Intelligent control system for forming cereal pieces suitable for the production of a baking plant

Abstract

The present application belongs to the technical field of grain block forming control, and specifically relates to a grain block forming intelligent control system suitable for a production baking workshop, comprising a raw material characteristic sensing and analyzing module, an equipment monitoring and analyzing module, an environmental disturbance judging and analyzing module, a forming intelligent control module and a workshop supervision end; the present application judges whether the raw material state meets the forming process requirements through the raw material characteristic sensing and analyzing module, does not perform grain block forming when a grain characteristic abnormal signal is generated, and performs corresponding treatment on the grain raw material, and analyzes the running process of the forming equipment and the environmental conditions of the production baking workshop, performs corresponding control operations when a process abnormal signal or an environmental disturbance abnormal signal is generated, can comprehensively monitor and reasonably analyze the forming influencing factors and realize abnormal adjustment control, and ensures the continuous stability of grain block forming and the quality of the produced grain blocks.

Description

Technical Field

[0001] This invention relates to the field of grain block forming control technology, specifically to an intelligent control system for grain block forming in production and baking workshops. Background Technology

[0002] Grain blocks are block-shaped food products made primarily from grains. The core ingredients typically include oats, wheat, rice, corn, and barley. These grains are rich in carbohydrates, dietary fiber, B vitamins, and other nutrients, providing the main energy source and basic texture for grain blocks. In the baking industry, grain blocks are a popular product that combines nutrition and convenience, and their market demand continues to grow, driving the continuous expansion of production scale.

[0003] Monitoring and regulation are required during the grain block forming process. Currently, it is difficult to reasonably analyze the characteristics of grain raw materials and the factors affecting forming and to achieve abnormal adjustment and control. Furthermore, it is impossible to accurately assess the degree of potential problems in forming stability and the performance of forming quality and to provide timely warnings. As a result, managers cannot take reasonable improvement measures in a timely manner, which is not conducive to ensuring the continuous stability of the grain block forming process and the quality of the grain blocks produced.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent control system for grain block forming suitable for production and baking workshops. It solves the problems of existing technologies, which make it difficult to reasonably analyze the characteristics of grain raw materials and the factors affecting forming and to achieve abnormal adjustment and control. Furthermore, it is difficult to accurately assess the degree of potential problems in forming stability and the performance of forming quality and provide timely warnings, which is not conducive to ensuring the quality and production efficiency of the produced grain blocks.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The intelligent control system for grain block forming in production and baking workshops includes a raw material characteristic sensing and analysis module, an equipment monitoring and analysis module, an environmental disturbance judgment and analysis module, a forming intelligent control module, and a workshop monitoring terminal. The raw material characteristic sensing and analysis module collects key characteristic parameters of grain raw materials, judges whether the raw material status meets the forming process requirements, and generates a grain characteristic qualified signal or a grain characteristic abnormal signal, and sends the grain characteristic abnormal signal to the workshop monitoring terminal.

[0008] During the grain block forming process, the equipment monitoring and analysis module monitors and analyzes the operation of the forming equipment, generates process qualified signals or process abnormal signals through analysis, and sends the process abnormal signals to the forming intelligent control module and the workshop monitoring terminal.

[0009] The environmental disturbance judgment module analyzes the environmental conditions of the production baking workshop, generates normal or abnormal environmental disturbance signals, and sends the abnormal environmental disturbance signals to the molding intelligent control module and the workshop monitoring terminal. When the molding intelligent control module receives the abnormal process signal or the abnormal environmental disturbance signal, it generates corresponding control commands and performs corresponding control operations based on the control commands.

[0010] Furthermore, the specific analysis process of the raw material characteristic perception and analysis module is as follows:

[0011] The variance value of grain raw material particle size is obtained and marked as grain particle size detection value. The grain particle size detection value is compared with the preset grain particle size detection threshold. If the grain particle size detection value exceeds the preset grain particle size detection threshold, an abnormal grain characteristic signal is generated.

[0012] If the grain particle size detection value does not exceed the preset grain particle size detection threshold, the deviation of the average temperature of the grain raw material from the standard raw material temperature is marked as the grain temperature measurement value, the deviation of the average moisture content of the grain raw material from the standard raw material moisture content is marked as the grain moisture measurement value, and the deviation of the average grain size of the grain raw material from the preset raw material particle size is marked as the grain particle measurement value.

[0013] The grain characteristic adaptation value is calculated by weighted summation of grain temperature, grain moisture and grain grain size. The grain characteristic adaptation value is then compared with a preset grain characteristic adaptation threshold. If the grain characteristic adaptation value exceeds the preset grain characteristic adaptation threshold, an abnormal grain characteristic signal is generated; if the grain characteristic adaptation value does not exceed the preset grain characteristic adaptation threshold, a qualified grain characteristic signal is generated.

[0014] Furthermore, the specific analysis process of the equipment monitoring and analysis module is as follows:

[0015] Once the molding pressure and mold temperature are obtained, the molding pressure and mold temperature are compared with the preset molding pressure range and preset mold temperature range respectively. If the molding pressure or mold temperature is not within the corresponding preset range, a process abnormality signal is generated.

[0016] If both the molding pressure and the mold temperature are within the corresponding preset range, the difference between the molding pressure and the median of the preset molding pressure range is calculated and the absolute value is taken to obtain the molding pressure value. Similarly, the mold temperature value is obtained, and the molding vibration frequency is marked as the molding vibration value.

[0017] The process monitoring value is calculated by weighted summation of the molding pressure value, molding temperature value, and molding vibration value. The process monitoring value is then compared with a preset process monitoring threshold. If the process monitoring value exceeds the preset process monitoring threshold, a process abnormality signal is generated; if the process monitoring value does not exceed the preset process monitoring threshold, a process qualified signal is generated.

[0018] Furthermore, the specific analysis process of the environmental disturbance judgment and analysis module is as follows:

[0019] The temperature deviation and humidity deviation values ​​of the production and baking workshop are obtained and the sum of the two is marked as the temperature and humidity disturbance value. The wind speed in the production and baking workshop is calculated by comparing the wind speed with the standard wind speed data and taking the absolute value to obtain the wind speed disturbance value. The dust concentration data of the production and baking workshop is marked as the dust disturbance value.

[0020] The environmental disturbance coefficient is calculated by weighted summation of temperature and humidity disturbance values, wind speed disturbance values, and dust disturbance values. The environmental disturbance coefficient is then compared with a preset environmental disturbance coefficient threshold. If the environmental disturbance coefficient exceeds the preset environmental disturbance coefficient threshold, an abnormal environmental disturbance signal is generated; if the environmental disturbance coefficient does not exceed the preset environmental disturbance coefficient threshold, a normal environmental disturbance signal is generated.

[0021] Furthermore, the molding intelligent control module is connected to the molding stability analysis module. The molding intelligent control module sends the molding control information during the detection period to the molding stability analysis module. The molding stability analysis module analyzes the potential molding stability problems during the detection period and generates a stability qualified signal or a stability abnormal signal through analysis. The stability abnormal signal is sent to the workshop monitoring terminal. When the workshop monitoring terminal receives the stability abnormal signal, it issues a corresponding warning.

[0022] Furthermore, the specific analysis process of the molding stability analysis module is as follows:

[0023] The system acquires the generation time of the corresponding process abnormal signal or environmental disturbance abnormal signal, marks the generation time as the first time, and marks the time when the corresponding control operation is completed as the second time. The system calculates the time difference between the second time and the first time to obtain the stable duration. The system compares the stable duration with the corresponding preset stable duration threshold. If the stable duration exceeds the preset stable duration threshold, the system marks the corresponding stable duration as an inefficient duration.

[0024] Furthermore, the detection period is divided into several sub-periods. If a process abnormality signal or an environmental disturbance abnormality signal is generated in the corresponding sub-period, the corresponding sub-period is marked as a poor period. The number of poor periods in the detection period is obtained and marked as poor period detection value, and the number of inefficient durations in the detection period is marked as inefficient statistical value. The ratio of stable duration to the corresponding preset stable duration threshold is calculated to obtain the stable duration measurement value. The average of all stable duration measurement values ​​in the detection period is calculated to obtain the stable duration decision value.

[0025] The stability risk coefficient is calculated by weighting and summing the poor-time detection value, the inefficient statistical value, and the stable-time decision value. The stability risk coefficient is then compared with a preset stability risk coefficient threshold. If the stability risk coefficient exceeds the preset stability risk coefficient threshold, an abnormal stability signal is generated; if the stability risk coefficient does not exceed the preset stability risk coefficient threshold, a qualified stability signal is generated.

[0026] Furthermore, the molding stability analysis module is connected to the molding quality assessment module. The molding stability analysis module sends a stability pass signal to the molding quality assessment module. When the molding quality assessment module receives the stability pass signal, it evaluates and analyzes the molding quality of the grain blocks during the detection period. Through analysis, it generates a quality assessment pass signal or a quality assessment abnormal signal, and sends the quality assessment abnormal signal to the workshop monitoring terminal. When the workshop monitoring terminal receives the quality assessment abnormal signal, it issues a corresponding warning.

[0027] Furthermore, the molding quality assessment module is connected to the 3D morphology defect intelligent detection module. This module utilizes multi-view vision and deep learning technology to detect 3D defects in the molded block in real time, including cracks, burrs, and missing corners, and sends the defect detection information to the molding quality assessment module and the workshop monitoring terminal. The specific operation process is as follows:

[0028] Multi-view image acquisition: Images of the molded block surface are captured from different angles using three high-speed industrial cameras;

[0029] 3D Reconstruction and Feature Extraction: A 3D point cloud model of the shaped block is generated using the structure-of-motion algorithm, and key indicators including surface curvature and texture features are extracted.

[0030] Defect classification and localization: Input feature data into the improved YOLOv7 deep learning model and output the defect type and location.

[0031] Furthermore, the specific analysis process of the molding quality assessment module includes:

[0032] All defect types of grain blocks produced during the detection period are obtained. The percentage of grain blocks involved in the corresponding defect type is marked as the defect matching value. The defect matching value is compared with the corresponding preset defect matching threshold. If the defect matching value exceeds the corresponding preset defect matching threshold, the corresponding type of defect is marked as an uncontrollable defect. If an uncontrollable defect exists during the detection period, a quality assessment abnormality signal is generated.

[0033] Furthermore, if there are no uncontrollable defects during the detection period, the number of defective grain blocks produced during the detection period is obtained and its ratio to the total number of grain blocks produced during the detection period is calculated to obtain the grain block defect value. The grain block defect value is then compared with a preset grain block defect threshold. If the grain block defect value exceeds the preset grain block defect threshold, a quality assessment anomaly signal is generated; if the grain block defect value does not exceed the preset grain block defect threshold, a quality assessment pass signal is generated.

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] 1. In this invention, the raw material characteristic sensing and analysis module determines whether the raw material state meets the molding process requirements. When an abnormal signal of grain characteristics is generated, the grain block molding is temporarily suspended and the grain raw material is processed accordingly. Furthermore, by analyzing the operation process of the molding equipment and the environmental conditions of the production and baking workshop, the molding influencing factors can be comprehensively monitored and rationally analyzed, and abnormal adjustment and control can be achieved to ensure the continuous stability of grain block molding and the quality of the produced grain blocks.

[0036] 2. In this invention, the molding stability analysis module analyzes potential molding stability issues during the detection period. When an abnormal stability signal is generated, the molding monitoring and management of grain blocks is strengthened to ensure the continuous stability of the grain block molding process. When a qualified stability signal is generated, the molding quality of grain blocks during the detection period is evaluated and analyzed. When an abnormal quality evaluation signal is generated, the cause is investigated and analyzed, and reasonable improvement measures are taken to further ensure the quality of the produced grain blocks. Attached Figure Description

[0037] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0038] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0039] Figure 2 This is a system block diagram of Embodiments 2 and 3 of the present invention. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Example 1: As Figure 1 As shown, the intelligent control system for grain block forming proposed in this invention, applicable to production and baking workshops, includes a raw material characteristic sensing and analysis module, an equipment monitoring and analysis module, an environmental disturbance judgment and analysis module, a forming intelligent control module, and a workshop monitoring terminal.

[0042] The raw material characteristic sensing and analysis module collects key characteristic parameters of the grain raw materials, determines whether the raw material state meets the molding process requirements, and generates a grain characteristic qualified signal or a grain characteristic abnormal signal. The abnormal grain characteristic signal is then sent to the workshop monitoring terminal. Upon receiving the abnormal signal, the workshop monitoring terminal issues a corresponding warning to remind management personnel to temporarily suspend grain block molding and to process the grain raw materials accordingly to ensure they meet the pre-molding characteristic requirements, thereby ensuring molding stability and the quality of the produced grain blocks. The specific analysis process of the raw material characteristic sensing and analysis module is as follows:

[0043] The variance value of the grain raw material particle size is obtained and marked as the grain particle size detection value. The grain particle size detection value is compared with the preset grain particle size detection threshold. If the grain particle size detection value exceeds the preset grain particle size detection threshold, it indicates that the grain raw material particle size is not uniform, which can easily lead to inconsistent forming density and affect the structural strength and quality of the grain block. In this case, an abnormal grain characteristic signal is generated.

[0044] If the grain particle size detection value does not exceed the preset grain particle size detection threshold, the deviation of the average temperature of the grain raw material from the standard raw material temperature is marked as the grain temperature measurement value, the deviation of the average moisture content of the grain raw material from the standard raw material moisture content is marked as the grain moisture measurement value, and the deviation of the average grain size of the grain raw material from the preset raw material particle size is marked as the grain particle measurement value.

[0045] The grain characteristic fit value is obtained by weighted summation of grain temperature, grain moisture, and grain grain measurements. Specifically, each of these values ​​is assigned a pre-defined weighting coefficient, and then multiplied by that coefficient. The sum of these three products is then labeled as the grain characteristic fit value. It should be noted that a higher grain characteristic fit value indicates a poorer overall condition of the grain raw material.

[0046] The grain characteristic adaptation value is compared with the preset grain characteristic adaptation threshold. If the grain characteristic adaptation value exceeds the preset grain characteristic adaptation threshold, it indicates that the overall condition of the grain raw material is poor, and an abnormal grain characteristic signal is generated. If the grain characteristic adaptation value does not exceed the preset grain characteristic adaptation threshold, it indicates that the overall condition of the grain raw material is good, and a qualified grain characteristic signal is generated.

[0047] During the grain block forming process, the equipment monitoring and analysis module monitors and analyzes the operation of the forming equipment. It generates either a process compliance signal or a process anomaly signal, and sends the anomaly signal to the forming intelligent control module and the workshop monitoring terminal. Upon receiving the anomaly signal, the forming intelligent control module generates corresponding control commands and performs appropriate control operations. The workshop monitoring terminal issues corresponding warnings upon receiving the anomaly signal. This process helps the equipment to stably and accurately execute the grain block forming operation, ensuring the quality of the grain blocks. The specific analysis process of the equipment monitoring and analysis module is as follows:

[0048] The molding pressure and mold temperature are obtained, and the molding pressure and mold temperature are compared with the preset molding pressure range and preset mold temperature range respectively. If the molding pressure or mold temperature is not within the corresponding preset range, it indicates that the equipment performance is poor during the grain block molding process, which is not conducive to ensuring the quality of the produced grain blocks, and a process abnormality signal is generated.

[0049] If both the molding pressure and the mold temperature are within the corresponding preset range, the difference between the molding pressure and the median of the preset molding pressure range is calculated and the absolute value is taken to obtain the molding pressure value. Similarly, the mold temperature value is obtained, and the molding vibration frequency is marked as the molding vibration value.

[0050] The process monitoring value is obtained by weighted summation of the molding pressure value, molding temperature value, and molding vibration value. Specifically, each molding pressure value, molding temperature value, and molding vibration value is assigned a corresponding preset weight coefficient, and then each of these values ​​is multiplied by its respective preset weight coefficient. The sum of these three products is then marked as the process monitoring value. It should be noted that the larger the process monitoring value, the worse the overall performance of the equipment during the grain block molding process.

[0051] The process monitoring value is compared with the preset process monitoring threshold. If the process monitoring value exceeds the preset process monitoring threshold, it indicates that the overall performance of the equipment during the grain block forming process is poor, which is not conducive to ensuring the quality of the produced grain blocks, and a process abnormality signal is generated. If the process monitoring value does not exceed the preset process monitoring threshold, it indicates that the overall performance of the equipment during the grain block forming process is good, which is conducive to ensuring the quality of the produced grain blocks, and a process qualified signal is generated.

[0052] The environmental disturbance judgment module analyzes the environmental conditions of the production baking workshop, generating normal or abnormal environmental disturbance signals. Abnormal environmental disturbance signals are sent to the forming intelligent control module and the workshop monitoring terminal. Upon receiving an abnormal environmental disturbance signal, the forming intelligent control module generates corresponding control commands and performs appropriate control operations. Upon receiving an abnormal environmental disturbance signal, the workshop monitoring terminal issues a corresponding warning. This helps reduce the adverse effects of environmental factors on the forming process, thereby further ensuring forming stability and grain block quality. The specific analysis process of the environmental disturbance judgment analysis module is as follows:

[0053] The temperature deviation (i.e., the deviation of the real-time temperature of the workshop from the suitable temperature of the workshop) and humidity deviation (i.e., the deviation of the real-time humidity of the workshop from the suitable humidity of the workshop) of the production and baking workshop are obtained, and the sum of the two values ​​is marked as the temperature and humidity disturbance value. The wind speed of the production and baking workshop is calculated by comparing the wind speed data with the standard wind speed data and the absolute value is taken to obtain the wind speed disturbance value. The dust concentration data of the production and baking workshop is marked as the dust disturbance value.

[0054] The environmental disturbance coefficient is calculated by weighted summation of temperature and humidity disturbance values, wind speed disturbance values, and dust disturbance values. Specifically, each of these values ​​is assigned a corresponding preset weight coefficient, and then multiplied by its respective preset weight coefficient. The sum of these three products is then labeled as the environmental disturbance coefficient. It should be noted that a larger environmental disturbance coefficient indicates a worse overall processing environment for the grain blocks.

[0055] The environmental disturbance coefficient is compared with the preset environmental disturbance coefficient threshold. If the environmental disturbance coefficient exceeds the preset environmental disturbance coefficient threshold, it indicates that the overall processing environment of the grain block is poor, and an abnormal environmental disturbance signal is generated. If the environmental disturbance coefficient does not exceed the preset environmental disturbance coefficient threshold, it indicates that the overall processing environment of the grain block is good, which is not conducive to the stable progress of the grain block forming process and to ensuring its quality, and a normal environmental disturbance signal is generated.

[0056] Example 2: Figure 2 As shown, the difference between this embodiment and Embodiment 1 is that the molding intelligent control module is communicatively connected to the molding stability analysis module. The molding intelligent control module sends the molding control information during the detection period to the molding stability analysis module. The molding stability analysis module analyzes the potential molding stability problems during the detection period and generates a stability qualified signal or a stability abnormal signal through analysis.

[0057] Furthermore, it sends stability anomaly signals to the workshop monitoring terminal. Upon receiving the stability anomaly signal, the workshop monitoring terminal issues a corresponding warning to remind managers to strengthen the monitoring and management of grain block formation and to take appropriate improvement measures as needed to ensure the continuous stability of the grain block formation process, demonstrating a high level of intelligence. The specific analysis process of the forming stability analysis module is as follows:

[0058] The system acquires the generation time of the corresponding process abnormal signal or environmental disturbance abnormal signal, marks the generation time as the first moment, and marks the completion time of the corresponding control operation as the second moment. The time difference between the second moment and the first moment is calculated to obtain the stable duration. The larger the stable duration value, the slower the response efficiency to the corresponding abnormal signal. The stable duration is compared with the corresponding preset stable duration threshold. If the stable duration exceeds the preset stable duration threshold, the corresponding stable duration is marked as an inefficient duration.

[0059] The detection period is divided into several sub-periods, all of which have the same duration. If a process abnormality signal or environmental disturbance abnormality signal is generated in the corresponding sub-period, the corresponding sub-period is marked as a poor period. The number of poor periods in the detection period is obtained and marked as poor period detection value, and the number of inefficient periods in the detection period is marked as inefficient statistical value. The stable period is calculated by the ratio of the stable period to the corresponding preset stable period threshold to obtain the stable period measurement value. The stable period measurement value is calculated by averaging all stable period measurement values ​​in the detection period.

[0060] The stability hazard coefficient is calculated by weighting and summing the poor-time detection value, inefficient statistical value, and stable-time decision value. Specifically, each of the poor-time detection value, inefficient statistical value, and stable-time decision value is assigned a corresponding preset weight coefficient, and each of these values ​​is multiplied by its respective preset weight coefficient. The sum of these three products is then labeled as the stability hazard coefficient. It should be noted that the larger the stability hazard coefficient, the higher the overall degree of stability hazard in the formation of grain blocks during the detection period.

[0061] The stability hazard coefficient is compared with the preset stability hazard coefficient threshold. If the stability hazard coefficient exceeds the preset stability hazard coefficient threshold, it indicates that the overall stability hazard of the grain block during the detection period is relatively high, and a stability abnormal signal is generated. If the stability hazard coefficient does not exceed the preset stability hazard coefficient threshold, it indicates that the overall stability hazard of the grain block during the detection period is relatively low, and a stability qualified signal is generated.

[0062] Example 3: Figure 2As shown, the difference between this embodiment and Embodiments 1 and 2 is that the molding stability analysis module is communicatively connected to the molding quality assessment module, and the molding quality assessment module is communicatively connected to the three-dimensional morphology defect intelligent detection module. The three-dimensional morphology defect intelligent detection module uses multi-view vision and deep learning technology to detect three-dimensional defects, including cracks, burrs, and missing corners, in the molded block in real time, and sends the defect detection information to the molding quality assessment module and the workshop monitoring terminal, so as to facilitate the understanding of the defect status of the produced grain blocks and help ensure the quality of the output grain blocks; the specific operation process is as follows:

[0063] Multi-view image acquisition: Images of the shaped block surface are captured from different angles (0°, 120°, 240°) using three high-speed industrial cameras (8-megapixel resolution, 150fps).

[0064] 3D Reconstruction and Feature Extraction: The Structure for Motion (SfM) algorithm is used to generate a 3D point cloud model of the shaped block and extract key indicators such as surface curvature and texture features.

[0065] Defect classification and localization: Input feature data into the improved YOLOv7 deep learning model and output the defect type (crack / burr / missing corner) and location.

[0066] Furthermore, the molding stability analysis module sends a stability pass signal to the molding quality assessment module. Upon receiving the stability pass signal, the molding quality assessment module evaluates and analyzes the molding quality of the grain blocks during the detection period, generating either a quality assessment pass signal or a quality assessment anomaly signal. The quality assessment anomaly signal is then sent to the workshop monitoring terminal. Upon receiving the quality assessment anomaly signal, the workshop monitoring terminal issues a corresponding warning to remind management personnel to promptly investigate and analyze the cause and take reasonable improvement measures to ensure the quality of the produced grain blocks. The specific analysis process of the molding quality assessment module is as follows:

[0067] All defect types present in the grain blocks produced during the inspection period are obtained. The percentage of grain blocks involved in the corresponding defect type is marked as the defect matching value. The defect matching value is compared with the corresponding preset defect matching threshold. If the defect matching value exceeds the corresponding preset defect matching threshold, it indicates that the corresponding type of defect occurs frequently during the inspection period, and the corresponding type of defect is marked as an uncontrollable defect. If there are uncontrollable defects during the inspection period, it indicates that the molding quality risk is high during the inspection period, and an abnormal quality assessment signal is generated.

[0068] If there are no uncontrollable defects during the detection period, the number of defective grain blocks produced during the detection period is obtained and its ratio to the total number of grain blocks produced during the detection period is calculated to obtain the grain block defect value. The grain block defect value is compared with a preset grain block defect threshold. If the grain block defect value exceeds the preset grain block defect threshold, it indicates that the molding quality performance during the detection period is poor, and a quality assessment abnormality signal is generated. If the grain block defect value does not exceed the preset grain block defect threshold, it indicates that the molding quality performance during the detection period is good, and a quality assessment qualified signal is generated.

[0069] The working principle of this invention is as follows: During use, the key characteristic parameters of the grain raw materials are collected through the raw material characteristic sensing and analysis module to determine whether the raw material state meets the requirements of the molding process. When an abnormal grain characteristic signal is generated, the grain block molding is temporarily suspended and the grain raw materials are processed accordingly to ensure molding stability and the quality of the produced grain blocks. Furthermore, the equipment monitoring and analysis module monitors and analyzes the operation process of the molding equipment, and the environmental disturbance judgment module analyzes the environmental conditions of the production and baking workshop. When an abnormal process signal or an abnormal environmental disturbance signal is generated, the molding intelligent control module performs corresponding control operations. This allows for comprehensive monitoring and reasonable analysis of molding influencing factors and the realization of abnormal adjustment and control, further ensuring the continuous stability of grain block molding and the quality of the produced grain blocks. The invention demonstrates a high level of intelligence.

[0070] In this invention, the threshold, preset value, or preset range settings are for result comparison and analysis to determine whether the result is good or bad. The magnitude of these values ​​is determined by a combination of large-scale model analysis of sample data and human experience, and can also be appropriately adjusted based on seasonal or common-sense influence conditions. Similarly, the preset weight coefficients and influence factors are assigned specific values ​​based on the magnitude of each parameter's influence on the result, ultimately reflecting the impact on the result. These settings are also determined by a combination of large-scale model analysis of sample data and human experience, and can also be appropriately adjusted based on seasonal or common-sense influence conditions.

[0071] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, enabling those skilled in the art to better understand and utilize it. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart control system for grain block forming suitable for production and baking workshops, characterized in that, It includes a raw material characteristic sensing and analysis module, an equipment monitoring and analysis module, an environmental disturbance judgment and analysis module, a molding intelligent control module, and a workshop monitoring terminal; the raw material characteristic sensing and analysis module collects key characteristic parameters of grain raw materials, judges whether the raw material status meets the molding process requirements and generates a grain characteristic qualified signal or a grain characteristic abnormal signal, and sends the grain characteristic abnormal signal to the workshop monitoring terminal; During the grain block forming process, the equipment monitoring and analysis module monitors and analyzes the operation of the forming equipment, generates process qualified signals or process abnormal signals through analysis, and sends the process abnormal signals to the forming intelligent control module and the workshop monitoring terminal. The environmental disturbance judgment module analyzes the environmental conditions of the production baking workshop, generates normal or abnormal environmental disturbance signals, and sends the abnormal environmental disturbance signals to the molding intelligent control module and the workshop monitoring terminal. When the molding intelligent control module receives the abnormal process signal or the abnormal environmental disturbance signal, it generates corresponding control commands and performs corresponding control operations based on the control commands. The molding intelligent control module is connected to the molding stability analysis module. The molding intelligent control module sends the molding control information during the detection period to the molding stability analysis module. The molding stability analysis module analyzes the potential molding stability problems during the detection period and generates a stability qualified signal or a stability abnormal signal through analysis. The stability abnormal signal is sent to the workshop monitoring terminal. When the workshop monitoring terminal receives the stability abnormal signal, it issues a corresponding warning. The molding stability analysis module is connected to the molding quality assessment module. The molding stability analysis module sends a stability qualified signal to the molding quality assessment module. When the molding quality assessment module receives the stability qualified signal, it evaluates and analyzes the molding quality of the grain block during the detection period. Through analysis, it generates a quality assessment qualified signal or a quality assessment abnormal signal and sends the quality assessment abnormal signal to the workshop monitoring terminal. When the workshop monitoring terminal receives the quality assessment abnormal signal, it issues a corresponding warning. The specific analysis process of the molding quality assessment module includes: All defect types of grain blocks produced during the detection period are obtained. The percentage of grain blocks involved in the corresponding defect type is marked as the defect matching value. The defect matching value is compared with the corresponding preset defect matching threshold. If the defect matching value exceeds the corresponding preset defect matching threshold, the corresponding type of defect is marked as an uncontrollable defect. If an uncontrollable defect exists during the detection period, a quality assessment abnormality signal is generated. If there are no uncontrollable defects during the detection period, the number of defective grain blocks produced during the detection period is obtained and the ratio is calculated to the total number of grain blocks produced during the detection period to obtain the grain block defect value. The grain block defect value is compared with the preset grain block defect threshold. If the grain block defect value exceeds the preset grain block defect threshold, a quality assessment abnormality signal is generated; if the grain block defect value does not exceed the preset grain block defect threshold, a quality assessment qualified signal is generated.

2. The intelligent control system for grain block forming suitable for production and baking workshops according to claim 1, characterized in that, The specific analysis process of the raw material characteristic sensing and analysis module is as follows: If the grain particle size detection value exceeds the preset grain particle size detection threshold, an abnormal grain characteristic signal is generated; if the grain particle size detection value does not exceed the preset grain particle size detection threshold, the grain characteristic adaptation value is calculated by weighted summation of the grain temperature measurement value, grain moisture measurement value, and grain particle size measurement value; if the grain characteristic adaptation value exceeds the preset grain characteristic adaptation threshold, an abnormal grain characteristic signal is generated; otherwise, a qualified grain characteristic signal is generated.

3. The intelligent control system for grain block forming suitable for production and baking workshops according to claim 1, characterized in that, The specific analysis process of the equipment monitoring and analysis module is as follows: If the molding pressure or mold temperature is not within the corresponding preset range, a process abnormality signal is generated; if both the molding pressure and mold temperature are within the corresponding preset range, the process monitoring value is calculated by weighted summation of the molding pressure value, molding temperature value, and molding vibration value. If the process monitoring value exceeds the preset process monitoring threshold, a process abnormality signal is generated; otherwise, a process qualified signal is generated.

4. The intelligent control system for grain block forming suitable for production and baking workshops according to claim 1, characterized in that, The specific analysis process of the environmental disturbance judgment and analysis module is as follows: The environmental disturbance coefficient is calculated by weighting and summing the temperature and humidity disturbance values, wind speed disturbance values, and dust disturbance values. If the environmental disturbance coefficient exceeds the preset environmental disturbance coefficient threshold, an abnormal environmental disturbance signal is generated; otherwise, a normal environmental disturbance signal is generated.

5. The intelligent control system for grain block forming suitable for production and baking workshops according to claim 1, characterized in that, The specific analysis process of the molding stability analysis module is as follows: The generation time of the corresponding process abnormal signal or environmental disturbance abnormal signal is obtained, and the corresponding generation time is marked as the first time. The time when the corresponding control operation is completed is marked as the second time. The time difference between the second time and the first time is calculated to obtain the stable duration. The stable duration is compared with the corresponding preset stable duration threshold. If the stable duration exceeds the preset stable duration threshold, the corresponding stable duration is marked as an inefficient duration. Furthermore, the detection period is divided into several sub-periods. If a process abnormality signal or an environmental disturbance abnormality signal is generated in the corresponding sub-period, the corresponding sub-period is marked as a poor period. The number of poor time periods within the detection period is obtained and marked as poor time detection value, and the number of inefficient time periods within the detection period is marked as inefficient statistical value. The stable time period is calculated by the ratio of the stable time period to the corresponding preset stable time period threshold to obtain the stable time period measurement value. The average of all stable time period measurement values ​​within the detection period is calculated to obtain the stable time decision value. The stability risk coefficient is calculated by weighting and summing the poor-time detection value, the inefficient statistical value and the stable-time decision value. The stability risk coefficient is compared with the preset stability risk coefficient threshold. If the stability risk coefficient exceeds the preset stability risk coefficient threshold, a stability anomaly signal is generated. If the stability risk coefficient does not exceed the preset stability risk coefficient threshold, a stability qualified signal is generated.

6. The intelligent control system for grain block forming suitable for production and baking workshops according to claim 1, characterized in that, The molding quality assessment module is connected to the 3D morphology defect intelligent detection module. The 3D morphology defect intelligent detection module utilizes multi-view vision and deep learning technology to detect 3D defects in real time and sends the defect detection information to the molding quality assessment module and the workshop monitoring terminal. The specific operation process is as follows: Images of the molded block surface are captured from different angles using a high-speed industrial camera. A 3D point cloud model of the molded block is generated using a motion recovery structure algorithm. Key indicators are extracted, and the feature data is input into an improved YOLOv7 deep learning model to output the defect type and location.

Images