Port environment risk monitoring and early warning method and system

Abstract

The invention relates to the technical field of environment safety early warning, in particular to a harbor environment risk monitoring and early warning method and system.The method comprises the steps that when safety early warning is conducted on the harbor environment, prediction indexes are classified into static indexes and non-static indexes, and in the subsequent index utilization process, the harbor environment risk monitoring and early warning method is provided for harbor environment risk monitoring and early warning. The time attribute of a non-static index is embodied, so that the accuracy of monitoring and early warning of the environmental risk of the port is improved; according to the method, time attribute weighting is carried out on the non-static index based on the continuous time function, the influence of the monitoring value on the weight is considered in the weighting process, and the accuracy of non-static index weighting at different times is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental safety early warning, and in particular to a port environmental risk monitoring and early warning method and system. Background Art

[0002] Dangerous goods container yards at ports are one of the main environmental safety issues and problems faced by the transportation industry. In order to effectively prevent and minimize the impact of accidents at dangerous goods container yards on water environment and water safety, this paper studies the identification of water environment risks at dangerous goods container yards at ports, establishes a water environment risk identification list, reveals the impact mechanism, and develops an environmental monitoring and emergency smart management and control platform, which can provide technical support for environmental impact assessment and emergency plans for dangerous goods container yard projects, as well as environmental protection design and enterprise water pollution risk emergency management.

[0003] In the prior art, early warning indicators are generally designed and then input into the prediction model to obtain the early warning level. However, in the above scheme, when issuing early warnings for sudden environmental safety in ports, all indicators are input into the prediction model without distinction. For some indicators related to environmental prediction, they themselves have dynamic significance, that is, they show a certain trend of change with the change of time, and this trend has a certain indicative effect on the early warning of sudden environment. Therefore, ignoring its time attribute will lead to low accuracy of port environmental risk monitoring and early warning. Summary of the invention

[0004] In view of this, the present invention proposes a port environmental risk monitoring and early warning method and system, which are used to improve the accuracy of port environmental risk monitoring and early warning.

[0005] In order to achieve the above object, a port environmental risk monitoring and early warning method is provided, the method comprising: S1: Determine the predictive indicators for port environmental risk monitoring and early warning; S2: classifying the prediction indicators into static indicators and non-static indicators; S3: performing a weighting operation on the prediction indicators to obtain a weight of each prediction indicator; The weighting operation of the prediction index is specifically as follows: S3.1: performing a weighting operation on the static indicators to obtain a weight base value of each static indicator; S3.2: performing a weighting operation on the non-static indicators to obtain a weight base value of each non-static indicator; The weighting formula of the non-static indicator is: ; ; Where a(t) is the time attribute factor of the non-static indicator; t is the sampling time, t0 is the initial timing time, λ(t) is the weight base value of the non-static indicator at time t, b i (t) is the monitoring value of the i-th indicator at sampling time t; B i is the preset threshold of the i-th indicator; S3.3: Obtain the weight of each prediction indicator based on the weight base value of each non-static indicator and the weight base value of each static indicator; S4: Preprocessing the numerical indicators in the prediction indicators according to the weight of each prediction indicator, and combining the non-numerical indicators in the prediction indicators and the values ​​of the preprocessed numerical indicators to obtain a data set for port environmental risk monitoring and early warning; S5: Establish a port environmental risk monitoring and early warning model; S6: Input the data set of the port environmental risk monitoring and early warning into the port environmental risk monitoring and early warning model to obtain a safety early warning result.

[0006] Preferably, t0 is the time when the content of dangerous goods in the air monitored by the monitoring point exceeds the corresponding threshold value as the initial timing time of t0; i The maximum historical content of dangerous goods in the air monitored by the monitoring point is used as the preset threshold value of the i-th indicator.

[0007] Preferably, in S1, the prediction indicators include the name of dangerous goods in the port, the category of dangerous goods in the port, the content of dangerous goods in the air, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port, the atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m 3 ), temperature where the dangerous goods are located, humidity where the dangerous goods are located, and wind speed where the dangerous goods are located.

[0008] Preferably, in S2, the static indicators are: name of dangerous goods in the port, category of dangerous goods in the port, relative vapor density of dangerous goods in the port, maximum storage capacity of dangerous goods in the port, atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m 3 ); The non-static indicators are: the content of dangerous goods in the air, the temperature where the dangerous goods are located, the humidity where the dangerous goods are located, and the wind speed where the dangerous goods are located.

[0009] Preferably, in S3.3, the weight of each prediction indicator is obtained by normalizing the weight base value of each non-static indicator and the weight base value of each static indicator.

[0010] Preferably, in S4, the numerical indicators in the prediction indicators are the content of dangerous goods in the air, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port, the atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m 3 ), temperature where the dangerous goods are located, humidity where the dangerous goods are located, and wind speed where the dangerous goods are located.

[0011] Preferably, in S4, the preprocessing operation is specifically: multiplying the monitoring value of each numerical indicator by the weight of the prediction indicator to obtain the value of the prediction indicator.

[0012] Preferably, in S5, an artificial neural network model is used as a port environmental risk monitoring and early warning model.

[0013] Preferably, the artificial neural network model comprises an input layer, a hidden layer and an output layer.

[0014] According to another aspect of the present invention, a port environmental risk monitoring and early warning system is provided, wherein the system adopts any one of the port environmental risk monitoring and early warning methods described above, and the system comprises: A prediction index determination module is used to determine prediction indexes for port environmental risk monitoring and early warning; An indicator classification module is used to classify the prediction indicators into static indicators and non-static indicators; A weighting module, used to perform a weighting operation on the prediction indicators to obtain the weight of each prediction indicator; A data set calculation module, used for preprocessing the numerical indicators in the prediction indicators according to the weight of each prediction indicator, and combining the non-numerical indicators in the prediction indicators and the values ​​of the preprocessed numerical indicators to obtain a data set for port environmental risk monitoring and early warning; Safety early warning model building module, used to build port environmental risk monitoring and early warning model; The early warning module is used to input the data set for port environmental risk monitoring and early warning into the port environmental risk monitoring and early warning model to obtain a safety early warning result. The advantages and beneficial effects of the present invention are: When the present invention performs safety early warning monitoring on port environmental risks, the prediction indicators are classified into static indicators and non-static indicators, wherein the static indicators are: the name of dangerous goods in the port, the category of dangerous goods in the port, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port, the atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m 3); non-static indicators are: the content of dangerous goods in the air, the temperature of the dangerous goods location, the humidity of the dangerous goods location, and the wind speed of the dangerous goods location; and in the subsequent indicator utilization process, the time attribute of the non-static indicators is reflected to improve the accuracy of port environmental risk monitoring and early warning; The present invention weights the time attributes of non-static indicators based on a continuous time function, and considers the influence of monitoring values ​​on the weights during the weighting process, thereby effectively improving the accuracy of weighting non-static indicators at different times. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the description of the present invention or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a port environmental risk monitoring and early warning method provided by an embodiment of the present invention; Figure 2 A flowchart of weighting operations for prediction indicators provided by an embodiment of the present invention; Figure 3 A structural diagram of an artificial neural network model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] As attached Figure 1 As shown, a port environmental risk monitoring and early warning method comprises the following steps: S1: Determine the predictive indicators for port environmental risk monitoring and early warning; In this step, the prediction indicators for port environmental risk monitoring and early warning are determined by searching literature and consulting experts; In this embodiment, the prediction indicators include the name of dangerous goods in the port, the category of dangerous goods in the port, the content of dangerous goods in the air, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port (TEU), the atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m3 ), temperature of the location where the dangerous goods are located, humidity of the location where the dangerous goods are located, wind speed of the location where the dangerous goods are located; Among them, the categories of dangerous goods include: The classification of dangerous goods is mainly based on their dangerous nature and potential hazards, and is usually divided into the following nine categories: Explosives (Class 1): This type of items includes explosive substances and items, such as dynamite, detonators, fireworks and firecrackers, etc. Explosives will react rapidly and violently under the action of pressure, temperature changes or other factors, producing explosive effects; Gases (Class 2): Gas dangerous goods are divided into flammable gases, non-flammable non-toxic gases, toxic gases, etc. Common gases include hydrogen, methane, carbon dioxide, etc.; Flammable liquids (Class 3): This type of substance can be ignited and burn rapidly at room temperature, such as gasoline, alcohol, diesel, etc.; Flammable solids (Class 4): This type of substance is flammable in the air or reacts violently with water in water, such as sulfur, white phosphorus, etc.; Oxidizing substances and organic peroxides (Class 5): Oxidizing substances can release oxygen to cause combustion, and organic peroxides are easily decomposed under external factors such as high temperature and impact, releasing a large amount of heat energy. Common oxidizing substances include potassium permanganate, 84 disinfectant, etc.; Toxic and infectious substances (Class 6): This type of substances includes infectious substances, such as pesticides, viruses, etc.; Radioactive substances (Class 7): Radioactive substances are radioactive, and common ones include luminous powder, uranium, etc.; Corrosive substances (Class 8): This type of substances is corrosive, such as sulfuric acid, hydrochloric acid, etc.; Miscellaneous dangerous substances and articles (Class 9): Including environmentally hazardous substances, such as lithium batteries, blue asbestos, etc.; Among them, this embodiment performs environmental safety warning for gaseous dangerous goods in ports, therefore, the content of dangerous goods in the air is used as a prediction index. Furthermore, the content of dangerous goods in the air is the content of dangerous goods in the air monitored by the sensor at the monitoring point; For example, the following table shows some prediction indicators for some other dangerous goods. Please refer to the table below for details.

[0019] Table 1 Some prediction indicators of gaseous dangerous goods (item 2.1)

[0020] S2: classifying the prediction indicators into static indicators and non-static indicators; In the field of port environmental risk safety warning, the prior art generally designs warning indicators and then inputs the indicators into the prediction model to obtain the warning level; however, in the above scheme, when warning the port environmental risk safety, all indicators are input into the prediction model without distinction. For some indicators related to environmental prediction, they themselves have dynamic significance, that is, they show a certain trend change with the change of time, and this trend has a certain indicative effect on the early warning of environmental risks. Therefore, ignoring their time attributes will lead to low accuracy of port environmental risk monitoring and early warning; therefore, according to the above status, this embodiment classifies the prediction indicators into static indicators and non-static indicators, and in the subsequent indicator utilization process, the time attributes of the non-static indicators are reflected to improve the accuracy of sudden environmental safety early warning; Specifically, the static indicators are: name of dangerous goods in the port, category of dangerous goods in the port, relative vapor density of dangerous goods in the port, maximum storage capacity of dangerous goods in the port (TEU), atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m 3 ); The non-static indicators are: the content of dangerous goods in the air, the temperature of the location where the dangerous goods are located, the humidity of the location where the dangerous goods are located, and the wind speed of the location where the dangerous goods are located; S3: performing a weighting operation on the prediction indicators to obtain a weight of each prediction indicator; In this step, attach Figure 2 The flowchart of weighting the prediction indicators is shown in the attached figure. Figure 2 As shown, the weighting operation of the prediction index is specifically as follows: S3.1: performing a weighting operation on the static indicators to obtain a weight base value of each static indicator; A preset number of experts are selected to score the importance of the static indicators, and then the average score is taken as the weight base value; S3.2: performing a weighting operation on the non-static indicators to obtain a weight base value of each non-static indicator; Compared with the prior art, this embodiment is the first to weight time attributes based on non-static indicators. Therefore, the expert scoring method cannot perform effective weighting operations. This embodiment proposes a non-static indicator weighting method for implementing non-static indicator weighting operations. The weighting formula of the non-static indicator is: ; ; Where a(t) is the time attribute factor of the non-static indicator; t is the sampling time, t0 is the initial timing time, λ(t) is the weight base value of the non-static indicator at time t, b i (t) is the monitoring value of the i-th indicator at sampling time t; B i is the preset threshold of the i-th indicator; In this embodiment, t0 is the time when the content of dangerous goods in the air monitored by the monitoring point exceeds the corresponding threshold value as the initial timing time of t0; i is the maximum historical content of dangerous goods in the air monitored by the monitoring point, and the maximum historical content is used as the preset threshold of the i-th indicator; For the purpose of convenient calculation, the time t0 can be assigned a value of 1, and the time t is defined as the ratio of the difference from the time t0 to the sampling interval; for example, the time t0 is 02:20; the time t is 02:40, and the sampling interval is 5 minutes, then t0 is 1 and t is 4; Through the above operations, the time attributes of non-static indicators are weighted based on continuous time functions, and the influence of monitoring values ​​on weights is considered in the weighting process, which effectively improves the accuracy of weighting of non-static indicators at different times.

[0021] S3.3: Obtain the weight of each prediction indicator based on the weight base value of each non-static indicator and the weight base value of each static indicator; In this step, the weight of each prediction indicator is obtained by normalizing the weight base value of each non-static indicator and the weight base value of each static indicator; S4: Preprocessing the numerical indicators in the prediction indicators according to the weight of each prediction indicator, and combining the non-numerical indicators in the prediction indicators and the values ​​of the preprocessed numerical indicators to obtain a data set for port environmental risk safety warning; The numerical indicators in the prediction index are the content of dangerous goods in the air, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port (TEU), the atmospheric toxicity endpoint concentration (1 / mg / m 3 ), atmospheric toxicity endpoint concentration (2 / mg / m 3 ), temperature of the location where the dangerous goods are located, humidity of the location where the dangerous goods are located, wind speed of the location where the dangerous goods are located; The preprocessing operation is specifically: multiplying the monitoring value of each numerical indicator by the weight of the prediction indicator to obtain the value of the prediction indicator; S5: Establish a port environmental risk monitoring and early warning model; In this step, an artificial neural network model is used as a port environmental safety risk warning model. Artificial Neural Networks (ANN) is a mathematical model that simulates the structure and function of a biological nervous system. It consists of a large number of nodes (called neurons) connected to each other. Each node represents a specific output function (called an activation function). The connection between nodes represents the weighted value of the signal (called weight). These weights are equivalent to the memory of the artificial neural network. The output of the artificial neural network model depends on the structure, connection mode, weight and activation function of the network. The artificial neural network model itself is usually an approximation of a certain algorithm or function in nature, or it may be an expression of a logical strategy; the artificial neural network model processes information by adjusting the connection relationship between a large number of nodes. Each node represents a specific output function (activation function), and the connection between nodes has a weight. These weights determine the strength of the signal passing through the connection. The network continuously adjusts these weights through learning to optimize the output of the network. The learning process of the network is usually achieved through mathematical statistical methods, so that the network can simulate human decision-making and judgment capabilities; In this embodiment, the attached Figure 3 The structure diagram of the artificial neural network model is shown in the attached figure. Figure 3 As shown, the artificial neural network model includes an input layer, a hidden layer and an output layer; The input layer is the starting point of the artificial neural network model and is used to receive a data set. The input layer does not perform calculations but only transmits the data in the data set to the hidden layer. The hidden layer is the part of the artificial neural network model that actually performs calculations and is responsible for extracting features from the data set transmitted by the input layer. The hidden layer can be one or more layers. The number of hidden layers can be adjusted according to the needs of specific tasks. Generally, increasing the number of hidden layers can increase the complexity of the network, enabling it to learn more complex patterns. Each hidden layer introduces nonlinearity through an activation function, enabling the network to learn complex nonlinear relationships. The hidden layer works through forward propagation and back propagation mechanisms. In forward propagation, the input data is calculated through the weights and biases of each layer to obtain the output. In back propagation, the weights and biases of each layer are adjusted through the gradient descent algorithm according to the error of the output layer to minimize the loss function. This process is iterated continuously until the network achieves satisfactory performance. In this embodiment, the activation function of the hidden layer is a ReLU activation function; The output layer is the last layer of the artificial neural network model, which is responsible for generating the final prediction result; S6: Input the data set of the port environmental risk monitoring and early warning into the port environmental risk monitoring and early warning model to obtain a safety early warning result.

[0022] Embodiment 2: This embodiment includes a port environmental risk monitoring and early warning system, the system adopts a port environmental risk monitoring and early warning method of embodiment 1, and the system includes: A prediction index determination module is used to determine prediction indexes for port environmental risk monitoring and early warning; An indicator classification module is used to classify the prediction indicators into static indicators and non-static indicators; A weighting module, used to perform a weighting operation on the prediction indicators to obtain the weight of each prediction indicator; A data set calculation module, used for preprocessing the numerical indicators in the prediction indicators according to the weight of each prediction indicator, and combining the non-numerical indicators in the prediction indicators and the values ​​of the preprocessed numerical indicators to obtain a data set for port environmental risk monitoring and early warning; Safety early warning model building module, used to build port environmental risk monitoring and early warning model; The early warning module is used to input the data set for port environmental risk monitoring and early warning into the port environmental risk monitoring and early warning model to obtain a safety early warning result. Embodiment 3, this embodiment includes a computer-readable storage medium, on which a data processing program is stored, and the data processing program is executed by a processor. A method for monitoring and early warning of port environmental risks in embodiment 1.

[0023] It should be understood by those skilled in the art that the embodiments of this article can be provided as methods, devices (equipment), or computer program products. Therefore, this article can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media generally contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0024] This document is described with reference to flowcharts and / or block diagrams of methods, apparatuses (devices), and computer program products according to the embodiments of this document. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0025] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0026] The embodiments and / or implementation methods described above are only used to illustrate the preferred embodiments and / or implementation methods of the technology of the present invention, and are not intended to impose any formal restrictions on the implementation methods of the technology of the present invention. Any person skilled in the art may make some changes or modifications to other equivalent embodiments without departing from the scope of the technical means disclosed in the content of the present invention, but they should still be regarded as the technology or embodiments that are essentially the same as the present invention. Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described here, and that various obvious changes, readjustments and substitutions can be made to those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention is described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A port environmental risk monitoring and early warning method, characterized in that: The method comprises the following steps: S1: Determine the predictive indicators for port environmental risk monitoring and early warning; S2: classifying the prediction indicators into static indicators and non-static indicators; S3: performing a weighting operation on the prediction indicators to obtain a weight of each prediction indicator; The weighting operation of the prediction index is specifically as follows: S3.1: performing a weighting operation on the static indicators to obtain a weight base value of each static indicator; S3.2: performing a weighting operation on the non-static indicators to obtain a weight base value of each non-static indicator; The weighting formula of the non-static indicator is: ； ； Where a(t) is the time attribute factor of the non-static indicator; t is the sampling time, t0 is the initial timing time, λ(t) is the weight base value of the non-static indicator at time t, b i (t) is the monitoring value of the i-th indicator at sampling time t; B i is the preset threshold of the i-th indicator; S3.3: Obtain the weight of each prediction indicator based on the weight base value of each non-static indicator and the weight base value of each static indicator; S4: Preprocessing the numerical indicators in the prediction indicators according to the weight of each prediction indicator, and combining the non-numerical indicators in the prediction indicators and the values ​​of the preprocessed numerical indicators to obtain a data set for port environmental risk monitoring and early warning; S5: Establish a port environmental risk monitoring and early warning model; S6: Input the data set of the port environmental risk monitoring and early warning into the port environmental risk monitoring and early warning model to obtain a safety early warning result.

2. A port environmental risk monitoring and early warning method according to claim 1, characterized in that: t0 is the time when the content of dangerous goods in the air monitored by the monitoring point exceeds the corresponding threshold, and this time is used as the initial timing time; i The maximum historical content of dangerous goods in the air monitored by the monitoring point is used as the preset threshold value of the i-th indicator.

3. A port environmental risk monitoring and early warning method according to claim 1, characterized in that: In S1, the prediction indicators include the name of dangerous goods in the port, the category of dangerous goods in the port, the content of dangerous goods in the air, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port, and the atmospheric toxicity endpoint concentration_1 / mg / m 3 , atmospheric toxicity endpoint concentration_2 / mg / m 3 , temperature where the dangerous goods are located, humidity where the dangerous goods are located, and wind speed where the dangerous goods are located.

4. A port environmental risk monitoring and early warning method according to claim 1, characterized in that: In S2, the static indicators are: the name of dangerous goods in the port, the category of dangerous goods in the port, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port, and the atmospheric toxicity endpoint concentration_1 / mg / m 3 , atmospheric toxicity endpoint concentration_2 / mg / m 3 The non-static indicators are: the content of dangerous goods in the air, the temperature where the dangerous goods are located, the humidity where the dangerous goods are located, and the wind speed where the dangerous goods are located.

5. A port environmental risk monitoring and early warning method according to claim 1, characterized in that: In S3.3, the weight of each prediction indicator is obtained by normalizing the weight base value of each non-static indicator and the weight base value of each static indicator.

6. A port environmental risk monitoring and early warning method according to claim 1, characterized in that: In S4, the numerical indicators in the prediction indicators are the content of dangerous goods in the air, the relative vapor density of dangerous goods in the port, the maximum storage capacity of dangerous goods in the port, and the atmospheric toxicity endpoint concentration_1 / mg / m 3 , atmospheric toxicity endpoint concentration_2 / mg / m 3 , temperature where the dangerous goods are located, humidity where the dangerous goods are located, and wind speed where the dangerous goods are located.

7. A port environmental risk monitoring and early warning method according to claim 6, characterized in that: In S4, the preprocessing operation is specifically: multiplying the monitoring value of each numerical indicator by the weight of the prediction indicator to obtain the value of the prediction indicator.

8. A port environmental risk monitoring and early warning method according to claim 1, characterized in that: In S5, an artificial neural network model is used as a port environmental risk monitoring and early warning model.

9. A port environmental risk monitoring and early warning method according to claim 8, characterized in that: The artificial neural network model includes an input layer, a hidden layer and an output layer.

10. A port environmental risk monitoring and early warning system, characterized in that: The system adopts a port environmental risk monitoring and early warning method according to any one of claims 1 to 9, and the system comprises: A prediction index determination module is used to determine prediction indexes for port environmental risk monitoring and early warning; An indicator classification module is used to classify the prediction indicators into static indicators and non-static indicators; A weighting module, used to perform a weighting operation on the prediction indicators to obtain the weight of each prediction indicator; A data set calculation module, used for preprocessing the numerical indicators in the prediction indicators according to the weight of each prediction indicator, and combining the non-numerical indicators in the prediction indicators and the values ​​of the preprocessed numerical indicators to obtain a data set for port environmental risk monitoring and early warning; Safety early warning model building module, used to build port environmental risk monitoring and early warning model; The early warning module is used to input the data set used for port environmental risk monitoring and early warning into the port environmental risk monitoring and early warning model to obtain a safety early warning result.

Images