Monitoring and processing method and device for cold-rolling mill gearbox, medium and equipment
By combining a recurrent neural network model with multiple data to monitor abnormalities in the cold rolling mill gearbox, the problem of difficulty in detecting early faults in existing technologies is solved, and accurate identification and timely processing of faults are achieved, ensuring stable production.
Patent Information
- Application Number
- CN202510686020.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-27
- Publication Date
- 2025-09-12
AI Technical Summary
Existing technologies make it difficult to detect early abnormalities in the gearbox of a cold rolling mill under complex working conditions through vibration data monitoring, resulting in difficulty in timely detection of faults and affecting normal production.
A recurrent neural network model is used to train the abnormal fault mapping relationship. Combining vibration data, temperature data, motor current data and strip shape data, through multiple data fusion and normalization processing, the cold rolling mill gearbox fault type can be accurately identified, and a control strategy can be formulated according to the fault type.
The accuracy of cold rolling mill gearbox fault identification is improved, early abnormalities are discovered in time, equipment accidents are avoided, and production stability is ensured.
Smart Images
Figure CN120628503A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of cold rolling mills, and in particular, to a method, device, medium, and equipment for monitoring and processing a gearbox of a cold rolling mill. Background Art
[0002] The cold rolling mill is the main equipment for strip steel production, including the cold rolling mill gearbox and rolling rollers. The cold rolling mill gearbox transmits the motor power to the rolling rollers through multiple stages, and continuously works in harsh operating environments such as heavy loads, alternating load impacts, high speeds, and high temperatures. It is subject to vibration impacts caused by load disturbances such as starting, speed changes, steel biting, and steel throwing. The rolling process is relatively complex and changeable, making the cold rolling mill gearbox prone to failure and even causing major accidents that affect normal production.
[0003] At present, abnormal conditions of cold rolling mill gearboxes are mainly monitored through vibration data, which makes it difficult to detect early abnormal conditions under complex working conditions. Summary of the Invention
[0004] The embodiments of the present application provide a method, device, medium, and equipment for monitoring and processing a cold rolling mill gearbox, which are used to solve the technical problem that it is difficult to detect early abnormal conditions under complex working conditions when monitoring abnormal conditions of the cold rolling mill gearbox through vibration data.
[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.
[0006] According to a first aspect of the present application, a method for monitoring a gearbox of a cold rolling mill is provided, the method comprising:
[0007] Acquiring first abnormality monitoring data of the cold rolling mill gearbox;
[0008] Based on a pre-established abnormal fault mapping relationship, the first fault type of the cold rolling mill gearbox is obtained according to the first abnormal monitoring data. The abnormal fault mapping relationship includes: multiple groups of abnormal monitoring data and the fault type corresponding to each group of abnormal monitoring data. Each group of abnormal monitoring data includes vibration data, temperature data, motor current data, cold rolling mill rolling force data and strip shape data. The motor current data is the current data of the motor connected to the cold rolling mill gearbox.
[0009] In some embodiments, based on the above solution, the method further includes:
[0010] Obtain historical abnormal monitoring data and historical fault type data corresponding to the historical abnormal monitoring data;
[0011] The abnormal fault mapping relationship is obtained according to the historical abnormal monitoring data and the historical fault type data.
[0012] In some embodiments, based on the aforementioned solution, obtaining the abnormal fault mapping relationship according to the historical abnormal monitoring data and the historical fault type data includes:
[0013] The historical abnormal monitoring data is used as an input vector and the historical fault type data is used as an output label to train a recurrent neural network model to characterize the abnormal fault mapping relationship through the input and output of the recurrent neural network model.
[0014] In some embodiments, based on the above solution, the historical abnormal monitoring data includes historical strip steel shape data, and the historical strip steel shape data is historical strip steel shape asymmetry, and the historical strip steel shape asymmetry is obtained by the following formula:
[0015] Where I is the historical strip shape asymmetry, x is the coordinate in the strip width direction, σ1(x) is the flatness stress with the coordinate in the strip width direction of [0, B / 2], σ2(-x) is the flatness stress with the coordinate in the strip width direction of [-B / 2, 0], the coordinate in the middle position in the strip width direction is 0, the coordinate at one end is -B / 2, and the coordinate at the other end is B / 2,
[0016] In some embodiments, based on the above solution, the historical abnormality monitoring data includes historical vibration data, and the historical vibration data is amplitude. The historical amplitude is obtained by the following formula:
[0017] Among them, E t is the historical amplitude at time t, N is the number of sampling points from time t-t0 to time t, and v(j) is the amplitude of the jth sampling point between time t-t0 and time t.
[0018] In some embodiments, based on the above solution, the historical abnormality monitoring data is obtained in the following manner:
[0019] Acquire historical original monitoring data, wherein the historical original monitoring data includes multiple types of original data, each of which includes a timestamp;
[0020] aligning the timestamps of the plurality of raw data so that the plurality of raw data form unified time series data;
[0021] The multiple raw data are normalized and fused to obtain the historical abnormality monitoring data.
[0022] According to a second aspect of the present application, a method for processing a gearbox of a cold rolling mill is provided, wherein the first fault type is obtained according to the method described in any embodiment of the first aspect of the present application;
[0023] Based on a pre-established fault processing mapping relationship, a first control strategy is obtained according to the first fault type, wherein the fault processing mapping relationship includes: multiple fault types and control strategies corresponding to each fault type, where the multiple fault types are normal, low-probability abnormal, and high-probability abnormal;
[0024] The cold rolling mill is controlled according to the first control strategy.
[0025] According to a third aspect of the present application, a monitoring device for a gearbox of a cold rolling mill is provided, the device comprising:
[0026] a first acquiring unit, for acquiring first abnormality monitoring data of the gearbox of the cold rolling mill;
[0027] The first obtaining unit obtains the first fault type of the cold rolling mill gearbox based on the pre-established abnormal fault mapping relationship and the first abnormal monitoring data, wherein the abnormal fault mapping relationship includes: multiple groups of abnormal monitoring data and the fault type corresponding to each group of abnormal monitoring data, each group of abnormal monitoring data includes vibration data, temperature data, motor current data, cold rolling mill rolling force data and strip shape data, and the motor current data is the current data of the motor connected to the cold rolling mill gearbox.
[0028] According to the fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. The computer program includes executable instructions. When the executable instructions are executed by a processor, the method described in any embodiment of the first aspect of the present application is implemented.
[0029] According to the fifth aspect of the present application, an electronic device is provided, comprising: one or more processors; and a memory for storing executable instructions of the processors, wherein when the executable instructions are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the first aspect of the present application.
[0030] The beneficial effects of this application are as follows:
[0031] Based on the abnormal fault mapping relationship, the first fault type corresponding to the first abnormal monitoring data is obtained according to the first abnormal monitoring data. The first abnormal monitoring data includes multiple data, and the accuracy of determining the fault is high, which can timely discover the early abnormality of the cold rolling mill gearbox.
[0032] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, explaining the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:
[0034] Figure 1 A flow chart showing a method for monitoring a gearbox of a cold rolling mill according to an embodiment of the present application is shown;
[0035] Figure 2 A block diagram of a monitoring device for a cold rolling mill gearbox according to an embodiment of the present application is shown;
[0036] Figure 3 A schematic diagram showing a computer-readable storage medium in an embodiment of the present application is shown;
[0037] Figure 4 A schematic diagram showing the system structure of an electronic device in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0038] Figure 1 A flow chart showing a method for monitoring a gearbox of a cold rolling mill according to an embodiment of the present application is shown. Figure 1 , provides a cold rolling mill gearbox monitoring method, including at least S1 to S2, which are detailed as follows:
[0039] In step S1, first abnormality monitoring data of the cold rolling mill gearbox is acquired.
[0040] In step S2, based on a pre-established abnormal fault mapping relationship, a first fault type of the cold rolling mill gearbox is obtained according to the first abnormal monitoring data. The abnormal fault mapping relationship includes: multiple sets of abnormal monitoring data and the fault type corresponding to each set of abnormal monitoring data. Each set of abnormal monitoring data includes vibration data, temperature data, motor current data, cold rolling mill rolling force data, and strip shape data. The motor current data is the current data of the motor connected to the cold rolling mill gearbox. The first abnormal monitoring data includes first vibration data, first temperature data, first motor current data, first cold rolling mill rolling force data, and first strip shape data.
[0041] It should be noted that the failure rate of cold rolling mill gearboxes is relatively high, accounting for more than 35% of mechanical failures, and the maintenance cost is high, which restricts the performance improvement of cold rolling mills. In actual production, the flatness quality of the hot-rolled incoming material, the operating status of the cold-rolling mill, and the status of the cold-rolling mill motor affect the cold-rolling mill gearbox. When the flatness quality of the hot-rolled incoming material is poor, especially when it has asymmetric defects such as edge waves, buckling, and uneven crown, it can easily lead to uneven rolling force distribution during cold-rolling production, thereby affecting the stability of the cold-rolling mill transmission equipment and inducing abnormal vibration of the cold-rolling mill gearbox. Furthermore, it causes rolling force fluctuations during cold-rolling production, increasing the load on the transmission motor and the cold-rolling mill gearbox, which can also cause abnormal vibration of the cold-rolling mill gearbox. If the fluctuation is large, the cold-rolling mill gearbox has to bear greater dynamic loads, which will aggravate gear wear or vibration of the cold-rolling mill gearbox. Therefore, vibration data is used to characterize the vibration of the cold-rolling mill gearbox, temperature data is used to characterize the temperature rise of the cold-rolling mill gearbox, motor current data is used as characterization data of the cold-rolling mill motor status, cold-rolling mill rolling force data is used to reflect the operating status of the cold-rolling mill, and strip flatness data is used to characterize the flatness quality of the hot-rolled incoming material.
[0042] In this way, the fault type can be determined through a variety of data, and even if the cold rolling mill gearbox is in an abnormal state in the early stage, it can be discovered in time.
[0043] In some embodiments, obtaining the first abnormal monitoring data of the cold rolling mill gearbox includes: obtaining the first temperature data and the first vibration data through a temperature sensor and a vibration sensor provided in the cold rolling mill gearbox, using a flatness meter to detect the flatness of the strip after rolling in the cold rolling mill to obtain flatness data, and using the control system of the cold rolling mill to obtain first motor current data and first cold rolling mill rolling force data.
[0044] It should be noted that the motor connected to the gearbox of the cold rolling mill transmits power to the upper working roll and the lower working roll of the cold rolling mill through the gearbox of the cold rolling mill, and a roll gap for rolling the strip is formed between the upper working roll and the lower working roll.
[0045] In some embodiments, the method further includes: obtaining historical abnormal monitoring data and historical fault type data corresponding to the historical abnormal monitoring data; and obtaining the abnormal fault mapping relationship based on the historical abnormal monitoring data and the historical fault type data. The historical abnormal monitoring data includes historical vibration data, historical temperature data, historical motor current data, historical cold rolling mill rolling force data, and historical strip shape data.
[0046] In some embodiments, obtaining the abnormal fault mapping relationship based on the historical abnormal monitoring data and the historical fault type data includes: using the historical abnormal monitoring data as an input vector and the historical fault type data as an output label, and training a recurrent neural network model to characterize the abnormal fault mapping relationship through the input and output of the recurrent neural network model.
[0047] In some embodiments, when training a recurrent neural network model, the method further includes: dividing 75% of the historical anomaly monitoring data as a training data set and 25% as a test data set; using an Adam (Adaptive Moment Estimation) optimizer as a model optimizer and a binary cross entropy loss function as a loss function.
[0048] In some embodiments, the loss function is expressed as follows: Among them, Loss is the loss function, N is the number of samples, Y i is the true fault type of the i-th sample, is the predicted fault type of the i-th sample.
[0049] In some embodiments, the recurrent neural network model is a long short-term memory network model, and the method further includes: constructing the long short-term memory network model.
[0050] In some embodiments, the long short-term memory network model includes an input layer, an LSTM (Long Short-Term Memory) layer, a fully connected layer, and an output layer. The input layer receives an input vector, the LSTM layer captures long-term dependencies in the time series, the fully connected layer maps the LSTM layer to a fault type, and the output layer outputs the fault type of the cold rolling mill gearbox. The fault type can also be a fault probability.
[0051] In some embodiments, based on the above solution, the historical abnormal monitoring data includes historical strip steel shape data, and the historical strip steel shape data is historical strip steel shape asymmetry, and the historical strip steel shape asymmetry is obtained by the following formula: Where I is the historical strip shape asymmetry, x is the coordinate in the strip width direction, σ1(x) is the flatness stress with the coordinate in the strip width direction of [0, B / 2], σ2(-x) is the flatness stress with the coordinate in the strip width direction of [-B / 2, 0], the coordinate in the middle position in the strip width direction is 0, the coordinate at one end is -B / 2, and the coordinate at the other end is B / 2,
[0052] It should be noted that when the strip is completely symmetrical, f(x) is 0, I=0; when the strip is completely asymmetrical, f(x) is |σ1(x)|+|σ2(-x)|, I=1. It can be seen that the historical strip shape asymmetry is between 0 and 1.
[0053] In some embodiments, the historical abnormality monitoring data includes historical vibration data, and the historical vibration data is amplitude. The historical amplitude is obtained by the following formula: Among them, E t is the historical amplitude at time t, N is the number of sampling points from time t-t0 to time t, and v(j) is the amplitude of the jth sampling point between time t-t0 and time t. t0 can be a unit of time, such as 1s.
[0054] In some embodiments, the historical abnormality monitoring data is obtained by: obtaining historical original monitoring data, the historical original monitoring data including multiple original data, each of the original data including a timestamp; aligning the timestamps of the multiple original data so that the multiple original data form a unified time series data; normalizing and fusing the multiple original data to obtain the historical abnormality monitoring data.
[0055] In some embodiments, the various raw data are normalized using the following formula: For X t (k) After normalization, X t (k) is the value of the kth original data at time t, is the maximum value of the kth original data, is the minimum value of the k-th original data. The k-th original data can also be understood as the k-th feature.
[0056] In some embodiments, multiple raw data are spliced together to obtain a high-dimensional feature vector, i.e., F t =[I t ,E t ,T t ,C t ,P t ], where F t is the high-dimensional feature vector at time t, I t is the historical strip shape asymmetry at time t, E t is the historical amplitude at time t, T t is the historical temperature at time t, C t is the historical motor current at time t, P t is the historical rolling force of the cold rolling mill at time t.
[0057] In some embodiments, after determining the first fault type of the cold rolling mill gearbox based on the first abnormality monitoring data, the method further includes: determining a first display color based on the first fault type based on a pre-established fault display mapping relationship, wherein the fault display mapping relationship includes multiple fault types and corresponding display colors for each fault type; and controlling a target human-machine interface to display the first display color. An operator can observe the display color of the target human-machine interface to determine the fault type, thereby facilitating timely resolution.
[0058] In some implementations, when the fault type is normal, the display color is green; when the fault type is a low probability abnormality, the display color is yellow; when the fault type is a high probability abnormality, the display color is red.
[0059] According to a second aspect of the present application, a method for processing a gearbox of a cold rolling mill is provided, wherein the first fault type is obtained according to the method described in any embodiment of the first aspect of the present application;
[0060] Based on a pre-established fault processing mapping relationship, a first control strategy is obtained according to the first fault type, wherein the fault processing mapping relationship includes: multiple fault types and control strategies corresponding to each fault type, where the multiple fault types are normal, low-probability abnormal, and high-probability abnormal;
[0061] The cold rolling mill is controlled according to the first control strategy.
[0062] In some embodiments, when the fault type is normal, the control strategy remains unchanged; when the fault type is a low-probability abnormality, the control strategy is to reduce the cold rolling mill speed by a first percentage and issue an alarm; when the fault type is a high-probability abnormality, the control strategy is to reduce the cold rolling mill speed by a second percentage and issue an alarm, where the second percentage is greater than the first percentage. The first percentage may be 10%, and the second percentage may be 30%.
[0063] It should be noted that controlling the cold rolling mill according to the first control strategy can be understood as automatically controlling the cold rolling mill. During manual control, when the fault type is a low-probability or high-probability abnormality, the operator is notified to handle it by himself, such as controlling the cold rolling mill to slow down or stop.
[0064] In the present application, based on the abnormal fault mapping relationship, according to the first abnormal monitoring data, the first fault type corresponding to the first abnormal monitoring data is obtained. The first abnormal monitoring data includes multiple data, and the accuracy of determining the fault is high. The early abnormal conditions of the cold rolling mill gearbox can be discovered in time, so that the faults of the cold rolling mill gearbox can be monitored and early-warned in time to avoid equipment accidents of the cold rolling mill gearbox. Human-computer interaction can be realized through the target human-computer interface, and the status of the cold rolling mill gearbox can be monitored conveniently and efficiently, and problems can be solved in time to ensure the normal production of the cold rolling mill.
[0065] Figure 2 A block diagram of a monitoring device for a cold rolling mill gearbox according to an embodiment of the present application is shown. Figure 2 According to a third aspect of the present application, a monitoring device 100 for a cold rolling mill gearbox is provided, the device comprising:
[0066] A first acquiring unit 101 acquires first abnormality monitoring data of the gearbox of the cold rolling mill;
[0067] The first obtaining unit 102 obtains the first fault type of the cold rolling mill gearbox based on the pre-established abnormal fault mapping relationship and the first abnormal monitoring data, wherein the abnormal fault mapping relationship includes: multiple groups of abnormal monitoring data and the fault type corresponding to each group of abnormal monitoring data, each group of abnormal monitoring data includes vibration data, temperature data, motor current data, cold rolling mill rolling force data and strip shape data, and the motor current data is the current data of the motor connected to the cold rolling mill gearbox.
[0068] Based on the same inventive concept, as a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored. The computer program includes executable instructions. When the executable instructions are executed by a processor, the method described in any embodiment of the first aspect of the present application is implemented.
[0069] In some possible implementations, various aspects of the present application may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary implementations of the present application described in the above "Exemplary Method" section of this specification.
[0070] refer to Figure 3As shown, a program product 200 for implementing the above method according to an embodiment of the present application is described. The program product 200 may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0071] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
[0072] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0073] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0074] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0075] As another aspect, the present application also provides an electronic device capable of implementing the above method.
[0076] Those skilled in the art will appreciate that various aspects of the present application can be implemented as systems, methods, or program products. Therefore, various aspects of the present application can be specifically implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation that combines hardware and software aspects, which may be collectively referred to herein as a "circuit," "module," or "system."
[0077] Refer to the following Figure 4 hereinafter, an electronic device 300 according to this embodiment of the present application is described. Figure 4 The electronic device 300 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.
[0078] like Figure 4 As shown, electronic device 300 is implemented as a general-purpose computing device. Components of electronic device 300 may include, but are not limited to, the aforementioned at least one processing unit 310, the aforementioned at least one storage unit 320, and a bus 330 connecting various system components (including storage unit 320 and processing unit 310).
[0079] The storage unit stores program code, which can be executed by the processing unit 310, so that the processing unit 310 performs the steps described in the above "Example Method" section of this specification according to various exemplary embodiments of the present application.
[0080] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 321 and / or a cache memory unit 322 , and may further include a read-only memory unit (ROM) 323 .
[0081] The storage unit 320 may also include a program / utility 324 having a set (at least one) of program modules 325, such program modules 325 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0082] Bus 330 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0083] The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 300, and / or any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. Figure 4 As shown, the network adapter 360 communicates with other modules of the electronic device 300 via the bus 330. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0084] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, the functional units may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.
[0085] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of the claims of the present application.
Claims
1. A method for monitoring a gearbox of a cold rolling mill, characterized in that: The method comprises: Acquiring first abnormality monitoring data of the cold rolling mill gearbox; Based on a pre-established abnormal fault mapping relationship, the first fault type of the cold rolling mill gearbox is obtained according to the first abnormal monitoring data. The abnormal fault mapping relationship includes: multiple groups of abnormal monitoring data and the fault type corresponding to each group of abnormal monitoring data. Each group of abnormal monitoring data includes vibration data, temperature data, motor current data, cold rolling mill rolling force data and strip shape data. The motor current data is the current data of the motor connected to the cold rolling mill gearbox.
2. A method for monitoring a gearbox of a cold rolling mill according to claim 1, characterized in that: The method further comprises: Obtain historical abnormal monitoring data and historical fault type data corresponding to the historical abnormal monitoring data; The abnormal fault mapping relationship is obtained according to the historical abnormal monitoring data and the historical fault type data.
3. The method for monitoring a gearbox of a cold rolling mill according to claim 2, characterized in that: The obtaining of the abnormal fault mapping relationship according to the historical abnormal monitoring data and the historical fault type data includes: The historical abnormal monitoring data is used as an input vector and the historical fault type data is used as an output label to train a recurrent neural network model to characterize the abnormal fault mapping relationship through the input and output of the recurrent neural network model.
4. The method for monitoring a gearbox of a cold rolling mill according to claim 2, wherein: The historical abnormal monitoring data includes historical strip steel shape data, and the historical strip steel shape data is historical strip steel shape asymmetry, which is obtained by the following formula: Where I is the historical strip shape asymmetry, x is the coordinate in the strip width direction, σ1(x) is the flatness stress with the coordinate in the strip width direction of [0, B / 2], σ2(-x) is the flatness stress with the coordinate in the strip width direction of [-B / 2, 0], the coordinate in the middle position in the strip width direction is 0, the coordinate at one end is -B / 2, and the coordinate at the other end is B / 2, 5. The method for monitoring a gearbox of a cold rolling mill according to claim 2, wherein: The historical abnormality monitoring data includes historical vibration data, and the historical vibration data is amplitude. The historical amplitude is obtained by the following formula: Among them, E t is the historical amplitude at time t, N is the number of sampling points from time t-t0 to time t, and v(j) is the amplitude of the jth sampling point between time t-t0 and time t.
6. The method for monitoring a gearbox of a cold rolling mill according to claim 2, characterized in that: The historical abnormal monitoring data is obtained in the following manner: Acquire historical original monitoring data, wherein the historical original monitoring data includes multiple types of original data, each of which includes a timestamp; aligning the timestamps of the plurality of raw data so that the plurality of raw data form unified time series data; The multiple raw data are normalized and fused to obtain the historical abnormality monitoring data.
7. A method for processing a gearbox of a cold rolling mill, characterized in that: According to the method according to any one of claims 1 to 6, obtaining the first fault type; Based on a pre-established fault processing mapping relationship, a first control strategy is obtained according to the first fault type, wherein the fault processing mapping relationship includes: multiple fault types and control strategies corresponding to each fault type, where the multiple fault types are normal, low-probability abnormal, and high-probability abnormal; The cold rolling mill is controlled according to the first control strategy.
8. A monitoring device for a cold rolling mill gearbox, characterized in that: The device comprises: a first acquiring unit, for acquiring first abnormality monitoring data of the gearbox of the cold rolling mill; The first obtaining unit obtains the first fault type of the cold rolling mill gearbox based on the pre-established abnormal fault mapping relationship and the first abnormal monitoring data, wherein the abnormal fault mapping relationship includes: multiple groups of abnormal monitoring data and the fault type corresponding to each group of abnormal monitoring data, each group of abnormal monitoring data includes vibration data, temperature data, motor current data, cold rolling mill rolling force data and strip shape data, and the motor current data is the current data of the motor connected to the cold rolling mill gearbox.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program includes executable instructions, and when the executable instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.
10. An electronic device, characterized in that: include: one or more processors; A memory for storing executable instructions of the processor, wherein when the executable instructions are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.