Node energy consumption monitoring and optimizing method of vermicelli continuous production line

Abstract

The invention discloses a node energy consumption monitoring and optimizing method for a vermicelli continuous production line, and relates to the technical field of data processing. The method comprises the following steps: acquiring historical node energy consumption data and current node energy consumption data; obtaining an energy consumption abnormal value based on the historical node energy consumption data and the current node energy consumption data; acquiring a severity value based on the energy consumption abnormal value; based on the severity value, obtaining a regulation and control coefficient; and adjusting the P value of the PID controller based on the regulation coefficient. According to the method, the severity value of the energy consumption abnormity of the current production node is obtained through analysis, and the P value of the PID controller is adjusted through the severity value, so that the phenomenon of long-time energy consumption waste caused by slow response of production equipment when the production of a certain node of fans is greatly abnormal is avoided, and the production efficiency is improved. And the phenomenon that energy consumption is increased due to the fact that production equipment responds too fast when production of a certain node of the fans is small and abnormal is also avoided.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically a method for monitoring and optimizing node energy consumption in a continuous vermicelli production line. Background Technology

[0002] In continuous vermicelli production lines, energy consumption monitoring is crucial for optimizing energy use and improving production efficiency. This is typically achieved by deploying sensor networks to collect real-time energy consumption parameters (e.g., electricity, water, and gas consumption) at each node of the production line, and then transmitting this data to a central control system for processing and analysis using wireless sensor network technology. This method enables comprehensive monitoring of energy consumption during continuous vermicelli production and allows for dynamic adjustment strategies based on real-time data. For example, PID controllers or collaborative control algorithms can dynamically adjust equipment operating parameters (e.g., temperature, pressure, and speed) according to the current production status and energy consumption. This dynamic adjustment effectively reduces energy consumption while ensuring vermicelli quality and production efficiency.

[0003] However, in continuous vermicelli production lines, the quality of raw materials varies between batches (e.g., different types of starch). This necessitates different adjustments to the equipment operating parameters at the same production node during different batches of vermicelli production to effectively reduce energy consumption. Furthermore, since vermicelli production nodes can influence each other (e.g., poor potato crushing results in increased energy consumption during subsequent grinding), higher demands are placed on the control of equipment operating parameters at each node of vermicelli production to effectively reduce energy consumption while ensuring vermicelli quality and production efficiency. Existing methods for monitoring and optimizing node energy consumption in continuous vermicelli production lines cannot accurately control response speed based on various energy consumption parameters. When an anomaly occurs at a certain node of vermicelli production, a slow response from the production equipment leads to prolonged energy waste, while an overly fast response results in increased energy consumption. Summary of the Invention

[0004] The purpose of this application is to provide a method for monitoring and optimizing node energy consumption in a continuous vermicelli production line, so as to solve the technical problem that existing technologies cannot accurately match the response speed of equipment with production anomalies.

[0005] To achieve the above objectives, this application provides the following technical solution: This application proposes a technical solution for monitoring and optimizing node energy consumption in a continuous vermicelli production line. The continuous vermicelli production line includes a PID controller, and the method includes: Acquire historical node energy consumption data and current node energy consumption data; the node energy consumption data includes at least the time-series energy consumption parameter values ​​of the corresponding production node during continuous fan production; Based on the historical node energy consumption data and the current node energy consumption data, energy consumption anomalies are obtained; the energy consumption anomalies are used at least to characterize the magnitude of the difference between the current node energy consumption data and the historical node energy consumption data. Based on the energy consumption anomaly value, a severity value is obtained; the severity value is at least used to characterize the magnitude of the increase in energy consumption anomaly value corresponding to each production node during the current continuous production of fans; Based on the severity value, the control coefficient is obtained; Based on the control coefficient, the P value of the PID controller is adjusted.

[0006] As a specific solution in this application, the step of obtaining abnormal energy consumption values ​​based on the historical node energy consumption data and the current node energy consumption data includes: Based on the historical node energy consumption data, multiple first sequences are obtained; the first sequence is a sequence formed by multiple time-series energy consumption parameter values ​​during the continuous production of any batch of fans in the historical node energy consumption data. Based on the current node energy consumption data, a second sequence is obtained; the second sequence is a sequence formed by multiple time-series energy consumption parameter values ​​during continuous fan production in the current node energy consumption data; Based on multiple first sequences, obtain the mean sequence; The energy consumption anomaly value is obtained based on the mean sequence and the second sequence.

[0007] As a specific solution in this application, before obtaining the mean sequence based on multiple first sequences, the method further includes: If the lengths of the first sequence and the second sequence are different, then the longest sequence is obtained based on the lengths of the first sequence and the second sequence. The sequence lengths of each first sequence and the second sequence are increased to the same length as the longest sequence based on the difference algorithm.

[0008] As a specific solution in this application, obtaining the energy consumption anomaly value based on the mean sequence and the second sequence includes: Based on the mean sequence and the second sequence, a difference sequence, a first difference sequence, and a second difference sequence are obtained; the sequence value in the difference sequence is equal to the sequence value in the second sequence minus the absolute value of the corresponding sequence value in the mean sequence; the sequence value in the first difference sequence is equal to the difference between two adjacent sequence values ​​in the mean sequence; the sequence value in the second difference sequence is equal to the difference between two adjacent sequence values ​​in the second sequence. A trend sequence is obtained based on the first difference sequence and the second difference sequence; the sequence value in the trend sequence is equal to the product of the corresponding sequence values ​​in the first difference sequence and the second difference sequence. The energy consumption anomaly value is obtained based on the difference sequence and the trend sequence.

[0009] As a specific solution in the technical solution of this application, the step of basing the difference sequence and the trend sequence includes: Based on the difference sequence, a first average value is obtained; the first average value is the average value of each sequence value in the difference sequence. Based on the trend sequence, a trend value is obtained; the trend value at least represents the number of sequence values ​​less than 0 in the trend sequence; Based on the first average value and the trend value, the energy consumption anomaly value is obtained.

[0010] As a specific solution in this application, obtaining the severity value based on the energy consumption anomaly includes: Based on the energy consumption anomaly value, multiple problem nodes are obtained from each production node that has been completed in the current continuous production of fans; the problem node is the production node whose corresponding energy consumption anomaly value is greater than or equal to a preset value. Based on each problem node, a continuity value is obtained; the continuity value is used to characterize at least the degree of proximity between each problem node and the current continuous production node of fans. The severity value is obtained based on the continuity value.

[0011] As a specific solution in the technical solution of this application, the step of obtaining the continuity value based on each problem node includes: Based on each problem node, obtain the sequence number of the production node corresponding to each problem node and the number of time-series energy consumption parameter values; The continuity value is obtained based on each quantity and each sequence number.

[0012] As a specific solution in this application, obtaining the severity value based on the continuity value includes: Based on the continuity value, a cumulative value is obtained; the cumulative value is used to characterize at least the ratio of the number of each problem node to the number of each production node that has been completed in the current continuous production of fans. Based on the energy consumption anomalies corresponding to each problem node, obtain the anomaly sequence; Based on the abnormal sequence, an abnormal repair value is obtained; the abnormal repair value is used to characterize at least the difficulty of repairing the energy consumption anomaly. The severity value is obtained based on the cumulative value and the anomaly repair value.

[0013] As a specific solution in the technical solution of this application, the step of obtaining the cumulative value based on the continuity value includes: Based on each problem node, a second average value and an anomaly ratio are obtained; the second average value is the average of the energy consumption anomalies of each production node that has been completed in the current continuous production of fans; the anomaly ratio is the ratio of the number of each problem node to the number of each production node that has been completed in the current continuous production of fans. The cumulative value is obtained based on the continuity value, the second average value, and the anomaly ratio.

[0014] As a specific solution in this application, the step of obtaining the abnormal repair value based on the abnormal sequence includes: Based on the abnormal sequence, obtain the maximum sequence value; Based on the maximum sequence value, multiple subsequent sequence values ​​are obtained from the abnormal sequence; the subsequent sequence values ​​are the sequence values ​​in the abnormal sequence that are ordered after the maximum sequence value. Based on the maximum sequence value and each subsequent sequence value, a fitted straight line is obtained; Based on the fitted straight line, the slope is obtained; The anomaly repair value is obtained based on the slope.

[0015] Compared with the prior art, the beneficial effects of this application are: This application analyzes the abnormal energy consumption values ​​at each production node during the continuous production process of rice noodles to obtain the severity value of the current production node's energy consumption anomaly. Then, it adjusts the P value of the PID controller based on the severity value. This avoids the phenomenon of slow response of production equipment leading to long-term energy waste when a large anomaly occurs at a certain node of rice noodle production, and also avoids the phenomenon of excessive response of production equipment leading to increased energy consumption when a small anomaly occurs at a certain node of rice noodle production. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a method for monitoring and optimizing node energy consumption in a continuous vermicelli production line as proposed in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. For example, the first sequence and the second sequence mentioned below belong to different sequences. It should be understood that such names can be used interchangeably where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. The division of modules in the embodiments of this application is merely a logical division. In actual applications, there may be other division methods. For example, multiple modules may be combined into or integrated into another system, or some features may be ignored or not performed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interface, and the indirect coupling or communication connection between modules may be electrical or other similar forms. None of these are limited in the embodiments of this application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed among multiple circuit modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of this application.

[0019] To address the technical problem mentioned in the background art—that existing technologies struggle to accurately match equipment response speed with production anomalies—this application proposes a method for monitoring and optimizing node energy consumption in a continuous vermicelli production line, wherein the continuous vermicelli production line includes a PID controller. For example... Figure 1 As shown, the node energy consumption monitoring and optimization method of the continuous vermicelli production line includes steps S100 to S500.

[0020] Step S100: Obtain historical node energy consumption data and current node energy consumption data.

[0021] It is important to understand that a continuous vermicelli production line is a complex industrial equipment used for the automated production of vermicelli. A continuous vermicelli production line consists of multiple production nodes, each responsible for different production stages. Generally, a continuous vermicelli production line includes at least the following production nodes: (1) Raw material processing: The raw materials are usually potatoes or sweet potatoes, etc. The raw materials need to be washed, soaked and crushed to ensure the uniformity and quality of the starch. (2) Slurrying and mixing: The starch and water are mixed in a certain proportion and stirred by a slurrying system to form a uniform paste. (3) Spreading and forming: The stirred starch paste is spread evenly on the forming belt through a slurry spreading device to form the prototype of vermicelli. (4) Steaming and cooking: The starch belt after spreading is steamed to cook and shape it. (5) Cooling and dehydration: The cooked vermicelli needs to be cooled quickly to prevent over-drying or deformation. Then, the excess moisture in the semi-finished product is further removed by a drying device to ensure the dryness of the finished product. (6) Cutting and shaping: After cooling, the vermicelli is cut into the required shape (e.g., vermicelli strips or vermicelli sheets) by a shredder or strip cutter and then sorted. (7) Aging treatment: The cut vermicelli needs to be treated by natural aging or low-temperature aging system to improve its toughness and taste. (8) Packaging and finished product output: Finally, the vermicelli that has passed inspection is weighed, packaged, and boxed and stored.

[0022] In this embodiment, the node energy consumption data includes at least the time-series energy consumption parameter values ​​of the corresponding production node during continuous fan production. It is important to understand that in this embodiment, appropriate monitoring parameters can be selected as the energy consumption parameter values ​​for a specific production node. For example, electricity consumption can be current, voltage, power, and electricity consumption; water consumption can be water usage and flow rate; steam consumption can be steam flow rate and steam pressure; compressed air consumption can be compressed air flow rate and pressure; and environmental temperature and humidity, etc.

[0023] Step S200: Based on the historical node energy consumption data and the current node energy consumption data, obtain the energy consumption anomaly value.

[0024] In this embodiment, the energy consumption anomaly value is used at least to characterize the magnitude of the difference between the current node's energy consumption data and the historical node's energy consumption data.

[0025] It's important to understand that while the batches of vermicelli production differ, the production process is generally similar. If there's a significant difference between the energy consumption data of the current production node and the historical energy consumption data for a particular batch of vermicelli, it indicates an anomaly in the production process. For example, sweet potatoes are more difficult to grind than potatoes; therefore, if sweet potatoes are the raw material for vermicelli production, the energy consumption at the raw material processing node will be significantly higher.

[0026] In the embodiments of this application, energy consumption anomalies can be obtained based on the historical node energy consumption data and the current node energy consumption data in any reasonable manner. For example, if the node energy consumption data can be electricity consumption or power, then the energy consumption anomaly can be the ratio of the current node energy consumption data to the historical node energy consumption data. In order to accurately determine whether the current production node is abnormal through the energy consumption anomaly value, in one embodiment of this application, step S200, the acquisition of energy consumption anomalies based on the historical node energy consumption data and the current node energy consumption data, includes steps S210 to S240.

[0027] Step S210: Based on the historical node energy consumption data, obtain multiple first sequences.

[0028] In this embodiment, historical node energy consumption data corresponds one-to-one with the first sequence. The first sequence is a sequence formed by multiple time-series energy consumption parameter values ​​during the continuous production of any batch of vermicelli in the historical node energy consumption data. For any historical node, the energy consumption parameter value at each moment in the continuous vermicelli production process constitutes a corresponding sequence, and the time interval between adjacent moments is equal. The length of this sequence represents the duration of the vermicelli production process in the historical stage. In this embodiment, the time-series energy consumption parameter value can be a time-series power value or a time-series current value, etc.

[0029] Step S220: Obtain the second sequence based on the current node energy consumption data.

[0030] In this embodiment, the second sequence is a sequence formed by multiple time-series energy consumption parameter values ​​during continuous fan production in the current node's energy consumption data.

[0031] Step S230: Obtain the mean sequence based on multiple first sequences.

[0032] In this embodiment, the mean sequence value is the average of the corresponding sequence values ​​in each first sequence. Specifically, based on multiple first sequences, the formula for calculating the mean sequence is as follows:

[0033] in, This represents the j-th sequence value in the mean sequence; n represents the number of elements in the first sequence. This represents the j-th sequence value in the k-th first sequence.

[0034] It is important to understand that during the energy consumption monitoring of a continuous production line for fans, the acquisition cycle for energy consumption parameters is fixed. If the time consumed at each historical production node is different, the length of each first sequence will be different. If the lengths of each first sequence are different, it is difficult to obtain the average sequence from the multiple first sequences. Based on this, in one embodiment of this application, before step S230, which involves obtaining the average sequence based on multiple first sequences, the method further includes steps S250 and S260.

[0035] Step S250: If the sequence lengths of each first sequence and the second sequence are different, then the longest sequence is obtained based on each first sequence and the second sequence.

[0036] It is important to understand that selecting the longest sequence from multiple sequences is a mature technique, which will not be elaborated upon here.

[0037] Step S260: Based on the difference algorithm, increase the sequence length of each first sequence and the second sequence to the same length as the longest sequence.

[0038] It is important to understand that interpolation algorithms are core tools in numerical analysis and scientific computing, used to estimate or construct the values ​​of new data points located between or outside a set of known discrete data points (sampling points). The core idea is "to infer the unknown from the known." In the embodiments of this application, no restrictions are placed on the interpolation algorithm used; for example, the interpolation algorithm can be Lagrange interpolation or mean-difference interpolation, etc.

[0039] Step S240: Obtain the energy consumption anomaly value based on the mean sequence and the second sequence.

[0040] In this embodiment, the energy consumption anomaly value can be obtained based on the mean sequence and the second sequence using any suitable method. As mentioned above, since the mean sequence is obtained by averaging the sequence values ​​in each of the first sequences, the closer each sequence value in the second sequence is to the corresponding sequence value in the mean sequence, the more normal the current production node is; otherwise, it is more abnormal. That is to say, in the embodiments of this application, the energy consumption anomaly value can be obtained through the similarity between the mean sequence and the second sequence.

[0041] It's important to understand that obtaining the similarity between two sequences (i.e., the mean sequence and the second sequence) is a mature technique and will not be elaborated upon here. For example, the Euclidean distance algorithm or the dynamic time warping algorithm can be used to obtain the similarity between the two sequences. In this embodiment, the reciprocal of the similarity can be used to represent the energy consumption outlier. That is, in this embodiment, the greater the similarity, the smaller the energy consumption outlier; the smaller the similarity, the larger the energy consumption outlier.

[0042] In a specific embodiment of this application, step S240, obtaining the energy consumption anomaly value based on the mean sequence and the second sequence, includes steps S241 to S243.

[0043] Step S241: Based on the mean sequence and the second sequence, obtain the difference sequence, the first difference sequence, and the second difference sequence.

[0044] In this embodiment, the sequence value in the difference sequence is equal to the absolute value of the corresponding sequence value in the mean sequence minus the sequence value in the second sequence. The sequence value in the first difference sequence is equal to the difference between two adjacent sequence values ​​in the mean sequence. The sequence value in the second difference sequence is equal to the difference between two adjacent sequence values ​​in the second sequence.

[0045] Specifically, in this embodiment, the formula for calculating the sequence value of the difference sequence is as follows:

[0046] in, This represents the j-th sequence value in the difference sequence; This represents the j-th sequence value in the mean sequence; This represents the j-th sequence value in the second sequence; This indicates that the absolute value is being calculated.

[0047] In this embodiment, the formula for calculating the sequence value of the first difference sequence is as follows:

[0048] in, This represents the j-th sequence value in the first difference sequence; This represents the j-th sequence value in the mean sequence; This represents the (j+1)th sequence value in the mean sequence.

[0049] In this embodiment, the formula for calculating the sequence value of the second difference sequence is as follows:

[0050] in, This represents the j-th sequence value in the second difference sequence; This represents the j-th sequence value in the second sequence; This represents the (j+1)th sequence value in the second sequence.

[0051] Step S242: Obtain a trend sequence based on the first difference sequence and the second difference sequence.

[0052] In this embodiment, the sequence value in the trend sequence is equal to the product of the corresponding sequence values ​​in the first difference sequence and the second difference sequence. Specifically, in this embodiment, the formula for calculating the trend sequence is as follows:

[0053] in, This represents the j-th sequence value in the trend sequence; This represents the j-th sequence value in the first difference sequence; This represents the j-th sequence value in the second difference sequence.

[0054] Step S243: Obtain the energy consumption anomaly value based on the difference sequence and the trend sequence.

[0055] It is important to understand that in this embodiment, the larger the variance or standard deviation of each sequence value in the trend sequence, the greater the difference in the magnitude of change between the sequence values ​​in the second sequence and the mean sequence, i.e., the greater the difference in the magnitude of change between the energy consumption data of the current node and the energy consumption data of historical nodes. If the sequence value in the trend sequence is positive, it means that the magnitude of change (i.e., increase or decrease) of the sequence values ​​in the second sequence and the mean sequence is the same; if the sequence value in the trend sequence is negative, it means that the magnitude of change of the sequence values ​​in the second sequence and the mean sequence is different. In other words, in the embodiments of this application, the energy consumption anomaly value can be obtained based on the difference sequence and the trend sequence. In other words, in the embodiments of this application, the energy consumption anomaly value can be obtained based on the difference sequence and the trend sequence in any reasonable way. For example, in a specific embodiment of this application, step S243: the step of obtaining the energy consumption anomaly value based on the difference sequence and the trend sequence may include steps S243a to S243c.

[0056] Step S243a: Obtain the first average value based on the difference sequence.

[0057] In this embodiment, the first average value is the average value of each sequence value in the difference sequence. Calculating the first average value of each sequence value in a certain sequence (i.e., the difference sequence) is a mature technique and will not be elaborated here.

[0058] Step S243b: Obtain the trend value based on the trend sequence.

[0059] In this embodiment, the trend value at least represents the number of sequence values ​​less than 0 in the trend sequence. As mentioned above, the more sequence values ​​less than 0 in the trend sequence, the greater the trend difference between the mean sequence and the second sequence.

[0060] Step S243c: Based on the first average value and the trend value, obtain the energy consumption anomaly value.

[0061] In this embodiment, the energy consumption anomaly value can be obtained based on the first average value and the trend value in any reasonable manner. For example, the energy consumption anomaly value can be the product of the first average value and the trend value. In a specific embodiment of this application, step S243, the calculation formula for obtaining the energy consumption anomaly value based on the first average value and the trend value is as follows:

[0062] in, Indicates anomaly values ​​in energy consumption; This represents the mean of the values ​​in the difference sequence. The variance of each value in the trend series is represented by ; S represents the number of values ​​in the trend series. This indicates the number of sequence values ​​less than 0 in the trend sequence; This represents a normalization function used to map the values ​​within the parentheses to the interval [0, 1]. In this embodiment, This represents the first average value; Indicates the trend value.

[0063] In this embodiment, the larger the mean A, the greater the difference between the second sequence and the mean sequence, and the more abnormal the energy consumption. The variance V of the trend sequence and The larger the ratio, the more drastic the difference between the second sequence and the mean sequence, and the greater the trend difference. For example, after the vermicelli raw materials are washed and crushed, the difference between the second sequence and the mean sequence is only due to the different mixing weights during the subsequent mixing process, and the trends of the second sequence and the mean sequence are basically the same. However, if the uniformity of the crushed raw materials is different during the subsequent crushing process, the uneven raw materials will cause large power fluctuations during the subsequent mixing process, resulting in a larger difference between the second sequence and the mean sequence, and thus obtaining larger anomalies in energy consumption.

[0064] Step S300: Obtain the severity value based on the energy consumption anomaly value.

[0065] In this embodiment, the severity value is used at least to characterize the magnitude of the increase in energy consumption anomalies at each production node during continuous fan production.

[0066] In this embodiment, the energy consumption anomaly value can be directly used as the severity value. It should be noted that the various production stages of the rice noodle production process can influence each other. For example, if the raw materials are difficult to crush, energy consumption will definitely increase during the crushing process; if the raw material crushing effect is poor, it will increase energy consumption in the subsequent grinding process. Therefore, when determining the severity value of the current production stage, it is also necessary to analyze the energy consumption anomalies of the completed production stages. Based on this, step S300, obtaining the severity value based on the energy consumption anomaly value, includes steps S310 to S330.

[0067] Step S310: Based on the energy consumption anomaly value, obtain multiple problem nodes from each production node that has been completed by the current continuous fan production.

[0068] In this embodiment, the problem node is the production node whose energy consumption anomaly value is greater than or equal to a preset value among all production nodes. As mentioned above, each production node corresponds to an energy consumption anomaly value. In this embodiment, a preset value can be set according to requirements, for example, the preset value can be 0.5 or 0.6, etc.

[0069] Step S320: Obtain the continuity value based on each problem node.

[0070] In this embodiment, the continuity value is used to characterize the proximity of each problem node to the current continuous production node of vermicelli production. It is important to note that the closer a problem node is to the current production node, the greater the impact of the problem node's anomaly on the current production node. In other words, during continuous vermicelli production, when a problem occurs at one production node, the problem often carries over to subsequent production nodes. For example, if the vermicelli raw material is poorly ground, it can easily lead to uneven spreading of the paste, and areas with thicker paste consume more energy during steaming and require longer cooling times.

[0071] In one embodiment of this application, step S320, obtaining a continuity value based on each problem node, includes steps S321 and S322.

[0072] Step S321: Based on each problem node, obtain the sequence number of the production node corresponding to each problem node and the number of time-series energy consumption parameter values.

[0073] In this embodiment, if a problem node is determined, the sequence number and the number of time-series energy consumption parameter values ​​corresponding to that problem node can be determined, which will not be elaborated here.

[0074] Step S322: Obtain the continuity value based on each quantity and each sequence number.

[0075] In this embodiment, the continuity value can be obtained based on each quantity and each sequence number using any reasonable method. For example, in step S322, the calculation formula for obtaining the continuity value based on each quantity and each sequence number is as follows:

[0076] in, Indicates the continuity value; This represents the normalization function, used to map the values ​​within the parentheses to the range [0, 1]; X represents the number of problem nodes. This represents the number of time-series energy consumption parameter values ​​corresponding to the i-th problem node; This represents the sequence number of the production node corresponding to the i-th problem node in the continuous production process of fans.

[0077] In this embodiment, if the sequence number of a problem node is larger, the problem node is closer to the current production node, which means that the problem node has a greater impact on the severity of the current production node; if the number of time-series energy consumption parameter values ​​corresponding to a problem node is larger, it means that the problem node occupies a longer time in the entire production process, which means that the problem node has a greater impact on the severity of the current production node.

[0078] Step S330: Obtain the severity value based on the continuity value.

[0079] In embodiments of this application, the severity value can be obtained based on the persistence value in any reasonable manner. For example, the persistence value can be directly used as the severity value.

[0080] As mentioned above, the larger the energy consumption anomaly value of a certain production node, the greater its impact on other subsequent production nodes. Based on this, in one embodiment of this application, step S330, obtaining the severity value based on the continuity value, includes steps S331 to S334.

[0081] Step S331: Obtain the cumulative value based on the continuity value.

[0082] In this embodiment, the cumulative value is used to characterize at least the ratio of the number of each problem node to the number of production nodes that have been completed in the current continuous fan production. That is, in this embodiment, the more problem nodes generated before the current production node, the greater the impact on that production node. In other words, in the embodiments of this application, the cumulative value can be obtained based on the continuity value in any reasonable manner. For example, the formula for calculating the cumulative value can be:

[0083] in, Indicates cumulative value; Indicates the number of each problem node; This indicates the number of production nodes that have been completed in the current continuous production of fans; Indicates a continuity value.

[0084] In a specific embodiment of this application, step S331: obtaining the cumulative value based on the continuity value includes steps S331a and S331b.

[0085] Step S331a: Based on each problem node, obtain the second average value and the anomaly ratio.

[0086] In this embodiment, the second average value is the average of the energy consumption anomalies of each production node that has been completed in the current continuous fan production. The anomaly ratio is the ratio of the number of problematic nodes to the number of production nodes that have been completed in the current continuous fan production.

[0087] Step S331b: Obtain the cumulative value based on the continuity value, the second average value, and the anomaly ratio.

[0088] In embodiments of this application, the cumulative value can be the sum of the continuity value, the second average value, and the anomaly ratio, or step S331b: based on the continuity value, the second average value, and the anomaly ratio, the calculation formula for the cumulative value is as follows:

[0089] in, Indicates cumulative value; This represents the average (also known as the second average) of the energy consumption anomalies at each production node that has been completed in the current continuous production of fans. Indicates the number of each problem node; This indicates the number of production nodes that have been completed in the current continuous production of fans; Indicates a continuity value.

[0090] Step S332: Obtain the anomaly sequence based on the energy consumption anomaly values ​​corresponding to each problem node.

[0091] It is important to understand that obtaining the corresponding sequence (i.e., the abnormal sequence) based on multiple values ​​(i.e., the energy consumption anomalies corresponding to each problem node) is a mature technology, which will not be elaborated here.

[0092] Step S333: Obtain the abnormal repair value based on the abnormal sequence.

[0093] As discussed earlier, each problematic production node prompts the continuous vermicelli production line to adjust its response speed to resolve the anomaly. For example, if the dried vermicelli has a high moisture content, the continuous vermicelli production line will increase the drying temperature. In other words, throughout the production process, if the energy consumption anomalies corresponding to each problematic node gradually decrease, it indicates that the adjusted response speed meets the requirements; conversely, if the energy consumption anomalies corresponding to each problematic node gradually increase, it indicates that the adjusted response speed does not meet the requirements.

[0094] In this embodiment, the anomaly repair value is used at least to characterize the difficulty of repairing energy consumption anomalies. As mentioned above, if the energy consumption anomaly values ​​corresponding to each problem node show a gradually decreasing trend, it indicates that the difficulty of repairing the energy consumption anomaly is relatively low; if the energy consumption anomaly values ​​corresponding to each problem node show a gradually increasing trend, it indicates that the difficulty of repairing the energy consumption anomaly is relatively high. Based on this, step S333, based on the anomaly sequence, obtains the anomaly repair value, including steps S335 to S339.

[0095] Step S335: Based on the abnormal sequence, obtain the maximum sequence value.

[0096] It is important to understand that extracting the maximum sequence value from a sequence is a mature technique.

[0097] Step S336: Based on the maximum sequence value, obtain multiple subsequent sequence values ​​from the abnormal sequence.

[0098] In this embodiment, the subsequent sequence value is the sequence value that is sorted after the maximum sequence value in the abnormal sequence. Reading all sequence values ​​after a certain sequence value (i.e., the maximum sequence value) in a certain sequence (i.e., the abnormal sequence) is a mature technology and will not be elaborated here.

[0099] Step S337: Obtain the fitted straight line based on the maximum sequence value and each subsequent sequence value.

[0100] It should be clear that forming a fitted straight line using multiple sequence values ​​is a mature technique, which will not be elaborated upon here.

[0101] Step S338: Obtain the slope based on the fitted straight line.

[0102] It's important to understand that once the fitted line is determined, the corresponding slope is also determined. In other words, obtaining the slope based on the fitted line is a mature technique, which will not be elaborated upon here.

[0103] Step S339: Obtain the anomaly repair value based on the slope.

[0104] In embodiments of this application, the anomaly repair value can be obtained based on the slope in any reasonable manner. For example, the slope can be used as the anomaly repair value.

[0105] Step S334: Obtain the severity value based on the cumulative value and the anomaly repair value.

[0106] In an embodiment of this application, step S334: Based on the cumulative value and the anomaly repair value, the calculation formula for obtaining the severity value is as follows:

[0107] Where Y represents the severity value; M represents the cumulative value; M represents the anomaly repair value. This represents the normalization function, used to map the values ​​within the parentheses to the range [0, 1]; t represents a constant, which can be set according to requirements, for example: the constant t can be 0.5 or 0.6, etc.

[0108] In this embodiment, a larger cumulative value or anomaly repair value indicates a greater severity level, meaning a more severe energy consumption anomaly caused by the continuous vermicelli production line. This suggests that the P value of the PID controller needs to be increased in subsequent processes to improve the response speed of the continuous vermicelli production line and prevent prolonged energy waste due to slow equipment response when anomalies occur at a certain stage of vermicelli production. Conversely, a smaller cumulative value or anomaly repair value indicates a smaller severity level, meaning the energy consumption anomaly caused by the continuous vermicelli production line is effectively controlled. This suggests that the P value of the PID controller does not need to be excessively increased in subsequent processes to avoid an overly rapid response from the continuous vermicelli production line leading to increased energy consumption.

[0109] Step S400: Obtain the control coefficient based on the severity value.

[0110] It's important to understand that in a continuous vermicelli production line, a PID controller can be used to adjust key parameters in the production process (such as temperature and flow rate) to optimize energy consumption. By adjusting the P value, the system's response speed and stability can be balanced, thereby reducing unnecessary energy consumption.

[0111] As mentioned above, the higher the severity value, the greater the need to increase the P value of the PID controller. Therefore, in the embodiments of this application, step S400, obtaining the control coefficient based on the severity value, may include steps S410 and S420.

[0112] Step S410: Obtain the default proportional gain coefficient of the PID controller based on the tuning method.

[0113] It's important to understand that tuning is a method for obtaining PID controller parameters; this is a mature technology and will not be elaborated upon here. The PID controller is a very common and well-known type of controller used to control industrial processes, mechanical systems, and various other systems. PID stands for Proportional, Integral, and Derivative, representing the three main components of the controller.

[0114] Step S420: Obtain the control coefficient based on the default proportional gain coefficient and the severity value.

[0115] In this embodiment, the control coefficient can be the product of the default proportional gain coefficient and the severity value. In this embodiment, a higher severity value indicates a greater need for a rapid response to promptly eliminate energy consumption anomalies. A slow response at this point could lead to prolonged energy waste. Conversely, a lower severity value indicates a lower likelihood of subsequent energy consumption anomalies, necessitating a reduced response speed to prevent increased energy consumption due to a rapid response.

[0116] Step S500: Adjust the P value of the PID controller based on the control coefficient.

[0117] In this embodiment, the formula for calculating the P value of the PID controller can be as follows: Current P value = Historical P value × Control coefficient. Generally, the P value of a PID controller cannot be infinitely large or infinitely small; that is, the P value of a PID controller has a certain range. In the embodiments of this application, if the calculated current P value is greater than the maximum range value corresponding to the PID controller's P value, then the current P value can be set to the maximum range value; if the calculated current P value is less than the minimum range value corresponding to the PID controller's P value, then the current P value can be set to the minimum range value.

[0118] Of course, in other embodiments of this application, the P value of the PID controller can also be adjusted in other ways as needed.

[0119] The embodiment of the node energy consumption monitoring and optimization method for a continuous vermicelli production line proposed in this application analyzes the abnormal energy consumption values ​​of each production node during the continuous vermicelli production process to obtain the severity value of the current production node's energy consumption anomaly, and then adjusts the P value of the PID controller based on the severity value. This avoids the phenomenon of slow response of production equipment leading to long-term energy waste when a large anomaly occurs at a certain node of vermicelli production, and also avoids the phenomenon of excessive response of production equipment leading to increased energy consumption when a small anomaly occurs at a certain node of vermicelli production.

[0120] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0121] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the methods, apparatuses, and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or modules may be electrical, mechanical, or other forms.

[0123] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0125] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0126] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video optical disc), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0127] Although embodiments of this application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles of this application.

Claims

1. A method for monitoring and optimizing node energy consumption in a continuous vermicelli production line, wherein the continuous vermicelli production line includes a PID controller, characterized in that, The method includes: Acquire historical node energy consumption data and current node energy consumption data; the node energy consumption data includes at least the time-series energy consumption parameter values ​​of the corresponding production node during continuous fan production; Based on the historical node energy consumption data and the current node energy consumption data, energy consumption anomalies are obtained; the energy consumption anomalies are used at least to characterize the magnitude of the difference between the current node energy consumption data and the historical node energy consumption data. Based on the energy consumption anomaly value, a severity value is obtained; the severity value is at least used to characterize the magnitude of the increase in energy consumption anomaly value corresponding to each production node during the current continuous production of fans; Based on the severity value, the control coefficient is obtained; Based on the control coefficient, the P value of the PID controller is adjusted.

2. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 1, characterized in that, The step of obtaining abnormal energy consumption values ​​based on the historical node energy consumption data and the current node energy consumption data includes: Based on the historical node energy consumption data, multiple first sequences are obtained; the first sequence is a sequence formed by multiple time-series energy consumption parameter values ​​during the continuous production of any batch of fans in the historical node energy consumption data. Based on the current node energy consumption data, a second sequence is obtained; the second sequence is a sequence formed by multiple time-series energy consumption parameter values ​​during continuous fan production in the current node energy consumption data; Based on multiple first sequences, obtain the mean sequence; The energy consumption anomaly value is obtained based on the mean sequence and the second sequence.

3. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 2, characterized in that, Before obtaining the mean sequence based on multiple first sequences, the method further includes: If the lengths of the first sequence and the second sequence are different, then the longest sequence is obtained based on the lengths of the first sequence and the second sequence. The sequence lengths of each first sequence and the second sequence are increased to the same length as the longest sequence based on the difference algorithm.

4. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 3, characterized in that, The step of obtaining the energy consumption anomaly value based on the mean sequence and the second sequence includes: Based on the mean sequence and the second sequence, a difference sequence, a first difference sequence, and a second difference sequence are obtained; the sequence value in the difference sequence is equal to the sequence value in the second sequence minus the absolute value of the corresponding sequence value in the mean sequence; the sequence value in the first difference sequence is equal to the difference between two adjacent sequence values ​​in the mean sequence; the sequence value in the second difference sequence is equal to the difference between two adjacent sequence values ​​in the second sequence. A trend sequence is obtained based on the first difference sequence and the second difference sequence; the sequence value in the trend sequence is equal to the product of the corresponding sequence values ​​in the first difference sequence and the second difference sequence. The energy consumption anomaly value is obtained based on the difference sequence and the trend sequence.

5. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 4, characterized in that, The step of obtaining the energy consumption anomaly based on the difference sequence and the trend sequence includes: Based on the difference sequence, a first average value is obtained; the first average value is the average value of each sequence value in the difference sequence. Based on the trend sequence, a trend value is obtained; the trend value at least represents the number of sequence values ​​less than 0 in the trend sequence; Based on the first average value and the trend value, the energy consumption anomaly value is obtained.

6. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to any one of claims 1 to 5, characterized in that, The process of obtaining a severity value based on the energy consumption anomaly includes: Based on the energy consumption anomaly value, multiple problem nodes are obtained from each production node that has been completed in the current continuous production of fans; the problem node is the production node whose corresponding energy consumption anomaly value is greater than or equal to a preset value. Based on each problem node, a continuity value is obtained; the continuity value is used to characterize at least the degree of proximity between each problem node and the current continuous production node of fans. The severity value is obtained based on the continuity value.

7. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 6, characterized in that, The process of obtaining continuity values ​​based on each problem node includes: Based on each problem node, obtain the sequence number of the production node corresponding to each problem node and the number of time-series energy consumption parameter values; The continuity value is obtained based on each quantity and each sequence number.

8. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 6, characterized in that, The process of obtaining the severity value based on the continuity value includes: Based on the continuity value, a cumulative value is obtained; the cumulative value is used to characterize at least the ratio of the number of each problem node to the number of each production node that has been completed in the current continuous production of fans. Based on the energy consumption anomalies corresponding to each problem node, obtain the anomaly sequence; Based on the abnormal sequence, an abnormal repair value is obtained; the abnormal repair value is used to characterize at least the difficulty of repairing the energy consumption anomaly. The severity value is obtained based on the cumulative value and the anomaly repair value.

9. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 8, characterized in that, The step of obtaining the cumulative value based on the continuity value includes: Based on each problem node, a second average value and an anomaly ratio are obtained; the second average value is the average of the energy consumption anomalies of each production node that has been completed in the current continuous production of fans; the anomaly ratio is the ratio of the number of each problem node to the number of each production node that has been completed in the current continuous production of fans. The cumulative value is obtained based on the continuity value, the second average value, and the anomaly ratio.

10. The method for monitoring and optimizing node energy consumption in a continuous vermicelli production line according to claim 8, characterized in that, The step of obtaining the anomaly repair value based on the anomaly sequence includes: Based on the abnormal sequence, obtain the maximum sequence value; Based on the maximum sequence value, multiple subsequent sequence values ​​are obtained from the abnormal sequence; the subsequent sequence values ​​are the sequence values ​​in the abnormal sequence that are ordered after the maximum sequence value. Based on the maximum sequence value and each subsequent sequence value, a fitted straight line is obtained; Based on the fitted straight line, the slope is obtained; The anomaly repair value is obtained based on the slope.

Images