Methods and systems for online monitoring and early warning of roller bearing temperatures in the dry press section of the acid washing technology.

Abstract

This invention proposes a method and system for online monitoring and early warning of the temperature of dry press roller bearing sections in acid washing technology, where the method includes: collecting aggregated data on the temperature and vibration of the bearing from wireless temperature and vibration sensors via Ethernet; processing the aggregated data to form a data model, and after training, obtaining a model to predict the bearing temperature; inputting real-time temperature and vibration data of the bearing into the bearing temperature prediction model, outputting the predicted bearing temperature within a certain future time window; and obtaining future early warning recommendations based on the early warning level and predicted bearing temperature.Wireless communication with temperature and vibration sensors is conducted via a wireless smart gateway, obtaining vibration and temperature data, reducing the difficulty of wiring layout, and facilitating improvement and implementation; through a trained bearing temperature prediction model, the bearing temperature within a certain time window in the future can be predicted in advance, providing data support for the operation and maintenance of the drying roller equipment, preventing malfunctions.

Description

An online monitoring and early warning method and system for the temperature of the squeeze roller bearing in the pickling process Technical Field

[0001] The present disclosure relates to the technical field of cold rolling processing lines, and in particular to an online monitoring and early warning method and system for the temperature of a squeeze roller bearing in a pickling process section. Background Art

[0002] The pickling process section mainly includes a pickling tank and a rinsing tank. The acid in the pickling tank reacts chemically with the iron oxide scale on the surface of the strip to remove the iron oxide scale. The rinsing tank cleans the residual pickling on the surface of the strip coming out of the pickling tank.

[0003] The pickling tank and rinsing tank are generally made of PPH or steel-lined rubber material, which is flammable. Squeezing rollers are installed at the acid tank inlet, outlet and between each acid tank to minimize the amount of acid brought out by the strip. Squeezing rollers are installed between each section of the rinsing tank to minimize the amount of rinsing water brought out by the strip.

[0004] During the pickling process, due to abnormal operation of the squeeze roller, the temperature of the squeeze roller bearing and bearing seat continued to rise, which eventually led to the pickling tank and rinsing tank catching fire, causing serious damage to the pickling tank and rinsing tank, and the unit stopped production, resulting in heavy losses.

[0005] Summary of the Invention

[0006] The present disclosure aims to solve at least one of the technical problems existing in the prior art, and proposes an online monitoring and early warning method and system for the temperature of a squeeze roller bearing in a pickling process.

[0007] In a first aspect, the present disclosure provides an online monitoring and early warning method for the bearing temperature of a squeeze roller in a pickling process, comprising:

[0008] Obtain comprehensive data on bearing seat temperature and vibration from wireless temperature and vibration sensors via Ethernet;

[0009] The comprehensive data is processed to form sample data and trained to obtain a bearing temperature prediction model;

[0010] Inputting real-time data of bearing seat temperature and vibration into the bearing temperature prediction model, and outputting the predicted bearing temperature within a certain time window in the future;

[0011] Future warning recommendations are obtained based on the warning level and the predicted bearing temperature.

[0012] Preferably, the processing of the comprehensive data to form sample data and training to obtain a bearing temperature prediction model specifically includes:

[0013] Process the comprehensive data of bearing seat temperature and vibration to form sample data;

[0014] Based on the sample data, select DeepAR, Informer, LSTNet, MLP, NBEATS, NHiTS, RNN, SCINet, TCN, TFT, or Transformer model for training and verification until the prediction deviation of the bearing temperature prediction model is controlled within the allowable range.

[0015] Preferably, the bearing seat temperature is the target to be predicted, the strip grade, strip width, strip thickness, strip speed and bearing seat vibration are covariates, and the data is divided into training data, verification data and test data sets.

[0016] Preferably, the ratio of the training data, validation data and test data set is 7:2:1.

[0017] Preferably, the LSTNet model is selected for training and verification based on the sample data, specifically including:

[0018] First, use PaddleTS to build a model network, predefine the time series length of the model input, the time series length of the model output, the loss function, the optimization algorithm, the optimizer parameters, and the maximum number of training rounds;

[0019] Use lstm.fit(train_dataset,val_dataset) to train and validate the model on the sample data, where train_dataset is the training data set and val_dataset is the validation data set;

[0020] During and after the training, MAE (Mean Absolute Error) and MSE (Mean Squared Error) are used to evaluate the model prediction effect. When the effect reaches the preset value, the bearing temperature prediction model is obtained.

[0021] Preferably, after the training process is completed, LSTM is used to save the trained bearing temperature prediction model.

[0022] Preferably, the obtaining of comprehensive data on bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet specifically includes: continuously collecting comprehensive data on bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet; storing the sample data in a bearing temperature monitoring and early warning server and visually displaying it on a display of the bearing temperature monitoring and early warning server.

[0023] Preferably, the warning levels include: suggestion to pay attention to operation, suggestion to conduct necessary inspections at an appropriate time, suggestion to perform maintenance during a planned shutdown in the near future, and suggestion to take maintenance measures as soon as possible.

[0024] In a second aspect, the present disclosure provides an online monitoring and early warning system for the temperature of a squeeze roller bearing in a pickling process section. The system can be used to implement an online monitoring and early warning method for the temperature of a squeeze roller bearing in a pickling process section. The system includes:

[0025] A data acquisition module is configured to acquire comprehensive data of bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet;

[0026] A model training module is configured to process the comprehensive data to form sample data and obtain a bearing temperature prediction model after training;

[0027] a prediction module configured to input real-time data of bearing seat temperature and vibration into the bearing temperature prediction model and output a predicted bearing temperature within a certain future time window;

[0028] The early warning module is configured to obtain future early warning suggestions based on the early warning level and the predicted bearing temperature.

[0029] In a third aspect, the present disclosure provides an electronic device, comprising:

[0030] one or more processors;

[0031] a memory for storing one or more programs;

[0032] When the one or more programs are executed by the one or more processors, the one or more processors implement an online monitoring and early warning method for the bearing temperature of a squeeze roller in a pickling process section. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] FIG1 is a flow chart of an online monitoring and early warning method for the bearing temperature of a squeeze roller in a pickling process section provided by an embodiment of the present disclosure;

[0034] FIG2 is a diagram showing the composition of an online monitoring and early warning system for the bearing temperature of a squeeze roller in a pickling process section according to an embodiment of the present disclosure;

[0035] FIG3 is a flow chart of a bearing temperature prediction model training according to an embodiment of the present disclosure;

[0036] FIG4 is a structural block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the present disclosure is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] Unless otherwise defined, the technical or scientific terms used in this disclosure should have the usual meanings understood by people with ordinary skills in the field to which this disclosure belongs. The words "first", "second" and similar terms used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "an" or "the" are not limited to quantity, but rather to the presence of at least one. Words such as "include" or "comprise" mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used for relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0039] In each accompanying drawing, identical elements are represented by similar reference numerals. For the sake of clarity, the various parts in the accompanying drawings are not all drawn to scale. In addition, some well-known parts may not be shown in the drawings.

[0040] Many specific details of the present disclosure are described below, such as component structures, materials, dimensions, processing techniques, and technologies, to provide a clearer understanding of the present disclosure. However, as will be appreciated by those skilled in the art, the present disclosure may be implemented without following these specific details.

[0041] As shown in FIG1 to FIG3, the embodiment of the present disclosure provides an online monitoring and early warning method for the bearing temperature of a squeeze roller in a pickling process, comprising the following steps:

[0042] S1, obtains comprehensive data of bearing seat temperature and vibration from wireless temperature and vibration sensors via Ethernet;

[0043] S2, processing the comprehensive data to form sample data and training it to obtain a bearing temperature prediction model;

[0044] S3, inputting the real-time data of the bearing seat temperature and vibration into the bearing temperature prediction model, and outputting the predicted bearing temperature within a certain time window in the future;

[0045] S4, obtaining future warning suggestions based on the warning level and the predicted bearing temperature.

[0046] It should be noted that the order of the above steps can be arbitrarily disrupted and is not limited by the present disclosure.

[0047] In a specific implementation scenario, implementing the above method requires building an online monitoring and early warning system for the squeeze roller bearing temperature in the pickling process. This system consists of a squeeze roller bearing seat C1, a wireless temperature and vibration sensor C2, a wireless intelligent gateway C3, an Ethernet network C4, a bearing temperature monitoring and early warning server C5, and a temperature monitoring and early warning module C6. The wireless temperature and vibration sensor C2 is attached to the squeeze roller bearing seat using a bonding / welding base or adapter bolts. The wireless intelligent gateway C3 wirelessly collects temperature and vibration data from the wireless temperature and vibration sensor C2 and transmits this data to the bearing temperature monitoring and early warning server via Ethernet C4. The temperature monitoring and early warning module C6 monitors the squeeze roller bearing temperature and issues early warnings.

[0048] During the production process, the temperature monitoring and early warning module C6 operates. This module primarily consists of a data acquisition and visualization module and a bearing temperature prediction and training module. The data acquisition and visualization module continuously collects comprehensive data on bearing seat temperature and vibration from wireless temperature and vibration sensors C2 via Ethernet C4. This sample data is stored on the hard drive of the bearing temperature monitoring and early warning server C5 and visualized on the display of the server. The visualized information includes the squeeze roller bearing seat number, real-time vibration temperature parameters, and operational statistics. The bearing temperature prediction and training module process is shown in Figure 3. The comprehensive data on bearing seat temperature and vibration is processed to generate sample data, with bearing seat temperature as the target to be predicted and strip grade, strip width, strip thickness, strip speed, and bearing seat vibration as covariates. The data is then divided into training, validation, and test data. Based on this sample data, a DeepAR, Informer, LSTNet, MLP, NBEATS, NHiTS, RNN, SCINet, TCN, TFT, or Transformer model is selected for training and validation until the bearing temperature prediction model's prediction error remains within an acceptable range.

[0049] Take LSTNet as an example:

[0050] First, use PaddleTS (a time series modeling Python library based on Baidu's deep learning framework PaddlePaddle) to build a model network. The main parameters are predefined, such as in_chuck_len (time series length of model input), out_chunk_len (time series length of model output), loss_fn (loss function), optimizer_fn (optimization algorithm), optimizer_paras (optimizer parameters) and max_epochs (maximum number of training rounds). After the model parameters are predefined, use lstm.fit(train_dataset,val_dataset) to train and verify the model using the dataset, where train_dataset is the training dataset and val_dataset is the verification dataset. During and after training, MAE (Mean Absolute Error) and MSE (Mean Squared Error) are used to evaluate the prediction effect of the hydrogen concentration prediction model. The smaller the MAE and MSE, the better the training effect. After training, the bearing temperature prediction model is obtained. Use lstm(lstm.save)("lstm") to save the trained model. It can be used by the bearing temperature online warning module to predict the bearing temperature within a certain time window in the future.

[0051] The temperature monitoring and early warning module collects real-time bearing seat vibration and temperature data. When these data exceed thresholds, it issues an alarm. It also uses a trained bearing temperature prediction model to predict bearing seat temperatures within a specific time window. Four early warning levels are provided: recommending operational attention, recommending necessary inspections at an appropriate time, recommending planned downtime for maintenance in the near future, and recommending immediate maintenance measures. This prevents tank fires caused by abnormal squeeze roller bearing temperatures.

[0052] The data acquisition and visualization module continuously collects data, collecting the vibration and temperature data of bearing seats of different brands, different widths, different thicknesses, different speeds and different time periods, and displays them visually on the C5 display of the bearing temperature monitoring and early warning server. The displayed information includes: the number of the squeeze roller bearing seat, real-time vibration temperature parameters and operation statistics.

[0053] Continuously monitor the temperature of the squeeze roller bearings and issue early warnings while the production line is running at full speed to avoid tank fire accidents caused by abnormal squeeze roller bearing temperatures.

[0054] The present disclosure also provides an online monitoring and early warning system for the temperature of a squeeze roller bearing in a pickling process. The system can be used to implement an online monitoring and early warning method for the temperature of a squeeze roller bearing in a pickling process. The system includes:

[0055] A data acquisition module is configured to acquire comprehensive data of bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet;

[0056] A model training module is configured to process the comprehensive data to form sample data and obtain a bearing temperature prediction model after training;

[0057] a prediction module configured to input real-time data of bearing seat temperature and vibration into the bearing temperature prediction model and output a predicted bearing temperature within a certain future time window;

[0058] The early warning module is configured to obtain future early warning suggestions based on the early warning level and the predicted bearing temperature. Beneficial effects:

[0059] The vibration and temperature data of the bearing seat are collected through the temperature vibration sensor, which is installed on the bearing seat of the squeeze roller through a connection method such as gluing / welding the base or adapter bolts, which is easy to install;

[0060] Vibration and temperature data can be acquired by communicating with wireless temperature and vibration sensors through a wireless intelligent gateway, which reduces wiring difficulty and facilitates transformation and implementation.

[0061] The trained bearing temperature prediction model can be used to predict the bearing temperature within a certain time window in the future, which can be used to make early judgments and provide data support for the operation and maintenance of the squeeze roller equipment to avoid accidents.

[0062] FIG4 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the present invention. As shown in FIG4 , an embodiment of the present invention provides an electronic device 1300, comprising a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are implemented: S1, obtaining comprehensive data on bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet;

[0063] S2, processing the comprehensive data to form sample data and training it to obtain a bearing temperature prediction model;

[0064] S3, inputting the real-time data of the bearing seat temperature and vibration into the bearing temperature prediction model, and outputting the predicted bearing temperature within a certain time window in the future;

[0065] S4, obtaining future warning suggestions based on the warning level and the predicted bearing temperature.

[0066] It should be noted that the computer-readable medium described in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-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 of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer 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. In the present disclosure, a computer-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, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0067] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the aforementioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0068] It will be understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present invention, and the present invention is not limited thereto. Those skilled in the art will appreciate that various modifications and improvements can be made without departing from the spirit and substance of the present invention, and such modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. An online monitoring and early warning method for the bearing temperature of a squeeze roller in a pickling process section, characterized in that: include: Obtain comprehensive data on bearing seat temperature and vibration from wireless temperature and vibration sensors via Ethernet; The comprehensive data is processed to form sample data and trained to obtain a bearing temperature prediction model; Input the real-time data of bearing seat temperature and vibration into the bearing temperature prediction model, and output the predicted bearing temperature within a certain time window in the future; Future warning recommendations are obtained based on the warning level and the predicted bearing temperature.

2. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 1 is characterized in that: The comprehensive data is processed to form sample data and trained to obtain a bearing temperature prediction model, which specifically includes: Process the comprehensive data of bearing seat temperature and vibration to form sample data; Based on the sample data, select DeepAR, Informer, LSTNet, MLP, NBEATS, NHiTS, RNN, SCINet, TCN, TFT or Transformer model for training and verification until the prediction deviation of the bearing temperature prediction model is controlled within the allowable range.

3. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 2 is characterized in that: The bearing seat temperature is the target to be predicted, the strip grade, strip width, strip thickness, strip speed and bearing seat vibration are covariates, and the data is divided into training data, verification data and test data sets.

4. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 3 is characterized in that: The ratio of the training data, validation data, and test data set is 7:2:

1.

5. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 2 is characterized in that: Based on the sample data, the LSTNet model is selected for training and verification, specifically including: First, use PaddleTS to build a model network, predefine the time series length of the model input, the time series length of the model output, the loss function, the optimization algorithm, the optimizer parameters and the maximum number of training rounds; Use lstm.fit(train_dataset,val_dataset) to train and verify the model on the sample data, where train_dataset is the training data set and val_dataset is the verification data set; During and after the training, MAE (Mean Absolute Error) and MSE (Mean Squared Error) are used to evaluate the prediction effect of the model. When the effect reaches the preset value, the bearing temperature prediction model is obtained. type.

6. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 5 is characterized in that: After the training process is completed, LSTM is used to save the trained bearing temperature prediction model.

7. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 1 is characterized in that: The method of obtaining comprehensive data of bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet specifically includes: continuously collecting comprehensive data of bearing seat temperature and vibration from the wireless temperature and vibration sensor via Ethernet; storing sample data in a bearing temperature monitoring and early warning server and visually displaying it on a display of the bearing temperature monitoring and early warning server.

8. The method for online monitoring and early warning of the temperature of the squeeze roller bearing in the pickling process section according to claim 1 is characterized in that: The warning levels include: recommending to pay attention to operation, recommending to conduct necessary inspections at an appropriate time, recommending to perform maintenance within a planned shutdown in the near future, and recommending to take maintenance measures as soon as possible.

9. An online monitoring and early warning system for the temperature of the squeeze roller bearing in the pickling process section, characterized in that: The system can be used to implement the online monitoring and early warning method for the temperature of the squeeze roller bearing in the pickling process section described in any one of claims 1 to 8, and the system comprises: A data acquisition module, configured to acquire comprehensive data of bearing seat temperature and vibration from a wireless temperature and vibration sensor via Ethernet; A model training module is configured to process the comprehensive data to form sample data and obtain a bearing temperature prediction model after training; A prediction module configured to input real-time data of bearing seat temperature and vibration into the bearing temperature prediction model and output a predicted bearing temperature within a certain time window in the future; The early warning module is configured to obtain future early warning suggestions based on the early warning level and the predicted bearing temperature.

10. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the online monitoring and early warning method for the bearing temperature of the squeeze roller in the pickling process section as described in any one of claims 1 to 8.

Images