An online monitoring and early warning method and system for bearing temperature of an acid washing process section wringing roller
By constructing a temperature prediction model for the squeeze roller bearings in the pickling process section, and utilizing wireless temperature and vibration sensors and Ethernet for online monitoring and early warning, the problem of tank fire caused by abnormal squeeze roller bearing temperature was solved, ensuring production safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WISDRI ENG & RES INC LTD
- Filing Date
- 2023-07-13
- Publication Date
- 2026-07-03
AI Technical Summary
In the pickling process, abnormal temperature of the squeeze roller bearings caused the tank to catch fire, resulting in serious damage and production stoppage. Existing technology lacks effective online monitoring and early warning methods.
By acquiring bearing housing temperature and vibration data from wireless temperature and vibration sensors via Ethernet, a bearing temperature prediction model is constructed. The model is then trained and validated using models such as LSTNet to predict the temperature within a certain time window in the future and provide early warning suggestions based on the warning level.
It enables real-time monitoring and early warning of the temperature of the extrusion roller bearings, avoiding fire accidents in the trough, ensuring production safety and reducing downtime losses.
Smart Images
Figure CN116698227B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of cold rolling processing line technology, and in particular to a method and system for online monitoring and early warning of the temperature of the extrusion roll bearing in the pickling process section. Background Technology
[0002] The pickling process mainly includes a pickling tank and a rinsing tank. In the pickling tank, the acid reacts chemically with the iron oxide scale on the surface of the strip steel to remove the iron oxide scale. The rinsing tank cleans the surface of the strip steel that has come out of the pickling tank to remove any remaining pickling residue.
[0003] Pickling tanks and rinsing tanks are generally made of PPH or steel lined with rubber, which are flammable. Squeeze rollers are installed at the inlet and outlet of the pickling tank and between each pickling tank to minimize the amount of acid carried out by the strip. Squeeze rollers are also installed between each section of the rinsing tank to minimize the amount of rinsing water carried out by the strip.
[0004] During the pickling process, the temperature of the squeeze roller bearing and bearing seat continued to rise due to abnormal operation of the squeeze roller, which eventually led to a fire in the pickling tank and rinsing tank, causing serious damage to the pickling tank and rinsing tank, resulting in the unit stopping production and heavy losses. Summary of the Invention
[0005] This disclosure aims to solve at least one of the technical problems existing in the prior art, and proposes a method and system for online monitoring and early warning of the temperature of the extrusion roller bearing in the pickling process section.
[0006] In a first aspect, this disclosure provides a method for online monitoring and early warning of the temperature of the extrusion roll bearing in the pickling process section, including:
[0007] Comprehensive data on bearing housing temperature and vibration are acquired via Ethernet from a wireless temperature and vibration sensor.
[0008] The comprehensive data is processed to form sample data, and then trained to obtain the bearing temperature prediction model.
[0009] The real-time data of bearing housing temperature and vibration are input into the bearing temperature prediction model, and the predicted bearing temperature within a certain time window is output.
[0010] Future warning suggestions are derived based on the warning level and the predicted bearing temperature.
[0011] Preferably, the step of processing the comprehensive data to form sample data and training it to obtain the bearing temperature prediction model specifically includes:
[0012] The combined data of bearing housing temperature and vibration are processed to form sample data;
[0013] Based on the sample data, DeepAR, Informer, LSTNet, MLP, NBEATS, NHiTS, RNN, SCINet, TCN, TFT, or Transformer models were selected for training and validation until the prediction deviation of the bearing temperature prediction model was controlled within the allowable range.
[0014] Preferably, the bearing housing temperature is the target to be predicted, and the strip steel grade, strip steel width, strip steel thickness, strip steel speed and bearing housing vibration are covariates, and the data are divided into training data, validation data and test dataset.
[0015] Preferably, the ratio of the training data, validation data, and test dataset is 7:2:1.
[0016] Preferably, the step of selecting the LSTNet model for training and validation based on sample data specifically includes:
[0017] First, PaddleTS is used to build the model network, and 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 are predefined.
[0018] Use lstm.fit(train_dataset,val_dataset) to train and validate the model using sample data, where train_dataset is the training dataset and val_dataset is the validation dataset;
[0019] During and after training, MAE (Mean Absolute Error) and MSE (Mean Squared Error) are used to evaluate the model's prediction performance. When the performance reaches the preset value, the bearing temperature prediction model is obtained.
[0020] Preferably, after the training process is completed, the trained bearing temperature prediction model is saved using LSTM.
[0021] Preferably, the step of acquiring comprehensive data on bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet specifically includes: continuously collecting comprehensive data on bearing housing 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 the display of the bearing temperature monitoring and early warning server.
[0022] Preferably, the warning levels include: recommending to pay attention to operation, recommending to conduct necessary inspections at an appropriate time, recommending to plan to shut down for maintenance in the near future, and recommending to take maintenance measures as soon as possible.
[0023] In a second aspect, this disclosure provides an online monitoring and early warning system for the temperature of the squeeze roller bearings in the pickling process section. The system can be used to implement an online monitoring and early warning method for the temperature of the squeeze roller bearings in the pickling process section. The system includes:
[0024] The data acquisition module is configured to acquire comprehensive data on bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet;
[0025] The model training module is configured to process the comprehensive data to form sample data and then train the model to obtain the bearing temperature prediction model.
[0026] The prediction module is configured to input real-time data of bearing housing temperature and vibration into the bearing temperature prediction model and output the predicted bearing temperature within a certain time window in the future.
[0027] The early warning module is configured to generate future early warning suggestions based on the early warning level and the predicted bearing temperature.
[0028] In a third aspect, this disclosure provides an electronic device, comprising:
[0029] One or more processors;
[0030] Memory, used to store one or more programs;
[0031] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for online monitoring and early warning of the temperature of the extrusion roller bearings in the pickling process section. Attached Figure Description
[0032] Figure 1 A flowchart illustrating an online monitoring and early warning method for the temperature of the squeeze roller bearing in the pickling process section, provided in this embodiment of the present disclosure;
[0033] Figure 2 A diagram illustrating the composition of the online monitoring and early warning system for the temperature of the squeeze roller bearings in the pickling process section provided in this embodiment of the disclosure;
[0034] Figure 3 A flowchart of the bearing temperature prediction model training process provided in this embodiment of the disclosure;
[0035] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation
[0036] To enable those skilled in the art to better understand the technical solutions of this disclosure, the disclosure will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0037] Unless otherwise defined, the technical or scientific terms used in this disclosure shall have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms “first,” “second,” and similar terms used in this disclosure are not intended to indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms “an,” “a,” or “the,” and similar terms are not intended to limit the quantity, but rather to indicate the presence of at least one. The terms “comprising,” “including,” or “including,” and similar terms mean that the element or object preceding the term encompasses the elements or objects listed following the term and their equivalents, without excluding other elements or objects. The terms “connected,” “linked,” and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms “upper,” “lower,” “left,” and “right,” etc., are used only for relative positional relationships, and these relative positional relationships may change accordingly when the absolute position of the described object changes.
[0038] In the various figures, the same elements are represented by similar reference numerals. For clarity, not all parts in the figures are drawn to scale. Furthermore, some well-known parts may not be shown in the figures.
[0039] Many specific details of this disclosure, such as the structure, materials, dimensions, processing methods, and techniques of the components, are described below to provide a clearer understanding of the disclosure. However, as those skilled in the art will understand, this disclosure may be implemented without following these specific details.
[0040] like Figures 1 to 3 As shown in the figure, this disclosure provides a method for online monitoring and early warning of the temperature of the extrusion roll bearing in the pickling process section, including the following steps:
[0041] S1 acquires comprehensive data on bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet;
[0042] S2, after processing the comprehensive data to form sample data and training it, a bearing temperature prediction model is obtained;
[0043] S3, input the real-time data of bearing housing temperature and vibration into the bearing temperature prediction model, and output the predicted bearing temperature within a certain time window in the future;
[0044] S4. Based on the warning level and the predicted bearing temperature, a future warning suggestion is obtained.
[0045] It should be noted that the order of the above steps can be rearranged arbitrarily and is not limited by this disclosure.
[0046] In a specific implementation scenario, to implement the above method, an online monitoring and early warning system for the temperature of the squeeze roller bearing in the pickling process section needs to be built. This system consists of a squeeze roller bearing housing C1, a wireless temperature and vibration sensor C2, a wireless smart gateway C3, an Ethernet connection 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 installed on the squeeze roller bearing housing via adhesive / welding or adapter bolts. The wireless smart gateway C3 collects the temperature and vibration data from the wireless temperature and vibration sensor C2 via wireless communication and transmits the data to the bearing temperature monitoring and early warning server via Ethernet C4. The temperature monitoring and early warning module C6 monitors the temperature of the squeeze roller bearing and issues early warnings.
[0047] During production, the temperature monitoring and early warning module C6 is activated. C6 mainly 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 housing temperature and vibration from the wireless temperature and vibration sensor C2 via Ethernet (C4). The sample data is stored on the hard drive of the bearing temperature monitoring and early warning server (C5) and visualized on the server's display. The visualized information includes: the squeeze roller bearing housing number, real-time vibration and temperature parameters, and operational statistics. The bearing temperature prediction and training module process is as follows: Figure 3 As shown, the comprehensive data of bearing housing temperature and vibration are processed to form sample data, in which bearing housing temperature is the target to be predicted, and strip steel grade, strip steel width, strip steel thickness, strip steel speed and bearing housing vibration are covariates. The data is divided into training data, validation data and test data. Based on the sample data, DeepAR, Informer, LSTNet, MLP, NBEATS, NHiTS, RNN, SCINet, TCN, TFT or Transformer models are selected for training and validation until the prediction deviation of the bearing temperature prediction model is controlled within the allowable range.
[0048] Taking LSTNet as an example:
[0049] First, PaddleTS (a Python library for time series modeling based on Baidu's deep learning framework PaddlePaddle) is used to build the model network. This mainly involves predefining parameters such as in_chuck_len (length of the time series input to the model), out_chunk_len (length of the time series output to the model), loss_fn (loss function), optimizer_fn (optimization algorithm), optimizer_paras (optimizer parameters), and max_epochs (maximum number of training epochs). After the model parameters are predefined, lstm.fit(train_dataset, val_dataset) is used to train and validate the model using the dataset, where train_dataset is the training dataset and val_dataset is the validation dataset. During and after training, MAE (Mean Absolute Error) and MSE (Mean Squared Error) are used to evaluate the prediction performance 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. The trained model is saved using lstm(lstm.save)("lstm"), and can be called by the online bearing temperature early warning module to predict the bearing temperature within a certain time window in the future.
[0050] The temperature monitoring and early warning module collects real-time bearing housing vibration and temperature data. When these data exceed thresholds, an alarm is triggered. Simultaneously, it uses a pre-trained bearing temperature prediction model to predict the bearing housing temperature within a future time window. The early warning levels are divided into four categories: "Recommend monitoring," "Recommend necessary inspection at an appropriate time," "Recommend planned shutdown for maintenance," and "Recommend immediate maintenance." This system helps prevent fires in the trough caused by abnormal extrusion roller bearing temperature.
[0051] The data acquisition and visualization module continuously collects data, including vibration and temperature data of bearing housings of different grades, widths, thicknesses, speeds, and time periods. The data is then visualized on the C5 monitor of the bearing temperature monitoring and early warning server, displaying information such as: extrusion roller bearing housing number, real-time vibration temperature parameters, and operational statistics.
[0052] Continuously monitor the temperature of the squeeze roller bearings and issue early warnings under full-speed operation of the production line to prevent fire accidents in the tank caused by abnormal temperature of the squeeze roller bearings.
[0053] This disclosure also provides an online monitoring and early warning system for the temperature of the extrusion roll bearing in the pickling process section. The system can be used to implement a method for online monitoring and early warning of the temperature of the extrusion roll bearing in the pickling process section. The system includes:
[0054] The data acquisition module is configured to acquire comprehensive data on bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet;
[0055] The model training module is configured to process the comprehensive data to form sample data and then train the model to obtain the bearing temperature prediction model.
[0056] The prediction module is configured to input real-time data of bearing housing temperature and vibration into the bearing temperature prediction model and output the predicted bearing temperature within a certain time window in the future.
[0057] The early warning module is configured to generate future early warning suggestions based on the early warning level and the predicted bearing temperature.
[0058] Beneficial effects:
[0059] Vibration and temperature data of the bearing housing are collected by a temperature and vibration sensor. The temperature and vibration sensor is installed on the squeeze roller bearing housing by means of adhesive / welding base or adapter bolts, which is convenient to install.
[0060] By communicating with wireless temperature and vibration sensors through a wireless smart gateway, vibration and temperature data can be obtained, reducing the difficulty of wiring and making it easier to implement the modification.
[0061] By using a well-trained bearing temperature prediction model to predict the bearing temperature within a certain time window in the future, it is possible to make advance predictions, provide data support for the operation and maintenance of extrusion roll equipment, and avoid accidents.
[0062] Please see Figure 4 This is a schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 4 As shown, an embodiment of the present invention provides an electronic device 1300, including 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, it performs the following steps: S1, acquiring comprehensive data of bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet.
[0063] S2, after processing the comprehensive data to form sample data and training it, a bearing temperature prediction model is obtained;
[0064] S3, input the real-time data of bearing housing temperature and vibration into the bearing temperature prediction model, and output the predicted bearing temperature within a certain time window in the future;
[0065] S4. Based on the warning level and the predicted bearing temperature, a future warning suggestion is obtained.
[0066] It should be noted that the computer-readable medium disclosed herein 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, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this 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, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.
[0067] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0068] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.
Claims
1. A method for online monitoring and early warning of the temperature of the squeeze roller bearing in a pickling process, characterized in that, include: Comprehensive data on bearing housing temperature and vibration are acquired via Ethernet from a wireless temperature and vibration sensor. The comprehensive data is processed to form sample data, and then trained to obtain the bearing temperature prediction model. The real-time data of bearing housing temperature and vibration are input into the bearing temperature prediction model, and the predicted bearing temperature within a certain time window is output. Based on the warning level and the predicted bearing temperature, future warning suggestions are obtained; The process of processing comprehensive data to form sample data and training it to obtain a bearing temperature prediction model specifically includes: The combined data of bearing housing temperature and vibration are processed to form sample data; Based on the sample data, DeepAR, Informer, LSTNet, MLP, NBEATS, NHiTS, RNN, SCINet, TCN, TFT, or Transformer models were selected for training and validation until the prediction deviation of the bearing temperature prediction model was controlled within the allowable range. The selection of the LSTNet model for training and validation based on sample data specifically includes: First, PaddleTS is used to build the model network, and 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 are predefined. Use lstm.fit(train_dataset, val_dataset) to train and validate the model on sample data, where train_dataset is the training dataset and val_dataset is the validation dataset; During and after training, MAE and MSE are used to evaluate the model's prediction performance. When the performance reaches the preset value, the bearing temperature prediction model is obtained. The bearing housing temperature is the target to be predicted, and the strip steel grade, strip steel width, strip steel thickness, strip steel speed and bearing housing vibration are covariates. The data is divided into training data, validation data and test dataset.
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, characterized in that, The ratio of the training data, validation data, and test dataset is 7:2:
1.
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 1, characterized in that, After the training process is completed, the trained bearing temperature prediction model is saved using LSTM.
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 1, characterized in that, The process of acquiring comprehensive data on bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet specifically includes: continuously collecting comprehensive data on bearing housing temperature and vibration from the 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 the display of the bearing temperature monitoring and early warning server.
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 1, characterized in that, The warning levels include: it is recommended to pay attention to the operation, it is recommended to conduct necessary inspections at an appropriate time, it is recommended to plan to shut down for maintenance in the near future, and it is recommended to take maintenance measures as soon as possible.
6. An online monitoring and early warning system for the temperature of the squeeze roller bearing in a 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 extrusion roll bearing in any of the pickling process sections described in claims 1 to 5. The system includes: The data acquisition module is configured to acquire comprehensive data on bearing housing temperature and vibration from a wireless temperature and vibration sensor via Ethernet; The model training module is configured to process the comprehensive data to form sample data and then train the model to obtain the bearing temperature prediction model. The prediction module is configured to input real-time data of bearing housing temperature and vibration into the bearing temperature prediction model and output the predicted bearing temperature within a certain time window in the future. The early warning module is configured to generate future early warning suggestions based on the early warning level and the predicted bearing temperature.
7. An electronic device, characterized in that, include: One or more processors; Memory, used to store 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 temperature of the squeeze roller bearing in the pickling process section as described in any one of claims 1 to 5.