Method and device for predicting moisture of cut tobacco at outlet of cut tobacco dryer and electronic equipment

Abstract

The embodiment of the invention discloses a cut tobacco moisture prediction method and device at an outlet of a cut tobacco dryer and electronic equipment. The method comprises the steps of obtaining first historical production data and historical weather data, and generating a first training data set and a second training data set; respectively training the initial model to obtain a first prediction model and a second prediction model; acquiring real-time combined data, respectively processing the real-time combined data based on the first prediction model and the second prediction model to obtain a first prediction result and a second prediction result, and generating a tobacco shred moisture prediction result based on the first prediction result and the second prediction result. According to the embodiment of the invention, the predicted moisture under the influence of real-time factors in a short time and the predicted moisture under the influence of systematic factors in a long time are respectively represented through two prediction results, so that the moisture condition of the tobacco shreds in production is more comprehensively and accurately grasped, and the moisture quality of finished tobacco shreds in production is better ensured.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to tobacco moisture prediction technology, and more particularly to a method, device and electronic equipment for predicting the moisture content of tobacco at the outlet of a tobacco drying machine. Background Art

[0002] In the tobacco heating process, the moisture control of tobacco is crucial to the quality of the final product. In the actual production process, even for the same batch of tobacco, the moisture content of tobacco after drying in the tobacco drying machine will change to a certain extent. If you want to better grasp the moisture quality of the finished tobacco products in production, you need to estimate the moisture content of the finished tobacco products exported by the tobacco drying machine, and decide whether to adjust the parameters of the tobacco drying machine based on the estimated results. At present, the staff generally judge the moisture content of the tobacco after drying based on their own experience, and adjust the parameters of the tobacco drying machine accordingly. They rely more on the richness of their own experience and are more subjective. They cannot accurately estimate the moisture content of tobacco, and thus cannot accurately guarantee the moisture quality of the finished tobacco products produced. Summary of the invention

[0003] In order to solve the above problems, one or more embodiments of this specification describe a method, device and electronic equipment for predicting the moisture content of cut tobacco at the outlet of a cut tobacco drying machine.

[0004] According to a first aspect, a method for predicting moisture content of cut tobacco at an outlet of a cut tobacco drying machine is provided, the method comprising: The first historical production data and the historical weather data are acquired, and after all timestamps of the first historical production data and the historical weather data are aligned based on delay processing, a first training data set and a second training data set are generated, wherein the input data of any data pair of the first training data set and the second training data set include the historical combined data of any timestamp, the output data of any data pair of the first training data set include the moisture content of the dried silk at a second before the timestamp, and the output data of any data pair of the second training data set include the moisture content of the dried silk at a preset time after the timestamp, and the historical combined data include the historical weather data and the first historical production data except the moisture content of the dried silk at a preset time; Based on the first training data set and the second training data set, initial models are trained respectively to obtain a first prediction model and a second prediction model, wherein the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data; Real-time combined data is acquired, and the real-time combined data is processed based on the first prediction model and the second prediction model respectively to obtain a first prediction result and a second prediction result, and a tobacco moisture prediction result is generated based on the first prediction result and the second prediction result.

[0005] Preferably, the first historical production data includes the zero value of the moisture meter before wire drying, the zero value of the moisture meter after wire drying, the moisture content of tobacco at the wire drying inlet, the tobacco flow rate at the wire drying inlet, the steam pressure value of wire drying, the wire drying outlet temperature, the steam flow rate in the wire drying area, the barrel temperature in the wire drying area, the hot air temperature of wire drying, the steam pressure before the valve, the workshop ambient humidity, the workshop ambient temperature, the dehumidification damper opening and the moisture content of the wire drying outlet.

[0006] Preferably, the delay-based processing to align all timestamps of the first historical production data and historical weather data includes: Delaying each first historical production data based on the data type, and calculating a moving average value corresponding to each data type according to the first historical production data within the delay time period; All timestamps of each of the moving averages and historical weather data are aligned based on the delay process.

[0007] Preferably, before generating the first training data set and the second training data set, the method further includes: The historical weather data with the same timestamp and the first historical production data except the moisture content at the dried silk outlet are combined based on a preset combination algorithm to obtain various historical combined data.

[0008] Preferably, generating the prediction result of moisture content in cut tobacco based on the first prediction result and the second prediction result includes: A prediction result trend graph is constructed based on the first prediction result and the second prediction result, and a tobacco moisture prediction result is generated according to the prediction result trend graph.

[0009] Preferably, after generating the cut tobacco moisture prediction result based on the first prediction result and the second prediction result, the method further includes: When the accumulated weight of the dried shredded tobacco on the electronic scale reaches the target weight, the first quantity of second historical production data is counted, and the first prediction model and the second prediction model are updated based on the second historical production data.

[0010] Preferably, after updating the first prediction model and the second prediction model based on the second historical production data, the method further includes: Every time a second number of second historical production data is counted, the first prediction model and the second prediction model are updated based on the second historical production data, and the second number is a number in which the accuracy of the prediction model tends to decrease.

[0011] According to a second aspect, a device for predicting moisture content of cut tobacco at an outlet of a cut tobacco drying machine is provided, the device comprising: A first acquisition module is used to acquire first historical production data and historical weather data, and generate a first training data set and a second training data set after aligning all timestamps of the first historical production data and historical weather data based on delay processing, wherein input data of any data pair of the first training data set and the second training data set include historical combined data of any timestamp, output data of any data pair of the first training data set include moisture at a dried silk thread outlet one second before the timestamp, and output data of any data pair of the second training data set include moisture at a dried silk thread outlet after a preset time has passed from the timestamp, and the historical combined data include historical weather data and the first historical production data except moisture at a dried silk thread outlet; A training module, for training initial models based on the first training data set and the second training data set respectively, to obtain a first prediction model and a second prediction model, wherein the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data; The second acquisition module is used to acquire real-time combined data, process the real-time combined data based on the first prediction model and the second prediction model respectively, obtain a first prediction result and a second prediction result, and generate a tobacco moisture prediction result based on the first prediction result and the second prediction result.

[0012] According to a third aspect, there is provided an electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0013] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or the processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0014] The method provided in the embodiments of this specification can train a first prediction model and a second prediction model according to a training data set after combining historical production data and historical weather data through delayed processing, so as to predict the moisture content of the tobacco at the outlet of the tobacco drying machine in the previous second and after a preset period of time. The two prediction results respectively represent the predicted moisture content under the influence of immediate factors in a shorter period of time and the predicted moisture content under the influence of systematic factors in a longer period of time, so as to grasp the moisture content of the tobacco in production more comprehensively and accurately, and better ensure the moisture quality of the finished tobacco products in production. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of a method for predicting moisture content of cut tobacco at the outlet of a cut tobacco drying machine in one embodiment of the present specification.

[0017] Figure 2 It is a schematic diagram of the structure of a tobacco moisture prediction device at the outlet of a tobacco drying machine in one embodiment of the present specification.

[0018] Figure 3 It is a structural diagram of an electronic device in one embodiment of this specification. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0020] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0021] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0022] See also Figure 1 , Figure 1 : is a flow chart of a method for predicting moisture content of cut tobacco at the outlet of a cut tobacco drying machine provided in an embodiment of the present application. In the embodiment of the present application, the method comprises: S101. Acquire first historical production data and historical weather data, and generate a first training data set and a second training data set after aligning all timestamps of the first historical production data and historical weather data based on delay processing.

[0023] Among them, the input data of any data pair of the first training data set and the second training data set include historical combined data of any timestamp, the output data of any data pair of the first training data set include the moisture content of the dried silk thread at the outlet one second before the timestamp, the output data of any data pair of the second training data set include the moisture content of the dried silk thread at the outlet after a preset time period from the timestamp, and the historical combined data include historical weather data and the first historical production data except the moisture content of the dried silk thread at the outlet.

[0024] The execution entity of this application can be a cloud server.

[0025] In the embodiment of the present specification, the cloud server will obtain the first historical production data, which is the historical data of parameters related to the moisture content of the finished tobacco in the tobacco drying production process, such as workshop environment humidity, tobacco moisture at the entrance of the drying machine, hot air temperature in the drying machine, tobacco moisture at the outlet of the drying machine, etc. In addition to the first historical production data, weather data is also introduced as an additional feature. Weather data may include factors such as temperature, humidity, wind speed and precipitation, which may have a significant impact on the moisture content of tobacco. Since there is a certain time interval between the change of weather data and the change of production data, it is necessary to set a certain time delay window by delay processing to align the timestamps of the first historical production data and the historical weather data, and finally generate a first training data set for training the first prediction model, and a second training data set for training the second prediction model. By combining production data and weather data, the trained model can have higher environmental adaptability and reduce quality fluctuations caused by environmental factors.

[0026] Specifically, the first historical production data and historical weather data of the same timestamp will be integrated into a data set, that is, integrated into historical combined data. The combined data is used as the input data of the model, so it is necessary to exclude the data expected to be output by the model, that is, the moisture content of the dried silk outlet. The training data set includes multiple data pairs, each of which is input data and output data associated with each other. For any data pair, the input data is the historical combined data at a certain timestamp. If it is a data pair of the first training data set, the corresponding output data is the moisture content of the dried silk outlet one second before the timestamp. The data of the previous second is selected for prediction because the equipment runs very fast in tobacco processing, and sometimes the sensor reading may fluctuate due to noise interference or other factors. By predicting the data of the previous second, almost instant process monitoring can be achieved, and these instantaneous fluctuations can be smoothed to provide more stable and reliable process variable estimates. If it is a data pair of the second training data set, the corresponding output data is the moisture content of the dried silk outlet after the preset time of the timestamp, so as to reflect the change of the moisture content of the dried silk outlet after a period of time. Among them, the specific window length of the time delay window in the delay processing and the preset time length corresponding to the output data in the second training data set can be set according to test experiments combined with experience.

[0027] In one possible implementation, the first historical production data includes the zero value of the moisture meter before wire drying, the zero value of the moisture meter after wire drying, the moisture content of tobacco at the wire drying inlet, the tobacco flow rate at the wire drying inlet, the steam pressure value of wire drying, the wire drying outlet temperature, the steam flow rate in the wire drying area, the barrel temperature in the wire drying area, the hot air temperature of wire drying, the steam pressure before the valve, the workshop ambient humidity, the workshop ambient temperature, the opening of the dehumidification damper and the moisture content at the wire drying outlet.

[0028] In the embodiments of the present specification, after acquiring the historical data, the historical data can first be cleaned to standardize and normalize the historical data. Then, through correlation analysis, the factors that have a greater impact on the moisture content of the dried tobacco outlet can be determined from the historical data as variables for model training. The historical data set of these variables is the first historical production data.

[0029] In one possible implementation, the delay-based processing to align all timestamps of the first historical production data and historical weather data includes: Delaying each first historical production data based on the data type, and calculating a moving average value corresponding to each data type according to the first historical production data within the delay time period; All timestamps of each of the moving averages and historical weather data are aligned based on the delay process.

[0030] In the embodiments of this specification, considering that each data feature is time-series, in order to make the model more effective and the data more accurate, the first historical production data will be delayed according to the data type to set a time delay window (i.e., delay time period), and the moving average of all the first historical production data of the data type in the window will be calculated to smooth the data fluctuations. Then, the moving average will be used to construct the training data set, and the moving average and historical weather data will be delayed again to align the timestamps of the two, so as to facilitate the subsequent generation of historical combined data.

[0031] In one possible implementation, before generating the first training data set and the second training data set, the method further includes: The historical weather data with the same timestamp and the first historical production data except the moisture content at the dried silk outlet are combined based on a preset combination algorithm to obtain various historical combined data.

[0032] In the embodiment of this specification, the timestamps of weather data and production data are aligned to ensure that data analysis is performed within the same time window. The corresponding formula is as follows: in, is the production data at time t, is the weather data for the time, is the delay time, is the combined data set, and f is a function that represents how to combine production data and weather data.

[0033] The cloud server is pre-set with a combination algorithm, which can be a splicing method, an aggregation method, a transform domain fusion, etc. Taking the splicing method as an example, the above formula can be transformed into: S102: Train initial models based on the first training data set and the second training data set respectively to obtain a first prediction model and a second prediction model.

[0034] Among them, the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data.

[0035] In the embodiments of this specification, the extreme neural network can better meet the prediction in the production process, so the extreme neural network model is selected as the initial model, and the first training data set and the second training data set are used to train different initial models respectively, and finally the first prediction model and the second prediction model are obtained. Among them, the weight parameter w and the bias parameter b of the model algorithm matrix will be determined by random numbers, and in order to make the prediction effect of the model more accurate, the model parameters will be regularized, and the regularization adopts ridge regression (C=0.01) to prevent the prediction model from overfitting.

[0036] The reason why the first prediction model and the second prediction model are trained separately is that the models can reflect the different characteristics of the data at different time scales. In addition, as a short-term prediction model, the first prediction model can ensure the reaction speed and achieve rapid response to meet the real-time control needs. It can quickly output the prediction results based on the current input, realize real-time process monitoring and feedback control, and ensure the stable operation of the production process. As a long-term prediction model, the second prediction model can include a more complex algorithm structure to improve accuracy, allow more complex calculations and analysis, consider more historical data and development trends, help plan and adjust production parameters in advance, optimize the efficiency of the entire production line, and prevent potential problems.

[0037] S103, acquiring real-time combined data, processing the real-time combined data based on the first prediction model and the second prediction model respectively to obtain a first prediction result and a second prediction result, and generating a tobacco moisture prediction result based on the first prediction result and the second prediction result.

[0038] In the embodiment of the present specification, after the first prediction model and the second prediction model are trained, real-time combined data, that is, real-time production data and weather data, will be obtained, and the real-time combined data will be input into the first prediction model and the second prediction model respectively to obtain the first prediction result and the second prediction result. The first prediction result can characterize the moisture content of the dried tobacco at the outlet of the previous second, and the second prediction result can characterize the moisture content of the dried tobacco at the outlet after a preset time. Finally, the cloud server will generate a prediction result of tobacco moisture content, which can be a table file, in which the first prediction result and the second prediction result are filled in, and the matching suggestion information is searched in the preset database according to the data difference between the first prediction result and the second prediction result and filled in the file to characterize whether there is an abnormality in the current production status, and the production parameters and specific adjustment values ​​recommended for adjustment when there is an abnormality. Based on the prediction result of tobacco moisture content, the staff can clearly and comprehensively understand the estimated moisture content of the dried tobacco outlet in the current production process, thereby better ensuring the moisture quality of the finished tobacco product.

[0039] In one possible implementation, generating a prediction result of moisture content in cut tobacco based on the first prediction result and the second prediction result includes: A prediction result trend graph is constructed based on the first prediction result and the second prediction result, and a tobacco moisture prediction result is generated according to the prediction result trend graph.

[0040] In the embodiments of the present specification, based on the first prediction result and the second prediction result, a prediction result trend graph can be constructed to characterize the moisture change trend of the tobacco at the drying outlet within a certain period of time. The prediction result trend graph will also be included in the tobacco moisture prediction result, so that the staff can intuitively observe the changes in the moisture of the tobacco, and then quickly determine whether the moisture will change significantly, and take corresponding treatment measures in advance for prevention.

[0041] In one possible implementation, after generating the cut tobacco moisture prediction result based on the first prediction result and the second prediction result, the method further includes: When the accumulated weight of the dried shredded tobacco on the electronic scale reaches the target weight, the first quantity of second historical production data is counted, and the first prediction model and the second prediction model are updated based on the second historical production data.

[0042] In the embodiment of the present specification, in the actual production process, as the amount of tobacco produced increases, the prediction model obtained by training with limited data will become increasingly difficult to accurately predict the moisture content of tobacco at the outlet of the drying shreds. In order to ensure the accurate prediction of the moisture content of the finished tobacco shreds, it is necessary to iteratively optimize and update the model according to the new historical production data continuously generated during the production process, that is, the second historical production data. When tobacco shreds are just beginning to be produced, the data is more likely to fluctuate. In order to reduce the accumulation of abnormal data and ensure the stability of the prediction model, the cumulative weighing weight of the electronic scale will be used as a judgment condition. If the cumulative weighing weight reaches the target weight (for example, 55KG), it is considered that enough tobacco shreds have been produced in this production process, the production has become stable, and the data is not likely to fluctuate. At this time, the newly generated second historical production data will be counted. After accumulating the first number of second historical production data, these second historical production data will be used to update the first prediction model and the second prediction model respectively. Among them, the first number can be a number preset by the staff based on experience, or it can be determined according to the minimum data required by the moving average calculation rule corresponding to the data delay.

[0043] In one possible implementation, after updating the first prediction model and the second prediction model based on the second historical production data, the method further includes: Every time a second number of second historical production data is counted, the first prediction model and the second prediction model are updated based on the second historical production data, and the second number is a number in which the accuracy of the prediction model tends to decrease.

[0044] In the embodiments of this specification, after the prediction model is trained, the prediction model can be tested to evaluate the amount of data that the model predicts before the accuracy of the prediction tends to decrease. The staff will determine the data volume node where the accuracy tends to decrease based on the test results, and set the second quantity accordingly. Starting from the second model update optimization in the production stabilization stage, each time the second amount of second historical production data is obtained, the prediction model will be updated again based on the second historical production data to continuously ensure the prediction accuracy of the prediction model throughout the production process.

[0045] The following will be combined with the attached Figure 2 , the tobacco moisture prediction device at the outlet of the tobacco drying machine provided in the embodiment of the present application is introduced in detail. Figure 2 The tobacco moisture prediction device at the outlet of the tobacco drying machine shown is used to implement the present application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0046] See also Figure 2 , Figure 2 Schematic diagram of the structure of a device for predicting moisture content of cut tobacco at the outlet of a cut tobacco drying machine provided in an embodiment of the present application. Figure 2 As shown, the device comprises: A first acquisition module 201 is used to acquire first historical production data and historical weather data, and generate a first training data set and a second training data set after aligning all timestamps of the first historical production data and historical weather data based on delay processing, wherein input data of any data pair of the first training data set and the second training data set include historical combined data of any timestamp, output data of any data pair of the first training data set include moisture at a dried silk strand outlet one second before the timestamp, output data of any data pair of the second training data set include moisture at a dried silk strand outlet after a preset time has passed from the timestamp, and the historical combined data include historical weather data and the first historical production data except moisture at a dried silk strand outlet; A training module 202 is used to train initial models based on the first training data set and the second training data set respectively to obtain a first prediction model and a second prediction model, wherein the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data; The second acquisition module 203 is used to acquire real-time combined data, process the real-time combined data based on the first prediction model and the second prediction model respectively to obtain a first prediction result and a second prediction result, and generate a tobacco moisture prediction result based on the first prediction result and the second prediction result.

[0047] In one possible implementation, the first historical production data includes the zero value of the moisture meter before wire drying, the zero value of the moisture meter after wire drying, the moisture content of tobacco at the wire drying inlet, the tobacco flow rate at the wire drying inlet, the steam pressure value of wire drying, the wire drying outlet temperature, the steam flow rate in the wire drying area, the barrel temperature in the wire drying area, the hot air temperature of wire drying, the steam pressure before the valve, the workshop ambient humidity, the workshop ambient temperature, the opening of the dehumidification damper and the moisture content at the wire drying outlet.

[0048] In one possible implementation, the first acquisition module 201 is specifically used for: Delaying each first historical production data based on the data type, and calculating a moving average value corresponding to each data type according to the first historical production data within the delay time period; All timestamps of each of the moving averages and historical weather data are aligned based on the delay process.

[0049] In one possible implementation, the first acquisition module 201 is further configured to: The historical weather data with the same timestamp and the first historical production data except the moisture content at the dried silk outlet are combined based on a preset combination algorithm to obtain various historical combined data.

[0050] In one possible implementation, the second acquisition module 203 is specifically used for: A prediction result trend graph is constructed based on the first prediction result and the second prediction result, and a tobacco moisture prediction result is generated according to the prediction result trend graph.

[0051] In one possible implementation, the second acquisition module 203 is further configured to: When the accumulated weight of the dried shredded tobacco on the electronic scale reaches the target weight, the first quantity of second historical production data is counted, and the first prediction model and the second prediction model are updated based on the second historical production data.

[0052] In one possible implementation, the second acquisition module 203 is further configured to: Every time a second number of second historical production data is counted, the first prediction model and the second prediction model are updated based on the second historical production data, and the second number is a number in which the accuracy of the prediction model tends to decrease.

[0053] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0054] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0055] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0056] The communication bus 302 is used to realize the connection and communication between these components.

[0057] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0058] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0059] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics central processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0060] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0061] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call the tobacco moisture prediction application at the outlet of the tobacco drying machine stored in the memory 305, and specifically perform the following operations: The first historical production data and the historical weather data are acquired, and after all timestamps of the first historical production data and the historical weather data are aligned based on delay processing, a first training data set and a second training data set are generated, wherein the input data of any data pair of the first training data set and the second training data set include the historical combined data of any timestamp, the output data of any data pair of the first training data set include the moisture content of the dried silk at a second before the timestamp, and the output data of any data pair of the second training data set include the moisture content of the dried silk at a preset time after the timestamp, and the historical combined data include the historical weather data and the first historical production data except the moisture content of the dried silk at a preset time; Based on the first training data set and the second training data set, initial models are trained respectively to obtain a first prediction model and a second prediction model, wherein the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data; Real-time combined data is acquired, and the real-time combined data is processed based on the first prediction model and the second prediction model respectively to obtain a first prediction result and a second prediction result, and a tobacco moisture prediction result is generated based on the first prediction result and the second prediction result.

[0062] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0063] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0064] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0065] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0066] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0067] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0068] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0069] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware. The program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0070] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for predicting moisture content of cut tobacco at the outlet of a cut tobacco drying machine, characterized in that: The method comprises: The first historical production data and the historical weather data are acquired, and after all timestamps of the first historical production data and the historical weather data are aligned based on delay processing, a first training data set and a second training data set are generated, wherein the input data of any data pair of the first training data set and the second training data set include the historical combined data of any timestamp, the output data of any data pair of the first training data set include the moisture content of the dried silk at a second before the timestamp, and the output data of any data pair of the second training data set include the moisture content of the dried silk at a preset time after the timestamp, and the historical combined data include the historical weather data and the first historical production data except the moisture content of the dried silk at a preset time; Based on the first training data set and the second training data set, initial models are trained respectively to obtain a first prediction model and a second prediction model, wherein the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data; Real-time combined data is acquired, and the real-time combined data is processed based on the first prediction model and the second prediction model respectively to obtain a first prediction result and a second prediction result, and a tobacco moisture prediction result is generated based on the first prediction result and the second prediction result.

2. The method according to claim 1, characterized in that The first historical production data includes the zero value of the moisture meter before wire drying, the zero value of the moisture meter after wire drying, the moisture content of the tobacco at the wire drying inlet, the tobacco flow rate at the wire drying inlet, the steam pressure value of the wire drying, the wire drying outlet temperature, the steam flow rate in the wire drying area, the barrel temperature in the wire drying area, the hot air temperature of the wire drying, the steam pressure before the valve, the workshop ambient humidity, the workshop ambient temperature, the dehumidification damper opening and the moisture content of the wire drying outlet.

3. The method according to claim 1, characterized in that The delay-based processing aligns all time stamps of the first historical production data and the historical weather data, including: Delaying each first historical production data based on the data type, and calculating a moving average value corresponding to each data type according to the first historical production data within the delay time period; All timestamps of each of the moving averages and historical weather data are aligned based on the delay process.

4. The method according to claim 1, characterized in that: Before generating the first training data set and the second training data set, the method further includes: The historical weather data with the same timestamp and the first historical production data except the moisture content at the dried silk outlet are combined based on a preset combination algorithm to obtain various historical combined data.

5. The method according to claim 1, characterized in that The generating the prediction result of moisture content of the cut tobacco based on the first prediction result and the second prediction result comprises: A prediction result trend graph is constructed based on the first prediction result and the second prediction result, and a tobacco moisture prediction result is generated according to the prediction result trend graph.

6. The method according to claim 1, characterized in that After generating the prediction result of cut tobacco moisture based on the first prediction result and the second prediction result, the method further includes: When the accumulated weight of the dried shredded tobacco on the electronic scale reaches the target weight, the first quantity of second historical production data is counted, and the first prediction model and the second prediction model are updated based on the second historical production data.

7. The method according to claim 6, characterized in that After the first prediction model and the second prediction model are updated based on the second historical production data, the method further includes: Every time a second number of second historical production data is counted, the first prediction model and the second prediction model are updated based on the second historical production data, and the second number is a number in which the accuracy of the prediction model tends to decrease.

8. A device for predicting moisture content of cut tobacco at the outlet of a cut tobacco drying machine, characterized in that: The device comprises: A first acquisition module is used to acquire first historical production data and historical weather data, and generate a first training data set and a second training data set after aligning all timestamps of the first historical production data and historical weather data based on delay processing, wherein input data of any data pair of the first training data set and the second training data set include historical combined data of any timestamp, output data of any data pair of the first training data set include moisture at a dried silk thread outlet one second before the timestamp, and output data of any data pair of the second training data set include moisture at a dried silk thread outlet after a preset time has passed from the timestamp, and the historical combined data include historical weather data and the first historical production data except moisture at a dried silk thread outlet; A training module, for training initial models based on the first training data set and the second training data set respectively, to obtain a first prediction model and a second prediction model, wherein the initial model is an extreme neural network model, the first prediction model is used to output the moisture content of the dried silk at the outlet in the previous second according to the current combined data, and the second prediction model is used to output the moisture content of the dried silk at the outlet after a preset time according to the current combined data; The second acquisition module is used to acquire real-time combined data, process the real-time combined data based on the first prediction model and the second prediction model respectively, obtain a first prediction result and a second prediction result, and generate a tobacco moisture prediction result based on the first prediction result and the second prediction result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images