CN113761785A - Method and device for determining thinning value of boiler and storage medium - Google Patents
Method and device for determining thinning value of boiler and storage medium Download PDFInfo
- Publication number
- CN113761785A CN113761785A CN202110655053.7A CN202110655053A CN113761785A CN 113761785 A CN113761785 A CN 113761785A CN 202110655053 A CN202110655053 A CN 202110655053A CN 113761785 A CN113761785 A CN 113761785A
- Authority
- CN
- China
- Prior art keywords
- neural network
- boiler
- maintenance data
- convolutional neural
- network model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 66
- 238000012423 maintenance Methods 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims description 67
- 238000012360 testing method Methods 0.000 claims description 36
- 239000013598 vector Substances 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 28
- 238000007781 pre-processing Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000013450 outlier detection Methods 0.000 claims 1
- 238000005260 corrosion Methods 0.000 abstract description 15
- 230000007797 corrosion Effects 0.000 abstract description 15
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000000053 physical method Methods 0.000 abstract description 5
- 238000012067 mathematical method Methods 0.000 abstract 1
- 238000003062 neural network model Methods 0.000 description 24
- 238000013528 artificial neural network Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000011176 pooling Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000010606 normalization Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004880 explosion Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004071 soot Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本申请公开了一种确定锅炉的减薄值的方法、装置以及存储介质。该方法包括：获取锅炉各部位的检修数据，其中检修数据是按照时间顺序获取的检修数据；以及利用预先训练的三维卷积神经网络模型，根据锅炉各部位的检修数据，对锅炉各部位的减薄数据进行预测。本发明无需分析管壁腐蚀因素，而是按照时间顺序获取锅炉各部位的检修数据，并利用预先训练的三维卷积神经网络模型，根据锅炉各部位的检修数据，通过人工智能分析的方式对锅炉各部位的减薄数据进行预测。从而有效提高了锅炉减薄预测的准确性。进而解决了现有技术中存在通过分析管壁腐蚀因素，结合数学物理方法建立模型来对锅炉减薄进行预测的方法的准确性低的技术问题。
The present application discloses a method, device and storage medium for determining a thinning value of a boiler. The method includes: acquiring the maintenance data of each part of the boiler, wherein the maintenance data is the maintenance data obtained in time sequence; Thin data for forecasting. The invention does not need to analyze the corrosion factors of the tube wall, but obtains the maintenance data of each part of the boiler in time sequence, and uses the pre-trained three-dimensional convolutional neural network model, according to the maintenance data of each part of the boiler, and analyzes the boiler through artificial intelligence. The thinning data of each part is predicted. Thus, the accuracy of boiler thinning prediction is effectively improved. Furthermore, the technical problem in the prior art that the method for predicting the boiler thinning by analyzing the corrosion factors of the tube wall and establishing a model in combination with a mathematical and physical method is solved.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, and a storage medium for determining a thinning value of a boiler.
Background
As a technology-intensive production unit, electric power production enterprises have various accident types. Data show that in various accidents of thermal power plants in China, boiler accidents account for more than 70% of total accidents of the power plants, leakage and explosion accidents of four types of pipes (namely four pipes for short) of superheaters, reheaters, economizers and water-cooled walls occur frequently, the number of the accidents is the largest, and the accidents account for more than 70% of the total accidents of the boilers, so that the problem that the safety production of the thermal power plants is troubled is solved.
For a long time, the research on the boiler four-tube accident mainly focuses on the analysis of the cause of tube explosion leakage after the accident occurs, and summarizes industrial production after the experience of tube explosion guides so as to prolong the service life of four tubes. Aiming at the thinning corrosion degree of each pipe, temperature and some soot are proposed to be main reasons for causing the corrosion thinning of the pipe wall. However, most of the existing boiler thinning prediction methods predict the thinning degree of the wall thickness of the pipe by analyzing the corrosion factors of the pipe wall and combining a mathematical physics method to establish a model, and the accuracy is low.
Aiming at the technical problem that the method for predicting the boiler thinning by analyzing the corrosion factors of the pipe wall and combining a mathematical physics method to establish a model in the prior art has low accuracy, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the disclosure provides a method and a device for predicting boiler thinning and a storage medium, so as to at least solve the technical problem that the method for predicting boiler thinning by analyzing pipe wall corrosion factors and combining a mathematical physics method to establish a model in the prior art is low in accuracy.
According to an aspect of the embodiments of the present disclosure, there is provided a method for predicting boiler thinning, including: acquiring overhaul data of each part of the boiler, wherein the overhaul data are different types of overhaul data detected at preset positions according to a time sequence; and determining the thinning value of the preset position according to the overhaul data by utilizing a pre-trained three-dimensional convolution neural network model.
According to another aspect of the embodiments of the present disclosure, there is also provided a storage medium including a stored program, wherein the method of any one of the above is performed by a processor when the program is executed.
According to another aspect of the embodiments of the present disclosure, there is also provided an apparatus for predicting boiler thinning, including: the acquisition module is used for acquiring the overhaul data of each part of the boiler, wherein the overhaul data are different types of overhaul data detected at preset positions according to a time sequence; and the prediction module is used for determining the thinning value of the preset position according to the overhaul data by utilizing a pre-trained three-dimensional convolution neural network model.
According to another aspect of the embodiments of the present disclosure, there is also provided an apparatus for predicting boiler thinning, including: a processor; and a memory coupled to the processor for providing instructions to the processor for processing the following processing steps: acquiring overhaul data of each part of the boiler, wherein the overhaul data are different types of overhaul data detected at preset positions according to a time sequence; and determining the thinning value of the preset position according to the overhaul data by utilizing a pre-trained three-dimensional convolution neural network model.
The invention provides a method for predicting boiler thinning. According to the method, the maintenance data of each part of the boiler are acquired according to the time sequence without analyzing the corrosion factors of the pipe wall, and the thinning data of each part of the boiler is predicted in an artificial intelligence analysis mode according to the maintenance data of each part of the boiler by utilizing a pre-trained three-dimensional convolutional neural network model. Therefore, the accuracy of boiler thinning prediction is effectively improved. The technical problem that the method for predicting the boiler thinning by analyzing the pipe wall corrosion factors and combining a mathematical physical method to establish a model in the prior art is low in accuracy is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:
fig. 1 is a hardware block diagram of a computing device for implementing the method according to embodiment 1 of the present disclosure;
FIG. 2 is a schematic diagram of a system for a method of predicting boiler thinning according to embodiment 1 of the present disclosure;
FIG. 3 is a schematic flow diagram of a method of predicting boiler thinning in accordance with embodiment 1 of the present disclosure;
FIG. 4 is a schematic diagram of a three-dimensional convolutional neural network model according to embodiment 1 of the present disclosure;
FIG. 5 is a schematic flow chart diagram of a method for predicting boiler thinning in accordance with embodiment 1 of the present disclosure;
FIG. 6 is a schematic diagram of an apparatus for predicting boiler thinning according to embodiment 2 of the present disclosure; and
FIG. 7 is a schematic diagram of an apparatus for predicting boiler thinning according to embodiment 3 of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. It is to be understood that the described embodiments are merely exemplary of some, and not all, of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
While the illustrated logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in an order different than that shown or described herein.
The method embodiments provided by the present embodiment may be executed in a computer terminal, a server or a similar computing device. FIG. 1 illustrates a block diagram of a hardware architecture of a computing device for implementing boiler thinning prediction. As shown in fig. 1, the computing device may include one or more processors (which may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computing device may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuitry may be a single, stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computing device. As referred to in the disclosed embodiments, the data processing circuit acts as a processor control (e.g., selection of a variable resistance termination path connected to the interface).
The memory may be used to store software programs and modules of application software, such as the corresponding program instruction/data storage device for predicting boiler thinning in the embodiments of the present disclosure, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the application programs described above are implemented to predict boiler thinning. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory located remotely from the processor, which may be connected to the computing device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device is used for receiving or transmitting data via a network. Specific examples of such networks may include wireless networks provided by communication providers of the computing devices. In one example, the transmission device includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computing device.
It should be noted here that in some alternative embodiments, the computing device shown in fig. 1 described above may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that FIG. 1 is only one example of a particular specific example and is intended to illustrate the types of components that may be present in a computing device as described above.
FIG. 2 is a schematic diagram of a system for a method of predicting boiler thinning according to the present embodiment. Referring to fig. 2, the system includes: the system comprises a sensor cluster 100 and a server 200, wherein the sensor cluster 100 comprises a plurality of sensors 101-10 n for detecting the temperatures of different parts of a boiler. The plurality of sensors 101-10 n are arranged on four types of tubes such as a superheater, a reheater, an economizer and a water wall, and are arranged at different positions of each type of tube. For example, a plurality of sensors may be provided at different positions of the superheater, respectively. Therefore, by the mode, the temperature of a plurality of preset positions of the boiler can be detected, and the overhaul data of the boiler can be obtained.
The server 200 communicates with the sensors 101-10 n to receive the maintenance data collected by the sensors 101-10 n and process the maintenance data received from the sensors 101-10 n. Wherein the processing of the service data by server 200 includes (but is not limited to): generating a training data set and a testing data set for training an artificial intelligence model according to the received historical overhaul data, determining a thinning value of the boiler according to the overhaul data and the like. It should be noted that the server 200 in the system may be adapted to the above-described hardware configuration.
Under the above operating environment, according to a first aspect of the present embodiment, a method for determining a thinning value of a boiler is provided, which is implemented by the server 200 shown in fig. 2. Fig. 3 shows a flow diagram of the method, which, with reference to fig. 3, comprises:
s302: acquiring overhaul data of a preset position of a boiler, wherein the overhaul data are different types of overhaul data detected at the preset position according to a time sequence; and
s304: and determining the thinning value of the preset position by utilizing a pre-trained three-dimensional convolution neural network model according to the overhaul data.
Specifically, in order to measure the thinning value of the boiler, the server 200 detects the overhaul data of a plurality of positions of the boiler through the sensors 101 to 10n of the sensor cluster 100. The sensors 101-104 are assumed to be arranged at a certain preset position of the boiler and used for measuring 4 different types of maintenance data (such as main steam flow, main steam temperature, main steam pressure and temperature of a measuring point), so that the sensors are used for measuring each maintenance data of the preset position of the boiler. Therefore, the sensors 101-104 can continuously provide corresponding types of maintenance data to the server 200 according to the time sequence. Accordingly, the server 200 may acquire the service data (S302).
Then, the server 200 determines a thinning value of the preset position in the boiler according to the overhaul data acquired by the sensors 101 to 104 according to the time sequence by using the pre-trained three-dimensional convolutional neural network model (S304).
In which figure 4 shows a block diagram of a three-dimensional convolutional neural network model. Referring to fig. 4, the convolutional neural network includes: a hard wiring layer; 7 × 33D convolution layers; 2 x 2 downsampling layers; 7 x 6 x 33D convolutional layers; 3 x 3 downsampling layers; 7 x 4 convolutional layers; and a full connection layer. Wherein the output of the fully connected layer is a single value indicative of the calculated reduction value.
Therefore, in the technical scheme of the embodiment, the received overhaul data is used as an input value of the three-dimensional convolutional neural network, and the thinning value at the preset position is calculated by using the three-dimensional convolutional neural network model.
As described in the background art, the conventional method for detecting the wall thickness of the four tubes at present is difficult to adapt to the needs of power generation enterprises at present, to guide the staff of the power enterprises to provide scientific guidance for the state of the four tubes of the boiler, and to grasp the leakage rule of the four tubes of the boiler, thereby causing economic loss of the enterprises and even affecting the life safety of the staff.
In view of the technical problems in the prior art, referring to fig. 2 to 4, the present invention provides a method for predicting boiler thinning. The method comprises the steps that firstly, different types of overhaul data at preset positions of a boiler are collected by sensors 101-104, wherein the overhaul data are obtained by the sensors 101-104 according to a time sequence, and the different types of overhaul data (such as main steam flow, main steam temperature, main steam pressure and temperature of a measuring point) at the preset positions. Therefore, when the boiler wall thickness is predicted, the condition of the boiler wall thickness reduction can be predicted according to the historical information of the boiler wall thickness at different times.
Then, the server 200 predicts the thinning value at the preset position according to the overhaul data by using the pre-trained three-dimensional convolutional neural network model, so as to determine the thinning value at the preset position. Therefore, the worker can repair the boiler according to the prediction result of the boiler thinning data of the server 200. According to the method, the maintenance data of each part of the boiler are acquired according to the time sequence without analyzing the corrosion factors of the pipe wall, and the thinning data of each part of the boiler is predicted in an artificial intelligence analysis mode according to the maintenance data of each part of the boiler by utilizing a pre-trained three-dimensional convolutional neural network model. Therefore, the accuracy of boiler thinning prediction is effectively improved. The technical problem that the method for predicting the boiler thinning by analyzing the pipe wall corrosion factors and combining a mathematical physical method to establish a model in the prior art is low in accuracy is solved.
Although the embodiment takes the sensors 101-104 as an example to illustrate the prediction of the thinning value of the preset position. But the service data measured for sensors at other locations is also applicable to the method described above. For example, the sensors 105-108 are used to measure different types of overhaul data at another location, so that the thinning value at the other location can be determined by using the overhaul data collected by the sensors 105-108 in time sequence and using the three-dimensional convolution neural network.
Optionally, the operation of determining the thinning value at the preset position according to the overhaul data by using a pre-trained three-dimensional convolutional neural network model includes: generating corresponding overhaul data vectors according to the overhaul data detected at the preset position at each time point; arranging the maintenance data vectors corresponding to the time points according to the time sequence to generate a maintenance data vector sequence corresponding to a preset position; and inputting the overhaul data vector sequence into the three-dimensional convolutional neural network model, and taking the output value of the full connecting layer of the three-dimensional convolutional neural network as the thinning value of the preset position.
Specifically, as described above, the present solution measures the maintenance data of the preset position of the boiler through the sensors 101 to 104, for example, so as to obtain a series of maintenance data in time sequence, which is specifically shown in the following table 1: (e.g., main steam flow, main steam temperature, main steam pressure, temperature of the point)
Referring to Table 1, the sensors 101-104 are time-sequenced from T1Time to TnThe maintenance data of corresponding types are respectively measured at all times, so that the maintenance data measured by each sensor at each time can form a maintenance data vector, and the maintenance data vector is obtained from T1Time to TnThe service data vectors measured at a time may form a sequence of service data vectors.
Thus, the repair data vector sequence may be arranged in a matrix form, for example, as follows:
therefore, the overhaul data vector sequence can be input into the three-dimensional convolution neural network model shown in fig. 4, so that the full connection layer of the three-dimensional convolution neural network model can output a numerical value for indicating the thinning value at the preset position.
Therefore, according to the technical scheme of the embodiment, aiming at the problem that the common convolutional neural network is difficult to extract the data time sequence characteristics, the technical scheme of the embodiment adopts three-dimensional convolution operation to process the overhaul data with the time sequence characteristics, and the 3DCNN also comprises an input side, a convolutional layer, a pooling layer and a full connection layer. And performing three-dimensional convolution operation on the convolution layer, and performing three-dimensional pooling operation on the pooling layer. The output of the convolution operation is not only related to the current moment, but also related to the input of the adjacent moment, so that the thinning value at the preset position of the boiler can be more accurately determined by adopting the three-dimensional convolution operation.
Optionally, training the three-dimensional convolutional neural network model by: acquiring historical overhaul data of each part of the boiler; generating a training data set and a testing data set for training the three-dimensional convolution neural network model according to historical overhaul data; and training the three-dimensional convolution neural network model by utilizing the training data set and the overhaul test data set. The server 200 first obtains historical overhaul data of various parts of the boiler, and then divides the historical overhaul information into a training data set and a testing data set. Where the training data set test data set may take the form shown in table 1 above, it is furthermore necessary to measure the actual thinning values corresponding thereto.
And training the three-dimensional convolution neural network model by utilizing the training data set and the test data set. And training the three-dimensional convolution neural network model, and predicting the thinning of the boiler after the training is finished. For example, the characteristic information of the boiler wall thickness at a certain time is input, and the output is the prediction of the boiler thinning. Therefore, the purpose that the established three-dimensional convolution neural network model can predict the thinning of the boiler through training is achieved through the method.
Optionally, the operation of generating a training data set and a testing data set for training the three-dimensional convolutional neural network model according to the historical overhaul data includes: preprocessing historical overhaul data, wherein the preprocessing comprises abnormal value detection and missing value processing; and carrying out normalization processing on the preprocessed data to generate a training data set and a test data set. When the historical overhaul data is processed, the server 200 first preprocesses the historical overhaul data and then normalizes the preprocessed data. By carrying out normalization processing on the data, the condition that the generated training data set and the test data set generate overfitting when the neural network is trained can be avoided, the stability and the generalization capability of the neural network can be improved, and the technical effect of removing interference data in the data set can be achieved by carrying out detection and missing value processing on abnormal values.
Optionally, the operation of training the three-dimensional convolutional neural network model by using the training data set and the test data set includes: respectively calculating the training data set and the test data set through a three-dimensional convolution neural network model to obtain output results, and comparing the mean square errors of the output results of the training data set and the test data set; and adjusting the weight matrix in the three-dimensional convolutional neural network model according to the condition of the mean square error. When the three-dimensional convolution neural network model is trained, the training data set and the test data set respectively pass through the three-dimensional convolution neural network model, and then output results of the training data set and the test data set, which are calculated by the three-dimensional convolution neural network model, are compared. And if the error of the two does not reach the set threshold value, adjusting the weight matrix in the three-dimensional convolution neural network model. When the error reaches the set threshold value, the learning is not carried out. Therefore, the technical effect of optimizing the link weights of all layers of the neural network to realize automatic learning can be realized in a reverse training mode.
Referring to fig. 5, the present invention provides a method for predicting boiler turndown. Firstly, analyzing influence factors of original data on boiler wall thickness reduction, then preprocessing the data by the server 200, wherein the preprocessing comprises abnormal value detection and missing value processing, and after preprocessing, performing normalization processing and establishing a data set. And then, the data set is divided into a training data set and a testing data set, a three-dimensional convolutional neural network model is established, and the three-dimensional convolutional neural network model is trained through the training data set and the testing data set. The result of training output takes the mean square error or the relative error as the accurate condition of the evaluation model, and the model hyper-parameters are adjusted in time according to the actual production needs. According to the training generation model, the influence of the operation data in different time periods on the wall thickness of the boiler can be evaluated.
Further, referring to fig. 1, according to a second aspect of the present embodiment, there is provided a storage medium. The storage medium comprises a stored program, wherein the method of any of the above is performed by a processor when the program is run.
In addition, the three-dimensional convolutional neural network model proposed in the present embodiment is, for example, a Convolutional Neural Network (CNN). Convolutional Neural Networks (CNN) are a class of feed forward neural networks that contain convolutional computations and have a deep structure, and are one of the representative algorithms for deep learning. The convolutional neural network has the characteristic learning ability and can carry out translation invariant classification on input information according to the hierarchical structure of the convolutional neural network. There are mainly the following advantages compared to conventional neural networks.
1) The connections between convolutional layers in a convolutional neural network are called sparse connections, i.e., neurons in a convolutional layer are connected to only part of their neighboring layers, not all neurons, as compared to full connections in a feed-forward neural network. Specifically, any one pixel (neuron) in the l-layer feature map of the convolutional neural network is only a linear combination of pixels in the receptive field defined by the convolutional kernel in the l-1 layer. The sparse connection of the convolutional neural network has a regularization effect, the stability and the generalization capability of the network structure are improved, overfitting is avoided, meanwhile, the total amount of weight parameters is reduced through the sparse connection, the fast learning of the neural network is facilitated, and the memory overhead is reduced during calculation.
2) All pixels in the same channel of the feature map in the convolutional neural network share a set of convolution kernel weight coefficients, and this property is called weight sharing. Weight sharing distinguishes convolutional neural networks from other neural networks that contain locally connected structures, which, while using sparse connections, have different weights for different connections. Weight sharing is the same as sparse connection, reduces the parameter total amount of the convolutional neural network, and has the regularization effect.
Further, the convolutional neural network includes: input side, convolutional layer, pooling layer, and full-link layer. The order in which 3 types of common constructs are built into the hidden layer is typically: input-convolutional layer-pooling layer-full-link layer-output.
In order to solve the problem that the CNN is difficult to extract the data time sequence characteristics, three-dimensional convolution operation is adopted to process input data with the time sequence characteristics, and the 3DCNN also comprises an input side, a convolution layer, a pooling layer and a full connection layer. And performing three-dimensional convolution operation on the convolution layer, and performing three-dimensional pooling operation on the pooling layer. The output of the convolution operation is not only related to the current time, but also related to the input of the adjacent time.
The 3DCNN training procedure is as follows:
1) forward training: at this stage, information is passed from the input layer to the output layer via a stepwise transformation. This process is also the process that the network performs during normal operation after training is completed. In this process, the network performs computations (in effect, the inputs are multiplied by the weight matrix of each layer to obtain the final output).
2) Reverse training: calculating the difference between the actual output Op and the corresponding ideal output Yp; the adjustment weight matrix is propagated back in a way that minimizes the error.
Loss Function (sometimes called Cost Function or Objective Function) is generally used in the reverse training to measure the dissatisfaction degree of the result. Intuitively, the larger the difference between the score function output result and the true result, the larger the loss function output, and vice versa.
According to the requirements of regression problems, the following methods are generally adopted:
1. mean square error (also known as MSE, L2 loss);
2. mean absolute value error (aka MAE, L1 loss);
3. huber loss, smoothed mean absolute error.
The invention also has the following advantages:
1. and reasonably processing the data by adopting a data analysis technology according to production data and boiler operation data provided by a production enterprise.
2. And by means of the preprocessed data, a machine learning method, namely a three-dimensional convolutional neural network model, is adopted to reasonably and effectively predict the wall thickness reduction condition of the boiler and reasonably guide enterprise production.
The key links of the invention are as follows: and predicting the boiler thinning by utilizing deep learning and a neural network.
The invention has the technical points that:
1. and extracting relevant characteristics by using boiler operation data and through a three-dimensional convolution neural network model to obtain the thinning condition of the pipe wall thickness of different parts.
2. The neural network in the present invention can also predict thinning by using methods such as RNN (recurrent neural network) lstm.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
Fig. 6 shows an apparatus 600 for predicting boiler thinning according to the present embodiment, the apparatus 600 corresponding to the method according to the first aspect of embodiment 1. Referring to fig. 6, the apparatus 600 includes: the acquisition module 610 is configured to acquire overhaul data of a preset position of a boiler, where the overhaul data are different types of overhaul data detected at the preset position according to a time sequence; and a prediction module 620, configured to determine, according to the overhaul data, a thinning value of the preset position by using a pre-trained three-dimensional convolutional neural network model.
Optionally, the prediction module comprises: the maintenance data vector generation submodule is used for generating corresponding maintenance data vectors according to the maintenance data detected at the preset position at each time point; the maintenance data vector sequence generation submodule is used for arranging maintenance data vectors corresponding to the time points according to the time sequence and generating maintenance data vector sequences corresponding to the preset positions; and the thinning value prediction submodule is used for inputting the overhaul data vector sequence into the three-dimensional convolution neural network model and taking the output value of the full connecting layer of the three-dimensional convolution neural network as the thinning value of the preset position.
Optionally, the three-dimensional convolutional neural network model is trained by the following sub-modules: obtaining a submodule: the method comprises the steps of obtaining historical overhaul data of each part of the boiler; generating a submodule: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring historical overhaul data; and a training submodule: the method is used for training the three-dimensional convolution neural network model by utilizing the training data set and the testing data set.
Optionally, the generating sub-module comprises: a pretreatment unit: the system is used for preprocessing historical overhaul data, wherein the preprocessing comprises abnormal value detection and missing value processing; and a generation unit: and the method is used for carrying out normalization processing on the preprocessed data to generate a training data set and a test data set.
Optionally, the training submodule comprises: a comparison unit: the device is used for respectively calculating the training data set and the test data set through a three-dimensional convolution neural network model to obtain output results, and comparing the mean square errors of the output results of the training data set and the test data set; and an adjusting unit: the method is used for adjusting the weight matrix in the three-dimensional convolutional neural network model according to the condition of mean square error.
Therefore, according to the embodiment, the maintenance data of each part of the boiler is acquired according to the time sequence without analyzing the pipe wall corrosion factors, and the thinning data of each part of the boiler is predicted in an artificial intelligence analysis mode according to the maintenance data of each part of the boiler by utilizing the pre-trained three-dimensional convolutional neural network model. Therefore, the accuracy of boiler thinning prediction is effectively improved. The technical problem that the method for predicting the boiler thinning by analyzing the pipe wall corrosion factors and combining a mathematical physical method to establish a model in the prior art is low in accuracy is solved.
Example 3
Fig. 7 shows an arrangement 700 for predicting boiler thinning according to the present embodiment, which arrangement 700 corresponds to the method according to the first aspect of embodiment 1. Referring to fig. 7, the apparatus 700 includes: a processor 710; and a memory 720, coupled to the processor 710, for providing instructions to the processor 710 to process the following process steps: acquiring overhaul data of a preset position of a boiler, wherein the overhaul data are different types of overhaul data detected at the preset position according to a time sequence; and determining the thinning value of the preset position according to the overhaul data by utilizing a pre-trained three-dimensional convolution neural network model.
Optionally, the operation of determining the thinning value at the preset position according to the overhaul data by using a pre-trained three-dimensional convolutional neural network model includes: generating corresponding overhaul data vectors according to the overhaul data detected at the preset position at each time point; arranging the maintenance data vectors corresponding to the time points according to the time sequence to generate a maintenance data vector sequence corresponding to a preset position; and inputting the overhaul data vector sequence into the three-dimensional convolutional neural network model, and taking the output value of the full connecting layer of the three-dimensional convolutional neural network as the thinning value of the preset position.
Optionally, training the three-dimensional convolutional neural network model by: acquiring historical overhaul data of each part of the boiler; generating a training data set and a testing data set for training the three-dimensional convolution neural network model according to historical overhaul data; and training the three-dimensional convolution neural network model by utilizing the training data set and the test data set.
Optionally, the operation of generating a training data set and a testing data set for training the three-dimensional convolutional neural network model according to the historical overhaul data includes: preprocessing historical overhaul data, wherein the preprocessing comprises abnormal value detection and missing value processing; and carrying out normalization processing on the preprocessed data to generate a training data set and a test data set.
Optionally, the operation of training the three-dimensional convolutional neural network model by using the training data set and the test data set includes: respectively calculating the training data set and the test data set through a three-dimensional convolution neural network model to obtain output results, and comparing the mean square errors of the output results of the training data set and the test data set; and adjusting the weight matrix in the three-dimensional convolutional neural network model according to the condition of the mean square error.
Therefore, according to the embodiment, the maintenance data of each part of the boiler is acquired according to the time sequence without analyzing the pipe wall corrosion factors, and the thinning data of each part of the boiler is predicted in an artificial intelligence analysis mode according to the maintenance data of each part of the boiler by utilizing the pre-trained three-dimensional convolutional neural network model. Therefore, the accuracy of boiler thinning prediction is effectively improved. The technical problem that the method for predicting the boiler thinning by analyzing the pipe wall corrosion factors and combining a mathematical physical method to establish a model in the prior art is low in accuracy is solved.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, which can store program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110655053.7A CN113761785A (en) | 2021-06-11 | 2021-06-11 | Method and device for determining thinning value of boiler and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110655053.7A CN113761785A (en) | 2021-06-11 | 2021-06-11 | Method and device for determining thinning value of boiler and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113761785A true CN113761785A (en) | 2021-12-07 |
Family
ID=78787444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110655053.7A Pending CN113761785A (en) | 2021-06-11 | 2021-06-11 | Method and device for determining thinning value of boiler and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761785A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117309195A (en) * | 2023-11-30 | 2023-12-29 | 中控技术股份有限公司 | Detection method and device of temperature measuring instrument and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063824A (en) * | 2018-07-25 | 2018-12-21 | 深圳市中悦科技有限公司 | Creation method, device, storage medium and the processor of deep layer Three dimensional convolution neural network |
| CN109559302A (en) * | 2018-11-23 | 2019-04-02 | 北京市新技术应用研究所 | Pipe video defect inspection method based on convolutional neural networks |
| CN111855547A (en) * | 2020-07-16 | 2020-10-30 | 东北电力大学 | Visual intelligent monitoring system and method for dust accumulation, corrosion and wear state of medium and low temperature flue gas heat exchange equipment |
| KR20210010194A (en) * | 2019-07-19 | 2021-01-27 | 울산과학기술원 | Deep-learning based Reheater Tube Leak detection Method for Thermoelectric power plant And Apparatus Of Thereof |
| CN112633131A (en) * | 2020-12-18 | 2021-04-09 | 宁波长壁流体动力科技有限公司 | Underground automatic tracking method based on deep learning video recognition |
| CN112765872A (en) * | 2020-11-17 | 2021-05-07 | 苏州西热节能环保技术有限公司 | Method and device for predicting wall thickness of water wall tube in furnace and readable storage medium |
-
2021
- 2021-06-11 CN CN202110655053.7A patent/CN113761785A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063824A (en) * | 2018-07-25 | 2018-12-21 | 深圳市中悦科技有限公司 | Creation method, device, storage medium and the processor of deep layer Three dimensional convolution neural network |
| CN109559302A (en) * | 2018-11-23 | 2019-04-02 | 北京市新技术应用研究所 | Pipe video defect inspection method based on convolutional neural networks |
| KR20210010194A (en) * | 2019-07-19 | 2021-01-27 | 울산과학기술원 | Deep-learning based Reheater Tube Leak detection Method for Thermoelectric power plant And Apparatus Of Thereof |
| CN111855547A (en) * | 2020-07-16 | 2020-10-30 | 东北电力大学 | Visual intelligent monitoring system and method for dust accumulation, corrosion and wear state of medium and low temperature flue gas heat exchange equipment |
| CN112765872A (en) * | 2020-11-17 | 2021-05-07 | 苏州西热节能环保技术有限公司 | Method and device for predicting wall thickness of water wall tube in furnace and readable storage medium |
| CN112633131A (en) * | 2020-12-18 | 2021-04-09 | 宁波长壁流体动力科技有限公司 | Underground automatic tracking method based on deep learning video recognition |
Non-Patent Citations (3)
| Title |
|---|
| 刘荣辉: "《大数据架构技术与实例分析》", 31 January 2018, 东北师范大学出版社, pages: 162 - 163 * |
| 闰佳瑛，朱希安: "基于3DCNN的锅炉再热器管壁减薄预测", 《北京信息科技大学学报（自然科学版）》, vol. 36, no. 1, pages 75 - 78 * |
| 高仕斌: "《中国智能铁路核心技术 高速铁路 智能牵引供电系统》", 31 December 2020, 西南交通大学出版社, pages: 91 - 92 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117309195A (en) * | 2023-11-30 | 2023-12-29 | 中控技术股份有限公司 | Detection method and device of temperature measuring instrument and electronic equipment |
| CN117309195B (en) * | 2023-11-30 | 2024-04-12 | 中控技术股份有限公司 | Detection method and device of temperature measuring instrument and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021204010A1 (en) | Time series anomaly detection method and apparatus, and computer device and storage medium | |
| Wang et al. | C-ECAFormer: A new lightweight fault diagnosis framework towards heavy noise and small samples | |
| CN118657404B (en) | A multi-modal power grid health assessment and analysis method | |
| CN110780164B (en) | Insulator infrared fault location and diagnosis method and device based on YOLO | |
| CN108776831A (en) | A kind of complex industrial process Data Modeling Method based on dynamic convolutional neural networks | |
| CN116186946B (en) | Hydraulic system fault diagnosis method and system based on diagnosis model | |
| Huang et al. | Attention-augmented recalibrated and compensatory network for machine remaining useful life prediction | |
| Zhang et al. | Spatial-temporal dual-channel adaptive graph convolutional network for remaining useful life prediction with multi-sensor information fusion | |
| He et al. | Remaining useful life prediction for bearing based on automatic feature combination extraction and residual multi-Head attention GRU network | |
| Mansouri et al. | A deep explainable model for fault prediction using IoT sensors | |
| CN112070156B (en) | Gas emission concentration prediction method and system based on GRU network | |
| CN113761785A (en) | Method and device for determining thinning value of boiler and storage medium | |
| Liao et al. | Nonparametric and semi-parametric sensor recovery in multichannel condition monitoring systems | |
| Pang et al. | RUL prediction for bivariate degradation process considering individual differences | |
| CN117612037A (en) | Power distribution network fault positioning method, device, equipment and readable storage medium | |
| Hu et al. | Research on the fault identification method of oil pumping unit based on residual network | |
| CN110222814A (en) | The pipe recognition methods again of Ethylene Cracking Furnace Tubes based on embedded DCNN | |
| CN114818116A (en) | Aircraft engine failure mode identification and service life prediction method based on joint learning | |
| CN115130671A (en) | Training method of equipment comprehensive efficiency prediction model, storage medium and electronic equipment | |
| Zhong et al. | DCSN: Focusing on hard samples mining in small-sample fault diagnosis of marine engine | |
| CN111310907A (en) | Microwave assembly fault diagnosis method, device and equipment | |
| CN118760677B (en) | Missing data complement method based on sparse topology space-time attention mechanism | |
| CN117011805B (en) | Data exception evaluation method, device, equipment and readable storage medium | |
| CN116701910B (en) | A method and system for generating adversarial samples based on dual feature selection | |
| Gong et al. | Toward safe human-robot interaction: More efficient safety monitoring technology for robotic arms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 751400 Hui Min Xiang, Ningdong Town, Lingwu City, Yinchuan City, Ningxia Hui Autonomous Region Applicant after: Guoneng Ningxia yuanyanghu first power generation Co.,Ltd. Address before: 751400 Hui Min Xiang, Ningdong Town, Lingwu City, Yinchuan City, Ningxia Hui Autonomous Region Applicant before: SHENHUA GUONENG NINGXIA COAL POWER CO.,LTD. |
|
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhuang Wenbin Inventor after: Yin Jiahan Inventor after: Yin Huimin Inventor before: Yin Huimin |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211207 |