Grain moisture content detection method and device, combine harvester, equipment and medium

Abstract

The invention provides a grain moisture content detection method and device, a combine harvester, equipment and a medium. The method comprises the steps that the temperature of the environment where grains are located, the relative dielectric constant of the grains and the volume weight of the grains within a preset time period are collected; based on the temperature, the relative dielectric constant and the volume weight, training through a grain moisture content detection model to obtain the moisture content of the grain in a preset time period; and periodically detecting the moisture content of the grains through a grain moisture content detection model. According to the cereal moisture content detection method provided by the invention, regression prediction of data is carried out by adopting a multi-influence-factor nonlinear method, fitting regression accuracy of a cereal moisture content detection model is improved by considering multiple influence factors, and the moisture content of the cereal is further periodically detected through the cereal moisture content detection model, so that the detection accuracy of the cereal moisture content is improved. The moisture content of the grains can be stably detected for a long time, the reliability is high, and the accuracy of detecting the moisture content of the grains is integrally improved.

Description

Technical Field

[0001] The present invention relates to the technical field of grain detection, and in particular to a grain moisture content detection method, device, combine harvester, equipment and medium. Background Art

[0002] The moisture content of grains refers to the percentage of water contained in grains. It is a key quality parameter that directly affects the grain's ability to preserve, its operability during processing, and the quality of the final product.

[0003] The current method for detecting grain moisture content is the indirect method. The indirect method uses physical quantities related to the moisture content of the substance being tested to reflect the moisture content, which is suitable for rapid detection in harvesting production. The indirect method often uses capacitance method or infrared method to detect grain moisture content. Among them, the capacitance method mostly uses electrode plates as a detection method. When the detection frequency is low, the capacitance value will be affected by conductivity and is easily affected by marginal effects during use. The equipment used by the infrared method is relatively expensive, and the infrared method has high requirements for environmental conditions. Changes in temperature, humidity, etc. will affect the measurement results. Therefore, the above methods are not very accurate in the actual grain moisture content detection process. Summary of the invention

[0004] The invention provides a method, a device, a combine harvester, equipment and a medium for detecting the moisture content of grains, so as to solve the problem of low accuracy in detecting the moisture content of grains in the prior art.

[0005] In a first aspect, the present invention provides a method for detecting moisture content of grains, comprising: Collect the temperature of the environment in which the grain is located, the relative dielectric constant and volume weight of the grain within a preset time period; Based on the temperature, the relative dielectric constant and the volume weight, a grain moisture content detection model is trained to obtain the moisture content of the grain within the preset time period; the grain moisture content detection model is built based on a GA-BP neural network model; The moisture content of the grains is periodically detected by the grain moisture content detection model.

[0006] In one embodiment, the collecting of the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period includes: Control the temperature sensor to collect the temperature of the environment where the grain is located within a preset time period; Controlling the moisture content sensor to collect the relative dielectric constant of the grains within the preset time period; Controlling the gravity sensor to collect the volume weight of the grains within the preset time period; Wherein, the temperature sensor, the moisture content sensor and the gravity sensor are arranged inside a grain collecting box, and the grain collecting box is used to store grains.

[0007] In one embodiment, the method of training a grain moisture content detection model based on the temperature, the relative dielectric constant and the volume weight to obtain the grain moisture content within the preset time period includes: Determine the region and variety information of the grain; The region information, the variety information, the temperature, the relative dielectric constant and the volume weight are input into the grain moisture content detection model to obtain the moisture content of the grain within the preset time period output by the grain moisture content detection model.

[0008] In one embodiment, the periodic detection of the moisture content of the grains by the grain moisture content detection model includes: Stop controlling the temperature sensor, the moisture content sensor and the gravity sensor to collect data; The grain is discharged from the grain collecting box into the grain unloading bin within the preset time period by means of a grain discharger; Stopping the discharge of grain from the grain collecting box into the grain unloading bin through the grain discharger; If the grain in the grain unloading bin reaches a preset position, the periodic detection of the moisture content of the grain is terminated; If the grain in the grain unloading bin has not reached the preset position, the steps of collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volumetric weight of the grain within a preset time period are repeated until the grain in the grain unloading bin reaches the preset position, and the moisture content of the grain within multiple preset time periods output by the grain moisture content detection model is obtained, and the periodic detection of the moisture content of the grain is ended.

[0009] In one embodiment, after periodically detecting the moisture content of the grains through the grain moisture content detection model, the method further comprises: After the grains in the grain unloading bin reach a preset position, the control display terminal displays information that the grain unloading bin is full, and displays the moisture content of the grains in multiple preset time periods.

[0010] In one embodiment, the grain moisture content detection model is trained in the following manner: Initialize the GA-BP neural network model; Obtain grain samples from different regions and varieties; Collecting a temperature sample of the environment in which the grain sample is located, a relative dielectric constant sample and a volume weight sample of the grain sample within the preset time period; Determining moisture content label data of the grain sample within the preset time period; Based on the grain sample, the region information sample of the grain sample, the variety information sample of the grain sample, the temperature sample, the relative dielectric constant sample, the volume weight sample and the moisture content label data, the GA-BP neural network model is trained to obtain the grain moisture content detection model.

[0011] In a second aspect, the present invention further provides a grain moisture content detection device, comprising: A collection module is used to collect the temperature of the environment in which the grains are located, the relative dielectric constant and the volume weight of the grains within a preset time period; A grain moisture content detection module, used to obtain the moisture content of the grain within the preset time period by training a grain moisture content detection model based on the temperature, the relative dielectric constant and the volume weight; the grain moisture content detection model is built based on a GA-BP neural network model; The periodic moisture content detection module is used to periodically detect the moisture content of grains through the grain moisture content detection model.

[0012] In a third aspect, the present invention further provides a combine harvester, comprising a grain moisture content detection device, a grain collecting box, a grain discharger, a grain unloading bin, a temperature sensor, a moisture content sensor, a gravity sensor and a display terminal; The grain collection box is used to store grains; The grain discharger is used to discharge the grain stored in the grain collecting box into the grain unloading bin; The grain unloading bin is used to store grain discharged from the grain collecting box; The temperature sensor is used to collect the temperature of the environment in which the grains are located; The moisture content sensor is used to collect the relative dielectric constant of the grain; The gravity sensor is used to collect the volume weight of the grains; Wherein, the temperature sensor, the moisture content sensor and the gravity sensor are arranged inside the grain collecting box; and the grain discharger is arranged between the grain collecting box and the grain unloading bin.

[0013] In a fourth aspect, the present invention provides a device, comprising an electronic device, wherein the electronic device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the grain moisture content detection methods described above are implemented.

[0014] In a fifth aspect, the present invention further provides a medium, comprising a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the grain moisture content detection methods described above are implemented.

[0015] The grain moisture content detection method, device, combine harvester, equipment and medium provided by the present invention comprehensively consider various influencing factors such as the temperature of the environment in which the grain is located, the relative dielectric constant and volume weight of the grain, etc., and perform regression prediction through a grain moisture content detection model obtained by building a GA-BP neural network model to obtain the moisture content of the grain in the current preset time period. Compared with the existing detection methods that mostly only use linear fitting methods, a nonlinear method of multiple influencing factors is used to perform regression prediction of data. By considering multiple influencing factors, the fitting regression accuracy of the grain moisture content detection model is improved. Further, through the grain moisture content detection model, the moisture content of the grain is periodically detected, and the long-term and stable detection of the moisture content of the grain is achieved with high reliability, thereby improving the accuracy of grain moisture content detection as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is one of the flow charts of the grain moisture content detection method provided by the present invention.

[0018] Figure 2 The present invention provides a system hardware block diagram of the combine harvester.

[0019] Figure 3 It is a schematic diagram for comparing the measured moisture content and the calculated moisture content provided by an embodiment of the present invention.

[0020] Figure 4 This is the second flow chart of the grain moisture content detection method provided by the present invention.

[0021] Figure 5 It is a comparative schematic diagram of the model prediction provided by the present invention.

[0022] Figure 6 It is a structural schematic diagram of a grain moisture content detection device provided by the present invention.

[0023] Figure 7 It is a schematic diagram of the device of the combine harvester provided by the present invention.

[0024] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein.

[0027] Combine the following Figure 1-Figure 8 The invention describes a method, a device, a combine harvester, equipment and a medium for detecting moisture content of grains.

[0028] Combination Figure 1 and Figure 2 , Figure 1 This is one of the flow charts of the method for detecting moisture content of grains provided by the present invention. Figure 2 The present invention provides a system hardware block diagram of the combine harvester.

[0029] like Figure 1 As shown, the method includes the following: Step 101, collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period; Step 102: Based on the temperature, the relative dielectric constant and the volume weight, a grain moisture content detection model is trained to obtain the grain moisture content within the preset time period; Step 103: Periodically detect the moisture content of the grains using the grain moisture content detection model.

[0030] It should be noted that the grain moisture content detection method provided in the embodiment of the present invention is implemented based on a combine harvester, which is an agricultural mechanical equipment mainly used for harvesting crops such as wheat, barley, corn, etc. Its function is to complete harvesting, threshing and cleaning crops in one step. Figure 2 As shown, the system of the combine harvester is composed of a sampling mechanism, a data acquisition module, a host computer terminal, and several wires and serial port data transmission lines for providing circuit connections, and the control chip inside the system is an STM32F103 chip.

[0031] The sampling mechanism is composed of a grain collecting box, a grain discharging motor, a motor driving module, a grain discharging device, a grain unloading bin and a supporting crossbeam. The grain collecting box is used to store grains harvested by a combine harvester. The grain discharging motor driving module is used to drive the grain discharging motor to start. The grain discharging motor is used to drive the grain discharging device to discharge the grains in the grain collecting box from the grain collecting box into the grain unloading bin. The grain unloading bin is used to store the grains discharged from the grain collecting box. The supporting crossbeam is used to provide structural support and stability for multiple components. The sampling mechanism and the supporting crossbeam are tightly combined with 4 M8 screws. The data acquisition module is composed of a temperature sensor, a moisture content sensor, a gravity sensor, a grain level sensor 1 and a grain level sensor 2. The temperature sensor, the moisture content sensor and the gravity sensor are all used to collect data related to the moisture content of grains. The grain level sensor 1 is used to detect whether the grains in the grain collecting box have reached a certain high level. The grain level sensor 2 is used to detect whether the grains in the grain unloading bin have reached a certain high level. The two grain level sensors can be used to judge the current grain sampling situation and realize the automatic control start and stop of the system. The host computer terminal is used to control the sampling mechanism and the data acquisition module to jointly complete the detection of grain moisture content, which can realize data storage and data processing. In addition, the host computer terminal also includes a display terminal, which can realize data display. Since the host computer terminal can control the sampling mechanism and the data acquisition module to jointly complete the detection of grain moisture content, the host computer terminal is the executor of the grain moisture content detection method of the present invention, which is equivalent to the grain moisture content detection device. The embodiment of the present invention uses the host computer terminal to describe the entire process.

[0032] In addition, the combine harvester system uses RS485 communication and serial port communication to achieve data transmission between different modules of the entire system. Modbus protocol is used through RS485 to collect data related to grain moisture content, and Modbus protocol is used to set the data frame header and tail of the transmitted hexadecimal data to verify the data and eliminate distorted data.

[0033] The following describes in detail the process of grain moisture content detection.

[0034] Specifically, the combine harvester starts the harvesting condition in the field. Under the harvesting condition, the harvested grains are thrown into the grain collecting box through the elevator and the axial agitator. A plurality of sensors are arranged in the grain collecting box to provide the sensors with a stable detection environment and a relatively sealed grain container, thereby ensuring that there is a stable container to contain the grains after they are thrown out from the elevator.

[0035] Furthermore, when the grain collection box is filled with grain, the grain level sensor 1 installed on the top of the grain collection box is triggered, and the grain level sensor 1 transmits a grain level signal to the host computer terminal, so that the host computer terminal activates multiple sensors and starts the detection condition.

[0036] Furthermore, the host terminal controls multiple sensors to collect the temperature of the environment in which the grains are located, the relative dielectric constant and the volume weight of the grains within a preset time period, wherein the preset time period is set according to actual conditions and can be set to 4 seconds.

[0037] Furthermore, the multiple sensors transmit the collected temperature of the environment in which the grains are located within a preset time period, the relative dielectric constant and the volume weight of the grains to the host computer terminal.

[0038] Furthermore, the host computer terminal trains the grain moisture content detection model based on the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period to obtain the moisture content of the grain within the preset time period, wherein the grain moisture content detection model is built based on the GA-BP neural network model, and the genetic algorithm - back propagation algorithm (Genetic Algorithm - Back Propagation, GA-BP) neural network model is a neural network model that combines the genetic algorithm and the back propagation algorithm.

[0039] It should be noted that, considering the large sample data and many input features, the traditional linear modeling method cannot fit nonlinear data well, and the support vector machine (SVM) regression has a poor fitting effect in large-capacity sample data. Therefore, the embodiment of the present invention introduces the BP neural network algorithm to perform data fitting prediction. The back propagation neural network model BP is a multi-layer feedforward neural network model that processes information through three layers of neurons in the input layer, hidden layer, and output layer. The signal forward propagation is optimized to find the optimal initialization parameters, and the error back propagation adjusts the weights and thresholds of the network. Factors affecting the moisture content of grains include relative dielectric constant, temperature, and volume weight. Therefore, relative dielectric constant, temperature, and volume weight are used as input features, and grain moisture content is used as an output parameter. The genetic algorithm is an algorithm designed based on Darwin's theory of evolution. The main idea of ​​the genetic algorithm is to simulate the process of natural selection and fitness increase in the process of biological evolution. Through operations such as selection, crossover, and mutation, the fitness of the population is continuously optimized to finally obtain the optimal solution. When using GA-BP neural network regression prediction problems, scientific research combines the search ability of genetic optimization algorithm and the learning ability of BP neural network, making full use of the advantages of both to obtain more accurate prediction results.

[0040] Furthermore, the host computer terminal will stop multiple sensors for data collection, start the grain discharge condition, and stop the grain discharge project after executing the preset time period. Furthermore, the host computer terminal will reactivate multiple sensors for data collection, and make predictions based on the collected data through the grain moisture content detection model. The conversion between the detection condition and the grain discharge condition is periodically realized in the above manner. During this period, the moisture content of the grain in the grain bin is predicted online through the grain moisture content detection model.

[0041] The grain moisture content detection method provided by the present invention comprehensively considers various influencing factors such as the temperature of the environment in which the grain is located, the relative dielectric constant and volume weight of the grain, and performs regression prediction through a grain moisture content detection model obtained by building a GA-BP neural network model to obtain the moisture content of the grain in the current preset time period. Compared with the existing detection methods that mostly only use linear fitting methods, a nonlinear method of multiple influencing factors is used to perform regression prediction of data. By considering multiple influencing factors, the fitting regression accuracy of the grain moisture content detection model is improved. Further, through the grain moisture content detection model, the moisture content of the grain is periodically detected to achieve long-term and stable detection of the moisture content of the grain with high reliability, thereby improving the accuracy of grain moisture content detection as a whole.

[0042] Further, based on step 101, the collecting of the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period includes: Control the temperature sensor to collect the temperature of the environment where the grain is located within a preset time period; Controlling the moisture content sensor to collect the relative dielectric constant of the grains within the preset time period; Controlling the gravity sensor to collect the volume weight of the grains within the preset time period; Wherein, the temperature sensor, the moisture content sensor and the gravity sensor are arranged inside a grain collecting box, and the grain collecting box is used to store grains.

[0043] It should be noted that at least a temperature sensor, a moisture content sensor and a gravity sensor are arranged inside the grain collection box, and the grain collection box provides a stable detection environment, so that the temperature sensor, the moisture content sensor and the gravity sensor can stably collect data related to the moisture content of grains.

[0044] Specifically, the host computer terminal controls the temperature sensor to collect the temperature of the environment in which the grain is located within a preset time period, controls the moisture content sensor to collect the relative dielectric constant of the grain within a preset time period, and controls the gravity sensor to collect the volume weight of the grain within a preset time period.

[0045] It should be noted that the relative dielectric constant of grains changes with the change of moisture content. The dielectric constant is a measure of the response of a medium to an electric field. An increase in moisture content will increase the dielectric constant of grains. Therefore, changes in moisture content will directly affect the response and performance of grains in electromagnetic fields. The volume weight of grains will change with the increase of moisture content. Usually, with the increase of moisture content, the density of grains will decrease because the addition of water will increase the volume of grains while the mass remains relatively unchanged or increases slightly. The moisture content of grains is usually affected by the ambient temperature. At high temperatures, the evaporation rate of moisture in grains will increase, while at low temperatures, condensation may occur or the evaporation rate may decrease. Therefore, the ambient temperature directly affects the moisture content of grains.

[0046] It should be further explained that for the factor of relative dielectric constant that affects moisture content, a detection method based on dielectric properties was selected for data collection, avoiding many shortcomings of the capacitance method, microwave method, near-infrared spectroscopy method, etc. that are currently widely used on the market, such as high sensor cost, parallel electrode plates are easily affected by marginal effects and vibrations, and hyperspectral method is not suitable for online monitoring outside the laboratory. This has realized a high-precision online detection method for grain moisture content that can be carried on a combine harvester.

[0047] Since the sampling mechanism of the embodiment of the present invention provides a stable detection environment and is suitable for the installation and mounting environment of the combine harvester, the temperature sensor, moisture content sensor and gravity sensor arranged inside the grain collection box can stably collect data related to the moisture content of the grain, thereby making the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain collected within a preset time period more accurate.

[0048] Further, based on step 102, the moisture content of the grains within the preset time period is obtained by training a grain moisture content detection model based on the temperature, the relative dielectric constant and the volume weight, including: Determine the region and variety information of the grain; The region information, the variety information, the temperature, the relative dielectric constant and the volume weight are input into the grain moisture content detection model to obtain the moisture content of the grain within the preset time period output by the grain moisture content detection model.

[0049] Specifically, the host terminal determines the region information and variety information of the grain.

[0050] Furthermore, the host computer terminal inputs the region information of the grain, the variety information of the grain, the temperature of the environment in which the grain is located, the relative dielectric constant of the grain and the volume weight of the grain into the grain moisture content detection model to obtain the moisture content of the grain within a preset time period output by the grain moisture content detection model.

[0051] In one embodiment, the implementation process of the grain moisture content detection model is as follows: read data, confirm the verification set and test set samples of the BP neural network model, scale the test data, eliminate the systematic errors caused by different dimensions, and normalize the data to between 0 and 1; set network parameters, set the maximum number of model iterations to 1000, the learning rate to 1×10-4, and the learning error threshold to 1×10-6; initialize parameters, set the initial population size N and the maximum number of iterations T of the GA algorithm, set the initial population size to 20, and the genetic generation to 100; calculate and store fitness, calculate individual fitness values ​​through fitness functions, and find individuals corresponding to the optimal fitness through crossover and mutation operations by genetic algorithms; the BP neural network uses the optimal individuals obtained by the genetic algorithm to assign initial weights and thresholds to the network, and predicts sample output after the network is trained with samples.

[0052] In one embodiment, in combination Figure 3 , Figure 3 The diagram is a comparison diagram between the measured moisture content and the calculated moisture content provided by the embodiment of the present invention. The moisture content of the grain calculated by the grain moisture content detection model is compared with the moisture content of the grain measured by the drying method. The correlation coefficient R² is 0.986. Figure 3 It can be seen that the error between the moisture content of grains calculated by the model and the moisture content of grains measured by the drying method is small. The drying method achieves moisture content detection by destroying the original physical properties of grain kernels. The test results are relatively accurate, but the cost is high and the detection cycle is long. It is not suitable for rapid online detection. Therefore, by comparison, it is found that the error between the moisture content calculated by the model and the moisture content measured by the drying method is small. It can be considered that the moisture content calculated by the model is more accurate, and rapid online detection can be achieved through model calculation.

[0053] The embodiment of the present invention inputs the collected relative dielectric constant, temperature, volume weight and other related information into the grain moisture content detection model built by the GA-BP neural network model, and performs regression prediction through the model, and can calculate the real-time moisture content according to the temperature under the current harvest state, the collected volume weight, the relative dielectric constant and other related data affecting the moisture content. Compared with the existing detection methods, which mostly only use the linear fitting method, the nonlinear method of multiple influencing factors is used to perform data regression prediction. By considering multiple influencing factors, especially the influencing factor of volume weight, the fitting regression accuracy of the grain moisture content detection model is improved, and the accuracy of the online detection of the grain moisture content of the combine harvester is improved. In addition, the grain moisture content detection process also takes into account factors such as the region information and variety information of the grain. Therefore, the regression prediction through the grain moisture content detection model is not only applicable to grains of a single variety in a single region, but also has an accurate detection effect on grains of different varieties in different regions, thereby improving the applicability of grain moisture content detection.

[0054] Further, based on step 103, the periodic detection of the moisture content of the grains by the grain moisture content detection model includes: Stop controlling the temperature sensor, the moisture content sensor and the gravity sensor to collect data; The grain is discharged from the grain collecting box into the grain unloading bin within the preset time period by means of a grain discharger; Stopping the discharge of grain from the grain collecting box into the grain unloading bin through the grain discharger; If the grain in the grain unloading bin reaches a preset position, the periodic detection of the moisture content of the grain is terminated; If the grain in the grain unloading bin has not reached the preset position, the steps of collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volumetric weight of the grain within a preset time period are repeated until the grain in the grain unloading bin reaches the preset position, and the moisture content of the grain within multiple preset time periods output by the grain moisture content detection model is obtained, and the periodic detection of the moisture content of the grain is ended.

[0055] Combination Figure 4 , Figure 4 This is the second flow chart of the grain moisture content detection method provided by the present invention.

[0056] Specifically, after the system is initialized, when the grain storage bin is full of grains, the grain level sensor 1 installed on the top of the grain collection box is triggered, and the grain level sensor 1 transmits a grain level signal to the host computer terminal. The host computer terminal activates the temperature sensor, moisture content sensor and gravity sensor to collect the temperature of the environment in which the grains are located, the relative dielectric constant and volume weight of the grains within a preset time period, respectively. Further, based on the collected data and the regional information and variety information of the grains, the grain moisture content detection model is used to predict the moisture content of the grains in the grain storage bin.

[0057] Furthermore, the host computer terminal turns off the temperature sensor, moisture content sensor and gravity sensor to stop the temperature sensor, moisture content sensor and gravity sensor from collecting data, that is, after starting the detection condition for a preset time period, the grain discharge condition is started.

[0058] Furthermore, the upper computer terminal controls the grain discharge electrical drive module to start grain discharge. After receiving the start signal, the grain discharge electrical drive module drives the grain discharge motor to start. The grain discharge motor drives the grain discharger located between the grain collecting box and the grain unloading bin, and drives the grain discharge shaft in the grain discharger. The grain discharger discharges the grain from the grain collecting box into the grain unloading bin within a preset time period.

[0059] Furthermore, after the upper computer terminal starts the grain discharge operation for a preset time period, the grain discharge motor is turned off to stop the grain discharger from discharging the grain from the grain collecting box into the grain unloading bin.

[0060] Furthermore, when the grain in the grain unloading bin reaches the preset position, which means that the grain unloading bin is nearly full of received grain, the grain will accumulate under the supporting beam, thereby triggering the grain level sensor 2 installed at the bottom of the supporting beam. Therefore, if the grain in the grain unloading bin reaches the preset position, the grain level sensor 2 is triggered, and the grain level sensor 2 transmits the grain level signal to the upper computer terminal, and the upper computer terminal ends the periodic detection of the moisture content of the grain in the grain unloading bin.

[0061] Furthermore, if the grain in the grain unloading bin has not reached the preset position and the grain level sensor 2 is not triggered, the host computer terminal repeats the steps of collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period until the grain in the grain unloading bin reaches the preset position, obtains the moisture content of the grain within multiple preset time periods output by the grain moisture content detection model, and ends the periodic detection of the moisture content of the grain.

[0062] Therefore, the detection working condition and the grain discharge working condition are switched in the above manner to achieve a working condition cycle and realize periodic detection of the moisture content of the grain.

[0063] In the embodiment of the present invention, when the grain bin is full of grains, after the grain level sensor 1 is triggered, motor control and signal acquisition are implemented according to the detection logic, and periodic switching between the detection condition and the grain discharge condition is performed, and the workflow of setting dynamic sampling, static intermittent detection and periodic grain discharge is realized, which can avoid the vibration generated by the combine harvester when discharging grain, which affects the data collected by multiple sensors and causes inaccurate prediction results output by the grain moisture content detection model. Therefore, by setting the workflow of dynamic sampling, static intermittent detection and periodic grain discharge, the stable measurement of temperature, relative dielectric constant, volume weight and other data related to grain moisture content and the accurate output of grain moisture content can be achieved.

[0064] Further, after periodically detecting the moisture content of the grains through the grain moisture content detection model, the method further comprises: After the grains in the grain unloading bin reach a preset position, the control display terminal displays information that the grain unloading bin is full, and displays the moisture content of the grains in multiple preset time periods.

[0065] Specifically, after the grain in the grain unloading bin reaches the preset position, in order to prevent the grain in the grain unloading bin from being overfilled and squeezing into the sampling mechanism, the upper computer terminal will end the periodic detection of the moisture content of the grain and control the display terminal to display the information that the grain unloading bin is full to prompt the product user.

[0066] Furthermore, the host computer terminal controls the display terminal to display the moisture content of the grains in multiple preset time periods output by the grain moisture content detection model.

[0067] The embodiment of the present invention displays the information that the grain unloading bin is full through the display terminal, so as to prompt the product user to clean up the grain in the grain unloading bin in time. At the same time, the grain moisture content data output by the model is also displayed through the display terminal, providing the product user with an intuitive moisture content status, which is convenient for judging the quality status of the currently harvested grains and making arrangements for the next stage of production.

[0068] Furthermore, the grain moisture content detection model is trained in the following way: Initialize the GA-BP neural network model; Obtain grain samples from different regions and varieties; Collecting a temperature sample of the environment in which the grain sample is located, a relative dielectric constant sample and a volume weight sample of the grain sample within the preset time period; Determining moisture content label data of the grain sample within the preset time period; Based on the grain sample, the region information sample of the grain sample, the variety information sample of the grain sample, the temperature sample, the relative dielectric constant sample, the volume weight sample and the moisture content label data, the GA-BP neural network model is trained to obtain the grain moisture content detection model.

[0069] Specifically, the host computer terminal initializes the GA-BP neural network model.

[0070] Furthermore, the host terminal obtains grain samples from different regions and varieties.

[0071] Furthermore, the host computer terminal can collect temperature samples of the environment in which the grain samples are located, relative dielectric constant samples and volume weight samples of the grain samples within a preset time period through sensors.

[0072] Furthermore, the host computer terminal determines the moisture content label data of the grain sample within a preset time period, and can obtain the moisture content label data of the grain sample by a direct method or an indirect method.

[0073] Furthermore, the host terminal trains the GA-BP neural network model based on the grain samples, the region information samples of the grain samples, the variety information samples of the grain samples, the temperature samples, the relative dielectric constant samples, the volume weight samples and the moisture content label data to obtain the grain moisture content detection model.

[0074] In order to verify that the BP neural network algorithm based on genetic optimization algorithm is stable and reliable, the original data is divided into 80 training sets and 25 validation sets using 4 models for prediction. The relevant validation evaluation indicators are shown in the table. Table 1 shows the prediction results of the support vector machine, BP neural network, GA-BP neural network based on genetic optimization, and neural network models based on particle swarm optimization and back propagation algorithm (Particle Swarm Optimization - Back Propagation Neural Network, PSO-BP). The prediction results are shown in Appendix 1.

[0075] The prediction accuracy of the model is mainly measured by root mean square error (RMSE), mean absolute error (MAE), mean bias error (MBE) and determination coefficient (R²). The specific calculation formula is as follows:

[0076] in, Represents actual value; represents the predicted value; n represents the number of samples; SSE represents the residual sum of squares; SST represents the total sum of squares of deviations.

[0077] The smaller the MAE, MBE, and RMSE, the closer the fitting effect is to the actual value, that is, the better the fitting effect is and the more accurate the prediction model is. The coefficient of determination R² indicates the goodness of fit of the function, and its value range is [0,1]. The closer it is to 1, the better the fitting effect of the function is.

[0078] Table 1 Model results

[0079] From Table 1, it can be seen that compared with the SVM support vector machine, the BP neural network and the GA-BP and PSO-BP neural network models can better predict the moisture content of grains at different temperatures and bulk densities. The root mean square error RMESE of the retraining set and the validation set of the GA-BP neural network model based on the genetic optimization algorithm are 0.2591 and 0.3061 respectively; the mean absolute error MAE is 0.17263 and 0.194; the mean square error MBE is 0.02355 and -0.016 respectively; the determination coefficient is 0.99633 and 0.99631 respectively. Compared with the traditional BP neural network model and the PSO-BP neural network model, the GA-BP neural network model has lower mean absolute error MAE and mean square error MBE on the retraining set and the validation set, and has a determination coefficient R² that is closer to 1, and the calculation accuracy is higher than that of the BP neural network model and the PSO-BP neural network model. This shows that the GA-BP neural network model is superior to other models in predicting the moisture content of grains at different temperatures and different bulk densities, and can better explore the nonlinear mapping relationship between temperature, bulk density, dielectric constant and grain moisture content.

[0080] The trained neural network model predicts moisture content. The best performance was achieved after 41 rounds of training, and the training error was 0.01764 after 100 rounds of training. Figure 5 , Figure 5 is a comparative schematic diagram of the model prediction provided by the present invention, Figure 5It can be seen that the maximum and minimum errors between the training set and the validation value are 5.52% and 0.018%, and the average relative error is 1.34%. The minimum error between the validation set and the test value is 0.0538%, the maximum error is 8.1984%, and the average relative error is 2.3%. Therefore, the GA-BP neural network model is suitable for the prediction and analysis of the moisture content of grains after training. It can well explore the relationship between temperature, dielectric constant and moisture content, and provide a feasible solution for the regression prediction of moisture content of grains with different volume weights and temperatures.

[0081] The embodiment of the present invention obtains temperature samples of the environment in which the grain samples are located, relative dielectric constant samples and volume weight samples of the grain samples, and regional information samples and variety information samples, and takes into account factors of different regions and different varieties of grain samples, as well as multiple factors affecting grain moisture content. Based on all-round factors and grain samples and moisture content label data of grain samples, a GA-BP neural network model is trained to obtain a grain moisture content detection model. The grain moisture content detection model can be used to calculate dynamic real-time moisture content, thereby improving the accuracy and applicability of grain moisture content detection.

[0082] The grain moisture content detection device provided by the present invention is described below. The grain moisture content detection device described below and the grain moisture content detection method described above can be referenced to each other.

[0083] Reference Figure 6 , Figure 6 It is a structural schematic diagram of a grain moisture content detection device provided by the present invention.

[0084] The grain moisture content detection device comprises: The collection module 610 is used to collect the temperature of the environment in which the grains are located, the relative dielectric constant and the volume weight of the grains within a preset time period.

[0085] The grain moisture content detection module 620 is used to obtain the moisture content of the grain within the preset time period by training the grain moisture content detection model based on the temperature, the relative dielectric constant and the volume weight; the grain moisture content detection model is built based on the GA-BP neural network model.

[0086] The periodic moisture content detection module 630 is used to periodically detect the moisture content of the grains through the grain moisture content detection model.

[0087] The grain moisture content detection device provided by the present invention comprehensively considers various influencing factors such as the temperature of the environment in which the grain is located, the relative dielectric constant and volume weight of the grain, etc., and performs regression prediction through a grain moisture content detection model obtained by building a GA-BP neural network model to obtain the moisture content of the grain in the current preset time period. Compared with the existing detection methods that mostly only use linear fitting methods, a nonlinear method of multiple influencing factors is used to perform regression prediction of data. By considering multiple influencing factors, the fitting regression accuracy of the grain moisture content detection model is improved. Further, through the grain moisture content detection model, the moisture content of the grain is periodically detected, and long-term and stable detection of the moisture content of the grain is achieved with high reliability, thereby improving the accuracy of grain moisture content detection as a whole.

[0088] Furthermore, the acquisition module 610 is also used for: Control the temperature sensor to collect the temperature of the environment where the grain is located within a preset time period; Controlling the moisture content sensor to collect the relative dielectric constant of the grains within the preset time period; Controlling the gravity sensor to collect the volume weight of the grains within the preset time period; Wherein, the temperature sensor, the moisture content sensor and the gravity sensor are arranged inside a grain collecting box, and the grain collecting box is used to store grains.

[0089] Furthermore, the grain moisture content detection module 620 is also used for: Determine the region and variety information of the grain; The region information, the variety information, the temperature, the relative dielectric constant and the volume weight are input into the grain moisture content detection model to obtain the moisture content of the grain within the preset time period output by the grain moisture content detection model.

[0090] Furthermore, the periodic moisture content detection module 630 is also used for: Stop controlling the temperature sensor, the moisture content sensor and the gravity sensor to collect data; The grain is discharged from the grain collecting box into the grain unloading bin within the preset time period by means of a grain discharger; Stopping the discharge of grain from the grain collecting box into the grain unloading bin through the grain discharger; If the grain in the grain unloading bin reaches a preset position, the periodic detection of the moisture content of the grain is terminated; If the grain in the grain unloading bin has not reached the preset position, the steps of collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volumetric weight of the grain within a preset time period are repeated until the grain in the grain unloading bin reaches the preset position, and the moisture content of the grain within multiple preset time periods output by the grain moisture content detection model is obtained, and the periodic detection of the moisture content of the grain is ended.

[0091] Furthermore, the grain moisture content detection device is also used for: After the grains in the grain unloading bin reach a preset position, the control display terminal displays information that the grain unloading bin is full, and displays the moisture content of the grains in multiple preset time periods.

[0092] Furthermore, the grain moisture content detection device is also used for: Initialize the GA-BP neural network model; Obtain grain samples from different regions and varieties; Collecting a temperature sample of the environment in which the grain sample is located, a relative dielectric constant sample and a volume weight sample of the grain sample within the preset time period; Determining moisture content label data of the grain sample within the preset time period; Based on the grain sample, the region information sample of the grain sample, the variety information sample of the grain sample, the temperature sample, the relative dielectric constant sample, the volume weight sample and the moisture content label data, the GA-BP neural network model is trained to obtain the grain moisture content detection model.

[0093] It should be noted that the grain moisture content detection device provided by the present invention can execute the grain moisture content detection method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0094] The combine harvester provided by the present invention is described below. The combine harvester described below and the grain moisture content detection method described above can be referenced to each other.

[0095] Reference Figure 7 , Figure 7 It is a schematic diagram of the device of the combine harvester provided by the present invention.

[0096] The combine harvester is composed of a sampling mechanism 1, a data acquisition module 2, a display terminal 3, and a built-in upper terminal.

[0097] The sampling mechanism is composed of a grain collecting box, a grain discharging motor, a motor driving module, a grain discharging device, a grain unloading bin and a supporting crossbeam. The grain collecting box is used to store grains harvested by a combine harvester. The grain discharging motor driving module is used to drive the grain discharging motor to start. The grain discharging motor is used to drive the grain discharging device to discharge the grains in the grain collecting box from the grain collecting box into the grain unloading bin. The grain unloading bin is used to store the grains discharged from the grain collecting box. The supporting crossbeam is used to provide structural support and stability for multiple components. The sampling mechanism and the supporting crossbeam are tightly combined with 4 M8 screws. The data acquisition module is composed of a temperature sensor, a moisture content sensor, a gravity sensor, a grain level sensor 1 and a grain level sensor 2. The temperature sensor, the moisture content sensor and the gravity sensor are all used to collect data related to the moisture content of grains. The grain level sensor 1 is used to detect whether the grains in the grain collecting box have reached a certain high level. The grain level sensor 2 is used to detect whether the grains in the grain unloading bin have reached a certain high level. The two grain level sensors can be used to judge the current grain sampling situation and realize the automatic control start and stop of the system. The host computer terminal is used to control the sampling mechanism and the data acquisition module to jointly complete the detection of grain moisture content, and can realize data storage and data processing. In addition, the host computer terminal also includes a display terminal to realize data display.

[0098] It should be noted that the combine harvester provided by the present invention can execute the grain moisture content detection method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0099] Figure 8 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute a method for detecting the moisture content of grains, which method includes: collecting the temperature of the environment in which the grains are located within a preset time period, the relative dielectric constant and the volume weight of the grains; based on the temperature, the relative dielectric constant and the volume weight, training a grain moisture content detection model to obtain the moisture content of the grains within the preset time period; the grain moisture content detection model is obtained based on the GA-BP neural network model; and the moisture content of the grains is periodically detected through the grain moisture content detection model.

[0100] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0101] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the grain moisture content detection method provided in the above-mentioned embodiments, and the method includes: collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period; based on the temperature, the relative dielectric constant and the volume weight, training a grain moisture content detection model to obtain the moisture content of the grain within the preset time period; the grain moisture content detection model is built based on the GA-BP neural network model; and periodically detecting the moisture content of the grain through the grain moisture content detection model.

[0102] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the grain moisture content detection method provided in the above-mentioned embodiments, the method comprising: collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period; based on the temperature, the relative dielectric constant and the volume weight, training a grain moisture content detection model to obtain the moisture content of the grain within the preset time period; the grain moisture content detection model is built based on the GA-BP neural network model; and periodically detecting the moisture content of the grain through the grain moisture content detection model.

[0103] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting moisture content of grains, characterized in that: include: Collect the temperature of the environment in which the grain is located, the relative dielectric constant and volume weight of the grain within a preset time period; Based on the temperature, the relative dielectric constant and the volume weight, a grain moisture content detection model is trained to obtain the moisture content of the grain within the preset time period; the grain moisture content detection model is built based on a GA-BP neural network model; The moisture content of the grains is periodically detected by the grain moisture content detection model.

2. The method for detecting moisture content of grains according to claim 1, characterized in that: The collecting of the temperature of the environment in which the grain is located, the relative dielectric constant and the volume weight of the grain within a preset time period includes: Control the temperature sensor to collect the temperature of the environment where the grain is located within a preset time period; Controlling the moisture content sensor to collect the relative dielectric constant of the grains within the preset time period; Controlling the gravity sensor to collect the volume weight of the grains within the preset time period; Wherein, the temperature sensor, the moisture content sensor and the gravity sensor are arranged inside a grain collecting box, and the grain collecting box is used to store grains.

3. The method for detecting moisture content of grains according to claim 1, characterized in that: The method of training a grain moisture content detection model based on the temperature, the relative dielectric constant and the volume weight to obtain the grain moisture content within the preset time period includes: Determine the region and variety information of the grain; The region information, the variety information, the temperature, the relative dielectric constant and the volume weight are input into the grain moisture content detection model to obtain the moisture content of the grain within the preset time period output by the grain moisture content detection model.

4. The method for detecting moisture content of grains according to claim 2, characterized in that: The step of periodically detecting the moisture content of the grains by using the grain moisture content detection model comprises: Stop controlling the temperature sensor, the moisture content sensor and the gravity sensor to collect data; The grain is discharged from the grain collecting box into the grain unloading bin within the preset time period by means of a grain discharger; Stopping the discharge of grain from the grain collecting box into the grain unloading bin through the grain discharger; If the grain in the grain unloading bin reaches a preset position, the periodic detection of the moisture content of the grain is terminated; If the grain in the grain unloading bin has not reached the preset position, the steps of collecting the temperature of the environment in which the grain is located, the relative dielectric constant and the volumetric weight of the grain within a preset time period are repeated until the grain in the grain unloading bin reaches the preset position, and the moisture content of the grain within multiple preset time periods output by the grain moisture content detection model is obtained, and the periodic detection of the moisture content of the grain is ended.

5. The method for detecting moisture content of grains according to claim 4, characterized in that: After the moisture content of the grains is periodically detected by the grain moisture content detection model, the method further comprises: After the grains in the grain unloading bin reach a preset position, the control display terminal displays information that the grain unloading bin is full, and displays the moisture content of the grains in multiple preset time periods.

6. The method for detecting moisture content of grains according to any one of claims 1 to 5, characterized in that: The grain moisture content detection model is trained in the following way: Initialize the GA-BP neural network model; Obtain grain samples from different regions and varieties; Collecting a temperature sample of the environment in which the grain sample is located, a relative dielectric constant sample and a volume weight sample of the grain sample within the preset time period; Determining moisture content label data of the grain sample within the preset time period; Based on the grain sample, the region information sample of the grain sample, the variety information sample of the grain sample, the temperature sample, the relative dielectric constant sample, the volume weight sample and the moisture content label data, the GA-BP neural network model is trained to obtain the grain moisture content detection model.

7. A grain moisture content detection device, characterized in that: include: A collection module is used to collect the temperature of the environment in which the grains are located, the relative dielectric constant and the volume weight of the grains within a preset time period; A grain moisture content detection module, used to obtain the moisture content of the grain within the preset time period by training a grain moisture content detection model based on the temperature, the relative dielectric constant and the volume weight; the grain moisture content detection model is built based on a GA-BP neural network model; The periodic moisture content detection module is used to periodically detect the moisture content of grains through the grain moisture content detection model.

8. A combine harvester, comprising the grain moisture content detection device according to claim 7, and further comprising a grain collecting box, a grain discharger, a grain unloading bin, a temperature sensor, a moisture content sensor, a gravity sensor and a display terminal; The grain collection box is used to store grains; The grain discharger is used to discharge the grain stored in the grain collecting box into the grain unloading bin; The grain unloading bin is used to store grain discharged from the grain collecting box; The temperature sensor is used to collect the temperature of the environment in which the grains are located; The moisture content sensor is used to collect the relative dielectric constant of the grain; The gravity sensor is used to collect the volume weight of the grains; Wherein, the temperature sensor, the moisture content sensor and the gravity sensor are arranged inside the grain collecting box; The grain discharger is arranged between the grain collecting box and the grain unloading bin.

9. A device, comprising an electronic device, the 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 grain moisture content detection method according to any one of claims 1 to 6 are implemented.

10. A medium, comprising a non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the grain moisture content detection method according to any one of claims 1 to 6 are implemented.

Images