Fine dried noodle production whole process intelligent management system and method

Abstract

The invention relates to the technical field of food production management, in particular to a full-flow intelligent management system and method for fine dried noodle production, and the system comprises an energy consumption management module which carries out the moving average calculation based on a production line energy consumption time sequence and technological parameters which are collected in real time in the operation of a fine dried noodle production line, and decomposing a fluctuation characteristic sequence and a continuous trend sequence of the current time period according to a moving average result, and generating energy consumption fluctuation data of the fine dried noodle production line. According to the method, through multi-stage data acquisition and processing and calculation of time-sharing moving average and energy consumption fluctuation characteristic decomposition, accurate fluctuation characteristic and trend separation of the energy consumption time sequence can be realized. In energy consumption distribution, real-time analysis of stage energy consumption requirements is utilized, weight adjustment of multi-dimensional process parameters is combined, and rationalization of dynamic energy consumption distribution values is achieved. Through data classification and consistency score calculation, the difference identification capability of multiple batches of parameters is significantly improved, and a basis is provided for fluctuation positioning of parameters in each stage of a production line.

Description

Technical Field

[0001] The present invention relates to the technical field of food production management, and particularly to an intelligent management system and method for the whole process of noodle production. Background Art

[0002] The technical field of noodle production management includes intelligent, automated, and refined management technologies in the food production process. Its core content is to conduct real-time monitoring, data collection and processing, and optimized management of the entire food production process through information technology and automated equipment. This technical field focuses on improving production efficiency, reducing costs, and ensuring product quality, covering the whole process management from raw material management, production process control to finished product inspection and packaging.

[0003] Among them, the intelligent management system for the whole process of noodle production refers to a system for data management of the whole process of noodle production, which mainly covers multiple technical matters such as raw material input, production process control, and finished product warehousing. This system collects key data of each link in the production process through Internet of Things devices, and combines production process models and data processing means to complete real-time monitoring and management of each link of the production line.

[0004] In the management of the whole process of noodle production in the prior art, although key data can be collected through Internet of Things devices, the processing and analysis of the data are still relatively single. In terms of energy consumption management, the prior art lacks refined consideration of the energy consumption distribution logic in the production process, and fails to make dynamic adjustments according to the actual energy consumption requirements and process characteristics of the production stage, which may lead to excessive or insufficient energy consumption in some stages, increasing the possibility of energy waste. In the management of multi-batch data, the prior art lacks in-depth analysis of the fluctuations and consistencies of production parameters, and is limited to data monitoring, unable to quantify the differences between parameters, and it is difficult to quickly locate the key links of parameter fluctuations in production. In addition, the prior art lacks a systematic basis for guiding the adjustment of equipment operation parameters, and the adjustment range usually depends on empirical settings, making it difficult to meet the needs of dynamic changes in parameter ranges. These deficiencies will lead to low energy consumption efficiency, large fluctuations in production parameters, and a decline in the stability of equipment operation, thus restricting the intelligent management ability of the entire noodle production process. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent management system and method for the whole process of noodle production.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: The intelligent management system for the whole process of noodle production includes:

[0007] The energy consumption management module is based on the production line energy consumption time series and process parameters collected in real time during the operation of the dried noodle production line, and performs a moving average calculation. According to the moving average result, the fluctuation characteristic sequence and the continuous trend sequence of the current period are decomposed to generate the energy consumption fluctuation data of the dried noodle production line;

[0008] The energy consumption allocation optimization module is based on the energy consumption fluctuation data of the dried noodle production line, analyzes the energy consumption requirements of each stage of the dried noodle production line, calculates the energy consumption allocation value according to the process parameter weight corresponding to the stage, and dynamically adjusts the allocation weight to generate the energy consumption allocation data of the dried noodle production line;

[0009] The parameter consistency analysis module is based on the energy consumption allocation data of the dried noodle production line, extracts the parameter distribution characteristics of each stage after the energy consumption adjustment of the dried noodle production line, and locates the parameter fluctuation links by classifying multiple batches of parameters respectively to obtain the parameter fluctuation data of the dried noodle production line;

[0010] The production line optimization module obtains the parameter fluctuation data of the dried noodle production line, analyzes the parameter fluctuation range of each stage, and limits the upper and lower limit intervals of the parameter change of each stage with reference to the parameter fluctuation range to generate the dynamic adjustment management result of the dried noodle production line.

[0011] As a further solution of the present invention, the steps of performing the moving average calculation are specifically as follows:

[0012] Based on the production line energy consumption time series and process parameters collected in real time during the operation of the dried noodle production line, including the drying temperature, the cooling temperature, the tensile force detected by the tension sensor, and the running speed of the production line conveyor belt, the production line energy consumption data is integrated;

[0013] Based on the production line energy consumption data, the formula:

[0014]

[0015] Calculate the moving average value S of each type of production line energy consumption data corresponding to the time period t t , and obtain the moving average result;

[0016] where n is the moving window size, t is the current time point index, and x i represents the production line energy consumption data acquisition value at the i-th moment.

[0017] As a further solution of the present invention, the steps of obtaining the energy consumption fluctuation data of the dried noodle production line are specifically as follows:

[0018] Based on the moving average result, decompose and analyze the data of each stage, extract the fluctuation points and continuous change ranges of each stage, and generate the fluctuation characteristic sequence and the continuous trend sequence;

[0019] Based on the fluctuation feature sequence and the continuous trend sequence, through time-axis alignment and data classification and collation, the data of each stage is grouped and stored, the distribution of fluctuation points and the trend change values are recorded, and the energy consumption fluctuation data of the noodle production line is generated.

[0020] As a further solution of the present invention, the steps of calculating the energy consumption allocation value are specifically as follows:

[0021] Based on the energy consumption fluctuation data of the noodle production line, analyze the energy consumption requirements of each stage of the noodle production line, including the drying stage, the cooling stage, the stretching stage, and the conveying stage. Collate the energy consumption data of each stage according to time periods, and statistically analyze the energy consumption requirements to generate the energy consumption requirement data of the noodle production line;

[0022] Based on the energy consumption requirement data of the noodle production line, use the formula:

[0023]

[0024] Calculate the energy consumption allocation value E of stage j j ;

[0025] where W j is the process parameter weight of stage j, D j is the energy consumption requirement value of stage j, V j is the energy consumption fluctuation amplitude of stage j, and T j is the energy consumption stability time range of stage j.

[0026] As a further solution of the present invention, the steps of obtaining the energy consumption allocation data of the noodle production line are specifically as follows:

[0027] Based on the energy consumption allocation values of the drying stage, the cooling stage, the stretching stage, and the conveying stage, by real-time monitoring the parameters of temperature, tension, and speed of each stage, dynamically adjust the corresponding allocation weights in combination with production requirements, and update the allocation values of each stage to generate the dynamically adjusted energy consumption allocation;

[0028] Based on the dynamically adjusted energy consumption allocation, integrate the energy consumption allocation data of each stage according to the time axis, record the allocation weights, energy consumption comparison, and change rate, and generate the energy consumption allocation data of the noodle production line.

[0029] As a further solution of the present invention, the steps of obtaining the parameter fluctuation data of the noodle production line are specifically as follows:

[0030] Based on the energy consumption allocation data of the noodle production line, extract the temperature distribution in the drying stage, the temperature change in the cooling stage, the tension change in the stretching stage, and the conveyor belt speed change in the conveying stage after energy consumption adjustment, classify the multi-batch parameters, and generate the multi-batch parameter classification result of the noodle production line;

[0031] Based on the classification results of the parameters of multiple batches of the dried noodle production line, the formula:

[0032]

[0033] is used to calculate the parameter consistency score C of batch b in the target stage of the dried noodle production line b ;

[0034] where m is the number of samples of the current batch b, is the parameter value of sample a in batch b, is the average value of the parameters of batch b;

[0035] Based on the parameter consistency score, locate the parameter fluctuation links in each stage, analyze and identify the parameter fluctuation conditions, and obtain the parameter fluctuation data of the dried noodle production line.

[0036] As a further solution of the present invention, the steps for obtaining the dynamic adjustment management result of the dried noodle production line are specifically as follows:

[0037] Based on the parameter fluctuation data of the dried noodle production line, analyze the parameter fluctuation ranges in the drying stage, cooling stage, stretching stage and conveying stage, adjust and limit the upper and lower limit intervals of the parameter changes in each stage, and generate the adjusted parameter interval data;

[0038] Based on the adjusted parameter interval data, analyze the influence range of the parameter changes in each stage on the operation of the equipment, provide adjustment guidance for the production line equipment in each stage, and generate the dynamic adjustment management result of the dried noodle production line.

[0039] An intelligent management method for the whole process of dried noodle production, the intelligent management method for the whole process of dried noodle production is executed based on the above-mentioned intelligent management system for the whole process of dried noodle production, and includes the following steps:

[0040] S1: Based on the production line energy consumption time series and process parameters collected in real time during the operation of the dried noodle production line, use moving average calculation to decompose the energy consumption data, and generate the energy consumption fluctuation data of the dried noodle production line;

[0041] S2: Based on the energy consumption fluctuation data of the dried noodle production line, analyze the energy consumption demand of the dried noodle production line, calculate the energy consumption allocation value of each stage according to the process parameter weights, and dynamically adjust the allocation weights to generate the energy consumption allocation data of the dried noodle production line;

[0042] S3: Based on the energy consumption allocation data of the dried noodle production line, extract the parameter distribution characteristics of each stage after the energy consumption adjustment of the dried noodle production line, classify the parameters of multiple batches and locate the parameter fluctuation links to obtain the parameter fluctuation data of the dried noodle production line;

[0043] S4: Based on the parameter fluctuation data of the dried noodle production line, analyze the parameter fluctuation range in each stage, limit and adjust the upper and lower limit intervals of the parameters in each stage, and generate the dynamic adjustment management result of the dried noodle production line.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0045] In the present invention, through multi-stage data collection and processing, as well as the calculation of time-sharing moving average and energy consumption fluctuation feature decomposition, the accurate separation of fluctuation features and trends of the energy consumption time series can be achieved. In energy consumption allocation, by using the real-time analysis of stage energy consumption requirements and combining with the weight adjustment of multi-dimensional process parameters, the rationalization of the dynamic energy consumption allocation value is realized. Through the calculation of data classification and consistency score, the ability to identify differences in multi-batch parameters is significantly improved, providing a basis for the fluctuation positioning of parameters in each stage of the production line. In the optimization of production line parameters, by adopting the refined analysis of the parameter fluctuation range and adjusting and limiting the upper and lower limits of parameter changes, the stability of the parameter distribution range is ensured, and the overall operation of the production line is optimized through equipment adjustment guidance. Overall, based on the decomposition of energy consumption time series data, the quantification of parameter consistency, and the integration of dynamic adjustment mechanisms, the problems in the prior art of inaccurate energy consumption allocation, insufficient analysis of multi-batch parameter fluctuations, and fuzzy adjustment range of equipment operation parameters are effectively solved, providing highly intelligent monitoring and management capabilities for the whole process of dried noodle production, reducing energy waste and improving the stability of production line operation. Brief Description of the Drawings

[0046] Figure 1 It is the system flow chart of the present invention;

[0047] Figure 2 It is the flow chart for calculating the moving average of the present invention;

[0048] Figure 3 It is the flow chart for obtaining the energy consumption fluctuation data of the dried noodle production line of the present invention;

[0049] Figure 4 It is the flow chart for calculating the energy consumption allocation value of the present invention;

[0050] Figure 5 It is the flow chart for obtaining the energy consumption allocation data of the dried noodle production line of the present invention;

[0051] Figure 6 It is the flow chart for obtaining the parameter fluctuation data of the dried noodle production line of the present invention;

[0052] Figure 7 It is the flow chart for obtaining the dynamic adjustment management result of the dried noodle production line of the present invention. Detailed Description of the Invention

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0055] Please refer to Figure 1 , the present invention provides a technical solution: the intelligent management system for the whole process of noodle production line includes.

[0056] The energy consumption management module is based on the production line energy consumption time series and process parameters collected in real time during the operation of the noodle production line, and performs a moving average calculation. According to the moving average result, the fluctuation characteristic sequence and the continuous trend sequence of the current period are decomposed to generate the energy consumption fluctuation data of the noodle production line;

[0057] The energy consumption allocation optimization module is based on the energy consumption fluctuation data of the noodle production line, analyzes the energy consumption requirements of each stage of the noodle production line, calculates the energy consumption allocation value according to the process parameter weight corresponding to the stage, and dynamically adjusts the allocation weight to generate the energy consumption allocation data of the noodle production line;

[0058] The parameter consistency analysis module is based on the energy consumption allocation data of the noodle production line, extracts the parameter distribution characteristics of each stage after the energy consumption adjustment of the noodle production line, and obtains the parameter fluctuation data of the noodle production line by classifying multiple batches of parameters and positioning the parameter fluctuation links respectively;

[0059] The production line optimization module obtains the parameter fluctuation data of the noodle production line, analyzes the parameter fluctuation range of each stage, and limits the upper and lower limit intervals of the parameter change of each stage with reference to the parameter fluctuation range to generate the dynamic adjustment management result of the noodle production line;

[0060] The energy consumption fluctuation data of the dried noodle production line includes fluctuation characteristic sequences, trend sequences, and energy consumption change data; the energy consumption allocation data of the dried noodle production line includes stage energy consumption demand allocation values, dynamic allocation weights, and energy consumption allocation structures; the parameter fluctuation data of the dried noodle production line includes drying stage temperature fluctuation data, cooling stage temperature change data, stretching stage tension fluctuation data, and conveying stage speed fluctuation data; the specific results of the dynamic adjustment management of the dried noodle production line are the parameter adjustment schemes for drying equipment, cooling equipment, stretching equipment, and conveying equipment.

[0061] Please refer to Figure 2 , and the steps for calculating the moving average are specifically as follows:

[0062] Based on the production line energy consumption time series and process parameters collected in real time during the operation of the dried noodle production line, including drying temperature, cooling temperature, tensile force detected by the tension sensor, and the running speed of the production line conveyor belt, the production line energy consumption data is integrated.

[0063] Collect the drying temperature and cooling temperature through temperature sensors, collect the tensile force in the stretching link through a tension sensor, collect the running speed of the production line conveyor belt through a speed sensor, arrange the collected parameter data in a time series, perform preliminary filtering on the collected data of each type of sensor, remove values exceeding the sensor range or mutation values, store the filtered data in the corresponding data groups respectively, and synchronously integrate the data at the same time point to ensure the time consistency of the parameters in the drying, cooling, stretching, and conveying links, form a complete time series data set, and integrate to obtain the production line energy consumption data.

[0064] Based on the production line energy consumption data, use the formula:

[0065]

[0066] Calculate the moving average value S of each type of production line energy consumption data for the corresponding period t t , and obtain the moving average result;

[0067] Among them, n is the moving window size, indicating the number of consecutive data points covered when calculating the moving average. This parameter is dynamically set according to the sampling interval and calculation target. For example, for the data collected every 5 seconds in real time on the dried noodle production line, if a 50 - second moving window is required, then n = 10. t is the index of the current time point, indicating the time point of the moving average calculation, usually corresponding to the current sampling point in the time series, and can be determined by timestamp matching. x i represents the production line energy consumption data acquisition value at the i - th moment, including the temperature in the drying stage, the temperature in the cooling stage, the tension in the stretching stage, and the speed in the conveying stage. The specific acquisition process is as follows: the drying temperature x i: Data is collected in real time through a temperature sensor installed inside the dryer. The accuracy range of the sensor is set to ±0.1°C, and data points are collected every 5 seconds. Cooling temperature x i : Data is obtained through a temperature and humidity sensor installed in the cooling section. The response time of the sensor to changes in air flow temperature is 3 seconds to ensure synchronization with the time series. Tensile tension x i : Real-time tensile force is obtained through a tension sensor installed at key parts of the stretching equipment, with the unit of Newton (N). Sensor data is obtained through recording the real-time changes during the stretching process. Conveyor speed x i : The real-time operating speed of the conveyor belt is collected through a speed sensor installed on the conveyor belt system, with the unit of meter per second (m / s). Sensor data is recorded every 5 seconds.

[0068] If the following data is collected within a certain time period on the noodle hanging production line, with a sampling interval of 5 seconds, a sliding window size set to n = 5, and the current time point index t = 10. The collected data is as follows:

[0069] Drying temperature data (unit: °C): 50.5, 50.7, 50.6, 50.4, 50.8, 50.9, 50.7, 50.6, 50.5, 50.4; Cooling temperature data (unit: °C): 30.2, 30.4, 30.5, 30.3, 30.1, 30.2, 30.4, 30.6, 30.3, 30.2; Tensile tension data (unit: N): 100.2, 100.5, 100.6, 100.4, 100.3, 100.2, 100.5, 100.6, 100.4, 100.3; Conveyor belt speed data (unit: m / s): 1.5, 1.6, 1.5, 1.5, 1.6, 1.7, 1.6, 1.5, 1.5, 1.4. Sliding average of drying temperature:

[0070] Sliding average of cooling temperature:

[0071] Sliding average of tensile tension:

[0072] Sliding average of conveyor belt speed:

[0073] The results show that the sliding average of drying temperature: 50.7°C; the sliding average of cooling temperature: 30.34°C; the sliding average of tensile tension: 100.4N; the sliding average of conveyor belt speed: 1.54m / s.

[0074] Please refer toFigure 3 , the steps for obtaining the energy consumption fluctuation data of the dried noodle production line are specifically as follows:

[0075] Based on the moving average result, decompose and analyze the data of each stage, extract the fluctuation points and continuous change ranges of each stage, and generate a fluctuation feature sequence and a continuous trend sequence;

[0076] Decompose the fluctuation feature sequence and the continuous trend sequence of the current time period according to the moving average result. Based on the moving average calculation results of the drying temperature, cooling temperature, stretching tension, and conveyor belt speed, decompose and analyze the parameter data of each process stage respectively. Taking the drying temperature as an example, the current moving average value is 50.7 °C. Compare this value with the moving average values of the previous and subsequent time periods. If the temperature fluctuation amplitude exceeds the set threshold (for example, ±0.5 °C), record the fluctuation point as a fluctuation feature point to form a fluctuation feature sequence; the moving average value is obtained by averaging the real-time data recorded by the temperature sensor in combination with the moving window method; similarly, for the moving average value of the cooling temperature of 30.34 °C, use the recorded data of the temperature and humidity sensor in the cooling link and perform average processing on the data within a 5-second interval to extract the change range of adjacent moving average values, and record all points with a temperature change amplitude exceeding 0.3 °C as fluctuation feature points; for the moving average value of the stretching tension of 100.4 N, calculate the average value based on the real-time recorded value of the tension sensor according to a fixed window (5 sampling points), analyze the change difference of adjacent moving average values, record the points exceeding 2 N as fluctuation points, and extract the continuous change trend of the tensile force; for the moving average value of the conveyor belt speed of 1.54 m / s, obtain it by smoothing the real-time sampling data of the conveyor belt speed sensor, analyze the speed change amount of the previous and subsequent time periods, record the points with a change exceeding 0.1 m / s as fluctuation points, combine the fluctuation points of the parameters of all stages to form an overall fluctuation feature sequence, and at the same time perform linear fitting on the continuous change trend of each stage to decompose the continuous trend sequence. Finally, organize the fluctuation feature sequence and the trend sequence into multiple groups of time series data respectively.

[0077] Based on the fluctuation feature sequence and the continuous trend sequence, through time axis alignment and data classification and organization, group and store the data of each stage, record the distribution of fluctuation points and the trend change values, and generate the energy consumption fluctuation data of the dried noodle production line;

[0078] First, summarize the fluctuation characteristic points and trend data of each process stage. Align all data points according to a unified time axis through timestamps to ensure the consistency of data at the same time point for each stage. Classify the aligned data into a drying stage, a cooling stage, a stretching stage, and a conveying stage. Based on the time series after data classification, group and store the fluctuation point data and trend data of each stage respectively to form the energy consumption fluctuation information of the stage performance. Record the number of fluctuation points, the distribution range, and the trend change value of each stage through data grouping, and re-integrate all grouped data into the unified energy consumption fluctuation data of the noodle production line. The data content includes the time series, the fluctuation point distribution information, and the trend change value of each stage.

[0079] Please refer to Figure 4 , and the steps for calculating the energy consumption allocation value are specifically as follows:

[0080] Based on the energy consumption fluctuation data of the noodle production line, analyze the energy consumption requirements of each stage of the noodle production line, including the drying stage, the cooling stage, the stretching stage, and the conveying stage. Group and organize the energy consumption data of each stage according to time periods, and conduct statistics on the energy consumption requirements to generate the energy consumption requirement data of the noodle production line;

[0081] Use the linear decomposition algorithm to decompose the energy consumption requirements of each stage of the noodle production line. Obtain the time series energy consumption values of each stage through the energy consumption fluctuation data of the noodle production line. First, divide the energy consumption data of each time period into process intervals of different stages. For example, divide the drying stage into multiple interval time periods, and calculate the total energy consumption value of each interval time period by accumulating the time series values of the energy consumption fluctuation data. The time series values are from the energy consumption metering device installed on the drying equipment, which records the energy consumption value of the equipment per second and generates a time series; for the cooling stage, extract the energy consumption change amplitude of each time period, and calculate the energy consumption requirement value of the intermediate time period through linear interpolation using the instantaneous values recorded by the energy consumption sensor and the fluctuation interval data. The linear interpolation calculates the intermediate interpolation using the starting value and the ending value of each time period; for the stretching stage, classify the time series energy consumption values according to the tension fluctuation range, associate the tension interval values recorded by the tension sensor with the corresponding energy consumption values in the time series, and statistically calculate the total energy consumption values corresponding to various tensions. The calculation result is obtained by accumulating the energy consumption values of the time periods corresponding to each tension interval; for the conveying stage, extract the energy consumption values of each speed interval according to the conveyor belt speed fluctuation range, and extract them after aligning the time series values recorded by the speed sensor with the energy consumption data generated by the energy consumption metering device. Complete the data weighted integration to form a complete energy consumption requirement table; obtain the energy consumption requirement values of the drying, cooling, stretching, and conveying stages through the above methods, and decompose all segmented data in combination with the continuity of the time series to finally form the energy consumption requirement decomposition table of each stage of the noodle production line.

[0082] Based on the energy consumption demand data of the dried noodle production line, the formula is used:

[0083]

[0084] Calculate the energy consumption allocation value E in stage j j ;

[0085] Among them, W j is the process parameter weight of stage j, representing the importance coefficient of the process in this stage. The weight value is obtained by quantifying the influence degree of the key parameters (such as drying temperature stability, cooling temperature and humidity fluctuation range, stretching tension change range, etc.) of each process stage of the dried noodle production line. For example: the smaller the drying temperature fluctuation range (for example, the fluctuation amplitude is within ±1°C), the higher the weight, because the stability of the drying temperature directly affects the moisture content and texture consistency of the dried noodles; the smaller the cooling temperature change range, the higher the weight, because the temperature stability in the cooling stage affects the shaping and subsequent packaging performance of the dried noodles; the smaller the stretching tension fluctuation range, the higher the weight, because the tension fluctuation affects the strength and toughness of the dried noodles; the more stable the conveying speed, the higher the weight, because the smooth operation of the conveyor belt affects the rhythm coordination of the entire production line. D j is the energy consumption demand value of stage j, representing the actual energy consumption demand in each stage during the operation of the dried noodle production line, which is obtained by cumulatively counting the total energy consumption in each stage. The acquisition method is to divide the energy consumption fluctuation data of the dried noodle production line into intervals by time period, and sum the energy consumption data in each interval. For example: the energy consumption demand value in the drying stage is obtained by summing up the real-time data recorded by the energy consumption sensor (such as the power consumption per unit time). V j is the energy consumption fluctuation amplitude of stage j, representing the dynamic change range of the energy consumption in this stage during the operation of the dried noodle production line, which is calculated by the difference between the maximum value and the minimum value in the energy consumption fluctuation data of this stage. The acquisition method is to extract and analyze the fluctuation points of the time series data recorded by the energy consumption sensor, and calculate the difference between the maximum value and the minimum value. For example: for the cooling stage, analyze the fluctuation range of the energy consumption data at different time points. If the maximum value of the data is 315W and the minimum value is 295W, then the fluctuation amplitude is 20W. T j is the energy consumption stability time range of stage j, representing the time period during which the energy consumption data remains within a certain stable range during the operation of the dried noodle production line, which is obtained by statistically analyzing the stable intervals of the time series data. The determination basis of the stable interval is that the energy consumption data fluctuation is within the set threshold (such as the fluctuation range is less than ±5%). For example: for the stretching stage, continuously record the time period during which the energy consumption fluctuation range in the time series is less than ±2%, and count its total duration as the stability time range.

[0086] The dried noodle production line is divided into four stages: drying stage, cooling stage, stretching stage, and conveying stage;

[0087] W 1 = 0.4, D 1 = 500, V 1 = 20, T 1 = 60 (drying stage);

[0088] W 2 = 0.3, D 2 = 300, V 2 = 15, T 2 = 50 (cooling stage);

[0089] W 3 = 0.2, D 3 = 200, V 3 = 10, T 3 = 40 (stretching stage);

[0090] W 4 = 0.1, D 4 = 100, V 4 = 5, T 4 = 30 (conveying stage).

[0091] Energy consumption allocation value for the drying stage:

[0092] Energy consumption allocation value for the cooling stage:

[0093] Energy consumption allocation value for the stretching stage:

[0094] Energy consumption allocation value for the conveying stage:

[0095] The results show that the energy consumption allocation value for the drying stage: 200.33; the energy consumption allocation value for the cooling stage: 90.3; the energy consumption allocation value for the stretching stage: 40.25; the energy consumption allocation value for the conveying stage: 10.17.

[0096] Please refer to Figure 5 , and the specific steps for obtaining the energy consumption allocation data of the dried noodle production line are as follows:

[0097] Based on the energy consumption allocation values of the drying stage, cooling stage, stretching stage, and conveying stage, by real-time monitoring parameters such as temperature, tension, and speed in each stage, dynamically adjusting the corresponding allocation weights in combination with production requirements, and updating the allocation values for each stage to generate the dynamically adjusted energy consumption allocation;

[0098] Adjustment and analysis are carried out according to the real-time production requirements of the dried noodle production line; the allocated value represents the actual energy consumption allocated to this stage during the entire production process, with the unit of watt (W) or kilowatt (kW), reflecting the proportion of electrical energy required for equipment operation and process execution in this stage; for example, when the temperature fluctuation monitored by the sensor in the drying stage exceeds the stable range of ±2°C, its weight is temporarily increased by 10% to cope with possible energy consumption fluctuations, and the allocated value of the drying stage is adjusted to 220.36; in the cooling stage, if it is detected that the cooling temperature drop rate increases from 1°C / minute to 3°C / minute in a short period of time, it indicates that the cooling energy consumption is too high. At this time, by reducing the weight of the cooling stage by 20%, the allocated energy consumption is adjusted from 90.3 to 72.24, and the remaining part of the energy consumption is preferentially adjusted to the drying stage and the stretching stage; for the stretching stage, when the amplitude of the tension fluctuation monitored in real time increases from 10 N to 15 N, the allocated weight is preferentially increased by 15%, and the energy consumption allocation value is adjusted from 40.25 to 46.29 to meet the tension requirements; in the conveying stage, since the allocated value of the energy consumption is small and the monitoring data shows that the conveyor belt speed remains stable at 5 m / s, the weight of this stage is not adjusted and the allocated value of 10.17 remains unchanged. Through the dynamic adjustment process of the weight of each of the above stages, an energy consumption allocation plan that meets the real-time production requirements is generated.

[0099] Based on the dynamically adjusted energy consumption allocation, integrate the energy consumption allocation data of each stage according to the time axis, record the allocated weight, energy consumption comparison and change rate, and generate the energy consumption allocation data of the dried noodle production line;

[0100] First, align the energy consumption allocation values of each stage after dynamic adjustment according to the time axis to ensure the consistency of the data of all stages on the same time basis. Subsequently, integrate the adjusted energy consumption allocation values to form a comprehensive energy consumption allocation table for the drying stage, the cooling stage, the stretching stage and the conveying stage, specifically including the time series energy consumption values of each stage, the adjusted allocated weight, the energy consumption comparison values before and after adjustment, and the energy consumption change rate. These data are obtained through the statistical calculation of the real-time monitoring values of the sensor and the correlation calculation of the adjustment parameters. Finally, record the integrated data of each stage into a unified data allocation table to generate the energy consumption allocation data of the dried noodle production line.

[0101] Please refer to Figure 6 , the steps for obtaining the parameter fluctuation data of the dried noodle production line are specifically as follows:

[0102] Based on the energy consumption allocation data of the dried noodle production line, extract the temperature distribution in the drying stage, the temperature change in the cooling stage, the tension change in the stretching stage, and the conveyor belt speed change in the conveying stage after energy consumption adjustment, classify the multi-batch parameters, and generate the classification results of the multi-batch parameters of the dried noodle production line;

[0103] Extract the parameter distribution characteristics of each stage after the energy consumption adjustment of the dried noodle production line, including the temperature distribution in the drying stage, the temperature change in the cooling stage, the tension change in the stretching stage, and the conveyor belt speed change in the conveying stage. Classify the multi-batch parameters separately through non-uniform fuzzy clustering. First, take the drying stage as an example, analyze the distribution data of the drying temperatures of multiple batches, obtain the temperature sampling points from each batch. For example, the drying temperatures recorded in batch 1 are 110.5°C, 111.2°C, and 110.9°C, and those in batch 2 are 109.8°C, 110.0°C, and 110.3°C. Divide the temperature data of each batch into several consecutive time periods, and define the center point of each time period as the initial reference value for fuzzy clustering. Subsequently, for the cooling stage, by collecting the temperature drop rate data, such as the cooling rates in batch 1 are 2.5°C / min, 2.6°C / min, and 2.4°C / min, and those in batch 2 are 2.3°C / min, 2.2°C / min, and 2.1°C / min. Similarly, divide the rate distribution into several time periods, and use the center value of the time period as the clustering base point for the cooling stage. Then, for the stretching stage, the collected tension data, such as in batch 1 are 50N, 48N, and 49N, and those in batch 2 are 47N, 45N, and 46N. Use the change range of the tension as the classification basis and combine the tension interval data within the time period to participate in the clustering. For the conveying stage, take the conveyor belt speed as an example. The recorded speeds in batch 1 are 5.2m / s, 5.1m / s, and 5.0m / s, and those in batch 2 are 4.8m / s, 4.9m / s, and 4.7m / s. Segment the speed data and perform fuzzy classification. Through the non-uniform fuzzy clustering algorithm, in each stage, classify the distribution characteristics of different batches, and classify the time period data with a relatively small distance from each other into the same category. For example, batches with a temperature distribution difference less than 0.5°C in the drying stage are classified into one category, batches with a temperature drop rate difference less than 0.2°C / min in the cooling stage are classified into one category, batches with a tension fluctuation range difference less than 3N are classified into one category, and batches with a conveying speed difference less than 0.3m / s are classified into one category. Finally, obtain the classification results of the multi-batch parameters of the dried noodle production line.

[0104] Based on the classification results of the multi-batch parameters of the dried noodle production line, use the formula:

[0105]

[0106] Calculate the parameter consistency score C of batch b in the target stage of the dried noodle production line b ;

[0107] where m is the sample quantity of the current batch b, referring to the number of sensor data points collected within the time period in a certain stage (such as the drying stage) of the dried noodle production line. Count the number of sensor data collection points within the time interval of the current batch. For example, through the temperature sensor sampling at a frequency of once per second, the sample quantity within 10 minutes is m = 600. is the parameter value of sample a in batch b, representing the specific sensor sampling value at a certain stage of the noodle production line, such as the temperature value recorded per second during the drying stage. Parameters such as temperature, tension, and speed are recorded in real time through sensors. Each is the direct output of the sensor at the corresponding time point, is the parameter mean of batch b, representing the average value of the parameters of all sample points within this batch, used to measure the overall trend of the data. a represents the a-th sample in batch b, which is automatically generated according to the sampling order recorded by the sensor. For example, the sample at the first time point is a = 1, the second time point is a = 2, and b is the batch number, representing the production batch being currently analyzed. For example, the 1st batch during the drying stage, the 2nd batch during the cooling stage, etc. The batch number is generated through production planning and time division to ensure the independence of data in different time periods.

[0108] For example, batch b 1 : The sampling values of the temperature parameter during the drying stage are [9.8, 10.2, 10.1, 10.0, 9.9, 10.3, 10.1], and the number of samples m = 7.

[0109] Calculate the mean

[0110] Calculate the deviation |9.8 - 10.06| = 0.26, |10.2 - 10.06| = 0.14, |10.1 - 10.06| = 0.04, |10.0 - 10.06| = 0.06, |9.9 - 10.06| = 0.16, |10.3 - 10.06| = 0.24, |10.1 - 10.06| = 0.04;

[0111] Sum and calculate the consistency score C b : 0.26 + 0.14 + 0.04 + 0.06 + 0.16 + 0.24 +

[0112] 0.04 = 0.94;

[0113] Consistency score:

[0114] This result indicates that batch b 1 has a parameter consistency score of 0.134.

[0115] Based on the parameter consistency score, locate the parameter fluctuation links at each stage, analyze and identify the parameter fluctuation situations to obtain the parameter fluctuation data of the noodle production line;

[0116] Based on the calculation results in paragraph 2, the batch consistency score C bBring it into the subsequent analysis, locate the parameter fluctuation links in each stage, and separately process the parameter fluctuation ranges in the drying stage, cooling stage, stretching stage, and conveying stage. First, screen the batch data with a consistency score lower than the set threshold in each stage. For example, the batch score in the drying stage is lower than the set threshold T = 0.15, indicating that the temperature parameter fluctuation of this batch exceeds the allowable range. Subsequently, calculate the maximum and minimum fluctuation values of all samples in this stage, and combine the actual temperature value array [9.8, 10.2, 10.1, 10.0, 9.9, 10.3, 10.1] sampled in this stage to obtain the maximum fluctuation value of |10.3 - 9.8| = 0.5. Subsequently, by comparing the difference between the maximum fluctuation value and the process standard fluctuation range R = 0.4, it is confirmed that the fluctuation amplitude exceeds the standard range. Similar analysis is performed on the batch in the cooling stage for the batch in the stretching stage for the batch in the conveying stage Classify the parameter fluctuations in all stages that exceed the standard range, generate fluctuation data records, and classify the data into categories such as fluctuating type, deviating type, and discrete type to obtain the parameter fluctuation data of the dried noodle production line.

[0117] Please refer to Figure 7 , and the specific steps for obtaining the dynamic adjustment management results of the dried noodle production line are as follows:

[0118] Based on the parameter fluctuation data of the dried noodle production line, analyze the parameter fluctuation ranges in the drying stage, cooling stage, stretching stage, and conveying stage, and adjust and limit the upper and lower limit intervals of the parameter changes in each stage to generate adjusted parameter interval data;

[0119] First, analyze the temperature fluctuation data obtained in the drying stage. Set the temperature fluctuation range to 35 - 50 °C. If the actual temperature exceeds this range, record the upper and lower limit values of the fluctuation as the maximum value of 53 °C and the minimum value of 33 °C respectively. Set the temperature change range in the cooling stage to 15 - 25 °C, and analyze that its fluctuation range is 19 - 27 °C, and record its upper and lower limit deviations as 2 °C and 3 °C respectively; the tension change in the stretching stage is set within the range of 10 - 20 N. By analysis, the maximum tension in this stage is 22 N and the minimum value is 9 N, and record the deviations as 2 N and 1 N respectively; the analysis range of the conveyor belt speed change in the conveying stage is set to 2 - 5 m / s. By calculation, the actual fluctuation range of the conveying speed is 1.8 - 5.2 m / s, and record the deviations as 0.2 m / s and 0.2 m / s respectively. Correct all parameters with fluctuation ranges exceeding the standard to the target range through limiting methods. For example, adjust the drying temperature deviation value of 3 °C so that its upper and lower limits remain within the range of 35 - 50 °C, and at the same time adjust the temperature deviation of 2 °C in the cooling stage to the target range to obtain the parameter interval after correcting the upper and lower limits of each stage.

[0120] Based on the adjusted parameter interval data, analyze the influence range of parameter changes in each stage on the operation of the equipment, provide adjustment guidance for the production line equipment in each stage, and generate the dynamic adjustment management results of the noodle production line;

[0121] According to the upper and lower limit intervals of the adjusted parameters, combined with the adjustment records of the specific fluctuation range, generate the corresponding operation guidance for the production line equipment. In the drying stage, by controlling the power output of the heating device, the temperature is stabilized within the adjusted target interval of 35 - 50 °C. Adjust the operating speed of the air-cooling equipment in the cooling stage to keep the cooling temperature fluctuation within the range of 15 - 25 °C. In the stretching stage, through the feedback control device of the tension sensor, ensure that the tension is maintained between 10 - 20 N. In the conveying stage, by adjusting the operating power of the conveyor belt drive motor, correct the conveying speed fluctuation to within the range of 2 - 5 m / s. Finally, combine the operation adjustment parameter records of all stages to generate the dynamic adjustment management results of the noodle production line.

[0122] The intelligent management method for the whole process of noodle production is based on the above-mentioned intelligent management system for the whole process of noodle production and includes the following steps:

[0123] S1: Based on the real-time collected production line energy consumption time series and process parameters during the operation of the noodle production line, use moving average calculation to decompose the energy consumption data and generate the energy consumption fluctuation data of the noodle production line;

[0124] S2: Based on the energy consumption fluctuation data of the noodle production line, analyze the energy consumption requirements of the noodle production line, calculate the energy consumption allocation value for each stage according to the process parameter weights, and dynamically adjust the allocation weights to generate the energy consumption allocation data of the noodle production line;

[0125] S3: Based on the energy consumption allocation data of the noodle production line, extract the parameter distribution characteristics of each stage after the energy consumption adjustment of the noodle production line, classify multiple batches of parameters and locate the parameter fluctuation links to obtain the parameter fluctuation data of the noodle production line;

[0126] S4: Based on the parameter fluctuation data of the noodle production line, analyze the parameter fluctuation range of each stage, limit and adjust the upper and lower limit intervals of the parameters in each stage, and generate the dynamic adjustment management results of the noodle production line.

[0127] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the relevant art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. The whole process intelligent management system of dried noodle production is characterized by: The system comprises: The energy consumption management module is based on the energy consumption time series and process parameters of the noodle production line collected in real time during operation, and performs sliding average calculation. According to the sliding average result, the fluctuation characteristic sequence and continuous trend sequence of the current period are decomposed to generate the energy consumption fluctuation data of the noodle production line; The energy consumption allocation optimization module analyzes the energy consumption demand of each stage of the noodle production line based on the energy consumption fluctuation data of the noodle production line, calculates the energy consumption allocation value according to the process parameter weight corresponding to the stage, and dynamically adjusts the allocation weight to generate the energy consumption allocation data of the noodle production line; The parameter consistency analysis module extracts the parameter distribution characteristics of each stage of the noodle production line after the energy consumption adjustment based on the energy consumption distribution data of the noodle production line, and obtains the parameter fluctuation data of the noodle production line by classifying multiple batches of parameters and locating the parameter fluctuation links; The production line optimization module obtains the parameter fluctuation data of the noodle production line, analyzes the parameter fluctuation range of each stage, and limits the upper and lower limits of the parameter changes in each stage with reference to the parameter fluctuation range, thereby generating a dynamic adjustment management result of the noodle production line.

2. The whole process intelligent management system of fine dried noodle production according to claim 1 is characterized in that: The steps of performing sliding average calculation are specifically as follows: Based on the real-time collection of production line energy consumption time series and process parameters during the operation of the noodle production line, including drying temperature, cooling temperature, tensile force detected by the tension sensor, and production line conveyor belt running speed, the production line energy consumption data is integrated; Based on the energy consumption data of the production line, the formula is adopted: Calculate the sliding average of the energy consumption data S of each type of production line for the corresponding period t t , get the sliding average result; Among them, n is the sliding window size, t is the current time point index, and x i Represents the energy consumption data collection value of the production line at the i-th moment.

3. The whole process intelligent management system of fine dried noodle production according to claim 2 is characterized in that: The steps for obtaining the energy consumption fluctuation data of the noodle production line are specifically as follows: Based on the sliding average result, the data of each stage is decomposed and analyzed, the fluctuation points and continuous change range of each stage are extracted, and the fluctuation feature sequence and continuous trend sequence are generated; Based on the fluctuation characteristic sequence and continuous trend sequence, the data of each stage are grouped and stored through time axis alignment and data classification, and the fluctuation point distribution and trend change value are recorded to generate energy consumption fluctuation data of the noodle production line.

4. The whole process intelligent management system of fine dried noodle production according to claim 3 is characterized in that: The steps of calculating the energy consumption allocation value are specifically as follows: Based on the energy consumption fluctuation data of the noodle production line, the energy consumption requirements of each stage of the noodle production line, including the drying stage, the cooling stage, the stretching stage, and the conveying stage, are analyzed, the energy consumption data of each stage are grouped and sorted according to time periods, and the energy consumption requirements are counted to generate energy consumption demand data of the noodle production line; Based on the energy consumption demand data of the noodle production line, the formula is used: Calculate the energy consumption allocation value E of stage j j ; Among them, W j is the process parameter weight of stage j, D j is the energy demand value of stage j, V j is the energy consumption fluctuation amplitude in stage j, T j is the energy consumption stability time range of stage j.

5. The whole process intelligent management system of fine dried noodle production according to claim 4 is characterized in that: The steps for obtaining the energy consumption distribution data of the noodle production line are specifically as follows: Based on the energy consumption allocation values ​​of the drying stage, cooling stage, stretching stage and conveying stage, by real-time monitoring of the temperature, tension and speed parameters of each stage, dynamically adjusting the corresponding allocation weights in combination with production needs, and updating the allocation values ​​of each stage, a dynamically adjusted energy consumption allocation is generated; Based on the dynamically adjusted energy consumption allocation, the energy consumption allocation data of each stage is integrated according to the time axis, the allocation weight, energy consumption comparison and change rate are recorded, and the energy consumption allocation data of the noodle production line is generated.

6. The whole process intelligent management system of fine dried noodle production according to claim 5, characterized in that: The steps for obtaining the parameter fluctuation data of the noodle production line are specifically as follows: Based on the energy consumption distribution data of the noodle production line, the temperature distribution in the drying stage, the temperature change in the cooling stage, the tension change in the stretching stage, and the conveyor belt speed change in the conveying stage after energy consumption adjustment are extracted, and multiple batches of parameters are classified to generate multiple batches of parameter classification results of the noodle production line; Based on the classification results of multiple batches of parameters of the noodle production line, the formula is adopted: Calculate the parameter consistency score C for batch b of the target stage of the noodle production line b ; Among them, m is the number of samples in the current batch b, is the parameter value of sample a in batch b, is the parameter mean of batch b; Based on the parameter consistency score, the parameter fluctuation link in each stage is located, the parameter fluctuation situation is analyzed and identified, and the parameter fluctuation data of the noodle production line is obtained.

7. The whole process intelligent management system of fine dried noodle production according to claim 6 is characterized in that: The steps for obtaining the dynamic adjustment management result of the noodle production line are specifically as follows: Based on the parameter fluctuation data of the noodle production line, the parameter fluctuation ranges in the drying stage, the cooling stage, the stretching stage and the conveying stage are analyzed, and the upper and lower limits of the parameter changes in each stage are adjusted and limited to generate adjusted parameter interval data; Based on the adjusted parameter interval data, the impact range of parameter changes on equipment operation at each stage is analyzed, adjustment guidance for production line equipment at each stage is provided, and dynamic adjustment management results for the noodle production line are generated.

8. The whole process intelligent management method of fine noodles production is characterized by: The whole process intelligent management system of fine dried noodle production according to any one of claims 1 to 7 is implemented, comprising the following steps: S1: Based on the energy consumption time series and process parameters of the production line collected in real time during the operation of the noodle production line, the energy consumption data is decomposed using the sliding average calculation to generate the energy consumption fluctuation data of the noodle production line; S2: Based on the energy consumption fluctuation data of the noodle production line, the energy consumption demand of the noodle production line is analyzed, the energy consumption allocation value of each stage is calculated according to the process parameter weight, and the allocation weight is dynamically adjusted to generate energy consumption allocation data of the noodle production line; S3: Based on the energy consumption distribution data of the noodle production line, extract the parameter distribution characteristics of each stage after the energy consumption of the noodle production line is adjusted, classify multiple batches of parameters and locate the parameter fluctuation link, and obtain the parameter fluctuation data of the noodle production line; S4: Based on the parameter fluctuation data of the noodle production line, the parameter fluctuation range of each stage is analyzed, and the upper and lower limits of the parameters of each stage are limited and adjusted to generate dynamic adjustment management results of the noodle production line.

Images