A method for safety monitoring and intelligent risk identification of high-risk operations in ports
By collecting and processing data in port operations, and using deep neural network models to identify and quantify high-risk scenarios, the problem of incomplete risk identification in existing technologies has been solved, enabling accurate risk warning and safety management.
Patent Information
- Application Number
- CN202411162155.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-23
AI Technical Summary
Existing port operation safety monitoring systems cannot fully cover all types of risks, lack scientific risk quantification and early warning signals, which limits the accuracy and effectiveness of early warning signals and makes it difficult to effectively identify and assess complex risks.
By collecting real-time environmental data and equipment operation data from the port operation area, preprocessing the data, and inputting it into a deep neural network model, potential high-risk operation scenarios are identified. Multiple analyses are then performed, and quantitative scoring is used to generate real-time risk level warning signals. These signals are further subdivided into three categories of risk indicators: physical, chemical, and behavioral. Each risk indicator is assigned a weight to generate accurate warning signals.
It enables accurate identification and early warning of high-risk operations at ports, improves the scientific nature and efficiency of safety management, avoids waste of resources, and ensures the effectiveness of accident prevention and safety management.
Smart Images

Figure CN118691090B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of port management and operation, and in particular to a method for safety monitoring and intelligent risk identification of high-risk operations in ports. Background Art
[0002] In port operations, there are many safety hazards due to factors such as complex operating environment, high-density logistics transportation, diverse mechanical equipment and harsh natural conditions. These hazards may cause major safety accidents, resulting in casualties, property losses and even environmental pollution. Therefore, effective monitoring and intelligent identification of high-risk scenarios in port operations are crucial to improving the safety and efficiency of port operations.
[0003] Traditional port safety management methods mostly rely on manual observation and empirical judgment, lack of systematicity and real-timeness, and are unable to accurately evaluate and warn potential high-risk operation scenarios. With the development of information technology, especially the maturity of big data, artificial intelligence and other technologies, new solutions have been provided for the safety monitoring of high-risk operations in ports. However, existing monitoring systems often only focus on a single risk source and fail to fully cover various risks such as physical, chemical and behavioral risks. In addition, there is a lack of scientific basis for risk quantification and early warning signal generation, which limits the accuracy and effectiveness of early warning signals.
[0004] In addition, the port operation environment is complex and changeable, and various risk factors are intertwined. Traditional methods are difficult to effectively identify and evaluate compound risks. Therefore, there is an urgent need for a new method that can comprehensively analyze various risk indicators, realize intelligent risk identification, and generate accurate early warning signals to improve the safety management level of port operations, reduce the possibility of accidents, and ensure the effective use of resources to avoid unnecessary cost expenditures.
[0005] Therefore, the prior art urgently needs a technical solution for high-risk port operation safety monitoring and risk intelligent identification method. Summary of the invention
[0006] In order to solve the above technical problems, the present invention provides a method for safety monitoring and intelligent risk identification of high-risk operations in ports, which is characterized by comprising the following steps:
[0007] Step S1, collecting real-time environmental data and equipment operation data in the port operation area;
[0008] Step S2: pre-processing the received real-time environmental data and equipment operation data;
[0009] Step S3: input the preprocessed real-time environmental data and equipment operation data into the pre-trained deep neural network model to identify potential high-risk operation scenarios;
[0010] Step S4, performing multiple analyses on potential high-risk operation scenarios, obtaining quantitative scores of potential high-risk operation scenarios according to the multiple analysis results, and generating different real-time risk level warning signals based on the quantitative scores of potential high-risk operation scenarios;
[0011] Step S41, obtaining all risk indicators in potential high-risk operation scenarios, judging all the obtained risk indicators, and dividing all the risk indicators into three categories according to the judgment results;
[0012] The three categories include physical risk indicators, chemical risk indicators, and behavioral risk indicators;
[0013] Step S42: performing importance analysis on the risk indicators included in each category of risk indicators, and ranking the risk indicators included in each category of risk indicators according to the importance analysis result, and obtaining the top five risk indicators based on the ranking result;
[0014] The top five physical risk indicators include: risk of falling during aerial work, mechanical failure of lifting equipment, sudden severe weather conditions, slips or falls caused by unstable ground, and fires caused by short circuits in electrical systems;
[0015] The top five risk indicators in the chemical risk category include: leakage and fire of flammable liquids, leakage of toxic gases, corrosion damage from chemicals, inhalation of harmful dust, and cross contamination caused by improper storage of chemicals;
[0016] The top five behavioral risk indicators include: operators failing to comply with safety regulations, untrained personnel operating complex equipment, distraction due to work fatigue, neglect of the use of personal protective equipment, and command errors due to communication errors;
[0017] Step S43: Analyze the top five risk indicators in each category of risk indicators to obtain the risk indicator value of each category of risk indicators;
[0018] Step S431, obtaining historical data of the top five risk indicators in each type of risk indicator;
[0019] Step S432: Obtain the historical occurrence probabilities of the top five risk indicators in each category of risk indicators through historical data, perform average processing on the historical occurrence probabilities, and obtain the historical average occurrence probability of the top five risk indicators in each category of risk indicators;
[0020] Step S433: Based on historical data, record and count the number of occurrences of the top five risk indicators in each category of risk indicators;
[0021] Step S434: based on historical data, obtain the current control measures corresponding to the top five risk indicators in each category of risk indicators, evaluate the control effectiveness of the current control measures on the top five risk indicators in each category of risk indicators, and assign control effectiveness scores to the top five risk indicators in each category of risk indicators according to the control effectiveness evaluation results;
[0022] Step S435: Based on the importance analysis result in step S42, assign the first weight to the top five risk indicators in each category of risk indicators;
[0023] Step S436, obtaining the risk indicator value of each type of risk indicator according to the historical average occurrence probability, occurrence number, control effectiveness score, and first weight of the top five risk indicators in each type of risk indicator;
[0024] The calculation formula group for obtaining the risk indicator value of each type of risk indicator is:
[0025] ;
[0026] ;
[0027] in, represents the risk indicator value of the jth risk indicator in the i-th risk indicator category; Represents the historical average probability of occurrence of the jth risk indicator in the i-th risk indicator; represents the number of occurrences of the j-th risk indicator in the i-th risk indicator; represents the control effectiveness score of the jth risk indicator in the i-th risk indicator; Represents the first weight of the j-th risk indicator in the i-th risk indicator; Represents the maximum value of the historical average occurrence probability of the j-th risk indicator in the i-th risk indicator; Represents the maximum number of occurrences of the j-th risk indicator in the i-th risk indicator; Represents the maximum value of the control effectiveness score of the j-th risk indicator in the i-th risk indicator; , , , represents the adjustment factor; represents the risk indicator value of the i-th risk indicator; k represents the number of the first weight; Represents the kth first weight in the i-th risk indicator;
[0028] Step S44, analyzing each type of risk indicator, and assigning a second weight to each type of risk indicator according to the analysis result;
[0029] Step S45, combining the risk indicator value of each type of risk indicator and the second weight to obtain a quantitative score of a potential high-risk operation scenario;
[0030] The calculation formula for obtaining the quantitative score of potential high-risk operation scenarios is:
[0031] ;
[0032] in, Represents the quantitative score of the sth potential high-risk operation scenario; Represents the second weight of the i-th risk indicator; represents the risk indicator value of the i-th risk indicator;
[0033] Step S46: obtaining quantitative scores of all potential high-risk operation scenarios, removing identical quantitative scores, retaining different quantitative scores, and generating different real-time risk level warning signals based on different quantitative scores;
[0034] Step S5: Take preventive measures according to the real-time risk level warning signal.
[0035] The embodiments of the present invention have the following technical effects:
[0036] The present invention aims to analyze the identified potential high-risk operation scenarios by means of quantitative analysis, so as to further identify and locate the sources of risk in the potential high-risk operation scenarios, improve the pertinence and efficiency of risk identification, and improve the scientificity and accuracy of risk identification. At the same time, based on the quantitative scores obtained from the quantitative analysis of potential high-risk operation scenarios, a more scientific and effective data-driven approach can be used as the standard for generating real-time risk level warning signals, that is, real-time risk level warning signals can be accurately generated, so that the generated real-time risk level warning signals can effectively prompt relevant personnel to take corresponding measures according to the risk level to avoid or reduce the impact of potential accidents, and avoid excessive intervention and waste of resources;
[0037] The present invention divides potential high-risk operation scenarios into three categories of risk indicators: physical, chemical, and behavioral, and selects the top five as key analysis objects. This fine classification method allows focusing on the factors that are most likely to cause accidents, thereby improving the accuracy of risk identification. Subsequently, these risk indicators are analyzed and ranked according to their importance, and the historical average probability of occurrence, number of occurrences, and control effectiveness score of each indicator are calculated based on historical data, and then the first weight is assigned according to the importance. This series of quantitative analyses ensures the scientificity and objectivity of the scoring system, so that the final scoring result can accurately reflect the true level of risk.
[0038] The present invention conducts in-depth mining of historical data of risk indicators, taking into account multiple dimensions such as historical average probability of occurrence, number of occurrences, effectiveness of control measures, etc., so that the quantitative scoring is no longer a simple evaluation of a single factor, but a complex calculation result that integrates multiple risk factors. This multiple analysis method can capture the multifaceted nature of risk and avoid assessment bias caused by ignoring some minor risks with significant cumulative impacts, thereby ensuring the comprehensiveness and accuracy of the final score;
[0039] The data-driven method of the present invention can reflect the changes in risks more objectively and timely than traditional qualitative or empirical judgments. By setting different levels of early warning signals based on different quantitative scores, relevant personnel can be prompted to take corresponding measures according to the risk level to avoid or mitigate the impact of potential accidents. This can effectively prevent accidents from happening and avoid the waste of resources caused by excessive intervention.
[0040] In summary, the present invention ensures the accuracy and scientificity of risk identification and early warning through fine classification, multiple analyses and quantitative scoring. This innovative method not only improves the efficiency of port operation safety management, but also provides port managers with clear operating guidelines by setting real-time risk level early warning signals, thereby playing a vital role in ensuring personnel safety, equipment integrity and smooth operations, and greatly improving the safety management level of the entire industry. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0042] Figure 1 It is a flow chart of a method for safety monitoring and intelligent risk identification of high-risk operations in ports provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only 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 belong to the scope of protection of the present invention.
[0044] Embodiment 1: Figure 1As shown, the present invention provides a method for safety monitoring and intelligent risk identification of high-risk operations in ports, comprising the following steps:
[0045] Step S1, collecting real-time environmental data and equipment operation data in the port operation area;
[0046] Environmental data collection:
[0047] Weather station monitoring data: There are multiple weather stations deployed in the port to collect meteorological parameters such as temperature, humidity, wind speed, wind direction, air pressure, rainfall, etc. These data are crucial for predicting extreme weather conditions such as typhoons and heavy rains, as they can affect the stability and safety of port equipment;
[0048] Water quality monitoring sensors: used to monitor pH, dissolved oxygen, salinity, etc. in port waters to identify changes in water quality caused by leaked chemicals, which pose a threat to port equipment and ecosystems;
[0049] Video surveillance system: uses high-definition cameras and thermal imaging cameras to collect real-time video streams to monitor personnel activities, equipment operations and abnormal behaviors in the work area;
[0050] Equipment operation data collection:
[0051] Cranes and handling equipment: Collect data including load weight, operation frequency, movement speed, position coordinates, etc. to assess the load and wear status of the equipment;
[0052] Ship data: including ship position, speed, route, draft, etc., which helps monitor the safe distance between ships and port facilities to avoid collision accidents;
[0053] Communications system: Record communications logs, including dispatch instructions, emergency calls, and communications failures, to assess communications reliability;
[0054] Step S2: pre-process the real-time environment data and equipment operation data by applying preset data cleaning rules;
[0055] Preset data cleaning rules:
[0056] Outlier detection: Use statistical methods such as Z-score and IQR to identify and handle abnormal readings outside the normal range. These outliers are caused by sensor failure or temporary interference.
[0057] Missing value processing: For missing data points, interpolation methods such as linear interpolation or machine learning-based prediction are used to fill in the missing data to maintain the continuity and integrity of the data;
[0058] Data fusion: Integrate data from different sources, for example, matching events in a video stream with corresponding equipment operation logs to better understand the context of the event;
[0059] Format standardization: ensure that all data is stored in a unified format to facilitate subsequent data analysis and model input;
[0060] Step S3: input the preprocessed real-time environmental data and equipment operation data into the pre-trained deep neural network model to identify potential high-risk operation scenarios;
[0061] First, select the model: the pre-trained deep neural network model can use any of the convolutional neural network, recurrent neural network, and Transformer models to identify potential high-risk operation scenarios;
[0062] Feature engineering is then performed to extract key features, such as vibration patterns of equipment, unsafe behavior patterns of personnel, and environmental change trends. These features are crucial for identifying high-risk scenarios.
[0063] Next comes the model training process: the model is trained on a historical dataset, including known accident cases and accident-free scenarios, to learn patterns that distinguish between safe and dangerous conditions;
[0064] Then, the necessary model validation process is carried out: the performance of the model is evaluated using cross-validation techniques to ensure the generalization ability of the model on unknown data;
[0065] Finally, real-time prediction processing is performed: the pre-processed real-time environmental data and real-time equipment operation data are input into the model, and the model outputs the risk score of each scenario in real time. A high score indicates a potential high-risk operation scenario.
[0066] Step S4, performing multiple analyses on potential high-risk operation scenarios, obtaining quantitative scores of potential high-risk operation scenarios according to the multiple analysis results, and generating different real-time risk level warning signals based on the quantitative scores of potential high-risk operation scenarios;
[0067] Step S41, obtaining all risk indicators in potential high-risk operation scenarios, using empirical methods to judge all the obtained risk indicators, and dividing all risk indicators into three categories according to the judgment results;
[0068] The three categories include physical risk indicators, chemical risk indicators, and behavioral risk indicators;
[0069] For example, all risk indicators may be classified by combining expert experience and judgment;
[0070] Among them, physical risk indicators: risks arising from the physical environment and operation process, such as unstable structure, mechanical failure, high-altitude operation, extreme weather conditions, etc.;
[0071] Chemical risk indicators: Involving improper storage, use, leakage of chemicals, and the resulting fire, explosion and poisoning risks;
[0072] Behavioral risk indicators: risks arising from human factors, including operating errors, violations of safety regulations, fatigue driving, lack of proper training, etc.
[0073] Step S42: performing importance analysis on the risk indicators included in each category of risk indicators, and ranking the risk indicators included in each category of risk indicators according to the importance analysis result, and obtaining the top five risk indicators based on the ranking result;
[0074] By evaluating the probability of occurrence, potential impact, and controllability of the risk indicators contained in each category of risk indicators, the importance of the risk indicators contained in each category of risk indicators can be determined;
[0075] The top five physical risk indicators include: risk of falling during aerial work, mechanical failure of lifting equipment, sudden severe weather conditions, slips or falls caused by unstable ground, and fires caused by short circuits in electrical systems;
[0076] The top five risk indicators in the chemical risk category include: leakage and fire of flammable liquids, leakage of toxic gases, corrosion damage from chemicals, inhalation of harmful dust, and cross contamination caused by improper storage of chemicals;
[0077] The top five behavioral risk indicators include: operators failing to comply with safety regulations, untrained personnel operating complex equipment, distraction due to work fatigue, neglect of the use of personal protective equipment, and command errors due to communication errors;
[0078] Step S43: Analyze the top five risk indicators in each category of risk indicators to obtain the risk indicator value of each category of risk indicators;
[0079] Step S431, obtaining historical data of the top five risk indicators in each type of risk indicator;
[0080] For example, the risk of falling during aerial work: collect all accident reports related to aerial work in the past five years, including the time, location, cause, and injuries of the accident;
[0081] Mechanical failures of lifting equipment: Summarize equipment maintenance records, especially those related to lifting equipment repairs, inspections and failures;
[0082] The other three physical risk indicators, as well as the other two risk indicators, also require the collection of relevant historical data;
[0083] Step S432: Obtain the historical occurrence probabilities of the top five risk indicators in each category of risk indicators through historical data, perform average processing on the historical occurrence probabilities, and obtain the historical average occurrence probability of the top five risk indicators in each category of risk indicators;
[0084] Analyze the historical data of each risk indicator, determine the total number of times each risk occurs and divide it by the total number of operations or total time period to obtain the probability of occurrence; average all historical occurrence probabilities to obtain the historical average probability of occurrence of each risk indicator;
[0085] Step S433: Based on historical data, record and count the number of occurrences of the top five risk indicators in each type of risk indicator within a specific time period;
[0086] Set a specific time period, such as the last year, and count the number of times each risk indicator appears during this period, which will reflect the recent level of risk activity;
[0087] Step S434: based on historical data, obtain the current control measures corresponding to the top five risk indicators in each category of risk indicators, evaluate the control effectiveness of the current control measures on the top five risk indicators in each category of risk indicators, and assign control effectiveness scores to the top five risk indicators in each category of risk indicators according to the control effectiveness evaluation results;
[0088] Fall risk in aerial work: Control measures include the use of safety belts, setting up safety nets, regular employee training, etc. Evaluate the effectiveness of these measures in reducing risks and give a score;
[0089] Mechanical failure of lifting equipment: Control measures include regular maintenance, use of high-quality parts, implementation of preventive maintenance plans, etc., evaluate the effectiveness of these measures and give a score;
[0090] Other risk indicators: Similarly, evaluate the control measures for other risk indicators, including equipment updates, employee training, emergency drills, etc., and give corresponding control effectiveness scores;
[0091] Step S435: Based on the importance analysis result in step S42, assign the first weight to the top five risk indicators in each category of risk indicators;
[0092] In step S42, the risk indicators have been sorted according to their importance. Now, a weight needs to be assigned to each risk indicator. The weighting method is not limited, and is preferably obtained through a weight prediction model, which reflects the relative importance of the risk indicators contained in each category of risk indicators in the overall risk assessment.
[0093] Step S436, obtaining the risk indicator value of each type of risk indicator according to the historical average occurrence probability, occurrence number, control effectiveness score, and first weight of the top five risk indicators in each type of risk indicator;
[0094] After completing the above steps, the historical average probability of occurrence, number of occurrences, control effectiveness score and the first weight of importance can be comprehensively considered and calculated using the following formula group, mainly to calculate the specific risk indicator value of each risk indicator;
[0095] The calculation formula group for obtaining the risk indicator value of each type of risk indicator is:
[0096] ;
[0097] ;
[0098] in, represents the risk indicator value of the jth risk indicator in the i-th risk indicator category; Represents the historical average probability of occurrence of the jth risk indicator in the i-th risk indicator; represents the number of occurrences of the j-th risk indicator in the i-th risk indicator; represents the control effectiveness score of the jth risk indicator in the i-th risk indicator; Represents the first weight of the j-th risk indicator in the i-th risk indicator; Represents the maximum value of the historical average occurrence probability of the j-th risk indicator in the i-th risk indicator; Represents the maximum number of occurrences of the j-th risk indicator in the i-th risk indicator; Represents the maximum value of the control effectiveness score of the j-th risk indicator in the i-th risk indicator; , , , represents the coefficient used to adjust the relative importance of each variable; represents the risk indicator value of the i-th risk indicator; k represents the number of the first weight; Represents the kth first weight in the i-th risk indicator;
[0099] Step S44, analyzing each type of risk indicator, and assigning a second weight to each type of risk indicator according to the analysis result;
[0100] In this phase, we will conduct an in-depth analysis of the physical, chemical and behavioral risk indicators and assign a second weight to each risk indicator based on the analysis results. This weight is intended to reflect the relative importance of different risk indicators in the overall risk assessment, taking into account their potential impact on personnel safety, property loss, business continuity and environmental impact;
[0101] Specifically, the analysis methods and steps are as follows:
[0102] 1. Literature review and industry standard research:
[0103] Review safety regulations, industry standards and best practices related to port operations to understand the general concerns of physical, chemical and behavioral risks in the industry;
[0104] 2. Expert consultation and risk assessment seminar:
[0105] Convene port safety management experts, equipment engineers, chemical safety experts and behavioral scientists to discuss the potential hazards of various risk indicators; conduct risk assessment workshops and invite front-line staff to participate and share the typical risks and challenges they encounter in their daily work, as well as the frequency and severity of these risks;
[0106] 3. Risk Matrix Analysis:
[0107] Use the risk matrix to assess the potential consequences and likelihood of each type of risk indicator to quantify the risk level; the risk matrix uses the severity of the consequences, from minor to catastrophic, and the likelihood of the event, from extremely unlikely to almost certain, as two axes, and puts each type of risk indicator in the matrix to visually display its risk level;
[0108] 4. Cost-Benefit Analysis:
[0109] Compare the cost of controlling each risk indicator with the benefits of risk reduction and identify the risk control measures with the best cost-effectiveness ratio; consider the long-term return on investment, including the capital expenditure of preventive measures, operating costs and the cost savings from avoiding accidents;
[0110] V. Scenario simulation and sensitivity analysis:
[0111] Use scenario simulation techniques to predict potential impacts under different risk indicators, such as financial losses, production disruptions, environmental damage, and reputational risks; conduct sensitivity analysis to test how changes in key assumptions affect the overall risk level of risk indicators;
[0112] 6. Comprehensive evaluation and weight allocation:
[0113] Based on the above analysis results, assign second weights to the physical, chemical and behavioral risk indicators respectively; the second weights should reflect the relative importance of the risks identified in the above analysis and the port management's tolerance for different types of risks;
[0114] After analyzing the above steps, the following conclusions are drawn:
[0115] Physical risk indicators are given a higher second weight because they are directly related to life safety and major property losses. Among them, the risk of falling during high-altitude operations and mechanical failures of lifting equipment are particularly emphasized due to their potential high casualty rates.
[0116] Chemical risk indicators are also given higher weights due to their long-term impact on the environment and public health crisis. Leakage and fire of flammable liquids, as well as leakage of toxic gases, are given special attention because of the widespread social concern and legal consequences they may cause.
[0117] Behavioral risk indicators, although the immediate losses caused directly may be low, their frequency and cumulative effects cannot be ignored, and are given a medium to high second weight. Operators' failure to comply with safety regulations and untrained personnel operating complex equipment are given importance due to their high preventability;
[0118] Step S45, combining the risk indicator value of each type of risk indicator and the second weight to obtain a quantitative score of a potential high-risk operation scenario;
[0119] The calculation formula for obtaining the quantitative score of potential high-risk operation scenarios is:
[0120] ;
[0121] in, Represents the quantitative score of the sth potential high-risk operation scenario, Represents the second weight of the i-th risk indicator; represents the risk indicator value of the i-th risk indicator;
[0122] Step S46: obtaining quantitative scores of all potential high-risk operation scenarios, removing identical quantitative scores, retaining different quantitative scores, and generating different real-time risk level warning signals based on different quantitative scores;
[0123] Step S5: Notify relevant personnel to take preventive measures according to different real-time risk level warning signals.
[0124] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.
[0125] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims
1. A method for safety monitoring and intelligent risk identification of high-risk operations in ports, characterized in that: The following steps are involved: Step S1, collecting real-time environmental data and equipment operation data in the port operation area; Step S2: preprocessing the real-time environment data and equipment operation data; Step S3: input the preprocessed real-time environmental data and equipment operation data into the pre-trained deep neural network model to identify potential high-risk operation scenarios; Step S4, performing multiple analyses on potential high-risk operation scenarios, obtaining quantitative scores of potential high-risk operation scenarios according to the multiple analysis results, and generating real-time risk level warning signals based on the quantitative scores of potential high-risk operation scenarios; Step S41, obtaining all risk indicators in potential high-risk operation scenarios, judging all the obtained risk indicators, and dividing all the risk indicators into three categories according to the judgment results; Step S42: performing importance analysis on the risk indicators included in each category of risk indicators, and ranking the risk indicators included in each category of risk indicators according to the importance analysis result, and obtaining the top five risk indicators based on the ranking result; Step S43: Analyze the top five risk indicators in each category of risk indicators to obtain the risk indicator value of each category of risk indicators; Step S431, obtaining historical data of the top five risk indicators in each type of risk indicator; Step S432: Obtain the historical occurrence probabilities of the top five risk indicators in each category of risk indicators through historical data, perform average processing on the historical occurrence probabilities, and obtain the historical average occurrence probability of the top five risk indicators in each category of risk indicators; Step S433: Based on historical data, record and count the number of occurrences of the top five risk indicators in each type of risk indicator; Step S434: based on historical data, obtain the current control measures corresponding to the top five risk indicators in each category of risk indicators, evaluate the control effectiveness of the current control measures on the top five risk indicators in each category of risk indicators, and assign control effectiveness scores to the top five risk indicators in each category of risk indicators according to the control effectiveness evaluation results; Step S435: Based on the importance analysis result in step S42, assign the first weight to the top five risk indicators in each category of risk indicators; Step S436, obtaining the risk indicator value of each type of risk indicator according to the historical average occurrence probability, occurrence number, control effectiveness score, and first weight of the top five risk indicators in each type of risk indicator; Step S44, analyzing each type of risk indicator, and assigning a second weight to each type of risk indicator according to the analysis result; Step S45, combining the risk indicator value of each type of risk indicator and the second weight to obtain a quantitative score of a potential high-risk operation scenario; Step S46: obtaining quantitative scores of all potential high-risk operation scenarios, removing identical quantitative scores, retaining different quantitative scores, and generating different real-time risk level warning signals based on different quantitative scores; Step S5: Take preventive measures according to the real-time risk level warning signal.
2. A method for safety monitoring and intelligent risk identification of high-risk port operations according to claim 1, characterized in that: The three categories include physical risk indicators, chemical risk indicators, and behavioral risk indicators.
3. A method for safety monitoring and intelligent risk identification of high-risk port operations according to claim 2, characterized in that: The top five physical risk indicators include: risk of falling during aerial work, mechanical failure of lifting equipment, sudden severe weather conditions, slips or falls caused by unstable ground, and fires caused by short circuits in electrical systems; The top five risk indicators in the chemical risk category include: leakage and fire of flammable liquids, leakage of toxic gases, corrosion damage from chemicals, inhalation of harmful dust, and cross contamination caused by improper storage of chemicals; The top five behavioral risk indicators include: operators failing to comply with safety regulations, untrained personnel operating complex equipment, distraction due to work fatigue, neglect of the use of personal protective equipment, and command errors due to communication errors.
4. A method for safety monitoring and intelligent risk identification of high-risk port operations according to claim 1, characterized in that: The calculation formula group for obtaining the risk indicator value of each type of risk indicator is: ; ; in, represents the risk indicator value of the jth risk indicator in the i-th risk indicator category; Represents the historical average probability of occurrence of the jth risk indicator in the i-th risk indicator; represents the number of occurrences of the j-th risk indicator in the i-th risk indicator; represents the control effectiveness score of the jth risk indicator in the i-th risk indicator; Represents the first weight of the j-th risk indicator in the i-th risk indicator; Represents the maximum value of the historical average occurrence probability of the j-th risk indicator in the i-th risk indicator; Represents the maximum number of occurrences of the j-th risk indicator in the i-th risk indicator; Represents the maximum value of the control effectiveness score of the j-th risk indicator in the i-th risk indicator; , , , represents the adjustment factor; represents the risk indicator value of the i-th risk indicator; k represents the number of the first weight; Represents the kth first weight in the i-th risk indicator.
5. A method for safety monitoring and intelligent risk identification of high-risk port operations according to claim 1, characterized in that: The calculation formula for obtaining the quantitative score of potential high-risk operation scenarios is: ; in, Represents the quantitative score of the sth potential high-risk operation scenario; Represents the second weight of the i-th risk indicator; Represents the risk indicator value of the i-th risk indicator.
Citation Information
Patent Citations
Risk monitoring method and device for road operation area and electronic equipment
CN112991747A
Power system network risk assessment method and system
CN113420992A
Quantitative evaluation system and method for reducing risks of production operators
CN114266441A
Medical safety risk assessment method and device, electronic equipment and storage medium
CN117808289A
Safety risk early warning model for hoisting operation of chemical enterprise
CN117808290A
Cited By
Port safety supervision and risk identification early warning system and method
CN119962948A
