Abnormality monitoring method and system for feed production control system

Abstract

The invention discloses an abnormality monitoring method and system for a feed production control system, and relates to the technical field of abnormality monitoring. During operation of the system, safety data of raw materials, production processes and feed finished products are collected by deploying various high-precision sensors, analysis equipment and sensors; a first data set, a second data set and a third data set are obtained, the collected data are preprocessed and calculated to obtain a production safety index Slaq, the production safety index Slaq is compared with a preset first qualified threshold value M and a preset second qualified threshold value N, a grade strategy scheme is obtained, abnormal conditions in the production process are detected in real time, potential problems are recognized, and the production safety index Slaq is obtained. According to the abnormal condition identified by the abnormal detection module, preliminary emergency treatment measures are executed, including adjusting production parameters or starting an emergency plan, and when the abnormal detection module or the abnormal response module identifies an abnormal condition, the abnormal condition is fed back to an operator in time in a sound-light alarm or mobile terminal notification mode.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal monitoring, and in particular to an abnormal monitoring method and system for a feed production control system. Background Art

[0002] In the field of food production, ensuring the safety and quality of products is always a key challenge. With the increase in market demand, the production process of food has become more complex and refined. Especially in the feed production control system, it involves multiple links such as raw material processing, production process control and finished product testing. Any abnormality in any link may lead to a decline in product quality or even safety problems. The current feed production control system usually relies on traditional manual monitoring and experience judgment, which are not only inefficient but also easily affected by human factors. The existing system is insufficient in the breadth and accuracy of data collection and cannot fully cover all kinds of problems that may arise in the production process. Even in data processing and anomaly detection, there are problems such as simple algorithms and slow response, which make it difficult to detect potential safety hazards in time, resulting in problems often being discovered in the finished product stage. In addition, most of the existing emergency response measures rely on post-intervention, lacking real-time and initiative, which is particularly insufficient under the fast production rhythm.

[0003] Due to the above shortcomings and deficiencies, when a problem occurs in a certain link of the production process, it is often impossible to identify and deal with it in time, resulting in abnormal situations. These abnormal situations may include deviations in production parameters, equipment failures, and even quality problems of raw materials or finished products. Once an abnormality occurs, it may cause the entire production line to stagnate, the product to be scrapped, and even affect consumer safety and brand reputation. These problems not only increase production costs, but also weaken the competitiveness of enterprises in the market. Therefore, a new monitoring system that can provide all-round monitoring and rapid response is urgently needed to fill the gaps in existing technologies. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an abnormality monitoring method and system for a feed production control system, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an abnormal monitoring system for feed production control system, including a data acquisition module, a data preprocessing module, an abnormal detection module, an abnormal response module, a data feedback module and an alarm feedback module;

[0006] The data acquisition module is used to collect safety data of raw materials, production processes and finished feed products by deploying a variety of high-precision sensors, analysis equipment and sensors to obtain the first data group, the second data group and the third data group;

[0007] The data preprocessing module is used to filter and standardize the collected data, remove noise and outliers, fill in missing data, normalize the preprocessed data, and calculate and obtain: production safety index Slaq;

[0008] The anomaly detection module is used to use the calculated data and machine learning model to compare the production safety index Slaq with the preset first qualified threshold M and the second preset qualified threshold N, obtain a level strategy solution, detect abnormal conditions in the production process in real time, and identify potential problems;

[0009] The abnormal response module is used to execute preliminary emergency treatment measures according to the abnormal situation identified by the abnormal detection module, including adjusting production parameters or initiating emergency plans;

[0010] The data feedback module is used to collect and analyze data feedback during the production process and optimize the control strategy and model parameters of the system;

[0011] The alarm feedback module is used to promptly feedback the abnormal situation to the operator through sound and light alarms or mobile terminal notifications when the abnormality detection module or the abnormality response module identifies an abnormality, and provide real-time monitoring and response suggestions.

[0012] Preferably, the data acquisition module includes a raw material data acquisition unit, a production process data acquisition unit and a finished product data acquisition unit;

[0013] The raw material data collection unit is used to collect safety data related to the raw materials entering the production process, including the moisture content P, by deploying a near-infrared spectrometer, a microbial detector and an atomic absorption spectrometer. h2o , Microbial content P mic , heavy metal residues hmr , pesticide residues pest and nutritional content uniformity P nutr , forming a first data group.

[0014] Preferably, the production process data acquisition unit is used to use an online mixing degree analyzer, a temperature sensor and a vibration monitoring sensor to continuously monitor the status of the production line, and collect data related to the safety of the production process in real time in each process link of feed production to obtain: mixing uniformity P mix , Temperature control accuracy P temp , production speed P speed , Equipment vibration frequency P vib and production pressure P press , forming a second data set.

[0015] Preferably, the finished product data acquisition unit is used to utilize a moisture analyzer, a hardness tester, and a microbial analyzer to perform safety and quality inspections on the finally produced feed finished product, and obtain: moisture content P fh2o , physical hardness P hard , finished product microbial content P fmic , nutritional component accuracy P fnutr and shelf life prediction P shelf , forming a third data group.

[0016] Preferably, the data preprocessing module includes a data cleaning unit and a data standardization unit;

[0017] The data cleaning unit is used to perform preliminary processing on the original data by applying filtering technology. The main tasks include filtering noise data, removing outliers, and filling in missing data, and screening the data;

[0018] The data standardization unit is used to perform standardization processing on the cleaned data so that the data is under the same dimension. After performing normalization processing on the data, calculate and obtain: production safety index S laq , raw material safety coefficient K rm , production process safety coefficient K proc and finished product safety coefficient K fp .

[0019] Preferably, the anomaly detection module includes an anomaly analysis unit;

[0020] The anomaly analysis unit is used to analyze the change of the production safety index Slaq in real time, and compare it with the preset first qualified threshold M and second qualified threshold N. Using a pre-trained machine learning model, according to the current value and historical trend of the production safety index Slaq, identify potential abnormal situations, and generate corresponding hierarchical policy solutions. When the production safety index Slaq exceeds or approaches the set threshold range, the unit will immediately trigger an alarm to prompt potential problems;

[0021] When Slaq > M, the system determines that the production safety index is within the normal range, indicating that the production process meets the safety standards and no adjustment is required;

[0022] When N < Slaq ≤ M, the system identifies that the production safety index is 20% lower than the normal range, indicating that there are potential risks and preventive measures need to be taken;

[0023] When Slaq ≤ N, the system determines that the production safety index is lower than the second qualified threshold, and the production process has entered an unsafe area, and emergency measures need to be taken immediately.

[0024] Preferably, the anomaly response module includes an emergency execution unit;

[0025] The emergency execution unit is used to execute immediate emergency response measures according to the severity of the abnormal situation, including automatic adjustment of key production parameters to quickly correct the abnormality, including adjusting temperature, pressure and production speed, and initiating emergency plans according to the type and level of abnormality, including automatic shutdown, switching to a backup system or notifying on-site personnel to take manual intervention.

[0026] Preferably, the data feedback module includes a feedback analysis unit;

[0027] The feedback analysis unit is used to collect real-time data feedback at each stage of the production process and conduct in-depth analysis of the data. By analyzing the data feedback, the control strategy is optimized, the set values ​​of production parameters are adjusted or the training data of the machine learning model is updated, the effectiveness of previous emergency measures is evaluated, and the control strategy is iteratively optimized based on the feedback results.

[0028] Preferably, the alarm feedback module includes an alarm notification unit;

[0029] The alarm notification unit is used to immediately trigger the sound and light alarm device when an abnormality is detected, send a clear warning signal to the operator, and send a detailed abnormality report to the operator through the mobile notification function, including the type, location and impact of the abnormality, to help the operator quickly understand and respond to the abnormal situation, and provide real-time response suggestions, including recommended emergency processing steps or parameter adjustment suggestions.

[0030] An abnormal monitoring method for a feed production control system comprises the following steps:

[0031] Step 1: Deploy a variety of high-precision sensors, analytical equipment and sensors to collect safety data of raw materials, production processes and finished feed products to obtain the first data group, the second data group and the third data group;

[0032] Step 2: Filter and standardize the collected data, remove noise and outliers, fill in missing data, normalize the pre-processed data, and calculate and obtain: production safety index Slaq;

[0033] Step 3: Using the calculated data and machine learning model, the production safety index Slaq is compared with the preset first qualified threshold M and the second preset qualified threshold N to obtain a level strategy solution, detect abnormal conditions in the production process in real time, and identify potential problems;

[0034] Step 4: Based on the abnormal situation identified by the abnormality detection module, perform preliminary emergency response measures, including adjusting production parameters or initiating emergency plans;

[0035] Step 5: Collect and analyze data feedback from the production process to optimize the system's control strategy and model parameters;

[0036] Step 6: When the abnormality detection module or abnormality response module identifies an abnormality, it will promptly feedback the abnormal situation to the operator through sound and light alarms or mobile notifications, and provide real-time monitoring and response suggestions.

[0037] The present invention provides an abnormal monitoring method and system for a feed production control system, which has the following beneficial effects:

[0038] (1) When the system is running, by deploying a variety of high-precision sensors, analytical equipment and sensors, it collects safety data of raw materials, production processes and feed products, obtains the first data group, the second data group and the third data group, and obtains the production safety index Slaq after preprocessing and calculation of the collected data. It is compared with the preset first qualified threshold M and the second preset qualified threshold N to obtain a level strategy plan, detect abnormal conditions in the production process in real time, identify potential problems, and execute preliminary emergency response measures based on the abnormal conditions identified by the abnormal detection module, including adjusting production parameters or activating emergency plans. When the abnormal detection module or the abnormal response module identifies an abnormality, the abnormal condition is promptly fed back to the operator through sound and light alarms or mobile terminal notifications.

[0039] (2) The system effectively improves the safety and reliability of the feed production process by integrating six modules: data acquisition, preprocessing, anomaly detection, anomaly response, data feedback, and alarm feedback. First, the data acquisition module comprehensively covers the safety data of raw materials, production processes, and finished products through a variety of high-precision sensors and analytical equipment to ensure the accuracy and comprehensiveness of the data. Subsequently, the data preprocessing module filters, standardizes, and normalizes the collected data to eliminate noise and outliers, ensure the consistency and reliability of the data, and obtains the production safety index Slaq by calculation, providing a solid foundation for subsequent detection and analysis.

[0040] (3) The system identifies potential production safety issues through real-time monitoring and analysis by the anomaly detection module, compares them with preset thresholds, and generates specific level strategy solutions. When an abnormal situation is detected, the abnormal response module can immediately initiate emergency response measures, such as automatically adjusting key production parameters or triggering emergency plans to ensure that the production process quickly returns to a safe state. The data feedback module continuously optimizes the control strategy and model parameters by continuously collecting and analyzing real-time data, thereby enhancing the system's adaptability and self-optimization capabilities.

[0041] (4) Compared with existing technical means, this system has achieved significant improvements in many aspects. It not only improves the ability to monitor the production process in all aspects, but also realizes a more intelligent abnormality identification and processing method by introducing machine learning models. At the same time, the multi-channel notification function of the alarm feedback module ensures that operators can obtain abnormal information in the first time and take corresponding measures quickly. These improvements ultimately led to a significant improvement in the safety, efficiency and product quality of the feed production process, reduced the incidence of production accidents, and improved the overall operational stability of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a block diagram of an abnormal monitoring system for a feed production control system of the present invention;

[0043] Figure 2 The present invention is a schematic diagram of the steps of an abnormal monitoring method for a feed production control system. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0045] Example 1

[0046] The present invention provides an abnormal monitoring system for feed production control system, please refer to Figure 1 , including a data acquisition module, a data preprocessing module, an anomaly detection module, an anomaly response module, a data feedback module and an alarm feedback module;

[0047] The data acquisition module is used to collect safety data of raw materials, production processes and finished feed products by deploying a variety of high-precision sensors, analysis equipment and sensors to obtain the first data group, the second data group and the third data group;

[0048] The data preprocessing module is used to filter and standardize the collected data, remove noise and outliers, fill in missing data, normalize the preprocessed data, and calculate and obtain: production safety index Slaq;

[0049] The anomaly detection module is used to use the calculated data and machine learning model to compare the production safety index Slaq with the preset first qualified threshold M and the second preset qualified threshold N, obtain a level strategy solution, detect abnormal conditions in the production process in real time, and identify potential problems;

[0050] The abnormal response module is used to execute preliminary emergency treatment measures according to the abnormal situation identified by the abnormal detection module, including adjusting production parameters or initiating emergency plans;

[0051] The data feedback module is used to collect and analyze data feedback during the production process and optimize the control strategy and model parameters of the system;

[0052] The alarm feedback module is used to promptly feedback the abnormal situation to the operator through sound and light alarms or mobile terminal notifications when the abnormality detection module or the abnormality response module identifies an abnormality, and provide real-time monitoring and response suggestions.

[0053] In this embodiment, by deploying a variety of high-precision sensors, analysis equipment and sensors, safety data of raw materials, production processes and finished feed products are collected, and a first data group, a second data group and a third data group are obtained. The collected data is pre-processed and calculated to obtain: a production safety index Slaq, and the production safety index Slaq is compared with a preset first qualified threshold M and a second preset qualified threshold N to obtain a level strategy scheme, detect abnormal conditions in the production process in real time, identify potential problems, and execute preliminary emergency response measures according to the abnormal conditions identified by the abnormal detection module, including adjusting production parameters or initiating emergency plans, collecting and analyzing data feedback in the production process, optimizing the control strategy and model parameters of the system, and when the abnormal detection module or the abnormal response module identifies an abnormality, the abnormal condition is promptly fed back to the operator through sound and light alarms or mobile terminal notifications, and real-time monitoring and response suggestions are provided.

[0054] Example 2

[0055] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a raw material data acquisition unit, a production process data acquisition unit and a finished product data acquisition unit;

[0056] The raw material data collection unit is used to collect safety data related to the raw materials entering the production process, including the moisture content P, by deploying a near-infrared spectrometer, a microbial detector and an atomic absorption spectrometer. h2o , Microbial content P mic , heavy metal residues hmr , pesticide residues pest and nutritional content uniformity P nutr , forming a first data group;

[0057] The production process data acquisition unit is used to use an online mixing degree analyzer, a temperature sensor and a vibration monitoring sensor to continuously monitor the status of the production line, collect data related to the safety of the production process in real time in each process link of feed production, and obtain: mixing uniformity P mix , Temperature control accuracy P temp , production speed P speed , Equipment vibration frequency P vib and production pressure P press , forming a second data group;

[0058] The finished product data acquisition unit is used to use a moisture analyzer, a hardness tester and a microbial analyzer to perform safety and quality tests on the final feed product to obtain: moisture content P fh2o , physical hardness P hard , Finished product microbial content P fmic , Nutritional content accuracy fnutr and shelf life prediction P shelf , forming a third data group.

[0059] In this embodiment, by introducing advanced detection equipment such as near-infrared spectrometer, microbial detector, atomic absorption spectrometer, etc., the raw material data acquisition unit can collect various safety data related to production raw materials in real time and efficiently. These data include key indicators such as moisture content, microbial content, heavy metal residues, pesticide residues, and uniformity of nutrients, forming a first data group. Compared with traditional collection methods, this multi-dimensional data collection method greatly improves the accuracy and integrity of the data, provides a reliable data basis for subsequent production processes, and avoids production deviations and safety hazards caused by incomplete or inaccurate data.

[0060] Example 3

[0061] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data preprocessing module includes a data cleaning unit and a data standardization unit;

[0062] The data cleaning unit is used to perform preliminary processing on the original data by applying filtering technology. The main tasks include filtering noise data, removing outliers and filling missing data, and screening the data;

[0063] The data standardization unit is used to standardize the cleaned data so that the data are in the same dimension, and the production safety index S is calculated after the data is normalized. laq , Raw material safety factor K rm , production process safety factor K proc And the finished product safety factor K fp ;

[0064] The production safety index S laq Calculated by the following formula:

[0065] Slaq=α*K rm +β*K proc +γ*K fp ;

[0066] In the formula, S laq represents the production safety index, K rm Indicates the safety factor of raw materials, K proc Represents the safety factor of the production process, K fp represents the safety factor of the finished product, α, β and γ represent the safety factor of the raw material K rm , production process safety factor K proc And the finished product safety factor K fp The proportionality coefficient of

[0067] Among them, 0≤α≤1, 0≤β≤1, 0≤γ≤1, and α+β+γ≤1.0;

[0068] The raw material safety factor K rm Calculated by the following formula:

[0069]

[0070] Where P h2o Indicates moisture content, P mic Indicates the microbial content, P hmr Indicates heavy metal residues, P pest Pesticide residues, P nutr It indicates the uniformity of nutritional ingredients. α1, α2, α3 and α4 are weight coefficients used to adjust the safety factor K of each parameter for raw materials. rm The impact of

[0071] The raw material safety factor K rm Used to evaluate the overall safety of raw materials; moisture content P h2o表示 The higher the moisture content, the greater the risk of microbial growth, so the reciprocal of the moisture content is used to express the impact; the microbial content P mic The reciprocal is used to indicate that the higher the content, the lower the safety. A small value ∈ 1 is added to avoid zero division errors; Phmr and Ppest: heavy metal residues and pesticide residues, the square root is used to indicate their combined impact on safety. The higher the content, the lower the safety, so it appears in the form of a reciprocal.

[0072] Among them, 0≤α1≤1, 0≤α2≤1, 0≤α3≤1, 0≤α4≤1, and α1+α2+α3+α4≤1.0.

[0073] The production process safety factor K proc Calculated by the following formula:

[0074]

[0075] Where P mix Indicates mixing uniformity, P temp Indicates the temperature control accuracy, P speed Indicates the production speed, P vib Indicates the vibration frequency of the device, P press represents the production pressure, β1, β2 and β3 represent weight coefficients, which are used to adjust the safety factor K of each parameter to the production process proc The impact of

[0076] The mixing uniformity P mix And temperature control accuracy P temp The ratio of the two reflects the effectiveness of the mixing process and the stability of temperature control. The ratio of the two reflects the effectiveness of the mixing process and the stability of temperature control; production speed P speed and the equipment vibration frequency P vib :The lower the vibration frequency, the higher the production speed and the more stable the system. Take the logarithm of its ratio to smooth the change; production pressure P press An exponential function is used to represent the nonlinear effect of pressure on safety. The higher the pressure, the lower the corresponding safety. μ represents the average pressure value, ensuring that the effect of pressure in the model is within a reasonable range. ∈2 is used to avoid division by zero errors when the vibration frequency is zero.

[0077] Among them, 0≤β1≤1, 0≤β2≤1, 0≤β3≤1, and β1+β2+β3≤1.0.

[0078] The finished product safety factor K fp Calculated by the following formula:

[0079]

[0080] Where P fh2o Indicates moisture content, P hard Indicates physical hardness, P fmic Indicates the microbial content of the finished product, P fnutr Indicates the accuracy of nutritional ingredients, P shelf represents the shelf life prediction, γ1, γ2 and γ3 represent weight coefficients, which are used to adjust the parameters for the safety factor K of the finished product. fp The impact of

[0081] The moisture content P fh2o and physical hardness P hardThe higher the hardness, the more water, which may reduce the product quality, so the ratio is used to express the impact; the finished product microbial content P fmic Use the reciprocal to indicate that the higher the content, the lower the safety; add a small value ∈3 to avoid zero division errors; the accuracy of nutritional ingredients P fnutr and shelf life prediction P shelf ,The higher the accuracy of the ingredients, the longer the shelf life, and the higher the safety and quality of the product.,σ,represents the adjustment factor, which is used to balance the trade-off between the nutritional ingredients and the shelf life;

[0082] Among them, 0≤γ1≤1, 0≤γ2≤1, 0≤γ3≤1, and γ1+γ2+γ3≤1.0.

[0083] In this embodiment, through the implementation of the data preprocessing module, the system significantly improves the accuracy and consistency of data processing. First, the data cleaning unit uses filtering technology to perform preliminary processing on the original data, effectively filters out noise data, removes outliers, and fills in missing data, making the data more accurate and reliable. Secondly, the data standardization unit performs standardized processing on the cleaned data so that the data can be compared and analyzed under the same dimension. Through these processing steps, the system can accurately calculate the production safety index Slaq, the raw material safety factor Krm, the production process safety factor Kproc and the finished product safety factor Kfp, thereby providing a solid foundation for subsequent abnormal detection and response. The application of this module reduces the potential risks caused by data errors and inconsistencies, and ensures the safety of the production process and the quality stability of the finished product.

[0084] Example 4

[0085] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the anomaly detection module includes an anomaly analysis unit;

[0086] The abnormality analysis unit is used to analyze the changes of the production safety index Slaq in real time, and compare it with the preset first qualified threshold M and second qualified threshold N, and use the pre-trained machine learning model to identify potential abnormal situations according to the current value and historical trend of the production safety index Slaq, and generate corresponding graded strategy solutions. When the production safety index Slaq exceeds or approaches the set threshold range, the unit will immediately trigger an alarm to prompt potential problems;

[0087] When Slaq>M, the system determines that the production safety index is within the normal range, indicating that the production process meets the safety standards and no adjustments are required. The production process parameters are continuously monitored to maintain the existing operating conditions to ensure that Slaq remains within the qualified range. Regularly perform system self-checks to ensure the normal operation of sensors and detection equipment;

[0088] When N < Slaq ≤ M, the system identifies that the production safety index is 20% lower than the normal range, indicating potential risks. Preventive measures need to be taken, and production parameters should be adjusted immediately. Key risk factors should be reduced first, such as the microbial content P mic or the temperature control accuracy P temp , and when necessary, reduce the production speed P speed to ensure the stability of other parameters. If S laq is close to M and the temperature control accuracy P temp exceeds the set range, it is recommended to adjust the temperature control to P temp ΔP to reduce risks;

[0089] When Slaq ≤ N, the system determines that the production safety index is lower than the second qualified threshold, and the production process has entered the unsafe area. Immediate emergency measures need to be taken, such as suspending the production line operation, comprehensively checking the status of production equipment and raw materials, and thoroughly overhauling key parameters such as heavy metal residues Phmr or the equipment vibration frequency P vib to ensure that the restored production process meets safety requirements. When necessary, reconfigure the production process parameters. If S laq is lower than N, production should be stopped immediately, and P vib should be detected and its value reduced P vib , while checking for heavy metal residues P hmr to ensure that they do not exceed the standard.

[0090] The abnormal response module includes an emergency execution unit;

[0091] The emergency execution unit is used to execute immediate emergency response measures according to the severity of the abnormal situation, including automatic adjustment of key production parameters to quickly correct the abnormality, such as adjusting temperature, pressure, and production speed, and starting emergency plans according to the abnormal type and level, including automatic shutdown, switching to a standby system, or notifying on-site personnel to take manual intervention.

[0092] The data feedback module includes a feedback analysis unit;

[0093] The feedback analysis unit is used to collect real-time data feedback at each stage of the production process and conduct in-depth analysis on these data. By analyzing the data feedback, optimize the control strategy, adjust the set values of production parameters, or update the training data of the machine learning model, evaluate the effectiveness of previous emergency measures, and iteratively optimize the control strategy according to the feedback results.

[0094] The alarm feedback module includes an alarm notification unit;

[0095] The alarm notification unit is used to immediately trigger the sound and light alarm device when an abnormality is detected, send a clear warning signal to the operator, and send a detailed abnormality report to the operator through the mobile notification function, including the type, location and impact of the abnormality, to help the operator quickly understand and respond to the abnormal situation, and provide real-time response suggestions, including recommended emergency processing steps or parameter adjustment suggestions.

[0096] In this embodiment, through the comprehensive application of the abnormal detection module, abnormal response module, data feedback module and alarm feedback module, the system greatly improves the safety and emergency response capabilities in the food production process. The abnormal detection module can quickly identify potential abnormal situations by real-time analysis of the production safety index Slaq, and generate corresponding grade strategy solutions according to different safety thresholds to ensure that the risk can be effectively controlled at the early stage. After detecting the abnormality, the abnormal response module immediately implements the corresponding emergency measures, automatically adjusts the key production parameters, prevents the abnormality from expanding, and ensures the continuity and safety of the production process. The data feedback module further optimizes the control strategy by conducting in-depth analysis of the real-time data at each stage of the production process, and continuously improves the overall performance of the system and the accuracy of the emergency response. The alarm feedback module ensures that the operator can obtain abnormal information and response suggestions in time through multi-channel and multi-mode alarm notifications, so as to quickly take appropriate measures to reduce the impact of abnormalities on production. In general, the synergy of these modules significantly improves the automation, response speed and safety reliability of the system, and effectively reduces the potential safety hazards and production losses that may occur in the production process.

[0097] Example 5

[0098] An abnormal monitoring method for feed production control system, please refer to Figure 2 , specifically: including the following steps:

[0099] Step 1: Deploy a variety of high-precision sensors, analytical equipment and sensors to collect safety data of raw materials, production processes and finished feed products to obtain the first data group, the second data group and the third data group;

[0100] Step 2: Filter and standardize the collected data, remove noise and outliers, fill in missing data, normalize the pre-processed data, and calculate and obtain: production safety index Slaq;

[0101] Step 3: Using the calculated data and machine learning model, the production safety index Slaq is compared with the preset first qualified threshold M and the second preset qualified threshold N to obtain a level strategy solution, detect abnormal conditions in the production process in real time, and identify potential problems;

[0102] Step 4: Based on the abnormal situation identified by the abnormality detection module, perform preliminary emergency response measures, including adjusting production parameters or initiating emergency plans;

[0103] Step 5: Collect and analyze data feedback from the production process to optimize the system's control strategy and model parameters;

[0104] Step 6: When the abnormality detection module or abnormality response module identifies an abnormality, it will promptly feedback the abnormal situation to the operator through sound and light alarms or mobile notifications, and provide real-time monitoring and response suggestions.

[0105] In this embodiment, the system can significantly improve the safety and stability of the food production process. The operations from the first step to the third step ensure the accurate collection, cleaning and standardization of data in the entire production chain from raw materials to finished products, so that the production safety index Slaq can reflect the real production status. By comparing with the preset threshold, the system can identify and classify abnormal situations in real time during the production process, and generate a graded strategy plan in a timely manner. The emergency treatment measures in the fourth step ensure that the system can respond quickly, adjust production parameters or start emergency plans at the beginning of the abnormality, thereby effectively avoiding the further expansion of safety risks. The fifth step improves the accuracy and efficiency of emergency response through continuous data feedback and analysis. The alarm feedback mechanism in the sixth step ensures that the operator can get information as soon as the abnormality occurs, and can take appropriate measures quickly according to the real-time suggestions provided by the system, thereby further reducing the impact of the abnormality on production. Through comprehensive data monitoring, intelligent analysis and accurate emergency response, the system greatly reduces the safety hazards in production and improves the safety, stability and reliability of the production process.

[0106] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An abnormal monitoring system for feed production control system, characterized by: It includes a data acquisition module, a data preprocessing module, an anomaly detection module, an anomaly response module, a data feedback module, and an alarm feedback module; The data acquisition module is used to collect safety data of raw materials, production processes, and finished feed products by deploying a variety of high-precision sensors, analysis devices, and sensors, and obtain the first data group, the second data group, and the third data group; The data preprocessing module is used to filter and standardize the collected data, remove noise and outliers, fill in missing data, normalize the preprocessed data, and calculate to obtain: the production safety index Slaq; The anomaly detection module is used to use the calculated data and machine learning models to compare the production safety index Slaq with the preset first qualified threshold M and the second preset qualified threshold N to obtain a hierarchical policy plan, and to detect anomalies in the production process in real time and identify potential problems; The anomaly response module is used to execute preliminary emergency treatment measures according to the anomalies identified by the anomaly detection module, including adjusting production parameters or activating emergency plans; The data feedback module is used to collect and analyze data feedback in the production process to optimize the control strategy and model parameters of the system; The alarm feedback module is used to, when an anomaly is identified by the anomaly detection module or the anomaly response module, promptly feedback the anomaly situation to the operator by means of audible and visual alarms or mobile device notifications, and provide real-time monitoring and response suggestions.

2. The abnormal monitoring system for feed production control system according to claim 1, characterized in that: The data acquisition module includes a raw material data acquisition unit, a production process data acquisition unit, and a finished product data acquisition unit; The raw material data collection unit is used to collect safety data related to the raw materials entering the production process, including the moisture content P, by deploying a near-infrared spectrometer, a microbial detector and an atomic absorption spectrometer. h2o , Microbial content P mic , heavy metal residues hmr , pesticide residues pest and nutritional content uniformity P nutr , forming a first data group.

3. The abnormal monitoring system for feed production control system according to claim 2, characterized in that: The production process data acquisition unit is used to use an online mixing degree analyzer, a temperature sensor and a vibration monitoring sensor to continuously monitor the status of the production line, collect data related to the safety of the production process in real time in each process link of feed production, and obtain: mixing uniformity P mix , Temperature control accuracy P temp , production speed P speed , Equipment vibration frequency P vib and production pressure P press , forming a second data set.

4. The abnormal monitoring system for feed production control system according to claim 2, characterized in that: The finished product data acquisition unit is used to use a moisture analyzer, a hardness tester and a microbial analyzer to perform safety and quality tests on the final feed product to obtain: moisture content P fh2o , physical hardness P hard , Finished product microbial content P fmic , Nutritional content accuracy fnutr and shelf life prediction P shelf , forming a third data group.

5. The abnormal monitoring system for feed production control system according to claim 1, characterized in that: The data preprocessing module includes a data cleaning unit and a data standardization unit; The data cleaning unit is used to perform preliminary processing on the original data by applying filtering techniques. The main tasks include filtering noise data, removing outliers, filling in missing data, and screening the data; The data standardization unit is used to standardize the cleaned data so that the data are in the same dimension, and the production safety index S is calculated after the data is normalized. laq , Raw material safety factor K rm , production process safety factor K proc And the finished product safety factor K fp .

6. The abnormal monitoring system for feed production control system according to claim 1, characterized in that: The anomaly detection module includes an anomaly analysis unit; The anomaly analysis unit is used to analyze the change of the production safety index Slaq in real time, compare it with the preset first qualified threshold M and the second qualified threshold N, use a pre-trained machine learning model, and identify potential anomalies according to the current value and historical trend of the production safety index Slaq, and generate corresponding hierarchical policy plans. When the production safety index Slaq exceeds or approaches the set threshold range, the unit will immediately trigger an alarm to prompt potential problems; When Slaq > M, the system determines that the production safety index is within the normal range, indicating that the production process meets the safety standards and no adjustment is required; When N < Slaq ≤ M, the system identifies that the production safety index is 20% lower than the normal range, indicating that there are potential risks and preventive measures need to be taken; When Slaq ≤ N, the system determines that the production safety index is lower than the second qualified threshold, and the production process has entered an unsafe area, and emergency measures need to be taken immediately.

7. The abnormal monitoring system for feed production control system according to claim 1, characterized in that: The anomaly response module includes an emergency execution unit; The emergency execution unit is used to execute immediate emergency response measures according to the severity of the abnormal situation, including automatic adjustment of key production parameters to quickly correct the abnormality, including adjusting temperature, pressure and production speed, and initiating emergency plans according to the type and level of abnormality, including automatic shutdown, switching to a backup system or notifying on-site personnel to take manual intervention.

8. The abnormal monitoring system for feed production control system according to claim 1, characterized in that: The data feedback module includes a feedback analysis unit; The feedback analysis unit is used to collect real-time data feedback at each stage of the production process and conduct in-depth analysis of the data. By analyzing the data feedback, the control strategy is optimized, the set values ​​of production parameters are adjusted or the training data of the machine learning model is updated, the effectiveness of previous emergency measures is evaluated, and the control strategy is iteratively optimized based on the feedback results.

9. The abnormal monitoring system for feed production control system according to claim 1, characterized in that: The alarm feedback module includes an alarm notification unit; The alarm notification unit is used to immediately trigger the sound and light alarm device when an abnormality is detected, send a clear warning signal to the operator, and send a detailed abnormality report to the operator through the mobile notification function, including the type, location and impact of the abnormality, to help the operator quickly understand and respond to the abnormal situation, and provide real-time response suggestions, including recommended emergency processing steps or parameter adjustment suggestions.

10. An abnormality monitoring method for a feed production control system, applied to an abnormality monitoring system for a feed production control system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Deploy a variety of high-precision sensors, analytical equipment and sensors to collect safety data of raw materials, production processes and finished feed products to obtain the first data group, the second data group and the third data group; Step 2: Filter and standardize the collected data, remove noise and outliers, fill in missing data, normalize the pre-processed data, and calculate and obtain: production safety index Slaq; Step 3: Using the calculated data and machine learning model, the production safety index Slaq is compared with the preset first qualified threshold M and the second preset qualified threshold N to obtain a level strategy solution, detect abnormal conditions in the production process in real time, and identify potential problems; Step 4: Based on the abnormal situation identified by the abnormality detection module, perform preliminary emergency response measures, including adjusting production parameters or initiating emergency plans; Step 5: Collect and analyze data feedback from the production process to optimize the system's control strategy and model parameters; Step 6: When the abnormality detection module or abnormality response module identifies an abnormality, it will promptly feedback the abnormal situation to the operator through sound and light alarms or mobile notifications, and provide real-time monitoring and response suggestions.

Images