Intelligent regulation and control method and system for food processing production line

Abstract

The invention relates to an intelligent regulation and control method and system for a food processing production line, and belongs to the technical field of food processing automatic control. Formula description information and monitoring instructions are automatically obtained and processed through a PLC control system, production automation is achieved, the system carries out segmented processing according to the processing time period described by a formula, determines processing parameter set values, calculates the process similarity between different products and carries out grouping, further, the processing time period is divided into flavor sub-stages, and the flavor sub-stages are divided into flavor sub-stages. A three-dimensional parameter group is established to finely regulate and control the flavor forming process, meanwhile, an edge calculation terminal is installed to be connected with all devices, the remaining processing time is analyzed in real time, a production sequence is dynamically adjusted based on a priority queue, the production efficiency is improved, the deviation value and the change rate of processing adjustable parameters are calculated, abnormal devices are determined and fed back for maintenance, and stable production is ensured. Manual intervention is reduced, the production automation and intelligence level is improved, and fine control and efficient production are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to an intelligent control method and system for a food processing production line, and belongs to the technical field of food processing automatic control. BACKGROUND

[0002] In the field of food processing automatic control technology, the process control of traditional marinated food processing production lines has long relied on manual operation mode. Specifically, the workshop operators need to check the processing parameters such as temperature and time of each steam boiler in real time, and manually control the processing of marinated food based on personal experience to control the flavor of the product. The core of this traditional control method is to maintain the stability of the processing parameters through manual intervention, but it has exposed many technical defects in actual production.

[0003] From the perspective of product quality control, the existing technology highly depends on manual experience, which leads to significant differences in key indicators such as softness and flavor of the same batch of food in the same workshop. For example, the deviation of manual temperature threshold judgment or the delay of time control will directly affect the Maillard reaction process and the efficiency of spice penetration, and thus cause insufficient flavor consistency. This quality fluctuation is caused by the fact that manual operation cannot accurately reproduce standardized process parameters, making it difficult to control the quality of finished products.

[0004] In terms of production efficiency and cost, the traditional manual control mode has obvious shortcomings. On the one hand, the process of manually monitoring and adjusting the parameters of each boiler is time-consuming and labor-intensive, making it difficult to achieve efficient management of multiple devices in parallel, resulting in limited overall production capacity of the production line. On the other hand, the continuous investment in labor costs and the rework loss caused by unstable quality further increases production costs. SUMMARY

[0005] The present application provides an intelligent control method and system for a food processing production line to solve the problems of process stability defects and production efficiency bottlenecks in the prior art.

[0006] The present application provides an intelligent control method and system for a food processing production line, which includes the following steps: S101: Obtain the recipe description information and monitoring instructions through the PLC control system and analyze and process them; S102: Process according to the processing time period described in the recipe, determine the processing parameter set value, calculate the process similarity between different products, group the products according to the similarity, split each processing time period into flavor sub-stages according to the flavor formation rule, and establish a three-dimensional parameter group to realize fine control of multiple key factors in the flavor formation process; S103: Install the edge computing terminal and connect the PLC control system, steam boiler sensor, exhaust fan, and order management system, and analyze the remaining processing time of each boiler in the PLC control system; S104: Dynamic production sequence adjustment based on priority queue, generate task queue according to real-time order and equipment state according to priority rules; S105: Obtain processing adjustable parameters based on processing time period, calculate deviation value and deviation change rate, determine abnormal steam boiler and abnormal processing data, control steam boiler state and feedback maintenance according to abnormal level and quantity threshold.

[0007] Preferably, the recipe description information and monitoring instructions are obtained through the server in step S101 to avoid errors in manual production process due to recipe memory; In step S102, the processing time period is segmented according to the recipe description, the parameter description sentence containing numbers is identified through the product process similarity grouping model, and the key processing parameter setting value is determined, including temperature parameter, time parameter, pressure parameter, and steam proportional valve parameter.

[0008] In step S102, the process similarity between different products is calculated by the inverse distance method, each parameter in the processing parameter setting value is assigned a weight, the initial similarity threshold is set by establishing an expert experience model, and the products are grouped according to the similarity.

[0009] When a new product is added, its average similarity with all existing groups is calculated, the similarity between the new product and each product in the group is calculated one by one, and the average value of the similarity of all products in the group is taken as the matching degree of the new product and the group.

[0010] In step S104, the order management system extracts the process parameters of the new product that needs to be queued, the current production task priority, the expected delivery time, and other order attributes, the PLC control system generates a temporary processing parameter template, and synchronizes it to the control module of the corresponding boiler, sets the priority coefficient according to the difference between the delivery period and the current time, calculates the process matching degree of the new product and the products in the queue according to the product process similarity grouping model, and assigns the priority according to the remaining processing time of the steam boiler.

[0011] In step S105, when the processing adjustable parameter exceeds the corresponding threshold, it is automatically marked as a single parameter anomaly, and a maintenance work order is generated for processing by the feedback maintenance personnel.

[0012] The three-dimensional parameter set includes a temperature parameter set, a pressure parameter set and a flavor stratification parameter set, a servo motor driven spice injection pump is installed on the cooking pot, a flow sensor is integrated, and communication is performed with a PLC control system, a three-dimensional parameter influence weight matrix is constructed, a basic weight is defined according to an expert experience model, the weight is corrected through regression analysis of historical production data, a Pearson correlation coefficient is calculated to adjust the weight value, a flavor parameter weight is defined according to a basic weight of an expert experience model, and initial similarity threshold values are set for each group through the expert experience model, and similar flavor characteristic vectors are grouped.

[0013] A three-dimensional fuzzy control model is constructed, a basic rule is defined according to an expert experience model, rules are supplemented through correlation analysis of historical production data, corresponding adjustment rules are generated, an edge computing terminal generates a spice injection timing table, receives an output of the three-dimensional fuzzy control model, and generates a plurality of parameter adjustment instructions executable by the PLC, and the PLC control system is interacted with data.

[0014] Real-time monitoring is performed on the steam pressure in the cooking pot and the workshop environment pressure, based on real-time data such as pressure fluctuation amplitude, the PLC control system sends a speed adjustment instruction to a variable frequency driver of an exhaust fan, so as to maintain the pressure in the cooking pot within a set range, a BP neural network model is established, historical production data is used to predict the soft and tender degree of the product, an optimal pressure fluctuation range is calculated, and the pressure setting parameters of the corresponding cooking pot are updated through the PLC control system.

[0015] An intelligent regulation and control system of a food processing production line comprises: A PLC control system: responsible for obtaining a formula and an instruction, processing processing data, generating a control parameter, adjusting a production sequence, linkage equipment control and abnormality detection; An edge computing terminal: a field data processing unit, which collects a cooking pot parameter in real time, analyzes a flavor parameter, executes linkage control and optimizes pressure data; A data acquisition and sensor module: which collects temperature and steam pressure data in real time, and provides feedback for the PLC control; An actuator module: which controls a steam proportional valve, an exhaust fan and a spice injection pump according to a PLC instruction; A management and communication module: which manages a formula and an instruction, uploads to the PLC and stores a formula library, generates a production task queue according to a priority and a process similarity, uploads basic data and processing progress, and supports data integration; An algorithm and model module: which standardizes parameters, calculates a similarity, realizes dynamic grouping of products, optimizes pressure data, predicts product quality and backstepping process parameters, quantifies parameter influence weights, and realizes multi-parameter collaborative adjustment; An abnormality detection and feedback module: which monitors a parameter threshold value, automatically generates a maintenance work order and feeds back.

[0016] The beneficial effects of the application are: The application provides an intelligent control method and system for a food processing production line, which can match and control different product process characteristics through a product process similarity grouping model and dynamic production sequence adjustment, realize combined production of similar process products, help reduce parameter reset times and parameter adjustment costs during switching, improve the flexibility and adaptability of the production line, split each processing time period into flavor sub-stages according to flavor formation rules, and establish a three-dimensional parameter group to realize fine control of multiple key factors in the flavor formation process, help improve the stability and consistency of product flavor, meet the needs of consumers for high-quality food, monitor the internal steam pressure of the cooking pot and the workshop environment pressure in real time, based on real-time data such as pressure fluctuation amplitude, the PLC control system sends a speed adjustment instruction to the exhaust fan frequency converter to maintain the internal pressure of the cooking pot within the set range, which helps reduce the impact of pressure fluctuations on product quality and improve the overall quality of the product, and through the establishment of a BP neural network model and other machine learning algorithms, historical production data is used to predict the soft and rotten degree of the product, and the optimal pressure fluctuation range and other process parameters are calculated, which helps optimize and adjust according to the needs of different products and improves the flexibility and adaptability of the process. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 FIG. 1 is a flowchart of an intelligent control method and system for a food processing production line according to the present application; Figure 2 FIG. 2 is a structural diagram of an intelligent control method and system for a food processing production line according to the present application. DETAILED DESCRIPTION

[0018] The preferred embodiments of the application will be described in detail below with reference to the accompanying drawings.

[0019] In Example 1, as shown in the drawings, the application provides an intelligent control method for a food processing production line, which includes: Figure 1 S101: Obtain the formula description information and monitoring instructions uploaded by the workshop management system through the PLC control system, determine the processing monitoring system state based on the monitoring instructions, obtain the basic data uploaded by the workshop operation terminal, receive the current processing data uploaded by the cooking workshop system, and perform analysis and processing; Specifically, the PLC control system communicates with the workshop management system, obtains the formula description information and monitoring instructions, such as the processing formula parameters of the product and the processing stage start-stop signal, through the server, to avoid production quality problems caused by formula memory errors during manual production.

[0020] ​S102: According to the processing time period described in the formula, the formula parameter description is divided into sentences according to the preset sentence length, the product process similarity grouping model is established, the parameter description sentence containing numbers is extracted, and the processing parameter setting value is determined combined with the context; Specifically, according to the processing time period described in the formula, such as preheating section, cooking section, holding section, product process similarity grouping model identifies parameter description sentence containing numbers, determines key processing parameter setting value, processing parameter setting value includes temperature parameter, time parameter, pressure parameter, steam proportional valve parameter, wherein temperature parameter includes target temperature of each processing stage, temperature fluctuation range, time parameter includes total food processing time, duration of each stage, pressure parameter includes steam pressure range, exhaust pressure threshold, steam proportional valve parameter includes valve opening range of each stage; The actual value of the parameter in different units is subtracted from the historical minimum value, and then divided by the difference between the historical maximum value and the minimum value, so that the parameters in different units are scaled to the interval of 0 to 1, so as to be in the same dimension for comparison; The process similarity between different products is calculated by the inverse distance method: first, calculate the difference value of the same parameter in each different product, square the difference value and add it, then take the square root of the sum to get the total distance, and the similarity is 1 divided by (1+total distance), so the smaller the distance, the higher the similarity.

[0021] Each parameter in the processing parameter setting value is assigned a weight, an initial similarity threshold is set by establishing an expert experience model, products are grouped according to similarity, and the similarity threshold is adjusted according to historical grouping data. When a new product is added, calculate its average similarity with all existing groups, calculate the similarity between the new product and each product in the group one by one, take the average of all product similarities in the group as the matching degree of the new product and the group, if it is greater than the similarity threshold, it is assigned to the group; Otherwise, a new process group is created.

[0022] S103: Install edge computing terminal in cooking workshop, connect PLC control system, steam cooking pot sensor, exhaust fan and order management system, deploy edge computing node to realize real-time data acquisition and processing; Specifically, read the temperature data and steam pressure data of each cooking pot, get the current opening of the steam proportional valve, the speed of the exhaust fan, and analyze the remaining processing time of each cooking pot in the PLC control system; Extract the new product process parameters needed to queue, current production task priority, expected delivery time and other order attributes through the order management system, PLC control system generates temporary processing parameter template, and synchronizes to the corresponding cooking pot control module.

[0023] S104: Dynamic production sequence adjustment based on priority queue, generate task queue according to real-time order and equipment state according to priority rule; Specifically, the priority coefficient is set according to the difference between the delivery period and the current time, the process matching degree of the new product and the products in the queue is calculated according to the product process grouping model, the remaining processing time, the current temperature / pressure, and the steam proportional valve opening of each steam digester are read in real time through the PLC control system, the priority is distributed according to the remaining processing time of the steam digester, the process group attribution and similarity data of the products in the current queue are obtained from the edge node cache, the process similarity of the new product and all products to be produced in the queue is calculated, the task position of the same group or similar group is found, if there is a product in the same group, the new product is inserted at the end of the group task, otherwise, the new product is inserted at the corresponding position according to the priority calculation result. The order management system arranges the orders in descending order of urgency according to the delivery period, and arranges the remaining orders in descending order of process similarity, and for tasks with the same priority, the remaining time of the equipment is arranged from short to long.

[0024] S105: Based on the processing time period, obtain the processing adjustable parameters, calculate the deviation value and the deviation change rate, determine the input and output values according to the deviation sign, compare the current processing data of each steam digester, determine the abnormal steam digester and abnormal processing data, and control the steam digester state and feedback maintenance according to the abnormal level and quantity threshold. Specifically, the processing adjustable parameters of this stage are extracted from the PLC control system based on the current processing time period, including temperature parameters, pressure parameters, processing time, and steam proportional valve opening. The real-time collected data is filtered and denoised to eliminate sensor fluctuation interference, and the parameter time sequence is generated. The processing adjustable parameter threshold is established according to the historical production data and the expert experience model. When the processing adjustable parameter exceeds the corresponding threshold, it is marked as a single-parameter abnormality, and a maintenance work order is automatically generated, including abnormal parameter log and occurrence time, which is processed by the feedback maintenance personnel.

[0025] In use, the PLC control system communicates with the plant management system, obtains formula description information and monitoring instructions through a server, avoids production quality problems caused by formula memory errors in manual production processes, segments processing time periods according to formula descriptions, identifies parameter description sentences containing numbers through a product process similarity grouping model, determines key processing parameter set values, the processing parameter set values include temperature parameters, time parameters, pressure parameters and steam proportional valve parameters, the temperature parameters include target temperatures and temperature fluctuation ranges of various processing stages, the time parameters include total food processing time and stage duration times, the pressure parameters include steam pressure ranges and exhaust pressure thresholds, and the steam proportional valve parameters include valve opening range ranges of various stages, different unit parameters are uniformly scaled into a 0-1 interval, so as to be in the same dimension for comparison, process similarity between different products is calculated through a distance inverse ratio method, each parameter in the processing parameter set value is assigned a value, weights are assigned, an initial similarity threshold value is set through an expert experience model, products are grouped according to similarity, and the similarity threshold value is adjusted according to subsequent historical grouping data, when a new product is added, average similarity between the new product and all existing groups is calculated, similarity between the new product and each product in the group is calculated one by one, an average value of similarity of all products in the group is taken as matching degree between the new product and the group, and if the matching degree is greater than the similarity threshold value, the new product is classified into the group.Otherwise, a new process group is created, and the temperature data and steam pressure data of each cooking pot are read in real time. The current opening of the steam proportional valve and the exhaust fan speed are obtained, and the remaining processing time of each cooking pot in the PLC control system is analyzed. The process parameters of the new product that needs to be queued, as well as the current production task priority, estimated delivery time and other order attributes are extracted through the order management system. The PLC control system generates a temporary processing parameter template and synchronizes it to the control module of the corresponding cooking pot. The priority coefficient is set according to the difference between the delivery date and the current time. The process matching degree between the new product and the products in the queue is calculated based on the product process similarity grouping model. The remaining processing time, current temperature / pressure, and steam proportional valve opening of each steam cooking pot are read in real time through the PLC control system. Priority is assigned according to the remaining processing time of the steam cooking pot. The process group affiliation and similarity data of the products in the current queue are obtained from the edge node cache, and the matching degree between the new product and all products to be produced in the queue is calculated. Process similarity identifies the location of tasks within the same or similar groups. If products within the same group exist, they are inserted at the end of the group. Otherwise, they are inserted at the corresponding location based on the priority calculation result. The order management system sorts tasks by delivery date in descending order of urgency. The remaining orders are sorted by process similarity from high to low. Tasks of the same priority are assigned from shortest to longest remaining time on the equipment. This allows for matching similar processing techniques to products in small batches of multiple varieties of braised food, allowing similar process products to be produced together, reducing the number of parameter resets and the cost of parameter adjustments during switching. Temperature parameters, pressure parameters, processing time, and steam proportional valve opening are collected in real time. Adjustable processing parameter thresholds are established based on historical production data and expert experience models. When an adjustable processing parameter exceeds the corresponding threshold, it is marked as a single parameter anomaly and a maintenance work order is automatically generated, including the abnormal parameter log and the time of occurrence. The work order is then processed and completed through feedback to maintenance personnel.

[0026] Compared with the existing design, the recipe description information and monitoring instructions uploaded by the workshop management system are automatically acquired and processed by the PLC control system, reducing manual intervention and improving the automation and intelligence level of the production line. The production quality problems caused by formula memory errors in the manual production process are avoided, the accuracy and consistency of the formula are ensured through automatic processing, the processing time period described in the formula is processed in sections, and a product process similarity grouping model is established, so that the key processing parameter setting value can be accurately controlled. The edge computing terminal is installed on the site of the cooking workshop to realize real-time data acquisition and processing, improve the timeliness and accuracy of data processing, and dynamically adjust the production sequence based on the priority queue. The production task can be flexibly adjusted according to the real-time order and equipment state, and the production efficiency is improved. When the adjustable parameter exceeds the corresponding threshold value, it is automatically marked as a single parameter exception, and a maintenance work order is generated for processing by the feedback maintenance personnel to ensure the stable operation of the production line. Through the product process similarity grouping model and dynamic production sequence adjustment, different product process characteristics can be matched and regulated, the combined production of similar process products can be realized, and the production demand of small batch and multi-species can be met.

[0027] In example 2, the product process similarity grouping model and dynamic production sequence adjustment in example 1 can be matched and regulated according to the process characteristics of different products to realize the combined production of similar process products. This embodiment is further improved on the basis of the above-mentioned embodiments.

[0028] This embodiment also includes: splitting each processing time period into flavor sub-stages according to flavor formation rules, each sub-stage corresponding to a specific flavor substance generation interval (such as a Maillard reaction section, a spice penetration section), establishing a three-dimensional parameter group for each sub-stage, the three-dimensional parameter group including a temperature parameter group, a pressure parameter group, and a flavor layering parameter group, the temperature parameter group including a target temperature, a temperature fluctuation threshold, and a temperature rise and fall rate, the temperature fluctuation threshold being adjusted according to the process stage, and the temperature rise and fall rate being used to control the flavor substance generation rate, the pressure parameter group including a steam pressure interval, an exhaust pressure threshold, and a pressure maintenance time, wherein the steam pressure interval is used to control the water activity and the spice diffusion efficiency to accelerate the penetration of spice molecules into the food interior, the exhaust pressure threshold is used to trigger exhaust to control the oxidative atmosphere in the pot to avoid the oxidation of unsaturated fatty acids to produce rancid taste, and the pressure fluctuation is used to promote the formation of pore structure to provide more sites for spice adsorption, and the pressure maintenance time is used to ensure sufficient flavor substance polymerization reaction, and the flavor layering parameter group includes a batch, a single batch size, a time point, and a rate, wherein the batch is divided into front, middle, and rear sections according to the flavor release characteristics, the rate includes uniform or gradient feeding to match the adsorption rate at different depths in the food; A three-dimensional parameter influence weight matrix is constructed, and the rows and columns correspond to the influence weights of temperature, pressure, and spices, respectively. The basic weights are defined according to an expert experience model, the weights are corrected through regression analysis of historical production data, and the Pearson correlation coefficient is calculated to adjust the weight values. The flavor hierarchical parameter group is converted into a calculable 10-dimensional feature vector, which specifically includes the number of batches, the time points of each batch, the amount of each batch, the characteristic values of the injection rate curve, and the proportion of spice components. The flavor parameter weight is added to the original distance inverse method calculation to calculate the flavor feature vector of different products. The flavor parameter weight is defined by an expert experience model to define the basic weight. The initial grouping is generated by K-means clustering of the flavor feature vector of the first batch of products. The initial similarity threshold of each group is set by an expert experience model. The gradient descent algorithm is run once every 24 hours to optimize the flavor parameter weight in the distance inverse method calculation. A servo motor driven spice injection pump and an integrated flow sensor are installed in the cooking pot, which communicates with the PLC control system through a communication protocol and transmits the flow and cumulative injection amount in real time. A three-dimensional fuzzy control model is constructed, in which the input variables are temperature deviation (actual temperature-set temperature), pressure deviation (actual pressure-set pressure), and spice deviation (actual injection amount-set injection amount), and the output variables are temperature adjustment amount, pressure adjustment amount, and spice adjustment amount. Each variable defines 7 fuzzy sets, including negative large, negative medium, negative small, zero, positive small, positive medium, and positive large. The membership function adopts a triangular membership function to calculate the membership degree of the real-time deviation value in each fuzzy set. The basic rules are defined by an expert experience model, and the rules are supplemented through correlation analysis of historical production data to generate corresponding adjustment rules. When multiple rules are triggered, the rule with the maximum membership degree product is executed first. The output of the three-dimensional fuzzy control model is transmitted to the PLC control system through the ModbusTCP protocol. Based on the parameter collaborative adjustment of the fuzzy control, the requirements of industrial batch production are met. The flavor parameter analyzer and the linkage control processor are built-in in the edge computing terminal. The flavor parameter analyzer analyzes the flavor hierarchical parameter group in the formula in real time to generate a spice injection timing table. The linkage control processor receives the output of the three-dimensional fuzzy control model to generate multi-parameter adjustment instructions executable by the PLC, which interacts with the PLC control system.

[0029] Specific in use, by installing a servo motor driven spice injection pump and integrated flow sensor in the cooking pot, communicating with the PLC control system through the communication protocol, real-time transmission of flow, cumulative injection volume, each processing time period is divided into flavor sub-stage according to the flavor forming rule, a three-dimensional parameter group is established according to each sub-stage, the three-dimensional parameter group includes temperature parameter group, pressure parameter group, flavor layering parameter group, through the synergistic mechanism of "temperature control reaction, pressure regulation diffusion, spice construction hierarchy", the technical upgrade from "single parameter control" to "multi-physical-chemical field coupling regulation" is constructed, the three-dimensional parameter influence weight matrix is constructed, the basic weight is defined according to the expert experience model, the weight is corrected through the regression analysis of historical production data, the Pearson correlation coefficient is calculated to adjust the weight value, the flavor parameter weight is added to the original distance inverse method calculation to calculate the different product flavor feature vector, the flavor parameter weight is defined by the expert experience model to define the basic weight, the initial similarity threshold is set for each group through the expert experience model, the similar flavor feature vector is grouped, the gradient descent algorithm is run once every 24 hours, the flavor parameter weight parameter in the distance inverse method calculation is optimized, the three-dimensional fuzzy control model is constructed, the basic rule is defined through the expert experience model, the rule is supplemented through the correlation analysis of historical production data, the corresponding adjustment rule is generated, when multiple rules are triggered, the rule is executed according to the "membership degree product maximum priority" principle, the three-dimensional fuzzy control model output is transmitted to the PLC control system through the ModbusTCP protocol, the edge computing terminal is built-in flavor parameter analyzer, linkage control processor, the flavor parameter analyzer analyzes the flavor layering parameter group in the formula in real time, generates the spice delivery timing table, the linkage control processor receives the three-dimensional fuzzy control model output, generates the multi-parameter adjustment instruction executable by PLC, and interacts with the PLC control system.

[0030] Compared with the existing design, by splitting the processing time period into flavor sub-stages according to the flavor formation rule, each sub-stage corresponds to a specific flavor substance generation interval (such as a Maillard reaction section, a spice penetration section), so that the generation of flavor substances can be more accurately controlled. By establishing a three-dimensional parameter group of temperature parameter group, pressure parameter group, and flavor layering parameter group, fine regulation of multiple key factors in the flavor formation process is realized, which helps to improve the stability and consistency of product flavor. The use of steam pressure interval control of water activity and spice diffusion efficiency accelerates the penetration of spice molecules into the food interior. At the same time, by controlling the exhaust pressure threshold to control the oxidative atmosphere in the pot, the oxidation of unsaturated fatty acids to produce rancid taste is avoided, and the formation of pore structure is promoted by pressure fluctuation to provide more sites for spice adsorption. Through fine regulation of the batch, single feeding amount, feeding time point, and feeding rate, the adsorption rate at different depths in the food is matched to realize uniform distribution and efficient aggregation of flavor substances. A three-dimensional fuzzy control model is constructed to calculate the membership degree through real-time deviation value and generate corresponding adjustment rules to realize the coordinated adjustment of temperature, pressure, and spice feeding amount, improve production efficiency and product quality stability, construct a three-dimensional parameter influence weight matrix, define the basic weight according to the expert experience model, and correct the weight through regression analysis of historical production data. Calculate the Pearson correlation coefficient to adjust the weight value and realize the continuous optimization of parameters. Through K-means clustering to generate initial grouping and gradient descent algorithm to optimize flavor parameter weight parameters, accurate grouping and continuous improvement of product flavor are realized. The edge computing terminal is built-in flavor parameter analyzer and linkage control processor, which can real-time analyze the flavor layering parameter group in the formula, generate spice feeding time sequence table, and receive three-dimensional fuzzy control model output to generate PLC executable multi-parameter adjustment instructions, realize real-time monitoring and accurate regulation of the production process.

[0031] In example 3, the flavor layering process is decomposed into multi-parameter coordinated instructions by reconstructing the formula data structure in example 2, so that the PLC control system can simultaneously process the coupling relationship of temperature, pressure, spice and other variables. This embodiment is further improved based on the above-mentioned embodiments.

[0032] In this embodiment, high-precision absolute pressure sensors are installed on the top or side of the inner wall of each steam digester at a vertical height of 1 / 3, connected to the analog input module of the edge computing terminal through waterproof cables, to collect steam pressure data inside the digester in real time. A gauge pressure sensor is installed outside the exhaust fan outlet and connected to the edge computing terminal to collect the ambient pressure reference value of the workshop. The edge computing terminal reads the data of the first and second pressure sensors at a cycle of 500 ms, synchronously obtains the steam pressure set interval of the corresponding digester in the PLC control system, establishes a single-digester pressure data set based on the digester identification number, applies the Kalman filtering algorithm to the collected pressure data, predicts the pressure change trend by establishing a state space model, corrects the error by combining the measured value, eliminates the high-frequency noise of the sensor, obtains the pressure fluctuation amplitude by calculating the maximum value of the absolute value of (real-time pressure value-set interval lower limit) and (set interval upper limit-real-time pressure value), and the PLC control system reads the current opening of the steam proportional valve, the actual pressure inside the steam digester, and the pressure set interval in real time. According to the linkage trigger condition, the steam valve opening is greater than the threshold value set by the expert experience model to start the linkage control, and the PLC control system sends the speed regulation instruction to the exhaust fan frequency converter through the Modbus TCP protocol. The pressure fluctuation amplitude, cooking time, and halogen soft and tender detection value are collected, a BP neural network model is established based on the historical production data of the pressure fluctuation amplitude, cooking time, and halogen soft and tender detection value, the input is the mean value of the fluctuation amplitude in the single-digester pressure data set and the set interval maintenance time, and the output is the halogen soft and tender prediction value. The edge computing terminal retrieves the historical pressure data of the same group of products from the process similarity grouping model, calculates the optimal pressure fluctuation interval, updates the pressure set parameters of the corresponding digester through the PLC control system, and synchronously updates the formula library of the workshop management system.

[0033] In use, the edge computing terminal collects the steam pressure data inside the digester through the absolute pressure sensor, collects the ambient pressure reference value of the workshop through the gauge pressure sensor, synchronously obtains the steam pressure set interval of the corresponding digester in the PLC control system to establish a single-digester pressure data set, calculates the pressure fluctuation amplitude, starts the linkage control according to the linkage trigger condition, sends the speed regulation instruction to the exhaust fan frequency converter when the pressure fluctuation amplitude is greater than the set threshold value, establishes a BP neural network model with the input being the mean value of the fluctuation amplitude in the single-digester pressure data set and the set interval maintenance time and the output being the halogen soft and tender prediction value, calculates the optimal pressure fluctuation interval by the edge computing terminal, updates the pressure set parameters of the corresponding digester through the PLC control system, and synchronously updates the formula library of the workshop management system.

[0034] Compared with the prior art, by installing a high-precision absolute pressure sensor at the top or side of the inner wall of each steam boiler at a vertical height of 1 / 3 and installing a gauge pressure sensor outside the air outlet of the exhaust fan, real-time monitoring of the steam pressure in the boiler and the workshop environment pressure is realized, so that the control system can make a quick response according to the real-time pressure condition, optimize the process parameters, and based on the real-time data such as pressure fluctuation amplitude, the PLC control system starts the linkage control and sends the speed regulation instruction to the exhaust fan frequency converter to maintain the pressure in the boiler within the set range, reduces the manual intervention, improves the automation level, and also ensures the stability of the production process and the consistency of the product quality. By establishing a BP neural network model, the historical production data are used to predict the soft and tender degree of the product, the edge computing terminal retrieves the historical pressure data of the same group of products from the process similarity grouping model, calculates the optimal pressure fluctuation range, and updates the pressure setting parameters of the corresponding boiler through the PLC control system, so that the process is more flexible and adaptable, and can be optimized and adjusted according to the requirements of different products.

[0035] As shown in Figure 2 Embodiment 4, the present application provides an intelligent regulation and control system of a food processing production line, comprising: The PLC control system: acquires the formula parameters and monitoring instructions of the workshop management system through the server, avoids manual memory errors, analyzes the processing parameters in the formula to generate a temporary processing template and synchronizes it to the boiler control module, dynamically adjusts the task queue based on the order priority and device state, supports new product insertion, sends adjustment instructions to devices such as exhaust fans and steam proportional valves, realizes pressure and temperature coordinated control, compares real-time processing data with threshold values, marks abnormal parameters and generates maintenance work orders; The edge computing terminal: reads the data such as boiler temperature, steam pressure and valve opening, analyzes the remaining processing time in the PLC, disassembles the flavor layering parameters in the formula, generates a spice feeding time sequence table, receives adjustment instructions output by the three-dimensional fuzzy control model, converts them into PLC executable control signals, applies Kalman filtering to the collected pressure data to eliminate noise and predict trends, and calculates the optimal pressure fluctuation range; The data acquisition and sensor module: acquires real-time temperature and steam pressure data to provide feedback for PLC control, acquires real-time absolute pressure in the boiler for calculating pressure fluctuation amplitude and linkage control, acquires the workshop environment pressure reference value for correcting the boiler pressure data to ensure measurement accuracy, and transmits real-time spice flow and cumulative injection amount to realize precise feeding in linkage with the PLC control system; The actuator module: adjusts the opening according to the PLC instructions to maintain the target temperature and pressure range of each processing stage, controls the pressure and oxidative atmosphere in the boiler, injects spices according to the time sequence of the flavor layering parameter group to match the food adsorption rate and realize uniform flavor distribution; Management and communication module: upload recipe description information and monitoring instructions, store recipe library and synchronize to PLC control system, extract order attributes, sort by urgency and process similarity, generate dynamic task queue, upload production basic data, assist PLC control system to complete data integration; Algorithm and model module: realize product clustering grouping based on process parameters, perform multi-dimensional precise control of flavor formation, quantify the influence degree of temperature, pressure and spices on flavor, and perform intelligent adjustment of multi-parameter deviation; Abnormality detection and feedback module: compare real-time parameters with historical threshold values, mark single-parameter abnormalities and automatically generate maintenance work orders.

[0036] The above describes the present application and its embodiments, which are not restrictive, and the drawings only show one of the embodiments of the present application, and the actual structure is not limited thereto. In summary, if a person skilled in the art is inspired thereby, without departing from the purpose of the present application, without creating a similar structure and embodiment of the technical solution, which should belong to the protection scope of the present application.

Claims

1. An intelligent control method for a food processing production line, characterized in that: The following steps are involved: S101: Obtain recipe description information and monitoring instructions through the PLC control system and perform analysis and processing; S102: Segment processing according to the processing time period described in the recipe, determine the processing parameter setting values, calculate the process similarity between different products, group the products according to the similarity, split each processing time period into flavor sub-stages according to the flavor formation rules, and establish a three-dimensional parameter group to achieve fine-grained control of multiple key factors in the flavor formation process; S103: Install the edge computing terminal and connect it to the PLC control system, steam boiler sensor, exhaust fan, and order management system to analyze the remaining processing time of each boiler in the PLC control system; S104: Dynamic production sequence adjustment based on priority queue, generating task queue according to priority rules based on real-time orders and equipment status; S105: Obtaining processing adjustable parameters based on the processing time period, calculating the deviation value and the deviation change rate, determining abnormal steam boilers and abnormal processing data, controlling the steam boiler status according to the abnormal level and quantity threshold, and providing feedback for maintenance.

2. The intelligent control method for a food processing production line according to claim 1, characterized in that: In step S101, the recipe description information and monitoring instructions are obtained through the server to avoid recipe memory errors during manual production; In step S102, the process is segmented according to the processing time period described in the recipe, and the parameter description sentences containing numbers are identified through the product process similarity grouping model to determine the key process parameter setting values. The process parameter setting values ​​include temperature parameters, time parameters, pressure parameters, and steam proportional valve parameters.

3. The intelligent control method for a food processing production line according to claim 1, characterized in that: In step S102, the process similarity between different products is calculated by the inverse distance method, each parameter in the processing parameter setting value is assigned a value and a weight is allocated, an initial similarity threshold is set by establishing an expert experience model, and the products are grouped according to the similarity.

4. The intelligent control method for a food processing production line according to claim 3, characterized in that: When a new product is added, its average similarity with all existing groups is calculated. The similarity between the new product and each product in the group is calculated one by one. The average similarity of all products in the group is taken as the matching degree between the new product and the group.

5. The intelligent control method for a food processing production line according to claim 1, characterized in that: In step S104, the order management system extracts the process parameters of the new product that needs to be queued, as well as order attributes such as the current production task priority and the estimated delivery time. The PLC control system generates a temporary processing parameter template and synchronizes it to the control module of the corresponding steam boiler. The priority coefficient is set according to the difference between the delivery date and the current time. The process matching degree between the new product and the products in the queue is calculated based on the product process similarity grouping model, and the priority is assigned according to the remaining processing time of the steam boiler.

6. The intelligent control method for a food processing production line according to claim 1, characterized in that: When the machining adjustable parameter exceeds the corresponding threshold in step S105, it is automatically marked as a single parameter abnormality, and a maintenance work order is generated and processed by feedback maintenance personnel.

7. The intelligent control method for a food processing production line according to claim 1, characterized in that: The three-dimensional parameter group includes a temperature parameter group, a pressure parameter group, and a flavor layering parameter group. A servo motor is installed in the cooking pot to drive a spice injection pump and an integrated flow sensor, and the cooking pot communicates with a PLC control system. A three-dimensional parameter influence weight matrix is ​​constructed, and a basic weight is defined according to an expert experience model. The weight is corrected through regression analysis of historical production data, and the Pearson correlation coefficient is calculated to adjust the weight value. The flavor parameter weight is defined by the expert experience model. An initial similarity threshold is set for each group through the expert experience model, and similar flavor feature vectors are grouped.

8. The intelligent control method for a food processing production line according to claim 7, characterized in that: Construct a three-dimensional fuzzy control model, define basic rules through expert experience model, supplement rules through correlation analysis of historical production data, generate corresponding adjustment rules, and the edge computing terminal generates a spice delivery schedule, receives the output of the three-dimensional fuzzy control model, and generates PLC-executable multi-parameter adjustment instructions to interact with the PLC control system.

9. The intelligent control method for a food processing production line according to claim 1, characterized in that: The steam pressure inside the cooking pot and the workshop environment pressure are monitored in real time. Based on real-time data such as the pressure fluctuation amplitude, the PLC control system sends speed adjustment instructions to the exhaust fan inverter to maintain the internal pressure of the cooking pot within the set range. A BP neural network model is established, and the softness of braised food is predicted using historical production data. The optimal pressure fluctuation range is calculated, and the pressure setting parameters of the corresponding cooking pot are updated through the PLC control system.

10. An intelligent control system for a food processing production line, characterized in that: include: PLC control system: responsible for obtaining recipes and instructions, processing processing data, generating control parameters, adjusting production sequences, linking equipment control and abnormality detection; Edge computing terminal: On-site data processing unit, real-time collection of cooking parameters, analysis of flavor parameters, execution of linkage control, and optimization of pressure data; Data acquisition and sensor module: collects temperature and steam pressure data in real time and provides feedback for PLC control; Actuator module: controls the steam proportional valve, exhaust fan, and spice injection pump according to PLC instructions; Management and communication module: manage recipes and instructions, upload them to the PLC and store the recipe library, generate production task queues based on priority and process similarity, upload basic data and processing progress, and support data integration; Algorithm and model module: standardize parameters and calculate similarity, realize dynamic product grouping, optimize pressure data, predict product quality and reverse engineer process parameters, quantify parameter influence weights, and realize multi-parameter coordinated adjustment; Abnormal detection and feedback module: monitors parameter thresholds, automatically generates maintenance work orders and provides feedback.

Images