Information adjustment method and device, electronic equipment and computer readable medium

Abstract

Embodiments of the present disclosure disclose information adjustment methods and devices, electronic equipment and computer readable media. A specific embodiment of the method comprises: obtaining target coke refining requirement information; determining a corresponding first clustering center from a first clustering center set; determining coke refining theory information; inputting at least one theoretical index information of a blending coal into a blending coal information expansion network model to generate a blending coal theoretical index information set; controlling a target coking equipment to realize coke refining; in response to the end of coke refining, obtaining a coking process actual operation parameter set and a blending coal actual index information set; inputting the corresponding parameter information set and the blending coal actual index information set into a coking energy consumption prediction model to output coking energy consumption prediction information; and adjusting the first clustering center in the first clustering center set. The embodiment can utilize the adjusted first clustering center set to efficiently realize coke refining and avoid resource waste.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer technology, and in particular, to an information adjustment method and device, an electronic device, and a computer readable medium. BACKGROUND

[0002] At present, as an important energy, coke is often used in various industrial industries (for example, ironmaking industry). For the coking, the commonly used way is: first, the index information in the coking process is determined by the relevant technical personnel according to experience. Then, according to the index information, the coking is realized.

[0003] However, the inventors have found that when the above-mentioned way is used to coking, the following technical problems often exist:

[0004] First, for coke with different quality requirements, more reasonable and accurate index information cannot be efficiently and flexibly determined, resulting in waste of resources.

[0005] Second, because the environmental characteristics of the environment where the coke is located are similar to the characteristics of the coke itself, the coke image cannot be accurately and effectively segmented by using a conventional image segmentation model.

[0006] The above information disclosed in the background section is only for the purpose of enhancing the understanding of the background of the inventive concepts, and therefore, it can contain information that does not form the prior art known to those of ordinary skill in the art in the country. SUMMARY

[0007] The summary section is provided to introduce the concepts briefly in a simplified form, which will be described in detail in the specific embodiments section. The summary section is not intended to identify key or essential features of the claimed technical solutions nor is it intended to be used to limit the scope of the claimed technical solutions.

[0008] Some embodiments of the present disclosure propose an information adjustment method and device, an electronic device, and a computer readable medium to solve one or more of the technical problems mentioned in the background section.

[0009] In a first aspect, some embodiments of the present disclosure provide an information adjustment method, comprising: obtaining target coke-making requirement information for a target coking device; determining a first clustering center corresponding to the target coke-making requirement information from a pre-configured first clustering center set as a target clustering center; determining coke-making theory information according to the target clustering center, wherein the coke-making theory information comprises at least one theoretical index information of a blending coal and a set of coking process required operation parameters, and the at least one theoretical index information of the blending coal is index information after principal component analysis; inputting the at least one theoretical index information of the blending coal into a blending coal information expansion network model to generate a set of theoretical index information of the blending coal; controlling the target coking device to realize coke-making according to the set of theoretical index information of the blending coal and the set of coking process required operation parameters; obtaining a set of actual operation parameters of the coking process and a set of actual index information of the blending coal determined by a monitoring instrument in response to the end of the coke-making; inputting a set of parameter information corresponding to the set of actual operation parameters of the coking process and the set of actual index information of the blending coal into a coking energy consumption prediction model to output coking energy consumption prediction information; and adjusting the first clustering center in the first clustering center set according to the coking energy consumption prediction information and the target coke-making requirement information.

[0010] In a second aspect, some embodiments of the present disclosure provide an information adjustment device, comprising: a first obtaining unit configured to obtain target coke-making requirement information for a target coking device; a first determining unit configured to determine a first clustering center corresponding to the target coke-making requirement information from a pre-configured first clustering center set as a target clustering center; a second determining unit configured to determine coke-making theory information according to the target clustering center, wherein the coke-making theory information comprises at least one theoretical index information of a blending coal and a set of coking process required operation parameters, and the at least one theoretical index information of the blending coal is index information after principal component analysis; a first input unit configured to input the at least one theoretical index information of the blending coal into a blending coal information expansion network model to generate a set of theoretical index information of the blending coal; a control unit configured to control the target coking device to realize coke-making according to the set of theoretical index information of the blending coal and the set of coking process required operation parameters; a second obtaining unit configured to obtain a set of actual operation parameters of the coking process and a set of actual index information of the blending coal determined by a monitoring instrument in response to the end of the coke-making; a second input unit configured to input a set of parameter information corresponding to the set of actual operation parameters of the coking process and the set of actual index information of the blending coal into a coking energy consumption prediction model to output coking energy consumption prediction information; and an adjustment unit configured to adjust the first clustering center in the first clustering center set according to the coking energy consumption prediction information and the target coke-making requirement information.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having stored thereon one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any implementation of the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0013] The above various embodiments of the present disclosure have the following beneficial effects: the information adjustment method of some embodiments of the present disclosure can efficiently realize the coking by using the adjusted first cluster center set, and avoid waste of resources. Specifically, the reason why the related coking is not efficient is that the more reasonable and accurate index information cannot be efficiently and flexibly determined for the coking with different quality requirements, resulting in waste of resources. Based on this, the information adjustment method of some embodiments of the present disclosure first acquires target coking requirement information for a target coking device, which is used to subsequently determine coking theory information corresponding to the target coking requirement information. Then, a first cluster center corresponding to the target coking requirement information is determined from a pre-configured first cluster center set as a target cluster center. Here, by using the pre-configured first cluster center for each type of coking requirement information, the most reasonable target cluster center corresponding to the target coking requirement information and most matched to the performance of the target coking device can be quickly and accurately determined, so as to subsequently generate coking theory information matched to the target coking requirement information. Then, the coking theory information matched to the target coking requirement information can be accurately determined according to the target cluster center. The coking theory information includes at least one theoretical index information of a blending coal and a set of required operation parameters in a coking process, and the at least one theoretical index information of the blending coal is index information after principal component analysis. Further, the at least one theoretical index information of the blending coal is input into a blending coal information expansion network model to generate a set of theoretical index information of the blending coal. Here, the index information expansion of the blending coal information expansion network model makes the at least one theoretical index information of the blending coal more perfect, so that more coking parameters can be referred to in subsequent coking. Then, the target coking device is controlled to realize accurate and efficient coking according to the set of theoretical index information of the blending coal and the set of required operation parameters in the coking process. Further, in response to the end of the coking, a set of actual operation parameters in the coking process determined by a monitoring instrument and a set of actual index information of the blending coal are acquired, which are used to subsequently determine actual coking energy consumption caused by the coking. Finally, the first cluster center in the first cluster center set is adjusted according to the coking energy consumption prediction information and the target coking requirement information. Here, the energy consumption is compared between the coking energy consumption prediction information and the coking energy consumption requirement information in the target coking requirement information, so as to determine whether there is an energy consumption problem in the whole coking process of determining the target cluster center to coking. Thus, the first cluster center in the first cluster center set is adjusted by judging the energy consumption, so that the first cluster center set is more accurate. Each first cluster center can accurately correspond to a unique coking requirement.In summary, by applying the first cluster center set and updating the first cluster center set, the coke can be efficiently refined by using the adjusted first cluster center set, and the waste of resources can be avoided. BRIEF DESCRIPTION OF DRAWINGS

[0014] The above and other features, aspects, and advantages of the present disclosure will become more apparent with reference to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, similar or same reference numerals can be used for similar or same elements. It should be understood that the drawings are schematic and elements and features can not be necessarily drawn to scale.

[0015] Figure 1 is a flowchart of some embodiments of the information adjustment method according to the present disclosure;

[0016] Figure 2 is a structural schematic diagram of some embodiments of the information adjustment apparatus according to the present disclosure;

[0017] Figure 3 is a structural schematic diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail with reference to the drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of protection of the present disclosure.

[0019] In addition, it should be further noted that only the parts related to the present application are shown in the drawings for ease of description. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0020] It should be noted that the terms “first”, “second”, and the like mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the adjectives “one”, “multiple” mentioned in the present disclosure are illustrative rather than limiting, and those skilled in the art should understand that, unless otherwise explicitly stated in the context, it should be understood as “one or more”.

[0022] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] Reference Figure 1 Fig. 1 shows a flow 100 of some embodiments of the information adjustment method according to the present disclosure. The information adjustment method comprises the following steps:

[0025] Step 101, obtaining target coke-making requirement information for a target coking device.

[0026] In some embodiments, the subject (e.g., an electronic device) of the above information adjustment method can obtain the target coke-making requirement information for the target coking device through wired or wireless connection. The target coking device can be a device for making coke. In practice, the target coking device can include, but is not limited to, at least one of the following: a coal blending feeding device, a coking oven, a raw coal gas treatment device, and a coke quenching device. The target coke-making requirement information can be the coke index information of the coke required by the coke-making requirement party. For example, the coke index information can include index information of a coke ash index, index information of a coke sulfur content index, coke abrasion resistance standard information, and coke crushing strength standard information.

[0027] Step 102, determining a first clustering center corresponding to the target coke-making requirement information from a pre-configured first clustering center set as a target clustering center.

[0028] In some embodiments, the subject can determine a first clustering center corresponding to the target coke-making requirement information from a pre-configured first clustering center set as a target clustering center. Each clustering center can be an encoding vector representing the corresponding characteristic information of the coke-making theory information corresponding to the coke-making requirement information. Each first clustering center has corresponding coke-making requirement information.

[0029] In practice, for the first clustering center as an encoding vector, the subject can input the first clustering center into a coke-making estimation information generation model to output the coke-making estimation information generation model corresponding to the coke-making theory information corresponding to the first clustering center (i.e., coke-making index information). The coke-making estimation information generation model can be a model for generating each coke index information of the coke after making. For example, the coke index generation model can be an RBF prediction model.

[0030] In practice, the first clustering center set can be generated by the following steps:

[0031] First, obtain a coke-making theory information set.

[0032] Secondly, each of the coke-making theory information in the set of coke-making theory information is input into an encoding network model to output an encoding vector, so as to obtain a set of encoding vectors. The information encoding network model can be a network model for encoding the coke-making theory information. For example, the encoding network model can be a Transformer encoding model.

[0033] Thirdly, the set of encoding vectors is clustered to obtain a first set of clustering centers. Each of the first clustering centers corresponds to a cluster of encoding vectors.

[0034] In some optional implementations of some embodiments, the determination of the first clustering center corresponding to the target coke-making requirement information from the preconfigured first set of clustering centers as the target clustering center can include the following steps:

[0035] Firstly, the coke-making requirement theory information corresponding to each of the first clustering centers in the first set of clustering centers is determined to obtain a set of coke-making requirement theory information.

[0036] Secondly, each of the coke-making requirement theory information in the set of coke-making requirement theory information is input into a coke-making estimation information generation model to output coke-making estimation information. The coke-making estimation information generation model can be a model for generating coke-making index information.

[0037] Thirdly, at least one of the first clustering centers is selected from the first set of clustering centers, in which the information difference between the coke-making estimation information corresponding to the first clustering center and the target coke-making requirement information satisfies a preset information difference condition. The preset information difference condition can be that the difference between the corresponding coke-making index information is within a corresponding interval range.

[0038] Fourthly, a weighted summation vector between each of the at least one of the first clustering centers is generated to obtain a set of summation vectors.

[0039] Fifthly, for each of the summation vectors in the set of summation vectors, verification information representing the feasibility ratio of the coke-making scheme corresponding to the summation vector is generated. The feasibility ratio can represent the success probability of executing the coke-making scheme by using the target coke-making equipment.

[0040] As an example, for each of the summation vectors in the set of summation vectors, the execution subject can input the summation vector into a feasibility ratio generation model to generate the feasibility ratio corresponding to the summation vector, so as to obtain the corresponding verification information. The feasibility ratio generation model can be a multi-layer convolutional neural network model.

[0041] Step 6, removing the summation vectors corresponding to the verification information representing that the feasibility ratio of the coking scheme is less than a predetermined ratio from the summation vector set to obtain a removed vector set. For example, the predetermined ratio is 60%.

[0042] Step 7, aggregating the removed vector set and the at least one first cluster center to generate an aggregated vector set.

[0043] Step 8, determining the coke coking energy consumption requirement information and coke coking value resource consumption information corresponding to each aggregated vector in the aggregated vector set to obtain a coke coking energy consumption requirement information set and a corresponding coke coking value resource consumption information set.

[0044] Step 9, generating a table for the coke coking energy consumption requirement information set and the coke coking value resource consumption information set.

[0045] Step 10, sending the table to the coking requirement party client for the cluster center to select the coke coking requirement theoretical information corresponding to the table.

[0046] Step 103, determining the coke coking theoretical information according to the target cluster center.

[0047] In some embodiments, the execution subject can determine the coke coking theoretical information according to the target cluster center. The coke coking theoretical information includes at least one blending coal theoretical index information and a coking process requirement operation parameter set. The at least one blending coal theoretical index information is index information after principal component analysis. The blending coal theoretical index information can be the theoretical index information of the blending ratio for coking. In practice, the at least one blending coal theoretical index information can include but is not limited to at least one of the following: ash content index information, moisture content index information, sulfur content index information, volatile content index information, coking time index information, and blending coal corresponding ratio index information. The coking process requirement operation parameter can be a coking operation parameter in the coking process. In practice, the coking process requirement operation parameter can include but is not limited to at least one of the following: machine side flue temperature parameter, coke side flue temperature parameter, machine side flue suction parameter, and coke side flue suction parameter. The principal component analysis can be a principal component analysis method (PCA) for blending coal theoretical index.

[0048] As an example, the execution subject can input the target cluster center into a decoding model to output the coke coking theoretical information. In practice, the decoding model can be a Transformer decoding model.

[0049] Step 104, inputting the at least one blending coal theoretical index information into a blending coal information expansion network model to generate a blending coal theoretical index information set.

[0050] In some embodiments, the execution subject can input the at least one blending coal theoretical index information into a blending coal information expansion network model to generate a blending coal theoretical index information set. The blending coal information expansion network model can be a model for generating index information corresponding to the blending coal. In practice, the blending coal information expansion network model can be a multi-head attention mechanism model. The number of blending coal theoretical index information included in the blending coal theoretical index information set is greater than the number of blending coal theoretical index information included in the at least one blending coal theoretical index information.

[0051] In step 105, the target coking equipment is controlled to realize coke coking according to the blending coal theoretical index information set and the coking process required operation parameter set.

[0052] In some embodiments, the execution subject can control the target coking equipment to realize coke coking according to the blending coal theoretical index information set and the coking process required operation parameter set.

[0053] For example, the execution subject can adjust the index corresponding to the blending coal according to the blending coal theoretical index information set, and adjust the operation parameter in the coking process according to the coking process required operation parameter set, to control the target coking equipment to realize coke coking.

[0054] In step 106, in response to the end of coke coking, a coking process actual operation parameter set and a blending coal actual index information set determined by a monitoring instrument are obtained.

[0055] In some embodiments, in response to the end of coke coking, the execution subject can obtain a coking process actual operation parameter set and a blending coal actual index information set determined by a monitoring instrument. The monitoring instrument can be an instrument for detecting the blending coal actual index information and / or the coking process actual operation parameter.

[0056] In step 107, a parameter information set corresponding to the coking process actual operation parameter set and the blending coal actual index information set are input into a coking energy consumption prediction model to output coking energy consumption prediction information.

[0057] In some embodiments, the execution subject can input the parameter information set corresponding to the coking process actual operation parameter set and the blending coal actual index information set into a coking energy consumption prediction model to output coking energy consumption prediction information. The coking energy consumption prediction model can be a model for predicting coking energy consumption information. The coking energy consumption can be energy information consumed in the entire process of coking coke. In practice, the coking energy consumption prediction model can be a residual network (Residual Network, ResNet) model.

[0058] Step 108, adjusting the first clustering center in the first clustering center set according to the coking energy consumption prediction information and the target coke making requirement information.

[0059] In some embodiments, the execution subject can adjust the first clustering center in the first clustering center set according to the coking energy consumption prediction information and the target coke making requirement information.

[0060] In some optional implementations of some embodiments, the target coke making requirement information includes coke making energy consumption requirement information. The coke making energy consumption requirement information can be maximum energy consumption requirement information for making coke.

[0061] Optionally, the adjusting the first clustering center in the first clustering center set according to the coking energy consumption prediction information and the target coke making requirement information can include the following steps:

[0062] First, in response to determining that the energy consumption value corresponding to the coking energy consumption prediction information is greater than the energy consumption value corresponding to the coke making energy consumption requirement information, a vector for the coking energy consumption prediction information is generated.

[0063] As an example, first, the execution subject can generate coke making actual information according to the coking process actual operation parameter set and the blending coal actual index information set. Then, the coke making actual information is input into the encoding network model to output the vector.

[0064] Second, the vector is added to the vector cluster corresponding to the target clustering center as a target vector cluster.

[0065] Third, the vector distance between the vector and the target clustering center is determined.

[0066] The vector distance can be a cosine distance.

[0067] Fourth, a vector region range is generated with a predetermined multiple value of the vector distance as the radius and the target clustering center as the center. For example, the predetermined multiple value can be 2 times.

[0068] Fifth, a vector set within the vector region range is determined from the target vector cluster.

[0069] Sixth, the vector set is clustered to obtain a second clustering center set.

[0070] Seventh, a weighted sum vector corresponding to each second clustering center in the second clustering center set is determined.

[0071] The eighth step is to determine the vector closest to the cosine distance of the weighted sum vector from the above vector set as the nearest cluster center.

[0072] The ninth step is to update the cluster center of the first cluster center set according to the nearest cluster center to obtain a candidate cluster center set.

[0073] As an example, first, the execution subject can replace the corresponding cluster center in the first cluster center set with the nearest cluster center to obtain a replacement cluster center set. Then, using the vector set corresponding to the replacement cluster center set, the replacement cluster center set is reprocessed for cluster center update to obtain a candidate cluster center set.

[0074] The tenth step is to generate an adjusted cluster center set according to the candidate cluster center set.

[0075] As an example, the execution subject can determine the candidate cluster center set as the adjusted cluster center set.

[0076] Optionally, the step of generating an adjusted cluster center set according to the candidate cluster center set can include the following steps:

[0077] The first step is to obtain a cluster cluster division label information set. The cluster cluster division label information can be the label information corresponding to each cluster cluster. That is, the difference between each label information of each two cluster clusters is large. According to each label, the division of the cluster cluster can be realized. In practice, the cluster cluster division label information set includes at least one remaining blending coal index label. The label of the at least one remaining blending coal index label is completely different from the at least one label corresponding to the at least one blending coal theoretical index information. In practice, the at least one remaining blending coal index label can include a blending coal fineness label, a blending coal coalification degree label, a blending coal lithofacies label, and a blending coal swelling pressure label.

[0078] The second step is to determine the label level corresponding to each cluster cluster division label information in the cluster cluster division label information set. Each label level has a corresponding cluster cluster division label information group.

[0079] For example, the at least one remaining blending coal index label includes a first blending coal theoretical index label, a second blending coal theoretical index label, and a third blending coal theoretical index label. The label level includes a first level, a second level, and a third level. The first blending coal theoretical index label corresponds to the first level. The second blending coal theoretical index label corresponds to the second level. The third blending coal theoretical index label corresponds to the third level.

[0080] The third step involves inputting each candidate cluster center from the aforementioned candidate cluster center set into the cluster partitioning label generation model to generate at least one cluster partitioning label for each candidate cluster center. This cluster partitioning label generation model can be a model that generates at least one other blended coal index label corresponding to at least one other blended coal index information. In practice, the aforementioned cluster partitioning label generation model can be a generative or adversarial neural network model.

[0081] Fourth, for every two candidate cluster centers in the above candidate cluster center set, perform the following determination steps:

[0082] Sub-step 1, for each tag level, performs the following proportional generation steps:

[0083] The first sub-step involves determining, in response to the determination that there is a difference in the content of the corresponding cluster partitioning labels, at least one cluster partitioning label information is determined where there is a difference in the content of the cluster partitioning labels between every two candidate cluster centers.

[0084] The second sub-step involves determining the label-level difference ratio corresponding to at least one cluster partitioning label information. This label-level difference ratio can be the ratio of the number of information items corresponding to at least one cluster partitioning label information to the number of information items corresponding to the cluster partitioning label information set.

[0085] Sub-step 2: Based on the obtained set of label-level difference ratios, generate merging information that characterizes whether each pair of candidate cluster centers is a cluster center to be merged.

[0086] As an example, in response to a situation where the label level difference ratio corresponding to the highest determined label level is greater than 60%, merge information is generated indicating that each pair of candidate cluster centers is a cluster center to be merged. In response to a situation where the label level difference ratio corresponding to the highest determined label level is less than 60%, and the label level difference ratios corresponding to the remaining predetermined number of label levels are less than 70%, merge information is generated indicating that each pair of candidate cluster centers is not a cluster center to be merged. In response to a situation where the label level difference ratio corresponding to the highest determined label level is less than 60%, and the label level difference ratios corresponding to the remaining predetermined number of label levels are greater than 70%, merge information is generated indicating that each pair of candidate cluster centers is a cluster center to be merged. The predetermined number can be the number of label levels minus 2.

[0087] The fifth step is to determine the set of candidate cluster centers as adjusted cluster centers in response to the determination that the cluster centers corresponding to each pair of candidate cluster centers do not merge.

[0088] Optionally, the steps also include:

[0089] In a first step, in response to determining that there exists a pair of candidate cluster centers corresponding to the merging information, the at least two candidate cluster centers to be merged are determined.

[0090] In a second step, it is determined whether there exists a repeated candidate cluster center in the at least two candidate cluster centers.

[0091] In a third step, in response to determining that there does not exist, a corresponding cluster merging is performed on the pair of corresponding cluster centers in the at least two candidate cluster centers to be merged according to the obtained merging information set, to obtain at least one merged cluster.

[0092] In a fourth step, for each of the at least one merged cluster, a weighted sum vector corresponding to the pair of cluster centers corresponding to the merged cluster is determined as a merged cluster center corresponding to the merged cluster.

[0093] In a fifth step, a cluster update is performed on the cluster set corresponding to the first cluster center set according to the at least one merged cluster, to obtain an updated cluster set.

[0094] As an example, the execution subject can replace the cluster subset in the cluster set with the at least one merged cluster to obtain the updated cluster set.

[0095] In a sixth step, the adjusted cluster center set is generated according to the updated cluster set and the obtained merged cluster center set.

[0096] As an example, the execution subject can perform a re-computation and selection of cluster centers according to the updated cluster set and the merged cluster center set, to generate the adjusted cluster center set.

[0097] In some optional implementations of some embodiments, after step 108, the steps further include:

[0098] In a first step, a coke image for the refined coke set is obtained.

[0099] In a second step, the coke image is input into a coke segmentation model to generate a coke sub-image, to obtain a coke sub-image set. The number of pixels of the coke object corresponding to each coke sub-image in the coke sub-image set is greater than a predetermined number. The coke segmentation model can be a neural network model for segmenting a coke sub-image. For example, the coke segmentation model can be a Mask R-CNN model.

[0100] In a third step, according to the coke part information corresponding to each coke sub-image, an image selective supplementing process is performed on each coke sub-image in the coke sub-image set to generate a supplemented image, to obtain a supplemented image set.

[0101] As an example, first, in response to determining that the coke part shown in the coke sub-image is a section part, a pixel gradient map of the pixel region corresponding to the section part is determined. Then, according to the pixel gradient map, pixel supplement is performed on the pixel region corresponding to the section part to obtain a supplemented image. In response to determining that the coke part shown in the coke sub-image is an edge part, the above-mentioned coke sub-image does not perform pixel supplement.

[0102] Fourthly, input each supplemented image in the above-mentioned supplemented image set into a feature extraction model to generate image feature information, and obtain an image feature information set. The feature extraction model can be a model for extracting image features. In practice, the feature extraction model includes a texture feature extraction sub-model and a granularity feature extraction sub-model. The feature extraction model can be a plurality of convolutional neural network modules. Each convolutional neural network module is composed of at least one convolutional neural network in series.

[0103] Fifthly, perform clustering processing on the above-mentioned image feature information set to obtain a cluster center set.

[0104] Sixthly, for each cluster center in the above-mentioned cluster center set, the following generation steps are performed:

[0105] Sub-step 1: input the above-mentioned cluster center into a coke appearance information generation model to output coke granularity uniformity information, coke transverse and longitudinal crack information, coke section information and coke edge information. The coke appearance information generation model can be a model for generating coke appearance information. In practice, the coke appearance information generation model can be a multi-class output residual network model.

[0106] Sub-step 2: generate first coke quality verification information according to the above-mentioned coke granularity uniformity information, the above-mentioned coke transverse and longitudinal crack information, the above-mentioned coke section information and the above-mentioned coke edge information.

[0107] As an example, in response to determining that the coke granularity uniformity information satisfies a preset granularity condition, the coke transverse and longitudinal crack information satisfies a preset transverse and longitudinal crack condition, and the coke edge information satisfies a preset edge condition, verification information representing that the coke quality is qualified is generated. The preset granularity condition can be that the uniformity of the corresponding coke granularity is in a preset interval. The preset transverse and longitudinal crack condition can be that the number of the transverse and longitudinal cracks corresponding to the coke is less than a predetermined number, and the size of the transverse and longitudinal cracks is less than a predetermined size. The preset edge condition can be that the sharpness of the edge corresponding to the coke is greater than a predetermined sharpness degree, and the sharpness of the edge is greater than a predetermined sharpness degree.

[0108] Fifthly, generate quality verification information for the above-mentioned set of refined coke according to the obtained first coke quality verification information set.

[0109] As an example, first, a proportion of verification information in the first coke quality verification information set that represents that coke quality is qualified is determined. Then, in response to determining that the proportion is greater than 60%, verification information representing that the quality of the refined coke set is qualified is generated.

[0110] Optionally, the execution subject inputs the coke image into the coke segmentation model to generate coke sub-images, and obtains a coke sub-image set, which can include the following steps:

[0111] In a first step, a binary image is obtained by performing binary processing on the coke image using a binary model included in the coke segmentation model according to a predetermined pixel division threshold. For example, the predetermined pixel division threshold can be 30.

[0112] In a second step, a binary image region corresponding to a value of 1 and having a pixel number greater than a predetermined number is determined from the binary image, and at least one binary image region is obtained.

[0113] In a third step, a region boundary shape corresponding to each binary image region in the at least one binary image region is determined.

[0114] In a fourth step, a binary image region having a shape different from a preset shape is removed from the at least one binary image region, and a first removed binary image region set is obtained. In practice, the preset shape can be a triangular shape.

[0115] In a fifth step, density information corresponding to a value of 1 in each first removed binary image region in the first removed binary image region set is determined.

[0116] In a sixth step, a first removed binary image region having density information less than a predetermined value is removed from the first removed binary image region set, and a second removed binary image region set is obtained.

[0117] In a seventh step, an image subset corresponding to the second removed binary image region set is input into a coke recognition model included in the coke segmentation model to output a coke recognition result set. The coke recognition model can be a model for recognizing whether an image object is coke. For example, the coke recognition model can be a multi-layer convolutional neural network model.

[0118] In an eighth step, an image corresponding to a coke recognition result representing that the image is not coke is removed from the image subset, and a removed image subset is obtained.

[0119] In a ninth step, each removed image in the removed image subset is input into an image segmentation model included in the coke segmentation model to output a coke sub-image set. The image segmentation model can be a model for segmenting coke objects in an image. For example, the image segmentation model can be a Faster RCNN model.

[0120] The contents of the first step to the ninth step above, as one of the application points of the present disclosure, solve the second technical problem mentioned in the background art, i.e., "because the environmental characteristics of the environment where the coke is located are similar to the characteristics of the coke itself, the coke image cannot be accurately and effectively segmented by a conventional image segmentation model". Based on this, the present disclosure can preliminarily screen out the image content in the coke image corresponding to the color tone associated with black through the binarization processing of the coke image, so as to remove the relevant background characteristic information and avoid the subsequent coke recognition model learning more useless feature information. In addition, through the screening of the shape and density corresponding to the binarized image area, the information of the items similar in color tone to the coke and the ground area information with low coke density in the coke image can also be removed, so that the image subset corresponding to the removed binarized image area set more embodies the content related to the coke. Based on this, the image segmentation model can be used again to remove more background feature information in the coke image, so that the coke segmentation is more efficient and accurate.

[0121] Optionally, the generating of the quality verification information for the set of cokes based on the obtained first coke quality verification information set can include the following steps:

[0122] In the first step, coke landing audio for a subset of cokes is obtained. The subset of cokes is a predetermined number of cokes randomly selected from the set of cokes.

[0123] In the second step, the coke landing audio is input into a coke landing sound category determination model to generate a landing sound category for each coke in the subset of cokes, thereby obtaining a set of landing sound categories. The coke landing sound category determination model can be a model for determining the landing sound category corresponding to the coke landing sound. The landing sound category can include a crisp category and a dull category. The landing sound is different for cokes with different water content, and the greater the moisture, the duller the landing sound. In practice, the coke landing sound category determination model can be a DNN (Deep-Learning Neural Network).

[0124] In the third step, the second coke quality verification information is generated based on the set of landing sound categories.

[0125] As an example, first, the execution subject can determine the proportion of the landing sound category corresponding to the crisp category. Then, in response to determining that the proportion of the landing sound category is greater than 60%, verification information representing that the quality of the subset of cokes is qualified is generated.

[0126] In the fourth step, the quality verification information is generated based on the first coke quality verification information set and the second coke quality verification information.

[0127] As an example, in response to determining that the first coke quality validation information set characterizes the set of refined cokes as being of acceptable quality, quality validation information is generated characterizing the set of refined cokes as being of acceptable quality. In response to determining that the first coke quality validation information set characterizes the set of refined cokes as being of unacceptable quality and the second coke quality validation information set characterizes the subset of cokes as being of unacceptable quality, quality validation information is generated characterizing the set of refined cokes as being of unacceptable quality.

[0128] The above various embodiments of the present disclosure have the following beneficial effects: the information adjustment method of some embodiments of the present disclosure can efficiently realize the coking by using the adjusted first cluster center set, and avoid waste of resources. Specifically, the reason why the related coking is not efficient is that the more reasonable and accurate index information cannot be efficiently and flexibly determined for the coking with different quality requirements, resulting in waste of resources. Based on this, the information adjustment method of some embodiments of the present disclosure first acquires target coking requirement information for a target coking device, which is used to subsequently determine coking theory information corresponding to the target coking requirement information. Then, a first cluster center corresponding to the target coking requirement information is determined from a pre-configured first cluster center set as a target cluster center. Here, by using the pre-configured first cluster center for each type of coking requirement information, the most reasonable target cluster center corresponding to the target coking requirement information and most matched to the performance of the target coking device can be quickly and accurately determined, so as to subsequently generate coking theory information matched to the target coking requirement information. Then, the coking theory information matched to the target coking requirement information can be accurately determined according to the target cluster center. The coking theory information includes at least one theoretical index information of a blending coal and a set of required operation parameters in a coking process, and the at least one theoretical index information of the blending coal is index information after principal component analysis. Further, the at least one theoretical index information of the blending coal is input into a blending coal information expansion network model to generate a set of theoretical index information of the blending coal. Here, the index information expansion of the blending coal information expansion network model makes the at least one theoretical index information of the blending coal more perfect, so that more coking parameters can be referred to in subsequent coking. Then, the target coking device is controlled to realize accurate and efficient coking according to the set of theoretical index information of the blending coal and the set of required operation parameters in the coking process. Further, in response to the end of the coking, a set of actual operation parameters in the coking process determined by a monitoring instrument and a set of actual index information of the blending coal are acquired, which are used to subsequently determine actual coking energy consumption caused by the coking. Finally, the first cluster center in the first cluster center set is adjusted according to the coking energy consumption prediction information and the target coking requirement information. Here, the energy consumption is compared between the coking energy consumption prediction information and the coking energy consumption requirement information in the target coking requirement information, so as to determine whether there is an energy consumption problem in the whole coking process of determining the target cluster center to coking. Thus, the first cluster center in the first cluster center set is adjusted by judging the energy consumption, so that the first cluster center set is more accurate. Each first cluster center can accurately correspond to a unique coking requirement.In summary, by applying and updating the first cluster center set, the coke can be efficiently refined by using the adjusted first cluster center set, and the waste of resources can be avoided.

[0129] Further referring to Figure 2 , as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of information adjustment devices, which correspond to the method embodiments shown in Figure 1 , and the information adjustment devices can be specifically applied in various electronic devices.

[0130] As shown in Figure 2 , an information adjustment device 200 includes a first obtaining unit 201, a first determining unit 202, a second determining unit 203, a first input unit 204, a control unit 205, a second obtaining unit 206, a second input unit 207, and an adjustment unit 208. The first obtaining unit 201 is configured to obtain target coke refining requirement information for a target coking device. The first determining unit 202 is configured to determine a first cluster center corresponding to the target coke refining requirement information from a pre-configured first cluster center set as a target cluster center. The second determining unit 203 is configured to determine coke refining theory information according to the target cluster center, wherein the coke refining theory information includes at least one theoretical index information of a blending coal and a set of coking process required operation parameters, and the at least one theoretical index information of the blending coal is index information after principal component analysis. The first input unit 204 is configured to input the at least one theoretical index information of the blending coal to a blending coal information expansion network model to generate a set of theoretical index information of the blending coal. The control unit 205 is configured to control the target coking device to realize coke refining according to the set of theoretical index information of the blending coal and the set of coking process required operation parameters. The second obtaining unit 206 is configured to obtain a set of actual operation parameters of the coking process and a set of actual index information of the blending coal determined by a monitoring instrument in response to the end of the coke refining. The second input unit 207 is configured to input a set of parameter information corresponding to the set of actual operation parameters of the coking process and the set of actual index information of the blending coal to a coking energy consumption prediction model to output coking energy consumption prediction information. The adjustment unit 208 is configured to adjust the first cluster center in the first cluster center set according to the coking energy consumption prediction information and the target coke refining requirement information.

[0131] It can be understood that the units recorded in the information adjustment device 200 correspond to each step in the method described with reference to Figure 1 . Therefore, the operations, features, and beneficial effects described above for the method also apply to the information adjustment device 200 and the units contained therein, and will not be described here again.

[0132] The following description refers to Figure 3 which shows a structural schematic diagram of an electronic device (e.g., electronic device) 300 suitable for use in implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the function and scope of use of embodiments of the present disclosure.

[0133] As Figure 3 shown, the electronic device 300 can include a processing device (e.g., central processor, graphics processor, etc.) 301 that can perform various appropriate actions and processes according to programs stored in a read-only memory 302 or loaded from a storage device 308 into a random access memory 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other through a bus 304. An input / output interface 305 is also connected to the bus 304.

[0134] Generally, the following devices can be connected to the input / output interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 can allow the electronic device 300 to communicate wirelessly or wired with other devices to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that all the devices shown are not required, and more or less devices can alternatively be implemented. Figure 3 Each block shown in the flowchart diagrams can represent a device, or a number of devices, as necessary.

[0135] In particular, the processes described above with reference to the flowchart diagrams can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication devices 309, or installed from the storage devices 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.

[0136] Note that the computer-readable medium or media used to provide the computer program sequence to the computer system can be embedded in a computer program product, which comprises all the respective features, which are provided with the computer program sequence, and which are enumerated above. It is understood that the computer-readable medium or media described herein are included in the computer program product, or are a component of the computer program product. In some embodiments of the disclosure, the computer-readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer-readable storage medium can be any tangible medium that contains, or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the disclosure, a computer-readable signal medium can include a computer-readable storage medium in baseband or propagated as a carrier wave in a propagated data signal, which contains a computer-readable program code. Such a propagated signal can take a wide variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium that is not a computer-readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0137] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0138] The computer readable medium can be included in the electronic device, or can exist separately from the electronic device. The computer readable medium bears one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire target coke-making requirement information for a target coking device; determine, from a pre-configured first cluster center set, a first cluster center corresponding to the target coke-making requirement information as a target cluster center; determine coke-making theory information according to the target cluster center, wherein the coke-making theory information includes at least one theoretical index information of a blending coal after principal component analysis and a set of coking process required operation parameters, and the at least one theoretical index information of the blending coal is input into a blending coal information expansion network model to generate a set of theoretical index information of the blending coal; control the target coking device to realize coke-making according to the set of theoretical index information of the blending coal and the set of coking process required operation parameters; in response to the end of coke-making, acquire a set of actual operation parameters of the coking process determined by a monitoring instrument and a set of actual index information of the blending coal; input the set of parameter information corresponding to the set of actual operation parameters of the coking process and the set of actual index information of the blending coal into a coking energy consumption prediction model to output coking energy consumption prediction information; and adjust the first cluster center in the first cluster center set according to the coking energy consumption prediction information and the target coke-making requirement information.

[0139] Computer program code for carrying out operations of some embodiments of the disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0140] The flow and block diagrams in the drawings represent possible architectural, functional, and operational architectures of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block can represent a module, a segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or combinations of hardware and software.

[0141] The units described in some embodiments of the present disclosure can be implemented by means of software, or can be implemented by hardware. The described units can also be arranged in a processor, for example, a processor can be described as including a first acquisition unit, a first determination unit, a second determination unit, a first input unit, a control unit, a second acquisition unit, a second input unit, and an adjustment unit. Among them, the names of these units do not constitute a limitation to the units themselves in some cases, for example, the first acquisition unit can also be described as "a unit for acquiring target coke refining requirement information for a target coking device".

[0142] The functions described above in the specification can be performed at least in part by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), etc.

[0143] The above description is merely some of the preferred embodiments of the present disclosure and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or equivalent features without departing from the above inventive concept. For example, the above features can be replaced with technical features disclosed in the embodiments of the present disclosure (but not limited to) having similar functions to form technical solutions.

Claims

1. An information adjustment method, comprising: Obtain information on the target coke refining requirements for the target coking equipment; The first cluster center corresponding to the target coke refining requirement information is determined from the pre-configured first cluster center set and used as the target cluster center; Based on the target cluster center, the theoretical information for coke refining is determined, wherein the theoretical information for coke refining includes: at least one theoretical index information for blended coal and a set of required operating parameters for the coking process, wherein the at least one theoretical index information for blended coal is the index information after principal component analysis; The at least one theoretical index information of blended coal is input into the blended coal information augmentation network model to generate a set of theoretical index information of blended coal; Control the target coking equipment to achieve coke production based on the theoretical index information set of the blended coal and the set of operating parameters required by the coking process; In response to the end of coke refining, acquire the set of actual operating parameters of the coking process and the set of actual indicators of the blended coal determined by monitoring instruments; The parameter information set corresponding to the actual operation parameter set of the coking process and the actual index information set of the blended coal are input into the coking energy consumption prediction model to output coking energy consumption prediction information. Based on the predicted coking energy consumption information and the target coke refining requirements information, the first cluster centers in the first cluster center set are adjusted. The target coke refining requirements information includes: coke refining energy consumption requirements information; and The step of adjusting the first cluster centers in the first cluster center set based on the coking energy consumption prediction information and the target coke refining requirements information includes: In response to determining that the energy consumption value corresponding to the coking energy consumption prediction information is greater than the energy consumption value corresponding to the coke refining energy consumption requirement information, a vector for the coking energy consumption prediction information is generated. The vector is added to the vector cluster corresponding to the target cluster center to form the target vector cluster. Determine the vector distance between the vector and the target cluster center; A vector region is generated with a predetermined multiple of the vector distance as the radius and the target cluster center as the center. Determine the set of vectors within the range of the vector region from the target vector cluster; The vector set is clustered to obtain a second cluster center set; Determine the weighted summation vector corresponding to each second cluster center in the second cluster center set; From the vector set, determine the vector whose cosine distance is closest to the weighted summation vector, and use it as the nearest cluster center; Based on the nearest cluster center, the first cluster center set is updated to obtain a candidate cluster center set; Based on the candidate cluster center set, an adjusted cluster center set is generated.

2. The method according to claim 1, wherein, The step of generating an adjusted cluster center set based on the candidate cluster center set includes: Obtain the cluster partitioning label information set; Determine the label level corresponding to each cluster partition label information in the cluster partition label information set, wherein each label level has a corresponding cluster partition label information group; Each candidate cluster center in the candidate cluster center set is input into the cluster partitioning label generation model to generate at least one cluster partitioning label for the candidate cluster center; For every two candidate cluster centers in the candidate cluster center set, the following determination steps are performed: For each tag level, perform the following proportional generation steps: In response to determining that there is a difference in the content of the corresponding cluster partitioning label, at least one cluster partitioning label information is determined to be present between every two candidate cluster centers, indicating a difference in the content of the cluster partitioning label. Determine the label level difference ratio corresponding to the label information of the at least one cluster; Based on the obtained set of label-level difference ratios, merge information is generated to characterize whether each pair of candidate cluster centers is a cluster center to be merged; In response to determining that the merging information corresponding to every two candidate cluster centers indicates that the corresponding cluster centers are not merged, the set of candidate cluster centers is determined as the adjusted set of cluster centers.

3. The method according to claim 2, wherein, The step of determining the first cluster center corresponding to the target coke refining requirement information from a pre-configured first cluster center set, as the target cluster center, includes: Determine the theoretical information on coke refining requirements corresponding to each first cluster center in the first cluster center set to obtain the set of theoretical information on coke refining requirements; Each piece of theoretical information on coke refining requirements in the theoretical information set of coke refining requirements is input into the coke refining prediction information generation model to output coke refining prediction information. At least one first cluster center is selected from the first cluster center set where the information difference between the corresponding coke refining prediction information and the target coke refining requirement information satisfies a preset information difference condition. Generate a weighted summation vector between every two first cluster centers in the at least one first cluster center, to obtain a set of summation vectors; For each summation vector in the summation vector set, generate verification information representing the feasibility ratio of the coking scheme corresponding to the summation vector; Remove the summation vectors from the summation vector set that correspond to the verification information indicating that the feasibility ratio of the coking scheme is less than a predetermined ratio, and obtain the vector set after removal. The removed vector set and the at least one first cluster center are aggregated to generate an aggregated vector set; Determine the coke refining energy consumption requirement information and coke refining value resource consumption information corresponding to each aggregation vector in the aggregation vector set, and obtain the coke refining energy consumption requirement information set and the corresponding coke refining value resource consumption information set; Generate tables for the coke refining energy consumption requirement information set and the coke refining value resource consumption information set; The table is sent to the refining requirement client so that the cluster center can select the corresponding theoretical information on coke refining requirements.

4. The method according to claim 3, wherein, The method further includes: Acquire coke images for the coke refining cluster; The coke image is input into the coke segmentation model to generate coke sub-images, thus obtaining a coke sub-image set; Based on the coke part information corresponding to each coke sub-image, each coke sub-image in the coke sub-image set is subjected to selective image supplementation processing to generate supplementary images, thus obtaining a supplementary image set; Each supplementary image in the supplementary image set is input into the feature extraction model to generate image feature information, thus obtaining an image feature information set; The image feature information set is clustered to obtain a cluster center set; For each cluster center in the cluster center set, perform the following generation steps: The cluster center is input into the coke appearance information generation model to output coke particle size uniformity information, coke transverse and longitudinal crack information, coke cross-section information and coke edge information. Based on the coke particle size uniformity information, the coke particle size transverse and longitudinal crack information, the coke cross-sectional information, and the coke edge and corner information, the first coke quality verification information is generated. Based on the obtained first coke quality verification information set, quality verification information for the refined coke set is generated.

5. The method according to claim 4, wherein, The step of generating quality verification information for the refined coke set based on the obtained first coke quality verification information set includes: Acquire audio of coke landing for a subset of refined coke, wherein the subset of refined coke is a predetermined number of cokes randomly selected from the set of refined cokes; The audio of the coke falling to the ground is input into the coke falling sound category determination model to generate the falling sound category for each coke in the coke subset, thus obtaining the falling sound category set; Based on the aforementioned set of landing sound categories, generate second coke quality verification information; Quality verification information is generated based on the first coke quality verification information set and the second coke quality verification information.

6. The method according to claim 5, wherein, The method further includes: In response to determining that there are two candidate cluster centers corresponding to the merging information characterization of the corresponding cluster centers, at least two candidate cluster centers to be merged are determined; Determine whether there are duplicate candidate cluster centers among the at least two candidate cluster centers; In response to the determination that it does not exist, based on the obtained merging information set, the corresponding cluster pairs of the at least two candidate cluster centers to be merged are merged to obtain at least one merged cluster; For each of the at least one merged clusters, the weighted sum vector corresponding to the two cluster centers of the merged cluster is determined as the merged cluster center of the merged cluster. Based on the at least one merged cluster, the cluster set corresponding to the first cluster center set is updated to obtain the updated cluster set; The adjusted cluster center set is generated based on the updated cluster set and the obtained merged cluster center set.

7. An information adjustment device, comprising: The first acquisition unit is configured to acquire target coke refining requirements information for the target coking equipment. The first determining unit is configured to determine, from a pre-configured set of first cluster centers, a first cluster center corresponding to the target coke refining requirement information, as the target cluster center; The second determining unit is configured to determine coke refining theoretical information based on the target cluster center, wherein the coke refining theoretical information includes: at least one blended coal theoretical index information and a set of operating parameters required for the coking process, wherein the at least one blended coal theoretical index information is index information after principal component analysis; The first input unit is configured to input the at least one theoretical index information of blended coal into the blended coal information augmentation network model to generate a set of theoretical index information of blended coal. The control unit is configured to control the target coking equipment to achieve coke production based on the set of theoretical index information of the blended coal and the set of operating parameters required by the coking process. The second acquisition unit is configured to acquire, in response to the end of coke refining, a set of actual operating parameters of the coking process and a set of actual index information of the blended coal determined by monitoring instruments. The second input unit is configured to input the parameter information set corresponding to the actual operation parameter set of the coking process and the actual index information set of the blended coal into the coking energy consumption prediction model, so as to output coking energy consumption prediction information. The adjustment unit is configured to adjust the first cluster center in the first cluster center set according to the coking energy consumption prediction information and the target coke refining requirement information, wherein the target coke refining requirement information includes: coke refining energy consumption requirement information; and the adjustment of the first cluster center in the first cluster center set according to the coking energy consumption prediction information and the target coke refining requirement information includes: in response to determining that the energy consumption value corresponding to the coking energy consumption prediction information is greater than the energy consumption value corresponding to the coke refining energy consumption requirement information, generating a vector for the coking energy consumption prediction information; adding the vector to the vector cluster corresponding to the target cluster center as a target vector cluster; and determining... The vector distance between the vector and the target cluster center; a vector region is generated with a radius equal to a predetermined multiple of the vector distance and the target cluster center as the center; a set of vectors within the vector region is determined from the target vector cluster; the vector set is clustered to obtain a second cluster center set; a weighted summation vector corresponding to each second cluster center in the second cluster center set is determined; the vector with the closest cosine distance to the weighted summation vector is determined from the vector set as the nearest cluster center; the first cluster center set is updated based on the nearest cluster center to obtain a candidate cluster center set; an adjusted cluster center set is generated based on the candidate cluster center set.

8. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images