Wheat processing dynamic control method based on artificial intelligence optimization

Abstract

The invention discloses a wheat processing dynamic control method based on artificial intelligence optimization, relates to the technical field of wheat processing, and aims to solve the problem that in the prior art, a control strategy is difficult to automatically correct according to real-time changes of wheat raw material characteristics, so that the stability of the processing process is poor. The method comprises the following steps: S1, constructing a data acquisition system, installing various sensors at key positions of a wheat processing production line, and acquiring wheat raw material characteristic data, equipment operation data and environment data in real time; s2, an artificial intelligence model is built, the collected data is utilized, the artificial intelligence model of the wheat processing process is built based on a deep learning algorithm, raw material characteristic data, equipment operation data and environment data are input into the artificial intelligence model, and optimal control parameters of all processing links are output. The method has the advantages that all processing links of the wheat are always in the optimal state, and the stable proceeding of the processing process is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of wheat processing technology, and more specifically, to a dynamic control method for wheat processing based on artificial intelligence optimization. Background Technology

[0002] Wheat is an important global food crop, and its processed products (such as flour) are the basic raw materials for the food industry. The quality of processing directly affects the taste, nutritional components and applicability of food for subsequent processing.

[0003] In the wheat processing industry, traditional control methods have long relied on fixed parameters and manual experience. For example, key parameters such as the roller pressure of the mill and the vibration frequency of the screening equipment in a wheat processing production line are usually preset based on the average characteristics of the raw materials. This makes it difficult to automatically adjust the control strategy according to real-time changes in the characteristics of the raw materials, resulting in poor stability of the processing process and difficulty in meeting the requirements of modern production for product quality uniformity. In view of this, we propose a dynamic control method for wheat processing based on artificial intelligence optimization. Summary of the Invention

[0004] The purpose of this invention is to provide a dynamic control method for wheat processing based on artificial intelligence optimization, which aims to solve the problem that existing technologies are unable to automatically correct control strategies according to real-time changes in the characteristics of wheat raw materials, resulting in poor stability of the processing process.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a dynamic control method for wheat processing based on artificial intelligence optimization, comprising the following steps:

[0006] S1. Construct a data acquisition system and install multiple sensors at key locations in the wheat processing production line to collect real-time data on wheat raw material characteristics, equipment operation data, and environmental data.

[0007] S2. Establish an artificial intelligence model and use the collected data to build an artificial intelligence model of the wheat processing process based on deep learning algorithms. The input of the artificial intelligence model is raw material characteristic data, equipment operation data and environmental data, and the output is the optimal control parameters for each processing stage.

[0008] S3. Dynamic control: Based on the established artificial intelligence model, the system acquires data collected by the data acquisition system in real time, calculates the optimal control parameters of each processing device under the current state, and sends control commands to each processing device. At the same time, it continuously monitors various data during the processing and feeds them back to the artificial intelligence model. The artificial intelligence model continuously optimizes the control parameters based on the new data.

[0009] S4. Quality monitoring: Install quality testing equipment at the finished product output end of the processing production line to monitor the quality indicators of the finished product in real time.

[0010] Preferably, in step S1 above, the sensor includes an online moisture detection sensor, a temperature sensor, a humidity sensor, a flow sensor, a pressure sensor, a vibration sensor, and a current sensor.

[0011] Preferably, in step S2 above, the deep learning algorithm employs a linear regression algorithm. It establishes a linear regression model by using raw material characteristic data, equipment operation data, and environmental data collected during wheat processing as independent variables, and control parameters of each processing stage as dependent variables. The formula is as follows: ,in, These are the predicted control parameters for the processing steps. These represent different independent variables, corresponding to various types of collected data. It is the intercept term. These are regression coefficients, calculated by fitting a large amount of historical data using the least squares method to ensure accurate predictions. The sum of squared errors between the actual value and the actual value is minimized. The error term represents random factors that the model cannot explain. By continuously updating the data and recalculating the regression coefficients, the model is optimized to achieve dynamic prediction of the control parameters of the processing stage.

[0012] Preferably, in step S4 above, the quality testing equipment includes a flour moisture content analyzer, a flour particle size analyzer, and a flour quality comprehensive analyzer.

[0013] Preferably, in step S1 above, the collected data is preprocessed, including removing abnormal data, standardizing data of different dimensions, and interpolating and completing data that is missing for a short period of time, to ensure that the data input into the artificial intelligence model is accurate and reliable.

[0014] Preferably, the historical data includes historical raw material characteristic data, equipment operation data, and historical environmental data of wheat processed by the wheat processing production line, collected by multiple sensors.

[0015] Preferably, in step S3 above, the control command transmission adopts a dual-channel redundancy mechanism of industrial Ethernet plus wireless backup link. When the main link communication is delayed, it automatically switches to the backup link to ensure the real-time performance of the control commands.

[0016] Preferably, step S4 above also includes feeding back the detected quality data to the artificial intelligence model, and the artificial intelligence model further adjusts the control parameters of the processing process based on the difference between the quality data and the target quality, forming a closed-loop control.

[0017] Compared with the prior art, the beneficial effects of the present invention are:

[0018] 1. This invention collects wheat raw material characteristics, equipment operation and environmental data in real time, and uses an artificial intelligence model to dynamically adjust control parameters. It can automatically correct the control strategy according to the real-time changes in raw material characteristics, which solves the problem of poor processing stability caused by the difficulty in adjusting the strategy in real time in the prior art. This ensures that each processing link is always in the optimal state and guarantees the stable progress of the processing.

[0019] 2. This invention uses deep learning algorithms to build a model based on a large amount of historical data. It calculates regression coefficients by fitting the data using the least squares method, continuously updates the data to optimize the model, and achieves dynamic prediction of control parameters in the processing stage. It can also more accurately capture the complex relationships between data, making the predicted control parameters more in line with actual processing needs and improving the accuracy of control.

[0020] 3. In this invention, the collected data is preprocessed, including removing abnormal data, standardizing data of different dimensions, and interpolating and completing short-term missing data. This ensures that the data input into the artificial intelligence model is accurate and reliable, providing a solid foundation for the model's accurate prediction and control, avoiding control deviations caused by data problems, and improving overall reliability.

[0021] 4. In this invention, a quality inspection device is installed at the finished product output end to detect quality indicators in real time and feed them back to the artificial intelligence model. The model further adjusts the control parameters based on the difference between the quality data and the target quality to form a closed-loop control. At the same time, the control command transmission adopts a dual-channel redundancy mechanism of industrial Ethernet plus wireless backup link to ensure the real-time performance of control commands. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating the method of the present invention. Detailed Implementation

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0024] Example 1

[0025] A dynamic control method for wheat processing based on artificial intelligence optimization, comprising the following steps:

[0026] S1. Construct a data acquisition system and install multiple sensors at key locations in the wheat processing production line to collect real-time data on wheat raw material characteristics, equipment operation, and environmental data. By collecting multi-dimensional data in real time using multiple sensors, comprehensive and accurate input information is provided for subsequent artificial intelligence models, ensuring that the models can accurately reflect the actual state of the processing process.

[0027] S2. Establish an artificial intelligence model and use the collected data to build an artificial intelligence model for wheat processing based on deep learning algorithms. The input of this artificial intelligence model is raw material characteristic data, equipment operation data and environmental data, and the output is the optimal control parameters for each processing stage. The model can dynamically generate the optimal control parameters based on real-time input data by mining the potential relationships between data through deep learning algorithms, so as to realize intelligent decision-making in the processing process.

[0028] S3. Dynamic control: Based on the established artificial intelligence model, the system acquires data collected by the data acquisition system in real time, calculates the optimal control parameters of each processing device under the current state, and sends control commands to each processing device. At the same time, it continuously monitors various data during the processing process and feeds them back to the artificial intelligence model. The artificial intelligence model continuously optimizes the control parameters based on the new data, so as to dynamically adjust the control parameters in real time, so that the processing equipment is always in the best operating state, adapts to the characteristics of raw materials and environmental changes, and improves processing efficiency and stability.

[0029] S4. Quality monitoring: Install quality testing equipment at the finished product output end of the processing production line to monitor the quality indicators of the finished product in real time. This allows for real-time monitoring of finished product quality, timely detection of quality problems during processing, and provides a basis for model optimization and production adjustments, thus ensuring product quality.

[0030] Furthermore, in step S1 above, the sensors include an online moisture detection sensor, a temperature sensor, a humidity sensor, a flow sensor, a pressure sensor, a vibration sensor, and a current sensor. By using multiple sensors to cover key parameters such as raw material moisture, equipment operating status, and environmental conditions, the comprehensiveness and accuracy of data acquisition are ensured, providing multi-dimensional data support for process control.

[0031] Furthermore, in step S2 above, the deep learning algorithm employs a linear regression algorithm. It uses raw material characteristic data, equipment operation data, and environmental data collected during wheat processing as independent variables, and control parameters of each processing stage as dependent variables to establish a linear regression model. The formula is as follows: ,in, These are the predicted control parameters for the processing steps. These represent different independent variables, corresponding to various types of collected data. It is the intercept term. These are regression coefficients, calculated by fitting a large amount of historical data using the least squares method to ensure accurate predictions. The sum of squared errors between the actual value and the actual value is minimized. The error term represents random factors that the model cannot explain. By continuously updating the data and recalculating the regression coefficients, the model is optimized to achieve dynamic prediction of control parameters in the processing stage. The linear regression algorithm establishes a quantitative relationship between input and output based on historical data, and the least squares method is used to optimize the parameters, enabling the model to dynamically predict the optimal control parameters based on real-time data, thus adapting to the complexity and dynamism of the wheat processing process.

[0032] Furthermore, in step S4 above, the quality testing equipment includes a flour moisture content analyzer, a flour particle size analyzer, and a flour quality comprehensive analyzer, to perform real-time testing of flour moisture, particle size, and overall quality, comprehensively evaluate the quality of the finished product, and provide direct quality feedback information for optimizing the processing process.

[0033] Furthermore, in step S1 above, the collected data is preprocessed, including removing outlier data, standardizing data of different dimensions, and interpolating and completing data that is missing for a short period of time. This ensures that the data input to the artificial intelligence model is accurate and reliable. Data preprocessing improves the quality and reliability of the input model data, avoids the impact of outliers and missing data on the model's prediction accuracy, and ensures that the control parameters output by the model are accurate and effective.

[0034] Furthermore, historical data includes data on the characteristics of raw materials, equipment operation, and historical environment of wheat processed on wheat processing production lines, collected through various sensors. The model is trained with a large amount of real historical data, enabling it to learn and capture the patterns and characteristics of the wheat processing process, thereby improving the accuracy and generalization ability of the model's predictions.

[0035] Furthermore, in step S3 above, the control command transmission adopts a dual-channel redundancy mechanism of industrial Ethernet plus wireless backup link. When the main link communication is delayed, it automatically switches to the backup link to ensure the real-time performance of the control commands. The dual-channel redundancy mechanism ensures the real-time performance and reliability of the control command transmission, avoids control delays or interruptions due to communication link failures, and ensures the stable operation of the processing equipment.

[0036] Furthermore, in step S4 above, the detected quality data is fed back to the artificial intelligence model. The artificial intelligence model adjusts the control parameters of the processing process based on the difference between the quality data and the target quality, forming a closed-loop control. The closed-loop control mechanism enables the processing process to dynamically optimize the control parameters based on real-time quality feedback, thereby continuously improving product quality and processing efficiency.

[0037] The embodiments disclosed in this invention are preferred embodiments, but are not limited thereto. Those skilled in the art can easily understand the spirit of this invention based on the above embodiments and make different extensions and variations, but as long as they do not depart from the spirit of this invention, they are all within the protection scope of this invention.

Claims

1. A dynamic control method for wheat processing based on artificial intelligence optimization, characterized in that, The method includes the following steps: S1. Construct a data acquisition system and install multiple sensors at key locations in the wheat processing production line to collect real-time data on wheat raw material characteristics, equipment operation data, and environmental data. S2. Establish an artificial intelligence model and use the collected data to build an artificial intelligence model of the wheat processing process based on deep learning algorithms. The input of the artificial intelligence model is raw material characteristic data, equipment operation data and environmental data, and the output is the optimal control parameters for each processing stage. S3. Dynamic control: Based on the established artificial intelligence model, the system acquires data collected by the data acquisition system in real time, calculates the optimal control parameters of each processing device under the current state, and sends control commands to each processing device. At the same time, it continuously monitors various data during the processing and feeds them back to the artificial intelligence model. The artificial intelligence model continuously optimizes the control parameters based on the new data. S4. Quality monitoring: Install quality testing equipment at the finished product output end of the processing production line to monitor the quality indicators of the finished product in real time.

2. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 1, characterized in that, In step S1 above, the sensors include an online moisture detection sensor, a temperature sensor, a humidity sensor, a flow sensor, a pressure sensor, a vibration sensor, and a current sensor.

3. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 1, characterized in that, In step S2 above, the deep learning algorithm employs a linear regression algorithm. It establishes a linear regression model by using raw material characteristic data, equipment operation data, and environmental data collected during wheat processing as independent variables, and control parameters of each processing stage as dependent variables. The formula is as follows: ,in, These are the predicted control parameters for the processing steps. These represent different independent variables, corresponding to various types of collected data. It is the intercept term. These are regression coefficients, calculated by fitting a large amount of historical data using the least squares method to ensure accurate predictions. The sum of squared errors between the actual value and the actual value is minimized. The error term represents random factors that the model cannot explain. By continuously updating the data and recalculating the regression coefficients, the model is optimized to achieve dynamic prediction of the control parameters of the processing stage.

4. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 1, characterized in that, In step S4 above, the quality testing equipment includes a flour moisture content analyzer, a flour particle size analyzer, and a flour quality comprehensive analyzer.

5. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 1, characterized in that, In step S1 above, the collected data is preprocessed, including removing abnormal data, standardizing data of different dimensions, and interpolating and completing data that is missing for a short period of time, to ensure that the data input into the artificial intelligence model is accurate and reliable.

6. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 3, characterized in that, The historical data refers to historical raw material characteristics data, equipment operation data, and historical environmental data of wheat processed on the wheat processing production line, collected through multiple sensors.

7. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 1, characterized in that, In step S3 above, the control command transmission adopts a dual-channel redundancy mechanism of industrial Ethernet plus wireless backup link. When the main link communication is delayed, it automatically switches to the backup link to ensure the real-time performance of the control commands.

8. The method for dynamic control of wheat processing based on artificial intelligence optimization according to claim 1, characterized in that, In step S4 above, the detected quality data is fed back to the artificial intelligence model. The artificial intelligence model further adjusts the control parameters of the processing process based on the difference between the quality data and the target quality, forming a closed-loop control.

Images