CN111861198B - Extraction and analysis method for mine team worker unsafe behavior propagation process - Google Patents
Extraction and analysis method for mine team worker unsafe behavior propagation process Download PDFInfo
- Publication number
- CN111861198B CN111861198B CN202010691231.7A CN202010691231A CN111861198B CN 111861198 B CN111861198 B CN 111861198B CN 202010691231 A CN202010691231 A CN 202010691231A CN 111861198 B CN111861198 B CN 111861198B
- Authority
- CN
- China
- Prior art keywords
- unsafe
- worker
- workers
- behavior
- behaviors
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for extracting and analyzing unsafe behavior propagation processes of mine team workers, which comprises a technique for realizing the occurrence propagation warning of unsafe behavior groups of the mine team workers based on an Agent modeling and simulation method (AMBS), and comprises the following steps: 1. establishing an information processing process model of the occurrence and propagation of unsafe behaviors of workers; 2. extracting and describing system elements such as a main body, a structure, an internal communication connection mode and the like of the team group system, and constructing an unsafe behavior propagation process conceptual model; 3. designing a main Agent model of a worker; 4. a worker unsafe behavior propagation decision mechanism design based on a cognitive process; 5. and (5) simulation implementation. On the basis of fully describing system elements in the team operation process, the dynamic propagation evolution process of unsafe behaviors of workers is dynamically presented, so that not only is the warning effect on the safe production process of the workers achieved, but also a basis is provided for safety management decisions.
Description
Technical Field
The invention relates to the field of computer software, in particular to an extraction and analysis method for a mine team worker unsafe behavior propagation process.
Background
Statistics data and related researches aiming at the coal mine safety production accident cause show that unsafe behavior in the working process of workers is a main factor for causing coal mine accidents. As a group operation, the unsafe behavior propagation among workers in the team further expands the sources of the unsafe behaviors, increases the occurrence probability of the unsafe behaviors and enhances the vitality of the unsafe behaviors. Therefore, research is necessary for the propagation process of unsafe behaviors of team workers, the problem of macroscopic phenomenon of unsafe behavior propagation is described and revealed from the overall view of the system, the propagation of unsafe behaviors is blocked, the propagation effect of the safe behaviors is improved, the generation of unsafe behaviors is reduced, and therefore the safety production risk and hidden danger are reduced, and the probability of occurrence of safety accidents is reduced.
The development process of the system and each element in the system is a process from low level to high level and from micro level to macro level, so that aiming at a coal mine production system, it is necessary to explore the unsafe behavior propagation of coal mine workers from a micro level, fully attach importance to and analyze the interaction relationship between workers and between individuals and the environment, which is the basis and condition that unsafe behavior is propagated, and the unsafe propagation process is more in accordance with the emerging rule of the evolution development of the system. From the microscopic view of individuals of workers, the macroscopic phenomenon problem of unsafe behavior propagation is described and revealed from the integral emerging view of a system by extracting and describing the interaction relationship among individuals of the microscopic workers and the interaction relationship between individuals and the environment, but the prior art does not have a corresponding complete data analysis method for extracting and analyzing the behaviors of workers in complex environments such as mines, and therefore, the technical problem is needed to be solved by the technicians in the field.
Disclosure of Invention
The invention aims at least solving the technical problems in the prior art, and particularly creatively provides an extraction and analysis method for the unsafe behavior propagation process of mine team workers.
In order to achieve the above object, the present invention provides a method for extracting and analyzing the propagation process of unsafe behavior of workers in a mine team, comprising the steps of:
s1, acquiring unsafe behavior data of workers in a mine, and establishing an information processing process model of the emerging and spread unsafe behavior of the workers;
s2, after training through a processing process model, building a team group system for unsafe behaviors of workers, and extracting and describing elements of a main body, a structure and an internal communication mode of the team group system;
s3, after extraction and depiction are completed, constructing an unsafe behavior propagation process conceptual model;
s4, after the process concept model is established, processing and designing the main Agent model of the worker;
s5, establishing a worker unsafe behavior propagation decision mechanism according to the formed unsafe behavior propagation process conceptual model and the worker main body Agent model;
s6, performing verification operation according to the established unsafe behavior propagation decision mechanism of the worker, and correcting according to dynamic propagation evolution of the unsafe behavior of the worker.
Preferably, the S1 includes:
s1-1, collecting unsafe behaviors of workers through mine image acquisition equipment, receiving actual working scene information in a mine through sensing the external environment of the mine, and defining an unsafe behavior model in the actual working scene information of the mine;
s1-2, extracting unsafe behaviors of workers through mine image acquisition equipment according to an unsafe behavior model, and performing information mapping on mine actual working scene information and the extracted unsafe behaviors of the workers at corresponding time points;
s1-3, cognizing and processing the unsafe behaviors of the workers according to the mapped unsafe behavior information of the workers, completing the cognizing and processing process according to understanding cognition of the unsafe behaviors of the workers in machine learning and the mapped unsafe behavior information of the workers,
s1-4, after collecting, copying and evolving unsafe behaviors of workers, properly selecting the unsafe behaviors of the workers and debugging a unsafe behavior data set of the workers; thereby forming an information processing model.
Preferably, the S2 includes:
s2-1, after training the information processing process model formed in the S1, refining unsafe behaviors of workers into executive behaviors of a team leader and executive behaviors of the workers;
s2-2, the executive actions of the group leader are formed into an executive lead unsafe action library, a task unsafe action library, a supervision unsafe action library and a coordination control unsafe action library;
s2-3, the worker execution behaviors are formed into a worker execution business unsafe behavior library, an operation technology unsafe behavior library and an demonstration operation unsafe behavior library;
preferably, the S3 includes:
s3-1, determining set communication rules and interaction connection situations of interaction between a worker main body Agent and external environment and interaction between other worker main body agents in the mine operation process;
s3-2, establishing a worker main body Agent behavior rule and a knowledge base;
s3-3, constructing an unsafe behavior propagation process conceptual model, defining unsafe behaviors propagated by unsafe behaviors of workers, describing differentiation in executive behaviors of group workers in mines and the executive behaviors of the workers, and defining concepts of the differentiated and homogenized executive behaviors of the group workers and the executive behaviors of the workers.
Preferably, the S4 includes:
s4-1, defining rules and a knowledge base for the behaviors of the main body agents of the workers, and then generating intrinsic factors for the intrinsic properties of the behaviors of the main body agents of the workers, namely unsafe behaviors of the workers, and psychological factors affecting decision-making of the unsafe behaviors of the workers, wherein the psychological factors comprise psychological processes and individuality factors. From the initiative of behaviors, the individuality of workers containing personality traits, personality literacy and other contents is divided into an initiative type and a passive type; the safety behavior willingness is used as an intermediate variable to reflect the psychological factor data of the main worker body group and the psychological factor data of the main worker body individual, which influence the unsafe behavior decision of the worker, so that the classification degree of the unsafe behavior of the worker is fed back and the degree of significance is extracted;
s4-2, importing the external attribute of the main Agent of the worker into the information factors of the role in the work of the mine, the situation in the mine and the occupation in the work of the worker, wherein the attribute of the main Agent of the worker is the attribute of the worker in the organization where the worker is taken as a social person, the social attribute of the main Agent of the worker comprises a job level and a compensation level, and in a production team of the mine, the job level of the worker is positively correlated with the risk level of unsafe behavior along with the rise of the job, and the compensation level is positively correlated with the job level;
s4-3, describing behavior knowledge standardization of workers in the working process by using a worker unsafe behavior quantification function, wherein the worker main Agent knowledge attribute is a characteristic of the workers, is an important index for the workers to examine unsafe behavior transmission, is an information resource for information and energy exchange between the workers and the external environment;
s4-4, the objective environment of the worker main body Agent worker in the working process comprises three aspects of a working environment, an organization environment and a system environment; the working environment has normative or non-normative enterprise facts which have guiding influence on the underground behaviors of workers, comprises working responsibilities, normative, superior indication and interaction relations among workers, and also comprises a working physical environment which is a physical environment condition directly acting on the working behaviors, such as the size, illumination, ventilation, noise and the like of an underground working site; the organization environment mainly shows the contents of the organization structure design, the salary level system, the incentive mechanism, the employee employment mechanism and the like of the enterprise; the system environment is a series of files with compendial meaning formulated around the development of enterprises and corresponding mission, and relevant national regulation system, including safety production management system, enterprise safety culture and operation regulations, and also including shaping and appeal of staff by enterprise manager.
Preferably, the step S5 includes:
s5-1, for a worker unsafe behavior decision mechanism: in the action decision process, more of the workers consider the risks of self benefit and avoidance brought by the finally selected actions, and the action decision process of the workers is described by applying a prospect theory based on the cognitive information processing process of the workers, wherein the theory divides the decision process of the risks into two processes, namely editing and evaluating. In the editing stage of risk evaluation, the individual members of workers acquire and process information by means of reference points, and in the evaluation stage, the information is judged by mainly relying on two methods, namely a cost function and a subjective probability weight function;
s5-2, establishing a worker unsafe behavior cost function: in the mine operation process, imitation or replication of worker's unsafe behavior is carried out by taking the unsafe behavior of the worker as a decision reference point and setting a cost function taking the unsafe behavior of the worker as a reference point.
S5-3, establishing a worker unsafe behavior weight function: and designing a weight function of the worker behavior decision according to the foreground theoretical decision model, and representing probability measurement of each expected result and the change influence of each expected result on the total utility.
S5-4, establishing an expected utility function of unsafe behaviors of workers: the preference of workers with different personal psychology for expected utility is different, so that the preference coefficient of the individual needs to be designed; wherein, for the workers with active personality and psychology, the preference of the worker for the salary grade and the job grade is larger than the influence of the demonstration effect of the worker's behavior, and for the workers with passive personality and psychology, the preference of the salary grade and the job grade is smaller than the influence of the demonstration effect of the worker's behavior in the working process. In addition, the judgment of the occurrence probability of the expected utility result by workers is influenced by situation factors, and the expected utility and the occurrence probability function thereof are determined according to the content and influence of the situation factors of the coal mine enterprises and the marginal incremental relation effect of expected benefits and grades. Accordingly, an expected utility function for a specific worker to evaluate the value of the expected target is set. When the effectiveness of the worker operation behavior is smaller than the behavior effectiveness achieved by the referenced worker, the worker operation behavior is regarded as loss, and a corresponding loss effectiveness function is obtained;
s5-5, transmitting decision function through unsafe behaviors of workers: the method comprises the steps that a worker unsafe behavior propagation decision mechanism is obtained through S5-1 to S5-4, and when the absolute value of the expected utility of the extracted worker unsafe behavior is larger than the absolute value of the loss utility of the worker unsafe behavior, worker unsafe behavior data prestored by a mine image acquisition device are judged to acquire the worker unsafe behavior data in real time; if the non-matching is the same behavior, the mine operation is continued, otherwise, the unsafe behavior is refused to be adopted.
Preferably, the step S6 includes:
s6-1, constructing a worker unsafe behavior main body behavior model, a worker unsafe behavior environment model and a worker unsafe behavior interaction model according to pre-stored working behavior data of a mine middle team leader execution behavior and a worker execution behavior and real-time collected working behavior data;
s6-2, formulating a simulation technical scheme of dynamic change target variables, team scales, intelligent agent parameter values and result output modes of unsafe behaviors of workers;
s6-3, the worker unsafe behavior adopts a worker unsafe behavior propagation decision mechanism and model parameters which are designed in the earlier stage; the unsafe behavior environment model of the worker is mainly based on information sources of the worker operation process in the mine, and the interaction model is designed to be a set communication rule and an interaction connection situation of interaction between the main Agent of the worker and the external environment and other agents;
s6-4, continuously collecting and updating a data set of unsafe behaviors of mine workers through a cloud server, updating a data set of unsafe behaviors of local workers, and carrying out decision making on the unsafe behaviors of the mine workers in real time through continuous training and updating and correcting dynamic propagation evolution of the unsafe behaviors of the workers.
Preferably, the unsafe behavior propagation process conceptual model constructed in S3-3 includes:
S-A, judging whether pre-stored unsafe behaviors of workers to be identified exist or not, and if so, determining that the unsafe behaviors of the workers to be identified exist; otherwise, no unsafe behaviors of workers exist, the unsafe behaviors of the workers in the mine are self-learned by using a clustering analysis posterior probability method to obtain expected values of the unsafe behaviors,
calculating posterior probability of unsafe behavior of workers by using a Bayes formula:
wherein according to the hidden variable f x The number of the example categories for forming unsafe behaviors of workers is d x =y, where subscript x is the category of worker unsafe, y is the number of worker unsafe acquired, T (d x =y; e) For unsafe actions of workers in category number d x The spatial distribution ratio occupied by y is marked by calculating a parameter E; wherein K, ψ are respectively a worker unsafe behavior judgment parameter and a probability analysis adjustment parameter, and a process function T (f) is calculated x |d x =y, K, ψ) to calculate the posterior probability, s is a positive integer, and the process function is spatially distributed in the unsafe behavior of the worker, through a hybrid modelThe ratio of the calculated spatial distribution to the process function in the unsafe behavior of the worker is calculated to obtain the posterior probability of the unsafe behavior,
forming initial clustering centers of unsafe behaviors of workers through posterior probability calculation, sequentially treating the unsafe behaviors of the workers to be clustered by taking each initial clustering center as a starting point, and calculating similarity of the unsafe behaviors of the workers:
wherein V (i) is a worker unsafe behavior sample function, V (j) is a worker unsafe behavior evaluation function, sigma is an adjustment coefficient, and i and j are positive integers;
setting worker unsafe behavior clustering sample L s Is a culling threshold of: r (L) s ) The clustering algorithm is:
wherein F is max (L s ,N i ) For clustering samples L s And behavioral criteria N i Is the maximum sample reference function of (2), W (L s ) For clustering samples L s Is the partial derivative of UWeight variable, C (L) s ,N i ) As a baseline reference function, and then multiplying the number P of people for worker unsafe behavior s Ratio to the total number of mine workers P
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
the coal mine worker unsafe behavior group propagation process model constructed based on ABMS fully pays attention to microscopic individual characteristics of the system, interaction between individuals and environment, fully considers the cognitive mechanism of unsafe behavior propagation, and dynamically and visually displays macroscopic phenomena of unsafe behavior propagation of workers in underground groups; by adjusting the model parameter variables, the model simulation result can reveal the action mechanism of main factors such as worker individuals and external environment on the unsafe behavior group propagation, thereby establishing a feasible unsafe behavior intervention path and strategy, preventing the unsafe behavior from diffusing and evolving in the group, and further reducing the unsafe behavior in the production process.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a model of the information processing process of the present invention for the emerging spread of mine team worker unsafe behavior;
FIG. 2 is a conceptual model of the mine team worker unsafe behavior propagation process of the present invention;
FIG. 3 is a worker subject Agent model parameter of the present invention;
FIG. 4 is a simulation framework of the mine worker unsafe behavior propagation process of the present invention;
fig. 5 is a general flow chart of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
The purpose of the invention is that: the modeling and simulation method and technology for the unsafe behavior propagation process are provided, macroscopic phenomena of unsafe behavior emerging propagation in a team system are described and displayed from the overall view of the system, dynamic and visual supervision and control of the unsafe behavior propagation process are realized, and the propagation of unsafe behavior in the team group operation process is restrained.
The invention aims at realizing the following technical scheme: on the basis of establishing an information processing process model for the occurrence and propagation of unsafe behaviors of workers, an ABMS modeling technology and a method are adopted, and the unsafe behavior propagation process model is established by describing system elements such as interaction relations among the main bodies (agents) of the workers, interaction between the workers and the environment, unsafe behavior propagation decisions of the main bodies of the workers and the like; based on an analog software platform, through controlling model variables, the phenomenon of propagation and emergence of unsafe behaviors of workers in different external environment conditions and under different individual attribute states is designed and simulated. The method comprises the following specific steps:
establishing an information processing process model of the occurrence and propagation of unsafe behaviors of workers, and describing a cognitive process of the occurrence and propagation of unsafe behaviors of workers according to information processing related theory and propagation theory, wherein the model comprises three parts, namely external information receiving, behavior decision process and initial behavior adaptation;
constructing an unsafe behavior propagation process conceptual model, identifying the characteristics of a main body, a structure, an internal communication connection mode and the like of a coal mine team group system, extracting system elements and describing the system elements;
designing a worker main body Agent model, wherein the design comprises the steps of designing individual factors and objective environment parameters of workers, wherein the individual factors are divided into psychological factors and individual attributes, and the objective environment is set aiming at enterprise situation factors and group factors;
designing an unsafe behavior propagation decision mechanism of a worker, and describing a behavior decision process mechanism of the worker by using a prospect theory, wherein the process comprises editing and evaluating two processes;
the simulation implementation is realized, based on an analog software platform, the attribute and the variable parameter are set, the model variable is dynamically adjusted to show unsafe behavior cognitive propagation unsafe behavior propagation emergence phenomena under different worker attributes and objective environments, and main influencing factors of the unsafe behavior propagation process are identified.
1. Establishing an information processing process model for the emerging propagation of unsafe behaviors of workers
Fig. 1 is an information processing process model for the occurrence and propagation of unsafe behaviors of mine team workers, which is established by the invention, and describes a cognitive process for the occurrence and propagation of unsafe behaviors of workers according to the information processing related theory and the propagation theory, wherein the cognitive process comprises three main parts, namely external information receiving, behavior decision process and initial behavior adaptation, and the specific implementation steps are as follows:
(1) And (5) external information receiving: the unsafe behavior information is received through formal or informal communication connection which is continuously performed among the unsafe behavior information. The communication connection mode between workers and team members is as follows: the team leader issues a job instruction, distributes tasks and monitors and manages the job process; the worker feeds back the problems or unsafe behaviors in the working process to the team leader in time; team members coordinate the progress of work, the delivery of work, and the disputes of work. The communication connection mode between workers is as follows: collaboration and assistance of workers during the operation of the same process or procedure; the hand-over operation of workers and workers in the next working procedure; and the technical and professional ability of workers is high, and the workers can propose work activities of friends.
(2) Behavior decision process: firstly, a worker completes identification and confirmation of information according to the existing knowledge and experience, so that the received information is deeply interpreted and understood. Then, in combination with the own demands, the thought of how to react to the information and make countermeasures is needed to be referred to other related information of the outside, wherein the related information is provided by workers, environments, managers and the like; accordingly, the worker will select the corresponding behavior based on his own motivation and job demand. When the unsafe behavior provided by the worker can meet the requirement of completing the operation, and meanwhile, the worker can obtain greater benefit than the safe operation can bring, the worker can neglect the defect of executing the unsafe behavior, select to copy or imitate the unsafe behavior of the worker and abandon executing the safe behavior.
(3) Initial behavior debugging: the worker selects unsafe behavior of the recipient worker after the behavior decision, adapts the original operation behavior, including copying, imitating the unsafe behavior, and evolves to develop new unsafe behavior. Copying is mechanically carried out in an original operation behavior mode; the imitation is to imitate unsafe behavior of other people and improve according to the characteristics of the imitation; the evolution development of unsafe behavior is to combine the self requirements and characteristics and evolve a new unsafe behavior.
2. Extracting and describing system elements such as main body, structure, internal communication connection mode and the like of a team group system
Fig. 2 is a conceptual model of unsafe behavior propagation process of mine team workers constructed by the invention, describing a dynamic development process of unsafe behavior propagation evolution, and specifically implementing the following steps:
(1) Identifying members (Agent types), external environments and internal structures of the underground team operating system.
The member types of the team system comprise a team leader and workers, the team leader plays roles of manager, performing functions of leader, allocation, supervision and coordination, and simultaneously supervising and checking the working process, and the workers play roles of executives and play roles of own business, technology, demonstration and the like.
The external environment acts as a trigger factor affecting the person's behavior, inducing the generation of behavior by affecting the person's psychological and cognitive processes. The external factors in the operation process are mainly enterprise situations where workers are located, including all enterprise environments related to the operation of the workers, and are reflected in three aspects of working environment, organization environment and system environment, and the mutual influence of the workers in the environment is classified as group factors.
Internal structure: the existing underground team working structure is in a divergent type, the inside of the existing underground team working structure adopts a top-down organization management mode, a team leader receives superior operation tasks and operation requirements, then the team leader downwards distributes the tasks, a team member individual completes a set target, workers also constantly keep information communication and feedback with the team leader, and workers cooperate and communicate with each other in the operation process.
(2) And determining established communication rules and interaction connection situations of interaction between the main Agent of the worker and the external environment and interaction between other agents in the underground operation process.
The communication manner between the worker bodies is in a one-to-one, one-to-many, many-to-one or many-to-many form. The communication process of unsafe behavior propagation takes the information of unsafe behavior suggested or implied by workers as an initial stage, then assimilates and conforms the information, and finally, the communication process is a self-adapting stage, wherein the worker adapts the original working behavior attitude and coping willingness as two cognitive structure changing modes for adopting unsafe behavior.
The communication connection situation between workers and team members is as follows: the team leader issues a job instruction, distributes tasks and monitors and manages the job process; the worker feeds back the problems or unsafe behaviors in the working process to the team leader in time; team members coordinate the progress of work, the delivery of work, and the disputes of work. The communication connection mode between workers is as follows: collaboration and assistance of workers during the operation of the same process or procedure; the hand-over operation of workers and workers in the next working procedure; and the technical and professional ability of workers is high, and the workers can propose work activities of friends.
(3) Establishing a worker main body Agent behavior rule and a knowledge base; the underground operation behavior of workers takes relevant coal mine safety production regulation systems such as coal mine safety regulations, coal mine safety operation regulations, post responsibilities and the like as the behavior rules, and the knowledge base comprises underground post expertise, safety knowledge, technical skills, working experience and the like.
(4) The information processing process of the unsafe behavior of the worker is clarified, and the information processing process is described according to the information processing process model of the unsafe behavior of the worker, which is shown in fig. 1, and is propagated.
3. Main body Agent model of designer
According to a behavior formula provided by Kurt Lewis, main influencing factors of an unsafe behavior propagation process of workers are identified from two aspects of an individual worker and an external environment, the main Agent model parameters of the workers shown in fig. 3 are designed, a main Agent model is defined according to the main Agent model parameters, subjective factors of the workers are mainly divided into three types of intrinsic attributes, extrinsic attributes and knowledge attributes in the setting of the model, objective environments are set for situation factors and group factors of enterprises, and the influence of the group factors mainly reflects in the interaction process among the workers.
(1) Intrinsic attributes, that is, intrinsic factors generated by the operation behaviors of workers, are psychological factors capable of influencing the action decisions of workers, including both psychological processes and individuality. From the initiative of behaviors, the individuality of workers containing personality traits, personality literacy and other contents is divided into an initiative type and a passive type; the safety behavior willingness is used as an intermediate variable to reflect the psychological process and the personal psychological of the main body of the worker, which influence the behavior decision in the operation process, and reflect the psychological appeal degree of the safety behavior of the worker.
(2) Extrinsic attributes refer to attributes that workers have in the organization as social people, and are related to the role they play, the situation they are in, and the interpersonal relationships. The social attributes mainly comprise job levels and salary levels, and in the coal mine production team, the job positions of workers are mainly divided into three levels: the common worker, technician and supervisor technician, the corresponding salary levels are positively correlated with job level presentation.
(3) The knowledge attribute is a characteristic of staff, is an important index for workers to examine unsafe behavior transmission, is an information resource for the workers to exchange information and energy with the external environment, and adopts a knowledge level quantization function proposed by Fang to describe the knowledge level of the workers in the working process.
(4) The objective environment where the worker works is mainly an enterprise situation, and comprises three aspects of a working environment, an organization environment and a system environment. The working environment has normative or non-normative enterprise facts which have guiding influence on the underground behaviors of workers, comprises working responsibilities, normative, superior instructions, interaction relations among workers and the like, and also comprises a physical working environment which is a physical environment condition directly acting on the working behaviors, such as the size, lighting, ventilation, noise and the like of an underground working site; the organization environment mainly shows the contents of the organization structure design, the salary level system, the incentive mechanism, the employee employment mechanism and the like of the enterprise; the system environment is a series of files with compendial meaning formulated around the development of enterprises and corresponding mission, and relevant national regulation system, including safety production management system, enterprise safety culture, operation regulations and the like, and also including shaping and appeal of staff by enterprise manager.
4. Design of worker unsafe behavior propagation decision mechanism based on cognitive process
Behavior decision model: in the action decision process, more of the workers consider the risks of self benefit and avoidance brought by the finally selected actions, and the action decision process of the workers is described by applying a prospect theory based on the cognitive information processing process of the workers, wherein the theory divides the decision process of the risks into two processes, namely editing and evaluating. In the editing stage of risk evaluation, the worker individual members collect and process information by means of the reference points, and in the evaluation stage, the information is judged by mainly relying on two parameters, namely a cost function and a subjective probability weight function.
Cost function: in the operation process, the transmission of behaviors such as imitation or replication of the unsafe behaviors of workers is to take the unsafe behaviors of workers as decision reference points, and set a cost function taking the unsafe behaviors of workers as reference points.
Weight function: and designing a weight function of the worker behavior decision according to the foreground theoretical decision model, and representing probability measurement of each expected result and the change influence of each expected result on the total utility.
Expected utility function: the preferences of workers of different personality psychology for the intended utility are different, and therefore the individual preference coefficients need to be designed. Wherein, for the workers with active personality and psychology, the preference of the worker for the salary grade and the job grade is larger than the influence of the demonstration effect of the worker's behavior, and for the workers with passive personality and psychology, the preference of the salary grade and the job grade is smaller than the influence of the demonstration effect of the worker's behavior in the working process. In addition, the judgment of the occurrence probability of the expected utility result by workers is influenced by situation factors, and the expected utility and the occurrence probability function thereof are determined according to the content and influence of the situation factors of the coal mine enterprises and the marginal incremental relation effect of expected benefits and grades. Accordingly, an expected utility function for a specific worker to evaluate the value of the expected target is set. When the effectiveness of the worker operation behavior is smaller than the effectiveness of the operation achieved by the reference worker, the worker operation behavior is regarded as loss, and a corresponding loss effectiveness function is obtained
Unsafe behavior propagates decision functions: combining the design to obtain an unsafe behavior propagation decision function, and when the absolute value of expected benefit utility is larger than the absolute value of expected loss utility, selecting to implement unsafe behaviors performed by workers; otherwise, the unsafe behavior of the worker is refused to be adopted.
5. Simulation implementation
Fig. 4 is a simulation framework of the unsafe behavior propagation process of mine workers, based on an analog software platform, based on a conceptual model of a previous system, a main body behavior model, an environment model and an interaction model are constructed according to the operation flow of a coal mine team and actual research requirements, and a simulation technical scheme comprising contents such as dynamic change target variables, team scales, parameter values of an agent, a result output mode and the like is formulated. The main body behavior model adopts a worker unsafe behavior propagation decision mechanism and model parameters which are designed in the earlier stage; the environment model is mainly based on information sources of the worker operation process and comprises carriers of information flows such as workers, managers, behavior instructions and the like; the interaction model designs established communication rules and interaction connection situations of interaction between the main Agent of the worker and the external environment and other agents.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (5)
1. The extraction and analysis method for the unsafe behavior propagation process of the mine team workers is characterized by comprising the following steps:
s1, acquiring unsafe behavior data of workers in a mine, and establishing an information processing process model of the emerging and spread unsafe behavior of the workers;
s2, after training through a processing process model, building a team group system for unsafe behaviors of workers, and extracting and describing main bodies, structures and internal communication mode elements of the team group system;
s3, after extraction and depiction are completed, constructing an unsafe behavior propagation process conceptual model;
s3-1, determining set communication rules and interaction connection situations of interaction between a worker main body Agent and external environment and interaction between other worker main body agents in the mine operation process;
s3-2, establishing a worker main body Agent behavior rule and a knowledge base;
s3-3, constructing an unsafe behavior propagation process conceptual model, defining unsafe behaviors propagated by workers, describing differentiation in executive behaviors of a group leader and the executive behaviors of the workers in a mine, and defining concepts of the differentiated and homogenized executive behaviors of the group leader and the executive behaviors of the workers;
the unsafe behavior propagation process conceptual model constructed in the S3-3 comprises the following steps:
S-A, judging whether pre-stored unsafe behaviors of workers to be identified exist or not, and if so, determining that the unsafe behaviors of the workers to be identified exist; otherwise, no unsafe behaviors of workers exist, the unsafe behaviors of the workers in the mine are self-learned by using a clustering analysis posterior probability method to obtain expected values of the unsafe behaviors,
calculating posterior probability of unsafe behavior of workers by using a Bayes formula:
wherein according to the hidden variable f x The number of the example categories for forming unsafe behaviors of workers is d x =y, where subscript x is the category of worker unsafe, y is the number of worker unsafe acquired, T (d x =y; e) For unsafe actions of workers in category number d x The spatial distribution ratio occupied by y is marked by calculating a parameter E; wherein K, ψ are respectively a worker unsafe behavior judgment parameter and a probability analysis adjustment parameter, and a process function T (f) is calculated x |d x =y, K, ψ) to calculate the posterior probability, s is a positive integer, and the process function is spatially distributed in the unsafe behavior of the worker, through a hybrid modelThe ratio of the calculated spatial distribution to the process function in the unsafe behavior of the worker is calculated to obtain the posterior probability of the unsafe behavior,
forming initial clustering centers of unsafe behaviors of workers through posterior probability calculation, sequentially treating the unsafe behaviors of the workers to be clustered by taking each initial clustering center as a starting point, and calculating similarity of the unsafe behaviors of the workers:
wherein V (i) is a worker unsafe behavior sample function, V (j) is a worker unsafe behavior evaluation function, sigma is an adjustment coefficient, and i and j are positive integers;
setting worker unsafe behavior clustering sample L s Is a culling threshold of: r (L) s ) The clustering algorithm is:
wherein F is max (L s ,N i ) For clustering samples L s And behavioral criteria N i Is the maximum sample reference function of (2), W (L s ) For clustering samples L s Is the partial derivative of U, a weight variable, C (L s ,N i ) As a baseline reference function, and then multiplying the number P of people for worker unsafe behavior s Ratio to the total number of mine workers P
S4, after the propagation process conceptual model is established, processing and designing the main Agent model of the worker;
s5, establishing a worker unsafe behavior propagation decision mechanism according to the formed unsafe behavior propagation process conceptual model and the worker main body Agent model;
s6, performing verification operation according to the established unsafe behavior propagation decision mechanism of the worker, and correcting according to dynamic propagation evolution of the unsafe behavior of the worker.
2. The mine team worker unsafe behavior propagation process extraction and analysis method of claim 1, wherein said S1 comprises:
s1-1, collecting unsafe behaviors of workers through mine image acquisition equipment, receiving actual working scene information in a mine through sensing the external environment of the mine, and defining an unsafe behavior model in the actual working scene information of the mine;
s1-2, extracting unsafe behaviors of workers through mine image acquisition equipment according to an unsafe behavior model, and performing information mapping on mine actual working scene information and the extracted unsafe behaviors of the workers at corresponding time points;
s1-3, performing cognitive processing on the unsafe behaviors of the workers according to the mapped unsafe behavior information of the workers, and completing a cognitive processing process according to understanding cognition on the unsafe behaviors of the workers in machine learning and the mapped unsafe behavior information of the workers;
s1-4, after collecting, copying and evolving unsafe behaviors of workers, properly selecting the unsafe behaviors of the workers and debugging a unsafe behavior data set of the workers; thereby forming an information processing model.
3. The mine team worker unsafe behavior propagation process extraction and analysis method of claim 1, wherein said S2 comprises:
s2-1, after training the information processing process model formed in the S1, refining unsafe behaviors of workers into executive behaviors of a team leader and executive behaviors of the workers;
s2-2, performing behaviors by the group leader to form a group leader execution leading unsafe behavior library, a work task allocation unsafe behavior library, a supervision unsafe behavior library and a coordination control unsafe behavior library;
s2-3, the worker performs behaviors to form a worker execution business unsafe behavior library, an operation technology unsafe behavior library and an demonstration operation unsafe behavior library.
4. The mine team worker unsafe behavior propagation process extraction and analysis method of claim 1, wherein said S5 comprises:
s5-1, for a worker unsafe behavior decision mechanism: in the action decision process, the worker considers the risk that the finally selected action can bring self benefit and avoid, describes the action decision process of the worker based on the cognitive information processing process of the worker by using a prospect theory, and the theory divides the decision process of the risk into two processes, namely editing and evaluating; in the editing stage of risk evaluation, the individual members of workers acquire and process information by means of reference points, and in the evaluation stage, the information is judged by mainly relying on two methods, namely a cost function and a subjective probability weight function;
s5-2, establishing a worker unsafe behavior cost function: in the mine operation process, imitation or replication of worker's unsafe behavior is carried out by taking the unsafe behavior of the worker as a decision reference point and setting a cost function taking the unsafe behavior of the worker as a reference point;
s5-3, establishing a worker unsafe behavior weight function: designing a weight function of a worker behavior decision according to a foreground theoretical decision model, and representing probability measurement of each expected result and the change influence of each expected result on the total utility;
s5-4, establishing an expected utility function of unsafe behaviors of workers: the preference of workers with different personal psychology for expected utility is different, so that the preference coefficient of the individual needs to be designed; wherein, for the workers with active personality and psychology, the preference of the workers with the salary grade and the job grade is larger than the influence of the demonstration effect of the worker's behavior, and for the workers with passive personality and psychology, the preference of the salary grade and the job grade is smaller than the influence of the demonstration effect of the worker's behavior in the working process; in addition, the judgment of the occurrence probability of the expected utility result by workers is influenced by situation factors, and the expected utility and the occurrence probability function thereof are determined according to the content and influence of the situation factors of the coal mine enterprises and the marginal incremental relation effect of expected benefits and grades; accordingly, setting an expected utility function for performing value evaluation on an expected target by a specific worker; when the effectiveness of the worker operation behavior is smaller than the behavior effectiveness achieved by the referenced worker, the worker operation behavior is regarded as loss, and a corresponding loss effectiveness function is obtained;
s5-5, transmitting decision function through unsafe behaviors of workers: the method comprises the steps that a worker unsafe behavior propagation decision mechanism is obtained through S5-1 to S5-4, and when the absolute value of the expected utility of the extracted worker unsafe behavior is larger than the absolute value of the loss utility of the worker unsafe behavior, worker unsafe behavior data prestored by a mine image acquisition device are judged to acquire the worker unsafe behavior data in real time; if the non-matching is the same behavior, the mine operation is continued, otherwise, the unsafe behavior is refused to be adopted.
5. The mine team worker unsafe behavior propagation process extraction and analysis method of claim 1, wherein said S6 comprises:
s6-1, constructing a worker unsafe behavior main body behavior model, a worker unsafe behavior environment model and a worker unsafe behavior interaction model according to pre-stored working behavior data of a mine middle team leader execution behavior and a worker execution behavior and real-time collected working behavior data;
s6-2, formulating a simulation technical scheme of dynamic change target variables, team scales, intelligent agent parameter values and result output modes of unsafe behaviors of workers;
s6-3, the unsafe behavior of the worker main body adopts a pre-designed unsafe behavior propagation decision mechanism and model parameters; the unsafe behavior environment model of the worker is mainly based on information sources of the worker operation process in the mine, and the interaction model is designed to be a set communication rule and an interaction connection situation of interaction between the main Agent of the worker and the external environment and other agents;
s6-4, continuously collecting and updating a data set of unsafe behaviors of mine workers through a cloud server, updating a data set of unsafe behaviors of local workers, and carrying out decision making on the unsafe behaviors of the mine workers in real time through continuous training and updating and correcting dynamic propagation evolution of the unsafe behaviors of the workers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010691231.7A CN111861198B (en) | 2020-07-17 | 2020-07-17 | Extraction and analysis method for mine team worker unsafe behavior propagation process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010691231.7A CN111861198B (en) | 2020-07-17 | 2020-07-17 | Extraction and analysis method for mine team worker unsafe behavior propagation process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111861198A CN111861198A (en) | 2020-10-30 |
| CN111861198B true CN111861198B (en) | 2023-09-29 |
Family
ID=73000489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010691231.7A Active CN111861198B (en) | 2020-07-17 | 2020-07-17 | Extraction and analysis method for mine team worker unsafe behavior propagation process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861198B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112727553B (en) * | 2021-02-05 | 2023-02-14 | 西安重装伟肯电气有限责任公司 | Underground personnel behavior safety supervision and management system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103716324A (en) * | 2013-12-31 | 2014-04-09 | 重庆邮电大学 | Virtual mine risk-taking behavior implementation system and method based on multiple agents |
| CN107436964A (en) * | 2017-01-08 | 2017-12-05 | 西安科技大学 | A kind of method of the evolution mechanism simulation analysis of miner's unsafe acts |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10739773B2 (en) * | 2017-09-28 | 2020-08-11 | Nec Corporation | Generative adversarial inverse trajectory optimization for probabilistic vehicle forecasting |
-
2020
- 2020-07-17 CN CN202010691231.7A patent/CN111861198B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103716324A (en) * | 2013-12-31 | 2014-04-09 | 重庆邮电大学 | Virtual mine risk-taking behavior implementation system and method based on multiple agents |
| CN107436964A (en) * | 2017-01-08 | 2017-12-05 | 西安科技大学 | A kind of method of the evolution mechanism simulation analysis of miner's unsafe acts |
Non-Patent Citations (4)
| Title |
|---|
| "Analysis of complexity of unsafe behavior in construction teams and a multiagent simulation;Li Z et al;Complexity;1-15 * |
| 基于ABMS的煤矿不安全行为惩罚制度有效性仿真;陈红 等;数学的实践与认识(第01期);53-71 * |
| 基于贝叶斯网络的电力企业安全生产风险管控系统;章伟林 等;计算机系统应用(第03期);102-107 * |
| 煤矿职工不安全行为仿真与预警控制系统研究;周鲁洁;中国博士学位论文全文数据库 工程科技Ⅰ辑;B021-27 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111861198A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cheng et al. | Evolutionary model of coal mine safety system based on multi-agent modeling | |
| CN109840838A (en) | Air control rule model system with double engines, control method and server | |
| CN105204631B (en) | A kind of VGE Role Modeling method and many role's cooperating methods | |
| CN103020332A (en) | Intelligent virtual maintenance training system for civil aircraft | |
| CN107248028B (en) | Method for handling passenger group events in large-area flight delay scene | |
| CN111861198B (en) | Extraction and analysis method for mine team worker unsafe behavior propagation process | |
| Lin et al. | Automation design in advanced control rooms of the modernized nuclear power plants | |
| CN103903088A (en) | High-speed railway construction project quality risk control system and method | |
| Konovalov et al. | The role of human factor in ensuring the safety of electric power objects after their intellectualization | |
| Bao et al. | Impacts of land expropriation on the entrepreneurial decision-making behavior of land-lost peasants: An agent-based simulation | |
| Xiao et al. | Decomposition of carbon emission influencing factors and research on emission reduction performance of energy consumption in China | |
| Xu et al. | Research on simulation of risk control strategy for air traffic controllers’ unsafe acts | |
| Wang et al. | Research on the evolution of incentive mechanisms for urban deep decarbonization under the vision of carbon neutrality: a perspective of multi-agent embedded participation | |
| Huang et al. | An evolutionary game-theoretic analysis of construction workers' unsafe behavior: Considering incentive and risk loss | |
| Sun et al. | A system dynamics model of prevention through design towards eliminating human error | |
| Li et al. | Game modelling and strategy research on trilateral evolution for coal-mine operational safety production system: a simulation approach | |
| Wu et al. | Analysis on coupling dynamic effect of human errors in aviation safety | |
| CN116011722A (en) | Large power grid-oriented man-machine cooperation regulation and control method, module and device | |
| CN113592311B (en) | Method for selecting personal factor method for complex man-machine system | |
| CN111400796B (en) | Agent-based indoor emergency evacuation location risk assessment method | |
| Li et al. | The Influence of Mutual Assistance of Construction Workers with Different Personality Traits on Team Safety | |
| Qi et al. | Simulation of Chinese coal mine safety supervision system performance based on netlogo platform | |
| Jiao et al. | TMT group decision method based on system dynamics and game control theory | |
| Li et al. | Dynamic simulation and control strategy exploration of the unsafe behavior of coal mine employees | |
| CN116384738A (en) | Research method for influence of safety atmosphere on interpersonal propagation of unsafe behavior in airport construction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |