Petrochemical port equipment operation safety risk early warning method and system based on support vector machine

Abstract

The present invention discloses a petrochemical port equipment operation safety risk early warning method and system based on a support vector machine, which solves the problem that the existing petrochemical port safety early warning analysis method only supports early warning judgments on safety issues with a single serious potential risk factor, and cannot conduct a comprehensive analysis of safety issues with multiple potential risk factors, thereby reducing the accuracy of early warning analysis. The method comprises: obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal, constructing and training an equipment safety standardization evaluation model; judging the operating status of petrochemical port equipment through the equipment safety standardization evaluation model; the present invention identifies real-time associated data based on the equipment safety standardization evaluation model, thereby being able to conduct a comprehensive analysis of equipment safety issues with multiple potential risk factors, judge the operating status of petrochemical port equipment, and provide early warnings for potential risks of equipment operation, thereby ensuring the smooth operation of petrochemical port equipment.

Description

Technical Field

[0001] The invention belongs to the technical field of petrochemical port area early warning, and in particular relates to a petrochemical port area equipment operation safety risk early warning method and system based on a support vector machine. Background Art

[0002] As a hub for water and land transportation, petrochemical ports are transit and distribution centers for goods. They have many work links, a complex operating environment, a wide range of involvement, and are highly comprehensive. Port production is a labor-intensive industry with loading and unloading operations as the main body. Mechanized, semi-mechanized, automated, and semi-automated operating methods are mostly used. Due to the complexity of port loading and unloading operations, ship types, cargo structures, production operating environments, equipment and loading and unloading processes, as well as the different qualities of production operators, port production has unique characteristics.

[0003] Safety early warning analysis is a series of management activities to monitor, identify, diagnose and evaluate the safety hazards of various equipment in the production of petrochemical port areas, namely, unsafe human behavior, unsafe conditions of objects, poor environmental conditions and other factors. The purpose of safety early warning analysis is to reveal the early signs of the development of accidents, identify the safe status of equipment operation in petrochemical port areas, and make judgments and issue warnings based on this, so as to provide a decision-making basis for preventive control measures; the existing safety early warning analysis method for petrochemical port areas only supports early warning judgments on safety issues with a single serious potential risk factor, and cannot conduct a comprehensive analysis of safety issues with multiple potential risk factors, which reduces the accuracy of early warning analysis. Based on this, we propose a petrochemical port area equipment operation safety risk early warning method and system based on support vector machine. Summary of the invention

[0004] The purpose of the present invention is to address the shortcomings of the prior art and provide a petrochemical port equipment operation safety risk warning method and system based on a support vector machine, which solves the problem that the existing petrochemical port safety warning analysis method only supports warning judgments on safety issues with a single serious potential risk factor, and cannot conduct comprehensive analysis of safety issues with multiple potential risk factors, thereby reducing the accuracy of the warning analysis.

[0005] The present invention is implemented in this way: a petrochemical port area equipment operation safety risk early warning method based on a support vector machine, the petrochemical port area equipment operation safety risk early warning method based on a support vector machine comprises:

[0006] Obtain multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal, wherein the monitoring data includes real-time correlation data and historical correlation data;

[0007] Load historical correlation data, build and train a device safety standardization assessment model based on the historical correlation data;

[0008] Based on the equipment safety standardization assessment model, real-time correlation data is identified, and the equipment operation status of the petrochemical port area is judged through the equipment safety standardization assessment model to determine whether the equipment operation status exceeds the preset first risk threshold. If it exceeds the first risk threshold, a first warning signal is issued;

[0009] If the equipment operating status does not exceed the preset first risk threshold, the real-time associated data is judged based on the pre-trained associated risk diagnosis model to determine whether the equipment operating status exceeds the second risk threshold. If it exceeds the second risk threshold, a second warning signal is issued.

[0010] Preferably, the method of obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal specifically includes:

[0011] Constructing a risk topology model for petrochemical port equipment based on support vector machine;

[0012] Acquire historical correlation data, evaluate key nodes in the petrochemical port equipment risk topology model based on the historical correlation data, and assign weights to the key nodes to obtain an optimized petrochemical port equipment risk topology model;

[0013] Based on the optimized petrochemical port equipment risk topology model, the three-dimensional monitoring system of the port monitoring terminal is arranged, and real-time correlation data is obtained through the three-dimensional monitoring system of the monitoring terminal.

[0014] Preferably, the method of obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal specifically includes:

[0015] The historical associated data are traversed, and a decision knowledge base is generated based on the optimized petrochemical port equipment risk topology model, wherein the decision knowledge base is used to provide risk response solutions to the associated risk diagnosis model.

[0016] Preferably, the method for constructing and training the equipment safety standardization assessment model specifically includes:

[0017] Obtain historical correlation data, normalize the historical correlation data based on a data normalization function to obtain normalized correlation data, and divide the normalized correlation data into a training set, a validation set, and a test set, with the distribution ratio of the training set, the validation set, and the test set being 60%, 20%, and 20%;

[0018] Among them, the data normalization function is expressed by the formula:

[0019]

[0020] In formula (1), G (x,y,z)represents the normalized value corresponding to the historical correlation data m with three-dimensional coordinates (x, y, z), μ represents the weight penalty factor for realizing the normalization transformation of the historical correlation data when passing through the normalization function, and c represents the transformation scale of the data normalization function, which is a constant;

[0021] Obtaining an initial training model of a device safety standardization assessment model, wherein the initial training model includes a linear kernel, a polynomial kernel, a radial kernel, and a sigmoid kernel function;

[0022] The training set is loaded, a radial kernel function is trained based on the training set, and the initial training model is iterated until the initial training model converges, wherein the radial kernel function is expressed as:

[0023]

[0024] Wherein, the σ represents a constant parameter of the kernel function;

[0025] Load the validation set, use the validation set as input, adjust the kernel function constants and hyperparameters of the initial training model, determine the error rate of the initial training model, and then obtain the optimized initial training model.

[0026] Preferably, the method for constructing and training the equipment safety standardization assessment model further includes:

[0027] Obtain a test set, and verify the error rate of the optimized initial training model based on the test set. If the error rate of the optimized initial training model is less than the preset error rate, output the function expression of the equipment safety standardization evaluation model, where the function expression of the equipment safety standardization evaluation model is expressed as:

[0028]

[0029] Among them, J m represents the risk value of port equipment operation corresponding to the historical correlation data m, b is the influence constant, which represents the s influencing factors (P1, P2, ...P s ) is the weight comparison matrix of a factor O1 in the previous influence level O, ε represents the normalized weight vector, α (x,y,z) represents the hyperparameter tuning function;

[0030]

[0031] in,

[0032]

[0033]

[0034] Where n represents the number of historical associated data m;

[0035] If the error rate of the optimized initial training model is greater than the preset error rate, adjust the hyperparameters of the optimized initial training model, and iteratively train the optimized initial training model based on the validation set until convergence.

[0036] Preferably, the method for judging real-time correlation data based on the pre-trained correlation risk diagnosis model specifically includes:

[0037] Acquire real-time associated data and calculate the support vector machine propagation value H of the real-time associated data m , where the support vector machine propagates the value H m Calculated by formula (7);

[0038]

[0039] Based on the support vector machine propagation value H m Calculate the risk radiation value of petrochemical port equipment corresponding to real-time correlation data.

[0040] Preferably, the method for judging real-time correlation data based on the pre-trained correlation risk diagnosis model specifically further includes:

[0041] Obtain the risk radiation value of petrochemical port equipment, and calculate the potential risk value of real-time associated data based on the risk radiation value of petrochemical port equipment.

[0042] Preferably, the potential risk value L of the real-time associated data is m Calculated by formula (8);

[0043]

[0044] Among them, φ and β represent the lower limit coefficient and upper limit coefficient of risk propagation in the associated risk diagnosis model, respectively, and f m represents the risk radiation value of petrochemical port equipment, where f m Calculated by formula (9);

[0045]

[0046] Among them, H m Indicates the support vector machine propagation value H corresponding to the current data m m .

[0047] On the other hand, the present invention also provides a petrochemical port area equipment operation safety risk early warning system based on a support vector machine, and the petrochemical port area equipment operation safety risk early warning system based on a support vector machine specifically includes:

[0048] A monitoring data acquisition module, wherein the monitoring data acquisition module acquires multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal, wherein the monitoring data includes real-time correlation data and historical correlation data;

[0049] A model building module, the model building module is used to load historical correlation data, build and train a device safety standardization assessment model and an associated risk diagnosis model based on the historical correlation data;

[0050] A first judgment module, wherein the first judgment module identifies real-time associated data based on the equipment safety standardization assessment model, judges the operating status of the petrochemical port equipment through the equipment safety standardization assessment model, and judges whether the equipment operating status exceeds a preset first risk threshold, and if it exceeds the first risk threshold, issues a first warning signal;

[0051] The second judgment module judges the real-time association data based on the pre-trained association risk diagnosis model to determine whether the equipment operation status exceeds a second risk threshold.

[0052] Preferably, the monitoring data acquisition module specifically includes:

[0053] A topology model building unit, wherein the topology model building unit builds a petrochemical port area equipment risk topology model based on a support vector machine;

[0054] A weight assignment unit, the weight assignment unit is used to obtain historical correlation data, evaluate key nodes in the petrochemical port equipment risk topology model based on the historical correlation data, and assign weights to the key nodes to obtain an optimized petrochemical port equipment risk topology model;

[0055] The monitoring terminal management unit arranges the three-dimensional monitoring system of the port monitoring terminal based on the optimized petrochemical port equipment risk topology model, and obtains real-time correlation data through the three-dimensional monitoring system of the monitoring terminal, and

[0056] A knowledge base service unit, the knowledge base service unit is used to traverse historical associated data and generate a decision knowledge base based on the optimized petrochemical port equipment risk topology model, wherein the decision knowledge base is used to provide risk response solutions to the associated risk diagnosis model.

[0057] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0058] The embodiment of the present invention identifies real-time associated data based on the equipment safety standardization assessment model, thereby being able to conduct a comprehensive analysis of equipment safety issues with multiple potential risk factors and judge the operating status of petrochemical port equipment. At the same time, it can also judge the potential risk value of real-time associated data based on a pre-trained associated risk diagnosis model, provide early warnings for potential risks in equipment operation, and ensure the smooth operation of petrochemical port equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of the implementation process of the petrochemical port equipment operation safety risk early warning method based on the support vector machine provided by the present invention.

[0060] Figure 2 The present invention shows a schematic diagram of the implementation process of a method for obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal.

[0061] Figure 3 A schematic diagram of the implementation process of the equipment safety standardization assessment model construction and training method is shown.

[0062] Figure 4 The figure shows a flowchart of the implementation of the real-time correlation data judgment method based on the pre-trained correlation risk diagnosis model.

[0063] Figure 5 The structural diagram of the petrochemical port equipment operation safety risk early warning system based on support vector machine is shown.

[0064] Figure 6 A structural schematic diagram of a monitoring data acquisition module is shown. DETAILED DESCRIPTION

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] The existing petrochemical port area safety early warning analysis method only supports early warning judgment of safety problems with a single serious potential risk factor, and cannot conduct a comprehensive analysis of safety problems with multiple potential risk factors, which reduces the accuracy of early warning analysis. Based on this, we propose a petrochemical port area equipment operation safety risk early warning method and system based on support vector machine. In short, the support vector machine petrochemical port area equipment operation safety risk early warning method includes obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port area equipment through the port area monitoring terminal, and then constructing and training equipment safety standardization evaluation models based on historical correlation data, judging the operating status of petrochemical port area equipment through the equipment safety standardization evaluation model, and finally judging the real-time correlation data based on the pre-trained correlation risk diagnosis model. The embodiment of the present invention can identify real-time correlation data based on the equipment safety standardization evaluation model, so as to comprehensively analyze the equipment safety problems with multiple potential risk factors and judge the operating status of petrochemical port area equipment. At the same time, it can also judge the potential risk value of real-time correlation data based on the pre-trained correlation risk diagnosis model, and give early warning for the potential risk of equipment operation, thereby ensuring the smooth operation of petrochemical port area equipment.

[0068] The embodiment of the present invention provides a petrochemical port equipment operation safety risk early warning method based on a support vector machine. Figure 1 The schematic diagram of the implementation process of the support vector machine petrochemical port equipment operation safety risk early warning method is shown. The support vector machine petrochemical port equipment operation safety risk early warning method specifically includes:

[0069] Step S10, obtaining multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal, wherein the monitoring data includes real-time correlation data and historical correlation data;

[0070] Step S20, loading historical correlation data, and building and training a device safety standardization assessment model based on the historical correlation data;

[0071] Step S30, identifying real-time associated data based on the equipment safety standardization assessment model, judging the operating status of the petrochemical port equipment through the equipment safety standardization assessment model, judging whether the equipment operating status exceeds a preset first risk threshold, and issuing a first warning signal if the first risk threshold is exceeded;

[0072] Step S40: If the equipment operation status does not exceed the preset first risk threshold, the real-time associated data is judged based on the pre-trained associated risk diagnosis model to determine whether the equipment operation status exceeds the second risk threshold. If it exceeds the second risk threshold, a second warning signal is issued.

[0073] The embodiment of the present invention identifies real-time associated data based on the equipment safety standardization assessment model, thereby being able to conduct a comprehensive analysis of equipment safety issues with multiple potential risk factors and judge the operating status of petrochemical port equipment. At the same time, it can also judge the potential risk value of real-time associated data based on a pre-trained associated risk diagnosis model, provide early warnings for potential risks in equipment operation, and ensure the smooth operation of petrochemical port equipment.

[0074] The embodiment of the present invention provides a method for obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal. Figure 2 The present invention shows a schematic diagram of a method for obtaining multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal. The method for obtaining multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal specifically includes:

[0075] Step S101, constructing a petrochemical port equipment risk topology model based on a support vector machine;

[0076] It should be noted that the petrochemical port area equipment includes but is not limited to tank area loading platform, tank area power supply equipment, monitoring equipment, temperature control equipment, tank area fire extinguishing equipment, tank area explosion-proof equipment (explosion-proof valves, explosion-proof lighting, explosion-proof cables), fire hydrants, fire water tanks, transportation pipelines, etc.

[0077] At the same time, the petrochemical port equipment risk topology model is a dynamic port equipment early warning monitoring system. The construction of the petrochemical port equipment risk topology model is based on the port equipment "man, machine, environment" indicator system, the external "man, machine, environment" indicator system, the natural environment early warning monitoring indicator system, and the social environment early warning monitoring indicator system. The key nodes in the petrochemical port equipment risk topology model are evaluated based on historical correlation data, and the key nodes are assigned weights. The main consideration is that the port equipment "man, machine, environment" indicator system has the greatest impact on the petrochemical port equipment risk topology model, while the external "man, machine, environment" indicator system, the natural environment early warning monitoring indicator system, and the social environment early warning monitoring indicator system have less impact.

[0078] Step S102, obtaining historical correlation data, evaluating key nodes in the petrochemical port equipment risk topology model based on the historical correlation data, and assigning weights to the key nodes to obtain an optimized petrochemical port equipment risk topology model;

[0079] Exemplarily, in step S102, the key nodes in the petrochemical port equipment risk topology model can be evaluated based on historical correlation data, and the grades of the key nodes can be divided into five levels: U1, U2, U3, U4, and U5, and the weight values ​​of the five levels can be 0.1, 0.2, 0.3, 0.4, and 0.5, respectively.

[0080] It should be noted that the historical correlation data can be obtained in real time from the data storage library of the port monitoring terminal. The port monitoring terminal can be a laptop computer, a personal digital assistant (PDA), a mobile phone and other devices that can communicate, and the historical correlation data include but are not limited to port personnel status monitoring indicators, machinery status monitoring indicators, cargo status monitoring indicators, operating environment monitoring indicators, port ship system monitoring indicators, port vehicle system monitoring indicators, climate monitoring indicators, port hydrological monitoring indicators, port population monitoring indicators, economic factor monitoring indicators and technical factor monitoring indicators.

[0081] In the present application, the petrochemical port equipment risk topology model can establish a network structure layer through the connection topology relationship between multiple groups of petrochemical port equipment and equipment control stations. For example, the equipment control stations are risk-stratified and zoned according to different risk levels, and petrochemical port equipment with the same risk level and connected are listed as the same layer, and petrochemical port equipment with the same risk level but not connected are listed as the same zone.

[0082] Step S103, arranging a three-dimensional monitoring system of port monitoring terminals based on the optimized petrochemical port equipment risk topology model, and acquiring real-time correlation data in real time through the three-dimensional monitoring system of the monitoring terminals.

[0083] Step S104, traversing the historical associated data, and generating a decision knowledge base based on the optimized petrochemical port equipment risk topology model, wherein the decision knowledge base is used to provide risk response solutions to the associated risk diagnosis model.

[0084] In this embodiment, the decision knowledge base generated by the petrochemical port equipment risk topology model is a dynamic knowledge base that can be updated, replaced, deleted and modified. The decision knowledge base can provide decision support for responding to the first warning signal and the second warning signal.

[0085] The embodiment of the present invention provides a method for constructing and training a device safety standardization assessment model. Figure 3 The following is a schematic diagram of the implementation process of a method for constructing and training a device safety standardization evaluation model. The method for constructing and training a device safety standardization evaluation model specifically includes:

[0086] Step S201, obtaining historical correlation data, normalizing the historical correlation data based on a data normalization function to obtain normalized correlation data, dividing the normalized correlation data into a training set, a validation set, and a test set, with the distribution ratio of the training set, the validation set, and the test set being 60%, 20%, and 20%;

[0087] Among them, the data normalization function is expressed by the formula:

[0088]

[0089] In formula (1), G (x,y,z) represents the normalized value corresponding to the historical association data m with three-dimensional coordinates (x, y, z), and μ represents the weight penalty factor for realizing the normalization transformation of the historical association data when the normalization function is passed. The weight penalty factor μ can be 0.05, and c represents the conversion scale of the data normalization function, which is a constant. In this embodiment, c can be 0.5, 0.25, 0.1 or 0.05.

[0090] Step S202, obtaining an initial training model of the equipment safety standardization assessment model, wherein the initial training model includes a linear kernel, a polynomial kernel, a radial kernel, and a sigmoid kernel function;

[0091] It should be noted that the initial training model of the equipment safety standardization assessment model is a support vector machine network (SVM, also known as support vector network), which is a supervised learning model and related learning algorithm for analyzing data in classification and regression analysis. For example, given a set of training instances, each training instance is labeled as belonging to one or the other of two categories, the SVM training algorithm creates a model that assigns new instances to one of the two categories, making it a non-probabilistic binary linear classifier.

[0092] In this embodiment, considering that the radial kernel has a wide range of applications and is mainly used in situations where the linear components are inseparable, the radial kernel function is selected as the kernel function of the initial training model. By selecting an initial training model with a wide range of applications, the present application can well solve the problem of nonlinear fitting of multiple factors and multiple data, and can obtain a global optimal solution, thereby avoiding the problems of local optimality and low global fitting degree in nonlinear fitting, thereby overcoming the shortcomings of traditional neural networks and ensuring the accuracy of the equipment safety standardization evaluation model.

[0093] Step S203, loading the training set, training the radial kernel function based on the training set, iterating the initial training model until the initial training model converges, wherein the radial kernel function is expressed as:

[0094]

[0095] Wherein, σ represents a constant parameter of the kernel function. In this embodiment, the number of iterations of the initial training model is 1000, and σ is 0.05.

[0096] Step S204, loading the validation set, taking the validation set as input, adjusting the kernel function constants and hyperparameters of the initial training model, determining the error rate of the initial training model, and obtaining the optimized initial training model.

[0097] In this embodiment, the error rate of the initial training model may be 0.005-0.001.

[0098] Step S205, obtaining a test set, and verifying the error rate of the optimized initial training model based on the test set. If the error rate of the optimized initial training model is less than the preset error rate, outputting the function expression of the equipment safety standardization evaluation model, wherein the function expression of the equipment safety standardization evaluation model is expressed as:

[0099]

[0100] In this embodiment, the preset error rate may be 0.002-0.001, where J m represents the port equipment operation risk value corresponding to the historical associated data m, b is an impact constant. In this embodiment, b can be a constant in the interval [0,2], representing the s influencing factors (P1, P2, ...P s ) is the weight comparison matrix of a factor O1 in the previous influence level O, ε represents the normalized weight vector, α (x,y,z) represents the hyperparameter tuning function;

[0101]

[0102] in,

[0103] It should be noted that the comparison between the s factors and the tth factor can be performed in pairs. For example, there are multiple levels that affect the status of a single group of equipment, such as impact level P and impact level O. The impact level P contains s influencing factors, and the impact level O contains t influencing factors. Then the impact matrix constant of the single group of equipment status is b.

[0104]

[0105]

[0106] Wherein, n represents the number of historical associated data m.

[0107] Step S206, if the error rate of the optimized initial training model is greater than the preset error rate, adjust the hyperparameters of the optimized initial training model, and iteratively train the optimized initial training model based on the validation set until convergence.

[0108] In this embodiment, the normalization of the training set, validation set and test set is proposed to facilitate the processing of various influencing factors. The main goal of data normalization is to map the normalized associated data corresponding to the training set, validation set and test set to the range of 0-1. Normalization of data is conducive to making the process of finding the optimal solution simpler, and the model is also easier to converge correctly.

[0109] It should be noted that, in step S206, the hyperparameters of the initial training model after adjustment and optimization can be adjusted by using K-fold cross validation combined with a network search method.

[0110] The embodiment of the present invention provides a method for judging real-time correlation data based on a pre-trained correlation risk diagnosis model. Figure 4 The figure shows a schematic diagram of the implementation process of a method for judging real-time associated data based on a pre-trained associated risk diagnosis model. The method for judging real-time associated data based on a pre-trained associated risk diagnosis model specifically includes:

[0111] Step S301: obtain real-time associated data and calculate the support vector machine propagation value H of the real-time associated data. m , where the support vector machine propagates the value H m Calculated by formula (7);

[0112]

[0113] Step S302: propagate the value H based on the support vector machine m Calculate the risk radiation value of petrochemical port equipment corresponding to real-time correlation data.

[0114] Step S303, obtaining the risk radiation value of the petrochemical port area equipment, and calculating the potential risk value of the real-time associated data based on the risk radiation value of the petrochemical port area equipment.

[0115] In this embodiment, the potential risk value L of the real-time associated data m Calculated by formula (8);

[0116]

[0117] Among them, φ and β represent the lower limit coefficient and upper limit coefficient of risk propagation in the associated risk diagnosis model, respectively, and f m represents the risk radiation value of petrochemical port equipment, where f m Calculated by formula (9);

[0118]

[0119] Among them, H m Indicates the support vector machine propagation value H corresponding to the current data m m .

[0120] It should be noted that φ and β represent the lower limit coefficient of risk propagation and the upper limit coefficient of risk propagation in the associated risk diagnosis model, respectively, and the lower limit coefficient of risk propagation can be 0.1, and the upper limit coefficient of risk propagation can be 1.

[0121] In this embodiment, the pre-trained associated risk diagnosis model is also constructed based on a support vector machine network (support vector machine, often referred to as SVM, also known as support vector network). The support vector machine network is a supervised learning model and related learning algorithm for analyzing data in classification and regression analysis. The training method of the associated risk diagnosis model is the same as the above-mentioned equipment safety standardization assessment model. Through the equipment safety standardization assessment model and the associated risk diagnosis model, the operating status of the petrochemical port equipment can be evaluated, and the potential risk value of the equipment can be calculated, thereby providing support for equipment operation early warning.

[0122] In this embodiment, the potential risk value L of the real-time associated data is m If the second risk threshold is exceeded, a second warning signal is issued, and the second risk threshold can be a constant in the range of [0.85-0.95]. When judging whether the equipment operating status exceeds the preset first risk threshold, the second risk threshold can be a constant in the range of [0.65-0.85].

[0123] On the other hand, the embodiment of the present invention also provides a petrochemical port equipment operation safety risk early warning system based on a support vector machine. Figure 5 The structural diagram of the support vector machine petrochemical port equipment operation safety risk early warning system is shown. The support vector machine petrochemical port equipment operation safety risk early warning system specifically includes:

[0124] A monitoring data acquisition module 100, wherein the monitoring data acquisition module 100 acquires multiple sets of monitoring data for characterizing the operating status of the petrochemical port equipment through the port monitoring terminal, wherein the monitoring data includes real-time correlation data and historical correlation data;

[0125] A model building module 200, wherein the model building module 200 is used to load historical correlation data, and to build and train a device safety standardization assessment model and an associated risk diagnosis model based on the historical correlation data;

[0126] The first judgment module 300 identifies the real-time associated data based on the equipment safety standardization assessment model, judges the operating status of the petrochemical port equipment through the equipment safety standardization assessment model, and judges whether the equipment operating status exceeds a preset first risk threshold. If the first risk threshold is exceeded, a first warning signal is issued;

[0127] The second judgment module 400 judges the real-time association data based on the pre-trained association risk diagnosis model to determine whether the equipment operation status exceeds a second risk threshold.

[0128] In this embodiment, the monitoring data acquisition module 100 can be connected to multiple groups of port monitoring terminals in a one-to-n manner, and the method for the model construction module 200 to specifically construct and train the equipment safety standardization assessment model can refer to the equipment safety standardization assessment model construction method mentioned above, which will not be repeated here. Each module in the model construction module 200 can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0129] It should be noted that data interaction can be achieved between the monitoring data acquisition module 100, the model building module 200, the first judgment module 300 and the second judgment module 400 by means of Bluetooth communication, 5G communication or DTU communication.

[0130] The embodiment of the present invention is provided with a model building module 200. The setting of the model building module 200 solves the problems of low accuracy of existing petrochemical port operation safety warnings and insufficient consideration of potential value information in historical data, thereby being able to judge the potential risk value of real-time associated data, issue warnings for potential risks in equipment operation, and ensure the smooth operation of petrochemical port equipment.

[0131] The embodiment of the present invention further provides a monitoring data acquisition module 100, Figure 6 The structure diagram of the monitoring data acquisition module 100 is shown, and the monitoring data acquisition module 100 specifically includes:

[0132] A topology model building unit 110, wherein the topology model building unit 110 builds a petrochemical port equipment risk topology model based on a support vector machine;

[0133] A weight assignment unit 120, the weight assignment unit 120 is used to obtain historical correlation data, evaluate key nodes in the petrochemical port equipment risk topology model based on the historical correlation data, and assign weights to the key nodes to obtain an optimized petrochemical port equipment risk topology model;

[0134] The monitoring terminal management unit 130 arranges the three-dimensional monitoring system of the port monitoring terminal based on the optimized petrochemical port equipment risk topology model, and obtains real-time correlation data in real time through the three-dimensional monitoring system of the monitoring terminal, and

[0135] The knowledge base service unit 140 is used to traverse the historical associated data and generate a decision knowledge base based on the optimized petrochemical port equipment risk topology model, wherein the decision knowledge base is used to provide risk response solutions to the associated risk diagnosis model.

[0136] On the other hand, an embodiment of the present invention further provides a computer device, which includes a display screen, a memory, a processor and a computer program, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the support vector machine petrochemical port equipment operation safety risk warning method are implemented.

[0137] On the other hand, the present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the support vector machine petrochemical port equipment operation safety risk warning method.

[0138] Exemplarily, the computer program can be divided into one or more modules, one or more modules are stored in the memory and executed by the processor to complete the present invention. One or more modules can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the above-mentioned computer program can be divided into units or modules of the petrochemical port equipment operation safety risk early warning system of the support vector machine provided by each of the above-mentioned system embodiments.

[0139] The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0140] The above-mentioned memory can be used to store computer programs and / or modules, and the above-mentioned processor realizes various functions of the above-mentioned terminal device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created by the use of the petrochemical port equipment operation safety risk early warning system based on the support vector machine. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart MediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0141] In summary, the present invention provides a petrochemical port equipment operation safety risk warning method and system based on a support vector machine. The embodiment of the present invention identifies real-time associated data based on an equipment safety standardization assessment model, thereby being able to conduct a comprehensive analysis of equipment safety issues with multiple potential risk factors and judge the operating status of petrochemical port equipment. At the same time, it can also judge the potential risk value of real-time associated data based on a pre-trained associated risk diagnosis model, warn of potential risks in equipment operation, and ensure the smooth operation of petrochemical port equipment.

[0142] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0143] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0144] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A petrochemical port equipment operation safety risk early warning method based on support vector machine, characterized by: Obtain multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal, wherein the monitoring data includes real-time correlation data and historical correlation data; Load historical correlation data, build and train a device safety standardization assessment model based on the historical correlation data; Based on the equipment safety standardization assessment model to identify real-time related data, the equipment safety standardization assessment model is used to determine the operating status of the petrochemical port equipment and whether the equipment operating status exceeds the preset first risk threshold. If it exceeds the first risk threshold, the first warning signal is issued. The output result of the equipment safety standardization assessment model is , Represents historical related data The corresponding risk value of port equipment operation; If the equipment operation status does not exceed the preset first risk threshold, the real-time associated data is judged based on the pre-trained associated risk diagnosis model to determine whether the equipment operation status exceeds the second risk threshold. If it exceeds the second risk threshold, a second warning signal is issued; The method for judging real-time associated data based on the pre-trained associated risk diagnosis model specifically includes: Acquire real-time correlation data and calculate the support vector machine propagation value of the real-time correlation data , where the support vector machine propagates the value Calculated by formula (7); （7）； Propagating values ​​based on support vector machines Calculate the risk radiation value of petrochemical port equipment corresponding to real-time correlation data; Obtain the risk radiation value of petrochemical port equipment, and calculate the potential risk value of real-time associated data based on the risk radiation value of petrochemical port equipment; The potential risk value of the real-time associated data Calculated by formula (8); （8） in, , They represent the lower limit coefficient of risk propagation and the upper limit coefficient of risk propagation in the associated risk diagnosis model respectively. Represents the risk radiation value of petrochemical port equipment, where Calculated by formula (9); （9） in, Indicates current data The corresponding support vector machine propagation value .

2. A petrochemical port equipment operation safety risk early warning method based on support vector machine as claimed in claim 1, characterized in that: The method for obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal specifically includes: Constructing a risk topology model for petrochemical port equipment based on support vector machine; Acquire historical correlation data, evaluate key nodes in the petrochemical port equipment risk topology model based on the historical correlation data, and assign weights to the key nodes to obtain an optimized petrochemical port equipment risk topology model; Based on the optimized petrochemical port equipment risk topology model, the three-dimensional monitoring system of the port monitoring terminal is arranged, and real-time correlation data is obtained through the three-dimensional monitoring system of the monitoring terminal.

3. A method for early warning of equipment operation safety risks in a petrochemical port area based on a support vector machine as claimed in claim 2, characterized in that: The method for obtaining multiple groups of monitoring data for characterizing the operating status of petrochemical port equipment through the port monitoring terminal specifically includes: The historical associated data are traversed, and a decision knowledge base is generated based on the optimized petrochemical port equipment risk topology model, wherein the decision knowledge base is used to provide risk response solutions to the associated risk diagnosis model.

4. A method for early warning of equipment operation safety risks in a petrochemical port area based on a support vector machine as claimed in claim 3, characterized in that: The method for constructing and training the equipment safety standardization assessment model specifically includes: Obtain historical correlation data, normalize the historical correlation data based on the data normalization function to obtain normalized correlation data, and divide the normalized correlation data into a training set, a validation set, and a test set. The distribution ratios of the training set, the validation set, and the test set are 60%, 20%, and 20%; Among them, the data normalization function is expressed by the formula: （1） In formula (1), Represents the three-dimensional coordinates as ( ) The corresponding normalized value is represents the weight penalty factor for normalizing historical correlation data through the normalization function, and Represents the conversion scale of the data normalization function, which is a constant; Obtaining an initial training model of a device safety standardization assessment model, wherein the initial training model includes a linear kernel, a polynomial kernel, a radial kernel, and a sigmoid kernel function; The training set is loaded, a radial kernel function is trained based on the training set, and the initial training model is iterated until the initial training model converges, wherein the radial kernel function is expressed as: （2） Among them, the Represents the constant parameter of the kernel function; Load the validation set, use the validation set as input, adjust the kernel function constants and hyperparameters of the initial training model, determine the error rate of the initial training model, and then obtain the optimized initial training model.

5. A method for early warning of equipment operation safety risks in a petrochemical port area based on a support vector machine as claimed in claim 4, characterized in that: The method for constructing and training the equipment safety standardization assessment model specifically includes: Obtain a test set, and verify the error rate of the optimized initial training model based on the test set. If the error rate of the optimized initial training model is less than the preset error rate, output the function expression of the equipment safety standardization evaluation model, where the function expression of the equipment safety standardization evaluation model is expressed as: （3） in, Represents historical related data The corresponding port equipment operation risk value, Influence constant, indicating historical related data Medium impact level middle Factors that influence Relative to the previous impact level One of the influencing factors The weight comparison matrix, represents the normalized weight vector, represents the hyperparameter tuning function; （4） in, （5） （6） in, Represents historical related data The number of If the error rate of the optimized initial training model is greater than the preset error rate, adjust the hyperparameters of the optimized initial training model, and iteratively train the optimized initial training model based on the validation set until convergence.

6. A petrochemical port equipment operation safety risk early warning system based on support vector machine, using the method according to any one of claims 1 to 5, characterized in that: include: A monitoring data acquisition module, wherein the monitoring data acquisition module acquires multiple sets of monitoring data for characterizing the operating status of petrochemical port equipment through a port monitoring terminal, wherein the monitoring data includes real-time correlation data and historical correlation data; A model building module, the model building module is used to load historical correlation data, build and train a device safety standardization assessment model and an associated risk diagnosis model based on the historical correlation data; A first judgment module, wherein the first judgment module identifies real-time associated data based on the equipment safety standardization assessment model, judges the operating status of the petrochemical port equipment through the equipment safety standardization assessment model, and judges whether the equipment operating status exceeds a preset first risk threshold, and if it exceeds the first risk threshold, issues a first warning signal; The second judgment module judges the real-time association data based on the pre-trained association risk diagnosis model to determine whether the equipment operation status exceeds a second risk threshold.

7. A petrochemical port equipment operation safety risk early warning system based on support vector machine as claimed in claim 6, characterized in that: The monitoring data acquisition module specifically includes: A topology model building unit, wherein the topology model building unit builds a petrochemical port area equipment risk topology model based on a support vector machine; A weight assignment unit, the weight assignment unit is used to obtain historical correlation data, evaluate key nodes in the petrochemical port equipment risk topology model based on the historical correlation data, and assign weights to the key nodes to obtain an optimized petrochemical port equipment risk topology model; The monitoring terminal management unit arranges the three-dimensional monitoring system of the port monitoring terminal based on the optimized petrochemical port equipment risk topology model, and obtains real-time correlation data through the three-dimensional monitoring system of the monitoring terminal, and A knowledge base service unit, the knowledge base service unit is used to traverse historical associated data and generate a decision knowledge base based on the optimized petrochemical port equipment risk topology model, wherein the decision knowledge base is used to provide risk response solutions to the associated risk diagnosis model.

Images