Method for monitoring running state of fiber cloth cover plasterboard production equipment

Abstract

The invention relates to the field of gypsum board production line quality control, in particular to a fiber cloth cover gypsum board production equipment operation state monitoring method, which comprises the following steps: obtaining a production parameter set at each moment in a current time period, the production parameter set comprising operation parameters of a plurality of equipment; the internal quality score of the gypsum board in the current time period is calculated, the internal quality score is in positive correlation with the optimal influence weight of the equipment and is in negative correlation with the fluctuation degree of the operation parameters, and when the internal quality score is smaller than a score threshold value, an equipment abnormity signal is sent out. By calculating the internal quality score of the fiber cloth cover plasterboard, the equipment condition of the production line is judged, the production quality of the production line is monitored, and the product quality of the fiber cloth cover plasterboard is improved.

Description

Technical Field

[0001] The present invention relates to the field of quality control of gypsum board production lines, and in particular to a method for monitoring the operating status of fiber cloth gypsum board production equipment. Background Art

[0002] The fiber cloth gypsum board production line consists of a variety of equipment, mainly including batching equipment, molding equipment, drying equipment and conveying equipment. When producing fiber cloth gypsum board, the batching equipment mixes various raw materials for manufacturing gypsum board according to proportion, and then puts the mixed raw materials into the molding equipment. The molding equipment extrude the mixed raw materials to form them, the drying equipment dries the extruded gypsum board, and the conveying equipment is used to convey the gypsum board materials at various manufacturing stages.

[0003] In the production process of fiber cloth gypsum board, the operation of various equipment on the production line is completed in coordination with each other. For example, the speed of material feeding by the batching equipment needs to be set in combination with the extrusion speed of the molding equipment, the drying speed of the drying equipment, and the conveying speed of the conveying equipment. The drying speed is controlled by the drying temperature. Therefore, the production quality of gypsum board is affected by multiple production equipment.

[0004] However, when equipment fails, the faulty equipment cannot be discovered in time, causing the production line to continue to run and produce gypsum boards, causing the quality of the produced gypsum boards to fluctuate greatly and easily resulting in unqualified products. Summary of the invention

[0005] In order to solve the problem that equipment failure cannot be discovered in time, resulting in large fluctuations in the quality of fiber-faced gypsum boards produced on a production line, the present invention provides a method for monitoring the operating status of fiber-faced gypsum board production equipment.

[0006] The present invention provides a method for monitoring the operating status of fiber cloth gypsum board production equipment, which adopts the following technical scheme: Obtain the production parameter set at each moment in the current time period, the production parameter set includes the operating parameters of multiple devices; Calculate the internal quality score of the gypsum board in the current time period. The internal quality score is positively correlated with the optimal impact weight of the equipment and negatively correlated with the fluctuation degree of the operating parameters. In response to the internal quality score being less than the score threshold, send a signal of equipment abnormality; Among them, the calculation method of the optimal impact weight of the running equipment is: Construct the distance function in the K-means algorithm. The expression of the distance function is:

[0007] In the formula, Represents a set of production parameters With center set The distance between Represents a set of production parameters The operating parameters of the nth device in, Represents the center set The operating parameters of the nth device in, Indicates the influence weight of the nth device; The K-means algorithm is used to cluster the production parameter sets at each moment in the current time period to obtain multiple clusters. The sum of the accuracies of the multiple clusters is used as the evaluation index, and the influence weight is updated until the evaluation index is greater than the preset evaluation threshold. The updated influence weight is screened to obtain the optimal influence weight.

[0008] The effect is that the influence weight of each equipment in the fiber-faced gypsum board production line is obtained by calculation, the influence weight is updated to obtain the optimal influence weight, and then, the internal quality score of the fiber-faced gypsum board is calculated to judge the equipment condition of the production line, realize the monitoring of the production quality of the production line, and improve the product quality of the fiber-faced gypsum board.

[0009] Preferably, the method for screening the updated influence weights to obtain the optimal influence weights is: The updated influence weights are sorted according to their numerical values, and the sorted influence weights are accumulated from front to back until the accumulated sum is greater than the preset weight threshold. The influence weight involved in the accumulation calculation is taken as the optimal influence weight.

[0010] Preferably, the method for screening the updated influence weights to obtain the optimal influence weights is: The updated impact weights are sorted according to their numerical values, and the sorted impact weights are accumulated from front to back until the accumulated sum is greater than the preset weight threshold. The impact weight items that are not involved in the cumulative calculation are deleted, and the K-means algorithm is used to cluster the production parameter sets at each moment in the current time period and calculate the evaluation index. The impact weight is updated until the evaluation index is greater than the preset evaluation threshold, and the updated impact parameter is used as the optimal impact weight.

[0011] The effect is that by calculating the optimal influence weight, the equipment that has a greater impact on the production quality of fiber-faced gypsum board is screened out, thereby achieving targeted monitoring of the equipment, reducing the monitoring workload and improving the monitoring efficiency.

[0012] Preferably, the expression of the internal quality score is: ; Where: represents the internal quality score of the gypsum board for the current time period, Indicates The optimal impact weight of a device, Indicates the current time period Benchmark data for each device, Indicates Standard data for each device, Indicates the current time period The variance of the operating parameters of each device, Indicates the total number of devices.

[0013] Preferably, the expression of the internal quality score is: ; Where: represents the internal quality score of the gypsum board for the current time period, Indicates The optimal impact weight of a device, Indicates the current time period Benchmark data for each device, Indicates Standard data for each device, Indicates the current time period The variance of the operating parameters of each device, Indicates the total number of devices.

[0014] The effect is that by calculating the internal quality score, the overall operating status of the production line can be understood in real time based on the quality score, making it easier to monitor the production line.

[0015] Preferably, the expression of the running benchmark data is:

[0016] Where: Indicates the current time period The average of the operating parameters of the equipment, Indicates the current time period The median of the operating parameters of the equipment, Indicates the current time period The mode of the operating parameters of a device.

[0017] The effect is that the operating benchmark data indicates the center of the current operating parameters of the corresponding equipment, and the operating status of the corresponding equipment in the current time period can be understood.

[0018] Preferably, the expression of the accuracy of the clustering is: ; In the formula, represents the accuracy of clustering. Represents the number of correct production parameter sets in the cluster, Represents the total number of production parameter sets for clustering clusters.

[0019] The effect is that by calculating the accuracy of clustering clusters, the clustering effect can be understood, and the influence weight can be further obtained through the clustering effect, thereby improving the accuracy of the influence weight.

[0020] Preferably, the influence weights are updated using a simulated annealing algorithm.

[0021] The present invention has the following technical effects: 1. The influence weights of each device in the fiber-faced gypsum board production line are calculated, and the influence weights are updated to obtain the optimal influence weights. Then, the internal quality scores of the fiber-faced gypsum board are calculated to judge the equipment status of the production line, monitor the production quality of the production line, and improve the product quality of the fiber-faced gypsum board.

[0022] 2. Cluster the production parameter set through the clustering algorithm, and then update the influence weight of each device. Update the influence weight through the accuracy of the clustering cluster, thereby improving the accuracy of the influence weight and further improving the monitoring effect of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0024] Figure 1 The present invention is a flowchart of a method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0027] The embodiment of the present invention discloses a method for monitoring the operating status of a fiber cloth gypsum board production equipment, referring to Figure 1 , including the following steps: S1: Obtain a production parameter set at each moment in the current time period, where the production parameter set includes operating parameters of multiple devices.

[0028] The fiber cloth gypsum board production line has multiple devices, and the operating parameters of multiple devices at the same time are obtained. For example, The production parameter set at the moment, The production parameter set at the moment includes the batching speed of the batching equipment, the extrusion pressure of the molding equipment, the drying temperature of the fiber cloth gypsum of the drying equipment, the conveying speed of the conveying equipment, and the operating parameters are normalized.

[0029] S2: Calculate the external score of the fiber cloth gypsum board at each moment in the current time period, and use the external score to classify the production parameter set in the current time period.

[0030] Get the actual length, width, thickness, density and weight of the fiber cloth faced gypsum board at the current moment, and set the length range, width range, thickness range, density range and weight range of the gypsum board. If the actual length is within the length range, the length score is recorded as 1, otherwise the length score is recorded as 0. Similarly, the width score, thickness score, density score and weight score are obtained, and the cumulative sum of the width score, thickness score, density score and weight score is used as the external score. It can be understood that the external score ranges from 0 to 5 points. The external score of the fiber cloth faced gypsum board at each moment in the current time period is calculated, and the production parameter set is classified according to the external score to obtain multiple categories, that is, the production parameter set with the same external score is divided into one category, and a score of 1 is recorded as category 1. Similarly, a score of 2 is recorded as category 2.

[0031] S3: Construct the distance function in the K-means algorithm.

[0032] The expression of the distance function is:

[0033] In the formula, represents the clustering distance of the K-means algorithm, Represents a set of production parameters The operating parameters of the nth device in, Represents the center set The operating parameters of the nth device in, Indicates the influence weight of the nth device. The larger the value is, the greater the impact of the equipment on the quality of the fiber-faced gypsum board during the production process of the fiber-faced gypsum board.

[0034] The average values ​​of the equipment operating parameters corresponding to the production parameter set in each category in step S2 are calculated to obtain a set of average values, and the set of average values ​​is used as the central set of the corresponding category. For example, for one of the categories, the category has production parameter sets a, b, and c, and parameter set a has ( , …、 ), similarly, parameter set b has ( , …、 ), parameter set c has ( , …、 ),Will , and The average value of , similarly, , and The average value of ,…,Will , and The average value of , the obtained ( , , …, ) as the center set .

[0035] S4: Use the K-means algorithm to cluster the production parameter sets at each moment in the current time period to obtain multiple clusters, use the sum of the accuracy of the multiple clusters as the evaluation index, and update the impact weight until the evaluation index is greater than the preset evaluation threshold.

[0036] Taking the center set N as the clustering center, the K-means algorithm is used to cluster the production parameter set. The number of clusters is the same as the number of categories obtained by classifying the production parameter set according to the external scores. For example, the production parameter set is classified according to the external scores to obtain 3 categories. Then when the K-means algorithm is used to cluster the production parameter set, the number of clusters is set to 3.

[0037] Calculate the accuracy of each cluster. The expression of the accuracy of the cluster is: ; In the formula, represents the accuracy of clustering. Represents the number of correct production parameter sets in the cluster, Represents the total number of production parameter sets of the cluster. Each cluster contains multiple production parameter sets. The number of production parameter sets of each category in the cluster is counted. For example, in cluster y, the number of production parameter sets is 10, of which the number of production parameter sets belonging to category 1 is 7, the number of production parameter sets belonging to category 2 is 2, and the number of production parameter sets belonging to category 3 is 1. Then the accuracy of cluster y is 7 / 10=0.7. Since the number of production parameter sets of category 1 is the largest in the cluster, cluster y is recorded as a category 1 cluster. Similarly, in other clusters, if the number of category 3 production parameter sets is the largest, the cluster is recorded as a category 3 cluster.

[0038] The sum of the accuracy of multiple clustering clusters is used as an evaluation index. The evaluation index is used to evaluate the clustering effect. The larger the value of the evaluation index, the better the clustering effect. The influence weight is updated using the simulated annealing algorithm until the evaluation index is greater than the preset evaluation threshold. At this time, the updated influence weight is obtained. The simulated annealing algorithm starts with the initial solution i and the initial value t of the control parameter, and repeats the iteration of "generate a new solution → calculate the objective function difference → accept or discard" for the current solution, and gradually decays the t value. The current solution at the end of the algorithm is the approximate optimal solution obtained. It is a heuristic random search process based on the Monte Carlo iterative solution method. The simulated annealing algorithm is a prior art, and the specific principle will not be repeated here. The evaluation threshold is set artificially according to the actual situation. For example, when the number of clusters is 3, the evaluation threshold is 2.7.

[0039] S5: Filter the updated influence weights to obtain the optimal influence weights.

[0040] In one embodiment, the updated influence weights are sorted according to the numerical values, and the sorted influence weights are accumulated from front to back until the accumulated sum is greater than the preset weight threshold, and the influence weights involved in the accumulation calculation are used as the optimal influence weights, which indicates that the corresponding equipment has a greater impact on the production quality of the fiber cloth gypsum board. The weight threshold is manually set according to the actual situation, for example, the weight threshold is 0.8.

[0041] For example, for the updated influence weight , , , , , in descending order, the sorting results are , , , , the influence weights are accumulated from front to back. If , The cumulative sum of is greater than the weight threshold, , As the optimal influence weight, delete the influence weight , .

[0042] In another embodiment, the updated impact weights are sorted according to their numerical values, and the sorted impact weights are accumulated from front to back until the accumulated sum is greater than a preset weight threshold, and the impact weight items not involved in the accumulation calculation are deleted. The K-means algorithm is used to cluster the production parameter sets at each moment in the current time period and calculate the evaluation index, and the impact weight is updated until the evaluation index is greater than the preset evaluation threshold, and the updated impact parameter is used as the optimal impact weight.

[0043] For example, for the updated influence weight , , , , , in descending order, the sorting results are , , , , the influence weights are accumulated from front to back. If , The cumulative sum of is greater than the weight threshold, , As the optimal influence weight, delete the influence weight , At this time, the expression of the distance function in the K-means algorithm is: , use the K-means algorithm to cluster the production parameter sets at each moment in the current time period and calculate the evaluation index, use the simulated annealing algorithm to update the influence weight until the evaluation index is greater than the preset evaluation threshold, and update the influence parameter , as the optimal impact weight.

[0044] S6: Calculate the internal quality score of the gypsum board in the current time period. The internal quality score is positively correlated with the optimal impact weight of the equipment and negatively correlated with the fluctuation degree of the operating parameters.

[0045] Calculate the running benchmark data. The expression of the running benchmark data is: , where: Indicates the current time period The average of the operating parameters of the equipment, Indicates the current time period The median of the operating parameters of the equipment, Indicates the current time period The operating benchmark data reflects the operating status of the equipment on the fiber cloth gypsum board production line in the current time period. Specifically, the operating parameters of the equipment fluctuate around the operating benchmark data.

[0046] In one embodiment, the internal quality score of the gypsum board is calculated, and the expression of the internal quality score is:

[0047] Where: represents the internal quality score of the gypsum board for the current time period, Indicates The optimal impact weight of a device, Indicates the current time period Benchmark data for each device, Indicates Standard data for each device, Indicates the current time period The variance of the operating parameters of each device, Indicates the total number of equipment. Standard data is based on the standard of the production process. For example, in the drying process of fiber cloth gypsum board, the standard drying temperature is used as the standard data of the drying equipment. When calculating the internal quality score, the influence weight is deleted. The value of is 0. The internal quality score indicates the quality status of the fiber cloth gypsum board produced by the production line in the current time period. The higher the score, the better the quality.

[0048] Indicates the current time period The fluctuation degree of the operating parameters of each device. The larger the value, the greater the fluctuation of the operating parameters of the corresponding device, and the more unstable the operating state of the device, which leads to the poorer quality of the fiber cloth gypsum board produced and the lower the internal quality score; It indicates the influence of the corresponding equipment on the quality of fiber cloth gypsum board. The larger the value is, the higher the internal quality score is.

[0049] In other embodiments, the expression for the internal quality score is:

[0050] Where: represents the internal quality score of the gypsum board for the current time period, Indicates The optimal impact weight of a device, Indicates the current time period Benchmark data for each device, Indicates Standard data for each device, Indicates the current time period The variance of the operating parameters of each device, Indicates the total number of devices.

[0051] S7: In response to the internal quality score being less than a score threshold, a signal of device abnormality is issued.

[0052] In one embodiment, when the internal quality score is less than the score threshold, it indicates that the quality of the fiber cloth gypsum board is poor in the current time period, and a signal of equipment abnormality is issued, such as a red light warning or a voice prompt, so as to facilitate timely maintenance of the equipment on the production line.

[0053] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0054] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the operating status of a fiber cloth gypsum board production equipment, characterized in that: Includes steps: Obtain the production parameter set at each moment in the current time period, the production parameter set includes the operating parameters of multiple devices; Calculate the internal quality score of the gypsum board in the current time period. The internal quality score is positively correlated with the optimal impact weight of the equipment and negatively correlated with the fluctuation degree of the operating parameters. In response to the internal quality score being less than the score threshold, send a signal of equipment abnormality; Among them, the calculation method of the optimal impact weight of the running equipment is: Construct the distance function in the K-means algorithm. The expression of the distance function is: In the formula, Represents a set of production parameters With center set The distance between Represents a set of production parameters The operating parameters of the nth device in, Represents the center set The operating parameters of the nth device in, Indicates the influence weight of the nth device; The K-means algorithm is used to cluster the production parameter sets at each moment in the current time period to obtain multiple clusters. The sum of the accuracies of the multiple clusters is used as the evaluation index, and the influence weight is updated until the evaluation index is greater than the preset evaluation threshold. The updated influence weight is screened to obtain the optimal influence weight.

2. A method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to claim 1, characterized in that: The method for filtering the updated influence weights to obtain the optimal influence weights is: The updated influence weights are sorted according to their numerical values, and the sorted influence weights are accumulated from front to back until the accumulated sum is greater than the preset weight threshold. The influence weight involved in the accumulation calculation is taken as the optimal influence weight.

3. The method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to claim 1, characterized in that: The method for filtering the updated influence weights to obtain the optimal influence weights is: The updated impact weights are sorted according to their numerical values, and the sorted impact weights are accumulated from front to back until the accumulated sum is greater than the preset weight threshold. The impact weight items that are not involved in the cumulative calculation are deleted, and the K-means algorithm is used to cluster the production parameter sets at each moment in the current time period and calculate the evaluation index. The impact weight is updated until the evaluation index is greater than the preset evaluation threshold, and the updated impact parameter is used as the optimal impact weight.

4. The method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to claim 1, characterized in that: The expression for the internal quality score is: Where: represents the internal quality score of the gypsum board for the current time period, Indicates The optimal impact weight of each device, Indicates the current time period Benchmark data for each device, Indicates Standard data for each device, Indicates the current time period The variance of the operating parameters of each device, Indicates the total number of devices.

5. The method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to claim 1, characterized in that: The expression for the internal quality score is: Where: represents the internal quality score of the gypsum board for the current time period, Indicates The optimal impact weight of each device, Indicates the current time period Benchmark data for each device, Indicates Standard data for each device, Indicates the current time period The variance of the operating parameters of each device, Indicates the total number of devices.

6. A method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to claim 4 or 5, characterized in that: The expression for running the benchmark data is: Where: Indicates the current time period The average of the operating parameters of the equipment, Indicates the current time period The median of the operating parameters of the equipment, Indicates the current time period The mode of the operating parameters of a device.

7. The method for monitoring the operating status of a fiber cloth-faced gypsum board production equipment according to claim 1, characterized in that: The expression of clustering accuracy is: In the formula, represents the accuracy of clustering. Represents the number of correct production parameter sets in the cluster, Represents the total number of production parameter sets for clustering clusters.

8. The method for monitoring the operating status of fiber cloth gypsum board production equipment according to claim 1, characterized in that: The influence weights are updated using the simulated annealing algorithm.

Images