Negative carbon emission optimization control method and system for industrial production

Abstract

The present invention relates to the field of industrial control management technology, and in particular to a method and system for optimizing negative carbon emissions control in industrial production, which first obtains multiple coordinate data and negative carbon emission data in a target area, then clusters the multiple coordinate data into a first clustering cluster, and clusters the multiple negative carbon emission data into a second clustering cluster, and then identifies the negative carbon emission abnormal area based on the difference between the first clustering cluster and the second clustering cluster, so as to optimize emissions control. The present invention clusters the coordinate data and the corresponding negative carbon emission data respectively, analyzes the distribution characteristics of the coordinate data and the negative carbon emission data through clustering, and then uses the difference in the distribution characteristics of the two to quickly locate the coordinate data and negative carbon emission data with different distribution characteristics, thereby quickly identifying the location of the carbon emission abnormality, solving the problem that the abnormal area of ​​negative carbon emissions cannot be quickly located in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial control management, and in particular to a method and system for optimizing negative carbon emissions control in industrial production. Background Art

[0002] At present, negative carbon emission control is usually based on carbon capture at fixed locations. Although this negative carbon emission optimization control method based on a fixed pattern can play some positive roles, it cannot cope with dynamic and complex situations, especially for some scenarios with a wide range of parks and complex and diverse equipment. Existing technology cannot accurately locate abnormal areas of negative carbon emissions, and thus cannot respond in a targeted manner.

[0003] Therefore, people are in urgent need of a negative carbon emission optimization control method that can quickly locate abnormal areas. Summary of the invention

[0004] Therefore, the present invention provides an industrial production negative carbon emission optimization control method and system to solve the problem in the prior art that abnormal areas of negative carbon emissions cannot be quickly located.

[0005] The present invention provides a method for optimizing and controlling negative carbon emissions in industrial production, comprising:

[0006] Obtaining coordinate data of multiple preset monitoring locations in the target area, as well as negative carbon emission data of each preset monitoring location;

[0007] Clustering the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data;

[0008] Clustering the multiple negative carbon emission data to obtain multiple second clusters consisting of the negative carbon emission data;

[0009] According to the difference between the correspondence between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster, identifying the negative carbon emission abnormal area;

[0010] Emission optimization control is carried out according to the negative carbon emission abnormal areas.

[0011] In a preferred embodiment, clustering the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data includes:

[0012] Taking Euclidean distance as the distance measurement method between coordinate data, multiple coordinate data are clustered based on the DBSCAN clustering algorithm to obtain multiple first clusters.

[0013] In a preferred embodiment: clustering the plurality of negative carbon emission data to obtain a plurality of second clusters consisting of the negative carbon emission data includes:

[0014] Finding a coordinate data closest to the centroid of each first cluster as the reference coordinate data corresponding to the first cluster;

[0015] The negative carbon emission data corresponding to the benchmark coordinate data is used as the initial center;

[0016] According to the initial center, multiple negative carbon emission data are clustered based on the K-means algorithm to obtain multiple second clusters;

[0017] The plurality of second clusters correspond one to one with the plurality of first clusters.

[0018] In a preferred embodiment: the negative carbon emission data is a vector, and in the step of clustering the multiple negative carbon emission data based on the K-means algorithm according to the initial center to obtain multiple second cluster clusters, cosine similarity is used as the distance measurement method between two negative carbon emission data.

[0019] In a preferred embodiment: the identifying of the negative carbon emission abnormal area according to the difference between the corresponding relationship between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster includes:

[0020] Counting the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster;

[0021] Obtaining a preset ratio threshold, and comparing the preset ratio threshold with the matching ratio of each second clustering cluster;

[0022] If there is a second cluster whose matching ratio is lower than the preset ratio threshold, the second cluster whose matching ratio is lower than the preset ratio threshold is regarded as an abnormal cluster;

[0023] According to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster, the negative carbon emission abnormal area is obtained.

[0024] In a preferred embodiment: the counting of the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster, includes:

[0025] Acquire the coordinate data of the first cluster corresponding to the target second cluster, and calculate the diameter of the first cluster corresponding to the target second cluster according to the distribution of the coordinate data of the first cluster corresponding to the target second cluster, wherein the target second cluster is the second cluster to be analyzed currently;

[0026] The matching ratio of the target second cluster is calculated by the following formula:

[0027] ;

[0028] in, is the matching ratio of the target second cluster, is the total number of coordinate data of the first cluster corresponding to the target second cluster, is the total number of negative carbon emission data in the second target cluster, is the number of negative carbon emission data in the target second cluster that matches the coordinate data in the corresponding first cluster, is the diameter of the first cluster corresponding to the target second cluster, and Adjust the parameters for different biases respectively.

[0029] In a preferred embodiment: the method of obtaining the negative carbon emission abnormal area according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster includes:

[0030] Obtaining coordinate data corresponding to negative carbon emission data in the abnormal cluster as the first target data set;

[0031] Performing hierarchical clustering on the first target data set to obtain a hierarchical clustering tree;

[0032] According to the division relationship of coordinate data in the hierarchical clustering tree, the negative carbon emission anomaly area is obtained.

[0033] In a preferred embodiment: the method of obtaining the negative carbon emission abnormal area according to the division relationship of the coordinate data in the hierarchical clustering tree includes:

[0034] Get the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree;

[0035] The cutoff height is obtained according to the product of the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree;

[0036] The hierarchical clustering tree is truncated based on the cutoff height to obtain a truncated tree;

[0037] According to the coordinate data corresponding to the leaf nodes in the truncated tree, the negative carbon emission anomaly area is obtained.

[0038] In a preferred embodiment: the method of obtaining the negative carbon emission abnormal area according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster includes:

[0039] Obtaining coordinate data in the first clustering cluster corresponding to the abnormal cluster, and calculating the radius of the first clustering cluster corresponding to the abnormal cluster according to the distribution of the coordinate data in the first clustering cluster corresponding to the abnormal cluster as the reference radius;

[0040] Obtaining coordinate data corresponding to negative carbon emission data in the abnormal cluster as the second target data set;

[0041] Using the average distance as the distance measure between clusters, agglomerative hierarchical clustering is performed on the second target data set;

[0042] In the process of agglomerative hierarchical clustering, when merging clusters, if the distance between all clusters is greater than the reference radius, clustering is stopped and multiple cluster subtrees are obtained;

[0043] According to the coordinate data corresponding to multiple root nodes in multiple clustering subtrees, the negative carbon emission abnormal area is obtained.

[0044] The present invention also provides an industrial production negative carbon emission optimization control system, comprising:

[0045] A data monitoring module, used to obtain coordinate data of multiple preset monitoring locations in the target area, and negative carbon emission data of each preset monitoring location;

[0046] A first clustering module, used for clustering the plurality of coordinate data to obtain a plurality of first clustering clusters consisting of the coordinate data;

[0047] A second clustering module is used to cluster the multiple negative carbon emission data to obtain multiple second clustering clusters consisting of the negative carbon emission data;

[0048] An abnormality monitoring module, used to identify an abnormal negative carbon emission area according to a difference in a correspondence between coordinate data included in the first cluster and negative carbon emission data included in the second cluster;

[0049] The optimization control module is used to perform emission optimization control according to the negative carbon emission abnormal area.

[0050] The beneficial effects of adopting the above embodiment are:

[0051] The present invention provides a method and system for optimizing and controlling negative carbon emissions in industrial production, which first obtains coordinate data of multiple preset monitoring positions in a target area, and negative carbon emission data of each preset monitoring position, and then clusters the multiple coordinate data to obtain multiple first clusters composed of coordinate data, clusters the multiple negative carbon emission data to obtain multiple second clusters composed of negative carbon emission data, and then identifies negative carbon emission abnormal areas according to the difference in the corresponding relationship between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster, and finally optimizes and controls emissions according to the negative carbon emission abnormal areas. Because carbon emissions are obviously continuously diffused in the air, their related indicators will also change continuously and smoothly without mutations, that is, under normal circumstances, the negative carbon emission data in the same area will be relatively close, and the negative carbon emission data and coordinate data should present the same distribution characteristics in space. Therefore, the present invention clusters the coordinate data and the corresponding negative carbon emission data respectively, analyzes the distribution characteristics of the coordinate data and the negative carbon emission data through clustering, and then uses the difference in their distribution characteristics to quickly locate the coordinate data and negative carbon emission data with different distribution characteristics, thereby quickly identifying the location of carbon emission anomalies, solving the problem in the prior art that it is impossible to quickly locate abnormal areas of negative carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A method flow chart of the method for optimizing and controlling negative carbon emissions in industrial production provided by the present invention;

[0053] Figure 2 for Figure 1 The method flow chart of step S104;

[0054] Figure 3 A method flow chart of the negative carbon emission optimization control system for industrial production provided by the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Combination Figure 1 As shown, a specific embodiment of the present invention discloses a method for optimizing negative carbon emissions in industrial production, comprising:

[0057] S101, obtaining coordinate data of multiple preset monitoring locations in a target area, and negative carbon emission data of each preset monitoring location;

[0058] S102, clustering the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data;

[0059] S103, clustering the multiple negative carbon emission data to obtain multiple second clusters consisting of the negative carbon emission data;

[0060] S104, identifying an abnormal negative carbon emission area according to a difference in a correspondence between coordinate data included in the first cluster and negative carbon emission data included in the second cluster;

[0061] S105. Optimize emission control according to the negative carbon emission abnormal area.

[0062] Since carbon emissions obviously diffuse continuously in the air, its related indicators will also change continuously and smoothly without sudden changes, that is, under normal circumstances, the negative carbon emission data in the same area will be relatively close, and the negative carbon emission data and coordinate data should show the same distribution characteristics in space. Therefore, the present invention clusters the coordinate data and the corresponding negative carbon emission data respectively, analyzes the distribution characteristics of the coordinate data and the negative carbon emission data through clustering, and then uses the difference in the distribution characteristics of the two to quickly locate the coordinate data and negative carbon emission data with different distribution characteristics, thereby quickly identifying the location of abnormal carbon emissions, solving the problem that the abnormal area of ​​negative carbon emissions cannot be quickly located in the prior art.

[0063] Furthermore, in a preferred embodiment, the above step S102, clustering the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data, specifically includes:

[0064] Taking Euclidean distance as the distance measurement method between coordinate data, multiple coordinate data are clustered based on the DBSCAN clustering algorithm to obtain multiple first clusters.

[0065] DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm that can effectively identify clusters in samples while handling noise and outliers. Compared with traditional distance-based clustering methods, DBSCAN does not require the number of clusters to be set in advance, but automatically determines the number and shape of clusters based on the density of samples. Its core idea is to regard high-density areas as part of the cluster and distinguish clusters from noise by determining core samples and boundary samples.

[0066] DBSCAN has many advantages, including high robustness to noise and density changes, can effectively handle clusters with irregular shapes, and does not require the number of clusters to be set in advance. In addition, DBSCAN is not affected by the order of data points in the data set, and is insensitive to the choice of parameters, so it has good versatility and scalability. In addition, DBSCAN can also effectively process large-scale data sets and maintain high performance when processing large-scale data. Therefore, DBSCAN has been widely used in various fields, such as image processing, bioinformatics, social network analysis, etc.

[0067] Most importantly, this embodiment uses DBSCAN to cluster multiple coordinate data, which can automatically analyze the number of first clusters without pre-specification, and the DBSCAN algorithm can be combined with the K-means algorithm described later to achieve automatic correspondence between the first cluster and the second cluster.

[0068] Specifically, in a preferred embodiment, the above step S103, clustering the multiple negative carbon emission data to obtain multiple second clusters consisting of the negative carbon emission data, specifically includes:

[0069] Finding a coordinate data closest to the centroid of each first cluster as the reference coordinate data corresponding to the first cluster;

[0070] The negative carbon emission data corresponding to the benchmark coordinate data is used as the initial center;

[0071] According to the initial center, multiple negative carbon emission data are clustered based on the K-means algorithm to obtain multiple second clusters;

[0072] The plurality of second clusters correspond one to one with the plurality of first clusters.

[0073] The K-means algorithm is a commonly used distance-based clustering algorithm that divides a data set into K clusters in an iterative manner, with each cluster represented by the nearest center point. The core idea of ​​the K-means algorithm is to assign sample points to the cluster represented by the nearest center point, and continuously update the position of the center point until a stable state is reached. Although the K-means algorithm is simple and intuitive, compared to DBSCAN, a natural defect of K-means is that the number of clusters K needs to be set in advance. In this embodiment, since a known number of first clustering clusters have been clustered by the DBSCAN algorithm, the number of clusters of the first clustering cluster can be directly used as the K value, that is, the reference coordinate data is determined by the centroid of the first clustering cluster, and the initial center of the K-means cluster is determined by the reference coordinate data (equivalent to determining the K value), so there is no need to pre-set the hyperparameter K. Most importantly, the K-means clustering algorithm in this embodiment is combined with the DBSCAN clustering algorithm, which not only realizes the clustering of the two types of data, but also naturally realizes the one-to-one correspondence between the first clustering cluster and the second clustering cluster, without the need for a complex analysis and pairing process, providing a data basis for post-analysis of differences to find abnormal areas, thereby improving the efficiency of the algorithm.

[0074] Furthermore, in a preferred embodiment, the negative carbon emission data is a vector, and in the step of clustering the multiple negative carbon emission data based on the K-means algorithm according to the initial center to obtain multiple second cluster clusters, cosine similarity is used as the distance measurement method between two negative carbon emission data.

[0075] In practice, there are many kinds of data that need to be monitored for negative carbon emissions, such as carbon dioxide concentration, temperature, humidity, etc. Therefore, in this embodiment, negative carbon emission data is constructed in the form of vectors, and the elements in the vectors are different monitoring data. In this way, this embodiment realizes the simultaneous analysis of multiple data from a macro perspective, so as to better optimize and control negative carbon emissions.

[0076] Further, combined with Figure 2 As shown, in a preferred embodiment, the above step S104, identifying the negative carbon emission abnormal area according to the difference in the correspondence between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster, specifically includes:

[0077] S201, counting the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster;

[0078] S202, obtaining a preset ratio threshold, and comparing the preset ratio threshold with the matching ratio of each second cluster;

[0079] S203: If there is a second cluster whose matching ratio is lower than a preset ratio threshold, the second cluster whose matching ratio is lower than the preset ratio threshold is regarded as an abnormal cluster;

[0080] S204. Obtain a negative carbon emission abnormal area according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster.

[0081] The difference in the distribution of the first cluster and the second cluster can reflect the area with abnormal negative carbon emissions. In the area with normal negative carbon emissions, the coordinate data in the first cluster should correspond to the negative carbon emission data in the second cluster. Therefore, in this embodiment, the corresponding relationship between the coordinate data in the first cluster and the negative carbon emission data in the second cluster is used to represent the difference between the corresponding first cluster and the second cluster. The second cluster with a high matching ratio indicates that its negative carbon emission data and the corresponding coordinate data in the first cluster have a good matching relationship and the data distribution is normal. On the contrary, the lower the matching ratio of the second cluster, the higher the probability that its negative carbon emission data is abnormal data.

[0082] It is understandable that in practice, other existing means such as Silhouette score may also be used to evaluate the difference between the first cluster and the second cluster.

[0083] Further, in a preferred embodiment, the above step S201, counting the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster, specifically includes:

[0084] Acquire the coordinate data of the first cluster corresponding to the target second cluster, and calculate the diameter of the first cluster corresponding to the target second cluster according to the distribution of the coordinate data of the first cluster corresponding to the target second cluster, wherein the target second cluster is the second cluster to be analyzed currently;

[0085] The matching ratio of the target second cluster is calculated by the following formula:

[0086] ;

[0087] in, is the matching ratio of the target second cluster, is the total number of coordinate data of the first cluster corresponding to the target second cluster, is the total number of negative carbon emission data in the second target cluster, is the number of negative carbon emission data in the target second cluster that matches the coordinate data in the corresponding first cluster, is the diameter of the first cluster corresponding to the target second cluster, and Adjust the parameters for different biases respectively.

[0088] In this embodiment, on the basis of calculating the proportion of coordinate data and negative carbon emission data matching, the overall scale change of clusters, the density of clusters and other considerations are further incorporated to make the matching ratio more scientific and reasonable. The second term in the above formula takes into account the overall scale change of clusters, and the proportion of the first term is corrected by the difference in the number of data in the first cluster and the second cluster: that is, when the difference in the number of data in the first cluster and the second cluster is too large, the probability of abnormality is higher, and the final calculated matching ratio value should be appropriately reduced to ensure accuracy. In addition, because the data types of the first cluster and the second cluster are different in practice, the distance measurement method is also different, and the distribution shape of the two in space is also different, so the number of data in the first cluster and the number of data in the second cluster will naturally have errors. Therefore, this embodiment compensates for this defect through the density of the first cluster, that is, the density is expressed by comparing the number of data in the first cluster with the radius of the first cluster. The higher the density, the greater the error caused by the different cluster shapes. At this time, the final matching ratio should be increased to compensate for the error.

[0089] After obtaining the abnormal cluster, the abnormal area can be directly located according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster. However, the abnormal area located in this way is too large. In order to improve the accuracy, the present invention further provides a preferred embodiment. In this embodiment, the above step S204, according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster, obtains the negative carbon emission abnormal area, specifically including:

[0090] Obtaining coordinate data corresponding to negative carbon emission data in the abnormal cluster as the first target data set;

[0091] Performing hierarchical clustering on the first target data set to obtain a hierarchical clustering tree;

[0092] According to the division relationship of coordinate data in the hierarchical clustering tree, the negative carbon emission anomaly area is obtained.

[0093] This embodiment uses hierarchical clustering to further analyze the abnormal clusters to obtain more accurate negative carbon emission abnormal areas. Hierarchical clustering is a cluster analysis method, and its basic idea is to build a hierarchical structure containing all samples by gradually merging or splitting clusters. In hierarchical clustering, samples can be gradually classified into larger and larger clusters or smaller and smaller subclusters according to their similarity or distance. This clustering method does not require the pre-specification of the number of clusters, but instead demonstrates the clustering relationship between data by constructing a clustering tree or distance matrix, thereby realizing exploratory data analysis. The advantage of hierarchical clustering is that it can provide richer information and help researchers discover clustering structures at different levels, rather than simply obtaining a certain clustering result. This method can also help understand the similarities, connections and differences between data, help discover potential patterns and structures, and is very suitable for scenarios where the number of clusters is uncertain or exploratory analysis is required. In addition, since the data of the abnormal clusters themselves is relatively small, the use of hierarchical clustering in this embodiment does not need to consider the problem of overly complex calculations, thereby ensuring computational efficiency.

[0094] Furthermore, in a preferred embodiment, the above step of obtaining the negative carbon emission abnormal area according to the division relationship of the coordinate data in the hierarchical clustering tree specifically includes:

[0095] Get the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree;

[0096] The cutoff height is obtained according to the product of the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree;

[0097] The hierarchical clustering tree is truncated based on the cutoff height to obtain a truncated tree;

[0098] According to the coordinate data corresponding to the leaf nodes in the truncated tree, the negative carbon emission anomaly area is obtained.

[0099] For the analysis of clustering trees, the cutoff height is very important, and in this embodiment, the method of multiplying the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree is adopted to obtain the cutoff height that conforms to the distribution law of the abnormal cluster itself. The truncated tree is the part above the truncation level in the clustering tree, and the distribution relationship of the coordinate data represented by its leaf nodes is the distribution mode that best conforms to the matching ratio of the abnormality calculated previously. At this time, the coordinate data corresponding to its leaf nodes can accurately locate the abnormal area.

[0100] In addition, different from the above-mentioned method of analyzing the abnormal area, the present invention also provides a preferred embodiment to analyze the negative carbon emission abnormal area in another different way:

[0101] In another preferred embodiment, the above step S204, obtaining the negative carbon emission abnormal area according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster, specifically includes:

[0102] Obtaining coordinate data in the first clustering cluster corresponding to the abnormal cluster, and calculating the radius of the first clustering cluster corresponding to the abnormal cluster according to the distribution of the coordinate data in the first clustering cluster corresponding to the abnormal cluster as the reference radius;

[0103] Obtaining coordinate data corresponding to negative carbon emission data in the abnormal cluster as the second target data set;

[0104] Using the average distance as the distance measure between clusters, agglomerative hierarchical clustering is performed on the second target data set;

[0105] In the process of agglomerative hierarchical clustering, when merging clusters, if the distance between all clusters is greater than the reference radius, clustering is stopped and multiple cluster subtrees are obtained;

[0106] According to the coordinate data corresponding to multiple root nodes in multiple clustering subtrees, the negative carbon emission abnormal area is obtained.

[0107] The clustering method is also used to analyze abnormal clusters. Unlike the previous embodiment, this embodiment uses a method of real-time monitoring of the distance between clusters. The radius of the first cluster is used as a benchmark. In the clustering process, the division method of multiple clusters whose distance exceeds the benchmark radius is found. At this time, the distance distribution of these clusters is obviously different from the distance distribution of the first cluster to which they should correspond, so that the abnormal area of ​​negative carbon emissions can be directly located. In addition, in this embodiment, there is no need to construct a complete clustering tree. Only multiple subtrees constructed in hierarchical clustering (equivalent to the part of the clustering tree below the truncation height in the previous embodiment) can be used to identify the distribution characteristics of abnormal clusters, thereby locating the abnormal area of ​​negative carbon emissions.

[0108] After the above process is completed, the negative carbon emission abnormal area can be obtained. At this time, step S105 can be performed to optimize the emission control according to the negative carbon emission abnormal area, that is, any existing method can be used for optimization control (such as suspending equipment operation, etc.).

[0109] Combination Figure 3 As shown, the present invention also provides an industrial production negative carbon emission optimization control system, comprising:

[0110] The data monitoring module 310 is used to obtain the coordinate data of multiple preset monitoring locations in the target area, and the negative carbon emission data of each preset monitoring location;

[0111] A first clustering module 320, used for clustering the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data;

[0112] A second clustering module 330 is used to cluster the multiple negative carbon emission data to obtain multiple second clusters consisting of the negative carbon emission data;

[0113] The abnormality monitoring module 340 is used to identify the negative carbon emission abnormal area according to the difference between the corresponding relationship between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster;

[0114] The optimization control module 350 is used to perform emission optimization control according to the negative carbon emission abnormal area.

[0115] It should be noted here that the corresponding industrial production negative carbon emission optimization control system provided in the above embodiments can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding contents in the above method embodiments, which will not be repeated here.

[0116] The present invention provides a method and system for optimizing and controlling negative carbon emissions in industrial production, which first obtains coordinate data of multiple preset monitoring positions in a target area, and negative carbon emission data of each preset monitoring position, and then clusters the multiple coordinate data to obtain multiple first clusters composed of coordinate data, clusters the multiple negative carbon emission data to obtain multiple second clusters composed of negative carbon emission data, and then identifies negative carbon emission abnormal areas according to the difference in the corresponding relationship between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster, and finally optimizes and controls emissions according to the negative carbon emission abnormal areas. Because carbon emissions are obviously continuously diffused in the air, their related indicators will also change continuously and smoothly without mutations, that is, under normal circumstances, the negative carbon emission data in the same area will be relatively close, and the negative carbon emission data and coordinate data should present the same distribution characteristics in space. Therefore, the present invention clusters the coordinate data and the corresponding negative carbon emission data respectively, analyzes the distribution characteristics of the coordinate data and the negative carbon emission data through clustering, and then uses the difference in their distribution characteristics to quickly locate the coordinate data and negative carbon emission data with different distribution characteristics, thereby quickly identifying the location of carbon emission anomalies, solving the problem in the prior art that it is impossible to quickly locate abnormal areas of negative carbon emissions.

[0117] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0118] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing and controlling negative carbon emissions in industrial production, characterized in that: include: Obtaining coordinate data of multiple preset monitoring locations in the target area, as well as negative carbon emission data of each preset monitoring location; Clustering the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data; Clustering the multiple negative carbon emission data to obtain multiple second clusters consisting of the negative carbon emission data; According to the difference between the correspondence between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster, identifying the negative carbon emission abnormal area; Optimize emission control based on negative carbon emission abnormal areas; The clustering of the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data includes: Taking Euclidean distance as the distance measurement method between coordinate data, clustering multiple coordinate data based on DBSCAN clustering algorithm to obtain multiple first clusters; The clustering of the plurality of negative carbon emission data to obtain a plurality of second clusters consisting of the negative carbon emission data includes: Finding a coordinate data closest to the centroid of each first cluster as the reference coordinate data corresponding to the first cluster; The negative carbon emission data corresponding to the benchmark coordinate data is used as the initial center; According to the initial center, multiple negative carbon emission data are clustered based on the K-means algorithm to obtain multiple second clusters; The plurality of second clusters correspond one to one with the plurality of first clusters; The identifying of the negative carbon emission abnormal area according to the difference between the correspondence between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster includes: Counting the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster; Obtaining a preset ratio threshold, and comparing the preset ratio threshold with the matching ratio of each second clustering cluster; If there is a second cluster whose matching ratio is lower than the preset ratio threshold, the second cluster whose matching ratio is lower than the preset ratio threshold is regarded as an abnormal cluster; According to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster, the negative carbon emission abnormal area is obtained.

2. The method for optimizing and controlling negative carbon emissions in industrial production according to claim 1, characterized in that: The negative carbon emission data is a vector. In the step of clustering the multiple negative carbon emission data based on the K-means algorithm according to the initial center to obtain multiple second clusters, cosine similarity is used as a distance measurement method between two negative carbon emission data.

3. The method for optimizing and controlling negative carbon emissions in industrial production according to claim 1, characterized in that: The counting of the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster, includes: Acquire the coordinate data of the first cluster corresponding to the target second cluster, and calculate the diameter of the first cluster corresponding to the target second cluster according to the distribution of the coordinate data of the first cluster corresponding to the target second cluster, wherein the target second cluster is the second cluster to be analyzed currently; The matching ratio of the target second cluster is calculated by the following formula: ； in, is the matching ratio of the target second cluster, is the total number of coordinate data of the first cluster corresponding to the target second cluster, is the total number of negative carbon emission data in the second target cluster, is the number of negative carbon emission data in the target second cluster that matches the coordinate data in the corresponding first cluster, is the diameter of the first cluster corresponding to the target second cluster, and They are different bias adjustment parameters.

4. The method for optimizing and controlling negative carbon emissions in industrial production according to claim 1, characterized in that: The method of obtaining the negative carbon emission abnormal area according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster includes: Obtaining coordinate data corresponding to negative carbon emission data in the abnormal cluster as the first target data set; Performing hierarchical clustering on the first target data set to obtain a hierarchical clustering tree; According to the division relationship of coordinate data in the hierarchical clustering tree, the negative carbon emission anomaly area is obtained.

5. The method for optimizing and controlling negative carbon emissions in industrial production according to claim 4, characterized in that: The negative carbon emission abnormal area is obtained according to the division relationship of the coordinate data in the hierarchical clustering tree, including: Get the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree; The cutoff height is obtained according to the product of the matching ratio corresponding to the abnormal cluster and the height of the hierarchical clustering tree; The hierarchical clustering tree is truncated based on the cutoff height to obtain a truncated tree; According to the coordinate data corresponding to the leaf nodes in the truncated tree, the negative carbon emission anomaly area is obtained.

6. The method for optimizing and controlling negative carbon emissions in industrial production according to claim 1, characterized in that: The method of obtaining the negative carbon emission abnormal area according to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster includes: Obtaining coordinate data in the first clustering cluster corresponding to the abnormal cluster, and calculating the radius of the first clustering cluster corresponding to the abnormal cluster according to the distribution of the coordinate data in the first clustering cluster corresponding to the abnormal cluster as the reference radius; Obtaining coordinate data corresponding to negative carbon emission data in the abnormal cluster as the second target data set; Using the average distance as the distance measure between clusters, agglomerative hierarchical clustering is performed on the second target data set; In the process of agglomerative hierarchical clustering, when merging clusters, if the distance between all clusters is greater than the reference radius, clustering is stopped and multiple cluster subtrees are obtained; According to the coordinate data corresponding to multiple root nodes in multiple clustering subtrees, the negative carbon emission abnormal area is obtained.

7. An industrial production negative carbon emission optimization control system, characterized in that: include: A data monitoring module, used to obtain coordinate data of multiple preset monitoring locations in the target area, as well as negative carbon emission data of each preset monitoring location; A first clustering module, used for clustering the plurality of coordinate data to obtain a plurality of first clustering clusters consisting of the coordinate data; A second clustering module is used to cluster the multiple negative carbon emission data to obtain multiple second clustering clusters consisting of the negative carbon emission data; An abnormality monitoring module, used to identify an abnormal negative carbon emission area according to a difference in a correspondence between coordinate data included in the first cluster and negative carbon emission data included in the second cluster; An optimization control module is used to optimize emission control according to the negative carbon emission abnormal area; The clustering of the plurality of coordinate data to obtain a plurality of first clusters consisting of the coordinate data includes: Taking Euclidean distance as the distance measurement method between coordinate data, clustering multiple coordinate data based on DBSCAN clustering algorithm to obtain multiple first clusters; The clustering of the plurality of negative carbon emission data to obtain a plurality of second clusters consisting of the negative carbon emission data includes: Finding a coordinate data closest to the centroid of each first cluster as the reference coordinate data corresponding to the first cluster; The negative carbon emission data corresponding to the benchmark coordinate data is used as the initial center; According to the initial center, multiple negative carbon emission data are clustered based on the K-means algorithm to obtain multiple second clusters; The plurality of second clusters correspond one to one with the plurality of first clusters; The identifying of the negative carbon emission abnormal area according to the difference between the correspondence between the coordinate data included in the first cluster and the negative carbon emission data included in the second cluster includes: Counting the number of negative carbon emission data in each second cluster that matches the coordinate data in the corresponding first cluster, and obtaining the matching ratio of each second cluster according to the total number of negative carbon emission data in each second cluster; Obtaining a preset ratio threshold, and comparing the preset ratio threshold with the matching ratio of each second clustering cluster; If there is a second cluster whose matching ratio is lower than the preset ratio threshold, the second cluster whose matching ratio is lower than the preset ratio threshold is regarded as an abnormal cluster; According to the coordinate data corresponding to the negative carbon emission data in the abnormal cluster, the negative carbon emission abnormal area is obtained.

Images