Method and system for determining expected service life of factory building drainage system

Abstract

The invention provides a method and system for determining the expected service life of a factory building drainage system, and the method comprises the steps: collecting the operation state data of the factory building drainage system, and carrying out the preprocessing of the operation state data, and obtaining the preprocessed operation state data; decomposing the preprocessed operation state data by using a UPEMD algorithm to obtain each modal component signal, extracting a characteristic modal component from each component signal by using a kernel principal component analysis method, and then constructing an operation state dimensionality reduction data matrix of the collection plant drainage system based on the characteristic modal component; substituting the operation state dimensionality reduction data matrix into a pre-trained drainage efficiency prediction model to obtain a drainage efficiency value of the plant drainage system; and determining the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system. According to the technical scheme, the calculation precision of the drainage efficiency value and the expected service life is improved.

Description

Technical Field

[0001] The present application relates to the technical field of predictive maintenance of plant drainage systems, and in particular to a method and system for determining the expected service life of a plant drainage system. Background Art

[0002] In modern industrial production, the stable operation of the plant drainage system is crucial to ensure the continuity of the production process and the safety of the equipment. However, since the drainage system is usually in a complex and changeable operating environment, its reliability problem is becoming increasingly prominent. The traditional drainage system maintenance method mainly relies on regular manual inspection and post-maintenance, which is not only inefficient but also difficult to prevent sudden failures. The existing drainage system maintenance technology mainly includes the following aspects: First, manual inspection is a traditional means of drainage system maintenance, and the system problems are discovered through regular inspections by operators. However, this method has great limitations, such as being limited by personnel experience, inspection frequency and field of vision, making it difficult to fully and timely discover potential faults. Secondly, post-maintenance after the failure is another common maintenance method. Although this method can solve the failure that has occurred, it is often accompanied by high maintenance costs and long downtime, which has a great impact on production. Thirdly, although some companies have begun to use monitoring equipment to monitor the drainage system in real time, these monitoring systems can usually only provide real-time operation data, lacking in-depth analysis of the data and the ability to predict failures. Summary of the invention

[0003] The present application provides a method and system for determining the expected service life of a plant drainage system, so as to at least solve technical problems such as the need for personnel inspection, shutdown, and inaccurate analysis.

[0004] The first embodiment of the present application provides a method for determining the expected service life of a plant drainage system, the method comprising:

[0005] Collecting operation status data of the plant drainage system, and preprocessing the operation status data to obtain preprocessed operation status data;

[0006] The pre-processed operation status data is decomposed by using the UPEMD algorithm to obtain various modal component signals, and the characteristic modal components are extracted from the various component signals by using the kernel principal component analysis method, and then the dimension reduction data matrix of the operation status of the plant drainage system is constructed based on the characteristic modal components;

[0007] Substituting the dimension reduction data matrix of the operating status into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system;

[0008] The expected service life of the plant drainage system is determined based on the drainage efficiency value of the plant drainage system.

[0009] Preferably, the operating status data includes: drainage flow, drainage pipe water level change value, and pipeline inner wall corrosion data.

[0010] Furthermore, the training process of the drainage efficiency prediction model includes:

[0011] Obtaining the dimension-reduced data matrix of the operation status of the plant drainage system at each moment in the historical period and the drainage efficiency value corresponding to the dimension-reduced data matrix of the operation status of the plant drainage system at each moment;

[0012] The reduced dimension data matrix of the plant drainage system's operating status at each moment is used as input, the drainage efficiency value corresponding to the reduced dimension data matrix of the plant drainage system's operating status at each moment is used as output, and the improved IOOA algorithm is used to optimize the initial FEDformer model to obtain a trained drainage efficiency prediction model;

[0013] Among them, the improved IOOA algorithm is obtained by improving the OOA algorithm using a multi-difference Cauchy mutation strategy and a refraction reverse learning strategy.

[0014] Furthermore, the determining the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system includes:

[0015] Determining an estimated value of a performance decay rate constant of the powerhouse drainage system based on a drainage efficiency value of the powerhouse drainage system;

[0016] The expected service life of the plant drainage system is determined based on the estimated value of the performance decay rate constant of the plant drainage system.

[0017] Furthermore, the expected service life of the plant drainage system is calculated as follows:

[0018]

[0019] Where T is the expected service life of the plant drainage system, P0 is the initial drainage efficiency value of the drainage system, and P min is the preset drainage efficiency threshold, and k is the estimated value of the performance decay rate constant.

[0020] Furthermore, the method further comprises:

[0021] Determining the drainage efficiency level of the plant drainage system according to the drainage efficiency value of the plant drainage system;

[0022] Wherein, when the drainage efficiency value of the plant drainage system is greater than 90%, the drainage efficiency level of the plant drainage system is determined to be level one;

[0023] When the drainage efficiency value of the plant drainage system is less than or equal to 90% and greater than or equal to 70%, the drainage efficiency level of the plant drainage system is determined to be level 2;

[0024] When the drainage efficiency value of the plant drainage system is less than 70%, it is determined that the drainage efficiency level of the plant drainage system is level three.

[0025] Furthermore, the method further comprises:

[0026] When the drainage efficiency level of the plant drainage system is level one, a level one warning signal is generated;

[0027] When the drainage efficiency level of the plant drainage system is level 2, a level 2 warning signal is generated;

[0028] When the drainage efficiency level of the plant drainage system is level three, a level three warning signal is generated.

[0029] The second embodiment of the present application provides a system for determining the expected service life of a plant drainage system, including:

[0030] A collection module, used for collecting the operation status data of the plant drainage system, and preprocessing the operation status data to obtain the preprocessed operation status data;

[0031] A decomposition and dimensionality reduction module is used to decompose the pre-processed operating status data using a UPEMD algorithm to obtain various modal component signals, and to extract characteristic modal components from the various component signals using a kernel principal component analysis method, and then to construct a dimension reduction data matrix of the operating status of the plant drainage system based on the characteristic modal components;

[0032] A prediction module, used for substituting the dimension reduction data matrix of the operating status into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system;

[0033] A determination module is used to determine the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system.

[0034] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0035] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect of the present application.

[0036] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0037] The present application proposes a method and system for determining the expected service life of a plant drainage system, the method comprising: collecting the operating status data of the plant drainage system, and preprocessing the operating status data to obtain the preprocessed operating status data; using the UPEMD algorithm to decompose the preprocessed operating status data to obtain each modal component signal, and using the kernel principal component analysis method to extract the characteristic modal components from each component signal, and then constructing the operating status reduction data matrix of the collected plant drainage system based on the characteristic modal components; substituting the operating status reduction data matrix into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system; and determining the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system. The technical solution proposed in the present application, through real-time monitoring, data analysis and prediction, can identify potential faults in advance, improve the operating stability of the drainage system, reduce maintenance costs, and ensure the continuity of the production process and the safety of equipment.

[0038] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0040] Figure 1 A flowchart of a method for determining the expected service life of a plant drainage system according to an embodiment of the present application;

[0041] Figure 2 A schematic diagram of a FEDformer model provided according to an embodiment of the present application;

[0042] Figure 3 A detailed flow chart of a method for determining an expected service life of a plant drainage system provided according to an embodiment of the present application;

[0043] Figure 4 A first structural diagram of a system for determining the expected service life of a plant drainage system provided according to an embodiment of the present application;

[0044] Figure 5A second structural diagram of a system for determining the expected service life of a plant drainage system provided according to an embodiment of the present application;

[0045] Figure 6 This is a third structural diagram of a system for determining the expected service life of a factory drainage system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0047] The present application proposes a method and system for determining the expected service life of a plant drainage system, the method comprising: collecting the operating status data of the plant drainage system, and preprocessing the operating status data to obtain the preprocessed operating status data; using the UPEMD algorithm to decompose the preprocessed operating status data to obtain each modal component signal, and using the kernel principal component analysis method to extract the characteristic modal components from each component signal, and then constructing the operating status reduction data matrix of the collected plant drainage system based on the characteristic modal components; substituting the operating status reduction data matrix into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system; and determining the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system. The technical solution proposed in the present application, through real-time monitoring, data analysis and prediction, identifies potential faults in advance, improves the operating stability of the drainage system, reduces maintenance costs, and ensures the continuity of the production process and the safety of equipment.

[0048] The following describes a method and system for determining the expected service life of a plant drainage system according to an embodiment of the present application with reference to the accompanying drawings.

[0049] Embodiment 1

[0050] Figure 1 This is a flow chart of a method for determining the expected service life of a plant drainage system according to one embodiment of the present application. Figure 1 As shown, the method includes:

[0051] Step 1: Collect the operation status data of the plant drainage system, and pre-process the operation status data to obtain the pre-processed operation status data.

[0052] In the disclosed embodiment, the operating status data includes: drainage flow, drainage pipe water level change value, and pipeline inner wall corrosion data.

[0053] Further, preprocessing the operating status data includes:

[0054] The operating status data is cleaned, outliers are detected and processed, and the data is interpolated and smoothed to remove noise and make it easier to analyze.

[0055] Step 2: Use the UPEMD algorithm to decompose the preprocessed operating status data to obtain various modal component signals, and use the kernel principal component analysis method to extract characteristic modal components from the various component signals, and then construct the reduced dimension data matrix of the operating status of the collected plant drainage system based on the characteristic modal components.

[0056] It should be noted that the UPEMD algorithm is used to decompose the preprocessed operating status data to obtain the modal components. The UPEMD algorithm is to add a multi-frequency signal ω(t) as an interference wave to the original plant drainage system signal to improve the signal decomposition and construct a shielding signal. The specific formula is as follows:

[0057] ω(t,θ)=ε·cos(2πf w t+θ)

[0058] Where ω(t, θ) is the interference wave after adding the phase; t is time; θ is the phase; ε is the amplitude; f w is the frequency.

[0059] Assume n p is the number of phases, assuming n p phases are uniformly distributed in the 2π space, then θ k It is expressed as:

[0060]

[0061] Where p is the number of added phases; n p is a positive integer that is an integer power of 2; k is the phase value.

[0062] We further obtain ω(t,θ k )as follows:

[0063]

[0064] Add positive and negative interference waves ω(t, θ) to the input signal x(t) k ) to get the interference signal and The formula is as follows:

[0065]

[0066] Using the Empirical Mode Decomposition (EMD) method and Decompose each interference signal with different phase into modal components and The results are averaged to obtain The formula is as follows:

[0067]

[0068] In the formula, is the number of iterations, and N is the length of the data.

[0069] in and The formula is as follows:

[0070]

[0071] In the formula, is the EMD operator. Finally, n p indivual Take the average value to get the mth IMF component The formula is as follows:

[0072]

[0073] According to the above formula, n p The larger the value, the more times the modal decomposition is performed, and the more detailed the modal components are.

[0074] The method of extracting characteristic modal components from each component signal by using the kernel principal component analysis method, and then constructing a dimension reduction data matrix for collecting the operating status of the plant drainage system based on the characteristic modal components, includes:

[0075] First, the original vibration signal data is nonlinearly mapped from space R to high-dimensional space H. The original vibration signal sample x z (z=1,2,3……Z), the image in H space is φ(x z ), its covariance matrix is ​​expressed as:

[0076]

[0077] Afterwards, for the matrix C H Solve the characteristic equation: C H V=λ q V, where V represents the matrix eigenvector; λ q represents the eigenvalue.

[0078] Next, multiply both sides of the above equation by φ(x z ), that is: φ(x z )C H V=λq (φ(x z )·V) The formula after refining V is as follows:

[0079]

[0080] In the formula, γ, ω represent different spatial signal samples; α γ represents the existence coefficient.

[0081] In order to avoid the problem of not being able to express φ(x z ), introduce the kernel matrix K γω =[φ(x γ )φ(x ω )], we can get the following formula:

[0082] Zλ q α μ =K γω α μ

[0083] In the formula, α μ =(α1,α2,……α z ) T ;

[0084] Finally, feature dimensionality reduction and fusion are performed, and the feature values ​​are arranged in descending order. η is the cumulative contribution rate threshold. The cumulative contribution rate of the first J features in the total number of features Q is:

[0085]

[0086] Step 3: Substitute the dimension-reduced data matrix of the operating status into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system.

[0087] It should be noted that the training process of the drainage efficiency prediction model includes:

[0088] Obtaining the dimension-reduced data matrix of the operation status of the plant drainage system at each moment in the historical period and the drainage efficiency value corresponding to the dimension-reduced data matrix of the operation status of the plant drainage system at each moment;

[0089] The reduced-dimensional data matrix of the operating status of the plant drainage system at each moment is taken as input, and the drainage efficiency value corresponding to the reduced-dimensional data matrix of the operating status of the plant drainage system at each moment is output. The improved IOOA algorithm is used to optimize the training of the initial FEDformer model to obtain the trained drainage efficiency prediction model.

[0090] It should be noted that the improved IOA algorithm is obtained by improving the OOA algorithm using a multi-difference Cauchy mutation strategy and a refraction reverse learning strategy.

[0091] The specific process is as follows:

[0092] In order to enhance the ability of OOA to jump out of the local optimum, new osprey individuals are generated by difference, and then the characteristics of the Cauchy distribution with a wide variation range and strong perturbation ability are used to generate large jumps for the new individuals. The multi-difference Cauchy mutation formula is as follows:

[0093]

[0094] In the formula, Represents X i Individuals obtained after multi-difference Cauchy mutation; X D , X E , X F represents three individuals randomly selected from the population; x best represents the optimal individual position of the population; F represents the Cauchy operator, and the formula of F is as follows:

[0095]

[0096] Where r1 is a random number in the interval [0,1].

[0097] The individuals obtained by multi-difference Cauchy mutation of osprey individuals may be worse than the original individuals. Therefore, the greedy selection principle is used to compare the fitness values ​​of the new and old individuals. When the individual obtained after mutation is better than the original individual, it is replaced. The greedy selection formula is as follows:

[0098]

[0099] The OOA algorithm effectively increases the diversity of the population through the multi-difference Cauchy mutation strategy and improves the algorithm's ability to escape from local optimality.

[0100] In order to further improve the accuracy and convergence speed of the algorithm, a refraction reverse learning strategy is introduced at the end of each iteration. Refraction reverse learning is a reverse learning strategy based on the refraction principle of light. a and b are the upper and lower limits of the interval range, respectively. a X b is the image of XX' formed by the refraction of the interstitial matrix, with heights h' and h respectively. Assume that X and X a They correspond to the coordinate values ​​on the x-axis respectively. The refraction imaging principle formula is as follows:

[0101]

[0102] make represents the dynamic scaling factor, and its value is equal to t, which changes linearly with the current number of iterations. Then X a The formula is as follows:

[0103]

[0104] is equivalent to:

[0105]

[0106] By introducing the refraction reverse learning strategy, the balance between exploration and development can be ensured. The search radius is dynamically adjusted according to the number of iterations and the global optimal solution, so that the search range in the early iteration stage is larger, increasing the possibility of global search; while in the later iteration stage, the search range gradually decreases, which is conducive to more refined development of high-quality solutions.

[0107] It should be noted that the encoder of the FEDformer model adopts a multi-layer structure and can be defined as: l∈{1,2,3…,N}, represents the output of the encoder at the lth layer. X represents the low-dimensional data matrix obtained by decomposing and reducing the historical data of the drainage system. After being standardized and embedded into a dimension suitable for model input, it will be used as the input of the encoder. The frequency domain enhancement module, sequence decomposition module and feedforward neural network are used in sequence. The frequency domain enhancement module is used to extract the important features of the sequence. The seasonal terms are then decomposed through the sequence decomposition module and fully connected in the feedforward neural network. The specific expression is as follows:

[0108]

[0109] In the formula, i∈{1, 2} represents the i-th seasonal component in the l-th layer, and the frequency domain enhancement module can calculate the attention in the frequency domain through Fourier transform and wavelet transform.

[0110] The decoder of the FEDformer model is similar, using a multi-layer structure and is defined as l∈{1,2,3…,N},} represents the output of the decoder at the lth layer. Different from the encoder, the decoder has to deal with two parts: the seasonal term and the trend term. The seasonal term will be added to the output of the decoder through various frequency domain enhancement mechanisms in turn; and the trend term T de By continuously accumulating, the utilization rate of information is increased. The specific expression is as follows:

[0111]

[0112]

[0113] In the formula, i∈{1, 2, 3} represents the i-th seasonal component and trend component in the l-th layer, respectively. l，i, i∈{1, 2, 3} represents the linear weight of the extracted i-th trend, and the final prediction output is a combination of the seasonal component and the trend component.

[0114] The schematic diagram of the FEDformer model can be shown as follows: Figure 2 shown.

[0115] The improved IOOA algorithm is used to optimize the learning rate, the number of heads in the self-attention mechanism, the size of the hidden layer, and the number of layers in the FEDformer model, which brings many benefits to predicting the performance and efficiency of the plant drainage system. First, the optimized model can more accurately predict the flow changes and potential risks of the drainage system, so that maintenance measures can be taken in advance to prevent flooding. The optimization of the learning rate ensures that the model can converge quickly and stably during the training process, reduces the prediction error, and improves the real-time performance of the prediction. The optimization of the number of self-attention heads enables the model to more effectively capture the complex dependencies in the drainage system data and improves the accuracy of the prediction. The optimization of the hidden layer size helps the model to better abstract and represent the characteristics of the drainage system and enhances the model's ability to identify abnormal situations. The optimization of the number of layers balances the depth and computational complexity of the model, making the model neither too simple nor too complex, thus achieving a good balance between prediction accuracy and computational efficiency.

[0116] In addition, the application of the improved IOOA algorithm reduces the need for manual parameter adjustment, automates the parameter optimization process, and saves R&D time and costs. For managers of plant drainage systems, this means that resources can be used more efficiently and more energy can be invested in the maintenance and optimization of drainage systems.

[0117] In summary, optimizing the FEDformer model parameters through the improved IOOA algorithm not only improves the accuracy of predicting the plant drainage system, but also improves the stability and reliability of the prediction system, providing a strong guarantee for the safe production and environmental protection of the plant.

[0118] Step 4: Determine the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system.

[0119] In the embodiment of the present disclosure, step 4 specifically includes:

[0120] Determining an estimated value of a performance decay rate constant of the powerhouse drainage system based on a drainage efficiency value of the powerhouse drainage system;

[0121] The expected service life of the plant drainage system is determined based on the estimated value of the performance decay rate constant of the plant drainage system.

[0122] It should be noted that the predicted drainage efficiency of the plant drainage system is used to calculate the expected service life of the plant drainage system. Drainage efficiency is a performance indicator of the drainage system at a specific point in time, reflecting the drainage capacity of the system. Changes in drainage efficiency can be reflected in the estimation of the performance decay rate constant k. If the drainage efficiency decreases significantly over time, this may mean that the k value is large, indicating that the system performance decays faster. On the contrary, if the drainage efficiency remains stable or decreases slowly, the k value may be small, indicating that the system performance decays slowly.

[0123] The expected service life of the plant drainage system is calculated as follows:

[0124]

[0125] Where T is the expected service life of the plant drainage system, P0 is the initial drainage efficiency value of the drainage system, and P min is the preset drainage efficiency threshold, and k is the estimated value of the performance decay rate constant.

[0126] It should be noted that the service life of the plant drainage system is usually affected by many factors, including material aging, frequency of use, maintenance status, environmental conditions, etc. The performance curve of the drainage system can be expressed by an exponential decay model, which is expressed as follows:

[0127] P(t)=P0×e -kt

[0128] In the formula, P(t) is the performance of the drainage system at time t, that is, the drainage efficiency; P0 is the initial performance of the drainage system (usually 100% at the time of installation), that is, the initial drainage efficiency value; k is the performance decay rate constant, which depends on factors such as the material, design, and use conditions of the drainage system; t is time, usually in years.

[0129] In order to estimate the service life of the drainage system, a performance threshold, namely the drainage efficiency threshold P, can be set. min , drainage efficiency threshold P min The formula is as follows:

[0130] P min =P0×e -kT

[0131] When the drainage efficiency of the drainage system drops to the performance threshold P min At this level, the system is considered to need replacement or major repair.

[0132] In an embodiment of the present disclosure, the method further includes:

[0133] Determining the drainage efficiency level of the plant drainage system according to the drainage efficiency value of the plant drainage system;

[0134] Wherein, when the drainage efficiency value of the plant drainage system is greater than 90%, the drainage efficiency level of the plant drainage system is determined to be level one;

[0135] When the drainage efficiency value of the plant drainage system is less than or equal to 90% and greater than or equal to 70%, the drainage efficiency level of the plant drainage system is determined to be level 2;

[0136] When the drainage efficiency value of the plant drainage system is less than 70%, it is determined that the drainage efficiency level of the plant drainage system is level three.

[0137] It should be noted that the drainage efficiency of the plant drainage system is directly related to the stability of the production environment and the safe operation of the equipment. In order to better manage and maintain the drainage system, its drainage efficiency, i.e., performance, is divided into three levels, and corresponding maintenance recommendations are given according to different levels.

[0138] The drainage efficiency of the first-level drainage system is greater than 90%, which means that the drainage is smooth and there is no blockage. The system can quickly remove the wastewater generated during the production process. For this level of drainage system, the maintenance recommendations are as follows:

[0139] Regular inspection: Conduct a comprehensive inspection of the drainage system every three months to ensure that pipes, valves, water pumps and other facilities are operating normally;

[0140] Desilting and dredging: Desilting and dredging should be carried out at least once a year to prevent the accumulation of sludge and debris that may lead to poor drainage;

[0141] Preventive maintenance: Regular maintenance of key components, such as applying lubricants and replacing worn parts, to extend the service life of the equipment.

[0142] The drainage efficiency of the secondary performance drainage system is greater than or equal to 70% and less than or equal to 90%. There are certain drainage problems, such as slow drainage speed and slight blockage. For this level of drainage system, the maintenance suggestions are as follows:

[0143] Encrypted inspection: Increase the inspection frequency to once every two months to detect and resolve problems in a timely manner;

[0144] Emergency dredging: When drainage is not smooth, dredge it immediately to prevent the problem from getting worse;

[0145] Renovation and reconstruction: Renovate old and damaged facilities to improve the overall performance of the drainage system.

[0146] The drainage efficiency of the third-level performance drainage system is less than 70%, which is manifested as serious blockage, poor drainage, and even affecting production. For this level of drainage system, the following maintenance suggestions are crucial:

[0147] Immediate rectification: Conduct a comprehensive inspection of the drainage system, identify the root cause of the problem, and develop a rectification plan;

[0148] Professional dredging: Hire a professional team to carry out dredging to ensure that the drainage system returns to normal operation;

[0149] Regular training: Strengthen the training of operators and managers to improve their knowledge and ability of drainage system maintenance.

[0150] In an embodiment of the present disclosure, the method further includes:

[0151] When the drainage efficiency level of the plant drainage system is level one, a level one warning signal is generated;

[0152] When the drainage efficiency level of the plant drainage system is level 2, a level 2 warning signal is generated;

[0153] When the drainage efficiency level of the plant drainage system is level three, a level three warning signal is generated.

[0154] It should be noted that these assessment levels are used to automatically generate early warning signals to alert the operation and maintenance team to take necessary preventive measures. At the same time, the system provides detailed assessment reports, records performance changes and recommended maintenance activities, and provides data support for operation and maintenance decisions. In addition, the design of the risk assessment prompt module allows it to continuously update the maintenance plan based on the latest performance data to ensure the operating efficiency and reliability of the plant drainage system.

[0155] The method for determining the expected service life of the plant drainage system proposed in this embodiment breaks through the limitations of traditional manual inspections and post-maintenance. Through real-time monitoring, data analysis and predictive maintenance, it realizes the intelligent management of the drainage system, identifies potential risks in advance, effectively reduces the failure rate, and ensures production safety and efficiency. In terms of data analysis, UPEMD and KPCA are used to decompose data and reduce feature dimensions to extract key information; in terms of predictive maintenance, the IOOA algorithm obtained by multi-strategy improved OOA algorithm is used to optimize the FEDformer model parameters, predict the drainage efficiency of the drainage system, and generate a performance degradation curve. According to the predicted drainage efficiency, the expected service life of the system is estimated, and a maintenance plan is formulated in advance. In terms of risk assessment, early warning signals are automatically generated according to the performance level to guide the operation and maintenance team to take preventive measures. Provide detailed evaluation reports, record performance changes and recommended maintenance activities, and provide data support for operation and maintenance decisions.

[0156] It should be noted that the detailed flow chart of the method for determining the expected service life of the plant drainage system proposed in this embodiment can be as follows: Figure 3 As shown, no further description is given here.

[0157] To sum up, the method for determining the expected service life of a factory drainage system proposed in this embodiment can identify potential faults in advance through real-time monitoring, data analysis and prediction, improve the operating stability of the drainage system, reduce maintenance costs, and ensure the continuity of the production process and the safety of the equipment.

[0158] Embodiment 2

[0159] Figure 4 The structure diagram of a system for determining the expected service life of a plant drainage system according to one embodiment of the present application is as follows: Figure 4 As shown, the system comprises:

[0160] The collection module 100 is used to collect the operation status data of the factory drainage system and pre-process the operation status data to obtain the pre-processed operation status data;

[0161] The operating status data include: drainage flow, drainage pipe water level change value, and pipeline inner wall corrosion data.

[0162] The decomposition and dimensionality reduction module 200 is used to decompose the pre-processed operating status data using the UPEMD algorithm to obtain various modal component signals, and extract characteristic modal components from the various component signals using the kernel principal component analysis method, and then construct the operating status dimensionality reduction data matrix of the collected plant drainage system based on the characteristic modal components;

[0163] A prediction module 300 is used to substitute the dimension reduction data matrix of the operating state into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system;

[0164] The training process of the drainage efficiency prediction model includes:

[0165] Obtaining the dimension-reduced data matrix of the operation status of the plant drainage system at each moment in the historical period and the drainage efficiency value corresponding to the dimension-reduced data matrix of the operation status of the plant drainage system at each moment;

[0166] The reduced dimension data matrix of the plant drainage system's operating status at each moment is used as input, the drainage efficiency value corresponding to the reduced dimension data matrix of the plant drainage system's operating status at each moment is used as output, and the improved IOOA algorithm is used to optimize the initial Transformer model to obtain a trained drainage efficiency prediction model;

[0167] Among them, the improved IOOA algorithm is obtained by improving the OOA algorithm using a multi-difference Cauchy mutation strategy and a refraction reverse learning strategy.

[0168] The determination module 400 is used to determine the expected service life of the factory building drainage system based on the drainage efficiency value of the factory building drainage system.

[0169] In the embodiment of the present disclosure, the determining module 400 is further used to:

[0170] Determining an estimated value of a performance decay rate constant of the powerhouse drainage system based on a drainage efficiency value of the powerhouse drainage system;

[0171] The expected service life of the plant drainage system is determined based on the estimated value of the performance decay rate constant of the plant drainage system.

[0172] The expected service life of the plant drainage system is calculated as follows:

[0173]

[0174] Where T is the expected service life of the plant drainage system, P0 is the initial drainage efficiency value of the drainage system, and P min is the preset drainage efficiency threshold, and k is the estimated value of the performance decay rate constant.

[0175] In the embodiments of the present disclosure, Figure 5 As shown, the system further includes: a level determination module 500;

[0176] The level determination module 500 is used to determine the drainage efficiency level of the plant drainage system according to the drainage efficiency value of the plant drainage system;

[0177] Wherein, when the drainage efficiency value of the plant drainage system is greater than 90%, the drainage efficiency level of the plant drainage system is determined to be level one;

[0178] When the drainage efficiency value of the plant drainage system is less than or equal to 90% and greater than or equal to 70%, the drainage efficiency level of the plant drainage system is determined to be level 2;

[0179] When the drainage efficiency value of the plant drainage system is less than 70%, it is determined that the drainage efficiency level of the plant drainage system is level three.

[0180] In the embodiments of the present disclosure, Figure 6 As shown, the system further includes: a generating module 600;

[0181] The generating module 600 is used for:

[0182] When the drainage efficiency level of the plant drainage system is level one, a level one warning signal is generated;

[0183] When the drainage efficiency level of the plant drainage system is level 2, a level 2 warning signal is generated;

[0184] When the drainage efficiency level of the plant drainage system is level three, a level three warning signal is generated.

[0185] To sum up, the expected service life determination system of a factory drainage system proposed in this embodiment can identify potential faults in advance through real-time monitoring, data analysis and prediction, improve the operating stability of the drainage system, reduce maintenance costs, and ensure the continuity of the production process and the safety of the equipment.

[0186] Embodiment 3

[0187] In order to implement the above embodiments, the present disclosure further proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in Embodiment 1 is implemented.

[0188] Embodiment 4

[0189] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in the first embodiment is implemented.

[0190] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0191] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0192] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining the expected service life of a plant drainage system, characterized in that: The method comprises: Collecting operation status data of the plant drainage system, and preprocessing the operation status data to obtain preprocessed operation status data; The pre-processed operation status data is decomposed by using the UPEMD algorithm to obtain various modal component signals, and the characteristic modal components are extracted from the various component signals by using the kernel principal component analysis method, and then the dimension reduction data matrix of the operation status of the plant drainage system is constructed based on the characteristic modal components; Substituting the dimension reduction data matrix of the operating status into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system; The expected service life of the plant drainage system is determined based on the drainage efficiency value of the plant drainage system.

2. The method according to claim 1, characterized in that The operation status data include: drainage flow, drainage pipe water level change value, and pipeline inner wall corrosion data.

3. The method according to claim 2, characterized in that The training process of the drainage efficiency prediction model includes: Obtaining the dimension-reduced data matrix of the operation status of the plant drainage system at each moment in the historical period and the drainage efficiency value corresponding to the dimension-reduced data matrix of the operation status of the plant drainage system at each moment; The reduced dimension data matrix of the plant drainage system's operating status at each moment is used as input, the drainage efficiency value corresponding to the reduced dimension data matrix of the plant drainage system's operating status at each moment is used as output, and the improved IOOA algorithm is used to optimize the initial FEDformer model to obtain a trained drainage efficiency prediction model; Among them, the improved IOOA algorithm is obtained by improving the OOA algorithm using a multi-difference Cauchy mutation strategy and a refraction reverse learning strategy.

4. The method according to claim 2, characterized in that The determining the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system comprises: Determining an estimated value of a performance decay rate constant of the powerhouse drainage system based on a drainage efficiency value of the powerhouse drainage system; The expected service life of the plant drainage system is determined based on the estimated value of the performance decay rate constant of the plant drainage system.

5. The method according to claim 4, characterized in that The expected service life of the plant drainage system is calculated as follows: Where T is the expected service life of the plant drainage system, P0 is the initial drainage efficiency value of the drainage system, and P min is the preset drainage efficiency threshold, and k is the estimated value of the performance decay rate constant.

6. The method according to claim 5, characterized in that The method further comprises: Determining the drainage efficiency level of the plant drainage system according to the drainage efficiency value of the plant drainage system; Wherein, when the drainage efficiency value of the plant drainage system is greater than 90%, the drainage efficiency level of the plant drainage system is determined to be level one; When the drainage efficiency value of the plant drainage system is less than or equal to 90% and greater than or equal to 70%, the drainage efficiency level of the plant drainage system is determined to be level 2; When the drainage efficiency value of the plant drainage system is less than 70%, it is determined that the drainage efficiency level of the plant drainage system is level three.

7. The method according to claim 6, characterized in that The method further comprises: When the drainage efficiency level of the plant drainage system is level one, a level one warning signal is generated; When the drainage efficiency level of the plant drainage system is level 2, a level 2 warning signal is generated; When the drainage efficiency level of the plant drainage system is level three, a level three warning signal is generated.

8. A system for determining the expected service life of a plant drainage system, characterized in that: The system comprises: A collection module, used for collecting the operation status data of the plant drainage system, and preprocessing the operation status data to obtain the preprocessed operation status data; A decomposition and dimensionality reduction module is used to decompose the pre-processed operating status data using a UPEMD algorithm to obtain various modal component signals, and to extract characteristic modal components from the various component signals using a kernel principal component analysis method, and then to construct a dimension reduction data matrix of the operating status of the plant drainage system based on the characteristic modal components; A prediction module, used for substituting the dimension reduction data matrix of the operating status into a pre-trained drainage efficiency prediction model to obtain the drainage efficiency value of the plant drainage system; A determination module is used to determine the expected service life of the plant drainage system based on the drainage efficiency value of the plant drainage system.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images