Smelting plant personnel behavior abnormity monitoring method and system

Abstract

The invention discloses a smelting plant personnel behavior abnormity monitoring method and system, and relates to the technical field of smelting plant monitoring, a three-dimensional analysis model is constructed, an abnormity sensitivity coefficient is set in combination with a working area risk type, and a quantitative basis is provided for abnormity detection; configuring a virtual human body model, capturing behavior tracks and actions of people by utilizing a visual analysis technology, and determining basic abnormal parameters; performing deep analysis on real-time behaviors of the virtual human body model by using an analog simulation recognition library, and dynamically determining observation abnormal parameters; and based on the basic abnormal parameter, the observation abnormal parameter and the abnormal sensitivity coefficient, the abnormal degree is comprehensively calculated, and accurate alarm is realized. The problems that traditional manual monitoring is prone to omission and inaccurate are solved, the safety monitoring efficiency and reliability of the smelting plant are remarkably improved through the automatic and intelligent monitoring means, and powerful technical guarantee is provided for safety production.

Description

Technical Field

[0001] The present invention relates to the technical field of smelting plant monitoring, and in particular to a method and system for monitoring abnormal behavior of personnel in a smelting plant. Background Art

[0002] In high-risk industrial environments such as smelting plants, the safety monitoring of personnel behavior is an important part of ensuring production and personnel life safety. However, the existing monitoring methods mainly rely on manual monitoring, which has significant disadvantages and needs to be improved urgently. The traditional manual monitoring method has the following main problems: First, due to the complex environment of the smelting plant and the dynamic and changeable behavior of personnel, it is difficult for monitoring personnel to maintain a high level of attention, and it is easy to miss key abnormal behaviors due to fatigue or negligence, resulting in safety hazards that cannot be discovered in time. Secondly, the accuracy of manual monitoring varies, and it is difficult to systematically analyze and quantitatively evaluate the complex three-dimensional spatial layout and personnel behavior characteristics, resulting in insufficient recognition accuracy of abnormal behavior. In addition, manual monitoring lacks the ability to deeply analyze historical accident data and real-time behavior performance, and cannot dynamically adjust the monitoring strategy, further reducing the effectiveness and timeliness of monitoring. Finally, traditional methods are mostly based on single observation results and lack a mechanism for comprehensive evaluation of multiple parameters, resulting in a high rate of false alarms or missed alarms, which is difficult to meet the high standards of modern industrial safety monitoring. Summary of the invention

[0003] The purpose of the present invention is to provide a monitoring method and system capable of accurately analyzing abnormal behavior of personnel in a smelting plant.

[0004] The present invention discloses a method for monitoring abnormal behavior of personnel in a smelting plant, comprising: Obtain the plane design drawing of the smelting plant, and build a three-dimensional analysis model of the smelting plant based on the plane design drawing. According to the work content of different working areas of the smelting plant, set abnormal sensitivity coefficients for different position spatial points of the three-dimensional analysis model of the smelting plant; Obtain the human characteristics and behavioral characteristics of personnel in different working areas of the smelting plant, configure a preset virtual human model based on the human characteristics and behavioral characteristics, map the corresponding virtual human model to the smelting plant three-dimensional analysis model, and perform initial behavioral analysis on the performance of the virtual human model to determine basic abnormal parameters; A number of personnel behavior identification rules are constructed, each of which includes a number of behavior description keywords, and the virtual human model is driven to perform simulation performance according to a preset control method, and the key behavior fragments in the simulation performance are intercepted and marked, and a number of description keywords are configured. If the combination of description keywords meets the personnel behavior identification rules within a continuous time period, the corresponding simulation performance is identified, and the simulation performance and the personnel behavior identification are constructed in a corresponding manner to obtain a simulation recognition library; Use the simulation recognition library to conduct in-depth behavioral analysis of the virtual human model in the 3D analysis model of the smelting plant to determine the observed abnormal parameters; The degree of abnormality of the virtual human body model is determined by combining the basic abnormal parameters, observed abnormal parameters and the corresponding abnormal sensitivity coefficients, and an alarm is issued based on the degree of abnormality.

[0005] In an embodiment disclosed in the present invention, based on the work contents of different working areas of the smelting plant, a method for setting abnormal sensitivity coefficients for different position spatial points of the three-dimensional analysis model of the smelting plant includes: According to the location of different work areas, the 3D analysis model of the smelting plant is delineated into 3D work blocks, including 3D smelting work blocks, 3D casting work blocks, 3D raw material storage work blocks and 3D equipment maintenance blocks; Based on the risk type label corresponding to the mark of each three-dimensional working block, the risk performance of each risk type label is analyzed, and based on the risk performance, the risk parameters of different position spatial points in the three-dimensional equipment working block are determined, and based on the risk parameters, the abnormal sensitivity coefficient of the corresponding position spatial point is determined.

[0006] In the embodiment disclosed in the present invention, the risk type label includes: For the three-dimensional melting work area, there are risks of high temperature and liquid metal splashing; For the three-dimensional casting work area, there are risks of mechanical injury and high temperature; For the three-dimensional raw material storage work area, fire risk, explosion risk, and chemical leakage risk; For the three-dimensional equipment maintenance area, there are risks of mechanical injury and electric shock.

[0007] In an embodiment disclosed in the present invention, a method for analyzing the risk performance of each risk type label includes: Obtain historical accident data of the smelting plant, determine the risk probability and risk consequence severity parameters of different spatial points, and calculate the product of the risk probability and the risk consequence severity parameter to obtain the risk parameter; Corresponding abnormal sensitivity coefficients are set for different risk parameters.

[0008] In an embodiment disclosed in the present invention, a method for configuring a preset virtual human model based on human body characteristics and behavioral characteristics includes: Use visual analysis technology to locate factory personnel in surveillance videos and determine their identities, clothing, behavior trajectories, and body movements; Constructing a virtual human body model, including a trunk expression line, an upper limb expression line and a lower limb expression line, wherein the upper limb expression line and the lower limb expression line are movably connected to the side and the bottom of the trunk expression line respectively, an upper limb swing mapping sphere is set for the connection between the upper limb expression line and the trunk expression line, and a lower limb swing mapping sphere is set for the connection between the lower limb expression line and the trunk expression line; If the identity and attire of the determined factory personnel meet the preset standards, the position change of the virtual human model in the three-dimensional analysis model of the smelting plant is determined based on the determined behavior trajectory, and the swing change of the upper limb expression line and the lower limb expression line relative to the torso expression line is determined based on the determined body movements.

[0009] In an embodiment disclosed in the present invention, a method for performing an initial behavior analysis on the performance of a virtual human model includes: Analyze the historical accident data and simulated accident data of the smelting plant to determine the working status of the equipment, the marked behavior trajectory and marked body movements of the factory workers when each accident occurs, and analyze the marked behavior trajectory and marked body movements to determine whether there are abnormal conditions. If there are abnormal conditions, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory, and the corresponding marked body movement is recorded as an abnormal body movement; The abnormal behavior trajectory and the abnormal body movement are divided into key abnormal sections to determine the abnormal behavior trajectory comparison group and the abnormal body movement comparison group. The key abnormal section division method includes: The time when the accident occurs is taken as the end analysis time node, and the end analysis time node is moved forward by a preset time period to determine the start analysis time node, and the corresponding time period between the start analysis time node and the end analysis time node is recorded as the abnormal analysis time segment; A number of abnormal analysis time nodes are evenly set for the abnormal analysis time segment, and the equipment working status corresponding to each abnormal analysis time node is determined. Based on the equipment working status, a standard behavior trajectory set and a standard body movement set of factory workers are determined for each abnormal analysis time node; Compare the marked behavior trajectory corresponding to the abnormal analysis time node with the standard behavior trajectory set. If no matching standard behavior trajectory is found in the standard behavior trajectory set, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory. Compare the marked body movement corresponding to the abnormal analysis time node with the standard body movement set. If no corresponding standard body movement is found in the standard body movement set, the corresponding marked body movement is identified as an abnormal body movement. Perform time relationship analysis on different abnormal behavior trajectories and abnormal body movements in the abnormal analysis time segment, determine the sequence, time interval and device status corresponding to the different abnormal behavior trajectories, and combine them into an abnormal behavior trajectory comparison group; determine the sequence, time interval and device status corresponding to different abnormal body movements, and combine them into an abnormal body movement comparison group; Step S206, combining a plurality of abnormal behavior trajectory comparison groups to obtain an abnormal behavior trajectory comparison set, combining a plurality of abnormal body movement comparison groups to obtain an abnormal body movement comparison set, using the abnormal behavior trajectory comparison set and the abnormal body movement comparison set to compare the virtual human body model, respectively, calculating first matching parameters between the virtual human body model and different abnormal behavior trajectory comparison groups, and second matching parameters between the virtual human body model and different abnormal body movement comparison groups, calculating an average value of the first matching parameter and an average value of the second matching parameter, and obtaining a first average matching parameter and a second average matching parameter; Based on the first average coincident parameter and the second average coincident parameter, a basic abnormal parameter is determined.

[0010] In an embodiment disclosed in the present invention, the method for calculating the basic abnormal parameter includes: Determine the current device working state corresponding to the virtual human model, and based on the equivalence of the device working state, screen the abnormal behavior trajectory comparison group and the abnormal body movement comparison group, and compare the screened abnormal behavior trajectory and abnormal body movement comparison group with the performance of the virtual human model, and determine the trajectory comparison result and the body movement comparison result; In the trajectory comparison result, a first equivalent frequency ratio of a first equivalent number of times the abnormal behavior trajectory appears to be identical to a first recorded number of times the abnormal behavior trajectory appears in the abnormal behavior trajectory comparison group is calculated, and based on the first equivalent frequency ratio, a first matching parameter is determined; in the body movement comparison result, a second equivalent frequency ratio of a second equivalent number of times the abnormal body movement is identical to a second recorded number of times the abnormal body movement appears in the abnormal body movement comparison group is calculated; Based on the first equivalent number ratio, a first consistent parameter is determined, based on the second equivalent number ratio, a second consistent parameter is determined, a first average consistent parameter and a second average consistent parameter are calculated, and a basic abnormal parameter is determined; Among them, the expression for calculating the basic abnormal parameters is: ; in, is the basic abnormal parameter, is the weight adjustment coefficient for abnormal behavior trajectory comparison, is the weight adjustment coefficient for abnormal body movement comparison, is the first equivalent frequency ratio corresponding to the i1th abnormal behavior trajectory comparison group, is the first equivalent number impact adjustment coefficient, is the first equivalent order impact adjustment constant, is the total number of abnormal behavior trajectory comparison groups screened out, is the second equivalent frequency ratio corresponding to the i2th abnormal body movement comparison group, is the second equivalent number impact adjustment coefficient, The adjustment constant for the second equivalent order effect, is the total number of abnormal body movement comparison groups screened out.

[0011] In an embodiment disclosed in the present invention, a method for performing in-depth behavior analysis on a virtual human model in a three-dimensional analysis model of a smelting plant using a simulation recognition library includes: According to the preset time length, the current behavior characteristics of the virtual human body model are intercepted to obtain the current behavior characteristic performance segment, and the current behavior fragments in the current behavior characteristic performance segment are identified by using the simulation recognition library, and each current behavior fragment is marked with a description keyword based on the recognition result; Step S402, analyzing the proportion of the current behavior segments marked with the descriptive keywords in the current behavior performance segments, and determining the observed abnormal parameters based on the preset proportion interval to which the segment proportion belongs.

[0012] In the embodiment disclosed in the present invention, the expression for determining the abnormality degree of the virtual human model is as follows, combining the basic abnormal parameters, observed abnormal parameters and the corresponding abnormal sensitivity coefficients of the virtual human model: ; in, For abnormal degree, is the abnormal sensitivity coefficient, is the basic abnormal parameter weight adjustment coefficient, To observe the abnormal parameter weight adjustment coefficient, is the basic abnormal parameter, To observe abnormal parameters.

[0013] In the embodiment disclosed in the present invention, there is also disclosed a smelting plant personnel behavior abnormality monitoring system, comprising: The first module is used to obtain the plane design drawing of the smelting plant, and build a three-dimensional analysis model of the smelting plant based on the plane design drawing. Based on the work content of different working areas of the smelting plant, the abnormal sensitivity coefficients are set for different position spatial points of the three-dimensional analysis model of the smelting plant; The second module is used to obtain the human characteristics and behavioral characteristics of personnel in different working areas of the smelting plant, and configure a preset virtual human model based on the human characteristics and behavioral characteristics, and map the corresponding virtual human model to the three-dimensional analysis model of the smelting plant, and perform initial behavioral analysis on the performance of the virtual human model to determine the basic abnormal parameters; The third module is used to construct a number of personnel behavior identification rules, each of which includes a number of behavior description keywords, and drives the virtual human model to perform simulation performance according to a preset control method, and intercepts and marks the key behavior fragments in the simulation performance, and configures a number of description keywords. If the combination of description keywords meets the personnel behavior identification rules within a continuous time period, the corresponding simulation performance is identified, and the simulation performance and the personnel behavior identification are constructed in a corresponding manner to obtain a simulation recognition library; The fourth module is used to use the simulation recognition library to conduct in-depth behavior analysis on the virtual human model in the three-dimensional analysis model of the smelting plant to determine the observed abnormal parameters; The fifth module is used to determine the abnormality degree of the virtual human body model by combining the basic abnormal parameters of the virtual human body model, the observed abnormal parameters and the corresponding abnormal sensitivity coefficients, and to issue an alarm based on the abnormality degree.

[0014] The present invention provides a method and system for monitoring abnormal behavior of personnel in a smelting plant, which relates to the field of monitoring technology for smelting plants, constructs a three-dimensional analysis model, sets an abnormal sensitivity coefficient in combination with the risk type of the work area, and provides a quantitative basis for abnormal detection; configures a virtual human model, uses visual analysis technology to capture the trajectory and actions of personnel behavior, and determines basic abnormal parameters; uses a simulation recognition library to deeply analyze the real-time behavior of the virtual human model, and dynamically determines the observed abnormal parameters; based on the basic abnormal parameters, observed abnormal parameters and abnormal sensitivity coefficients, comprehensively calculates the degree of abnormality, and realizes accurate alarm. The present invention solves the problem of easy omissions and inaccuracies in traditional manual monitoring, and significantly improves the efficiency and reliability of safety monitoring in smelting plants through automated and intelligent monitoring methods, providing a strong technical guarantee for safe production.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A method step diagram of a method for monitoring abnormal behavior of personnel in a smelting plant disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0018] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should be the common meanings understood by the technical personnel described in the present invention.

[0019] Example:

[0020] The present invention discloses a method for monitoring abnormal behavior of personnel in a smelting plant, referring to Figure 1 ,include: Step S100, obtaining a plan design drawing of the smelting plant, and constructing a three-dimensional analysis model of the smelting plant based on the plan design drawing, and setting abnormal sensitivity coefficients for different position spatial points of the three-dimensional analysis model of the smelting plant based on the work content of different work areas of the smelting plant.

[0021] First, obtain the floor plan of the smelting plant and build a three-dimensional analysis model based on the plan. Then, according to the work content of different work areas of the smelting plant, divide the three-dimensional model into multiple work blocks, such as three-dimensional smelting work blocks, three-dimensional casting work blocks, three-dimensional raw material storage work blocks, and three-dimensional equipment maintenance blocks. For each work block, analyze its potential risk type (such as high temperature, mechanical injury, fire, etc.), and combine historical accident data to calculate the risk parameter of each location point (the product of risk probability and consequence severity). Finally, based on the risk parameter, set the abnormal sensitivity coefficient of each location point (the higher the risk, the greater the sensitivity coefficient), providing a spatial dimension risk assessment basis for subsequent abnormal monitoring of personnel behavior.

[0022] Step S200, obtain the human body characteristics and behavioral characteristics of personnel in different working areas of the smelting plant, and configure a preset virtual human body model based on the human body characteristics and behavioral characteristics, and map the corresponding virtual human body model into the three-dimensional analysis model of the smelting plant, and perform initial behavioral analysis on the performance of the virtual human body model to determine basic abnormal parameters.

[0023] First, construct several rules for identifying human behavior, each of which contains multiple behavior description keywords. Then, drive the virtual human model to perform simulation performance, intercept key behavior fragments, and mark description keywords for each fragment. If the combination of description keywords meets the identification rules, the performance is identified as human behavior. Finally, combine the simulation performance with the corresponding identification results to form a simulation recognition library, which provides an identification basis for subsequent deep behavior analysis.

[0024] Step S300, construct a number of personnel behavior identification rules, each of which includes a number of behavior description keywords, and drive the virtual human model to perform simulation performance according to a preset control method, and intercept and mark the key behavior segments in the simulation performance, and configure a number of description keywords. If the combination of description keywords meets the personnel behavior identification rules within a continuous time period, the corresponding simulation performance is identified, and the simulation performance and personnel behavior identification are constructed in a corresponding manner to obtain a simulation recognition library.

[0025] Step S400, using the simulation recognition library to perform in-depth behavior analysis on the virtual human model in the three-dimensional analysis model of the smelting plant to determine the observed abnormal parameters.

[0026] According to the preset time length, the current behavior characteristics of the virtual human model are intercepted to obtain the current behavior characteristic performance segment. The behavior segments in the current behavior characteristic performance segment are identified using the simulation recognition library, and descriptive keywords are marked for each segment. The proportion of the behavior segments marked with descriptive keywords in the entire performance segment is analyzed, and based on the preset proportion interval to which the segment proportion belongs, the observation abnormality parameter is determined, and the abnormal performance of the virtual human model is further quantified by comparing the simulation recognition library.

[0027] Step S500, combining the basic abnormal parameters of the virtual human body model, the observed abnormal parameters and the corresponding abnormal sensitivity coefficients, determines the abnormality degree of the virtual human body model, and issues an alarm based on the abnormality degree.

[0028] The abnormal degree of the virtual human model is calculated by combining the basic abnormal parameters, observed abnormal parameters and abnormal sensitivity coefficients of the corresponding position points. According to the abnormal degree, it is determined whether to trigger an alarm. Among them, the calculation formula of the abnormal degree comprehensively considers the weight adjustment coefficient of the basic abnormal parameters, the weight adjustment coefficient of the observed abnormal parameters and the abnormal sensitivity coefficient. Through this method, accurate monitoring and real-time alarm of abnormal behavior of personnel are achieved.

[0029] In an embodiment disclosed in the present invention, based on the work contents of different working areas of the smelting plant, a method for setting abnormal sensitivity coefficients for different position spatial points of the three-dimensional analysis model of the smelting plant includes: Step S101, according to the locations of different working areas, the three-dimensional analysis model of the smelting plant is delineated into three-dimensional working blocks, including a three-dimensional smelting working block, a three-dimensional casting working block, a three-dimensional raw material storage working block and a three-dimensional equipment maintenance block.

[0030] According to the location of different working areas in the smelting plant, the 3D analysis model is divided into multiple 3D working blocks, including 3D smelting working blocks, 3D casting working blocks, 3D raw material storage working blocks and 3D equipment maintenance blocks. The division is based on the work content and potential risk characteristics of each area. For example, the smelting block involves the risk of high temperature and liquid metal splashing, the casting block may have mechanical injury and high temperature risks, the raw material storage block may have fire, explosion and chemical leakage risks, and the equipment maintenance block faces mechanical injury and electric shock risks. By clarifying the functions and risk characteristics of each working block, the foundation is laid for subsequent risk analysis and abnormal sensitivity coefficient setting.

[0031] Step S102, based on the risk type label corresponding to the mark of each three-dimensional working block, and analyzing the risk performance of each risk type label, based on the risk performance, determine the risk parameters of different position space points in the three-dimensional equipment working block, and based on the risk parameters, determine the abnormal sensitivity coefficient of the corresponding position space point.

[0032] For each three-dimensional work area, mark its corresponding risk type label, such as high temperature risk, liquid metal splash risk, mechanical injury risk, fire risk, explosion risk and chemical leakage risk. Based on each risk type label, analyze its risk performance, including calculating the risk probability of different position space points (based on historical accident data) and assessing the severity of risk consequences (such as casualties and equipment damage). Multiply the risk probability by the severity of the consequences to obtain the risk parameter of each position space point. Finally, based on the risk parameter, set the abnormal sensitivity coefficient of the corresponding position space point. The higher the risk parameter, the greater the abnormal sensitivity coefficient. This method ensures that the setting of the abnormal sensitivity coefficient matches the actual risk level, and provides a scientific and quantitative basis for abnormal monitoring of personnel behavior.

[0033] In the embodiment disclosed in the present invention, the risk type label includes: For the three-dimensional smelting work area, there are risks of high temperature and liquid metal splashing; for the three-dimensional casting work area, there are risks of mechanical injury and high temperature; for the three-dimensional raw material storage work area, there are risks of fire, explosion and chemical leakage; for the three-dimensional equipment maintenance area, there are risks of mechanical injury and electric shock.

[0034] In an embodiment disclosed in the present invention, a method for analyzing the risk performance of each risk type label includes: Step S1021, obtaining historical accident data of the smelting plant, determining the risk probability and risk consequence severity parameters of different spatial points, and calculating the product of the risk probability and the risk consequence severity parameter to obtain the risk parameter.

[0035] By obtaining the historical accident data of the smelting plant, the risk probability and risk consequence severity parameters of different spatial points are determined. The risk probability is calculated based on the frequency of historical accidents, and the risk consequence severity parameter is quantified according to the degree of loss caused by the accident (such as casualties, equipment damage, etc.). The risk probability is multiplied by the risk consequence severity parameter to obtain the risk parameter of each spatial point. This process provides a specific quantitative basis for the subsequent setting of abnormal sensitivity coefficients.

[0036] Step S1022: setting corresponding abnormal sensitivity coefficients for different risk parameters.

[0037] For each location spatial point, the calculated risk parameter is used to set the corresponding abnormal sensitivity coefficient. The larger the risk parameter, the higher the potential risk of the location point, so the abnormal sensitivity coefficient will also increase accordingly. Through this correspondence, it is ensured that high-risk areas are given higher attention in personnel behavior monitoring, thereby improving safety management effects.

[0038] In an embodiment disclosed in the present invention, a method for configuring a preset virtual human model based on human body characteristics and behavioral characteristics includes: Step S201, using visual analysis technology to locate the factory personnel in the surveillance video, and determine the identity, clothing, behavior trajectory and body movements of the factory personnel.

[0039] Through visual analysis technology, factory personnel in surveillance videos can be accurately located and their identities, clothing, behavior trajectories, and body movements can be identified. Identity and clothing recognition ensure the accuracy and compliance of personnel behavior analysis, while the extraction of behavior trajectories and body movements provides basic data support for the construction of virtual human models.

[0040] Step S202, constructing a virtual human body model, including a trunk expression line, an upper limb expression line and a lower limb expression line, wherein the upper limb expression line and the lower limb expression line are movably connected to the side and the bottom of the trunk expression line respectively, an upper limb swing mapping sphere is set for the connection between the upper limb expression line and the trunk expression line, and a lower limb swing mapping sphere is set for the connection between the lower limb expression line and the trunk expression line.

[0041] A virtual human model is constructed based on the physical and behavioral characteristics of factory personnel. The model includes a trunk expression line, an upper limb expression line, and a lower limb expression line, wherein the upper limb expression line and the lower limb expression line are movably connected to the side and bottom of the trunk expression line, respectively. An upper limb swing mapping sphere is set at the connection between the upper limb expression line and the trunk expression line, and a lower limb swing mapping sphere is set at the connection between the lower limb expression line and the trunk expression line. These designs can accurately simulate human body movements and provide technical support for subsequent abnormal behavior analysis.

[0042] Step S203, if the determined identity and attire of the factory personnel meet the preset standards, the position change of the virtual human model in the three-dimensional analysis model of the smelting plant is determined based on the determined behavior trajectory, and the swing change of the upper limb expression line and the lower limb expression line relative to the torso expression line is determined based on the determined body movement.

[0043] If the identity and clothing of the factory personnel meet the preset standards, the position change of the virtual human model in the smelting plant three-dimensional analysis model is determined based on their behavior trajectory. At the same time, based on their body movements, the swing changes of the upper limb expression line and the lower limb expression line relative to the torso expression line are determined. This process maps the behavior of real people to the virtual human model, providing dynamic data support for subsequent behavior anomaly detection and risk warning.

[0044] In an embodiment disclosed in the present invention, a method for performing an initial behavior analysis on the performance of a virtual human model includes: Step S204, analyze the historical accident data and simulated accident data of the smelting plant to determine the working status of the equipment, the marked behavior trajectories and marked body movements of the factory workers when each accident occurs, and analyze the marked behavior trajectories and marked body movements to determine whether there are any abnormal situations. If there are any abnormal situations, the corresponding marked behavior trajectories are identified as abnormal behavior trajectories, and the corresponding marked body movements are recorded as abnormal body movements.

[0045] The historical accident data and simulated accident data of the smelting plant are analyzed to determine the working status of the equipment, the behavior trajectory (marked behavior trajectory) and body movements (marked body movements) of the factory workers when each accident occurs. By analyzing the marked behavior trajectory and marked body movements, it is determined whether there is an abnormal situation. If there is an abnormal situation, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory, and the corresponding marked body movement is recorded as an abnormal body movement.

[0046] Step S205, dividing the abnormal behavior trajectory and the abnormal body movement into key abnormal sections, and determining the abnormal behavior trajectory comparison group and the abnormal body movement comparison group. The method of dividing the key abnormal sections includes:

[0047] The abnormal behavior trajectory and abnormal body movement are divided into key abnormal sections to generate abnormal behavior trajectory comparison groups and abnormal body movement comparison groups. The specific method includes the following steps: Step S2051, taking the time when the accident occurs as the end analysis time node, and moving the end analysis time node forward by a preset time period, determining the start analysis time node, and recording the corresponding time period between the start analysis time node and the end analysis time node as the abnormal analysis time segment.

[0048] The time when the accident occurred is taken as the end analysis time node, and the end analysis time node is moved forward by a preset time period (e.g. 5 minutes before the accident occurred) to determine the start analysis time node. The time period between the start analysis time node and the end analysis time node is recorded as the abnormal analysis time segment.

[0049] Step S2052, a number of abnormal analysis time nodes are evenly set for the abnormal analysis time segment, and the equipment working status corresponding to each abnormal analysis time node is determined, and based on the equipment working status, the standard behavior trajectory set and standard body movement set of the factory workers are determined for each abnormal analysis time node.

[0050] Several abnormal analysis time nodes are evenly set within the abnormal analysis time segment, and the equipment working status corresponding to each time node is determined. Based on the equipment working status, the standard behavior trajectory set and standard body movement set of factory workers at each time node are determined.

[0051] Step S2053, compare the marked behavior trajectory corresponding to the abnormal analysis time node with the standard behavior trajectory set. If no matching standard behavior trajectory is found in the standard behavior trajectory set, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory. Compare the marked body movements corresponding to the abnormal analysis time node with the standard body movement set. If no corresponding standard body movement is found in the standard body movement set, the corresponding marked body movement is identified as an abnormal body movement.

[0052] The marked behavior trajectory of each abnormal analysis time node is compared with the standard behavior trajectory set. If no matching standard behavior trajectory is found in the standard behavior trajectory set, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory. Similarly, the marked body movement of each abnormal analysis time node is compared with the standard body movement set. If no matching standard body movement is found, the corresponding marked body movement is identified as an abnormal body movement.

[0053] Step S2054, perform time relationship analysis on different abnormal behavior trajectories and abnormal body movements in the abnormal analysis time segment, determine the sequence, time intervals and corresponding device states of different abnormal behavior trajectories, and combine them into an abnormal behavior trajectory comparison group, determine the sequence, time intervals and corresponding device states of different abnormal body movements, and combine them into an abnormal body movement comparison group.

[0054] Perform temporal relationship analysis on different abnormal behavior trajectories and abnormal body movements in the abnormal analysis time segment, including determining the sequence, time interval, and corresponding device status of the abnormal behavior trajectories, and combining them into abnormal behavior trajectory comparison groups. Perform similar analysis on abnormal body movements to generate abnormal body movement comparison groups.

[0055] Step S206, combining several abnormal behavior trajectory comparison groups to obtain an abnormal behavior trajectory comparison set, combining several abnormal body movement comparison groups to obtain an abnormal body movement comparison set, using the abnormal behavior trajectory comparison set and the abnormal body movement comparison set to compare the virtual human body model, respectively, calculating the first matching parameter of the virtual human body model and the different abnormal behavior trajectory comparison groups, as well as the second matching parameter of the virtual human body model and the different abnormal body movement comparison groups, calculating the average value of the first matching parameter and the average value of the second matching parameter, and obtaining the first average matching parameter and the second average matching parameter.

[0056] Combine multiple abnormal behavior trajectory comparison groups into an abnormal behavior trajectory comparison set, and combine multiple abnormal body movement comparison groups into an abnormal body movement comparison set. Use the comparison set to compare the virtual human body model and calculate the following parameters: The first matching parameter: the matching degree between the virtual human model and the comparison groups of different abnormal behavior trajectories.

[0057] The second matching parameter: the matching degree between the virtual human model and the comparison groups of different abnormal body movements.

[0058] The average values ​​of all the first matching parameters are calculated to obtain the first average matching parameter; the average values ​​of all the second matching parameters are calculated to obtain the second average matching parameter.

[0059] Step S207, determining a basic abnormal parameter based on the first average coincident parameter and the second average coincident parameter.

[0060] Based on the first average matching parameter and the second average matching parameter, the basic abnormal parameters of the virtual human model are determined. The basic abnormal parameters are used to quantify the matching degree between the virtual human model and the abnormal behavior trajectory and body movements, providing a basis for subsequent risk warning and safety management.

[0061] In an embodiment disclosed in the present invention, the method for calculating the basic abnormal parameter includes: Step S2061, determine the current device working state corresponding to the virtual human body model, and based on the equivalence of the device working state, screen the abnormal behavior trajectory comparison group and the abnormal body movement comparison group, and compare the screened abnormal behavior trajectory and abnormal body movement comparison group with the performance of the virtual human body model respectively to determine the trajectory comparison result and the body movement comparison result.

[0062] Step S2062, in the trajectory comparison result, calculate the first equivalent number ratio of the first equivalent number of times the abnormal behavior trajectory appears to the first recorded number of times the abnormal behavior trajectory appears in the abnormal behavior trajectory comparison group, and based on the first equivalent number ratio, determine the first matching parameter, and in the body movement comparison result, calculate the second equivalent number ratio of the second equivalent number of times the abnormal body movement appears to the second recorded number of times the abnormal body movement appears in the abnormal body movement comparison group.

[0063] Step 2063, based on the first equivalent frequency ratio, determine the first consistent parameter, based on the second equivalent frequency ratio, determine the second consistent parameter, calculate the first average consistent parameter and the second average consistent parameter, and determine the basic abnormal parameter.

[0064] Among them, the expression for calculating the basic abnormal parameters is: .

[0065] in, is the basic abnormal parameter, is the weight adjustment coefficient for abnormal behavior trajectory comparison, is the weight adjustment coefficient for abnormal body movement comparison, is the first equivalent frequency ratio corresponding to the i1th abnormal behavior trajectory comparison group, is the first equivalent number impact adjustment coefficient, is the first equivalent order impact adjustment constant, is the total number of abnormal behavior trajectory comparison groups screened out, is the second equivalent frequency ratio corresponding to the i2th abnormal body movement comparison group, is the second equivalent number impact adjustment coefficient, The adjustment constant for the second equivalent order effect, is the total number of abnormal body movement comparison groups screened out.

[0066] In an embodiment disclosed in the present invention, a method for performing in-depth behavior analysis on a virtual human model in a three-dimensional analysis model of a smelting plant using a simulation recognition library includes: Step S401, according to a preset time length, the current behavior characteristics of the virtual human body model are intercepted to obtain the current behavior characteristic performance segment, and the current behavior fragments in the current behavior characteristic performance segment are identified by using a simulation recognition library, and each current behavior fragment is marked with descriptive keywords based on the recognition result.

[0067] Step S402, analyzing the proportion of the current behavior segments marked with the descriptive keywords in the current behavior performance segments, and determining the observed abnormal parameters based on the preset proportion interval to which the segment proportion belongs.

[0068] In the embodiment disclosed in the present invention, the expression for determining the abnormality degree of the virtual human model is as follows, combining the basic abnormal parameters, observed abnormal parameters and the corresponding abnormal sensitivity coefficients of the virtual human model: .

[0069] in, For abnormal degree, is the abnormal sensitivity coefficient, is the basic abnormal parameter weight adjustment coefficient, To observe the abnormal parameter weight adjustment coefficient, is the basic abnormal parameter, To observe abnormal parameters.

[0070] In the embodiment disclosed in the present invention, there is also disclosed a smelting plant personnel behavior abnormality monitoring system, comprising: The first module is used to obtain the plan design drawing of the smelting plant, and build a three-dimensional analysis model of the smelting plant based on the plan design drawing. Based on the work content of different work areas of the smelting plant, abnormal sensitivity coefficients are set for different position spatial points of the three-dimensional analysis model of the smelting plant.

[0071] The second module is used to obtain the human and behavioral characteristics of personnel in different working areas of the smelting plant, and configure a preset virtual human model based on the human and behavioral characteristics, and map the corresponding virtual human model to the three-dimensional analysis model of the smelting plant, and perform initial behavioral analysis on the performance of the virtual human model to determine basic abnormal parameters.

[0072] The third module is used to construct a number of personnel behavior identification rules, each of which includes a number of behavior description keywords, and drives the virtual human model to perform simulation performance according to the preset control method, and intercepts and marks the key behavior fragments in the simulation performance, and configures a number of description keywords. If the combination of description keywords meets the personnel behavior identification rules within a continuous time period, the corresponding simulation performance is identified, and the simulation performance and personnel behavior identification are constructed in a corresponding manner to obtain a simulation recognition library.

[0073] The fourth module is used to use the simulation recognition library to conduct in-depth behavioral analysis of the virtual human model in the three-dimensional analysis model of the smelting plant to determine the observed abnormal parameters.

[0074] The fifth module is used to determine the abnormality degree of the virtual human body model by combining the basic abnormal parameters of the virtual human body model, the observed abnormal parameters and the corresponding abnormal sensitivity coefficients, and to issue an alarm based on the abnormality degree.

[0075] The present invention provides a method and system for monitoring abnormal behavior of personnel in a smelting plant, which relates to the field of monitoring technology for smelting plants, constructs a three-dimensional analysis model, sets an abnormal sensitivity coefficient in combination with the risk type of the work area, and provides a quantitative basis for abnormal detection; configures a virtual human model, uses visual analysis technology to capture the trajectory and actions of personnel behavior, and determines basic abnormal parameters; uses a simulation recognition library to deeply analyze the real-time behavior of the virtual human model, and dynamically determines the observed abnormal parameters; based on the basic abnormal parameters, observed abnormal parameters and abnormal sensitivity coefficients, comprehensively calculates the degree of abnormality, and realizes accurate alarm. The present invention solves the problem of easy omissions and inaccuracies in traditional manual monitoring, and significantly improves the efficiency and reliability of safety monitoring in smelting plants through automated and intelligent monitoring methods, providing a strong technical guarantee for safe production.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for monitoring abnormal behavior of personnel in a smelting plant, characterized in that: include: Obtain the plane design drawing of the smelting plant, and build a three-dimensional analysis model of the smelting plant based on the plane design drawing. According to the work content of different working areas of the smelting plant, set abnormal sensitivity coefficients for different position spatial points of the three-dimensional analysis model of the smelting plant; Obtain the human characteristics and behavioral characteristics of personnel in different working areas of the smelting plant, configure a preset virtual human model based on the human characteristics and behavioral characteristics, map the corresponding virtual human model to the smelting plant three-dimensional analysis model, and perform initial behavioral analysis on the performance of the virtual human model to determine basic abnormal parameters; A number of personnel behavior identification rules are constructed, each of which includes a number of behavior description keywords, and the virtual human model is driven to perform simulation performance according to a preset control method, and the key behavior fragments in the simulation performance are intercepted and marked, and a number of description keywords are configured. If the combination of description keywords meets the personnel behavior identification rules within a continuous time period, the corresponding simulation performance is identified, and the simulation performance and the personnel behavior identification are constructed in a corresponding manner to obtain a simulation recognition library; Use the simulation recognition library to conduct in-depth behavioral analysis of the virtual human model in the 3D analysis model of the smelting plant to determine the observed abnormal parameters; The degree of abnormality of the virtual human body model is determined by combining the basic abnormal parameters, observed abnormal parameters and the corresponding abnormal sensitivity coefficients, and an alarm is issued based on the degree of abnormality.

2. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 1, characterized in that: Based on the work contents of different work areas of the smelting plant, the method of setting abnormal sensitivity coefficients for different position spatial points of the 3D analysis model of the smelting plant includes: According to the location of different work areas, the 3D analysis model of the smelting plant is delineated into 3D work blocks, including 3D smelting work blocks, 3D casting work blocks, 3D raw material storage work blocks and 3D equipment maintenance blocks; Based on the risk type label corresponding to the mark of each three-dimensional working block, the risk performance of each risk type label is analyzed, and based on the risk performance, the risk parameters of different position spatial points in the three-dimensional equipment working block are determined, and based on the risk parameters, the abnormal sensitivity coefficient of the corresponding position spatial point is determined.

3. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 2, characterized in that: Risk type labels include: For the three-dimensional melting work area, there are risks of high temperature and liquid metal splashing; For the three-dimensional casting work area, there are risks of mechanical injury and high temperature; For the three-dimensional raw material storage work area, fire risk, explosion risk, and chemical leakage risk; For the three-dimensional equipment maintenance area, there are risks of mechanical injury and electric shock.

4. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 2, characterized in that: The method for analyzing the risk performance of each risk type label includes: Obtain historical accident data of the smelting plant, determine the risk probability and risk consequence severity parameters of different spatial points, and calculate the product of the risk probability and the risk consequence severity parameter to obtain the risk parameter; Corresponding abnormal sensitivity coefficients are set for different risk parameters.

5. The method for monitoring abnormal behavior of personnel in a smelting plant according to claim 1, characterized in that: The method for configuring a preset virtual human model based on human body characteristics and behavioral characteristics includes: Use visual analysis technology to locate factory personnel in surveillance videos and determine their identities, clothing, behavior trajectories, and body movements; Constructing a virtual human body model, including a trunk expression line, an upper limb expression line and a lower limb expression line, wherein the upper limb expression line and the lower limb expression line are movably connected to the side and the bottom of the trunk expression line respectively, an upper limb swing mapping sphere is set for the connection between the upper limb expression line and the trunk expression line, and a lower limb swing mapping sphere is set for the connection between the lower limb expression line and the trunk expression line; If the identity and attire of the determined factory personnel meet the preset standards, the position change of the virtual human model in the three-dimensional analysis model of the smelting plant is determined based on the determined behavior trajectory, and the swing change of the upper limb expression line and the lower limb expression line relative to the torso expression line is determined based on the determined body movements.

6. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 5, characterized in that: Methods for conducting initial behavioral analysis of the virtual human model's performance include: Analyze the historical accident data and simulated accident data of the smelting plant to determine the working status of the equipment, the marked behavior trajectory and marked body movements of the factory workers when each accident occurs, and analyze the marked behavior trajectory and marked body movements to determine whether there are abnormal conditions. If there are abnormal conditions, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory, and the corresponding marked body movement is recorded as an abnormal body movement; The abnormal behavior trajectory and the abnormal body movement are divided into key abnormal sections to determine the abnormal behavior trajectory comparison group and the abnormal body movement comparison group. The key abnormal section division method includes: The time when the accident occurs is taken as the end analysis time node, and the end analysis time node is moved forward by a preset time period to determine the start analysis time node, and the corresponding time period between the start analysis time node and the end analysis time node is recorded as the abnormal analysis time segment; A number of abnormal analysis time nodes are evenly set for the abnormal analysis time segment, and the equipment working status corresponding to each abnormal analysis time node is determined. Based on the equipment working status, a standard behavior trajectory set and a standard body movement set of factory workers are determined for each abnormal analysis time node; Compare the marked behavior trajectory corresponding to the abnormal analysis time node with the standard behavior trajectory set. If no matching standard behavior trajectory is found in the standard behavior trajectory set, the corresponding marked behavior trajectory is identified as an abnormal behavior trajectory. Compare the marked body movement corresponding to the abnormal analysis time node with the standard body movement set. If no corresponding standard body movement is found in the standard body movement set, the corresponding marked body movement is identified as an abnormal body movement. Perform time relationship analysis on different abnormal behavior trajectories and abnormal body movements in the abnormal analysis time segment, determine the sequence, time interval and device status corresponding to the different abnormal behavior trajectories, and combine them into an abnormal behavior trajectory comparison group; determine the sequence, time interval and device status corresponding to different abnormal body movements, and combine them into an abnormal body movement comparison group; Combining several abnormal behavior trajectory comparison groups to obtain an abnormal behavior trajectory comparison set, combining several abnormal body movement comparison groups to obtain an abnormal body movement comparison set, using the abnormal behavior trajectory comparison set and the abnormal body movement comparison set to compare the virtual human body model, respectively, calculating first matching parameters between the virtual human body model and different abnormal behavior trajectory comparison groups, and second matching parameters between the virtual human body model and different abnormal body movement comparison groups, calculating an average value of the first matching parameter and an average value of the second matching parameter, and obtaining a first average matching parameter and a second average matching parameter; Based on the first average coincident parameter and the second average coincident parameter, a basic abnormal parameter is determined.

7. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 6, characterized in that: Methods for calculating basic anomaly parameters include: Determine the current device working state corresponding to the virtual human model, and based on the equivalence of the device working state, screen the abnormal behavior trajectory comparison group and the abnormal body movement comparison group, and compare the screened abnormal behavior trajectory and abnormal body movement comparison group with the performance of the virtual human model, and determine the trajectory comparison result and the body movement comparison result; In the trajectory comparison result, a first equivalent frequency ratio of a first equivalent number of times the abnormal behavior trajectory appears to be identical to a first recorded number of times the abnormal behavior trajectory appears in the abnormal behavior trajectory comparison group is calculated, and based on the first equivalent frequency ratio, a first matching parameter is determined; in the body movement comparison result, a second equivalent frequency ratio of a second equivalent number of times the abnormal body movement is identical to a second recorded number of times the abnormal body movement appears in the abnormal body movement comparison group is calculated; Based on the first equivalent number ratio, a first consistent parameter is determined, based on the second equivalent number ratio, a second consistent parameter is determined, a first average consistent parameter and a second average consistent parameter are calculated, and a basic abnormal parameter is determined; Among them, the expression for calculating the basic abnormal parameters is: ； in, is the basic abnormal parameter, is the weight adjustment coefficient for abnormal behavior trajectory comparison, is the weight adjustment coefficient for abnormal body movement comparison, is the first equivalent frequency ratio corresponding to the i1th abnormal behavior trajectory comparison group, is the first equivalent number impact adjustment coefficient, is the first equivalent order impact adjustment constant, is the total number of abnormal behavior trajectory comparison groups screened out, is the second equivalent frequency ratio corresponding to the i2th abnormal body movement comparison group, is the second equivalent number impact adjustment coefficient, The adjustment constant for the second equivalent order effect, is the total number of abnormal body movement comparison groups screened out.

8. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 1, characterized in that: The method of using the simulation recognition library to perform in-depth behavior analysis on the virtual human model in the three-dimensional analysis model of the smelting plant includes: According to the preset time length, the current behavior characteristics of the virtual human body model are intercepted to obtain the current behavior characteristic performance segment, and the current behavior fragments in the current behavior characteristic performance segment are identified by using the simulation recognition library, and each current behavior fragment is marked with a description keyword based on the recognition result; Analyze the proportion of current behavior segments marked with descriptive keywords in the current behavior performance segments, and determine the observation abnormal parameters based on the preset proportion interval to which the segment proportion belongs.

9. A method for monitoring abnormal behavior of personnel in a smelting plant according to claim 1, characterized in that: Combining the basic abnormal parameters, observed abnormal parameters and corresponding abnormal sensitivity coefficients of the virtual human body model, the expression for determining the abnormal degree of the virtual human body model is: ； in, For abnormal degree, is the abnormal sensitivity coefficient, is the basic abnormal parameter weight adjustment coefficient, To observe the abnormal parameter weight adjustment coefficient, is the basic abnormal parameter, To observe abnormal parameters.

10. A smelting plant personnel behavior abnormal monitoring system, characterized in that: include: The first module is used to obtain the plane design drawing of the smelting plant, and build a three-dimensional analysis model of the smelting plant based on the plane design drawing. Based on the work content of different working areas of the smelting plant, the abnormal sensitivity coefficients are set for different position spatial points of the three-dimensional analysis model of the smelting plant; The second module is used to obtain the human characteristics and behavioral characteristics of personnel in different working areas of the smelting plant, and configure a preset virtual human model based on the human characteristics and behavioral characteristics, and map the corresponding virtual human model to the three-dimensional analysis model of the smelting plant, and perform initial behavioral analysis on the performance of the virtual human model to determine the basic abnormal parameters; The third module is used to construct a number of personnel behavior identification rules, each of which includes a number of behavior description keywords, and drives the virtual human model to perform simulation performance according to a preset control method, and intercepts and marks the key behavior fragments in the simulation performance, and configures a number of description keywords. If the combination of description keywords meets the personnel behavior identification rules within a continuous time period, the corresponding simulation performance is identified, and the simulation performance and the personnel behavior identification are constructed in a corresponding manner to obtain a simulation recognition library; The fourth module is used to use the simulation recognition library to conduct in-depth behavior analysis on the virtual human model in the three-dimensional analysis model of the smelting plant to determine the observed abnormal parameters; The fifth module is used to determine the abnormality degree of the virtual human body model by combining the basic abnormal parameters of the virtual human body model, the observed abnormal parameters and the corresponding abnormal sensitivity coefficients, and to issue an alarm based on the abnormality degree.

Images