High-pressure jet pipeline pressure warning method and system

Abstract

The present invention relates to online intelligent detection and discloses a high-pressure jet pipeline pressure early warning method and system to provide early warning of possible pressure drops or fluctuations. The method includes: training, verifying, and testing a surface quality rating model based on image data of the target surface before and after cleaning at different jet pressure levels in a data set; constructing an observation sequence based on the rating data before and after cleaning obtained from any cleaning area of ​​the target surface based on the trained surface quality rating model, combined with the pressure data of the high-pressure pump during the cleaning process; estimating three key parameters of the jet tube pressure estimation HMM model based on an unsupervised learning method for a corresponding number of observation sequences; then decoding the implicit state of the real-time observation sequence within a time window based on the key parameters of the HMM model to obtain a jet tube pressure state sequence; and then judging whether the pressure is abnormal and executing early warning processing based on the value changes of the jet tube pressure state sequence.

Description

Technical Field

[0001] The present invention relates to the field of online intelligent detection technology, and in particular to a high-pressure jet pipeline pressure early warning method and system. Background Art

[0002] In a high-pressure abrasive water jet surface cleaning device, the cleaning process occurs in a cleaning station. Each cleaning station contains a set of jet pipes, and the terminal of each jet pipe is connected to a jet nozzle. A high-pressure pump generates high-pressure water, which is transported to the jet nozzle through the jet pipe. After mixing with the abrasive, it impacts the steel plate to remove surface impurities. Each cleaning station can complete the cleaning of a strip-shaped sub-area along the conveying direction of the steel plate. The cleaning effect depends largely on the pressure of the high-pressure water in the jet pipe. In a surface cleaning device, ideally, the pressure of each jet pipe in the same group should be uniform and close. However, due to pipeline wear, the presence of foreign matter, turbulence effects, burst pipes and other problems, the pressure of some jet pipes drops or fluctuates, resulting in a decrease in cleaning quality.

[0003] In industry, perforated pressure gauges or pressure sensors are commonly used to measure pressure in metal high-pressure pipelines. However, in high-pressure water jetting devices, the jet nozzles require frequent disassembly, maintenance, and angle adjustment. Therefore, the jet tube connected to the jet nozzle is made of non-metallic materials. Partial perforation will weaken the structural strength, making it more likely to cause leakage problems during long-term use. Therefore, pressure gauges or pressure sensors are only suitable for jet tube pressure testing during the experimental stage and are not feasible as long-term online detection devices. Summary of the Invention

[0004] The purpose of the present invention is to disclose a high-pressure jet pipeline pressure early warning method and system, which can evaluate the pressure of the jet tube by observing the time series data of the surface cleaning quality and provide early warning for possible pressure drops or fluctuations.

[0005] To achieve the above-mentioned purpose, the high-pressure jet pipeline pressure early warning method disclosed in the present invention includes:

[0006] Step S1, training, validating and testing a surface quality rating model based on image data of the target surface before and after cleaning at different jet pressure levels in the data set;

[0007] Step S2: constructing an observation sequence based on the rating data before and after cleaning obtained from any cleaning area of ​​the target surface based on the trained surface quality rating model and combining it with the pressure data of the high-pressure pump during the cleaning process;

[0008] Step S3: For a corresponding number of observation sequences, estimate the initial state distribution vector, state transition probability matrix, and observation probability distribution of the jet tube pressure estimation HMM model based on an unsupervised learning method;

[0009] Step S4: Decode the implicit state of the real-time observation sequence within a time window based on the initial state distribution vector, state transition probability matrix, and observation probability distribution of the HMM (Hidden Markov Model) model to obtain the jet tube pressure state sequence. Then, determine whether the pressure is abnormal based on the value changes of the jet tube pressure state sequence. If so, perform early warning processing.

[0010] Preferably, the time series data formed by the corresponding number of observation sequences The form is: ;in, is the surface quality rating before cleaning, is the surface quality rating after cleaning, Indicates the cleaning effect. Indicates the set pressure of the high-pressure pump. T represents the number of data samples, represents the time index of the corresponding sample in the time series data, and .

[0011] Preferably, the unsupervised learning method in step S3 adopts the Baum-Welch algorithm, and the algorithm for decoding the implicit state in step S4 adopts the Viterbi algorithm.

[0012] Optionally, the target is a steel plate, and the jet tube pressure states include five states: low pressure, relatively low pressure, average pressure, relatively high pressure, and high pressure. Furthermore, the same steel plate corresponds to at least two camera positions during the cleaning process. The data set in step S1 includes image data of the area corresponding to each camera position before and after cleaning. In step S4, the real-time operating status of each camera position is synchronously monitored online using parallel threads.

[0013] To achieve the above objectives, the present invention also discloses a high-pressure jet pipeline pressure warning system, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor implements the above method when executing the computer program.

[0014] Preferably, the high-pressure jet pipeline pressure warning system of the present invention specifically includes:

[0015] Data acquisition subsystem: includes a camera device, an image acquisition module, a historical database module, and a data processing module; wherein the image acquisition module is used to collect real-time image data of the steel plate surface before and after cleaning, the historical database module is used to store the steel plate surface images before and after cleaning and the high-pressure pump pressure data, and the data processing module is used to pre-process the images of the steel plate before and after cleaning;

[0016] The steel plate surface quality evaluation subsystem includes a surface image dataset and a surface quality evaluation network. The surface image dataset consists of pre- and post-cleaning sub-images segmented by the steel plate conveying direction and cleaning position, along with the corresponding quality labels. The surface quality evaluation network is constructed using a deep learning architecture. The network is trained and evaluated using the dataset, and a surface quality evaluation model is generated when the required quality is met.

[0017] Jet tube pressure interval estimation subsystem: used to train the pressure estimation model based on the time series data set. The time series data of the time series data set is ,in, is the surface quality rating before cleaning, is the surface quality rating after cleaning, Indicates the cleaning effect, and , Indicates the set pressure of the high-pressure pump. represents the number of data samples, Represents the time index of the corresponding sample in the time series data. The pressure estimation model is trained using the Baum-Welch algorithm. By maximizing the likelihood function of the observation sequence, the three key parameters of the HMM model, namely the initial state distribution vector π, the state transition probability matrix A, and the observation probability distribution B, are estimated. Finally, the HMM model for the jet tube pressure state estimation is determined.

[0018] The jet tube pressure warning subsystem for time series data acquisition and real-time pressure estimation includes time series data acquisition and real-time pressure estimation modules. The appropriate time window length is selected according to the equipment operation experience. , according to the window length and time sequence, the real-time observation time series data on cleaning quality is formed , and then decode the implicit pressure state according to the Viterbi algorithm to obtain the pressure state sequence ,according to According to the changes in the medium pressure state, low pressure or pressure fluctuation alarm will be issued.

[0019] The present invention has the following beneficial effects:

[0020] 1. According to the surface quality changes of the steel plate and other targets before and after cleaning, the pressure of the jet tube can be monitored according to the cleaning stations in the cleaning device, which helps to achieve rapid early warning and fault location.

[0021] 2. It overcomes the problem that high-pressure jet tubes cannot be installed with online pressure detection instruments, and realizes online real-time estimation of the pressure of high-pressure jet tubes, which is conducive to further ensuring the cleaning quality.

[0022] 3. In-depth analysis of the calculated changes in the jet tube pressure state is beneficial for further evaluating the operating status of the high-pressure water jet surface cleaning device; for example, early warnings of low pressure or pressure fluctuations can be issued based on the changes in the decoded implicit pressure state.

[0023] The present invention will be described in further detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0025] Figure 1 It is a specific deployment diagram of the actual application scenario of the high-pressure jet pipeline warning system disclosed in the embodiment of the present invention in the cleaning of wide steel plates.

[0026] Figure 2 yes Figure 1 Schematic diagram of the partitioning of medium-width steel plates.

[0027] Figure 3 It is a flow chart of the high-pressure jet pipeline early warning method disclosed in an embodiment of the present invention.

[0028] Figure 4 This is a specific functional block diagram of each subsystem in the high-pressure jet pipeline early warning system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The embodiments of the present invention are described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many different ways as defined and covered by the claims.

[0030] Example 1

[0031] This embodiment discloses a high-pressure jet pipeline early warning method applied to wide steel plates, comprising the following steps:

[0032] Step 1: Use different pressure ranges for cleaning, collect images before and after cleaning, and create a data set for the surface quality rating model. The specific process is:

[0033] (1) Based on the operating experience of the surface cleaning device, the pressure of the high-pressure pump is divided into several intervals from low to high. At each different pressure level, a set number of steel plates are cleaned, and images of each steel plate before and after cleaning are collected.

[0034] (2) According to the number m of cleaning stations in the surface cleaning device, the steel plate image is divided into m rectangular sub-images along the width direction (transport direction) (i.e., one station is responsible for cleaning the steel plate area corresponding to one rectangular sub-image). The surface quality of the sub-images is judged based on experience, and these sub-images are manually labeled with surface quality grade labels to create a data set D1, that is, D1 consists of the sub-images segmented from the steel plate image and the surface quality grade labels corresponding to the sub-images.

[0035] Step 2: Build a deep learning network for surface cleaning quality rating, train the network using dataset D1, and generate a deployable surface quality rating model.

[0036] Preferably, in this step, D1 can be divided into a training set, a validation set, and a test set in a ratio of 8:1:1 to train the deep learning network. The input of the network is the image data, i.e., the rectangular sub-images of the steel plate before and after cleaning described in step 1. The output layer of the network is a fully connected layer + Softmax activation. The output cleaning quality category is the surface quality classification, i.e., the label content of the surface quality grade described in step 1. The loss function is the cross entropy loss, and the training goal is to make the loss function At the very least, AdamW can be used as the optimizer, and the validation set can be used to evaluate network performance, including accuracy and F1-Score. Once the requirements are met, the test set can be used for independent testing to evaluate the generalization ability of the network. Once the requirements are met, a deployable surface quality rating model in ONNX format is generated.

[0037] Loss Function Can be: Among them, the tag , c is the total number of label categories for surface quality ratings, and the predicted probability distribution is a probability vector, each element of which represents the predicted probability of a surface quality grade category.

[0038] Step 3: Use the surface quality rating data output from step 2 as observable input features to construct input data sequence samples, and automatically optimize the three key parameters of the HMM model through the Baum-Welch algorithm to generate observable data. Mapping to the jet tube pressure range The HMM model of the hidden state space of . The specific process is:

[0039] (1) Constructing observable input feature sequences ,in, Indicates the time index of the corresponding sample in the time series data, Represents the number of data samples in the sequence, is the surface quality rating before cleaning, is the surface quality rating after cleaning, , indicating the cleaning effect, Indicates the set pressure of the high-pressure pump and specifies the implicit jet tube pressure state sequence , ~ Respectively represent (low pressure, lower, average, higher, high), that is, the pressure of the jet tube is The value of the moment belongs to ~ One of the five states.

[0040] (2) Input sequence through features The three key parameters of the jet tube pressure estimation HMM model are estimated by an unsupervised learning method. The three key parameters include the initial state distribution vector π, the state transition probability matrix A and the observation probability distribution B.

[0041] During the processing, first Normalize to get the input feature input sequence represented by real values , and randomly initialize π, A and B, set the maximum number of iterations and convergence threshold, and then use the Baum-Welch algorithm to estimate the parameters π, A and B of the HMM model by maximizing the likelihood function of the observation sequence.

[0042] For example, if the range of the jet tube pressure state is specified as S = (low pressure, lower pressure, average pressure, higher pressure, high pressure), then the number of states N = 5, and the initial state distribution row vector is The state transition probability matrix A is a 5×5 matrix, and the observation probability distribution B represents each implicit state of the jet tube pressure. Generate observable input features The probability of the observed variable It is a continuous four-dimensional feature vector (mass before cleaning, mass after cleaning, change in cleaning mass, high-pressure pump set pressure), so B is composed of each implicit state The mean and covariance matrix of is randomly initialized when using the Baum-Welch algorithm. , since the pressure state transfer of the jet tube is mainly concentrated in the adjacent states (the pressure change is relatively gentle), the matrix A is randomly initialized and normalized, for example:

[0043] .

[0044] When using the Baum-Welch algorithm, the input sequence is based on the characteristics The data set updates the values ​​of π, A, and B.

[0045] Step 4: Use the HMM model to estimate the surface quality observable sequence input in real time to obtain the jet tube pressure state sequence.

[0046] In this step, the sequence length (which can be adjusted empirically) is defined as The specific process is: use the Viterbi algorithm to decode the implicit state and find the most likely pressure state sequence , that is, maximize ,in, For the The specific process can be divided into four steps: initialization, recursion, termination and backtracking.

[0047] initialization: .

[0048] Recursion: ; .in, ; Record from the start time to the current time, and the current state is The maximum probability path when ; Record the previous state Transfer to current state To obtain the maximum probability.

[0049] Termination state ( = ): .

[0050] Backtracking = ~1): Path restoration of the maximum possible jet tube pressure state sequence ; .

[0051] In the above formula, π, A, and B are the parameters of the HMM model obtained after iterating based on the training data in step 3. After the HMM model is trained using a set of input feature sequence data, these three parameters π, A, and B are fixed and remain unchanged during the pressure state estimation. However, the HMM model can be retrained using new input feature sequence data and can therefore be changed after retraining.

[0052] Step 5: During the online detection process, the jet tube pressure state sequence within a time window is obtained according to the HMM model The pressure abnormality is judged based on the value change and an early warning is output.

[0053] This step can divide the judgment of early warning into low pressure and pressure fluctuation. Among them, the change rule of the jet tube pressure state sequence corresponding to low pressure is: if within the current time window The value of shows a decrease twice in a row, and the subsequent pressure state continues to be at a lower level or below, triggering a low pressure alarm, and the corresponding jet pressure pipe needs to be repaired. The change rule of the jet pipe pressure state sequence corresponding to the pressure fluctuation is: if within the current time window The value fluctuates repeatedly between two non-adjacent states, triggering a pressure fluctuation alarm, which requires systematic investigation.

[0054] A specific application scenario based on the above technical core is as follows Figure 1 As shown, the meaning of each index is: 1 represents the front visual detection device at the cleaning inlet end, 2 represents the rear visual detection device at the cleaning outlet end, 3 represents the high-pressure jet tube, 4 represents the high-pressure jet tube pressure warning system, 5 represents the conveyor roller, 6 represents the steel plate before cleaning, 7 represents the steel plate after cleaning by the high-pressure abrasive water jet, 8 represents the cleaning position in the high-pressure water jet surface cleaning device. Only the jet tube in position No. 1 is drawn in the figure, but the arrangement principle and method of the jet tubes in other positions are the same as those in position No. 1.

[0055] Figure 2 In the figure, area 1 to area 4 represent four strip areas virtually divided along the steel plate conveying direction, indicating that each area consists of Figure 2 The corresponding cleaning stations in the cleaning machine are responsible for cleaning. Each cleaning station is equipped with a set of cleaning nozzles. Each set of jet nozzles is connected to a set of high-pressure jet pipes. Each set of high-pressure jet pipes is connected to a high-pressure pump. The total width of the steel plate is 2 meters. The steel plate must pass through 4 cleaning stations before the entire area can be cleaned.

[0056] The data set in step 1 can be constructed by: keeping the set steel plate conveying speed unchanged, controlling the operating pressure of the high-pressure pump determined by experience to be between 40 and 50 MPa, dividing the pressure of the high-pressure pump into 20 gears, each gear is 0.5 MPa, and a total of 20 gears, starting from 40 MPa, cleaning 10 steel plates in each gear until the high-pressure pump pressure exceeds 50 MPa, using Figure 1 The front and rear cameras in the system shoot the surface of the steel plate, obtaining a total of 400 steel plate images. In addition, relevant image data can be retrieved from the historical database to further increase the image sample.

[0057] Then the images before and after cleaning in the sample are processed according to Figure 2As shown, the surface quality of each sub-image is evaluated using a 7-category label set Q = {very poor quality, poor quality, relatively poor quality, average, good quality, good quality, and very good quality}. The data samples are divided into a dataset D1 consisting of sub-images before and after cleaning and their corresponding quality grade labels.

[0058] Furthermore, the EfficientNet network architecture can be used to train a surface cleaning quality assessment model. Using the model module of the Keras library in the deep learning framework TensorFlow, the EfficientNet model is loaded. The network output layer is constructed using the Dense interface. The model module's fit interface is used to set hyperparameters, train the model, and verify model performance. If the model meets the predetermined performance criteria, the surface cleaning quality assessment model constructed with EfficientNet is exported as a deployable model in ONNX format.

[0059] Afterwards, the data set D1 in the embodiment is further processed to construct the data set D2= .

[0060] Through the data set D2= The three key parameters of the HMM model for jet tube pressure estimation are estimated by the unsupervised learning method, including the initial state distribution vector π, the state transition probability matrix A and the observation probability distribution B. Normalize to get the input feature input sequence represented by real values ,For example When the evaluation value of is "poor quality", the normalized result is , randomly initialize π, A, B, set the maximum number of iterations and convergence threshold, and then use the Baum-Welch algorithm to estimate the parameters π, A, B of the HMM model by maximizing the likelihood function of the observation sequence. The parameter estimation process can create an HMM model through the GaussianHMM function provided by the hmmlearn library and train it using the model's fit function.

[0061] against Figure 1 The four sets of high-pressure jet tubes in the cleaning device are used to collect observation time series data. Assuming that the length of the acquisition time window is defined as 10, the acquisition data of each set of jet tubes is ,in They are The surface quality rating and quality change before and after cleaning corresponding to each position are input into the trained HMM model to obtain four sets of pressure estimation data sequences of the jet tube. , each of which The value of pressure is one of the following five: low pressure, lower pressure, average pressure, higher pressure, and high pressure. The process can be obtained through the predict function of the trained HMM model.

[0062] In this way, the window of data observation can be slid to continuously obtain the pressure state of the jet tube. , to achieve online pressure estimation of four sets of jet tubes. For example, in a specific solution, the pressure states of the four sets of jet tubes are obtained as follows:

[0063] Group 1: .

[0064] Group 2: .

[0065] Group 3: .

[0066] Group 4: .

[0067] In the third group of jet tubes, the pressure dropped twice in succession and continued to remain in a lower pressure range. It can be analyzed that there may be a low pressure failure, so a low pressure warning is issued for the third group of jet tubes.

[0068] Example 2

[0069] This embodiment discloses a high-pressure jet pipeline pressure warning system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a similar method to the above embodiment is implemented. The core content can be summarized as follows: Figure 3 The following steps are shown:

[0070] Step S1: Training, validating, and testing a surface quality rating model based on pre- and post-cleaning image data of the target surface at different jet pressure levels in the dataset. Optionally, the target includes, but is not limited to, the steel plates described in the above embodiments. If the same steel plate is cleaned by at least two camera positions, the dataset includes pre- and post-cleaning image data for the area corresponding to each camera position.

[0071] Step S2: construct an observation sequence based on the rating data before and after cleaning obtained based on the trained surface quality rating model for any cleaning area of ​​the target surface and the pressure data of the high-pressure pump during the cleaning process.

[0072] Preferably, the time series data formed by the corresponding number of observation sequences The form is: ;in, is the surface quality rating before cleaning, is the surface quality rating after cleaning, Indicates the cleaning effect. Indicates the set pressure of the high-pressure pump. T represents the number of data samples, represents the time index of the corresponding sample in the time series data, and .

[0073] Step S3: For a corresponding number of observation sequences, estimate the initial state distribution vector, state transition probability matrix and observation probability distribution of the jet tube pressure estimation HMM model based on an unsupervised learning method.

[0074] Preferably, the unsupervised learning method of this step adopts the Baum-Welch algorithm; the jet tube pressure state includes five states: low pressure, relatively low, average, relatively high and high.

[0075] Step S4: Decode the implicit state of the real-time observation sequence within a time window based on the initial state distribution vector, state transition probability matrix, and observation probability distribution of the HMM (Hidden Markov Model) model to obtain the jet tube pressure state sequence. Then, determine whether the pressure is abnormal based on the value changes of the jet tube pressure state sequence. If so, perform early warning processing.

[0076] Preferably, the algorithm for decoding the implicit state in this step adopts the Viterbi algorithm. Furthermore, this step performs synchronous online detection of the real-time operating status of each machine position using parallel threads.

[0077] like Figure 4 As shown, a specific high-pressure jet pipeline pressure warning system includes:

[0078] Data acquisition subsystem: includes a camera device, an image acquisition module, a historical database module and a data processing module; among them, the image acquisition module is used to collect real-time image data of the steel plate surface before and after cleaning, the historical database module is used to store the steel plate surface images before and after cleaning and the high-pressure pump pressure data, and the data processing module is used to pre-process the images of the steel plate before and after cleaning.

[0079] Steel plate surface quality evaluation subsystem: includes a surface image dataset and a surface quality evaluation network. The surface image dataset consists of sub-images before and after cleaning, which are divided according to the steel plate conveying direction and cleaning position, and the corresponding quality labels of the images. The surface quality evaluation network is constructed by a network based on a deep learning architecture. The network is trained and evaluated using the dataset. Once the requirements are met, a surface quality evaluation model is generated.

[0080] Jet tube pressure interval estimation subsystem: used to train the pressure estimation model based on the time series data set. The time series data of the time series data set is ,in, is the surface quality rating before cleaning, is the surface quality rating after cleaning, Indicates the cleaning effect, and , Indicates the set pressure of the high-pressure pump. represents the number of data samples. The pressure estimation model is trained using the Baum-Welch algorithm. By maximizing the likelihood function of the observation sequence, the three key parameters of the HMM model, namely the initial state distribution vector π, the state transition probability matrix A, and the observation probability distribution B, are estimated. Finally, the HMM model for jet tube pressure state estimation is determined.

[0081] The jet tube pressure warning subsystem for time series data acquisition and real-time pressure estimation includes time series data acquisition and real-time pressure estimation modules. The appropriate time window length is selected according to the equipment operation experience. , according to the window length and time sequence, the real-time observation time series data on cleaning quality is formed , and then decode the implicit pressure state according to the Viterbi algorithm to obtain the pressure state sequence ,according to According to the changes in the medium pressure state, low pressure or pressure fluctuation alarm will be issued.

[0082] In summary, the high-pressure jet pipeline pressure warning method and system disclosed in the above embodiments of the present invention respectively have at least the following beneficial effects:

[0083] 1. According to the surface quality changes of the steel plate and other targets before and after cleaning, the pressure of the jet tube can be monitored according to the cleaning stations in the cleaning device, which helps to achieve rapid early warning and fault location.

[0084] 2. It overcomes the problem that high-pressure jet tubes cannot be installed with online pressure detection instruments, and realizes online real-time estimation of the pressure of high-pressure jet tubes, which is conducive to further ensuring the cleaning quality.

[0085] 3. In-depth analysis of the calculated changes in the jet tube pressure state is beneficial for further evaluating the operating status of the high-pressure water jet surface cleaning device; for example, early warnings of low pressure or pressure fluctuations can be issued based on the changes in the decoded implicit pressure state.

[0086] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A high-pressure jet pipeline pressure early warning method, characterized in that: include: Step S1, training, validating and testing a surface quality rating model based on image data of the target surface before and after cleaning at different jet pressure levels in the data set; Step S2: constructing an observation sequence based on the rating data before and after cleaning obtained from any cleaning area of ​​the target surface based on the trained surface quality rating model and combining it with the pressure data of the high-pressure pump during the cleaning process; Step S3: For a corresponding number of observation sequences, estimate the initial state distribution vector, state transition probability matrix, and observation probability distribution of the jet tube pressure estimation HMM model based on an unsupervised learning method; Step S4: Decode the implicit state of the real-time observation sequence within a time window based on the initial state distribution vector, state transition probability matrix, and observation probability distribution of the HMM model to obtain the jet tube pressure state sequence. Then, determine whether the pressure is abnormal based on the value changes of the jet tube pressure state sequence. If so, perform early warning processing; Among them, the time series data formed by the corresponding number of observation sequences The form is: ;in, is the surface quality rating before cleaning, is the surface quality rating after cleaning, Indicates the cleaning effect. Indicates the set pressure of the high-pressure pump. T represents the number of data samples, represents the time index of the corresponding sample in the time series data, and .

2. The high-pressure jet pipeline pressure early warning method according to claim 1 is characterized in that: The unsupervised learning method in step S3 adopts the Baum-Welch algorithm.

3. The high-pressure jet pipeline pressure early warning method according to claim 1 is characterized in that: The algorithm for decoding the implicit state in step S4 adopts the Viterbi algorithm.

4. The high-pressure jet pipeline pressure early warning method according to any one of claims 1 to 3, characterized in that: The target is a steel plate, and the pressure state of the jet tube includes five states: low pressure, lower pressure, average pressure, higher pressure and high pressure.

5. The high-pressure jet pipeline pressure early warning method according to any one of claims 1 to 3, characterized in that: The same steel plate corresponds to at least two camera positions during the cleaning process. The data set in step S1 includes image data of the area corresponding to each camera position before and after cleaning. In step S4, the real-time operating status of each camera position is synchronously detected online using parallel threads.

6. A high-pressure jet pipeline pressure warning system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

7. The high-pressure jet pipeline pressure warning system according to claim 6, characterized in that: Specifically include: Data acquisition subsystem: includes a camera device, an image acquisition module, a historical database module, and a data processing module; wherein the image acquisition module is used to collect real-time image data of the steel plate surface before and after cleaning, the historical database module is used to store the steel plate surface images before and after cleaning and the high-pressure pump pressure data, and the data processing module is used to pre-process the images of the steel plate before and after cleaning; The steel plate surface quality evaluation subsystem includes a surface image dataset and a surface quality evaluation network. The surface image dataset consists of pre- and post-cleaning sub-images segmented by the steel plate conveying direction and cleaning position, along with the corresponding quality labels. The surface quality evaluation network is constructed using a deep learning architecture. The network is trained and evaluated using the dataset, and a surface quality evaluation model is generated when the required quality is met. Jet tube pressure interval estimation subsystem: used to train the pressure estimation model based on the time series data set. The time series data of the time series data set is ,in, is the surface quality rating before cleaning, is the surface quality rating after cleaning, Indicates the cleaning effect, and , Indicates the set pressure of the high-pressure pump. represents the number of data samples, Represents the time index of the corresponding sample in the time series data. The pressure estimation model is trained using the Baum-Welch algorithm. By maximizing the likelihood function of the observation sequence, the three key parameters of the HMM model, namely the initial state distribution vector π, the state transition probability matrix A, and the observation probability distribution B, are estimated. Finally, the HMM model for the jet tube pressure state estimation is determined. The jet tube pressure warning subsystem for time series data acquisition and real-time pressure estimation includes time series data acquisition and real-time pressure estimation modules. The appropriate time window length is selected according to the equipment operation experience. , according to the window length and time sequence, the real-time observation time series data on cleaning quality is formed , and then decode the implicit pressure state according to the Viterbi algorithm to obtain the pressure state sequence ,according to According to the changes in the medium pressure state, low pressure or pressure fluctuation alarm will be issued.

Images