temperature as much as possible.
In another specific embodiment of step 103, at least a part of the first data set may be input into the prediction model based on the second specific embodiment of step 101, then the prediction model may output predicted temperature values corresponding to a plurality of temperature measuring points in the target grain bin in each day in a second period, the second period may be a day from the day of the first preset history time to a third preset history time, the third preset history time is after the first preset history time, and then at least one second data set may be obtained, where a specific number of the second data sets is the same as a number of days included in the second period, and the specific third preset history time may be preset according to an actual situation.
Furthermore, if there is a defect in the measured temperature values of the plurality of temperature measuring points in the target granary in the period corresponding to the second data set, the second data set can be used for supplementing so that when the future grain temperature is predicted according to the historical grain temperature, the historical grain temperature is more complete, and therefore the predicted future grain temperature can be more accurate.
In the embodiment of the application, a plurality of original data sets are firstly obtained, then the original data set of which the target granary is in a non-empty state in the corresponding period is used as a first data set, and then at least one second data set is determined according to the plurality of first data sets, wherein the starting time of the first period in the periods corresponding to the plurality of second data sets is the ending time of the last period in the periods corresponding to the plurality of original data sets or is before the ending time. Therefore, the embodiment of the application can automatically predict the second data set, namely, automatically predict the grain temperature, so that the grain temperature is predicted more objectively, and the scheme predicts the second data set according to the original data set of the target grain bin in a non-empty state in a corresponding period, so that the interference of the temperature in the grain bin to the grain temperature prediction in the empty state can be reduced, and the grain temperature prediction can be more reliable and more accurate.
Based on the embodiment of the application, the automatic recognition and pre-early warning of the conditions such as heating, mildew, grain quality change and the like of the grains can be further carried out, so that the grain temperature prediction method has important practical significance and economic benefit for reducing grain loss
In the embodiments of the present application, the following description will be given by taking the case where the grain temperature prediction is to predict the grain temperature data of the future time with respect to the grain temperature data of the history time.
In one possible implementation, step 102 includes the following specific processes:
acquiring an outside temperature value of a target granary in a period corresponding to each original data set;
taking a measured temperature value, the difference value between the measured temperature value and the temperature value outside the bin in the corresponding period of which is smaller than a first threshold value, as a first temperature value;
determining at least a period with a corresponding first quantity ratio greater than a second threshold value as a blank period in periods corresponding to a plurality of original data sets, wherein the first quantity ratio corresponding to the period is a ratio of the quantity of first temperature values in the period to the quantity of measured temperature values in the period;
and in the periods corresponding to the plurality of original data sets, determining the original data set corresponding to the period which is not the empty period as a first data set, so that the original data set of which the target granary is in a non-empty state in the corresponding period is taken as the first data set.
Wherein the first threshold may be 0.01 ℃ to 0.1 ℃, the second threshold may be 0.7 to 0.9, for example, the first threshold is 0.05 ℃, and the second threshold is 0.8.
When determining the first data set, for each period corresponding to the original data set, acquiring the temperature outside the target granary at different times in the period, taking the average value of the temperatures outside the target granary at different times in the period as the value of the temperature outside the target granary in the period, taking the measured temperature value with the difference value of the temperature outside the target granary in the corresponding period smaller than the first threshold value as the first temperature value, determining at least the period with the corresponding first quantity ratio larger than the second threshold value as the empty period in the period corresponding to the original data sets, finally deleting the original data sets which are not the empty period and correspond to the period from the original data sets acquired in the step 101, and taking each remaining original data set as the first data set.
In this embodiment of the present application, for a period corresponding to each original data set, if a temperature difference between an extra-bin temperature value corresponding to the period and a most of measured temperature values corresponding to the period is smaller, then a target grain bin in the period is most likely to be an empty bin, and the period can be determined to be an empty bin period at this time.
In one possible implementation manner, the determining, in periods corresponding to the plurality of original data sets, at least periods in which the corresponding first number ratio is greater than the second threshold value as empty periods includes the following specific processes:
determining a period of which the corresponding first quantity ratio is larger than a second threshold value as an initial empty period in the periods corresponding to the plurality of original data sets;
acquiring a plurality of period groups, wherein the period groups comprise a plurality of continuous periods in periods corresponding to the plurality of original data groups;
taking a period group with a corresponding second number ratio greater than a third threshold value as a blank period group, wherein the second number ratio corresponding to the period group is the ratio of the number of initial blank periods included in the period group to the number of periods included in the period group;
each initial empty period and each period in the set of empty periods is determined to be an empty period, respectively.
Where a single period group may be one month, for example, 1 month is one period group, the period group includes 31 consecutive periods, that is, 31 periods are 1 month and 1 day, 1 month and 2 days, … …, and 1 month and 31 days, respectively. The third threshold may be 0.7 to 0.9, for example, the third threshold is 0.8.
In this embodiment of the present application, if the number of periods corresponding to the first number ratio in the same period group is greater than the second threshold, the period group is taken as a empty period group. Therefore, the periods in the same period group are continuous, and the switching frequency of the empty state and the non-empty state of the actual granary is relatively low, so that if more corresponding periods with the first quantity ratio larger than the second threshold value exist in the same period group, the large probability of the target granary in the period group is always in the empty state, and the accuracy of determining the empty period can be improved by determining the empty period group.
In one possible implementation manner, the step 103 includes the following specific processes:
obtaining a corresponding supplementary data set of the empty bin period according to a first data set of a plurality of periods in a period window corresponding to the empty bin period, wherein the period window comprises a plurality of continuous periods, any period included in the period window of the empty bin period is the empty bin period, and the supplementary data set comprises supplementary temperature values corresponding to a plurality of temperature measuring points in a target granary in the corresponding empty bin period;
at least one second data set is determined based on the plurality of supplemental data sets and the plurality of first data sets.
The period window of the empty period may include a plurality of continuous periods with the empty period as a central period, for example, the empty period is 3 months and 16 days, and the period window includes 5 periods, and the period window of the empty period is 3 months and 14 days, 3 months and 15 days, 3 months and 16 days, 3 months and 17 days, and 3 months and 18 days.
In the process of determining at least one second data set according to the plurality of first data sets, whether a period which is not a blank period exists before the blank period and after the blank period in a period window of the blank period or not can be determined, if yes, an original data set corresponding to a period which is closest to the blank period before the blank period is taken as a first original data set corresponding to the blank period, an original data set corresponding to a period which is closest to the blank period after the blank period is taken as a second original data set corresponding to the blank period, then measured temperature values corresponding to the same temperature measuring point in the first original data set corresponding to the blank period and the second original data set corresponding to the blank period are averaged, the average value corresponding to each temperature measuring point is taken as a supplementary temperature value of the temperature measuring point, so that a supplementary data set corresponding to the blank period is obtained, and at least one second data set is determined according to the plurality of supplementary data sets and the plurality of first data sets.
In the embodiment of the application, the first data set corresponding to the period in the same period window can be used for determining the empty bin period in the period window to supplement the grain temperature data corresponding to the empty bin period if the grain bin is in a non-empty bin state during the empty bin period, so that grain temperature prediction can be performed based on more grain temperature data, and the reliability and accuracy of grain temperature prediction are improved.
In a possible implementation manner, before determining the at least one second data set according to the plurality of supplemental data sets and the plurality of first data sets, the step 103 further includes the following specific processes:
if the supplementary data set does not comprise the supplementary temperature value corresponding to any temperature measuring point in the target granary, determining the supplementary temperature value corresponding to the temperature measuring point according to the supplementary temperature value in the supplementary data set, and adding the supplementary temperature value corresponding to the temperature measuring point into the supplementary data set;
if the first data set does not include the measured temperature value corresponding to any temperature measuring point in the target granary, determining the measured temperature value corresponding to the temperature measuring point according to the measured temperature value in the first data set, and adding the measured temperature value corresponding to the temperature measuring point into the first data set.
For each supplementary data set, if the supplementary data set does not include a supplementary temperature value corresponding to any temperature measuring point in the target granary, determining an average value of supplementary temperature values corresponding to 6 temperature measuring points located closest to the temperature measuring point in the supplementary data set, wherein the average value is the supplementary temperature value corresponding to the temperature measuring point; similarly, for each first data set, if the first data set does not include the measured temperature value corresponding to any temperature measuring point in the target grain bin, the average value of the measured temperature values corresponding to 6 temperature measuring points located closest to the temperature measuring points in the first data set, up, down, left, right, front and rear, can be determined as the measured temperature value corresponding to the temperature measuring point.
In the embodiment of the application, the grain temperature data in the supplementary data set and the first data set can be more complete through supplementing the missing values in the supplementary data set and the first data set, so that the accuracy of determining the second data set based on the supplementary data set and the first data set can be improved, namely the accuracy of grain temperature prediction is improved.
In one possible implementation manner, the determining at least one second data set according to the plurality of supplemental data sets and the plurality of first data sets includes the following specific processes:
The method comprises the steps of obtaining a target period number, wherein the target period number is any one of the maximum continuous period numbers corresponding to a plurality of granaries, the target granaries are any one of the plurality of granaries, and the maximum continuous period number corresponding to the target granaries is the period number corresponding to a plurality of continuous periods with the largest included periods in periods corresponding to a plurality of supplementary data sets and periods corresponding to a plurality of first data sets;
determining a first period number and a second period number according to a target period number, wherein the target period number is the sum of the first period number and the second period number, and the first period number is larger than the second period number;
in the successive periods of the target number of periods, a first number of successive periods starting from the first period is determined as a first successive period group, and a second number of successive periods ending with the last period is determined as a second successive period group;
and determining a second data set corresponding to the second continuous period set according to the supplementary data set corresponding to the first continuous period set and the first data set.
When the number of target periods is determined, for each of the plurality of barns, all first data sets and all supplementary data sets of the barn can be determined through a grain temperature prediction method, then a plurality of continuous periods with the largest included period are determined in periods corresponding to all first data sets of the barn and periods corresponding to all supplementary data sets of the barn, and the number of periods included in the plurality of continuous periods is determined, wherein the number is the largest continuous period number corresponding to the barn.
After determining the maximum continuous period number of each granary, the maximum continuous period number with the largest value and smaller difference with the maximum continuous period number of the value in the maximum continuous period number of all granaries can be used as the target period number L.
And determining a first period number n and a second period number m according to the target period number L, wherein m+n=L and n > m.
Then, for each of n consecutive periods before and closest to the current time, if there is a corresponding first data set in the period, the first data set is taken as an input data set corresponding to the period, if there is a corresponding supplementary data set in the period, the supplementary data set is taken as an input data set corresponding to the period, and if there is neither a corresponding input data set nor a corresponding supplementary data set in the period, the input data set corresponding to the supplementary data set is determined as a null data set. Each input data set can exist in a three-dimensional matrix form, a first granary with the largest number of temperature measuring point layers, a second granary with the largest number of temperature measuring point rows and a third granary with the largest number of temperature measuring point rows are determined in the plurality of granaries, the number of layers of each three-dimensional matrix is the number of the temperature measuring point layers of the first granary, the number of rows of each three-dimensional matrix is the number of the temperature measuring point rows of the second granary, and the number of columns of each three-dimensional matrix is the number of the temperature measuring point rows of the second granary. For the granary with fewer temperature measuring points, the measured temperature value and the supplementary temperature value corresponding to the temperature measuring points which do not exist in the corresponding three-dimensional matrix can be 0.
And inputting the n input data sets into a prediction model, wherein the prediction model can output m second data sets, the periods corresponding to the m second data sets are continuous with the n continuous periods, and the m second data sets are sequentially output according to the corresponding period sequence. For example, m > 5, if the grain temperature on day 5 from the day of the current time is to be predicted, the 5 th second data set of the output is obtained.
The prediction model may include a 3DCNN network, an LSTM network, an input of the LSTM network being an output of the 3DCNN network, and an input of the linear layer being an output of the LSTM network; in the process of training the prediction model, the grain temperature predicted value and the true value can be used for calculating the loss function MSE, and the optimal model solution is obtained by minimizing the loss function through an optimizer Adam.
When the effect of the prediction model is evaluated, the predicted temperature value in the same second data set can be processed by using MAE (Mean Absolute Error, average absolute error), and the smaller the MAE value corresponding to the second data set is, the better the prediction effect is.
Grain temperature prediction device
Corresponding to the above method embodiments, fig. 2 shows a schematic diagram of a grain temperature prediction apparatus according to an embodiment of the present application, and as shown in fig. 2, the grain temperature prediction apparatus 200 includes:
An obtaining unit 201, configured to obtain a plurality of original data sets, where the original data sets include measured temperature values corresponding to a plurality of temperature measurement points in a target grain bin in corresponding periods, and periods corresponding to different original data sets are different;
a screening unit 202, configured to take, as a first data set, an original data set of the target grain bin in a non-empty state in a corresponding period;
a determining unit 203, configured to determine at least one second data set according to the plurality of first data sets, where the second data set includes predicted temperature values corresponding to a plurality of temperature measurement points in the target grain bin in a corresponding period, periods corresponding to different second data sets are different, and a start time of a first period in the periods corresponding to the plurality of second data sets is an end time of a last period in the periods corresponding to the plurality of original data sets, or is before the end time.
In this embodiment of the present application, the obtaining unit 201 obtains a plurality of original data sets, the screening unit 202 uses, as a first data set, an original data set of the target grain bin in a non-empty state in a corresponding period, and the determining unit 203 determines at least one second data set according to the plurality of first data sets, where a start time of a first period in the periods corresponding to the plurality of second data sets is an end time of a last period in the periods corresponding to the plurality of original data sets, or is before the end time. Therefore, the embodiment of the application can automatically predict the second data set, namely, automatically predict the grain temperature, so that the grain temperature is predicted more objectively, and the scheme predicts the second data set according to the original data set of the target grain bin in a non-empty state in a corresponding period, so that the interference of the temperature in the grain bin to the grain temperature prediction in the empty state can be reduced, and the grain temperature prediction can be more reliable and more accurate.
It should be noted that, the grain temperature prediction device in this embodiment is used to implement the corresponding grain temperature prediction method in the foregoing method embodiment, and has the beneficial effects of the corresponding method embodiment, which is not described herein again.
Electronic equipment
Fig. 3 is a schematic block diagram of an electronic device provided in an embodiment of the present application, where the embodiment of the present application is not limited to a specific implementation of the electronic device. As shown in fig. 3, the electronic device may include: a processor (processor) 302, a communication interface (Communications Interface) 304, a memory (memory) 306, and a communication bus 308. Wherein:
processor 302, communication interface 304, and memory 306 perform communication with each other via communication bus 308.
Communication interface 304 for communicating with other electronic devices or servers.
Processor 302 is configured to execute program 310, and may specifically perform the relevant steps of any of the foregoing embodiments of the grain temperature prediction method.
In particular, program 310 may include program code including computer-operating instructions.
The processor 302 may be a CPU or a specific integrated circuit ASIC (Application Specific Integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors comprised by the smart device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
RISC-V is an open source instruction set architecture based on the principle of Reduced Instruction Set (RISC), which can be applied to various aspects such as single chip microcomputer and FPGA chip, and can be particularly applied to the fields of Internet of things security, industrial control, mobile phones, personal computers and the like, and because the real conditions of small size, rapidness and low power consumption are considered in design, the RISC-V is particularly suitable for modern computing equipment such as warehouse-scale cloud computers, high-end mobile phones, micro embedded systems and the like. With the rise of AIoT of the artificial intelligent Internet of things, RISC-V instruction set architecture is also receiving more and more attention and support, and is expected to become a CPU architecture widely applied in the next generation.
The computer operation instructions in embodiments of the present application may be computer operation instructions based on a RISC-V instruction set architecture, and correspondingly, the processor 302 may be RISC-V based instruction set design. Specifically, the chip of the processor in the electronic device provided in the embodiment of the present application may be a chip designed by using a RISC-V instruction set, and the chip may execute executable codes based on the configured instructions, thereby implementing the grain temperature prediction method in the above embodiment.
Memory 306 for storing programs 310. Memory 306 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 310 may be specifically configured to cause processor 302 to perform the grain temperature prediction method of any of the foregoing embodiments.
The specific implementation of each step in the procedure 310 may refer to corresponding descriptions in the corresponding steps and units in any of the foregoing grain temperature prediction method embodiments, which are not repeated herein. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.
Through the electronic equipment provided by the embodiment of the application, a plurality of original data sets are firstly obtained, then the original data set of which the target granary is in a non-empty state in a corresponding period is used as a first data set, and then at least one second data set is determined according to the plurality of first data sets, wherein the starting time of the first period in the periods corresponding to the plurality of second data sets is the ending time of the last period in the periods corresponding to the plurality of original data sets or is before the ending time. Therefore, the embodiment of the application can automatically predict the second data set, namely, automatically predict the grain temperature, so that the grain temperature is predicted more objectively, and the scheme predicts the second data set according to the original data set of the target grain bin in a non-empty state in a corresponding period, so that the interference of the temperature in the grain bin to the grain temperature prediction in the empty state can be reduced, and the grain temperature prediction can be more reliable and more accurate.
Computer storage medium
The present application also provides a computer readable storage medium storing instructions for causing a machine to perform a grain temperature prediction method as described herein. Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present application.
Examples of the storage medium for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communication network.
Computer program product
Embodiments of the present application also provide a computer program product comprising computer instructions that instruct a computing device to perform any corresponding operations of the above-described method embodiments.
It should be noted that, the information related to the user (including, but not limited to, user equipment information, user personal information, etc.) and the data related to the embodiment of the present application (including, but not limited to, sample data for training the model, data for analyzing, stored data, displayed data, etc.) are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and are provided with corresponding operation entries for the user to select authorization or rejection.
It should be noted that, according to implementation requirements, each component/step described in the embodiments of the present application may be split into more components/steps, and two or more components/steps or part of operations of the components/steps may be combined into new components/steps, so as to achieve the purposes of the embodiments of the present application.
The above-described methods according to embodiments of the present application may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and to be stored in a local recording medium downloaded through a network, so that the methods described herein may be stored on such software processes on a recording medium using a general purpose computer, special purpose processor, or programmable or special purpose hardware such as an ASIC or FPGA. It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by a computer, processor, or hardware, performs the methods described herein. Furthermore, when a general purpose computer accesses code for implementing the methods illustrated herein, execution of the code converts the general purpose computer into a special purpose computer for performing the methods illustrated herein.
It should be noted that, the information related to the user (including, but not limited to, user equipment information, user personal information, etc.) and the data related to the embodiment of the present application (including, but not limited to, sample data for training the model, data for analyzing, stored data, displayed data, etc.) are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and are provided with corresponding operation entries for the user to select authorization or rejection.
Those of ordinary skill in the art will appreciate that the elements and method steps of the examples described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.
The above embodiments are only for illustrating the embodiments of the present application, but not for limiting the embodiments of the present application, and various changes and modifications can be made by one skilled in the relevant art without departing from the spirit and scope of the embodiments of the present application, so that all equivalent technical solutions also fall within the scope of the embodiments of the present application, and the scope of the embodiments of the present application should be defined by the claims.

Claims (10)

1. A method for predicting grain temperature, comprising:
acquiring a plurality of original data sets, wherein the original data sets comprise measured temperature values corresponding to a plurality of temperature measuring points in a target granary in corresponding periods, and the periods corresponding to different original data sets are different;
taking an original data set of which the target granary is in a non-empty granary state in a corresponding period as a first data set;
and determining at least one second data set according to the first data sets, wherein the second data set comprises predicted temperature values corresponding to a plurality of temperature measuring points in the target granary in corresponding periods, different periods corresponding to the second data sets are different, and the starting time of the first period in the periods corresponding to the second data sets is the ending time of the last period in the periods corresponding to the original data sets or is before the ending time.
2. The method of claim 1, wherein the taking as the first data set the raw data set for the corresponding period that the target grain bin is in a non-empty state comprises:
acquiring an outside temperature value of the target granary in a period corresponding to each original data set;
Taking a measured temperature value, the difference value between the measured temperature value and the temperature value outside the bin in the corresponding period of which is smaller than a first threshold value, as a first temperature value;
determining a period with a corresponding first quantity ratio larger than a second threshold value as a blank period in periods corresponding to the plurality of original data sets, wherein the first quantity ratio corresponding to the period is a ratio of the quantity of first temperature values in the period to the quantity of measured temperature values in the period;
and in the periods corresponding to the plurality of original data sets, determining the original data set which is not corresponding to the period of the empty bin period as the first data set, so that the original data set which is in the non-empty bin state in the corresponding period is used as the first data set.
3. The method of claim 2, wherein the determining, among the periods corresponding to the plurality of raw data sets, at least a period for which the corresponding first number ratio is greater than the second threshold value as a blanking period comprises:
determining a period of which the corresponding first quantity ratio is larger than a second threshold value as an initial empty period in the periods corresponding to the plurality of original data sets;
acquiring a plurality of period groups, wherein the period groups comprise a plurality of continuous periods in periods corresponding to the plurality of original data groups;
Taking a period group with a corresponding second number ratio greater than a third threshold value as a blank period group, wherein the second number ratio corresponding to the period group is the ratio of the number of initial blank periods included in the period group to the number of periods included in the period group;
and respectively determining each initial empty bin period and each period in the empty bin period group as an empty bin period.
4. A method according to claim 2 or 3, wherein said determining at least one second data set from a plurality of said first data sets comprises:
obtaining a corresponding supplementary data set of the empty bin period according to a plurality of first data sets corresponding to the periods in a period window corresponding to the empty bin period, wherein the period window comprises a plurality of continuous periods, any period included in the period window of the empty bin period is the empty bin period, and the supplementary data set comprises supplementary temperature values corresponding to a plurality of temperature measuring points in a target granary in the corresponding empty bin period;
at least one second data set is determined from the plurality of supplemental data sets and the plurality of first data sets.
5. The method of claim 4, wherein said determining at least one second data set from a plurality of said first data sets before said determining at least one second data set from a plurality of said supplemental data sets and a plurality of said first data sets, further comprises:
If the supplementary data set does not comprise the supplementary temperature value corresponding to any temperature measuring point in the target granary, determining the supplementary temperature value corresponding to the temperature measuring point according to the supplementary temperature value in the supplementary data set, and adding the supplementary temperature value corresponding to the temperature measuring point into the supplementary data set;
if the first data set does not include the measured temperature value corresponding to any temperature measuring point in the target granary, determining the measured temperature value corresponding to the temperature measuring point according to the measured temperature value in the first data set, and adding the measured temperature value corresponding to the temperature measuring point into the first data set.
6. The method of claim 4, wherein said determining at least one second data set from a plurality of said supplemental data sets and a plurality of said first data sets comprises:
obtaining a target period number, wherein the target period number is any one of the maximum continuous period numbers corresponding to a plurality of granaries, the target granaries are any one of the granaries, the maximum continuous period number corresponding to the target granaries is the period number corresponding to a plurality of continuous periods with the largest included period in the periods corresponding to a plurality of supplementary data sets and the periods corresponding to a plurality of first data sets;
Determining a first period number and a second period number according to the target period number, wherein the target period number is the sum of the first period number and the second period number, and the first period number is larger than the second period number;
in the successive periods of the target number of periods, determining a first number of successive periods starting from a first period as a first successive period group, and determining a second number of successive periods ending with a last period as a second successive period group;
and determining a second data group corresponding to the second continuous period group according to the supplementary data group corresponding to the first continuous period group and the first data group.
7. A grain temperature prediction apparatus, comprising:
the acquisition unit is used for acquiring a plurality of original data sets, wherein the original data sets comprise measured temperature values corresponding to a plurality of temperature measuring points in a target granary in a corresponding period, and the periods corresponding to different original data sets are different;
the screening unit is used for taking an original data set of which the target granary is in a non-empty granary state in a corresponding period as a first data set;
and the determining unit is used for determining at least one second data set according to the plurality of first data sets, wherein the second data set comprises predicted temperature values corresponding to a plurality of temperature measuring points in the target granary in corresponding periods, periods corresponding to different second data sets are different, and the starting time of the first period in the periods corresponding to the plurality of second data sets is the ending time of the last period in the periods corresponding to the plurality of original data sets or is before the ending time.
8. An electronic device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the grain temperature prediction method according to any one of claims 1-6.
9. A computer storage medium having stored thereon a computer program which when executed by a processor implements the grain temperature prediction method of any one of claims 1 to 6.
10. A computer program product comprising computer instructions that instruct a computing device to perform the grain temperature prediction method of any one of claims 1-6.
CN202311774771.1A 2023-12-21 2023-12-21 Grain temperature prediction method and device, electronic equipment and storage medium Pending CN117609736A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311774771.1A CN117609736A (en) 2023-12-21 2023-12-21 Grain temperature prediction method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311774771.1A CN117609736A (en) 2023-12-21 2023-12-21 Grain temperature prediction method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117609736A true CN117609736A (en) 2024-02-27

Family

ID=89948046

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311774771.1A Pending CN117609736A (en) 2023-12-21 2023-12-21 Grain temperature prediction method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117609736A (en)

Similar Documents

Publication Publication Date Title
CN112529301A (en) Power consumption prediction method, equipment and storage medium
CN110995524B (en) Flow data monitoring method and device, electronic equipment and computer readable medium
CN113406496B (en) Battery capacity prediction method, system, device and medium based on model migration
CN113268641B (en) User data processing method based on big data and big data server
CN110454910B (en) Method and equipment for defrosting of air conditioner
CN118134820B (en) Self-adaptive optical remote sensing image relative radiation correction method
CN110378529A (en) Data generation method and device, readable storage medium and electronic equipment
CN116559667A (en) Model training method and device, battery detection method and device, equipment and medium
CN113240076A (en) Clock error abnormal data detection method based on clustering and neural network algorithm
CN113986700A (en) Data acquisition frequency optimization method, system, device and storage medium
CN111027435B (en) Identification system, device and method based on gradient lifting decision tree
CN117609736A (en) Grain temperature prediction method and device, electronic equipment and storage medium
CN117742816A (en) Operation control method and device of baseboard management controller
CN112906883A (en) Hybrid precision quantization strategy determination method and system for deep neural network
CN111865267B (en) Temperature measurement data prediction method and device
CN110968640A (en) Oil well data processing method and device and oil well control system
CN115877242B (en) Method for evaluating battery health state, electronic equipment and readable storage medium
CN112861951B (en) Image neural network parameter determining method and electronic equipment
CN116579551B (en) Intelligent management system and method based on intelligent manufacturing
CN113408834B (en) Communication success rate prediction method and device based on self-learning
CN117349670B (en) Tumor detection model training system, method, equipment and storage medium
CN115149126B (en) Battery pack information processing method, apparatus, electronic device, and computer-readable medium
CN117037887B (en) Solid state disk life prediction method and device
CN117314205B (en) Method and device for reporting detection results of compartment interstitial evaluation items
CN118424362B (en) Inductor temperature drift calibration method, system, electronic equipment and storage medium

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