Grate cooler equipment parameter optimization method based on clustering algorithm

Abstract

The invention relates to the technical field of grate cooler parameter control, and discloses a grate cooler equipment parameter optimization method based on a clustering algorithm, which comprises the following steps: a modeling stage: acquiring two sections of sample data according to the characteristics of a grate cooler, respectively training two sections of model groups on the basis of the two sections of sample data, and acquiring a cluster by adopting the model groups; an optimization stage: obtaining a sample set according to the established clustering cluster, screening the sample set to obtain candidate samples, and performing value score evaluation on the candidate samples to obtain an optimization value; in the updating stage, periodic updating data is obtained, the original sample set is replaced, then the model is trained, and the original model is updated. According to the method, the change of the working condition of the grate cooler can be automatically monitored in real time, the value of the control parameter can be given, the workload of an operator on the grate cooler is reduced, meanwhile, the parameter adjustment reason and the data source of the grate cooler can be explained, the result is more persuasive, the credibility is improved, and the energy consumption is effectively reduced.

Description

Technical Field

[0001] The invention relates to the technical field of grate cooler control, and in particular to a grate cooler equipment parameter optimization method based on a clustering algorithm. Background Art

[0002] Grate cooler is a kind of equipment commonly used in cement production process, used to cool hot gas and solidify clinker. It realizes rapid cooling and heat recovery of clinker through special grate plate structure and efficient cooling system, and improves production efficiency and energy utilization efficiency. The main control parameters of grate cooler include the current of multiple cooling fans and the current of hydraulic motor that drives the grate plate. Generally, the current of hydraulic motor is not directly controlled by the operator group or algorithm, but by the dedicated PID or PLC unit according to the given grate speed. Therefore, the control parameters of grate cooler can be simplified to the current of cooling fan and grate speed. At present, most of the grate cooler control in cement production still needs to be adjusted by operators with corresponding experience. However, due to the large number of parameters for controlling the normal operation of grate cooler and the strong coupling between factors, the control is difficult, the operation workload is large, the labor intensity is high and the work efficiency is low. If only experienced operators are used for control, it will still cause problems such as parameter adjustment lag and poor stability. In addition, the operation of the grate cooler consumes a lot of electricity because the operation of the cooling fan and grate bed requires a lot of electricity, which causes the energy consumption of the grate cooler to be high. When there are problems with the control parameters, the energy consumption will increase further.

[0003] At present, a small amount of cement production will use an automated way to control the grate cooler, using rule engines, fuzzy reasoning, predictive control and other methods to optimize the control parameters of the grate cooler, such as the fan current and grate speed. This has improved work efficiency and reduced labor intensity to a certain extent. However, these typical optimization methods also have some defects. For example, the effectiveness of the rule engine depends greatly on the completeness of experience and the significance of the working condition characteristics. When the experience is incomplete or the working condition characteristics are not obvious, its effect may deteriorate rapidly. Fuzzy reasoning can better handle uncertainty and ambiguity in industrial control, but it is also highly dependent on pre-defined fuzzy rules, and traditional fuzzy reasoning systems usually do not have self-learning capabilities, making it difficult to automatically optimize rules based on new data. The predictive control method achieves the purpose of pre-adjusting the grate cooler by predicting the relevant key controlled variables in advance, and theoretically has a good control effect. However, the effect of this method is very dependent on the accuracy of the prediction model. Since variables that cannot be accurately measured, such as the temperature of the clinker out of the rotary kiln, have a great influence on the prediction of the controlled variables of the grate cooler, it is difficult to establish an accurate and reliable prediction model for the grate cooler. In addition, intelligent methods such as fuzzy reasoning and predictive control often lack explainability, and it is difficult to gain the trust of the operator group by optimizing the control parameters. In severe cases, the operator group may even disable the use of the automated algorithm, making it unable to play an auxiliary role. There are always problems such as high labor intensity, heavy workload, high energy consumption of the grate cooler, and poor operating stability. Summary of the invention

[0004] The present invention aims to provide a grate cooler equipment parameter optimization method based on clustering algorithm to solve the problem that the existing grate cooler control prediction results cannot be reasonably explained and analyzed to assist control, resulting in large workload, poor stability and high energy consumption of grate cooler control operations.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a method for optimizing the parameters of grate cooler equipment based on a clustering algorithm. This scheme sets up two groups of models in a targeted manner according to the structure of the grate cooler equipment, and conducts model training separately to ensure the accuracy and fit of the data. It can obtain data in real time and monitor the changes of the grate cooler, and give control parameter values ​​to reduce the workload, thereby improving the control efficiency and timeliness, ensuring the stable operation of the grate cooler, and further reducing energy consumption. At the same time, in the optimization stage, it can explain the reasons for the adjustment of the grate cooler parameters and the source of the data, so that the data output by the model is interpretable, which can be more in line with the experience judgment of the operating team and improve the credibility of the model. The optimization method of this scheme specifically includes the following steps:

[0006] Modeling phase:

[0007] S11, obtaining time series samples, dividing the time series samples into one-stage samples and two-stage samples according to the characteristics of the grate cooler, and extracting multi-dimensional features of the samples accordingly, which are used to train the working condition clustering model of the grate cooler to obtain a one-stage model group and a two-stage model group;

[0008] S12, obtaining clusters of historical samples according to each model group, and calculating the cluster centers as the cluster features, dividing the sample data into corresponding clusters, and making the model groups persistent;

[0009] Optimization stage:

[0010] S21, determine the current control state of the grate cooler, and enter the optimization process according to the control state;

[0011] S22, obtaining the real-time working condition data corresponding to each model group, calculating the cluster to which the real-time working condition data belongs, and obtaining a sample set according to the cluster characteristics; filtering the sample set according to the set filtering mode to obtain candidate samples;

[0012] S23, calculating the value scores of the candidate samples according to the evaluation method, selecting a number of sample data with the highest value scores, taking their average as the optimal value and sending it to the control system;

[0013] Update phase:

[0014] S31, acquiring update data according to a set period to form update samples, and replacing part of the sample set to form an update set;

[0015] S32, setting an initial cluster center, using the update set to train the initial cluster center until the model converges, and obtaining an updated model group;

[0016] S33, the updated model group is used in the optimization process.

[0017] The principles and advantages of this solution are:

[0018] In the actual control of the grate cooler, since there are many control parameters of the grate cooler and the parameters are coupled with each other, when constructing the prediction model of the grate cooler, the relationship between the parameters will be considered to build a comprehensive prediction model to ensure the accuracy of the data and the mutual influence, thereby ensuring the feasibility of the prediction model. At the same time, building a comprehensive model can also make more effective use of limited resources and reduce the investment of manpower and material resources. Therefore, when constructing the prediction model of the grate cooler, the construction of multiple models will not be considered. In addition, the coordination and management between multiple models will also be a more complicated issue. And the grate cooler itself is an equipment control system, so it will not be thought that multiple prediction models need to be constructed for control, which increases the workload, and thus the complex construction of multiple models is generally not considered.

[0019] But in fact, in the actual operation of the grate cooler, the grate cooler itself contains 11 fans and 2 sections of grate plates. Although the main function of the fans is to increase the cooling effect, discharge heat from the system, and maintain the operating temperature of the equipment, the grate plates are mainly used to adjust the flow of cooling medium. Therefore, a comprehensive method is adopted for unified control during control. However, there are many types of fans. When facing different cooling positions, their corresponding parameters need to be adjusted, resulting in many control parameters and strong correlation, which is difficult to split and control one by one. After careful analysis, this solution found that among these 11 fans and 2 sections of grate plates, some fans are subject to the same operating requirements and control parameters. Therefore, according to the process flow of cement burning and the function of the grate cooler, the points with causal relationship with the control of the grate speed and cooling fan current of the grate cooler are selected, and combined with the structural characteristics of the grate cooler, the two-stage control model of the grate cooler, the first stage control and the second stage control, are established respectively, and the measuring points are grouped to train the model, so that the model can better fit the actual operation state of the grate cooler, and realize precise regulation according to different operation requirements, thereby further reducing the energy consumption of the grate cooler. At the same time, these two groups of models can automatically monitor the changes in the working conditions of the grate cooler in real time and give the values ​​of the control parameters, reducing the workload of the operator on the grate cooler, making the reasons for the parameter adjustment of the grate cooler and the data source clear, so as to be more convincing, and improve the credibility of the control system, so as to achieve the effect of effective prediction and regulation, realize reliable auxiliary control, truly effectively reduce the workload and labor intensity of the operator group, and improve control efficiency.

[0020] At the same time, this scheme makes the average value of the secondary and tertiary air temperatures increase by 17.2℃ compared with the control of the operator group, and the standard deviation average decreases by 6.1℃, so the heat recovery is more sufficient and the stability is higher. From the perspective of energy consumption, the method proposed in this scheme can save 3.4% of the system power consumption of the grate cooler compared with the control of the operator group.

[0021] In summary, the implementation of this solution has the following advantages:

[0022] (1) It can reduce the intervention of the operator team and greatly reduce the workload and labor intensity of the operator team;

[0023] (2) Ensure the stable operation of the grate cooler and reduce the power consumption of the grate cooler;

[0024] (3) Make the algorithm output values ​​interpretable, provide auxiliary analysis basis, improve the credibility of the results, and ensure usability.

[0025] Furthermore, in the optimization stage, the filtering modes include three types, namely upper and lower limit constraint filtering, change constraint filtering and similarity filtering; the upper and lower limit constraint filtering is to select samples within the upper and lower limits according to the set upper and lower limits of the parameter items; the change constraint filtering is to delete samples whose parameter item changes exceed the threshold; the similarity filtering is to calculate the fusion similarity between the historical samples and the current samples, and retain the 5 samples with the highest similarity scores.

[0026] Furthermore, in the optimization stage, the evaluation method is to calculate the value score of the candidate sample according to the following formula:

[0027] Value score = (secondary air temperature + tertiary air temperature) / average fan current.

[0028] Furthermore, in the modeling stage, the time series samples are variables related to the control parameters of the grate cooler; among them, the first-stage samples are the data of the first five cooling fans corresponding to the first grate plate of the grate cooler; the second-stage samples are the data of the last six cooling fans corresponding to the second grate plate of the grate cooler, and the corresponding number of sample measurement points selected for the first stage is 22 and the number of sample measurement points for the second stage is 23.

[0029] Furthermore, in the modeling stage, it also includes grouping within the first stage sample and the second stage sample respectively; performing histogram analysis on the given values ​​of the raw material feed amount in the sample, grouping according to the analysis results, and then performing modeling processing within the group respectively to form multiple unit models, and the multiple unit models constitute a first stage model group or a two stage model group.

[0030] Furthermore, the modeling stage also includes preprocessing the time series sample data, and the preprocessing includes the following sub-steps:

[0031] S11.1, obtain the clustering characteristics of the time series sample data of each measuring point, including the mean μ, standard deviation σ, maximum value and minimum value of each measuring point;

[0032] S11.2, use the z-score method to normalize the values ​​of each measuring point, and the calculation expression is m ′ =(m-μ) / σ, where m is the original measurement point value, m ′ is the normalized measurement point value;

[0033] S11.3, use a sliding window with a window size of 10 and a step size of 5 to obtain the mean of the measurement point values.

[0034] Furthermore, in the modeling stage, the method of obtaining clusters includes the following sub-steps:

[0035] S12.1, according to the set clustering radius, minimum number of samples and search step, traverse each sample in the data set, calculate the number of samples in the neighborhood of each sample, and when the number of samples is not less than the minimum number of samples, divide them into core samples;

[0036] S12.2, taking any core sample as the center, searching for other core samples within the clustering radius, and marking the samples within this range as a cluster according to the fusion similarity index;

[0037] S12.3, switch the central core sample and repeat S12.2 until all core samples are visited and unlabeled samples are removed; and the set clustering effect index is used to evaluate the clustering effect.

[0038] Furthermore, the fusion similarity index includes sample similarity and measurement point similarity; the sample similarity is the sum of similarities of each measurement point constituting the sample; the measurement point similarity includes cosine similarity of measurement point statistics and sequence similarity of measurement point shapes.

[0039] Furthermore, the clustering effect index = intra-cluster divergence / inter-cluster divergence; the intra-cluster divergence is the average value of sample distances within a cluster; the inter-cluster divergence is the average value of sample distances between clusters.

[0040] Furthermore, the cosine similarity is expressed as In the formula, δ is the two measuring points and The cosine similarity of The measurement point sequence The statistical eigenvector of The measurement point sequence The statistical eigenvector of , ||·|| represents the modulus of the vector. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural schematic diagram of a method for optimizing parameters of grate cooler equipment based on a clustering algorithm according to the present invention.

[0042] Figure 2 The present invention discloses a distribution histogram of given values ​​of raw material feed quantity in a grate cooler equipment parameter optimization method based on a clustering algorithm. DETAILED DESCRIPTION

[0043] The following is further described in detail through specific implementation methods:

[0044] Embodiment 1

[0045] As attached Figure 1As shown, a method for optimizing the parameters of a grate cooler equipment based on a clustering algorithm in this embodiment is based on a dynamic clustering algorithm, so that the output results not only have a certain degree of interpretability, but also provide reliable parameter adjustment recommendations, reduce the workload of the operator group on the grate cooler, and can also ensure real-time and stable adjustment of the grate cooler fan current and grate speed to achieve the effect of saving energy consumption. In this embodiment, the optimization method mainly includes three steps: modeling stage, optimization stage and update stage, which are described in detail below.

[0046] 1. Modeling phase.

[0047] Data acquisition: First, obtain the relevant point data of the grate cooler from the DCS. In this embodiment, the start and end time of the historical data can be set to, for example, 2023.06.01 to 2024.06.01. With an annual cycle, the DCS samples the value of the measurement point once every 2 seconds. Excluding the downtime period, a total of 11,059,200 samples are collected, and the data volume is huge. Therefore, in the historical data obtained, it is necessary to select the measurement point.

[0048] Measuring point selection: According to the cement burning process and the function of the grate cooler, select the points that are causally related to the control of the grate speed of the grate cooler and the current of the cooling fan, including the feedback value of the O2 concentration at the outlet of the preheater C1, the feedback value of the negative pressure at the outlet of the preheater C1, the feedback value of the temperature at the outlet of the decomposition furnace, the feedback value of the negative pressure at the outlet of the decomposition furnace, the feedback value of the temperature of the smoke chamber at the tail of the kiln, the feedback value of the negative pressure of the smoke chamber at the tail of the kiln, the flame temperature feedback value of the fire-watching TV at the head of the kiln, the clinker temperature feedback value of the fire-watching TV at the head of the kiln, the rotary Controlled variables include kiln power feedback value, rotary kiln speed feedback value, kiln head hood negative pressure feedback value, secondary air temperature feedback value, tertiary air temperature feedback value, waste heat power generation temperature feedback value, grate cooler first-stage grate pressure feedback value, grate cooler second-stage grate pressure feedback value, as well as raw meal feed quantity given value, grate cooler first-stage grate speed given value, grate cooler second-stage grate speed given value, grate cooler 11 cooling fan current given value, etc., a total of 30 measuring points, after completing the measuring point selection, the measuring points are grouped and processed.

[0049] Measuring point grouping: In this embodiment, the grate cooler involved is a two-stage grate cooler, that is, there are two independently moving clinker cooling sections, in which the first grate plate of the grate cooler is cooled by the first five cooling fans, and the second grate plate is cooled by the last six cooling fans. Therefore, according to the structure of the grate cooler, two control models of the first stage control and the second stage control of the grate cooler are established respectively. And because there are multiple models in both stages of control, they are recorded as a first stage model group and a second stage model group. In this embodiment, the model principles, modeling and use steps in the first stage model group and the second stage model group are exactly the same.

[0050] The 30 measuring points obtained were grouped according to the two-stage control model, and one of the model groups included 22 measuring points, including the O2 concentration feedback value at the outlet of preheater C1, the negative pressure feedback value at the outlet of preheater C1, the temperature feedback value at the outlet of decomposition furnace, the negative pressure feedback value at the outlet of decomposition furnace, the temperature feedback value of the smoke chamber at the tail of kiln, the negative pressure feedback value of the smoke chamber at the tail of kiln, the flame temperature feedback value of the kiln head fire-watching TV, the clinker temperature feedback value of the kiln head fire-watching TV, the power feedback value of the rotary kiln, the speed feedback value of the rotary kiln, the negative pressure feedback value of the kiln head hood, the secondary air temperature feedback value, the tertiary air temperature feedback value, the waste heat power generation temperature feedback value, the pressure feedback value under the first grate of the grate cooler, the given value of the raw meal feed amount, the given value of the first grate speed of the grate cooler, the given value of the current of cooling fans No. 1 to 5 of the grate cooler, etc. The second-stage model group includes 23 measurement points, including the O2 concentration feedback value at the outlet of preheater C1, the negative pressure feedback value at the outlet of preheater C1, the temperature feedback value at the outlet of decomposition furnace, the negative pressure feedback value at the outlet of decomposition furnace, the temperature feedback value of the smoke chamber at the end of kiln, the negative pressure feedback value of the smoke chamber at the end of kiln, the flame temperature feedback value of the kiln head fire-watching TV, the clinker temperature feedback value of the kiln head fire-watching TV, the power feedback value of the rotary kiln, the speed feedback value of the rotary kiln, the negative pressure feedback value of the kiln head hood, the secondary air temperature feedback value, the tertiary air temperature feedback value, the waste heat power generation temperature feedback value, the pressure feedback value under the second-stage grate of the grate cooler, the raw material feed amount given value, the second-stage grate speed given value of the grate cooler, and the current given value of the cooling fan No. 6 to 11 of the grate cooler. Among them, the controlled variables involved in the first and second-stage model groups are used to describe the working conditions and are used as the data source for extracting features for the subsequent construction of clustering models. After completing the grouping of the measurement points, the corresponding time series samples are obtained respectively, divided into the first-stage sample and the second-stage sample, and the sample is constructed.

[0051] Sample construction: Since the process from feeding raw materials into the preheater to cooling the clinker in the grate cooler is a process with a large time lag, in this embodiment, the constructed working condition sample is in the form of a time series with a long time span. It is set to 30 minutes based on process experience, and sampling is performed every 2 seconds, that is, each sample consists of 900 sampling points. Among them, each sampling point of the first-stage model group is a vector composed of the values ​​of the above 22 measuring points, that is, one sample is a 900×22 matrix; each sampling point of the second-stage model group is a vector composed of the values ​​of the above 23 measuring points, that is, one sample is a 900×23 matrix. A non-overlapping sliding window is used to construct the sample, that is, the number of time steps in the sampling window is 900, and the total number of samples corresponding to each model in the historical data is 11,512.

[0052] After sampling is completed, the samples are grouped. In this embodiment, in the cement burning system, the raw material feed rate is the most fundamental factor affecting the working conditions. Other control variables are mainly set to adapt the raw material feed rate, and the same is true for the grate cooler control parameters. Therefore, in this embodiment, the raw material feed rate given values ​​in the historical data samples are histogram analyzed to draw a distribution histogram of the sample raw material feed rate given values. Figure 2As shown, the raw material feed amount given value shows an obvious approximate mixed Gaussian distribution form, and there are multiple typical clustering intervals. Therefore, in this embodiment, according to the central value of the clustering interval of the feed amount, the anchor points of the raw material feed amount given value are set, such as 500, 510, 520, 525, 530, 540, 550, 560, 570, 580, 590, 600, 605, 610, 615, 620, 625, 630, 635, 640, 645, 650. The samples are divided into sample groups represented by the nearest anchor points according to the raw material feed amount given value, and modeling is performed separately, so as to facilitate the rapid grouping of the acquired sample data and ensure accuracy and stability. In this embodiment, when reasoning, the anchor point closest to the real-time raw material feed amount is first found, and then the clustering model of the anchor point is used for reasoning. Therefore, there are multiple models in the first-stage model group and the second-stage model group according to the grouping of the raw material feed amount given value.

[0053] In this embodiment, the acquired measuring point data is also preprocessed, and the preprocessing steps include:

[0054] 1) Count the clustering features of the time series sample data of each measuring point, including the mean μ, standard deviation σ, maximum value and minimum value of the measuring point, and generate some feature parameters as part of the subsequent clustering features.

[0055] 2) Use the z-score method to normalize the values ​​of each measuring point, and the calculation expression is m ′ =(m-μ) / σ, where m is the original measurement point value, m ′ is the normalized measurement point value.

[0056] 3) A sliding window with a window size of 10 and a step size of 5 is used to obtain the mean of the measured point values, which reduces the volatility of the measured point data and highlights the overall shape and trend of the measured point data changes.

[0057] After the processing of the measuring point data is completed, the multi-dimensional features of the samples are extracted, and the fusion similarity is used as the sample similarity measurement indicator to perform sample clustering for training the working condition clustering model of the grate cooler to obtain the first-stage model group and the second-stage model group.

[0058] In this embodiment, the fusion similarity index includes sample similarity and measurement point similarity. Sample similarity is the sum of similarities of each measurement point constituting the sample. Measurement point similarity includes cosine similarity of measurement point statistics and sequence similarity of measurement point shapes.

[0059] Among them, the cosine similarity of the measurement points is calculated using the feature vector composed of the statistical mean, standard deviation, maximum value and minimum value of the measurement points. For example, for a certain measurement point sequence and Assume that their statistical eigenvectors are and Then the cosine similarity is expressed as Here, ||·|| represents the modulus of the vector.

[0060] The sequence similarity is calculated using the Dynamic Time Wrapping (DTW) algorithm, which finds an optimal matching path between two measurement point sequences through dynamic programming, so that the sum of the distances between the corresponding points of the two measurement point sequences on the time axis is minimized. The sum of the minimum distances is the sequence similarity. After calculating the cosine similarity and sequence similarity of the measurement point, the two similarities are added together as the fusion similarity of the measurement point.

[0061] The calculated fusion similarity is used to cluster the samples, and the clustering clusters of the historical samples are obtained according to each model group. In this embodiment, the samples in each raw material feed amount given value group in the first stage model group and the second stage model group are clustered respectively. In this embodiment, the density-based spatial clustering algorithm (Density-Based Spatial Clustering of Application with Noise, DBSCAN) is used to cluster based on the distribution density of the samples. There is no need to pre-specify the number of clusters to be clustered, and the clusters existing in the sample distribution can be automatically mined. The cluster center is calculated as the cluster feature, and the sample data is divided into the corresponding cluster to make the model group persistent. In this embodiment, the method of obtaining the cluster includes the following steps:

[0062] 1) Specify two hyperparameters, the clustering radius ε and the minimum number of samples minPts. In this embodiment, the optimal values ​​of these two hyperparameters need to be determined by grid search, and the basis for determining the optimal values ​​is the final clustering effect.

[0063] The clustering effect is evaluated by using the set clustering effect index, where the clustering effect index = intra-cluster divergence / inter-cluster divergence; the intra-cluster divergence is the average value of the sample distance within the cluster; the inter-cluster divergence is the average value of the sample distance between the clusters. In this embodiment, the search ranges of the clustering radius ε and the minimum number of samples minPts are set to 2.0-10.0 and 20-100, respectively, and the search step sizes are set to 0.5 and 5, respectively.

[0064] According to the set clustering radius, minimum number of samples and search step, each sample in the data set is traversed to calculate the number of samples in the neighborhood of each sample. In this embodiment, the neighborhood is an area whose distance from the sample is not greater than the clustering radius. When the number of samples in the neighborhood of each sample is not less than the minimum number of samples minPts, the sample is classified as a core sample.

[0065] 2) Taking any core sample as the center, that is, starting from any unvisited core sample, search for other core samples within its clustering radius, and repeat this step for each core sample in the field until no new core samples appear in the neighborhood. According to the fusion similarity index, the core samples within this range and the samples in the neighborhood are marked as a cluster.

[0066] 3) Switch the central core sample and repeat step 2) until all core samples are visited, and remove the unmarked samples, that is, remove the samples that do not belong to any cluster; and use the set clustering effect index to evaluate the clustering effect to optimize the clustering effect. In this embodiment, after grid search, the optimal clustering radius ε and the minimum number of samples minPts hyperparameters are set to 4.0 and 35 respectively. Under this hyperparameter combination condition, the value of intra-cluster divergence / inter-cluster divergence is the smallest.

[0067] At the same time, in this embodiment, the model is also persisted. That is, after the samples grouped according to the given value of the raw material feed amount are clustered as described above, the first-stage model group generates a total of several cluster models, and the second-stage model group generates a total of several cluster models, the samples are divided according to the cluster model and the cluster center of each cluster is calculated, and the cluster model, cluster cluster label, sample set corresponding to the cluster cluster, and cluster cluster center are saved to the disk.

[0068] 2. Optimization stage.

[0069] Determine whether to enter the optimization process: obtain the data of the relevant points at the current moment from the DCS system to form a sample to describe the current working conditions. The sample is composed of multi-dimensional measurement point data of 900 current and historical time steps. The mean, standard deviation, maximum value, and minimum value of each measurement point of the sample are extracted, and normalization and smoothing operations are performed. Check whether there are abnormal working conditions based on real-time data. In this embodiment, check whether the current grate cooler valve group pressure, grate plate temperature, and firing quality indicators are abnormal. If abnormal, the control of the grate cooler is taken over by the work group or the expert control model. At the same time, check whether the current grate cooler system work group operation signal is valid. If there is a work group operation, it remains controlled by the work group, otherwise enter the automatic optimization process of the grate cooler control parameters.

[0070] Load the saved clustering model, clustering cluster mark, sample set corresponding to the clustering cluster, clustering cluster center and other data from the disk; obtain the raw material feed quantity given value data of the real-time working condition sample corresponding to each model group, and locate the current sample to the corresponding clustering model in the first model group and the second model group respectively. In the corresponding clustering model, input the sample features required by the first model group and the second model group, calculate the fusion similarity between the sample features and the centers of all clustering clusters, and the cluster with the highest fusion similarity is the cluster to which the current working condition sample belongs, and obtain the mark of the corresponding cluster.

[0071] According to the label of the cluster to which the current working condition sample belongs, all historical sample sets belonging to the cluster are obtained, and the sample sets are filtered according to the set filtering mode to obtain candidate samples.

[0072] In this embodiment, there are three filtering modes, namely upper and lower limit constraint filtering, change constraint filtering and similarity filtering. Among them, upper and lower limit constraint filtering is to select samples within the upper and lower limits according to the set upper and lower limits of the parameter items. That is, the given values ​​of the first stage grate speed, the second stage grate speed, and the current of 11 fans of the sample shall not exceed the upper and lower limits of the values ​​given by the current working group, and only samples within the upper and lower limits are retained. If the number of remaining samples after filtering is 0, all samples are retained, and the given values ​​of the grate speed and current of these samples are modified to the upper limit value or the lower limit value. If it exceeds the upper limit value, it is changed to the upper limit value, and if it is lower than the lower limit value, it is changed to the lower limit value.

[0073] The change constraint filtering is to delete samples whose parameter item change exceeds the threshold. In this embodiment, a large change in the control variable in a short period of time will cause a sharp change in the working condition and break the steady state of the working condition. Therefore, the actual operation requires that the absolute value of the change of the first-stage grate speed given value, the second-stage grate speed given value, and the 11 fans' current given value shall not exceed the upper limit, the change of a single grate speed given value shall not exceed 0.4, and the change of a single fan current given value shall not exceed 5.0. According to this change constraint, delete the samples whose change exceeds the upper limit in the sample set. If the number of remaining samples after filtering is 0, all samples are retained, and the grate speed given value and current given value of these samples are modified to the upper limit of the current given value change.

[0074] Similarity filtering is to calculate the fusion similarity of historical samples and current working condition samples, sort the historical samples from large to small according to the similarity, and retain the 5 samples with the highest similarity scores. If the number of remaining samples is less than 5, all samples are retained.

[0075] The value scores of the obtained candidate samples are calculated according to the evaluation method, and several sample data with the highest value scores are selected, and their average is taken as the optimal value and sent to the control system.

[0076] In this embodiment, the evaluation method is to calculate the value score of the candidate sample according to the following formula: value score = (secondary air temperature + tertiary air temperature) / fan current mean. In this embodiment, the value score is evaluated for each candidate sample after multiple filtering, that is, the higher the secondary air temperature, the higher the tertiary air temperature, and the lower the fan current mean, the higher the value score of the sample. The candidate samples are sorted from large to small according to the value score, and the first stage grate speed given value, the second stage grate speed given value, and the 11 fan current given values ​​corresponding to the candidate sample with the highest value score are selected as the given values ​​of the grate cooler control parameters in the next time step and sent to the control system.

[0077] 3. Update phase.

[0078] In this embodiment, as the grate cooler continues to operate, new sample data is continuously generated. These new data represent the latest operating status of the current grate cooler and are more valuable than historical data. Therefore, update data is obtained according to the set period to form update samples, and an update set is formed after replacing part of the sample set. The latest accumulated update set is used regularly to update the core clustering model of this solution online.

[0079] In this embodiment, the update cycle is set to trigger the update process at 0:00 on the 1st of each month, and the operating condition data accumulated since the last update is constructed as update samples. Based on the timestamp order and the "first in, first out" principle, the same number of old samples as the update sample set are discarded, and the update samples and the remaining old samples are merged into a new update set.

[0080] The existing cluster center is used as the initial cluster center, and the model is retrained on the new update set until the model converges to obtain an updated model group, which is used in the optimization process. In this embodiment, the update stage can track the long-term changes in the overall operating state of the grate cooler, making the adjustment of the control parameters of the grate cooler more adaptive.

[0081] In this embodiment, the updating phase is decoupled from the optimization phase, and two processes are used to respectively realize optimization and updating, so that the new model can be applied to the optimization process in a timely manner after the clustering model is updated.

[0082] In this embodiment, according to the actual application scenario, the recommended parameters obtained through model calculation are used to control the grate cooler in the production environment.

[0083] In this embodiment, the grate cooler is divided into two parts according to its equipment structure, and two groups of models are set up in a targeted manner. From the perspective of real-time performance, this solution is deployed on the server, which can automatically monitor the changes in the working conditions of the grate cooler in real time and give the optimal value. However, the operator group not only has to take care of the grate cooler but also the other equipment. Therefore, it is difficult to give the optimal current and grate pressure settings based on real-time data, thereby reducing the workload of the operator group on the grate cooler. From the perspective of heat recovery effect, the method proposed in this solution increases the average of the second and third wind temperatures by 17.2°C relative to manual operation, and reduces the standard deviation by 6.1°C, making heat recovery more sufficient and more stable. From the perspective of energy consumption, the method proposed in this solution can save 3.4% of the system power consumption of the grate cooler compared to when the operator group is operating. This also shows that the tuning result of this solution is more stable than when the operator group is operating.

[0084] The above is only an embodiment of the present invention, and the common knowledge such as the known specific technical solutions and / or characteristics in the solution is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical solution of the present invention, several modifications and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A method for optimizing grate cooler equipment parameters based on clustering algorithm, characterized in that: The following steps are included: Modeling phase: S11, obtaining time series samples, dividing the time series samples into one-stage samples and two-stage samples according to the characteristics of the grate cooler, and extracting multi-dimensional features of the samples accordingly, which are used to train the working condition clustering model of the grate cooler to obtain a one-stage model group and a two-stage model group; S12, obtaining clusters of historical samples according to each model group, and calculating the cluster centers as the cluster features, dividing the sample data into corresponding clusters, and making the model groups persistent; Optimization stage: S21, determine the current control state of the grate cooler, and enter the optimization process according to the control state; S22, obtaining the real-time working condition data corresponding to each model group, calculating the cluster to which the real-time working condition data belongs, and obtaining a sample set according to the cluster characteristics; filtering the sample set according to the set filtering mode to obtain candidate samples; S23, calculating the value scores of the candidate samples according to the evaluation method, selecting a number of sample data with the highest value scores, taking their average as the optimal value and sending it to the control system; Update phase: S31, acquiring update data according to a set period to form update samples, and replacing part of the sample set to form an update set; S32, setting an initial cluster center, using the update set to train the initial cluster center until the model converges, and obtaining an updated model group; S33, the updated model group is used in the optimization process.

2. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 1, characterized in that: In the optimization stage, the filtering modes include three types, namely upper and lower limit constraint filtering, change constraint filtering and similarity filtering; The upper and lower limit constraint filtering is to select samples within the upper and lower limits according to the set upper and lower limits of the parameter items; the change constraint filtering is to delete samples whose parameter item changes exceed the threshold; the similarity filtering is to calculate the fusion similarity between the historical samples and the current samples, and retain the 5 samples with the highest similarity scores.

3. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 1, characterized in that: In the optimization stage, the evaluation method is to calculate the value score of the candidate sample according to the following formula: Value score = (secondary air temperature + tertiary air temperature) / average fan current.

4. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 1, characterized in that: In the modeling stage, the time series samples are variables related to the control parameters of the grate cooler; among them, the first-stage samples are the data of the first five cooling fans corresponding to the first grate plate of the grate cooler; the second-stage samples are the data of the last six cooling fans corresponding to the second grate plate of the grate cooler, and the corresponding first-stage sample measurement points are 22 and the second-stage sample measurement points are 23.

5. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 1, characterized in that: In the modeling stage, it also includes grouping within the first stage sample and the second stage sample respectively; performing histogram analysis on the given values ​​of the raw material feed amount in the sample, grouping according to the analysis results, and then performing modeling processing within the group to form multiple unit models. The multiple unit models constitute a first stage model group or a two stage model group.

6. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 4, characterized in that: The modeling phase also includes preprocessing of time series sample data, which includes the following sub-steps: S11.1, obtain the clustering characteristics of the time series sample data of each measuring point, including the mean μ, standard deviation σ, maximum value and minimum value of each measuring point; S11.2, use the z-score method to normalize the values ​​of each measuring point, and the calculation expression is m ′ =(m-μ) / σ, where m is the original measurement point value, m ′ is the normalized measurement point value; S11.3, use a sliding window with a window size of 10 and a step size of 5 to obtain the mean of the measurement point values.

7. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 4, characterized in that: In the modeling phase, the method of obtaining clusters includes the following sub-steps: S12.1, according to the set clustering radius, minimum number of samples and search step, traverse each sample in the data set, calculate the number of samples in the neighborhood of each sample, and when the number of samples is not less than the minimum number of samples, divide them into core samples; S12.2, taking any core sample as the center, searching for other core samples within the clustering radius, and marking the samples within this range as a cluster according to the fusion similarity index; S12.3, switch the central core sample, repeat S12.2 until all core samples are visited, and the unlabeled samples are removed; and the set clustering effect index is used to evaluate the clustering effect.

8. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 7, characterized in that: The fusion similarity index includes sample similarity and measurement point similarity; the sample similarity is the sum of similarities of each measurement point constituting the sample; the measurement point similarity includes cosine similarity of measurement point statistics and sequence similarity of measurement point shapes.

9. The method for optimizing parameters of grate cooler equipment based on clustering algorithm according to claim 7, characterized in that: The clustering effect index = intra-cluster divergence / inter-cluster divergence; the intra-cluster divergence is the average value of sample distances within a cluster; the inter-cluster divergence is the average value of sample distances between clusters.

10. The method for optimizing grate cooler equipment parameters based on clustering algorithm according to claim 8, characterized in that: The cosine similarity is expressed as In the formula, δ is the two measuring points and The cosine similarity of The measurement point sequence The statistical eigenvector of The measurement point sequence The statistical eigenvector of , ||·|| represents the modulus of the vector.

Images