Multi-process spinning energy consumption optimization decision-making system

Abstract

The invention relates to the technical field of spinning production, and discloses a multi-process spinning energy consumption optimization decision system, which comprises a data acquisition module, an energy consumption analysis module, a strategy generation module, a scheduling optimization module, a reference comparison module and a decision output module. The data acquisition module acquires equipment parameters and energy consumption data and sets a monitoring interval; the energy consumption analysis module divides process nodes and generates energy consumption feature vectors; the strategy generation module extracts key indexes to establish optimization rules; the scheduling optimization module identifies the operation mode and calculates the energy consumption fluctuation amplitude; the reference comparison module deduces an optimal energy consumption threshold value and generates a deviation sequence; and the decision output module integrates the deviation sequence to form an optimized decision scheme. According to the system, fine management and dynamic optimization of energy consumption of the whole spinning process are achieved, the energy utilization efficiency is improved, the production cost is reduced, and the system is suitable for energy consumption optimization control in the spinning production process.

Description

Technical Field

[0001] The invention relates to the technical field of spinning production, in particular to a multi-process spinning energy consumption optimization decision system. Background Art

[0002] In the spinning production process, the energy consumption management of multiple processes has always been the focus of the industry. The traditional spinning energy consumption management method has many shortcomings and cannot meet the needs of the modern textile industry for efficient, energy-saving and low-carbon production.

[0003] From the perspective of data collection and monitoring, traditional systems are often unable to achieve comprehensive and real-time collection of equipment parameters and energy consumption data for multiple processes. There is a lack of refined energy consumption monitoring intervals set according to the characteristics of different processes, which makes it impossible to accurately grasp the actual energy consumption status of each process and it is difficult to discover energy consumption anomalies and high-energy consumption links.

[0004] In terms of energy consumption analysis, traditional methods lack scientific division of process nodes and in-depth feature analysis of energy consumption data. It is impossible to build an effective process feature library, and it is difficult to mine the intrinsic relationship between process parameter vectors through similar process matching and cluster analysis, which makes the analysis of energy consumption data remain superficial and cannot generate vectors that can accurately reflect the energy consumption characteristics of the process, thus affecting the formulation of subsequent optimization strategies.

[0005] In the strategy generation stage, it is difficult for traditional methods to accurately extract key energy consumption indicators from complex energy consumption data. There is a lack of systematic energy consumption optimization rules associated with process nodes, and the optimization rules cannot be dynamically adjusted according to the number of process nodes. As a result, the optimization strategy is not targeted and effective enough, and it is impossible to achieve accurate control of the energy consumption of each process node.

[0006] During the scheduling optimization process, traditional systems cannot effectively identify the timing factors and fluctuation factors in the equipment operation mode, and it is difficult to build a state transition network and dynamically schedule key energy consumption indicators based on it. It is also impossible to accurately calculate the energy consumption fluctuation range of each process node under different scheduling strategies, which makes energy consumption scheduling lack of scientific basis and difficult to achieve dynamic optimization of energy consumption.

[0007] In terms of benchmark comparison and decision output, traditional methods lack a scientific method for deriving the optimal energy consumption threshold and are unable to generate an accurate process energy consumption deviation sequence by comparing with historical data. Moreover, when integrating the deviation sequence to form an optimized decision-making plan, there is a lack of comprehensive analysis of the energy consumption fluctuation direction, convergence rate and diffusion rate, resulting in poor scientificity and operability of the decision-making plan. Summary of the invention

[0008] The purpose of the present invention is to provide a multi-process spinning energy consumption optimization decision system to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solution: a multi-process spinning energy consumption optimization decision-making system, and the system includes: A data acquisition module, which is used to obtain equipment parameters and energy consumption data in the spinning production process, and set an energy consumption monitoring interval corresponding to the process; An energy consumption analysis module, which is used to divide a plurality of process nodes within the energy consumption monitoring interval, perform feature analysis on the energy consumption data of each process node, and generate an energy consumption feature vector corresponding to the process node; A strategy generation module, which is used to extract key energy consumption indicators from the energy consumption feature vector, establish an energy consumption optimization rule associated with the process node, and obtain the process control parameters corresponding to the rule; A scheduling optimization module, which is used to identify the equipment operation mode in the process control parameters, perform dynamic scheduling on the key energy consumption indicators according to the operation mode, and calculate the energy consumption fluctuation range of each process node under different scheduling strategies; A benchmark comparison module, which is used to deduce the optimal energy consumption threshold according to the energy consumption fluctuation range, and generate a process energy consumption deviation sequence by comparing the current process energy consumption value with the optimal energy consumption threshold; A decision output module, which is used to analyze the process energy consumption deviation sequence, and integrate the process energy consumption deviation sequence into an energy consumption optimization decision-making scheme based on the energy consumption fluctuation trend of the process node.

[0010] Preferably, the implementation method of the energy consumption analysis module includes: constructing a process feature library corresponding to the process node, and the process feature library includes a process parameter vector mapped by equipment parameters and energy consumption data; Perform similar process matching on the process parameter vector, and divide the process parameter vector into process clustering groups according to the matching result; extract the distribution center point of the energy consumption data from the process clustering group, and set the distribution center point as the process node.

[0011] Preferably, dividing the process clustering group of the process parameter vector further includes: According to the equipment type and production stage in the process parameter vector, extract equipment rotation speed, yarn count, and environmental temperature and humidity parameters, and generate a process feature label based on the above parameters; Associate the process feature label with the process parameter vector, and screen the process parameter vectors with a process similarity higher than the preset process threshold to form a process clustering group by calculating the process similarity between the feature labels.

[0012] Preferably, the implementation method of generating the energy consumption feature vector corresponding to the process node includes: For each process node, according to the time series position of the node in the energy consumption monitoring interval, obtain the energy consumption fluctuation data of the node within a preset period, and calculate the energy consumption fluctuation coefficient of the node; When the energy consumption fluctuation coefficient exceeds the first fluctuation threshold, mark the node as a high-energy-consuming node and extract its energy consumption data to form an energy consumption feature vector; when the energy consumption fluctuation coefficient is lower than the first fluctuation threshold, mark the node as a steady-state node, and perform weighted superposition on the energy consumption data of the adjacent nodes of the node, and reconstruct the superimposed data into an energy consumption feature vector.

[0013] Preferably, the implementation manner of the policy generation module includes: Separate the equipment energy consumption ratio, idling energy consumption ratio and load fluctuation parameters from the energy consumption feature vector, and generate an energy consumption optimization rule for the process node based on the above parameters; If the number of process nodes covered by the current energy consumption optimization rule is less than the preset node threshold, traverse the energy consumption feature vectors of adjacent process nodes, and add the energy consumption indicators not included in the optimization rules of adjacent nodes to the current rule.

[0014] Preferably, the implementation manner of the scheduling optimization module includes: obtaining the timing factor of the start-stop frequency and the fluctuation factor of the load change amplitude in the equipment operation mode; Construct a state transition network associated with the timing factor and the fluctuation factor, and determine the energy consumption fluctuation amplitude under different scheduling strategies according to the transition probabilities of each path in the network.

[0015] Preferably, constructing the state transition network further includes: Identify the periodic characteristics of the timing factor. If the current periodic characteristics exactly match the preset production cycle, set the timing factor as the starting node of the state transition network; Calculate the transfer correlation degree between the timing factor and the fluctuation factor, and generate the intermediate nodes and termination nodes of the state transition network in descending order of the correlation degree; Perform state backtracking on the termination node. When the correlation degree of the termination node is lower than the preset correlation threshold, output it as the final path of the state transition network.

[0016] Preferably, the implementation manner of calculating the energy consumption fluctuation amplitude includes: Statistically calculate the mean value of the timing factor and the range of the fluctuation factor of each termination node in the state transition network, and calculate the global variance of all node factors; Take the difference between the mean value of the timing factor of a single termination node and the mean value of the timing factors of adjacent nodes, divide by the global variance to obtain the timing fluctuation coefficient; at the same time, calculate the ratio of the range of the fluctuation factor to the global variance, and weight and sum the two as the energy consumption fluctuation amplitude of the node.

[0017] Preferably, the implementation manner of deriving the optimal energy consumption threshold includes: Extract the fluctuation pattern in the historical data that is closest to the current energy consumption fluctuation amplitude, and calculate the Manhattan distance in the time series distribution between the two as the first reference value; Statistically analyze the difference in the number of extreme points between the current energy consumption fluctuation range and the historical fluctuation pattern, and use the difference quantity as the second reference value. Based on the linear combination of the first reference value and the second reference value, match the optimal energy consumption threshold in the preset energy consumption threshold table.

[0018] Preferably, the implementation method of the decision output module includes: dividing the positive fluctuation interval and the negative fluctuation interval according to the energy consumption fluctuation direction of each node in the process energy consumption deviation sequence; Extract the convergence rate of the energy consumption deviation in the positive fluctuation interval and the diffusion rate of the energy consumption deviation in the negative fluctuation interval, and perform weighted fusion of the two according to the production weight of the process nodes to generate the core adjustment parameter of the energy consumption optimization decision plan.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: The data acquisition module can obtain the equipment parameters and energy consumption data in the spinning production process, and set the energy consumption monitoring interval corresponding to the process, realizing the real-time, comprehensive acquisition and refined monitoring of the energy consumption data of each process, providing an accurate and reliable data basis for subsequent energy consumption analysis and optimization.

[0020] The energy consumption analysis module constructs a process feature library, performs similar process matching and clustering analysis on the process parameter vector, scientifically divides the process nodes, and generates energy consumption feature vectors in different ways for different types of nodes (high energy consumption nodes and steady state nodes), realizing the in-depth feature analysis of the energy consumption data, being able to accurately reveal the energy consumption characteristics and laws of each process node, and providing strong support for formulating targeted energy consumption optimization strategies.

[0021] The strategy generation module extracts key energy consumption indicators from the energy consumption feature vectors, establishes energy consumption optimization rules associated with the process nodes, and can dynamically expand the optimization rules according to the number of process nodes, ensuring the comprehensiveness and pertinence of the optimization rules, being able to effectively cover the energy consumption optimization needs of each process node, and improving the efficiency and effect of energy consumption optimization.

[0022] The scheduling optimization module obtains the timing factor and fluctuation factor in the equipment operation mode, constructs a state transition network, calculates the energy consumption fluctuation range of each process node under different scheduling strategies, realizes the dynamic scheduling and scientific analysis of the key energy consumption indicators, provides a scientific basis for selecting the optimal energy consumption scheduling strategy, can effectively reduce the energy consumption fluctuation, and improve the stability and efficiency of energy utilization.

[0023] The benchmark comparison module extracts the fluctuation pattern from the historical data, calculates the Manhattan distance and the difference in the number of extreme points, deduces the optimal energy consumption threshold, and generates the process energy consumption deviation sequence, providing a scientific benchmark for accurately evaluating the current process energy consumption status, being able to timely detect the energy consumption deviation, and providing a basis for subsequent decision-making adjustment.

[0024] The decision output module divides the fluctuation range according to the process energy consumption deviation sequence, extracts the convergence rate and diffusion rate, generates the core adjustment parameters, integrates the deviation sequence into an energy consumption optimization decision plan, realizes the intelligent transformation from data to decision-making, can provide scientific and operable energy consumption optimization decisions for production management personnel, guide production practice, significantly reduce the energy consumption cost of spinning production, and improve the economic and environmental benefits of production. Brief Description of the Drawings

[0025] Figure 1 It is the working principle diagram of the multi-process spinning energy consumption optimization decision-making system of the present invention; Figure 2 It is the flow chart of clustering and grouping of process parameter vectors; Figure 3 It is the flow chart of generating energy consumption optimization rules. Detailed Embodiments

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] Please refer to Figures 1-3 , the multi-process spinning energy consumption optimization decision-making system involved in the present invention, this system includes: a data acquisition module, an energy consumption analysis module, a strategy generation module, a scheduling optimization module, a benchmark comparison module and a decision output module. The specific implementation steps are as follows: The data acquisition module obtains the equipment parameters and energy consumption data in the spinning production process, and sets the energy consumption monitoring interval corresponding to the process. For example, in the carding process, collect equipment parameters such as the rotation speed and feeding amount of the carding machine, as well as the real-time energy consumption data of this process, and set a specific energy consumption monitoring interval for the carding process to limit the scope and time period of data acquisition.

[0028] The energy consumption analysis module divides multiple process nodes within the energy consumption monitoring interval, analyzes the characteristics of the energy consumption data of each process node, and generates an energy consumption feature vector corresponding to the process node. For example, within the energy consumption monitoring interval of the drawing process, several process nodes are divided according to the time sequence or process stage of the production process. Each node corresponds to a specific production time period or process operation step, and then the energy consumption data of each node is analyzed to extract the key information that can reflect the energy consumption characteristics of this node, forming an energy consumption feature vector.

[0029] The strategy generation module extracts key energy consumption indicators from the energy consumption feature vector, establishes energy consumption optimization rules associated with process nodes, and obtains the process control parameters corresponding to the rules. Taking the roving process as an example, key indicators such as the proportion of equipment energy consumption and the proportion of idle energy consumption are extracted from the energy consumption feature vector of this process node. Based on these indicators, corresponding energy consumption optimization rules are established. For example, when the proportion of equipment energy consumption exceeds a certain threshold, the operating parameters of the equipment are adjusted. At the same time, the process control parameters corresponding to these rules are determined, such as the rotation speed adjustment value and the feeding amount adjustment value of the equipment.

[0030] The scheduling optimization module identifies the equipment operating mode in the process control parameters, dynamically schedules the key energy consumption indicators according to the operating mode, and calculates the energy consumption fluctuation range of each process node under different scheduling strategies. In the spinning process, it is identified that the equipment operating modes include normal operating mode, frequent start-stop mode, etc. For different operating modes, key energy consumption indicators such as load fluctuation parameters are dynamically adjusted and scheduled. Then, the energy consumption fluctuation range of this process node under different scheduling strategies is calculated to evaluate the effects of different scheduling strategies.

[0031] The benchmark comparison module derives the optimal energy consumption threshold based on the energy consumption fluctuation range, and generates a process energy consumption deviation sequence by comparing the current process energy consumption value with the optimal energy consumption threshold. For example, in the winding process, based on the energy consumption fluctuation range of this process node, combined with historical data and production process requirements, the optimal energy consumption threshold of this process is derived and determined. Then, the actual energy consumption value of the current process is compared with the optimal energy consumption threshold, and the difference between the two is calculated to form a process energy consumption deviation sequence to reflect the difference between the current energy consumption and the optimal energy consumption.

[0032] The decision output module analyzes the process energy consumption deviation sequence, and integrates the process energy consumption deviation sequence into an energy consumption optimization decision plan based on the energy consumption fluctuation trend of the process node. In the entire spinning production process, the decision output module analyzes the process energy consumption deviation sequences of each process node, judges whether the energy consumption fluctuation trend of each node is rising, falling or remaining stable. Then, based on these trends and deviation sequences, the optimization suggestions for each process are integrated to form a complete energy consumption optimization decision plan to guide the energy consumption optimization adjustment in the production process.

[0033] The technical solution of the present invention will be further described in detail below with specific embodiments. Example 1:

[0034] The specific implementation method of the energy consumption analysis module is as follows: construct a process feature library corresponding to process nodes, and the process feature library contains process parameter vectors mapped from equipment parameters and energy consumption data. In the spinning production system, different process nodes have unique equipment operating states and energy consumption characteristics. For example, the carding process involves the operation of key components such as the licker-in, cylinder, and doffer of the carding machine. Equipment parameters such as the rotational speed and vibration frequency of these components directly affect the energy consumption of the carding process. At the same time, the energy consumption data of the carding process not only includes the total energy consumption value but also covers the time distribution characteristics of energy consumption, such as the instantaneous power change curve. Integrate and process these equipment parameters and energy consumption data and map them into high-dimensional process parameter vectors. Each dimension represents a specific equipment parameter or energy consumption feature. For example, the first dimension of the vector can represent the rotational speed of the licker-in of the carding machine, the second dimension represents the vibration frequency of the cylinder, and the third dimension represents the energy consumption value per unit time, etc. Through this mapping method, the complex equipment operating state and energy consumption data are transformed into a mathematically processable vector form, which is convenient for subsequent analysis and processing.

[0035] Perform similar process matching on the process parameter vectors, and divide the process clustering groups of the process parameter vectors according to the matching results. In actual spinning production, the same type of process nodes may have certain differences due to factors such as production batches and equipment models, but generally have similar energy consumption characteristics and equipment operating modes. The process of similar process matching first requires defining a suitable similarity measurement method. The Euclidean distance can be used as the similarity measurement standard. For two process parameter vectors, calculate their Euclidean distance in the high-dimensional space. The smaller the distance, the higher the similarity. Cosine similarity can also be considered. It measures the similarity of the directions of two vectors and is suitable for processing high-dimensional sparse data. After calculating the similarity, use the hierarchical clustering algorithm to perform clustering analysis on the process parameter vectors. The hierarchical clustering algorithm forms a tree-shaped clustering structure by continuously merging or splitting clustering groups. In this system, according to the preset similarity threshold, merge the process parameter vectors with similarity higher than this threshold into a process clustering group. For example, for multiple nodes in the carding process, by calculating the similarity of their process parameter vectors, group the nodes with higher similarity into the same clustering group. In this way, the nodes in the carding process can be classified according to energy consumption characteristics and equipment operating modes, which is convenient for subsequent targeted analysis and optimization of different types of nodes.

[0036] Extract the distribution center point of the energy consumption data from the process clustering group and set the distribution center point as the process node. In each process clustering group, the energy consumption data presents certain distribution characteristics. By calculating statistics such as the mean and median of the energy consumption data dimension in all process parameter vectors within the clustering group, the distribution center point of the energy consumption data can be determined. For example, for a clustering group containing multiple carding process nodes, calculate the mean of the energy consumption data of all nodes within the group, and use this mean as the energy consumption distribution center point of the clustering group. Setting the distribution center point as the process node can represent the typical energy consumption characteristics and equipment operation modes of the clustering group. The advantage of doing this is that it can simplify the subsequent analysis and processing process, convert the analysis of a large number of process nodes into the analysis of a few representative nodes, and at the same time retain the main characteristics and information of the original data.

[0037] In addition, the process clustering group that divides the process parameter vector also includes: extracting the equipment speed, yarn count, and environmental temperature and humidity parameters according to the equipment type and production stage in the process parameter vector, and generating process feature labels based on the above parameters. The equipment type is an important basis for distinguishing different processes, and different types of equipment have different energy consumption characteristics and operation modes. In spinning production, there are significant differences in the structure and function of equipment such as carding machines, draw frames, roving frames, and spinning frames, and their energy consumption characteristics are also different. The production stage reflects the technological process of spinning production. From different stages such as opening and cleaning, carding, drawing, to roving and spinning, the production tasks and technological requirements in each stage are different, and the energy consumption characteristics also change accordingly. The equipment speed directly affects the energy consumption level of the equipment. Generally speaking, the higher the speed, the greater the energy consumption, but at the same time, the production efficiency may also be higher. The yarn count is an index to measure the thickness of the yarn, and different counts of yarn have different requirements for equipment and energy consumption during production. The environmental temperature and humidity parameters have an important impact on the spinning production process. Too high or too low temperature and humidity may cause the equipment to operate unstably, increase energy consumption, and also affect the quality of the yarn. Generating process feature labels based on these parameters, each label represents a specific combination of equipment type, production stage, and parameters. For example, a process feature label can be expressed as "carding process - high speed - high count yarn - suitable temperature and humidity". Such a label can accurately describe the characteristics and status of the process node, providing more abundant information for subsequent process clustering and analysis.

[0038] Associate process feature tags with process parameter vectors. By calculating the process similarity between feature tags, screen out the process parameter vectors with similarity higher than the preset process threshold to form process clustering groups. Each process parameter vector is associated with one or more process feature tags, which describe the characteristics and states of the process nodes represented by the vector. When calculating the process similarity between feature tags, semantic similarity calculation methods can be used. For equipment type tags, score according to the functional and structural similarity of the equipment. For example, there is a certain similarity in function between a carding machine and a comber, and the similarity score of their equipment type tags can be 0.7. For production stage tags, score according to the sequence and process relevance of the production process. For example, the carding stage and the drawing stage are two consecutive stages in spinning production, and the similarity score of their production stage tags can be 0.8. For parameter tags such as equipment speed, yarn count, and environmental temperature and humidity, score according to the proximity of parameter values. Combine these tag similarities to obtain the process similarity between feature tags. When the similarity between two process feature tags is higher than the preset process threshold, classify their corresponding process parameter vectors into the same process clustering group. In this way, process nodes with similar characteristics and states can be more accurately grouped into the same group, improving the accuracy and effectiveness of process clustering.

[0039] In practical applications, the process of constructing a process feature library needs to consider the integrity and accuracy of data. High-precision sensors and data acquisition systems are required for the collection of equipment parameters and energy consumption data to ensure the authenticity and reliability of the data. When mapping data into process parameter vectors, data preprocessing is required, including operations such as data cleaning and normalization, to eliminate noise and outliers in the data and improve the quality of the vectors. When performing similar process matching on process parameter vectors, the selection of the similarity measurement method is crucial. Different similarity measurement methods are applicable to different types of data and application scenarios, and need to be selected and adjusted according to specific situations. In the clustering process, the preset similarity threshold also affects the quality of the clustering results. Too high a threshold may lead to overly scattered clustering groups, while too low a threshold may lead to overly concentrated clustering groups, losing the meaning of clustering. Therefore, it is necessary to determine an appropriate similarity threshold through experiments and analysis.

[0040] When extracting the distribution center point of energy consumption data from the process clustering group, it is necessary to consider the distribution characteristics of the data. For data with a normal distribution, the mean is a good representative of the distribution center point; however, for data with a non-normal distribution, the median may be more representative of the central tendency of the data. Therefore, when calculating the distribution center point, it is necessary to analyze the distribution characteristics of the data and select an appropriate statistic as the distribution center point. When generating process feature labels, it is necessary to ensure that the labels can accurately reflect the characteristics and states of the process nodes. The design of the labels should be concise and clear, while having sufficient information content. When associating process feature labels with process parameter vectors, it is necessary to establish an effective mapping mechanism to ensure that each vector can be accurately associated with the corresponding label. When calculating the process similarity between feature labels, the accuracy of the semantic similarity calculation method directly affects the result of process clustering. It is necessary to comprehensively consider all aspects of the labels and adopt an appropriate scoring method to improve the accuracy of similarity calculation.

[0041] Through the above implementation methods, the energy consumption analysis module can effectively analyze and process the energy consumption data in the spinning production process, classify the complex process nodes according to the energy consumption characteristics and equipment operation modes, extract representative process nodes, and provide strong support for subsequent energy consumption optimization decisions. This method can not only improve the efficiency and accuracy of energy consumption analysis, but also provide more targeted energy consumption optimization suggestions for spinning production enterprises, helping enterprises reduce production costs, improve production efficiency, and achieve sustainable development. Example 2:

[0042] The implementation method of generating the energy consumption characteristic vector corresponding to the process node is as follows: For each process node, according to the chronological position of the node in the energy consumption monitoring interval, obtain the energy consumption fluctuation data of the node within the preset period, and calculate the energy consumption fluctuation coefficient. During the spinning production process, each process node is arranged in chronological order within the energy consumption monitoring interval to form a continuous production process. The setting of the preset period needs to be combined with the production rhythm and data collection frequency of the specific process. For example, for the high-speed spinning process, the preset period can be set to 15 minutes, while for the relatively slow opening and cleaning process, the preset period can be extended to 1 hour. Taking a certain node in the roving process as an example, the chronological position of this node in the energy consumption monitoring interval is the 3rd hour segment, and the preset period is 1 hour. The system collects the energy consumption data of this node within this 1 hour in real time through the energy consumption sensor installed on the roving frame, including instantaneous power, cumulative energy consumption, etc., to form an energy consumption fluctuation data sequence. The calculation of the energy consumption fluctuation coefficient is based on the statistical characteristics of this data sequence. Common calculation methods include standard deviation, coefficient of variation, etc. The standard deviation reflects the degree of dispersion of the energy consumption data relative to the mean value, and the coefficient of variation is the ratio of the standard deviation to the mean value, which is used to eliminate the problem that the fluctuation degrees of different process nodes are not comparable due to differences in energy consumption mean values. For example, if the mean value of the energy consumption data of this roving process node is 100 kW·h and the standard deviation is 15 kW·h, then the coefficient of variation is 0.15, and this value is used as the energy consumption fluctuation coefficient of this node.

[0043] When the energy consumption fluctuation coefficient exceeds the first fluctuation threshold, mark this node as a high-energy-consuming node, and extract its energy consumption data to form an energy consumption characteristic vector. The setting of the first fluctuation threshold needs to comprehensively consider the technological requirements of spinning production and historical energy consumption data, and is usually determined by statistical analysis of the energy consumption fluctuation coefficients of similar process nodes. For example, take the upper quartile of the energy consumption fluctuation coefficients of all similar nodes as the threshold. If the energy consumption fluctuation coefficient 0.15 of the above-mentioned roving process node exceeds the preset first fluctuation threshold 0.12, then it is determined that this node is a high-energy-consuming node. At this time, the system extracts key characteristic parameters from the energy consumption fluctuation data of this node, including energy consumption peak value, valley value, mean value, variance, slopes of the energy consumption rising edge and falling edge, etc. These parameters describe the energy consumption characteristics of this node from different dimensions: the energy consumption peak value reflects the energy consumption demand of the equipment under extreme working conditions, the valley value represents the energy consumption level when the equipment is lightly loaded or on standby, the mean value reflects the average energy consumption intensity, the variance characterizes the severity of the energy consumption fluctuation, and the slope reflects the rate of energy consumption change. Arrange these parameters in the preset order to form a multi-dimensional energy consumption characteristic vector, such as [peak value, valley value, mean value, variance, rising slope, falling slope]. This vector comprehensively records the energy consumption characteristics of the high-energy-consuming node, providing a detailed basis for subsequent energy consumption analysis and optimization strategy formulation.

[0044] When the energy consumption fluctuation coefficient is lower than the first fluctuation threshold, mark this node as a steady-state node, and perform weighted superposition on the energy consumption data of the adjacent nodes of this node. Reconstruct the superposed data into an energy consumption feature vector. The energy consumption fluctuation of the steady-state node is relatively stable, but analyzing its data alone may not comprehensively reflect the actual energy consumption characteristics of this node in the production process. Therefore, it is necessary to conduct a comprehensive analysis in combination with the data of adjacent nodes. The range of adjacent nodes can be determined according to the continuity of the process. For example, for a continuously produced process, 1-2 nodes before and after this node can be selected as adjacent nodes. The setting of weights follows the principle of "the closer the distance, the greater the weight", that is, the closer the adjacent node is to the time series position of the steady-state node, the higher the weight assigned to its energy consumption data during superposition. Taking a steady-state node in the drawing process as an example, its adjacent nodes are the previous node and the next node. The weight of the previous node is set to 0.4, the weight of this node is 0.2, and the weight of the next node is 0.4. The system obtains the energy consumption data of these three nodes within their respective preset cycles, namely the energy consumption sequence A of the previous node, the energy consumption sequence B of this node, and the energy consumption sequence C of the next node. First, perform normalization processing on each sequence to eliminate the influence of dimensions, and then perform superposition according to the weights to obtain the superposed energy consumption data sequence D = 0.4×A + 0.2×B + 0.4×C. Then, perform feature extraction on the superposed sequence D. The extracted feature parameters are similar to those of high-energy-consuming nodes, including mean, variance, peak value, valley value, etc. However, due to the superposition of the data of adjacent nodes, these feature parameters can better reflect the overall energy consumption trend of this steady-state node and its surrounding production links. Combine these feature parameters into an energy consumption feature vector, such as [superposed mean, superposed variance, superposed peak value, superposed valley value]. This vector not only contains the energy consumption information of the steady-state node itself but also incorporates the influence of adjacent nodes, making the description of energy consumption characteristics more comprehensive and accurate.

[0045] In practical applications, the adjustment of the preset cycle needs to be carried out according to the actual situation of the production site. For example, when the equipment is maintained or the process parameters change, the preset cycle can be appropriately shortened to more intensively monitor the changes in energy consumption data. The calculation method of the energy consumption fluctuation coefficient can also be selected according to the data characteristics. For non-normally distributed data, robust statistics such as absolute mean deviation can be used instead of standard deviation to reduce the influence of outliers on the fluctuation coefficient. The setting of the first fluctuation threshold is a dynamic optimization process. With the improvement of production processes and the update of equipment, it is necessary to regularly re-evaluate and adjust the threshold to ensure that the division of high-energy-consuming nodes and steady-state nodes always conforms to the actual production situation.

[0046] When superimposing the data of adjacent nodes on the steady-state nodes, the distribution of weights can also consider the correlation of equipment operating states. For example, if the adjacent node and the steady-state node belong to the continuous operation stage of the same piece of equipment, the weight can be appropriately increased; if they belong to the processes of different equipment, the weight can be correspondingly decreased. In addition, the normalization process before data superposition is crucial. The energy consumption data of different process nodes may have different dimensions and numerical ranges, and the normalization process can unify the data to the same scale, avoiding the distortion of the superposition result caused by dimensional differences. The dimension of the reconstructed energy consumption feature vector can be adjusted according to actual needs. If a more detailed analysis of the energy consumption change trend is required, feature parameters related to time series, such as autocorrelation coefficient and partial autocorrelation coefficient, can be added.

[0047] Through the above method, the system can flexibly generate different types of energy consumption feature vectors according to the energy consumption fluctuation characteristics of process nodes. For high-energy-consuming nodes, directly extract their own key energy consumption features, which is convenient for analyzing the reasons for abnormal energy consumption and formulating optimization strategies; for steady-state nodes, generate feature vectors by fusing the data of adjacent nodes, which can capture the potential energy consumption change rules caused by process connection or equipment linkage in the production process, providing a more comprehensive perspective for overall energy consumption optimization. This differential processing method not only ensures a rapid response to abnormal energy consumption states but also realizes in-depth mining of energy consumption characteristics under normal production states, improving the comprehensiveness and accuracy of the system's energy consumption analysis of the spinning production process. Example 3:

[0048] The implementation method of the strategy generation module includes: separating the equipment energy consumption ratio, idling energy consumption ratio, and load fluctuation parameters from the energy consumption feature vector, and generating energy consumption optimization rules for process nodes based on the above parameters. In the spinning production system, the energy consumption feature vector contains multi-dimensional data reflecting the energy consumption characteristics of process nodes. The equipment energy consumption ratio reflects the proportion of energy consumption actually used for production during the operation of production equipment, which is an important indicator to measure the energy efficiency of equipment. For example, during the process of carding cotton fibers by a carding machine, the proportion of energy consumption directly used for processing, such as the motor running and the licker-in rotating, in the total energy consumption is the equipment energy consumption ratio. The idling energy consumption ratio reflects the energy consumption of the equipment under the condition of no effective load, such as the energy consumption when the equipment is started but not yet put into production or during production breaks. For a roving frame, the idling state when waiting for the feeding of sliver or changing the bobbin will generate a certain amount of energy consumption, and the proportion of this part of energy consumption in the total energy consumption is the idling energy consumption ratio. The load fluctuation parameter describes the severity of the load change during the operation of the equipment. Excessive load fluctuation will not only increase energy consumption but also may affect the service life of the equipment and the product quality. During the spinning process of a ring spinning frame, due to the change of yarn tension or the unevenness of the feeding amount, the motor load will fluctuate, and the amplitude and frequency of this fluctuation are the specific manifestations of the load fluctuation parameter.

[0049] The system accurately separates these three key parameters from the energy consumption characteristic vectors through a preset algorithm. For the equipment energy consumption ratio, the system analyzes the correlation between the energy consumption data and the equipment operating status, identifies the energy consumption part directly related to production, and calculates its proportion in the total energy consumption. During the identification process, the system refers to the process parameters and operating modes of the equipment. For example, the energy consumption distribution of the carding machine at different rotational speeds is used to accurately divide the equipment energy consumption and other energy consumption. For the no-load energy consumption ratio, the system detects the start-stop status and load condition of the equipment. When the equipment is in the running state but has no effective load, the energy consumption data at this time is recorded, and the proportion of this part of the energy consumption in the entire production cycle is calculated. The system establishes a characteristic model of the equipment no-load state, and accurately identifies the no-load state by comparing the real-time energy consumption data with the model characteristics. For the load fluctuation parameter, the system analyzes the time series data of the equipment load, calculates statistical quantities such as the standard deviation and coefficient of variation of the load, so as to quantify the degree of load fluctuation. The system also analyzes the frequency characteristics of the load fluctuation to identify the main fluctuation frequency components in order to deeply understand the reasons for the load fluctuation.

[0050] Based on the separated equipment energy consumption ratio, no-load energy consumption ratio, and load fluctuation parameters, the system generates energy consumption optimization rules for the process nodes. If the equipment energy consumption ratio is relatively low, it indicates that the energy efficiency of the equipment has not been fully utilized, and there may be problems such as equipment aging and unreasonable process parameters. In response to this situation, the generated optimization rules may include suggestions for equipment maintenance and adjustment of process parameters to improve the equipment operation efficiency. If the no-load energy consumption ratio is relatively high, it indicates that there is a lot of ineffective energy consumption in the equipment. The optimization rules may suggest optimizing the production process and reducing the no-load time of the equipment. For example, by reasonably arranging the production plan, the equipment can be stopped in time during the production gap. If the load fluctuation parameter is large, it indicates that the equipment runs unstably, which may lead to increased energy consumption and decreased product quality. The optimization rules may propose to adjust the control strategy of the equipment, such as adopting closed-loop control and adding buffer devices, to reduce the load fluctuation.

[0051] If the number of process nodes covered by the current energy consumption optimization rule is less than the preset node threshold, the energy consumption characteristic vectors of adjacent process nodes are traversed, and the energy consumption indicators not included in the optimization rules of adjacent nodes are added to the current rule. The preset node threshold is a value set according to the production scale and management requirements, which represents the minimum number of process nodes that the energy consumption optimization rule should cover. When the system finds that the currently generated energy consumption optimization rule only covers a few process nodes and does not reach the preset node threshold, it indicates that the coverage of the current rule is not comprehensive enough and may not meet the overall energy consumption optimization requirements. At this time, the system will traverse and analyze the energy consumption characteristic vectors of adjacent process nodes.

[0052] Adjacent process nodes refer to the preceding and succeeding process nodes that are closely connected to the current process node in the production process. In spinning production, the adjacent process nodes of the carding process may be the opening and cleaning process and the drawing process. The system will extract the energy consumption feature vectors of these adjacent nodes and analyze the energy consumption indicators included in their corresponding optimization rules. Add the energy consumption indicators not included in the current rule to the current rule to expand the coverage of the rule. If the optimization rule of the adjacent drawing process includes the energy consumption indicator of "the impact of roller speed fluctuation on energy consumption" and this indicator is not covered in the current optimization rule of the carding process, the system will incorporate this indicator into the optimization rule of the carding process. In this way, continuously improve and expand the energy consumption optimization rules to enable them to more comprehensively cover the energy consumption characteristics of each process node and improve the effect of energy consumption optimization.

[0053] In practical applications, the algorithm for separating key parameters from the energy consumption feature vectors needs to be continuously optimized and adjusted to adapt to the characteristics of different types of equipment and production processes. For new spinning equipment, its energy consumption characteristics may be different from those of traditional equipment, and the separation algorithm needs to be improved accordingly. When generating energy consumption optimization rules, the feasibility and operability of the rules need to be considered. The proposed optimization suggestions should be specific and clear and achievable under the existing production conditions. When traversing the energy consumption feature vectors of adjacent process nodes, an effective data association mechanism needs to be established to ensure that relevant information of adjacent nodes can be accurately obtained. The system also needs to verify the rationality of the newly added energy consumption indicators to avoid introducing irrelevant or incorrect indicators.

[0054] To improve the performance and efficiency of the strategy generation module, the system can adopt parallel computing technology to analyze and process the energy consumption feature vectors of multiple process nodes simultaneously. A knowledge base of energy consumption optimization rules can also be established to store and manage the effective rules generated in history for reference and reuse in subsequent optimization processes. In this way, more comprehensive and effective energy consumption optimization rules can be generated quickly, providing strong support for the energy consumption management of spinning production. The system can also be integrated with the production management system to directly convert the generated optimization rules into production instructions to achieve the automation and intelligence of energy consumption optimization.

[0055] When dealing with complex production scenarios, the strategy generation module can also consider the mutual relationships between multiple energy consumption indicators. There may be mutual influences among the equipment energy consumption ratio, no-load energy consumption ratio, and load fluctuation parameters. For example, excessive load fluctuation may lead to an increase in the no-load energy consumption of the equipment. The system can adopt multivariate statistical analysis methods to deeply explore the internal connections between these indicators, thereby generating more comprehensive and effective energy consumption optimization rules. The system can also prioritize the optimization rules according to different production requirements and goals to ensure that energy consumption is minimized to the greatest extent while meeting production requirements.

[0056] Through the above implementation manners, the policy generation module can extract key parameters from the energy consumption feature vectors, generate targeted energy consumption optimization rules, and ensure the comprehensiveness and effectiveness of the rules by expanding the rule coverage. This method can not only help spinning enterprises accurately identify energy consumption problems, but also provide specific optimization suggestions to guide enterprises to implement energy consumption management measures, improve energy utilization efficiency, and reduce production costs. Embodiment 4:

[0057] The implementation manner of the scheduling optimization module is as follows: Obtain the timing factor of the start-stop frequency and the fluctuation factor of the load change amplitude in the device operation mode. In the spinning production system, the operation mode of the device has a significant impact on energy consumption. The timing factor of the start-stop frequency reflects the number of times and the time distribution law of the start and stop of the device within a certain time period. For example, during the production process of a shift, the spinning frame may perform multiple start-stop operations due to shift change, equipment maintenance, or raw material supply. The time points and frequencies of these start-stop operations constitute the main content of the timing factor. By analyzing the historical operation data of the device, the periodic pattern of the start-stop frequency can be identified, such as the high-frequency start-stop at the start of the machine every morning and the low-frequency start-stop during the lunch break.

[0058] The fluctuation factor of the load change amplitude describes the degree of change in the load size of the device during operation. For the roving frame, when the thickness of the fed sliver is uneven or the spinning process parameters are adjusted, the load of the device will fluctuate accordingly. This fluctuation will not only affect the energy consumption of the device, but may also have an adverse impact on product quality. The calculation of the fluctuation factor needs to consider multiple dimensions such as the amplitude, frequency, and duration of the load change. The degree of fluctuation can be quantified by calculating statistical quantities such as the standard deviation and range of the load data, and at the same time, the frequency distribution of the fluctuation is analyzed to determine the main fluctuation frequency components.

[0059] Construct a state transition network associated with the timing factor and the fluctuation factor, and determine the energy consumption fluctuation amplitude under different scheduling strategies according to the transition probabilities of each path in the network. The state transition network is a mathematical model used to describe the transition relationship between system states. In this embodiment, the timing factor and the fluctuation factor are used as state nodes in the network, and the connections between the nodes represent the transition relationship between states. Each transition relationship is assigned a transition probability, which reflects the likelihood of transitioning from one state to another under specific conditions.

[0060] When constructing a state transition network, it is first necessary to determine the set of nodes in the network. The timing factor can be divided into different states according to the high or low start-stop frequency, such as high-frequency start-stop state, medium-frequency start-stop state, and low-frequency start-stop state. The fluctuation factor can also be similarly divided into different states, such as high-fluctuation state, medium-fluctuation state, and low-fluctuation state. Combining these states forms the set of nodes in the state transition network. For example, a node can be represented as the "high-frequency start-stop - high-fluctuation" state, and another node can be represented as the "low-frequency start-stop - low-fluctuation" state.

[0061] Determine the transition relationships and transition probabilities between nodes. The determination of transition relationships needs to be based on the physical laws of equipment operation and historical data. In spinning production, the high-frequency start-stop state often leads to an increase in the amplitude of load fluctuations. Therefore, there is a possibility of transitioning from the "high-frequency start-stop - low-fluctuation" state to the "high-frequency start-stop - high-fluctuation" state. The calculation of transition probabilities requires statistical analysis using historical data. By mining a large amount of historical operation data, count the number of transitions between states under different conditions, and thus calculate the corresponding transition probabilities.

[0062] According to the transition probabilities of each path in the state transition network, the amplitude of energy consumption fluctuations under different scheduling strategies can be evaluated. If a new scheduling strategy is adopted to reduce the start-stop frequency of the equipment, then in the state transition network, the probability of the system transitioning from the high-frequency start-stop state to the low-frequency start-stop state will increase. By analyzing the impact of this state transition on the amplitude of energy consumption fluctuations, the effect of the new scheduling strategy can be predicted. Specifically, for each possible state transition path, calculate the product of its transition probability and the amplitude of energy consumption fluctuations corresponding to this path, and then sum the results of all paths to obtain the expected amplitude of energy consumption fluctuations under this scheduling strategy.

[0063] Constructing the state transition network also includes: identifying the periodic characteristics of the timing factor. If the current periodic characteristics exactly match the preset production cycle, then set the timing factor as the starting node of the state transition network. In spinning production, the operation of many devices has obvious periodic characteristics. The production of the spinning frame usually follows shifts, and the production process and equipment operation mode of each shift are basically the same, so the start-stop frequency also shows periodic changes. By performing spectral analysis or autocorrelation analysis on the historical data of the timing factor, its periodic characteristics can be identified.

[0064] The preset production cycle is a time cycle set according to the enterprise's production plan and process requirements, such as the duration of a shift, the production time of a day, etc. When the periodic characteristics of the identified timing factor exactly match the preset production cycle, it indicates that the change rule of the equipment's start-stop frequency is highly consistent with the production plan. In this case, setting the timing factor as the starting node of the state transition network can more accurately reflect the change process of the equipment's operating state. Taking an 8-hour shift as an example, if the periodic characteristics of the timing factor are also 8 hours and the start-stop frequency distribution within each cycle is similar, then using this timing factor as the starting node can better describe the state transition of the equipment from the start to the end of the shift.

[0065] Calculate the transfer correlation degree between the timing factor and the fluctuation factor, and generate the intermediate nodes and termination nodes of the state transition network in order from high to low correlation degree. The transfer correlation degree is an index to measure the degree of mutual influence between the timing factor and the fluctuation factor. In spinning production, the change in the start-stop frequency often causes a change in the load fluctuation amplitude, and there is a certain correlation between the two. Statistical methods such as correlation analysis and Granger causality test can be used to calculate the transfer correlation degree.

[0066] By calculating the correlation degree between the timing factor and the fluctuation factor in different states, determine the correlation strength between them. If the correlation degree between the high-frequency start-stop state and the high-load fluctuation state is high, it indicates that frequent start-stop operations are likely to cause an increase in the load fluctuation amplitude. Generate the intermediate nodes and termination nodes of the state transition network in order from high to low correlation degree. The state combinations with high correlation degrees are preferentially used as intermediate nodes to reflect the main change paths of the equipment's operating state; the state combinations with lower correlation degrees are used as termination nodes, indicating the stable states or abnormal states that the equipment may enter.

[0067] Perform state backtracking on the termination nodes. When the correlation degree of the termination node is lower than the preset correlation threshold, output it as the final path of the state transition network. State backtracking means starting from the termination node and tracing back along the transfer path to the starting node to check the rationality and effectiveness of the entire path. In the state transition network, some termination nodes may be caused by data noise or accidental factors, and their correlation degree with the starting node is low. These nodes have little predictive value for the energy consumption fluctuation amplitude.

[0068] The preset correlation threshold is a preset value used to judge whether the correlation between the termination node and the starting node is strong enough. When the correlation degree of the termination node is lower than this threshold, it indicates that the state transition path represented by this node is less likely to occur in actual production or has a small impact on the energy consumption fluctuation amplitude. Using such a termination node as the final path of the state transition network can exclude some unreasonable paths and improve the accuracy of predicting the energy consumption fluctuation amplitude.

[0069] The implementation methods for calculating the energy consumption fluctuation range include: statistically calculating the mean value of the timing factor and the range of the fluctuation factor for each termination node in the state transition network, and calculating the global variance of all node factors. The mean value of the timing factor reflects the average level of the equipment start-stop frequency under the state represented by the termination node. For a termination node representing "low-frequency start-stop - low fluctuation", calculating the mean value of the timing factor in the historical data can obtain the average start-stop frequency of the equipment in this state. The range of the fluctuation factor represents the difference between the maximum value and the minimum value of the load change amplitude in this state, which describes the range of load fluctuations.

[0070] The global variance is the comprehensive variance of the timing factors and fluctuation factors of all nodes, which reflects the degree of dispersion of the equipment operating state in the entire state transition network. By calculating the global variance, the operating stability of the equipment in different states can be understood. If the global variance is large, it indicates that the operating state of the equipment is relatively dispersed and the possibility of energy consumption fluctuation is also large; conversely, if the global variance is small, it indicates that the operating state of the equipment is relatively concentrated and the energy consumption fluctuation is relatively small.

[0071] Subtract the mean value of the timing factor of a single termination node from the mean value of the timing factor of the adjacent node, and divide by the global variance to obtain the timing fluctuation coefficient; at the same time, calculate the ratio of the range of the fluctuation factor to the global variance, and sum the two weighted to obtain the energy consumption fluctuation range of this node. The timing fluctuation coefficient measures the change degree of the timing factor of a single termination node relative to the adjacent node, which reflects the fluctuation of the equipment start-stop frequency between different states. The ratio of the range of the fluctuation factor to the global variance represents the relative size of the load fluctuation amplitude within the global range.

[0072] Combine these two indicators into a comprehensive energy consumption fluctuation range indicator through weighted summation. The selection of the weight needs to be adjusted according to the specific production situation and equipment characteristics. If the start-stop frequency of the equipment has a greater impact on energy consumption, the weight of the timing fluctuation coefficient can be appropriately increased; if the load fluctuation amplitude has a more significant impact on energy consumption, the weight of the ratio of the range of the fluctuation factor to the global variance can be increased. The energy consumption fluctuation range calculated in this way can comprehensively consider the impacts of the equipment start-stop frequency and the load change amplitude on energy consumption, providing an accurate basis for optimizing the scheduling strategy.

[0073] In practical applications, the quality and quantity of data need to be considered when constructing the state transition network. The accuracy and integrity of historical data directly affect the reliability of the state transition network. If there is noise or missing values in the data, it may lead to inaccurate state partitioning and deviation in the calculation of transition probabilities. Therefore, before constructing the network, data preprocessing is required, including operations such as data cleaning and interpolation filling.

[0074] The complexity of the state transition network also needs to be reasonably controlled. If the number of nodes is too large or the transition relationships are too complex, it will increase the computational complexity and the difficulty of analysis, and may also lead to overfitting problems. In practical applications, the state transition network can be appropriately simplified according to the characteristics of the equipment and the complexity of the production process, while retaining the main states and transition relationships.

[0075] When calculating the energy consumption fluctuation range, the selection of weights is a key issue. Different equipment and production processes may have different sensitivities to the start-stop frequency and the load fluctuation range. Therefore, it needs to be adjusted according to specific circumstances. The appropriate weight values can be determined through expert experience or the analysis of historical data. The method of adaptive weights can also be adopted to dynamically adjust the weights according to real-time production data, so as to improve the accuracy of calculating the energy consumption fluctuation range.

[0076] Through the above implementation methods, the scheduling optimization module can accurately obtain the key factors in the equipment operation mode, construct an effective state transition network, and calculate the energy consumption fluctuation range under different scheduling strategies based on this network. This method can not only help enterprises predict the trend of energy consumption changes, but also provide a scientific basis for optimizing scheduling strategies, so as to achieve the goal of reducing energy consumption and improving production efficiency. Example 5:

[0077] The implementation method for deriving the optimal energy consumption threshold is as follows: Extract the fluctuation pattern in the historical data that is closest to the current energy consumption fluctuation range, and calculate the Manhattan distance in the time series distribution between the two as the first reference value. In the spinning production system, the historical data stores a large number of energy consumption fluctuation patterns in different time periods, and these patterns reflect the energy consumption characteristics of the equipment under various operating conditions. The current energy consumption fluctuation range refers to the degree of change of the energy consumption of the equipment or process over time during the current production process. By analyzing the fluctuation patterns in the historical data and finding the pattern closest to the current fluctuation range, it can provide a reference for determining the optimal energy consumption threshold.

[0078] The Manhattan distance is an index used to measure the distance between two vectors in a multi-dimensional space. In this embodiment, it is used to measure the difference in the time series distribution between the current fluctuation pattern and the historical fluctuation pattern. Specifically, represent the current fluctuation pattern and the historical fluctuation pattern as time series vectors respectively, and the elements of each vector correspond to the energy consumption values at different time points. Calculate the sum of the absolute values of the differences in the energy consumption values of these two vectors at each time point, and the result obtained is the Manhattan distance. For example, if the energy consumption values of the current fluctuation pattern at three consecutive time points are 、 、 , and the energy consumption values of the historical fluctuation pattern at the same time points are 、 、 , then their Manhattan distance is:

[0079] The smaller the distance value is, the more similar the two fluctuation patterns are in the time series distribution.

[0080] Statistically analyze the difference in the number of extreme points between the current energy consumption fluctuation range and the historical fluctuation pattern, and use the difference quantity as the second reference value. Extreme points refer to the maximum and minimum points in the energy consumption time series, which reflect the intensity and change trend of energy consumption fluctuations. By comparing the number of extreme points of the current energy consumption fluctuation range with that of the historical fluctuation pattern, the smaller the difference quantity is, the more similar the change trends of the two fluctuation patterns are. In spinning production, certain process adjustments or equipment failures may cause changes in the number of extreme points of energy consumption fluctuations. Therefore, by comparing the number of extreme points, the similarity between the current fluctuation pattern and the historical pattern can be judged more accurately.

[0081] Based on the linear combination of the first reference value and the second reference value, match the optimal energy consumption threshold in the preset energy consumption threshold table. The preset energy consumption threshold table is established in advance according to a large amount of historical data and production experience, and it records the optimal energy consumption thresholds corresponding to different combinations of reference values. The first reference value and the second reference value are linearly combined according to certain weights to obtain a comprehensive reference value. For example, the comprehensive reference value The calculation formula is:

[0082] Where: is the first reference value, is the second reference value, and are weight coefficients, and satisfy .

[0083] By adjusting the weight coefficients, the importance of the two reference values can be weighed according to the actual production situation. According to the calculated comprehensive reference value, find the closest corresponding value in the preset energy consumption threshold table, and this value is the optimal energy consumption threshold under the current production conditions.

[0084] The implementation method of the decision output module includes: dividing the positive fluctuation interval and the negative fluctuation interval according to the energy consumption fluctuation direction of each node in the process energy consumption deviation sequence. The process energy consumption deviation sequence refers to the difference sequence between the actual energy consumption value of each process node and the optimal energy consumption threshold. The energy consumption fluctuation direction refers to the positive or negative nature of the deviation value. If the deviation value is positive, it means that the actual energy consumption of this node is higher than the optimal energy consumption threshold, belonging to the situation of energy consumption exceeding the standard; if the deviation value is negative, it means that the actual energy consumption is lower than the optimal energy consumption threshold, and there may be problems such as low equipment operation efficiency or insufficient production.

[0085] By traversing the sequence of process energy consumption deviations, continuous positive deviation value nodes are divided into positive fluctuation intervals, and continuous negative deviation value nodes are divided into negative fluctuation intervals. In a certain process of spinning production, if the energy consumption deviation values of the first three process nodes are all positive, the deviation values of the next two nodes are negative, and the deviation values of the following four nodes are positive again, then the first three nodes can be divided into a positive fluctuation interval, the middle two nodes can be divided into a negative fluctuation interval, and the last four nodes can be divided into another positive fluctuation interval. This division method helps to visually identify the energy consumption abnormal areas and provides a basis for subsequent analysis and processing.

[0086] Extract the convergence rate of the energy consumption deviation within the positive fluctuation interval and the diffusion rate of the energy consumption deviation within the negative fluctuation interval, and weight and fuse the two according to the production weights of the process nodes to generate the core adjustment parameters of the energy consumption optimization decision-making scheme. The convergence rate refers to the speed at which the energy consumption deviation value gradually decreases over time or as the process progresses within the positive fluctuation interval, which reflects the system's own adjustment ability to energy consumption overrun. The diffusion rate refers to the speed at which the absolute value of the energy consumption deviation value gradually increases over time or as the process progresses within the negative fluctuation interval, which indicates the degree of deterioration of the energy consumption shortage situation.

[0087] When calculating the convergence rate and the diffusion rate, methods such as linear regression can be used to fit the energy consumption deviation values within the fluctuation interval to obtain the trend line of the deviation value changing with time or the process. The slope of the trend line is the corresponding rate. For the positive fluctuation interval, if the slope of the trend line is negative and its absolute value is large, it indicates that the convergence rate is fast and the system can quickly reduce the degree of energy consumption overrun; for the negative fluctuation interval, if the slope of the trend line is negative and its absolute value is large, it indicates that the diffusion rate is fast and the energy consumption shortage situation is deteriorating rapidly.

[0088] The production weight of a process node reflects the importance of this node in the entire production process and the degree of influence on the quality of the final product. The production weights of key process nodes are relatively high, and the production weights of non-key process nodes are relatively low. The convergence rate and the diffusion rate are weighted and fused according to the production weights of each process node to obtain a comprehensive adjustment parameter. For example, for a certain positive fluctuation interval, calculate the product of the convergence rate of each node and the production weight, and then add up the results of all nodes to obtain the comprehensive convergence index of this interval; similarly, for the negative fluctuation interval, calculate the comprehensive diffusion index. Further fusion processing of these two indexes generates the final core adjustment parameter.

[0089] This core adjustment parameter comprehensively considers the severity and change trends of both energy consumption over - standard and energy consumption under - standard situations, as well as the importance of each process node in production. Based on this parameter, targeted energy - consumption optimization decision - making schemes can be formulated, such as adjusting equipment operation parameters, optimizing production processes, re - allocating resources, etc. In this way, the decision - making output module can transform complex energy - consumption deviation information into specific and operable optimization suggestions, providing strong support for the enterprise's energy - consumption management.

[0090] In practical applications, when extracting similar fluctuation patterns from historical data, it is necessary to effectively organize and index the historical data. Clustering algorithms can be used to classify historical fluctuation patterns and establish a classification index to quickly find the pattern closest to the current fluctuation amplitude. When calculating the Manhattan distance, in order to improve the calculation efficiency, dimensionality reduction techniques can be used to pre - process the time - series vector and reduce the amount of calculation.

[0091] When counting the number of extreme points, it is necessary to determine a suitable extreme - point detection method. A simple method is to set a threshold, and when the change in energy - consumption value exceeds this threshold, it is determined as an extreme point. More complex algorithms, such as wavelet transform and sliding window methods, can also be used to improve the accuracy of extreme - point detection. The establishment of the preset energy - consumption threshold table needs to fully consider various possible production situations and equipment states. Through the analysis of historical data and machine - learning algorithms, the internal relationship between the reference value and the optimal energy - consumption threshold can be mined, so as to establish an accurate and comprehensive threshold table.

[0092] When dividing the positive - fluctuation interval and the negative - fluctuation interval, it is necessary to handle the boundary conditions well. When adjacent positive and negative deviation - value nodes appear alternately, it is necessary to determine whether to divide them into independent intervals or merge them into one interval according to specific situations. A minimum - interval - length threshold can be set, and when the interval length is less than this threshold, it is merged with the adjacent interval.

[0093] When calculating the convergence rate and the diffusion rate, although the linear regression method is simple and easy to use, it may not be accurate enough for complex non - linear fluctuation patterns. In this case, non - linear regression or time - series analysis methods can be considered to improve the accuracy of rate calculation. The determination of the production weight of process nodes needs to comprehensively consider multiple factors, such as the position of the process in the production process, the degree of influence on product quality, and the energy - consumption ratio. Multi - criterion decision - making methods such as the analytic hierarchy process and the Delphi method can be used to scientifically and reasonably determine the production weights of each process node.

[0094] Through the above implementation manners, the system can accurately deduce the optimal energy consumption threshold and generate an effective energy consumption optimization decision-making scheme based on the sequence of process energy consumption deviations. This method not only considers the temporal characteristics and extreme value characteristics of energy consumption fluctuations, but also combines the production importance of process nodes, making the optimization decision-making more scientific and reasonable. In actual production, this method can help enterprises promptly discover abnormal energy consumption situations, formulate targeted improvement measures, improve energy utilization efficiency, reduce production costs, and achieve sustainable development.

[0095] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0096] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-process spinning energy consumption optimization decision-making system, characterized in that, Including: A data acquisition module, which is used to obtain equipment parameters and energy consumption data in the spinning production process and set an energy consumption monitoring interval corresponding to the process; An energy consumption analysis module, which is used to divide multiple process nodes within the energy consumption monitoring interval, perform feature analysis on the energy consumption data of each process node, and generate an energy consumption feature vector corresponding to the process node; A strategy generation module, which is used to extract key energy consumption indicators from the energy consumption feature vector, establish an energy consumption optimization rule associated with the process node, and obtain the process control parameters corresponding to the rule; A scheduling optimization module, which is used to identify the equipment operation mode in the process control parameters, dynamically schedule the key energy consumption indicators according to the operation mode, and calculate the energy consumption fluctuation range of each process node under different scheduling strategies; A benchmark comparison module, which is used to deduce the optimal energy consumption threshold based on the energy consumption fluctuation range, and generate a process energy consumption deviation sequence by comparing the current process energy consumption value with the optimal energy consumption threshold; A decision output module, which is used to analyze the process energy consumption deviation sequence and integrate the process energy consumption deviation sequence into an energy consumption optimization decision scheme based on the energy consumption fluctuation trend of the process node.

2. The multi-process spinning energy consumption optimization decision-making system according to claim 1, wherein, The implementation method of the energy consumption analysis module includes: constructing a process feature library corresponding to the process node, and the process feature library contains the process parameter vector mapped by the equipment parameter and the energy consumption data; Performing similar process matching on the process parameter vector, dividing the process clustering group of the process parameter vector according to the matching result; extracting the distribution center point of the energy consumption data from the process clustering group and setting the distribution center point as the process node.

3. The multi-process spinning energy consumption optimization decision-making system according to claim 2, characterized in that, Dividing the process clustering group of the process parameter vector further includes: Extracting the equipment rotation speed, yarn count, and ambient temperature and humidity parameters according to the equipment type and production stage in the process parameter vector, and generating a process feature label based on the above parameters; Associating the process feature label with the process parameter vector, and screening the process parameter vectors with a process similarity higher than the preset process threshold to form a process clustering group by calculating the process similarity between the feature labels.

4. The multi-process spinning energy consumption optimization decision-making system according to claim 1, characterized in that, The implementation method of generating the energy consumption feature vector corresponding to the process node includes: For each process node, according to the time sequence position of the node in the energy consumption monitoring interval, obtaining the energy consumption fluctuation data of the node within a preset period and calculating the energy consumption fluctuation coefficient of the node; When the energy consumption fluctuation coefficient exceeds the first fluctuation threshold, marking the node as a high-energy consumption node and extracting its energy consumption data to form an energy consumption feature vector; when the energy consumption fluctuation coefficient is lower than the first fluctuation threshold, marking the node as a steady-state node, and performing weighted superposition on the energy consumption data of the adjacent nodes of the node, and reconstructing the superposed data into an energy consumption feature vector.

5. The multi-process spinning energy consumption optimization decision-making system according to claim 1, wherein The implementation method of the strategy generation module includes: Separating the equipment energy consumption ratio, no-load energy consumption ratio, and load fluctuation parameters from the energy consumption feature vector, and generating an energy consumption optimization rule for the process node based on the above parameters; If the number of process nodes covered by the current energy consumption optimization rule is less than the preset node threshold, traversing the energy consumption feature vectors of adjacent process nodes and adding the energy consumption indicators not included in the optimization rules of the adjacent nodes to the current rule.

6. The multi-process spinning energy consumption optimization decision-making system according to claim 1, wherein The implementation method of the scheduling optimization module includes: obtaining the time sequence factor of the start-stop frequency and the fluctuation factor of the load change amplitude in the equipment operation mode; Construct a state transition network associated with the time series factor and the volatility factor, and determine the energy consumption fluctuation range under different scheduling strategies according to the transition probabilities of each path in the network.

7. The multi-process spinning energy consumption optimization decision-making system according to claim 6, characterized in that, Constructing the state transition network also includes: Identifying the periodic characteristics of the time series factor. If the current periodic characteristics exactly match the preset production cycle, set the time series factor as the starting node of the state transition network; Calculating the transfer correlation degree between the time series factor and the volatility factor, and generating the intermediate nodes and the end nodes of the state transition network in descending order of the correlation degree; Performing state backtracking on the end nodes. When the correlation degree of the end node is lower than the preset correlation threshold, output it as the final path of the state transition network.

8. The multi-process spinning energy consumption optimization decision-making system according to claim 7, characterized in that, The implementation method of calculating the energy consumption fluctuation range includes: Statistical mean of the time series factor and the range of the volatility factor of each end node in the state transition network, and calculate the global variance of all node factors; Take the difference between the mean value of the time series factor of a single end node and the mean value of the time series factor of the adjacent node, and divide it by the global variance to obtain the time series fluctuation coefficient; at the same time, calculate the ratio of the range of the volatility factor to the global variance, and weight the sum of the two as the energy consumption fluctuation range of this node.

9. The multi-process spinning energy consumption optimization decision-making system according to claim 1, characterized in that The implementation method of deriving the optimal energy consumption threshold includes: Extract the fluctuation pattern in the historical data that is closest to the current energy consumption fluctuation range, and calculate the Manhattan distance in the time series distribution between the two as the first reference value; Statistical difference in the number of extreme points between the current energy consumption fluctuation range and the historical fluctuation pattern, and take the difference number as the second reference value; Based on the linear combination of the first reference value and the second reference value, match the optimal energy consumption threshold in the preset energy consumption threshold table.

10. The multi-process spinning energy consumption optimization decision-making system according to claim 1, characterized in that, The implementation method of the decision output module includes: dividing the positive fluctuation interval and the negative fluctuation interval according to the energy consumption fluctuation direction of each node in the process energy consumption deviation sequence; Extract the convergence rate of the energy consumption deviation in the positive fluctuation interval and the diffusion rate of the energy consumption deviation in the negative fluctuation interval, and weight and fuse the two according to the production weights of the process nodes to generate the core adjustment parameter of the energy consumption optimization decision scheme.

Images