Roller replacement method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a roller replacement method and device, computer equipment, a readable storage medium and a program product, and relates to the technical field of steel manufacturing. The method comprises the steps that in response to a replacement monitoring instruction for a target roller, plate blank attribute information of each target plate blank rolled by the target roller is obtained; for each target plate blank, based on the plate blank attribute information of the target plate blank, screening out a target plate blank category to which the target plate blank belongs from the plurality of candidate plate blank categories; the rolling weights of all the target plate blank types are accumulated, and the rolling weight sum is obtained; the rolling weight is used for representing the influence degree of the target plate blank belonging to the target plate blank category on the target roller in the rolling process; under the condition that the rolling weight sum exceeds the weight threshold value, a replacement instruction for the target roller is generated; the replacement instruction is used for indicating replacement of the target roller. By adopting the method, the production efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of steel manufacturing, and in particular to a roll replacement method, device, computer equipment, readable storage medium and program product. Background Art

[0002] In the field of steel manufacturing, rollers are one of the important tools. The main function of rollers is to cause plastic deformation of slabs through pressure, so as to roll out the required steel. At present, rollers will inevitably wear out after being used for a period of time, so in order to ensure production efficiency, rollers need to be replaced in time.

[0003] In the prior art, the timing of roller replacement is usually determined based on human experience, but this method that relies on human subjective consciousness cannot guarantee the accuracy of roller replacement, thus affecting production efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a roll replacement method, device, computer equipment, computer-readable storage medium and computer program product that can improve production efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for replacing a rolling mill roll, comprising: in response to a replacement monitoring instruction for a target rolling mill roll, respectively obtaining slab attribute information of each target slab rolled by the target rolling mill roll; for each target slab, based on the slab attribute information of the target slab, screening out a target slab category to which the target slab belongs from a plurality of candidate slab categories; accumulating the rolling weights of the respective target slab categories to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling mill roll during the rolling process; when the rolling weight sum exceeds a weight threshold, generating a replacement instruction for the target rolling mill roll; the replacement instruction is used to instruct the replacement of the target rolling mill roll.

[0006] In one of the embodiments, the process of determining the candidate slab category includes: obtaining multiple historical rolling plans for a target rolling mill, and selecting at least one candidate slab as a clustering center from multiple historical slabs in the multiple historical rolling plans; respectively obtaining first attribute information of each candidate slab and second attribute information of each other slab in the multiple historical slabs except the candidate slabs; based on each first attribute information and each second attribute information, clustering each other slab with each candidate slab to obtain multiple candidate slab categories.

[0007] In one of the embodiments, based on each first attribute information and each second attribute information, each other slab is clustered with each candidate slab to obtain a plurality of candidate slab categories, including: vectorizing each first attribute information and each second attribute information respectively to obtain a first attribute vector of each candidate slab and a second attribute vector of each other slab; determining the vector distance between each first attribute vector and each second attribute vector; clustering each other slab with the candidate slab having the smallest vector distance to obtain a plurality of candidate slab categories.

[0008] In one of the embodiments, the process of determining the rolling weight also includes: counting the number of slabs belonging to each candidate slab category in each historical rolling plan; establishing a weight constraint condition that matches the number of slabs; and determining the rolling weight of each candidate slab category based on the weight constraint condition.

[0009] In one of the embodiments, the rolling weight of each candidate slab category is determined according to the weight constraint, including: establishing an objective function with the goal of minimizing the weight error according to the weight constraint; solving the objective function by the least squares method to obtain the rolling weight of each candidate slab category.

[0010] In one of the embodiments, the method includes: counting the total length of each target slab, and taking the total length of the slab as the rolling mileage of the target roll; based on the rolling mileage, performing performance analysis on the target roll to obtain the performance analysis result of the target roll.

[0011] In the second aspect, the present application also provides a rolling roller replacement device, including: a slab information acquisition module, used to respond to the replacement monitoring instruction for the target rolling roller, and respectively obtain the slab attribute information of each target slab rolled by the target rolling roller; a slab category determination module, used to screen out the target slab category to which the target slab belongs from multiple candidate slab categories based on the slab attribute information of the target slab for each target slab; a weight accumulation module, used to accumulate the rolling weights of each target slab category to obtain the rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; a rolling roller replacement module, used to generate a replacement instruction for the target rolling roller when the rolling weight sum exceeds the weight threshold; the replacement instruction is used to instruct the replacement of the target rolling roller.

[0012] In the third aspect, the present application also provides a computer device, including a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: in response to a replacement monitoring instruction for a target rolling roller, respectively obtaining slab attribute information of each target slab rolled by the target rolling roller; for each target slab, based on the slab attribute information of the target slab, screening out the target slab category to which the target slab belongs from multiple candidate slab categories; accumulating the rolling weights of each target slab category to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; when the rolling weight sum exceeds the weight threshold, generating a replacement instruction for the target rolling roller; the replacement instruction is used to instruct the replacement of the target rolling roller.

[0013] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the following steps when executed by a processor: in response to a replacement monitoring instruction for a target rolling roller, respectively obtaining slab attribute information of each target slab rolled by the target rolling roller; for each target slab, based on the slab attribute information of the target slab, screening out a target slab category to which the target slab belongs from a plurality of candidate slab categories; accumulating the rolling weights of each target slab category to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; when the rolling weight sum exceeds a weight threshold, generating a replacement instruction for the target rolling roller; the replacement instruction is used to instruct the replacement of the target rolling roller.

[0014] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, which implements the following steps when executed by a processor: in response to a replacement monitoring instruction for a target rolling roll, respectively obtaining slab attribute information of each target slab rolled by the target rolling roll; for each target slab, based on the slab attribute information of the target slab, screening out a target slab category to which the target slab belongs from a plurality of candidate slab categories; accumulating the rolling weights of each target slab category to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roll during the rolling process; when the rolling weight sum exceeds a weight threshold, generating a replacement instruction for the target rolling roll; the replacement instruction is used to instruct the replacement of the target rolling roll.

[0015] The above-mentioned roll replacement method, device, computer equipment, computer-readable storage medium and computer program product, in response to the replacement monitoring instruction for the target roll, first obtain the slab attribute information of each target slab rolled by the target roll. For each target slab, based on the slab attribute information of the target slab, the target slab category to which the target slab belongs is screened from multiple candidate slab categories. Thus, the rolling weight of each target slab category is obtained respectively, and each rolling weight is accumulated to obtain the rolling weight sum. When the rolling weight sum exceeds the weight threshold, the target roll is replaced. It can be understood that the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roll during the rolling process. That is to say, the timing of roll replacement in the present application is determined according to the degree of influence of different categories of slabs on the roll during the slab rolling process. Compared with the current method of replacing rolls by relying on manual experience, the present application can more accurately and reliably determine when to replace the roll, improve the accuracy of roll replacement, thereby improving production efficiency, and can also improve the service life of the roll. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] FIG1 is an application environment diagram of a roll replacement method according to an embodiment;

[0018] FIG2 is a schematic flow diagram of a roll replacement method in one embodiment;

[0019] FIG3 is a schematic diagram of a roller rolling a slab in one embodiment;

[0020] FIG4 is a schematic diagram of a process of slab clustering in one embodiment;

[0021] FIG5 is a schematic diagram of a process of slab clustering in another embodiment;

[0022] FIG6 is a schematic diagram of a process for determining a rolling weight in one embodiment;

[0023] FIG7 is a schematic diagram of a process for determining rolling weight in another embodiment;

[0024] FIG8 is a schematic diagram of a process flow of roller performance analysis in one embodiment;

[0025] FIG9 is a structural block diagram of a roll replacement device in one embodiment;

[0026] FIG. 10 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] The roller replacement method provided in the embodiment of the present application can be applied to the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 responds to the replacement instruction for the target roller initiated by the terminal 102, and obtains the slab attribute information of each target slab rolled by the target roller. For each target slab, based on the slab attribute information of the target slab, the target slab category to which the target slab belongs is selected from multiple candidate slab categories. Thus, the rolling weights of each target slab category are obtained respectively, and the rolling weights are accumulated to obtain the rolling weight sum, which is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roller during the rolling process. When the rolling weight sum exceeds the weight threshold, the server 104 instructs to replace the target roller. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and Internet of Things devices. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0029] In an exemplary embodiment, as shown in FIG. 2 , a roller replacement method is provided, which is described by taking the method applied to the server 104 in FIG. 1 as an example, including:

[0030] Step S202, in response to the replacement monitoring instruction for the target rolling roller, respectively obtain the slab property information of each target slab rolled by the target rolling roller.

[0031] Among them, the rollers belong to the working parts on the rolling mill, usually a pair of rollers rotating in opposite directions. Figure 3 shows a schematic diagram of rollers rolling slabs. A gap or hole of a certain shape is formed between the two rollers. The pressure generated by the rolling of the rollers causes the slab passing through the gap or hole to undergo plastic deformation, thereby forming steel. The target roller may refer to a roller that needs to be replaced and monitored. The replacement monitoring instruction may refer to an instruction used to monitor whether the target roller needs to be replaced. The target slab may refer to the slab rolled by the target roller. The slab attribute information may refer to the attribute information of the target slab, including but not limited to the width, thickness, hardness, furnace temperature, etc. of the target slab. Of course, other attribute information such as chemical composition, rolling speed, etc. may also be configured according to production requirements.

[0032] For example, when the server receives the replacement monitoring instruction for the target rolling roller sent by the terminal, it can first query the target slabs currently rolled by the target rolling roller and obtain the attribute information of each target slab to facilitate the subsequent determination of the slab category of the target slab.

[0033] In one example, the slab property information may be obtained from a rolling mill system, that is, the rolling mill system may record all slabs rolled by the rolling rollers and the property information of the slabs.

[0034] Step S204 , for each target slab, based on the slab attribute information of the target slab, a target slab category to which the target slab belongs is screened from a plurality of candidate slab categories.

[0035] The candidate slab category may refer to a predefined slab category, such as a class A slab, a class B slab, or a class C slab. Of course, other names may also be used to define slab categories in practical applications. The target slab category refers to the slab category to which the target slab belongs.

[0036] Exemplarily, after the server obtains the attribute information of each target slab, it can filter out the slab category to which each target slab belongs from various predefined candidate slab categories based on the attribute information.

[0037] In one example, the server may use a clustering method to determine the slab category to which each target slab belongs. That is, the server may obtain the cluster center corresponding to each candidate slab category. It can be understood that the cluster center is essentially also a slab. The server may then vectorize the slab attribute information of the target slab to obtain the attribute vector of the target slab. Then, the vector distance between the attribute vector and the attribute vector corresponding to each cluster center is calculated. The cluster center with the smallest vector distance is determined, and the candidate slab category corresponding to the cluster center is used as the slab category to which the target slab belongs.

[0038] In one example, each candidate slab category may be determined based on multiple historical rolling plans of the target roll. It should be noted that the replaced roll may be put into use again after repair, so the roll may have multiple historical rolling plans.

[0039] Step S206, summing up the rolling weights of each target slab category to obtain a rolling weight sum, where the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roll during the rolling process.

[0040] It can be understood that the roller renewal depends on its wear degree, and the main cause of roller wear is the rolling slab, so the rolling weight is defined in this embodiment to reflect the influence of different types of slabs on the roller during the rolling process. When the influence reaches a certain threshold, the roller can be replaced, which improves the accuracy of roller replacement. Different types of slabs can be pre-configured with different rolling weights, and the sum of the rolling weights of each target slab category is the rolling weight sum, which reflects the total influence of each current target slab on the target roller.

[0041] For example, after determining the target slab category of each target slab, the server can query the rolling weight corresponding to each target slab category, and sum the rolling weights corresponding to these target slab categories to obtain a rolling weight sum, which can be used to reflect the degree of influence of all target slabs on the target roller during the rolling process.

[0042] Step S208, when the rolling weight exceeds the weight threshold, generating a replacement instruction for the target roll; the replacement instruction is used to instruct to replace the target roll.

[0043] The weight threshold may refer to a threshold configured in advance for the rolling weight. When the threshold is exceeded, it means that the influence of each current target slab on the target roll has reached the limit, and the target roll needs to be replaced. When the threshold is not exceeded, it means that the influence of each current target slab on the target roll has not reached the limit, and the target roll may not be replaced temporarily. In one example, the weight threshold may be 1.

[0044] For example, after calculating the rolling weight sum, the server can compare the rolling weight sum with a pre-configured weight threshold. When the rolling weight sum exceeds the threshold, the server can generate a replacement instruction for the target roll to indicate that the target roll needs to be replaced, so that the technician can replace the roll in time.

[0045] In one example, the server can also be configured with two modes: online roll replacement and offline roll replacement. Online roll replacement means that the server is online and monitors the rolling situation in real time. When the target roll rolls a new slab, the server can calculate the category of the slab in real time and accumulate the corresponding rolling weight. Offline roll replacement means that the server is offline and the rolling sequence is set in advance for the slabs that need to be rolled. According to the rolling sequence, the slab category and rolling weight are automatically calculated.

[0046] In one example, when the rolling weight exceeds the weight threshold, the server can generate a replacement instruction and issue a roll change warning at the same time.

[0047] In this embodiment, in response to the replacement monitoring instruction for the target roll, the server first obtains the slab attribute information of each target slab rolled by the target roll. For each target slab, based on the slab attribute information of the target slab, the target slab category to which the target slab belongs is screened from multiple candidate slab categories. Thus, the rolling weights of each target slab category are obtained respectively, and the rolling weights are accumulated to obtain the rolling weight sum. When the rolling weight sum exceeds the weight threshold, the target roll is replaced. It can be understood that the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roll during the rolling process. That is to say, the timing of roll replacement in this embodiment is determined according to the degree of influence of different categories of slabs on the roll during the slab rolling process. Compared with the current method of replacing rolls by relying on manual experience, this embodiment can more accurately and reliably determine when to replace the roll, improve the accuracy of roll replacement, thereby improving production efficiency, and can also increase the service life of the roll.

[0048] In an exemplary embodiment, as shown in FIG4 , the process of determining the candidate slab category includes:

[0049] Step S402, obtaining multiple historical rolling plans for the target roll, and selecting at least one candidate slab from multiple historical slabs of the multiple historical rolling plans as a cluster center.

[0050] Among them, the historical rolling plan may refer to the slab rolling plan of the target roller in a historical period such as a week or a month, which may include but is not limited to the number of rolled slabs, rolling time, rolling plan number, etc. The historical slab refers to the slab in the historical rolling plan, which can be understood as the slab rolled by the target roller in the historical period. The candidate slab can be any slab in each historical slab. The cluster center refers to a special sample in the cluster analysis, which is used to represent a certain class, and other samples are determined by calculating the distance with it to determine whether they belong to this class. It should be noted that in this embodiment, the determination of each candidate slab type is achieved by cluster analysis. In a preferred example, it can be a K-means clustering algorithm. The K-means clustering algorithm is an unsupervised learning algorithm, which is mainly used to divide the data set into K categories, so that each data point is as close as possible to the cluster center to which it belongs, while ensuring that the distance between different cluster centers is as large as possible. In this embodiment, the cluster center is any slab in each historical slab, and it can be judged later whether other slabs except the cluster center belong to each cluster center, that is, the candidate slab.

[0051] For example, the server may define various candidate slab categories in advance. That is, the server may obtain multiple rolling plans of the target roll in the historical period, each rolling plan may contain multiple historical slabs, and the server may randomly select any number of candidate slabs from these historical slabs as cluster centers.

[0052] Step S404 , respectively obtaining first attribute information of each candidate slab and second attribute information of each other slab among a plurality of historical slabs except the candidate slabs.

[0053] The first attribute information refers to the slab attribute information of the candidate slab, and the second attribute information refers to the slab attribute information of other slabs. The slab attribute information may include but is not limited to the slab width, thickness, hardness, furnace temperature and other information. Other slabs refer to the slabs in the history except the candidate slabs.

[0054] For example, after selecting each candidate slab as the cluster center, the server can obtain the attribute information of each candidate slab. At the same time, for each other slab in each historical slab except each candidate slab, the server also needs to obtain the attribute information of each other slab to facilitate subsequent clustering.

[0055] Step S406: based on each first attribute information and each second attribute information, cluster each other slab with each candidate slab to obtain a plurality of candidate slab categories.

[0056] Clustering can be understood as the process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects. The class generated by clustering is a collection of data objects that are similar to objects in the same class and different from objects in other classes. In this embodiment, it means that the slabs in the same candidate slab category are similar to each other and different from slabs in other categories. The similarity and difference here can be understood as the similarity and difference of attribute information.

[0057] Exemplarily, after the server obtains the first attribute information of each candidate slab and the second attribute information of each other slab, it can calculate the distance between each other slab and each candidate slab, that is, the clustering center, based on the first attribute information and the second attribute information, and thus cluster each other slab into the corresponding candidate slab according to each distance to obtain each candidate slab category.

[0058] In this embodiment, each historical slab rolled by the target roll is clustered to obtain each candidate slab category, thereby improving the reliability and accuracy of the candidate slab category, thereby improving the accuracy of roll replacement and further improving production efficiency.

[0059] In an exemplary embodiment, as shown in FIG5 , based on each first attribute information and each second attribute information, each other slab is clustered with each candidate slab to obtain a plurality of candidate slab categories, including:

[0060] Step S502 , respectively performing vectorization processing on each first attribute information and each second attribute information to obtain a first attribute vector of each candidate slab and a second attribute vector of each other slab.

[0061] The vectorization process may refer to a process of converting non-numeric data into numeric data. The first attribute vector may refer to a vector obtained after vectorization process is performed on the first attribute information. The second attribute vector may refer to a vector obtained after vectorization process is performed on the second attribute information.

[0062] Exemplarily, after obtaining the first attribute information of each candidate slab and the second attribute information of each other slab, the server may further vectorize the first attribute information and the second attribute information, that is, convert the first attribute information and the second attribute information into numerical vectors to facilitate subsequent distance calculation.

[0063] Step S504: determining the vector distance between each first attribute vector and each second attribute vector.

[0064] The vector distance may be used to quantify the attribute similarity between the first attribute vector and the second attribute vector.

[0065] For example, after calculating each first attribute vector and each second attribute vector, the server can calculate the vector distance to evaluate the similarity between the slabs. In this example, the Euclidean distance is used to calculate the vector distance, and the expression is as follows:

[0066]

[0067] Where x represents the first attribute vector, y represents the second attribute vector, i represents the i-th attribute, and n represents the number of attributes. Represents the standard deviation of the i-th attribute.

[0068] Step S506: clustering the candidate slabs with the smallest vector distances from the other slabs to obtain a plurality of candidate slab categories.

[0069] Among them, the smaller the vector distance, the more similar the slabs are. Conversely, the larger the vector distance, the greater the difference between the slabs.

[0070] Exemplarily, after calculating the vector distance between each other slab and each candidate slab based on each first attribute vector and each second attribute vector, the server can cluster each other slab into the candidate slab with the smallest vector distance thereto, thereby forming various candidate slab categories.

[0071] For example, assuming there are candidate slab 1, candidate slab 2 and other slab 3, the vector distance between other slab 3 and candidate slab 1 is x1, the vector distance between other slab 3 and candidate slab 2 is x2, and x1 is less than x2, then other slab 3 and candidate slab 1 are clustered to form a candidate slab category.

[0072] In this embodiment, by vectorizing the attribute information, the vector distance between other slabs and the candidate slab as the cluster center is calculated, and then the slab clustering is realized to obtain multiple candidate slab categories. The accuracy of the candidate slab categories is improved, thereby improving the accuracy of the roll replacement and further improving the production efficiency.

[0073] In an exemplary embodiment, as shown in FIG6 , the process of determining the rolling weight further includes:

[0074] Step S602, counting the number of slabs belonging to each candidate slab category in each historical rolling plan.

[0075] The number of slabs refers to the total number of slabs belonging to each candidate slab category in each historical rolling plan.

[0076] Exemplarily, after determining each candidate slab category, the server can further determine the rolling weight of each candidate slab category. The server can first count the total number of slabs belonging to each candidate slab category in each historical rolling plan. It is understandable that there can be historical slabs of different candidate slab categories in a historical rolling plan, for example, there can be both Class A slabs and Class B slabs in a historical rolling plan.

[0077] Step S604, establishing a weight constraint condition that matches the number of slabs.

[0078] The weight constraint condition may refer to a constraint condition formulated for the rolling weight. In this embodiment, the weight constraint condition may be related to the number of slabs.

[0079] In one example, the expression of the weight constraint is as follows:

[0080]

[0081] Where, j represents the jth candidate slab category, C represents the number of candidate slab categories, represents the rolling weight of the jth candidate slab category, It represents the number of slabs belonging to the jth candidate slab category in the i-th historical rolling plan.

[0082] For example, after the server counts the total number of slabs belonging to each candidate slab category in each historical rolling plan, it can establish a constraint condition for the rolling weight based on the total number of slabs in each candidate slab category. Of course, in actual applications, other constraints can also be established according to actual conditions.

[0083] Step S606, determining the rolling weight of each candidate slab category according to the weight constraint condition.

[0084] Exemplarily, after the server establishes the constraint conditions for the rolling weight, it can calculate the rolling weight of each candidate slab category based on the constraint conditions and the corresponding objective function.

[0085] In this embodiment, by counting the total number of slabs belonging to each candidate slab category in each historical rolling plan, the corresponding weight constraint conditions are established, and then the rolling weight of each candidate slab category is calculated, thereby improving the accuracy of the rolling weight, thereby improving the accuracy of roll replacement, and further improving production efficiency.

[0086] In an exemplary embodiment, as shown in FIG7 , according to the weight constraint condition, the rolling weight of each candidate slab category is determined, including:

[0087] Step S702: establishing an objective function with the goal of minimizing the weight error according to the weight constraint condition.

[0088] The objective function refers to a mathematical function that includes an optimization target. In this embodiment, the optimization target may be minimizing the weight error.

[0089] In one example, the objective function can be expressed as:

[0090]

[0091] Where N represents the number of historical rolling plans.

[0092] Exemplarily, after establishing the weight constraint condition, the server can create an objective function according to the weight constraint condition to obtain an objective function with the goal of minimizing the weight error.

[0093] Step S704, solving the objective function by the least square method to obtain the rolling weight of each candidate slab category.

[0094] Among them, it can be understood that since the number N of historical rolling plans is often much greater than the number C of candidate slab categories, the linear equations formed are overdetermined, and an overdetermined system of equations refers to a system of equations in which the number of equations is greater than the number of unknowns. In this case, the system of equations usually has no exact solution because not all equations can be satisfied at the same time. Based on this, the least squares method is used in this embodiment, and the best function matching of the data can be found by minimizing the sum of squares of errors. In the case of an overdetermined system of equations, the least squares method provides a method for finding the best fitting solution, i.e., a set of rolling weights, which can fit the historical rolling plan well.

[0095] Exemplarily, after establishing the objective function, the server may use the least square method to solve the objective function to obtain the rolling weight of each candidate slab category.

[0096] In this embodiment, the objective function is solved by the least square method, which can well fit the historical rolling plan, so that the calculated rolling weights are more reliable and accurate, thereby improving the accuracy of roll replacement and further improving production efficiency.

[0097] In an exemplary embodiment, as shown in FIG8 , the method further includes:

[0098] Step S802, counting the total length of each target slab, and using the total length of the slab as the rolling mileage of the target rolling roller.

[0099] The total length of the slab refers to the sum of the lengths of the target slabs. The rolling mileage may refer to the total rolling length of the target roll. In this embodiment, the total length of the slab is used to represent the rolling mileage of the target roll.

[0100] For example, after replacing the target roll, the server can further evaluate the performance of the target roll. At this time, the server can count the total length of each target slab, and use the total length of the slab as the rolling mileage of the target roll, which can be used as one of the important bases for subsequent evaluation of the performance of the target roll.

[0101] Step S804: Based on the rolling mileage, a performance analysis is performed on the target roll to obtain a performance analysis result of the target roll.

[0102] The performance analysis may refer to the process of analyzing the performance of the target roll during the rolling process. The performance analysis results may include but are not limited to the bite ability, thermal crack resistance, thermal shock resistance, rolling speed, wear rate, etc. of the target roll.

[0103] For example, after the server obtains the rolling mileage of the target roll, it can analyze the performance of the target roll in combination with other information of the target roll, such as rolling temperature, cooling method, material, rolling environment, etc., to obtain the performance analysis result of the target roll, which can facilitate subsequent optimization of the roll and the rolling process.

[0104] In this embodiment, the rolling mileage of the target roll is calculated to evaluate the performance of the target roll, thereby facilitating optimization of the roll and the rolling process, improving the stability and reliability of the roll, and thus improving production efficiency.

[0105] In a specific embodiment, the process of the roll replacement method further includes:

[0106] The server obtains multiple historical rolling plans for the target roll, and selects at least one candidate slab as the cluster center from multiple historical slabs in the multiple historical rolling plans. The first attribute information of each candidate slab and the second attribute information of each other slab in the multiple historical slabs except the candidate slabs are obtained respectively. Each first attribute information and each second attribute information are vectorized respectively to obtain the first attribute vector of each candidate slab and the second attribute vector of each other slab. The vector distance between each first attribute vector and each second attribute vector is calculated. The candidate slabs with the smallest vector distance are clustered with each other slab to obtain multiple candidate slab categories. The number of slabs belonging to each candidate slab category in each historical rolling plan is counted. A weight constraint matching the number of slabs is established. According to the weight constraint, an objective function with the goal of minimizing the weight error is established. The objective function is solved by the least squares method to obtain the rolling weight of each candidate slab category.

[0107] In response to the replacement monitoring instruction for the target roll, the server obtains the slab attribute information of each target slab rolled by the target roll. For each target slab, based on the slab attribute information of the target slab, the target slab category to which the target slab belongs is screened out from multiple candidate slab categories. The rolling weights of each target slab category are accumulated to obtain the rolling weight sum. The rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roll during the rolling process. When the rolling weight sum exceeds the weight threshold, a replacement instruction for the target roll is generated; the replacement instruction is used to instruct the replacement of the target roll. The total slab length of each target slab is counted, and the total slab length is used as the rolling mileage of the target roll. Based on the rolling mileage, the performance of the target roll is analyzed to obtain the performance analysis results of the target roll.

[0108] In this embodiment, in response to the replacement monitoring instruction for the target roll, the server first obtains the slab attribute information of each target slab rolled by the target roll. For each target slab, based on the slab attribute information of the target slab, the target slab category to which the target slab belongs is screened from multiple candidate slab categories. Thus, the rolling weights of each target slab category are obtained respectively, and the rolling weights are accumulated to obtain the rolling weight sum. When the rolling weight sum exceeds the weight threshold, the target roll is replaced. It can be understood that the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roll during the rolling process. That is to say, the timing of roll replacement in this embodiment is determined according to the degree of influence of different categories of slabs on the roll during the slab rolling process. Compared with the current method of replacing rolls by relying on manual experience, this embodiment can more accurately and reliably determine when to replace the roll, improve the accuracy of roll replacement, thereby improving production efficiency, and can also increase the service life of the roll.

[0109] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0110] Based on the same inventive concept, the embodiment of the present application also provides a roll replacement device for implementing the roll replacement method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more roll replacement device embodiments provided below can refer to the limitations of the roll replacement method above, and will not be repeated here.

[0111] In an exemplary embodiment, as shown in FIG9 , a roll replacement device is provided, including: a slab information acquisition module 902, for obtaining, in response to a replacement monitoring instruction for a target roll, respective slab attribute information of each target slab rolled by the target roll; a slab category determination module 904, for screening, for each target slab, based on the slab attribute information of the target slab, a target slab category to which the target slab belongs from a plurality of candidate slab categories; a weight accumulation module 906, for accumulating the rolling weights of the respective target slab categories to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roll during the rolling process; a roll replacement module 908, for generating a replacement instruction for the target roll when the rolling weight sum exceeds a weight threshold; the replacement instruction is used to instruct the replacement of the target roll.

[0112] In one of the embodiments, the device is also used to: obtain multiple historical rolling plans for the target rolling mill, and select at least one candidate slab as a clustering center from multiple historical slabs in the multiple historical rolling plans; respectively obtain first attribute information of each candidate slab, and second attribute information of each other slab in the multiple historical slabs except the candidate slabs; based on each first attribute information and each second attribute information, cluster each other slab with each candidate slab to obtain multiple candidate slab categories.

[0113] In one of the embodiments, the device is also used to: vectorize each first attribute information and each second attribute information respectively to obtain a first attribute vector of each candidate slab and a second attribute vector of each other slab; determine the vector distance between each first attribute vector and each second attribute vector; cluster the candidate slabs with the smallest vector distance from each other slab to obtain multiple candidate slab categories.

[0114] In one of the embodiments, the device is also used to: count the number of slabs belonging to each candidate slab category in each historical rolling plan; establish weight constraints that match the number of slabs; and determine the rolling weight of each candidate slab category based on the weight constraints.

[0115] In one of the embodiments, the device is also used to: establish an objective function with the goal of minimizing the weight error according to the weight constraint condition; solve the objective function by the least squares method to obtain the rolling weight of each candidate slab category.

[0116] In one of the embodiments, the device is also used to: count the total length of each target slab, and use the total length of the slab as the rolling mileage of the target roll; based on the rolling mileage, perform performance analysis on the target roll to obtain the performance analysis result of the target roll.

[0117] Each module in the above-mentioned roll changing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0118] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG10. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store roller replacement data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a roller replacement method is implemented.

[0119] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0120] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: in response to a replacement monitoring instruction for a target rolling roller, respectively obtaining slab attribute information of each target slab rolled by the target rolling roller; for each target slab, based on the slab attribute information of the target slab, screening out a target slab category to which the target slab belongs from a plurality of candidate slab categories; accumulating the rolling weights of the respective target slab categories to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; when the rolling weight sum exceeds a weight threshold, generating a replacement instruction for the target rolling roller; the replacement instruction is used to instruct the replacement of the target rolling roller.

[0121] In one embodiment, the processor also implements the following steps when executing the computer program: in response to a replacement monitoring instruction for a target rolling roller, respectively obtain slab attribute information of each target slab rolled by the target rolling roller; for each target slab, based on the slab attribute information of the target slab, screen out the target slab category to which the target slab belongs from multiple candidate slab categories; add up the rolling weights of each target slab category to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; when the rolling weight sum exceeds a weight threshold, generate a replacement instruction for the target rolling roller; the replacement instruction is used to instruct the replacement of the target rolling roller.

[0122] In one embodiment, when the processor executes the computer program, the following steps are also implemented: vectorizing each first attribute information and each second attribute information respectively to obtain the first attribute vector of each candidate slab and the second attribute vector of each other slab; determining the vector distance between each first attribute vector and each second attribute vector; clustering the candidate slabs with the smallest vector distance from each other slab to obtain multiple candidate slab categories.

[0123] In one embodiment, when the processor executes the computer program, the following steps are also implemented: counting the number of slabs belonging to each candidate slab category in each historical rolling plan; establishing a weight constraint condition that matches the number of slabs; and determining the rolling weight of each candidate slab category based on the weight constraint condition.

[0124] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the weight constraint, an objective function is established with the goal of minimizing the weight error; the objective function is solved by the least squares method to obtain the rolling weight of each candidate slab category.

[0125] In one embodiment, when the processor executes the computer program, the following steps are also implemented: counting the total length of each target slab, and taking the total length of the slab as the rolling mileage of the target roller; based on the rolling mileage, performing a performance analysis on the target roller to obtain a performance analysis result of the target roller.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: in response to a replacement monitoring instruction for a target roll, slab attribute information of each target slab rolled by the target roll is obtained respectively; for each target slab, based on the slab attribute information of the target slab, the target slab category to which the target slab belongs is screened from multiple candidate slab categories; the rolling weights of the respective target slab categories are added to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target roll during the rolling process; when the rolling weight sum exceeds a weight threshold, a replacement instruction for the target roll is generated; the replacement instruction is used to instruct the replacement of the target roll.

[0127] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining multiple historical rolling plans for the target rolling mill, and selecting at least one candidate slab as a clustering center from multiple historical slabs in the multiple historical rolling plans; respectively obtaining first attribute information of each candidate slab and second attribute information of each other slab in the multiple historical slabs except the candidate slabs; based on each first attribute information and each second attribute information, clustering each other slab with each candidate slab to obtain multiple candidate slab categories.

[0128] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: vectorizing each first attribute information and each second attribute information respectively to obtain the first attribute vector of each candidate slab and the second attribute vector of each other slab; determining the vector distance between each first attribute vector and each second attribute vector; clustering the candidate slabs with the smallest vector distance from each other slab to obtain multiple candidate slab categories.

[0129] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: counting the number of slabs belonging to each candidate slab category in each historical rolling plan; establishing a weight constraint condition that matches the number of slabs; and determining the rolling weight of each candidate slab category based on the weight constraint condition.

[0130] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the weight constraint, an objective function is established with the goal of minimizing the weight error; the objective function is solved by the least squares method to obtain the rolling weight of each candidate slab category.

[0131] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: counting the total length of each target slab, and taking the total length of the slab as the rolling mileage of the target roll; based on the rolling mileage, performing a performance analysis on the target roll to obtain a performance analysis result of the target roll.

[0132] In one embodiment, a computer program product is provided, comprising a computer program, which implements the following steps when executed by a processor: in response to a replacement monitoring instruction for a target rolling roll, respectively obtaining slab attribute information of each target slab rolled by the target rolling roll; for each target slab, based on the slab attribute information of the target slab, screening out a target slab category to which the target slab belongs from a plurality of candidate slab categories; accumulating the rolling weights of the respective target slab categories to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roll during the rolling process; when the rolling weight sum exceeds a weight threshold, generating a replacement instruction for the target rolling roll; the replacement instruction is used to instruct the replacement of the target rolling roll.

[0133] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining multiple historical rolling plans for the target rolling mill, and selecting at least one candidate slab as a clustering center from multiple historical slabs in the multiple historical rolling plans; respectively obtaining first attribute information of each candidate slab and second attribute information of each other slab in the multiple historical slabs except the candidate slabs; based on each first attribute information and each second attribute information, clustering each other slab with each candidate slab to obtain multiple candidate slab categories.

[0134] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: vectorizing each first attribute information and each second attribute information respectively to obtain the first attribute vector of each candidate slab and the second attribute vector of each other slab; determining the vector distance between each first attribute vector and each second attribute vector; clustering the candidate slabs with the smallest vector distance from each other slab to obtain multiple candidate slab categories.

[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: counting the number of slabs belonging to each candidate slab category in each historical rolling plan; establishing a weight constraint condition that matches the number of slabs; and determining the rolling weight of each candidate slab category based on the weight constraint condition.

[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the weight constraint, an objective function is established with the goal of minimizing the weight error; the objective function is solved by the least squares method to obtain the rolling weight of each candidate slab category.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: counting the total length of each target slab, and taking the total length of the slab as the rolling mileage of the target roll; based on the rolling mileage, performing a performance analysis on the target roll to obtain a performance analysis result of the target roll.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0140] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0141] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A roll replacement method, characterized in that: The method comprises: In response to a replacement monitoring instruction for a target rolling roll, respectively acquiring slab property information of each target slab rolled by the target rolling roll; For each of the target slabs, based on the slab attribute information of the target slab, selecting a target slab category to which the target slab belongs from a plurality of candidate slab categories; The rolling weights of the target slab categories are accumulated to obtain a rolling weight sum; the rolling weight is used to indicate the influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; In the case where the rolling weight sum exceeds a weight threshold, a replacement instruction for the target roll is generated; the replacement instruction is used to instruct the replacement of the target roll.

2. The method according to claim 1, characterized in that The process of determining the candidate slab category includes: Acquire multiple historical rolling plans for the target roll, and select at least one candidate slab from multiple historical slabs in the multiple historical rolling plans as a cluster center; Respectively acquiring first attribute information of each candidate slab and second attribute information of each other slab among the plurality of historical slabs except the candidate slabs; Based on each of the first attribute information and each of the second attribute information, each of the other slabs is clustered with each of the candidate slabs to obtain a plurality of candidate slab categories.

3. The method according to claim 2, characterized in that The clustering of the other slabs and the candidate slabs based on the first attribute information and the second attribute information to obtain a plurality of candidate slab categories includes: Performing vectorization processing on each of the first attribute information and each of the second attribute information respectively, to obtain a first attribute vector of each of the candidate slabs and a second attribute vector of each of the other slabs; Determine a vector distance between each of the first attribute vectors and each of the second attribute vectors; Clustering the candidate slabs having the smallest vector distances with each of the other slabs to obtain a plurality of candidate slab categories.

4. The method according to claim 2, characterized in that: The process of determining the rolling weight also includes: Counting the number of slabs belonging to each candidate slab category in each of the historical rolling plans; Establishing a weight constraint condition matching the number of slabs; According to the weight constraint condition, the rolling weight of each candidate slab category is determined.

5. The method according to claim 4, characterized in that Determining the rolling weight of each candidate slab category according to the weight constraint condition includes: According to the weight constraint condition, an objective function is established with the goal of minimizing the weight error; The objective function is solved by the least square method to obtain the rolling weight of each candidate slab category.

6. The method according to claim 1, characterized in that The method comprises: Counting the total length of each target slab, and taking the total length of the slab as the rolling mileage of the target roller; Based on the rolling mileage, a performance analysis is performed on the target roller to obtain a performance analysis result of the target roller.

7. A roll replacement device, characterized in that: The device comprises: A slab information acquisition module, for respectively acquiring slab property information of each target slab rolled by the target roller in response to a replacement monitoring instruction for the target roller; A slab category determination module is used to select, for each target slab, a target slab category to which the target slab belongs from a plurality of candidate slab categories based on the slab attribute information of the target slab; A weight accumulation module, used for accumulating the rolling weights of each target slab category to obtain a rolling weight sum; the rolling weight is used to indicate the degree of influence of the target slab belonging to the target slab category on the target rolling roller during the rolling process; The roll replacement module is used to generate a replacement instruction for the target roll when the rolling weight exceeds a weight threshold; the replacement instruction is used to instruct the replacement of the target roll.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images