Chemical storage tank pressure resistance testing method and system based on artificial intelligence

Abstract

A method and system for testing the pressure resistance of chemical storage tanks based on artificial intelligence, which obtains the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period; arranges the temperature value, liquid level value and pressure value of the multiple predetermined time points into a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector according to the time dimension; performs time series correlation coding on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain a chemical storage tank pressure resistance time series correlation feature; and, based on the chemical storage tank pressure resistance time series correlation feature, determines whether the pressure resistance performance of the chemical storage tank meets the predetermined standard. In this way, the operating status and performance changes of the storage tank can be automatically obtained in real time, and potential problems can be discovered in advance, avoiding production losses and human errors caused by traditional solutions, thereby improving the safety and reliability of the storage tank.

Description

Technical Field

[0001] The present application relates to the field of intelligent testing technology, and more specifically, to a chemical storage tank pressure resistance testing method and system based on artificial intelligence. Background Art

[0002] Chemical storage tanks are containers used to store and transport chemical substances, and are widely used in the petroleum, chemical, pharmaceutical, food and other industries. Chemical storage tanks are usually made of metal (such as steel, aluminum alloy) or non-metal (such as polymer) materials, with a certain size and capacity, and their pressure resistance directly affects production safety and efficiency.

[0003] Pressure resistance testing refers to the process of evaluating and verifying the safety performance of chemical storage tanks under pressure. Chemical storage tanks are subjected to internal pressure during use, so they must have sufficient pressure resistance to prevent leakage, explosion or other serious accidents.

[0004] Traditional chemical tank pressure resistance test programs usually include static tests and dynamic tests. Static tests are performed by filling the tank with liquid or gas and applying a certain pressure to observe whether the tank deforms, leaks or ruptures. Dynamic tests simulate pressure changes under actual use conditions, such as by applying pulse pressure or performing vibration tests.

[0005] However, traditional test methods have some limitations. First, these tests usually require shutdown and emptying of the tank, resulting in production interruption and increased maintenance costs, resulting in production losses and environmental pollution. Second, the test cycle is long and cannot provide real-time monitoring and evaluation. In addition, there may be human errors in the test process, and the actual pressure resistance performance evaluation of the tank may be inaccurate.

[0006] Therefore, an artificial intelligence-based pressure resistance testing solution for chemical storage tanks is desired. Summary of the invention

[0007] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a chemical storage tank pressure resistance test method and system based on artificial intelligence, which obtains the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period; arranges the temperature value, liquid level value and pressure value of the multiple predetermined time points according to the time dimension as a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector; performs time series correlation coding on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain the chemical storage tank pressure resistance time series correlation feature; and, based on the chemical storage tank pressure resistance time series correlation feature, determines whether the pressure resistance performance of the chemical storage tank meets the predetermined standard. In this way, the operating status and performance changes of the storage tank can be automatically obtained in real time, and potential problems can be discovered in advance, avoiding production losses and human errors caused by traditional solutions, thereby improving the safety and reliability of the storage tank.

[0008] In the first aspect, a method for testing the pressure resistance of a chemical storage tank based on artificial intelligence is provided, which comprises:

[0009] Obtain the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period;

[0010] Arranging the temperature values, liquid level values ​​and pressure values ​​at the plurality of predetermined time points into a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector according to the time dimension;

[0011] Performing time series correlation coding on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain a time series correlation feature of the pressure resistance of the chemical storage tank; and

[0012] Based on the time series correlation characteristics of the pressure resistance of the chemical storage tank, it is determined whether the pressure resistance performance of the chemical storage tank meets the predetermined standard.

[0013] In the second aspect, a chemical storage tank pressure resistance testing system based on artificial intelligence is provided, which includes:

[0014] A data acquisition module is used to obtain the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period;

[0015] A vector arrangement module, used for arranging the temperature values, liquid level values ​​and pressure values ​​at the plurality of predetermined time points into a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector according to the time dimension;

[0016] A timing correlation coding module, used for performing timing correlation coding on the temperature timing input vector, the liquid level timing input vector and the pressure timing input vector to obtain a timing correlation feature of the pressure resistance of the chemical storage tank; and

[0017] The pressure resistance performance determination module is used to determine whether the pressure resistance performance of the chemical storage tank meets the predetermined standard based on the time series correlation characteristics of the pressure resistance of the chemical storage tank. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a flow chart of a chemical storage tank pressure resistance testing method based on artificial intelligence according to an embodiment of the present application.

[0020] Figure 2 Schematic diagram of the architecture of the artificial intelligence-based pressure resistance testing method for chemical storage tanks according to an embodiment of the present application.

[0021] Figure 3 It is a block diagram of a chemical storage tank pressure resistance testing system based on artificial intelligence according to an embodiment of the present application.

[0022] Figure 4 This is a scenario diagram of the artificial intelligence-based pressure resistance testing method for chemical storage tanks according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] Unless otherwise specified, all technical and scientific terms used in the embodiments of the present application have the same meaning as those commonly understood by those skilled in the art of the present application. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit the scope of this application.

[0025] In the embodiments of the present application, it should be noted that, unless otherwise specified and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection or a connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0026] It should be noted that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\third" can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0027] Chemical storage tanks are containers used to store and transport chemicals, and are widely used in the petroleum, chemical, pharmaceutical, food and other industries. They are used to store liquid, gas or powdered substances to meet the needs of production, processing and transportation. The main function of chemical storage tanks is to safely store and protect chemicals to prevent accidents such as leakage, volatilization, pollution or explosion. They must have sufficient pressure resistance to withstand the effects of internal pressure and corrosion resistance to resist the erosion of chemicals on the tank material.

[0028] Chemical storage tanks are usually made of metal (such as steel, aluminum alloy) or non-metal (such as polymer) materials. Metal storage tanks usually have high strength and corrosion resistance, suitable for storing large volumes of chemicals. Non-metallic storage tanks have light weight, good corrosion resistance and cost-effectiveness, suitable for some special chemical storage needs.

[0029] The size and capacity of chemical storage tanks can be designed and manufactured according to specific needs. They can be small tanks for laboratories or small-scale production, or giant tanks for industrial production and large-scale storage. The shape of the tank can be cylindrical, spherical or other special shapes, depending on the purpose of the tank and the limitations of the installation site. For the safety performance evaluation of chemical storage tanks, pressure resistance testing is an important task. Through static tests and dynamic tests, the pressure resistance of the tank is evaluated and verified to ensure its safety performance under pressure.

[0030] Pressure resistance testing is the process of evaluating and verifying the safety performance of chemical storage tanks under pressure. Chemical storage tanks are subjected to internal pressure during use, so they must have sufficient pressure resistance to prevent leakage, explosion or other serious accidents.

[0031] Traditional chemical storage tank pressure resistance test programs usually include static tests and dynamic tests.

[0032] The static test is to fill the tank with liquid or gas and apply a certain pressure to observe whether the tank is deformed, leaked or ruptured. This test can evaluate the pressure resistance of the tank in a static state. The static test usually includes the following steps:

[0033] Tank preparation: Clean the tank and drain its contents to ensure the tank is in a clean condition.

[0034] Filling: Filling a tank with liquid or gas and gradually increasing the pressure.

[0035] Pressure maintenance: Maintain the pressure in the tank for a period of time and observe whether there is any abnormality in the tank.

[0036] Pressure release: Release the pressure in the tank and check if there are any problems such as leakage or deformation.

[0037] Dynamic testing simulates the pressure changes under actual use conditions to evaluate the pressure resistance of the tank under dynamic conditions. Common dynamic testing methods include applying pulse pressure or performing vibration tests. This test can simulate the pressure changes of the tank during transportation or operation and detect the tank's response to pressure shocks. Dynamic testing usually includes the following steps:

[0038] Pressure Cycling: Apply periodic pressure changes to simulate pressure fluctuations in actual operation.

[0039] Pressure Shock: Apply a transient high-pressure shock to test the tank's ability to respond to sudden pressure changes.

[0040] Inspection and recording: Check the tank surface for leakage, deformation or other abnormal conditions, and record the test results.

[0041] Traditional chemical tank pressure resistance test programs usually include the following main steps: During the design phase, engineers will calculate and evaluate the pressure resistance performance based on factors such as the size, material, and expected operating conditions of the tank. These calculations are usually based on relevant standards and specifications, such as ASME (American Society of Mechanical Engineers) standards and API (American Petroleum Institute) standards. Static testing is to evaluate the pressure resistance performance of the tank in a static state. The test is to fill the tank with liquid or gas and apply a certain pressure to observe whether the tank is deformed, leaked, or ruptured. Dynamic testing is to evaluate the pressure resistance performance of the tank under actual operating conditions. This test simulates the pressure changes and stress conditions that the tank may encounter during operation.

[0042] However, there are some limitations in the traditional pressure resistance test methods. Traditional pressure resistance tests usually require shutdown and emptying of the tank to ensure the safety of the test. This will lead to production interruptions and production losses, and increase maintenance costs. In addition, emptying the tank may cause environmental pollution, especially for tanks storing hazardous substances. Static tests can only evaluate the pressure resistance of the tank in a static state, and cannot simulate the pressure changes under actual use conditions. However, in actual operation, the tank may be subject to pressure fluctuations of different frequencies and amplitudes, such as liquid shock, gas pulsation, etc. The traditional test method cannot accurately evaluate the pressure resistance of the tank under these dynamic conditions. Traditional pressure resistance tests usually require a long test time and high costs. Steps such as preparing the tank, applying pressure, maintaining pressure, and releasing pressure all take a lot of time and resources. In addition, the demand for test equipment and personnel will also increase the cost of the test. Traditional test methods may have certain safety risks. When high pressure is applied, the tank may leak, rupture, or explode, posing a threat to personnel and the environment.

[0043] In order to overcome these limitations, some new pressure resistance test methods and technologies are being developed, such as non-destructive testing technology, numerical simulation methods, sensor monitoring, etc., to improve test efficiency, reduce costs and enhance safety. These new technologies can perform online monitoring and evaluation without stopping production and emptying the tank, providing more accurate and real-time pressure resistance performance information.

[0044] Therefore, the artificial intelligence-based pressure resistance testing solution for chemical storage tanks provides a new method to realize online monitoring and evaluation of the pressure resistance performance of storage tanks by real-time monitoring and analysis of data such as temperature, liquid level and pressure of storage tanks, thereby improving the safety and reliability of storage tanks.

[0045] Figure 1 This is a flow chart of a chemical storage tank pressure resistance testing method based on artificial intelligence according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the structure of a chemical storage tank pressure resistance test method based on artificial intelligence according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the artificial intelligence-based chemical storage tank pressure resistance test method includes: 110, obtaining the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period; 120, arranging the temperature values, liquid level values ​​and pressure values ​​of the multiple predetermined time points according to the time dimension as a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector; 130, performing time series correlation encoding on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain a chemical storage tank pressure resistance time series correlation feature; and, 140, determining whether the pressure resistance performance of the chemical storage tank meets the predetermined standard based on the chemical storage tank pressure resistance time series correlation feature.

[0046] In step 110, the accuracy and reliability of the monitoring equipment are ensured to obtain accurate temperature, liquid level and pressure data, and appropriate sensors and data acquisition systems are selected, and calibration and verification are performed to ensure the accuracy of the data. By obtaining temperature, liquid level and pressure data, the process status and operating conditions inside the storage tank can be understood, providing necessary input data for subsequent pressure resistance evaluation.

[0047] In step 120, the acquired temperature, liquid level and pressure values ​​are arranged in time order at predetermined time intervals to form a time series input vector, ensuring the continuity and consistency of the time series to accurately reflect the change trend inside the storage tank. By arranging the data in the time dimension, the changes in the temperature, liquid level and pressure inside the storage tank can be captured, and preparation is provided for the subsequent time series correlation coding and pressure resistance evaluation.

[0048] In step 130, a suitable temporal association encoding method, such as a recurrent neural network (RNN) or a long short-term memory network (LSTM), is used to encode the temperature, liquid level and pressure temporal input vectors, so that the temporal association characteristics between different variables can be captured and relevant information about the pressure resistance of the storage tank can be extracted. Through temporal association encoding, the temporal data of temperature, liquid level and pressure can be converted into a representation with temporal association characteristics, which helps to extract the association rules between the internal variables of the storage tank and provide a more comprehensive and accurate feature representation for the pressure resistance evaluation.

[0049] In step 140, the obtained pressure resistance time series correlation characteristics are compared with the predetermined standards using appropriate pressure resistance evaluation methods and standards, and the pressure resistance performance of the storage tank is judged to be in compliance with the requirements according to the requirements of the predetermined standards. The pressure resistance performance of the storage tank can be evaluated more comprehensively and accurately through the pressure resistance evaluation based on the time series correlation characteristics. This method can take into account the changes and correlations in the time dimension, improve the reliability and accuracy of the evaluation, and help ensure the safety performance of the storage tank.

[0050] In response to the above technical problems, the technical concept of the present application is to collect the temperature, liquid level and pressure values ​​of the chemical storage tank in real time through a sensor group, and introduce data processing and analysis algorithms at the back end to perform time-series coordinated analysis of the temperature, liquid level and pressure values ​​of the chemical storage tank, so as to realize online monitoring and evaluation of the pressure resistance performance of the chemical storage tank. In this way, the operating status and performance changes of the storage tank can be automatically obtained in real time, and potential problems can be discovered in advance, avoiding production losses and human errors caused by traditional solutions, thereby improving the safety and reliability of the storage tank.

[0051] Specifically, in the technical solution of the present application, first, the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period are obtained. Next, considering that the temperature value, liquid level value and pressure value of the monitored chemical storage tank not only have a dynamic change law of time series in the time dimension, but also have a synergistic correlation relationship between these parameters, they jointly affect the pressure resistance performance detection and evaluation of the chemical storage tank. Therefore, in order to realize the online monitoring and evaluation of the pressure resistance performance of chemical storage tanks, to discover potential problems in advance and improve the safety and reliability of storage tanks, in the technical solution of the present application, it is necessary to arrange the temperature values, liquid level values ​​and pressure values ​​of the multiple predetermined time points according to the time dimension as a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector, so as to respectively integrate the time series distribution information of the temperature value, the liquid level value and the pressure value in the time dimension.

[0052] In one embodiment of the present application, the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector are time-series associated encoded to obtain a time-series associated feature of the pressure resistance of a chemical storage tank, including: up-sampling the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector based on linear interpolation to obtain a dense temperature time series input vector, a dense liquid level time series input vector and a dense pressure time series input vector; performing time series feature extraction on the dense temperature time series input vector, the dense liquid level time series input vector and the dense pressure time series input vector respectively through a time series feature extractor based on a deep neural network model to obtain a temperature time series feature vector, a liquid level time series feature vector and a pressure time series feature vector; and, fusing the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector to obtain a posterior probability feature vector of the pressure resistance of a chemical storage tank as the time-series associated feature of the pressure resistance of a chemical storage tank.

[0053] Among them, the time series feature extractor based on the deep neural network model is a time series feature extractor based on a one-dimensional convolutional layer.

[0054] Then, in order to improve the accuracy of the pressure resistance performance detection of the chemical storage tank, it is necessary to further perform up-sampling based on linear interpolation on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain a dense temperature time series input vector, a dense liquid level time series input vector and a dense pressure time series input vector, so as to increase the density and smoothness of the parameter data of the chemical storage tank, so as to facilitate the subsequent better pressure resistance performance detection and evaluation of the chemical storage tank. It should be understood that through the up-sampling of linear interpolation, the data points in the original temperature time series input vector, the liquid level time series input vector and the pressure time series input vector can be interpolated to generate more data points. In this way, it is helpful to increase the resolution in the time dimension, so that the coordinated changes in the parameter time series of the chemical storage tank are more detailed and visible. At the same time, linear interpolation can perform smooth interpolation between sampling points, reduce the impact of noise and mutations, and improve the continuity and stability of the data.

[0055] Furthermore, the dense temperature time series input vector, the dense liquid level time series input vector and the dense pressure time series input vector are subjected to feature mining in a time series feature extractor based on a one-dimensional convolutional layer to respectively extract the time series dynamic correlation feature information of the temperature value, the liquid level value and the pressure value in the time dimension, thereby obtaining the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector.

[0056] In one embodiment of the present application, the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector are fused to obtain a posterior probability feature vector of the pressure resistance of a chemical storage tank as the time series correlation feature of the pressure resistance of the chemical storage tank, including: using a Bayesian probability model to fuse the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector to obtain a posterior probability feature vector of the pressure resistance of the chemical storage tank.

[0057] Furthermore, after obtaining the temporal dynamic change characteristics of the temperature value, liquid level value and pressure value of the chemical storage tank in the time dimension, the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector are fused. Specifically, in the technical solution of the present application, a Bayesian probability model can be used to fuse the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector to obtain a posterior probability feature vector of the pressure resistance of the chemical storage tank. By using the Bayesian probability model, the correlation and dependency between the different parameter feature vectors of the chemical storage tank can be taken into account, and reasonable probability inference can be performed. In this way, the parameter posterior feature vector can be estimated more accurately, thereby improving the detection capability of the pressure resistance performance of the chemical storage tank. Specifically, the Bayesian probability model can utilize the known temperature time series feature vector, the liquid level time series feature vector, and the pressure time series feature vector, combined with prior knowledge, to calculate the probability distribution of the posterior probability feature vector of the pressure resistance of the chemical storage tank, wherein the posterior probability feature vector of the pressure resistance of the chemical storage tank can comprehensively consider the parameter time series feature information of multiple chemical storage tanks, provide a more comprehensive and accurate feature representation, and facilitate more accurate detection of the pressure resistance performance of chemical storage tanks.

[0058] In one embodiment of the present application, based on the time series correlation characteristics of the pressure resistance of the chemical storage tank, determining whether the pressure resistance performance of the chemical storage tank meets the predetermined standard includes: calculating the pressure resistance transfer matrix of the pressure time series feature vector relative to the posterior probability feature vector of the pressure resistance of the chemical storage tank; performing soft matching of the rank permutation distribution of the pressure resistance transfer matrix with the feature scale as the mimicking mask to obtain an optimized pressure resistance transfer matrix; and passing the optimized pressure resistance transfer matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the pressure resistance performance of the chemical storage tank meets the predetermined standard.

[0059] Next, in order to further improve the accuracy of the pressure resistance performance detection of the chemical storage tank, it is necessary to calculate the pressure resistance transfer matrix of the pressure time series feature vector relative to the posterior probability feature vector of the pressure resistance of the chemical storage tank, so as to map the time series change characteristics of the pressure into the high-dimensional space of the parameter time series collaborative correlation characteristics of the chemical storage tank, thereby obtaining the pressure resistance transfer matrix of the pressure time series change characteristic information based on the parameter time series collaborative correlation characteristics of the chemical storage tank.

[0060] In particular, in the technical solution of the present application, when a quasi-Bayesian model is used to fuse the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector to obtain the posterior probability feature vector of the pressure resistance of the chemical storage tank, since the Bayesian model uses point-by-point Bayesian calculation to fuse the temporal local correlation characteristics of the temperature value, liquid level value and pressure value expressed by the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector respectively, the posterior probability feature vector of the pressure resistance of the chemical storage tank also conforms to the temporal local correlation characteristic distribution of the relevant parameters. In this way, when calculating the transfer matrix of the pressure time series feature vector relative to the posterior probability feature vector of the pressure resistance of the chemical storage tank, if the pressure time series feature vector is transferred to If the parameter temporal local correlation characteristics followed by the pressure time series feature vector and the chemical tank pressure resistance posterior probability feature vector are used as foreground object features, the transfer matrix will introduce background distribution noise while introducing the global temporal domain transfer feature representation, and while performing the high-rank distribution representation between the vector and the matrix when calculating the transfer matrix, the pressure resistance transfer matrix as the transfer matrix will also cause a temporal probability density mapping error relative to the pressure time series feature vector and the chemical tank pressure resistance posterior probability feature vector due to the heterogeneous distribution of the prior-posterior probability space of the high-dimensional features of the pressure time series feature vector and the chemical tank pressure resistance posterior probability feature vector, thereby affecting the accuracy of the classification result obtained by the pressure resistance transfer matrix through the classifier.

[0061] Based on this, the applicant of the present application denotes the pressure resistance transfer matrix, for example, as Performing soft matching of the rank arrangement distribution with the characteristic scale as the imitation mask is specifically expressed as: performing soft matching of the rank arrangement distribution with the characteristic scale as the imitation mask on the pressure resistance transfer matrix using the following optimization formula to obtain the optimized pressure resistance transfer matrix; wherein the optimization formula is:

[0062]

[0063] in, is the pressure resistance transfer matrix, is the first The eigenvalues ​​of the positions, is the scale of the pressure resistance transfer matrix, represents the square of the Frobenius norm of the pressure resistance transfer matrix, represents the second norm of the pressure resistance transfer matrix, and is a weighted hyperparameter, represents exponential operation, is the first The eigenvalue of the location.

[0064] Here, the soft matching of the rank arrangement distribution of the feature scale as the imitation mask can focus on the foreground object features and ignore the background distribution noise when mapping the high-dimensional features to be regressed into the probability density space, and through the pressure resistance transfer matrix The distribution of the pyramid rank arrangement distribution is soft matched with different norms, thereby effectively capturing the correlation between the central area and the tail area of ​​the probability density distribution, avoiding the pressure resistance transfer matrix The probability density mapping deviation caused by the probability space heterogeneous distribution of the high-dimensional features is improved, thereby improving the accuracy of the classification results obtained by the pressure resistance transfer matrix through the classifier. In this way, the pressure resistance performance and operating status of the chemical storage tank can be automatically monitored and evaluated online based on the coordinated changes in the temperature, liquid level and pressure time series of the chemical storage tank, so as to discover and solve potential problems in advance, thereby improving the safety and reliability of the storage tank.

[0065] In one embodiment of the present application, the optimized pressure resistance transfer matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the pressure resistance performance of the chemical storage tank meets a predetermined standard, including: expanding the optimized pressure resistance transfer matrix into a classification feature vector according to a row vector or a column vector; using multiple fully connected layers of the classifier to fully connect encode the classification feature vector to obtain an encoded classification feature vector; and passing the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0066] Then, the optimized pressure resistance transfer matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the pressure resistance performance of the chemical storage tank meets the predetermined standard. In other words, the pressure time series characteristic information about the chemical storage tank is used for classification processing based on the parameter time series collaborative correlation characteristics of the chemical storage tank, so as to realize online monitoring and evaluation of the pressure resistance performance of the chemical storage tank. In this way, the operating status and performance changes of the storage tank can be automatically obtained in real time, and potential problems can be discovered in advance, avoiding production losses and human errors caused by traditional solutions, thereby improving the safety and reliability of the storage tank.

[0067] In summary, an artificial intelligence-based pressure resistance testing method for chemical storage tanks based on the embodiment of the present application is clarified, and the temperature value, liquid level value and pressure value of the chemical storage tank are collected in real time through a sensor group, and a data processing and analysis algorithm is introduced at the back end to perform a time series collaborative analysis of the temperature value, liquid level value and pressure value of the chemical storage tank, so as to realize online monitoring and evaluation of the pressure resistance performance of the chemical storage tank. In this way, the operating status and performance changes of the storage tank can be automatically obtained in real time, and potential problems can be discovered in advance, avoiding production losses and human errors caused by traditional solutions, thereby improving the safety and reliability of the storage tank.

[0068] In one embodiment of the present application, Figure 3 FIG. 1 is a block diagram of a chemical storage tank pressure resistance test system based on artificial intelligence according to an embodiment of the present application. Figure 3 As shown, according to the artificial intelligence-based chemical storage tank pressure resistance testing system 200 of the embodiment of the present application, it includes: a data acquisition module 210, which is used to obtain the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period; a vector arrangement module 220, which is used to arrange the temperature values, liquid level values ​​and pressure values ​​of the multiple predetermined time points according to the time dimension into a temperature timing input vector, a liquid level timing input vector and a pressure timing input vector; a timing association coding module 230, which is used to perform timing association coding on the temperature timing input vector, the liquid level timing input vector and the pressure timing input vector to obtain a timing association feature of the pressure resistance of the chemical storage tank; and a pressure resistance performance determination module 240, which is used to determine whether the pressure resistance performance of the chemical storage tank meets the predetermined standard based on the timing association feature of the pressure resistance of the chemical storage tank.

[0069] In the artificial intelligence-based chemical storage tank pressure resistance test system, the timing association encoding module includes: an upsampling unit, which is used to perform linear interpolation upsampling on the temperature timing input vector, the liquid level timing input vector and the pressure timing input vector to obtain a dense temperature timing input vector, a dense liquid level timing input vector and a dense pressure timing input vector; a timing feature extraction unit, which is used to perform timing feature extraction on the dense temperature timing input vector, the dense liquid level timing input vector and the dense pressure timing input vector respectively through a timing feature extractor based on a deep neural network model to obtain a temperature timing feature vector, a liquid level timing feature vector and a pressure timing feature vector; and a fusion unit, which is used to fuse the temperature timing feature vector, the liquid level timing feature vector and the pressure timing feature vector to obtain a posterior probability feature vector of the pressure resistance of the chemical storage tank as the timing association feature of the pressure resistance of the chemical storage tank.

[0070] In the artificial intelligence-based chemical storage tank pressure resistance testing system, the time series feature extractor based on the deep neural network model is a time series feature extractor based on a one-dimensional convolutional layer.

[0071] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above-mentioned artificial intelligence-based chemical tank pressure resistance test system have been referred to above. Figure 1 to Figure 2 The description of the artificial intelligence-based chemical storage tank pressure resistance test method has been introduced in detail, and therefore, its repeated description will be omitted.

[0072] As described above, the artificial intelligence-based chemical storage tank pressure resistance testing system 200 according to the embodiment of the present application can be implemented in various terminal devices, such as a server for artificial intelligence-based chemical storage tank pressure resistance testing. In one example, the artificial intelligence-based chemical storage tank pressure resistance testing system 200 according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the artificial intelligence-based chemical storage tank pressure resistance testing system 200 can be a software module in the operating system of the terminal device, or it can be an application developed for the terminal device; of course, the artificial intelligence-based chemical storage tank pressure resistance testing system 200 can also be one of the many hardware modules of the terminal device.

[0073] Alternatively, in another example, the artificial intelligence-based chemical storage tank pressure resistance testing system 200 and the terminal device may also be separate devices, and the artificial intelligence-based chemical storage tank pressure resistance testing system 200 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0074] Figure 4 FIG. 1 is a schematic diagram of a scenario of a chemical storage tank pressure resistance test method based on artificial intelligence according to an embodiment of the present application. Figure 4 As shown, in this application scenario, first, the temperature values ​​of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period are obtained (for example, Figure 4 C1 as shown in the figure), level value (e.g. Figure 4 C2) and pressure values ​​(e.g. Figure 4 Then, the obtained temperature value, liquid level value and pressure value are input to a server (for example, Figure 4 In S) shown in the figure, the server is capable of processing the temperature value, the liquid level value and the pressure value based on an artificial intelligence-based chemical storage tank pressure resistance test algorithm to determine whether the pressure resistance performance of the chemical storage tank meets the predetermined standard.

[0075] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0076] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0077] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0078] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A chemical storage tank pressure resistance test method based on artificial intelligence, characterized in that: include: Obtain the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period; Arranging the temperature values, liquid level values ​​and pressure values ​​at the plurality of predetermined time points into a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector according to the time dimension; Performing time series correlation coding on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain a time series correlation feature of the pressure resistance of the chemical storage tank; as well as Determining whether the pressure resistance performance of the chemical storage tank meets a predetermined standard based on the temporal correlation characteristics of the pressure resistance of the chemical storage tank; Based on the temporal correlation characteristics of the pressure resistance of the chemical storage tank, determining whether the pressure resistance performance of the chemical storage tank meets the predetermined standard includes: Calculating the pressure resistance transfer matrix of the pressure time series feature vector relative to the posterior probability feature vector of the pressure resistance of the chemical storage tank; Performing soft matching of the rank arrangement distribution using the characteristic scale as the imitation mask on the pressure resistance transfer matrix to obtain an optimized pressure resistance transfer matrix; and Passing the optimized pressure resistance transfer matrix through a classifier to obtain a classification result, wherein the classification result is used to indicate whether the pressure resistance performance of the chemical storage tank meets a predetermined standard; The pressure resistance transfer matrix is ​​subjected to soft matching of the rank arrangement distribution with the characteristic scale as the imitation mask to obtain an optimized pressure resistance transfer matrix, including: The pressure resistance transfer matrix is ​​subjected to soft matching of the rank arrangement distribution with the characteristic scale as the imitation mask using the following optimization formula to obtain the optimized pressure resistance transfer matrix; Wherein, the optimization formula is: Wherein, M is the pressure resistance transfer matrix, m i,j is the eigenvalue of the (i, j)th position of the pressure resistance transfer matrix, S is the scale of the pressure resistance transfer matrix, represents the square of the Frobenius norm of the pressure resistance transfer matrix, ||M||2 represents the bi-norm of the pressure resistance transfer matrix, and α is a weighted hyperparameter, exp(·) represents an exponential operation, and m′ i,j is the eigenvalue of the (i, j)th position of the optimized pressure resistance transfer matrix.

2. The artificial intelligence-based pressure resistance testing method for chemical storage tanks according to claim 1 is characterized in that: The temperature time series input vector, the liquid level time series input vector and the pressure time series input vector are time series associated and encoded to obtain a time series associated feature of the pressure resistance of the chemical storage tank, including: Performing up-sampling based on linear interpolation on the temperature time series input vector, the liquid level time series input vector and the pressure time series input vector to obtain a dense temperature time series input vector, a dense liquid level time series input vector and a dense pressure time series input vector; Performing time series feature extraction on the intensive temperature time series input vector, the intensive liquid level time series input vector, and the intensive pressure time series input vector respectively through a time series feature extractor based on a deep neural network model to obtain a temperature time series feature vector, a liquid level time series feature vector, and a pressure time series feature vector; and The temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector are fused to obtain a posterior probability feature vector of the pressure resistance of the chemical storage tank as the time series correlation feature of the pressure resistance of the chemical storage tank.

3. The artificial intelligence-based pressure resistance testing method for chemical storage tanks according to claim 2 is characterized in that: The temporal feature extractor based on the deep neural network model is a temporal feature extractor based on a one-dimensional convolutional layer.

4. The artificial intelligence-based pressure resistance testing method for chemical storage tanks according to claim 3 is characterized in that: The temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector are integrated to obtain a posterior probability feature vector of the pressure resistance of the chemical storage tank as the time series correlation feature of the pressure resistance of the chemical storage tank, including: using a Bayesian probability model to integrate the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector to obtain the posterior probability feature vector of the pressure resistance of the chemical storage tank.

5. The artificial intelligence-based pressure resistance testing method for chemical storage tanks according to claim 4 is characterized in that: The optimized pressure resistance transfer matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the pressure resistance performance of the chemical storage tank meets the predetermined standard, including: Expanding the optimized pressure resistance transfer matrix into classification feature vectors according to row vectors or column vectors; Performing full connection encoding on the classification feature vector using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and The encoded classification feature vector is passed through the Softmax classification function of the classifier to obtain the classification result.

6. A chemical tank pressure resistance test system based on artificial intelligence, characterized in that: include: A data acquisition module is used to obtain the temperature value, liquid level value and pressure value of the monitored chemical storage tank at multiple predetermined time points within a predetermined time period; A vector arrangement module, used for arranging the temperature values, liquid level values ​​and pressure values ​​at the plurality of predetermined time points into a temperature time series input vector, a liquid level time series input vector and a pressure time series input vector according to the time dimension; A timing correlation coding module, used for performing timing correlation coding on the temperature timing input vector, the liquid level timing input vector and the pressure timing input vector to obtain a timing correlation feature of the pressure resistance of the chemical storage tank; as well as A pressure resistance performance determination module, used to determine whether the pressure resistance performance of the chemical storage tank meets a predetermined standard based on the time series correlation characteristics of the pressure resistance of the chemical storage tank; The pressure resistance performance determination module is used to: Calculating the pressure resistance transfer matrix of the pressure time series feature vector relative to the posterior probability feature vector of the pressure resistance of the chemical storage tank; Performing soft matching of the rank arrangement distribution of the characteristic scale as the imitation mask on the pressure resistance transfer matrix to obtain an optimized pressure resistance transfer matrix; as well as Passing the optimized pressure resistance transfer matrix through a classifier to obtain a classification result, wherein the classification result is used to indicate whether the pressure resistance performance of the chemical storage tank meets a predetermined standard; The pressure resistance transfer matrix is ​​subjected to soft matching of the rank arrangement distribution with the characteristic scale as the imitation mask using the following optimization formula to obtain the optimized pressure resistance transfer matrix; Wherein, the optimization formula is: Wherein, M is the pressure resistance transfer matrix, m i,j is the eigenvalue of the (i, j)th position of the pressure resistance transfer matrix, S is the scale of the pressure resistance transfer matrix, represents the square of the Frobenius norm of the pressure resistance transfer matrix, ||M||2 represents the bi-norm of the pressure resistance transfer matrix, and α is a weighted hyperparameter, exp(·) represents an exponential operation, and m′ i,j is the eigenvalue of the (i, j)th position of the optimized pressure resistance transfer matrix.

7. The artificial intelligence-based chemical tank pressure resistance testing system according to claim 6 is characterized in that: The timing association coding module includes: an upsampling unit, configured to perform upsampling based on linear interpolation on the temperature time series input vector, the liquid level time series input vector, and the pressure time series input vector to obtain a dense temperature time series input vector, a dense liquid level time series input vector, and a dense pressure time series input vector; a timing feature extraction unit, configured to extract timing features from the intensive temperature timing input vector, the intensive liquid level timing input vector, and the intensive pressure timing input vector respectively through a timing feature extractor based on a deep neural network model to obtain a temperature timing feature vector, a liquid level timing feature vector, and a pressure timing feature vector; and A fusion unit is used to fuse the temperature time series feature vector, the liquid level time series feature vector and the pressure time series feature vector to obtain a posterior probability feature vector of the pressure resistance of the chemical storage tank as the time series correlation feature of the pressure resistance of the chemical storage tank.

8. The artificial intelligence-based chemical tank pressure resistance testing system according to claim 7 is characterized in that: The temporal feature extractor based on the deep neural network model is a temporal feature extractor based on a one-dimensional convolutional layer.

Images