Roll crack prediction system and method, computer equipment, readable storage medium and program product

Abstract

The invention relates to a roller crack prediction system and method, computer equipment, a readable storage medium and a program product, and is applied to the technical field of big data, and the system comprises a temperature detection device, a roller recognition unit and a controller; the temperature detection device is configured to detect roller temperature information when a to-be-detected roller is offline; the roller identification unit is configured to identify roller information of the to-be-detected roller, and the roller information is used for representing the use condition of the to-be-detected roller; and the controller is configured to perform roller crack prediction on the to-be-detected roller according to the roller temperature information and the roller information to obtain a roller crack prediction result. By adopting the method, the use safety of the roller can be improved.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a roll crack prediction system, method, computer device, computer-readable storage medium and computer program product. Background Art

[0002] Rollers are very important processing tools in the steel production process (such as continuous casting, hot rolling, cold rolling, leveling, straightening, etc.). During the production process, fine cracks may appear inside the rolls. If the fine cracks inside the rolls cannot be identified in time, serious accidents such as roll explosion are likely to occur after the rolls are put back on line, resulting in low safety in the use of the rolls. Summary of the invention

[0003] Based on this, it is necessary to provide a roll crack prediction system, method, computer equipment, computer readable storage medium and computer program product that can improve the safety of roll use in response to the above technical problems.

[0004] In a first aspect, the present application provides a roll crack prediction system, comprising: a temperature detection device, a roll identification unit and a controller;

[0005] The temperature detection device is configured to detect the temperature information of the roller when the roller to be detected is off the production line;

[0006] The roller identification unit is configured to identify roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected;

[0007] The controller is configured to perform roll crack prediction on the roll to be inspected according to the roll temperature information and the roll information to obtain a roll crack prediction result.

[0008] In one of the embodiments, when the roller to be inspected rolls off the roller track, the temperature detection device is placed in the side area of ​​the roller track; when the roller to be inspected rolls off the transport vehicle, the temperature detection device is placed in the transport unloading area corresponding to the roller to be inspected.

[0009] In one of the embodiments, when the roller to be detected goes offline on the roller track, the controller is further configured to perform roller crack prediction on the roller to be detected based on the roller information and target temperature information to obtain a roller crack prediction result, wherein the target temperature information is selected from the roller temperature information based on the collection time corresponding to the roller temperature information and the offline speed of the roller to be detected during the process of going offline on the roller track.

[0010] In one embodiment, the controller is further configured to perform roller crack prediction on the roller to be detected based on the roller fusion feature to obtain a roller crack prediction result, wherein the roller fusion feature is obtained by fusing the roller temperature weighted feature and the roller usage weighted feature, the roller temperature weighted feature is obtained by weighting the first weight corresponding to the roller temperature feature and the roller temperature feature, the roller temperature feature is a feature extracted from the target temperature information, the roller usage weighted feature is obtained by weighting the second weight corresponding to the roller usage feature and the roller usage feature, and the roller usage feature is a feature extracted from the roller information.

[0011] In one embodiment, the controller is further configured to generate a first weight corresponding to the roller temperature characteristic and a second weight corresponding to the roller usage characteristic according to the target temperature information and roller information of the roller to be inspected, respectively, wherein the higher the first importance of the roller crack prediction for the roller to be inspected represented by the target temperature information, the larger the first weight generated, and the higher the second importance of the roller crack prediction for the roller to be inspected represented by the roller information, the larger the second weight generated.

[0012] In one of the embodiments, when the environmental visibility of the detection environment corresponding to the roller to be detected meets the preset visibility condition, the temperature detection device is a remote temperature detection device; when the environmental visibility of the detection environment corresponding to the roller to be detected does not meet the preset visibility condition, the temperature detection device is a contact temperature detection device.

[0013] In a second aspect, the present application also provides a method for predicting roll cracks, comprising:

[0014] Acquiring roller temperature information of the roller to be detected, and acquiring roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected;

[0015] According to the roll temperature information and the roll information, a roll crack prediction is performed on the roll to be inspected to obtain a roll crack prediction result.

[0016] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0017] Acquiring roller temperature information of the roller to be detected, and acquiring roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected;

[0018] According to the roll temperature information and the roll information, a roll crack prediction is performed on the roll to be inspected to obtain a roll crack prediction result.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0020] Acquiring roller temperature information of the roller to be detected, and acquiring roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected;

[0021] According to the roll temperature information and the roll information, a roll crack prediction is performed on the roll to be inspected to obtain a roll crack prediction result.

[0022] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0023] Acquiring roller temperature information of the roller to be detected, and acquiring roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected;

[0024] According to the roll temperature information and the roll information, a roll crack prediction is performed on the roll to be inspected to obtain a roll crack prediction result.

[0025] The above-mentioned roller crack prediction system, method, computer device, computer-readable storage medium and computer program product, because when the roller temperature is high, there may be uneven cooling degrees in different areas of the roller, which may cause cracks inside the roller. Therefore, the roller temperature information of the roller to be detected can be detected by a temperature detection device, and the roller information characterizing the usage status of the roller to be detected can be identified by a roller identification unit. Then, the controller can predict the roller crack of the roller to be detected based on the roller temperature information and the roller information to obtain a roller crack prediction result. The roller temperature and the roller information that can characterize the usage status of the roller are used as the basis for crack prediction of the roller to be detected, thereby ensuring the accuracy of the roller crack prediction, so that when cracks are detected in the roller to be detected, processing can be performed, thereby ensuring the safety of roller use. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] 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.

[0027] Figure 1 A schematic diagram of the structure of a roll crack prediction system in one embodiment;

[0028] Figure 2 A diagram showing an application environment of a method for predicting roll cracks in an embodiment;

[0029] Figure 3 A schematic diagram of a process flow of a method for predicting roll cracks in one embodiment;

[0030] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] 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.

[0032] It should be noted that the information (including but not limited to roller temperature information and roller information, etc.) and data (including but not limited to data 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 acquisition, transmission, storage, use and processing of relevant data are in compliance with the relevant provisions of national laws and regulations. The content pushed to the user (for example, roller crack prediction results, etc.) can be rejected by the user or can be easily rejected by the user. In the embodiments of this application, some software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0033] In an exemplary embodiment, Figure 1 As shown, a roll crack prediction system is provided, which includes a temperature detection device 102, a roll identification unit 104 and a controller 106. The controller 106 is connected to the temperature detection device 102 for communication, and the controller 106 is connected to the roll identification unit 104 for communication.

[0034] The roll to be inspected is a roll waiting for roll crack prediction, and the roll to be inspected may be a roll that has just come off the production line, or a roll before being put on the production line, and there is no limitation here.

[0035] The temperature detection device is configured to detect the temperature information of the rolling mill roll when the rolling mill roll to be detected is off the production line.

[0036] As an embodiment, when the roller to be inspected is off the roller track, the temperature detection device is placed in the side area of ​​the roller track; when the roller to be inspected is off the roller track on the transport vehicle, the temperature detection device is placed in the transport unloading area corresponding to the roller to be inspected, wherein the transport vehicle can be a crane trolley.

[0037] In this way, an adaptive placement scheme for the temperature detection device of the roll to be detected under different roll unloading methods can be provided to ensure that the roll temperature information of the roll to be detected detected by the temperature detection device can accurately reflect the actual temperature value of the roll to be detected.

[0038] As an embodiment, the number of the temperature detection devices may be one or more.

[0039] It is understandable that in order to ensure that the roller temperature information can accurately reflect the actual temperature value of the roller to be detected, it is usually necessary to perform temperature detection on multiple parts of the roller to be detected.

[0040] Because the roller to be inspected can be moved by the roller track when it is off-line on the roller track, the temperature detection device can measure the temperature of multiple parts of the roller to be inspected when the roller to be inspected moves. Therefore, in this case, one temperature detection device can be set. When the roller to be inspected is off-line on the transport vehicle, the roller to be inspected will not move. Therefore, multiple temperature detection devices need to be set to achieve temperature detection of multiple parts of the roller to be inspected.

[0041] When the roller to be inspected is off the roller track, the placement position of the temperature detection device can be fixed or movable. When the roller to be inspected is off the transport vehicle and the number of temperature detection devices is set to one, the placement position of the temperature detection device is movable, and the temperature of multiple parts of the roller to be inspected can be measured by moving. When the roller to be inspected is off the transport vehicle and the number of temperature detection devices is set to multiple, the placement position of the temperature detection device can be fixed or movable.

[0042] When the placement position of the temperature detection device is fixed, since the placement position of the temperature detection device cannot be changed, the placement position of the temperature detection device matches the placement position of the roller to be detected.

[0043] When the environmental visibility of the detection environment corresponding to the roller to be detected meets the preset visibility condition, the temperature detection device is a remote temperature detection device; when the environmental visibility of the detection environment corresponding to the roller to be detected does not meet the preset visibility condition, the temperature detection device is a contact temperature detection device.

[0044] Among them, the ambient visibility can be determined by at least one of the ambient dust content and the ambient water mist content. Specifically, the higher the ambient dust content, the lower the ambient visibility, and the higher the ambient water mist content, the lower the ambient visibility. The preset visibility condition can be a preset ambient visibility range, for example, less than a preset visibility threshold. Furthermore, the preset visibility threshold is a visibility critical value set as needed to determine whether the ambient visibility of the detection environment is high.

[0045] In this way, when the environmental visibility of the detection environment corresponding to the roller to be detected meets the preset visibility condition, that is, when the environmental visibility of the detection environment is high, temperature detection is performed by using a more convenient remote temperature detection device; and when the environmental visibility of the detection environment corresponding to the roller to be detected does not meet the preset visibility condition, that is, when the environmental visibility of the detection environment is low, if the remote temperature detection device is still used for temperature detection, the dust and / or water mist in the detection environment may interfere with the temperature detection of the remote temperature detection device, and it is easy for the roller temperature information obtained by the detection to deviate greatly from the actual temperature value of the roller to be detected. Therefore, when the environmental visibility of the detection environment is low, a contact temperature detection device is used for temperature detection to ensure the accuracy of the roller temperature detection.

[0046] The roller identification unit is configured to identify roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected.

[0047] Among them, the roll information includes at least one of the roll number, roll type, roll history processing information, roll current processing information and roll shape information. The roll number is used to identify the unique number of the roll. The roll history processing information includes at least one of the number of times the roll has been online in history, the roll history grinding amount, historical crack detection results and the length of time the roll has been online in history. The roll current processing information includes at least one of the time the roll was offline, the length of time the roll was last online, the number of kilometers rolled when the roll was last online, the number of rolling blocks when the roll was last online and the estimated time the roll was online. The roll shape information includes at least one of the roll diameter and the roll shape.

[0048] As an embodiment, the roller identification unit is configured to collect a roller image carrying the characteristics of the roller to be detected, and perform image recognition on the roller image to obtain the roller number, roller diameter and roller shape of the roller to be detected.

[0049] It is understandable that the image acquisition environment corresponding to the roller image may have poor lighting, or the roller number engraved on the roller to be inspected may not be obvious on the surface of the roller to be inspected, resulting in the roller number being unable to be clearly identified through the roller image.

[0050] As another embodiment, the roller number sent by the user is obtained.

[0051] In this way, it can be ensured that the obtained roll number is accurate.

[0052] As another embodiment, the roller tracking online time of the roller corresponding to each roller number is obtained, wherein the roller tracking online time is detected by sensors deployed on the roller track; the roller online time corresponding to the roller to be detected is obtained; and the number that matches the corresponding roller tracking online time and the roller online time is selected from each roller number to be determined as the roller number of the roller to be detected.

[0053] In this way, the roll number can be automatically determined while ensuring that the acquired roll number is accurate.

[0054] As one embodiment, the roller identification unit is configured to obtain a roller process log, wherein the roller process log includes a correspondence between a roller number of at least one preset roller and roller historical processing information; according to the roller number of the roller to be detected, the roller historical processing information and the roller offline time corresponding to the roller to be detected are queried from the roller process log.

[0055] As an embodiment, the roll identification unit is configured to obtain a roll processing plan corresponding to the roll to be detected, and identify an estimated roll online time of the roll to be detected from the roll processing plan.

[0056] The controller is configured to predict the roll crack of the roll to be inspected according to the roll temperature information and the roll information, and obtain the roll crack prediction result.

[0057] Among them, the roller crack prediction result can be a two-category result, including a prediction result of the presence of cracks in the roller or a prediction result of the absence of cracks in the roller; the roller crack prediction result can also be a probability prediction result, used to characterize the probability of cracks appearing in the roller; the roller crack prediction result can also be a degree prediction result, used to characterize the crack propagation range corresponding to the roller, for example, it can be a range composed of the circumscribed shape of the crack predicted to exist in the roller, such as a circumscribed circle, a circumscribed polygon, etc.

[0058] As one embodiment, the controller is configured to input the roller temperature information and the roller information into a pre-trained first roller crack prediction model (by mapping the roller temperature information and the roller information through the first roller crack prediction model) to obtain a roller crack prediction result, wherein the first roller crack prediction model is trained by a first preset sample, and the first preset sample is composed of the roller temperature information and the roller information of multiple first training rollers, and the actual roller crack results corresponding to the multiple first training rollers.

[0059] As another embodiment, the controller is configured to obtain a first roller crack table, wherein the first roller crack table is composed of the correspondence between the roller temperature information and the roller information of the roller and the roller crack result, and based on the roller temperature information and the roller information of the roller to be detected, the first roller crack table is queried to obtain the roller crack prediction result.

[0060] In the present embodiment, when the roller temperature is high, there may be uneven cooling degrees in different areas of the roller, resulting in cracks inside the roller. Therefore, the roller temperature information of the roller to be detected can be detected by the temperature detection device, and the roller information characterizing the use status of the roller to be detected can be identified by the roller identification unit. Then, the controller can predict roller cracks of the roller to be detected based on the roller temperature information and the roller information to obtain a roller crack prediction result. The roller temperature and the roller information that can characterize the use status of the roller are used as the basis for crack prediction of the roller to be detected, thereby ensuring the accuracy of the roller crack prediction. Therefore, when cracks are detected in the roller to be detected, processing can be performed, thereby ensuring the safety of roller use.

[0061] As an embodiment, when the roller to be inspected goes offline on the roller track, the controller is also configured to perform roller crack prediction on the roller to be inspected based on the roller information and the target temperature information to obtain a roller crack prediction result. The target temperature information is selected from the roller temperature information based on the collection time corresponding to the roller temperature information and the offline speed of the roller to be inspected when it goes offline on the roller track.

[0062] Furthermore, the target temperature information is temperature information selected from the roller temperature information, the corresponding collection time of which matches the arrival time of the roller to be detected at the temperature detection area corresponding to the temperature detection device. The arrival time of the roller to be detected at the temperature detection area is determined by the offline speed of the roller to be detected in the roller track process and the temperature detection area corresponding to the temperature detection device.

[0063] In this way, it can be ensured that the deviation between the acquired target temperature information and the actual temperature value of the roller to be detected is smaller.

[0064] As an embodiment, the controller is further configured to perform roller crack prediction on the roller to be inspected based on the roller fusion feature to obtain a roller crack prediction result, wherein the roller fusion feature is obtained by fusing the roller temperature weighted feature and the roller usage weighted feature, the roller temperature weighted feature is obtained by weighting the first weight corresponding to the roller temperature feature and the roller temperature feature, the roller temperature feature is a feature extracted from the target temperature information, the roller usage weighted feature is obtained by weighting the second weight corresponding to the roller usage feature and the roller usage feature, and the roller usage feature is a feature extracted from the roller information.

[0065] Further, as an embodiment, the controller is configured to input the roller fusion features into a pre-trained second roller crack prediction model (by mapping the roller fusion features through the second roller crack prediction model) to obtain a roller crack prediction result, wherein the second roller crack prediction model is trained by a second preset sample, and the second preset sample is composed of roller fusion features of multiple second training rollers and real roller crack results corresponding to multiple first training rollers.

[0066] As another embodiment, the controller is configured to obtain a second roller crack table, wherein the second roller crack table is composed of the correspondence between the roller fusion characteristics of the roller and the roller crack results, and according to the roller fusion characteristics of the roller to be detected, the first roller crack table is queried to obtain the roller crack prediction result.

[0067] As an embodiment, the controller is also configured to generate a first weight corresponding to the roller temperature characteristic and a second weight corresponding to the roller usage characteristic based on the target temperature information and roller information of the roller to be inspected, respectively, wherein the higher the first importance of the roller crack prediction for the roller to be inspected represented by the target temperature information, the larger the first weight generated, and the higher the second importance of the roller crack prediction for the roller to be inspected represented by the roller information, the larger the second weight generated.

[0068] The higher the temperature value represented by the target temperature information is, the higher the first importance of the target temperature information for the roll crack prediction of the roll to be inspected is.

[0069] In this way, the higher the temperature value represented by the target temperature information, the higher the roller temperature of the roller to be detected, and the higher the risk of cracks in the roller to be detected. In this case, the higher the first importance is set, the larger the first weight generated is, and the higher the decision-making proportion of the roller temperature feature corresponding to the target temperature information participating in the roller crack prediction is, so the accuracy of the roller crack prediction is improved.

[0070] Among them, when the roll information includes the roll history processing information, the longer the use time of the roll to be detected represented by the roll history processing information, the lower the remaining service life of the roll to be detected, and the higher the risk of cracks in the roll to be detected. In this case, the higher the second importance is set, the larger the second weight generated is, and then the roll usage characteristics corresponding to the roll information participate in the decision-making proportion of roll crack prediction. Therefore, the accuracy of roll crack prediction is improved.

[0071] Furthermore, when the roller history processing information includes the number of times the roller has been online in history, the greater the number of times the roller has been online in history, the roller history processing information indicates that the roller to be detected has been used for a longer time; when the roller history processing information includes the amount of grinding and cutting in history, the greater the amount of grinding and cutting in history, the roller history processing information indicates that the roller to be detected has been used for a longer time; when the roller history processing information includes the length of time the roller has been online in history, the longer the length of time the roller has been online in history, the roller history processing information indicates that the roller to be detected has been used for a longer time.

[0072] In this way, a quantified method for the use time of the roller to be detected is provided, which ensures an accurate evaluation of the use time of the roller to be detected, thereby ensuring that the generated second weight is more accurate.

[0073] The roll crack prediction method provided in the embodiment of the present application can be applied to Figure 2 In the application environment shown. Among them, the terminal 202 communicates with the controller 106 through the network. The data storage system can store the data that the server 106 needs to process. The data storage system can be integrated on the controller 106, or it can be placed on the cloud or other network servers. The controller 106 communicates with the temperature detection device 102 through the network, and the controller 106 communicates with the roller identification unit 104 through the network. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The controller 106 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0074] In an exemplary embodiment, Figure 3 As shown, a roll crack prediction method is provided, which is applied to Figure 2The controller 106 in FIG. 1 is taken as an example to illustrate, and the following steps 302 to 304 are included. Among them:

[0075] Step 302, obtaining roller temperature information of the roller to be detected, and obtaining roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected.

[0076] Exemplarily, step 302 includes: acquiring roller temperature information of the roller to be detected obtained by the temperature detection device, and acquiring roller information of the roller to be detected obtained by the roller identification unit.

[0077] Step 304: predict the roll cracks of the roll to be inspected based on the roll temperature information and the roll information to obtain a roll crack prediction result.

[0078] As an embodiment, step 304 includes: obtaining the collection time corresponding to the roller temperature information and the line speed of the roller to be detected during the process of going offline on the roller track; selecting target temperature information from the roller temperature information according to the collection time corresponding to the roller temperature information and the line speed of the roller to be detected during the process of going offline on the roller track; and predicting roller cracks on the roller to be detected according to the target temperature information and the roller information to obtain a roller crack prediction result.

[0079] Furthermore, according to the collection time corresponding to the roller temperature information and the speed at which the roller to be detected goes off the roller track, target temperature information is selected from the roller temperature information, including: acquiring a temperature detection area corresponding to the temperature detection device; determining an arrival time of the roller to be detected at the temperature detection area corresponding to the temperature detection device according to the temperature detection area corresponding to the temperature detection device and the speed at which the roller to be detected goes off the roller track; and selecting temperature information from the roller temperature information whose corresponding collection time matches the arrival time corresponding to the roller to be detected.

[0080] As an embodiment, a roller crack prediction is performed on a roller to be inspected according to target temperature information and roller information to obtain a roller crack prediction result, including: extracting roller temperature characteristics from the target temperature information, and extracting roller usage characteristics from the roller information; weighting the roller temperature characteristics according to a first weight corresponding to the roller temperature characteristics to obtain a roller temperature weighted characteristic, and weighting the roller usage characteristics according to a second weight corresponding to the roller usage characteristics to obtain a roller usage weighted characteristic; fusing the roller usage weighted characteristic and the roller temperature weighted characteristic to obtain a roller fusion characteristic; and predicting roller cracks on the roller to be inspected according to the roller fusion characteristic to obtain a roller crack prediction result.

[0081] Furthermore, the method also includes: determining a first importance of the target temperature information for the prediction of roll cracks of the roll to be inspected based on the target temperature information, and determining a second importance of the roll information for the prediction of roll cracks of the roll to be inspected based on the roll information; generating a first weight based on the first importance, and generating a second weight based on the second importance.

[0082] In the above-mentioned roller crack prediction method, roller temperature information of the roller to be detected and roller information of the roller to be detected are obtained, wherein the roller information is used to characterize the use condition of the roller to be detected; roller crack prediction is performed on the roller to be detected based on the roller temperature information and the roller information to obtain a roller crack prediction result, and the roller temperature and the roller information that can characterize the use condition of the roller are used as the basis for crack prediction of the roller to be detected, thereby ensuring the accuracy of roller crack prediction, so that when cracks are detected in the roller to be detected, processing can be performed, thereby ensuring the safety of roller use.

[0083] As a detailed embodiment, roller temperature information of a roller to be detected is obtained, and roller information of the roller to be detected is obtained, wherein the roller information is used to characterize the use status of the roller to be detected; the collection time corresponding to the roller temperature information and the line speed of the roller to be detected during the process of going offline from the roller track are obtained; target temperature information is selected from the roller temperature information according to the collection time corresponding to the roller temperature information and the line speed of the roller to be detected during the process of going offline from the roller track; based on the target temperature information, a first importance of the target temperature information for roller crack prediction of the roller to be detected is determined, and based on the roller information, a second importance of the roller information for roller crack prediction of the roller to be detected is determined; a first weight is generated according to the first importance, and a second weight is generated according to the second importance.

[0084] Furthermore, a roller temperature feature is extracted from the target temperature information, and a roller usage feature is extracted from the roller information; the roller temperature feature is weighted according to a first weight corresponding to the roller temperature feature to obtain a roller temperature weighted feature, and the roller usage feature is weighted according to a second weight corresponding to the roller usage feature to obtain a roller usage weighted feature; the roller usage weighted feature and the roller temperature weighted feature are fused to obtain a roller fusion feature; based on the roller fusion feature, a roller crack prediction is performed on the roller to be inspected to obtain a roller crack prediction result.

[0085] In this way, by acquiring the roller temperature information of the roller to be detected, and acquiring the roller information of the roller to be detected, wherein the roller information is used to characterize the use condition of the roller to be detected; based on the roller temperature information and the roller information, a roller crack prediction is performed on the roller to be detected, and a roller crack prediction result is obtained. The roller temperature and the roller information that can characterize the use condition of the roller are used as the basis for crack prediction of the roller to be detected, thereby ensuring the accuracy of the roller crack prediction, so that when cracks are detected in the roller to be detected, processing can be performed, thereby ensuring the safety of the roller.

[0086] It should be understood that, although the steps in the flowcharts involved in the above 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 is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may 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 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.

[0087] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. 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 in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for predicting roll cracks is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0088] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0089] 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 steps in the above-mentioned method embodiments when executing the computer program.

[0090] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0091] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0092] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments 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 this 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.

[0093] 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.

[0094] The above 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 crack prediction system, characterized in that: The system includes a temperature detection device, a roll identification unit and a controller; The temperature detection device is configured to detect the temperature information of the roller when the roller to be detected is off the production line; The roller identification unit is configured to identify roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected; The controller is configured to perform roll crack prediction on the roll to be inspected according to the roll temperature information and the roll information to obtain a roll crack prediction result.

2. The system according to claim 1, characterized in that When the roller to be inspected rolls off the roller track, the temperature detection device is placed in the side area of ​​the roller track; when the roller to be inspected rolls off the transport vehicle, the temperature detection device is placed in the transport unloading area corresponding to the roller to be inspected.

3. The system according to claim 2, characterized in that When the roller to be detected goes offline on the roller track, the controller is also configured to perform roller crack prediction on the roller to be detected based on the roller information and target temperature information to obtain a roller crack prediction result. The target temperature information is selected from the roller temperature information based on the collection time corresponding to the roller temperature information and the offline speed of the roller to be detected during the process of going offline on the roller track.

4. The system according to claim 3, characterized in that The controller is also configured to perform roller crack prediction on the roller to be detected based on the roller fusion feature to obtain a roller crack prediction result, wherein the roller fusion feature is obtained by fusing the roller temperature weighted feature and the roller usage weighted feature, the roller temperature weighted feature is obtained by weighting the first weight corresponding to the roller temperature feature and the roller temperature feature, the roller temperature feature is a feature extracted from the target temperature information, the roller usage weighted feature is obtained by weighting the second weight corresponding to the roller usage feature and the roller usage feature, and the roller usage feature is a feature extracted from the roller information.

5. The system according to claim 4, characterized in that The controller is also configured to generate a first weight corresponding to the roller temperature characteristic and a second weight corresponding to the roller usage characteristic according to the target temperature information and roller information of the roller to be inspected, respectively, wherein the higher the first importance of the roller crack prediction for the roller to be inspected represented by the target temperature information, the larger the first weight generated, and the higher the second importance of the roller crack prediction for the roller to be inspected represented by the roller information, the larger the second weight generated.

6. The system according to any one of claims 1 to 5, characterized in that When the environmental visibility of the detection environment corresponding to the roller to be detected meets the preset visibility condition, the temperature detection device is a remote temperature detection device; when the environmental visibility of the detection environment corresponding to the roller to be detected does not meet the preset visibility condition, the temperature detection device is a contact temperature detection device.

7. A method for predicting roll cracks, characterized in that: Applied to the controller according to any one of claims 1 to 6, the method comprises: Acquiring roller temperature information of the roller to be detected, and acquiring roller information of the roller to be detected, wherein the roller information is used to characterize the use status of the roller to be detected; According to the roll temperature information and the roll information, a roll crack prediction is performed on the roll to be inspected to obtain a roll crack prediction result.

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 claim 7 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 claim 7 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 claim 7 are implemented.

Images