CN115729186A - Safety state multi-mode real-time intelligent control master machine, method and system - Google Patents
Safety state multi-mode real-time intelligent control master machine, method and system Download PDFInfo
- Publication number
- CN115729186A CN115729186A CN202211441277.9A CN202211441277A CN115729186A CN 115729186 A CN115729186 A CN 115729186A CN 202211441277 A CN202211441277 A CN 202211441277A CN 115729186 A CN115729186 A CN 115729186A
- Authority
- CN
- China
- Prior art keywords
- safety
- monitoring
- level
- node
- real
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a multi-mode real-time intelligent control master machine, a method and a system for safety state, wherein the multi-mode real-time intelligent control master machine for safety state comprises a parameter selection module for a user to select monitoring parameters, a data transceiving module for receiving real-time monitoring values of the monitoring parameters selected by the user and sending the real-time monitoring values to a control module, and the control module is embedded into multi-level multi-mode fusion assessment early warning models corresponding to a plurality of different monitoring scenes and used for determining the monitoring scenes according to the monitoring parameters selected by the user, calling the multi-level multi-mode fusion assessment early warning models corresponding to the monitoring scenes and carrying out safety assessment early warning by combining the real-time monitoring values of the monitoring parameters. The invention develops real-time intelligent management and control equipment with cross-scene variable parameters and variable modes for safety states based on the technology of the Internet of things, can expand parameter types when scene monitoring parameters change, is suitable for mode expansion of multi-level safety multi-mode management and control, integrates multi-mode evaluation and early warning, and provides multiple safety guarantees.
Description
Technical Field
The invention belongs to the field of safety monitoring, and particularly relates to a safety state multi-mode real-time intelligent control master machine, a method and a system.
Background
Safety monitoring is a safety production technical means of all walks of life, and the intelligent level of safety monitoring equipment determines the safety production control effect. The intellectualization of safety production monitoring equipment in each field needs to be further improved. The main technical problem that current safety in production monitoring equipment exists includes: (1) The contradiction between the relatively perfect monitoring of the safe production state and the insufficient real-time analysis and comprehensive evaluation of the safe production state. (2) The monitoring intellectualization and the safety production control decision mainly depend on the contradiction of manpower. (3) The contradiction between the multi-parameter of safety production monitoring and the multi-level multi-mode control of the safety production state in real time cooperation.
Therefore, a multi-level real-time intelligent management and control master machine with a multi-mode security state and a multi-mode, which can select parameter types and can expand modes, is urgently needed and adapts to production and living activities and equipment facility characteristics of a changeable scene.
Disclosure of Invention
The invention provides a multi-mode real-time intelligent control master machine, a method and a system for a safety state, aiming at developing a safety state real-time intelligent control device with cross-scene variable parameters and variable modes by utilizing the technology of the Internet of things, expanding the parameter types when scene monitoring parameters change, adapting to the mode expansion of multi-level safety multi-mode control and realizing multi-mode fusion assessment and early warning. Therefore, the intellectualization and the universality of the safety monitoring instrument are promoted, the safety supervision threshold is reduced, the safety supervision cost is saved, the service scope of the safety production department monitoring technology is improved, and the safety production is promoted.
To achieve the above object, according to a first aspect of the present invention, there is provided a security status multimodal real-time intelligent management and control master machine, including: the device comprises a parameter selection module, a data transceiving module and a control module;
the parameter selection module is used for a user to select monitoring parameters;
the data transceiver module is used for receiving the real-time monitoring value of the monitoring parameter selected by the user and sending the real-time monitoring value to the control module;
the control module is embedded with a plurality of multi-level multi-modal fusion assessment early warning models corresponding to different monitoring scenes and used for determining the monitoring scenes according to monitoring parameters selected by a user, calling the multi-level multi-modal fusion assessment early warning models corresponding to the monitoring scenes and carrying out safety assessment early warning by combining real-time monitoring values of the monitoring parameters;
the multi-level multi-mode fusion assessment early warning model comprises a node-level mode fusion layer, a process-level mode fusion layer and a process-level mode fusion layer from bottom to top;
the node-level modal fusion layer is used for judging whether each node has a safety risk or not according to the real-time monitoring value and the preset threshold value of the monitoring parameter of each node, alarming if the node has the safety risk, and calculating the safety evaluation value of each node;
the process-level modal fusion layer is used for calculating the safety assessment values of all the processes according to the safety assessment values of all the nodes so as to judge whether safety risks exist in all the processes or not, and if so, alarming is carried out;
and the process level modal fusion layer is used for judging whether each process has a safety risk or not according to the safety assessment score of each process, and if so, giving an alarm.
Preferably, the node-level modal fusion layer adopts a series fusion model: when any monitoring parameter of the node exceeds a preset threshold, the node is determined to have a safety risk, the safety assessment score of the node is 100, or the safety assessment score of the node is determined according to the percentage exceeding the preset threshold.
Preferably, the procedure-level modal fusion layer adopts a weighted fusion model: and calculating the weighted score of the process according to the weight and the score of the nodes included in the process, and if the weighted score exceeds a preset risk threshold, determining that the process has a safety risk.
Preferably, the flow-level modal fusion layer adopts a series fusion model: and when any procedure of the flow has a safety risk, the flow is determined to have the safety risk.
Preferably, the system further comprises a modality extension module for extending or selecting the monitoring parameters, the nodes, the procedures or the processes by the user.
According to a second aspect of the present invention, there is provided a multi-modal real-time intelligent management and control method for a security state, applied to a control module for managing and controlling a master machine according to the first aspect, including:
determining a monitoring scene according to monitoring parameters selected by a user, calling a multi-level multi-modal fusion assessment early warning model corresponding to the monitoring scene, and carrying out safety assessment early warning by combining real-time monitoring values of the monitoring parameters;
the multi-level multi-mode fusion assessment early warning model comprises a node-level mode fusion layer, a process-level mode fusion layer and a process-level mode fusion layer from bottom to top;
the node-level modal fusion layer is used for judging whether each node has a safety risk or not according to the real-time monitoring value and a preset threshold value of the monitoring parameter of each node, alarming if the node has the safety risk, and calculating the safety evaluation value of each node;
the process-level modal fusion layer is used for calculating the safety assessment values of all the processes according to the safety assessment values of all the nodes so as to judge whether safety risks exist in all the processes or not, and if so, alarming is carried out;
and the process-level modal fusion layer is used for judging whether each process has a safety risk or not according to the safety assessment score of each process, and alarming if the process has the safety risk.
According to a third aspect of the present invention, there is provided a security status multimodal real-time intelligent management and control system, including: a computer-readable storage medium and a processor;
the computer-readable storage medium is used for storing executable instructions;
the processor is configured to read executable instructions stored in the computer-readable storage medium and execute the method according to the second aspect.
In general, compared with the prior art, the technical scheme conceived by the invention can achieve the following beneficial effects:
according to the multi-mode real-time intelligent control master machine for the safety state, provided by the invention, the real-time intelligent control equipment for the safety state with cross-scene variable parameters and variable modes is developed by utilizing the technology of the Internet of things, when scene monitoring parameters are changed, the parameter types can be expanded, the model expansion of multi-level safety multi-mode control is adapted, multi-mode fusion evaluation early warning is realized, and multiple safety guarantees are provided. Therefore, the intelligentization and the universality of the safety monitoring instrument are promoted, the safety supervision threshold is reduced, the safety supervision cost is saved, the breadth of the safety production department monitoring technical service is improved, and the safety production is promoted.
Drawings
Fig. 1 is one of schematic structural diagrams of a security status multimodal real-time intelligent management and control master according to an embodiment of the present invention;
fig. 2 is a second schematic structural diagram of the multi-modal real-time intelligent security master according to the embodiment of the present invention;
FIG. 3 is a multi-level multi-modal fusion data flow diagram of a multi-level multi-modal fusion assessment early warning model provided by an embodiment of the present invention;
fig. 4 is a schematic view of an application flow of the multi-modal real-time intelligent management and control master in the security state according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In various factory and engineering safety monitoring and detection, technical personnel usually select monitoring parameters according to scene safety risk assessment results, sensors are arranged at sensitive positions of safety risks, acquisition and analysis instruments are used for acquiring sensor data of corresponding types, professionals make monitoring single-parameter state and multi-parameter object safety state assessment early warning standards based on real-time data according to experience and relevant standard standards, and monitoring personnel analyze monitoring data according to the monitoring parameters to conduct safety risk control. The method integrates parameter states, and various security risks in the scene are evaluated and early warned in a multi-mode state. High cost and insufficient real-time performance. The intelligent multi-parameter multi-modal real-time safety state monitoring and control equipment is urgently needed to be established according to the characteristics of real-time performance, multiple safety parameters and multiple safety modes of safety risk control.
Based on the method, the invention provides a multi-mode real-time intelligent control master machine, a method and a system for the safety state.
For ease of understanding, the relevant definitions are first explained as follows:
mode: the subject's direct or indirect description of the attributes of the object, the way it is viewed, to achieve a particular goal. One way in which a subject obtains object attribute target information or one means that the subject takes with respect to an object for the purpose is a modality.
Multimodal: the multi-modal nature of the object or the various means or ways in which the subject describes the object is known as multi-modal.
Safety: the method refers to a state that the life health and safety of people are not endangered in the scene of human productive life.
Security risk: refers to the root cause or factor that may endanger the human life health and safety in the human productive life scene.
Security risk modality: the method refers to factors which may endanger the life health and safety of people in the production and living scenes of human beings, and each type of factor is a mode, such as an explosion accident risk mode in flow factory production, a collapse accident risk mode in factory construction and the like.
Parameters of the security risk modality: various parameters which may cause the occurrence of the security risk mode, such as the influence factors of the explosion accident risk mode: flammable and explosive articles, leakage of facilities for storing flammable and explosive articles, poor ventilation of places, ultrahigh temperature and the like.
Scene: production and living activities and places thereof are collectively called.
The embodiment of the invention provides a multi-mode real-time intelligent management and control master machine in a safe state, as shown in fig. 1, comprising:
the device comprises a parameter selection module, a data transceiving module, a control module and an alarm module;
the parameter selection module is used for a user to select monitoring parameters;
the data transceiver module is used for receiving the real-time monitoring value of the monitoring parameter selected by the user and sending the real-time monitoring value to the control module;
the control module is embedded with a plurality of multi-level multi-modal fusion assessment early warning models corresponding to different monitoring scenes and used for determining the monitoring scenes according to monitoring parameters selected by a user, calling the multi-level multi-modal fusion assessment early warning models (parameter-node-process-flow multi-level multi-modal fusion assessment early warning models) corresponding to the monitoring scenes and carrying out safety assessment early warning by combining real-time monitoring values of the monitoring parameters;
the multi-level multi-mode fusion assessment early warning model comprises a node-level mode fusion layer, a process-level mode fusion layer and a process-level mode fusion layer from bottom to top;
the node-level modal fusion layer is used for judging whether each node has a safety risk or not according to the real-time monitoring value and a preset threshold value of the monitoring parameter of each node, alarming if the node has the safety risk, and calculating the safety evaluation value of each node;
the process-level modal fusion layer is used for calculating the safety assessment values of all the processes according to the safety assessment values of all the nodes so as to judge whether safety risks exist in all the processes or not, and if so, alarming is carried out;
and the process-level modal fusion layer is used for judging whether each process has a safety risk or not according to the safety assessment score of each process, and alarming if the process has the safety risk.
Preferably, the node-level modal fusion layer adopts a series fusion model: when any monitoring parameter of the node exceeds a preset threshold, the node is determined to have a safety risk, the safety assessment score of the node is 100, or the safety assessment score of the node is determined according to the percentage exceeding the preset threshold.
For example, if the monitored value of a certain monitoring parameter exceeds ten percent of the preset threshold, the safety assessment score of the node is 10, and if the monitored value of a certain monitoring parameter exceeds fifty percent of the preset threshold, the safety assessment score is 50. The more the preset threshold is exceeded, the higher the safety assessment score, representing a higher safety risk.
Preferably, the procedure-level modal fusion layer adopts a weighted fusion model: and calculating a weighted score of the process according to the weight and the score of the node included in the process, taking the weighted score as a safety evaluation score of the process, and if the weighted score exceeds a preset risk threshold, determining that the process has a safety risk.
Preferably, the flow-level modal fusion layer adopts a tandem fusion model: and when any procedure of the flow has a safety risk, the flow is determined to have the safety risk.
Preferably, the intelligent management and control mother machine further comprises a modality extension module, which is used for a user to extend or select monitoring parameters, nodes, processes or procedures, that is, is used for the user to extend or select multi-level multi-modalities of parameter modalities and nodes, processes and procedures, so that the user can set the multi-level multi-modality fusion assessment early warning model individually.
Furthermore, the alarm module is a sound-light alarm module, which can be arranged at each monitoring parameter, each node, each process and each flow, and can perform sound-light alarm when safety risks exist.
Specifically, the female machine of real-time intelligent management and control of safe state multimode includes: the device comprises a control module, a parameter selection module, a mode expansion module and a real-time data transceiving module; the system is characterized in that the Internet of things is used as a technical means, and a single chip microcomputer is used as a core to be connected with a data receiving and transmitting module, an acousto-optic early warning module, a parameter selection module and a mode expansion module. As shown in fig. 2, the real-time intelligent monitoring function of the master unit for the safety state provided by the present invention includes: the system comprises a monitoring parameter type selection function, a multi-level security mode expansion function, a data transceiving function, a multi-level multi-mode fusion analysis, evaluation and early warning function, and functional modules for realizing the functions, as shown in fig. 1.
The control module is embedded with a plurality of multi-level safety state multi-mode fusion assessment early warning models corresponding to different monitoring scenes and is used for determining the monitoring scenes according to the monitoring parameters selected by a user, calling the monitoring parameters, nodes, processes and multi-level multi-mode fusion assessment early warning models corresponding to the monitoring scenes and adapting the monitoring parameters to the models to perform safety assessment early warning.
That is, the control module comprises a multi-level multi-mode fusion analysis and assessment early warning module (namely, a scene-parameter-node-process-flow multi-level multi-mode fusion analysis module, a scene-parameter-node-process-flow safety assessment early warning module at each level), and is used for fusing safety multi-mode state parameters at each level according to the multi-mode fusion model of the corresponding monitoring scene embedded in the host machine according to the multi-mode parameter state data of the multi-mode of each level scene, further judging the safety multi-mode real-time state grade at each level according to the scene multi-level state assessment grade model embedded in the host machine, and performing early warning according to the requirement after comparing the safety multi-mode real-time state grade with the scene safety early warning threshold embedded in the host machine. As shown in fig. 2.
The corresponding relation between the monitoring parameters, the monitoring scene and the multi-level multi-modal fusion assessment early warning model is written into the control module in advance. Therefore, the control module can determine a monitoring scene according to the monitoring parameters selected by the control main body and call the corresponding multi-level multi-modal fusion assessment early warning model, and the multi-level multi-modal fusion assessment early warning model further comprises a safety threshold (namely a preset threshold) of each monitoring parameter and a preset risk threshold of each process. The correspondence can be written in a user manual.
The parameter selection module is used for a user to select the parameter type to be monitored, can adapt to the safety monitoring parameter change of a changeable scene, and is embedded into the parameter type library of the master machine to select the scene safety monitoring parameters to be controlled by the master machine; the multi-level security mode expansion module is used for expanding parameters, nodes, processes and flows of the adaptive scene by the user in a multi-level security state mode.
The real-time state data transceiver module is used for receiving the real-time sensing parameter state data of the selected parameter type and transmitting related data to the upper equipment; namely, the data transceiver module is used for receiving the intelligent monitoring parameter state data of the selected type of parameters and transmitting the relevant data of the master to the upper-level equipment.
As shown in fig. 3, the parameter, node, process, and flow multi-level security state multi-modal fusion assessment and early warning model includes a node-level modal fusion layer, a process-level modal fusion layer, and a flow-level modal fusion layer from bottom to top, and is used for performing multi-level security multi-modal fusion and multi-level security state assessment and early warning.
The control module is connected with the parameter selection module and used for selecting the parameter types to be controlled, after the parameter types are selected, the control module drives the receiving module to receive the parameter state real-time data sent by the scene intelligent perception sensor of the selected parameters, the control module automatically adapts the parameter state real-time data to the corresponding parameter level multi-mode, node, process and flow multi-mode fusion model, the edge calculation evaluates the multi-level safety multi-mode state and gives an early warning, and the data uploading module is driven to upload the data. The control module takes a single chip microcomputer as equipment and is embedded with a parameter type library, a scene modal model library, a scene multi-modal fusion model library, a scene safety multi-modal assessment model library, a scene safety state assessment grade model library and a data identification library.
The multi-level multi-modal fusion function shown in fig. 2 comprises a multi-modal fusion model library embedded in the parameter, node, process and flow level of the control module. The multi-level safety state assessment early warning function comprises a scene, parameters, nodes, processes and a process level safety state assessment level model library of an embedded control module. Namely, the control module is embedded into a parameter type database, a scene and parameter, node, process and flow multi-layer modal database, a multi-layer scene security multi-modal fusion database and a scene flow security state assessment early warning model database.
As shown in fig. 4, the control main body selects parameters according to the security monitoring parameters of the control scene, determines security modalities of each level of the scene-parameter-node-process-flow, the control module receives parameter selection and modality extension information, the driving data receiving module receives scene parameter state data sent by the scene intelligent sensor in real time, adapts to security modality models of each level of the scene, drives multi-modal fusion analysis of each level of the scene-parameter-node-process-flow, judges security states of each level of the scene, performs early warning of exceeding a threshold value, and then uploads the received data and decision data of the host.
Further, the parameter selection module and the mode expansion module can both use a keyboard connected with a port of the single chip microcomputer as equipment, and realize parameter selection and mode expansion through mapping of the keyboard, parameter types and modes.
The data receiving module takes the wireless receiving and sending device as equipment and is driven by the control module, and when the parameters and the modes of the scene are determined, the control module drives the data receiving module to receive the parameter state real-time data sent by the intelligent sensor for controlling the scene parameters. And after the real-time data is processed and a scene multi-level multi-mode safety control decision is formed, the decision information and the received data are wirelessly uploaded to the upper equipment.
The scene-parameter-node-process-flow multi-level multi-mode fusion analysis module receives scene real-time monitoring parameter state data transmitted by the data receiving and transmitting module, fuses multi-modes of each level according to the parameter multi-mode fusion model, and sequentially performs node multi-mode and process multi-mode fusion analysis according to the parameter multi-mode data.
The scene-parameter-node-process-flow each-level safety assessment early warning module carries out safety state assessment early warning of each level in sequence according to a scene, parameter, node, process and flow each-level safety state assessment early warning model according to a scene-parameter-node-process-flow each-level multi-mode fusion analysis result.
The intelligent control master machine provided by the invention selects a middle-end PIC16F877 singlechip as a chip of a safety-state multi-mode real-time intelligent control master machine expansion module, a WIFI communication module for receiving and transmitting data is connected with a port B, a port A is connected with item scene selection setting and monitoring parameter selection setting, a port C is connected with a scene safety multi-mode fusion model selection setting port, a port D is connected with a mode parameter selection setting port of a control level, and a port E is connected with voice early warning and light prompting. The control module chip is embedded into a parameter type database, a security mode database, a security multi-mode fusion model library and a security state evaluation model library.
The safety state multi-mode real-time intelligent control master machine provided by the invention has a parameter type selection function, a mode expansion function, a multi-mode fusion and safety state assessment early warning function and a data receiving and sending function; in order to realize the function device, a parameter type information base, a modal information base, a multi-modal fusion model base and a safety state assessment early warning module base are embedded. The manufacturing method is that parameter type and safety mode expansion are realized by a parameter type information base and a mode information base which are embedded into the main machine through a communication channel inside the main machine and a designed parameter mode selection key; providing a multi-mode fusion model library embedded in a parent machine, and performing safe multi-mode fusion layer by layer from parameter-node-process-flow by edge calculation; by embedding the monitoring project, scene and parameter state evaluation model base of the host machine, the state evaluation early warning of the monitored object is analyzed and evaluated by edge calculation, and the informatization application of the safety monitoring data is realized. When the intelligent management and control master machine is used, the monitoring parameters of the monitored objects are selected and received according to the scene, and after various types of modes of the scene are determined according to the safety monitoring content of each monitoring level, normal use can be started. The monitoring host machine control module drives the data receiving and sending module to receive monitoring parameter state data of the monitored object, the mode fusion module fuses the safe multi-mode data step by step according to the hierarchy, the safety assessment early warning module assesses the safety state level of the hierarchy step by step according to the hierarchy and carries out early warning, and the data receiving and sending module uploads related information.
The application of the safe-state multi-mode real-time intelligent control master machine provided by the embodiment of the invention is further explained by taking the jacking operation of a building construction tower crane as an example.
The tower crane jacking operation aims at jacking 1 standard joint height after the tower top originally connected with the standard joint of the tower body is disconnected, adding 1 new standard joint, connecting the lower part of the tower body with the tower body, and connecting the upper part of the tower body with the tower top, so that the tower crane height is increased. The operation process is complex and high in risk, and becomes the 1 st high-risk activity in the building construction process. The main monitoring parameters related to the safety operation comprise: 1) Meteorological parameters: indexes such as wind speed, direction, temperature and humidity; 2) Operating activity quality parameters: such as jacking displacement and speed indexes of the oil cylinder; 3) The working quality parameters of each procedure are as follows: such as the climbing claw is in place and the beam is in a safe state; 4) The operation safety condition parameters of each procedure are as follows: such as the tower crane deflection, the connection state of the standard section of the tower crane and the like. The tower crane jacking operation flow comprises the following main processes: 1) Preparation (including equipment facility status, safe operation condition check confirmation); 2) Jacking in a trial manner; 3) Jacking for the 1 st time; 4) Lifting a jacking oil cylinder cross beam; 5) Repeating the steps 3) and 4) until the jacking space can be filled with 1 standard knot; 6) Connecting a newly added standard section; 7) And after the safety inspection is confirmed, adding 1 standard section for operation at this time and ending. The tower crane jacking process operation safety monitoring and supervision hierarchy comprises a front-end parameter layer (station work quality safety monitoring-front-end parameter single index state), a parameter multi-mode fusion layer (station work quality safety monitoring-station multi-index comprehensive state), a process multi-mode fusion layer (operation team layer quality safety control-multi-station multi-index comprehensive state) and a process multi-mode fusion layer (project layer quality safety supervision-multi-process multi-index comprehensive quality safety state).
By utilizing the safe state multi-mode real-time intelligent control master machine provided by the invention, parameters monitored by intelligent sensors are selected to be distributed on site: the control module determines a monitoring scene as tower crane jacking operation according to the parameters and calls a corresponding multi-level multi-mode fusion assessment early warning model.
1) Front end parameter layer, the jacking process of 1 st includes that the hydro-cylinder is operated, the operation of jacking crossbeam, the activity climbs 3 stations of claw operation, uses the hydro-cylinder operation station as the example here: the method comprises two parameters of displacement and displacement speed of an oil cylinder piston, wherein the displacement parameter value range is that the stepping distance h +50mm displacement speed is 0-15mm/s. Beyond the warning, the cylinder operator should make corrections immediately.
2) The parameter multi-mode fusion layer (namely the node multi-mode fusion layer) still takes the oil cylinder operation station in the jacking procedure of the 1 st time as an example: the displacement and speed parameter states need to be considered, and generally, any parameter exceeding the standard is dangerous, so a series model can be adopted, namely, the worst parameter state is taken for parameter fusion, namely, as long as one index exceeds the limit, parameter multi-mode state early warning is sent out, the data identification and the quantity value of a problem sensor are output, and a station operator needs to correct the data identification and the quantity value immediately.
3) The procedure multi-mode fusion layer takes the 1 st jacking procedure as an example and comprises an oil cylinder operation station 1, a jacking cross beam operation station 2 and a movable climbing claw operation station 3. The oil cylinder operation station operates and controls the extending length of an oil cylinder piston to be slightly larger than the step height of a standard section and slightly return, the jacking cross beam operation station 2 watches the locking of left and right pin shafts of a cross beam (the logic state index value is 1), the movable climbing claw operation station 3 operates the movable climbing claw, the movable climbing claw is operated to be close to a chord rod of the standard section after crossing the step (the logic state index value is 0), and the oil cylinder piston accurately falls into the step when retracting (the logic state index value is 1). Multi-parameter fusion layer: the station 1 is 2 parameters of displacement and speed of the oil cylinder piston; station 2 is 2 logical switch parameters of a left pin shaft and a right pin shaft of the beam; and the station 3 is a left-right movable climbing claw with 2 logic switch parameters. This process safety multimode except the quality safety of each station, two parameters of environment wind speed and body of the tower slope state during whole hydro-cylinder jacking directly influence this process safety, consequently, to these 3 stations, every station all includes 2 work quality safety parameters plus 2 safety parameters of environment wind speed and body of the tower slope, total 4 safety parameters, from process safety angle, any 1 failure of 4 parameters in each station will lead to the station work to fail, consequently, 3 station multi-parameter fusion all should adopt 4 parameter series models. And, jacking process multimode fusion 1 time, including the multimode fusion to 3 stations, the work quality safety of 3 any 1 stations of station is not conform to and all leads to the failure of this process, but the work quality safety that jacking crossbeam operation station 2 and activity climbed claw operation station 3 has the lethality, can lead to major production incident to take place usually, consequently, including jacking process fusion 1 time can adopt the weighting model, wherein station 1 weight 0.2, station 2 and station 3 are equally important, weight each 0.4.
Taking a jacking cross beam lifting procedure as an example, the jacking cross beam lifting procedure comprises an oil cylinder operation station 1, a jacking cross beam operation station 2 and a movable claw climbing station 3, wherein parameters of each station are the same as parameters of each station of the jacking procedure of the 1 st time in type, but parameter thresholds are different. In the jacking cross beam lifting process: the parameters of the station 1 are oil cylinder piston displacement (the h is reduced to minus 50-0mm for 1 step) and speed parameters (0-15 mm/s); station 2 multi-parameter position left and right beam pin logical state (1 → 0 → 1); and the working position 3 has multiple parameters of a logic state (always 1) of a left movable claw climbing state and a right movable claw climbing state. And considering the environmental wind speed and the tower body inclination parameters which influence the working procedure operation safety, the station quality safety adopts a 4-parameter series model to carry out multi-mode fusion. The multi-mode fusion of the process still suggests the adoption of a weighting model, and the movable paw climbing state in the process is the basis and is most important, so the weights of 3 stations are respectively 0.2, 0.2 and 0.6.
4) And (4) performing multi-mode fusion, wherein the process only considers the two processes of jacking for the 1 st time and jacking up the cross beam as an example. The process quality safety comprises a process quality safety multi-mode state, a tower crane structural component connecting state which influences the process operation quality safety, a tower crane rotation braking state, a jacking operator on duty and other factors, therefore, in the process safety multi-mode fusion, process operation safety condition indexes comprising 3 parameters of structural component connection, rotation braking and jacking operator on duty need to be added, and the process safety multi-mode fusion is carried out according to a series model with the 1 st jacking process and the jacking cross beam lifting process respectively. The process multi-mode safety comprises a 1 st jacking process and a jacking cross beam lifting process, and a series fusion model is adopted.
The embodiment of the invention provides a multi-mode real-time intelligent management and control method for a safety state, which is applied to a control module for managing and controlling a master machine in any one of the embodiments and comprises the following steps:
determining a monitoring scene according to monitoring parameters selected by a user, calling a multi-level multi-modal fusion assessment early warning model corresponding to the monitoring scene, and carrying out safety assessment early warning by combining real-time monitoring values of the monitoring parameters;
the multi-level multi-mode fusion assessment early warning model comprises a node-level mode fusion layer, a process-level mode fusion layer and a process-level mode fusion layer from bottom to top;
the node-level modal fusion layer is used for judging whether each node has a safety risk or not according to the real-time monitoring value and a preset threshold value of the monitoring parameter of each node, alarming if the node has the safety risk, and calculating the safety evaluation value of each node;
the process-level modal fusion layer is used for calculating the safety assessment values of all the processes according to the safety assessment values of all the nodes so as to judge whether safety risks exist in all the processes or not, and if so, alarming is carried out;
and the process level modal fusion layer is used for judging whether each process has a safety risk or not according to the safety assessment score of each process, and if so, giving an alarm.
The embodiment of the invention provides a multi-mode real-time intelligent management and control system for a safety state, which is characterized by comprising the following steps: a computer-readable storage medium and a processor;
the computer-readable storage medium is used for storing executable instructions;
the processor is configured to read executable instructions stored in the computer-readable storage medium and execute the method according to the above embodiment.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. The utility model provides a female machine of real-time intelligent management and control of safe state multimode, which characterized in that includes: the device comprises a parameter selection module, a data transceiving module and a control module;
the parameter selection module is used for a user to select monitoring parameters;
the data transceiver module is used for receiving the real-time monitoring value of the monitoring parameter selected by the user and sending the real-time monitoring value to the control module;
the control module is embedded with a plurality of multi-level multi-modal fusion assessment early warning models corresponding to different monitoring scenes and used for determining the monitoring scenes according to monitoring parameters selected by a user, calling the multi-level multi-modal fusion assessment early warning models corresponding to the monitoring scenes and carrying out safety assessment early warning by combining real-time monitoring values of the monitoring parameters;
the multi-level multi-mode fusion assessment early warning model comprises a node-level mode fusion layer, a process-level mode fusion layer and a process-level mode fusion layer from bottom to top;
the node-level modal fusion layer is used for judging whether each node has a safety risk or not according to the real-time monitoring value and a preset threshold value of the monitoring parameter of each node, alarming if the node has the safety risk, and calculating the safety evaluation value of each node;
the process-level modal fusion layer is used for calculating the safety assessment values of all the processes according to the safety assessment values of all the nodes so as to judge whether safety risks exist in all the processes or not, and if so, alarming is carried out;
and the process-level modal fusion layer is used for judging whether each process has a safety risk or not according to the safety assessment score of each process, and alarming if the process has the safety risk.
2. The master of claim 1, wherein the node-level modal fusion layer employs a tandem fusion model: when any monitoring parameter of the node exceeds a preset threshold, the node is determined to have a safety risk, the safety assessment score of the node is 100, or the safety assessment score of the node is determined according to the percentage exceeding the preset threshold.
3. The master machine of claim 2, wherein the process-level modal fusion layer employs a weighted fusion model: and calculating the weighted score of the process according to the weight and the score of the nodes included in the process, and if the weighted score exceeds a preset risk threshold, determining that the process has a safety risk.
4. The master of claim 3, wherein the process-level modal fusion layer employs a tandem fusion model: and when any procedure of the flow has a safety risk, the flow is determined to have the safety risk.
5. The master of claim 1, further comprising a modality extension module for user extension or selection of monitoring parameters, nodes, procedures or processes.
6. A multi-modal real-time intelligent management and control method for a safety state is applied to the control module for managing and controlling the mother machine according to any one of claims 1 to 5, and is characterized by comprising the following steps:
determining a monitoring scene according to monitoring parameters selected by a user, calling a multi-level multi-modal fusion assessment early warning model corresponding to the monitoring scene, and carrying out safety assessment early warning by combining real-time monitoring values of the monitoring parameters;
the multi-level multi-mode fusion assessment early warning model comprises a node-level mode fusion layer, a process-level mode fusion layer and a process-level mode fusion layer from bottom to top;
the node-level modal fusion layer is used for judging whether each node has a safety risk or not according to the real-time monitoring value and a preset threshold value of the monitoring parameter of each node, alarming if the node has the safety risk, and calculating the safety evaluation value of each node;
the process-level modal fusion layer is used for calculating the safety assessment values of all the processes according to the safety assessment values of all the nodes so as to judge whether safety risks exist in all the processes or not, and if so, alarming is carried out;
and the process-level modal fusion layer is used for judging whether each process has a safety risk or not according to the safety assessment score of each process, and alarming if the process has the safety risk.
7. The utility model provides a real-time intelligent management and control system of security state multimode which characterized in that includes: a computer-readable storage medium and a processor;
the computer-readable storage medium is used for storing executable instructions;
the processor is configured to read executable instructions stored in the computer-readable storage medium and execute the method of claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211441277.9A CN115729186B (en) | 2022-11-17 | 2022-11-17 | Multi-mode real-time intelligent control host machine, method and system for safety state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211441277.9A CN115729186B (en) | 2022-11-17 | 2022-11-17 | Multi-mode real-time intelligent control host machine, method and system for safety state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115729186A true CN115729186A (en) | 2023-03-03 |
| CN115729186B CN115729186B (en) | 2023-08-25 |
Family
ID=85296323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211441277.9A Active CN115729186B (en) | 2022-11-17 | 2022-11-17 | Multi-mode real-time intelligent control host machine, method and system for safety state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115729186B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060074704A1 (en) * | 2004-10-01 | 2006-04-06 | Microsoft Corporation | Framework to model cross-cutting behavioral concerns in the workflow domain |
| CN104820995A (en) * | 2015-04-21 | 2015-08-05 | 重庆大学 | Large public place-oriented people stream density monitoring and early warning method |
| CN108345994A (en) * | 2018-02-05 | 2018-07-31 | 华中科技大学 | A kind of acquisition of work progress security knowledge, expression and the course monitoring method of structuring |
| CN109143984A (en) * | 2017-06-27 | 2019-01-04 | 中国石油化工股份有限公司 | A kind of multi-layer control device and method preventing shift-converter temperature runaway |
| CN109360384A (en) * | 2018-11-22 | 2019-02-19 | 华中科技大学 | A kind of the front end early warning system and method for engineering structure safe condition |
| CN109375594A (en) * | 2018-10-10 | 2019-02-22 | 杭州润缘信息科技有限公司 | Urban safety wisdom control platform and managing and control system |
| US20200202471A1 (en) * | 2017-09-25 | 2020-06-25 | New Go - Arc (2015) Ltd. | Personalized display of real-time safety information of an industrial environment |
| CN113095638A (en) * | 2021-03-26 | 2021-07-09 | 华中科技大学 | Program type operation construction navigation and safety monitoring system and method |
| EP3885972A1 (en) * | 2020-03-24 | 2021-09-29 | Siemens Aktiengesellschaft | Context based perception method and system for managing environmental safety in a computing environment |
| CN114527717A (en) * | 2022-02-25 | 2022-05-24 | 苏州盛虹数云科技有限公司 | Chemical safety production early warning system and safety early warning method thereof |
| KR102413257B1 (en) * | 2021-09-29 | 2022-06-27 | 주식회사 휴랜 | Smart safety management system for construction sites with generality and scalability |
| CN115169779A (en) * | 2022-05-12 | 2022-10-11 | 国家电投集团内蒙古能源有限公司 | Enterprise safety risk early warning prediction system and method |
| CN115330129A (en) * | 2022-07-15 | 2022-11-11 | 国能黄骅港务有限责任公司 | Enterprise safety risk early warning analysis method and system |
-
2022
- 2022-11-17 CN CN202211441277.9A patent/CN115729186B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060074704A1 (en) * | 2004-10-01 | 2006-04-06 | Microsoft Corporation | Framework to model cross-cutting behavioral concerns in the workflow domain |
| CN104820995A (en) * | 2015-04-21 | 2015-08-05 | 重庆大学 | Large public place-oriented people stream density monitoring and early warning method |
| CN109143984A (en) * | 2017-06-27 | 2019-01-04 | 中国石油化工股份有限公司 | A kind of multi-layer control device and method preventing shift-converter temperature runaway |
| US20200202471A1 (en) * | 2017-09-25 | 2020-06-25 | New Go - Arc (2015) Ltd. | Personalized display of real-time safety information of an industrial environment |
| CN108345994A (en) * | 2018-02-05 | 2018-07-31 | 华中科技大学 | A kind of acquisition of work progress security knowledge, expression and the course monitoring method of structuring |
| CN109375594A (en) * | 2018-10-10 | 2019-02-22 | 杭州润缘信息科技有限公司 | Urban safety wisdom control platform and managing and control system |
| CN109360384A (en) * | 2018-11-22 | 2019-02-19 | 华中科技大学 | A kind of the front end early warning system and method for engineering structure safe condition |
| EP3885972A1 (en) * | 2020-03-24 | 2021-09-29 | Siemens Aktiengesellschaft | Context based perception method and system for managing environmental safety in a computing environment |
| CN113095638A (en) * | 2021-03-26 | 2021-07-09 | 华中科技大学 | Program type operation construction navigation and safety monitoring system and method |
| KR102413257B1 (en) * | 2021-09-29 | 2022-06-27 | 주식회사 휴랜 | Smart safety management system for construction sites with generality and scalability |
| CN114527717A (en) * | 2022-02-25 | 2022-05-24 | 苏州盛虹数云科技有限公司 | Chemical safety production early warning system and safety early warning method thereof |
| CN115169779A (en) * | 2022-05-12 | 2022-10-11 | 国家电投集团内蒙古能源有限公司 | Enterprise safety risk early warning prediction system and method |
| CN115330129A (en) * | 2022-07-15 | 2022-11-11 | 国能黄骅港务有限责任公司 | Enterprise safety risk early warning analysis method and system |
Non-Patent Citations (9)
| Title |
|---|
| DONGPING FANG 等: "Load distribution assessment of reinforced concrete buildings during construction with structural characteristic parameter approach", TSINGHUA SCIENCE AND TECHNOLOGY * |
| HAIPENG WANG 等: "Research and Application of Artificial Technology for Substation Environment Surveillance System", 2019 IEEE 8TH JOINT INTERNATIONAL INFORMATION TECHNOLOGY AND ARTIFICIAL INTELLIGENCE CONFERENCE(ITAIC) * |
| SHUANGPIN LI 等: "Research on intelligent monitoring system of hydraulic engineering based on digital twin", 2021 7TH INTERNATIONAL CONFERENCE ON HYDRAULIC AND CIVIL ENGINEERING & SMART WATER CONSERVANCY AND INTELLIGENT DISASTER REDUCTION FORUM(ICHCE & SWIDR) * |
| 张伟 等: "基于物联网的塔式起重机安全监控系统", 中国安全科学学报, pages 55 - 62 * |
| 张充 等: "塔式起重机结构安全监测参数选取及测点布置", 中国安全科学学报 * |
| 林湘宁 等: "基于风机主动控制的风电场低电压穿越能力深度挖掘研究", 中国电机工程学报 * |
| 王鹏飞: "多控制功能电表关键技术研究", 中国优秀硕士学位论文全文数据库 工程科技II辑 * |
| 赵挺生 等: "基于多空间过程状态转移的塔吊顶升导航系统", 土木工程与管理学报 * |
| 阮斯洁;刘检华;唐承统;庄存波;周子岩;: "面向复杂产品装配的多维度工艺数据管理系统", 计算机集成制造系统, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115729186B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10019892B1 (en) | Risk assessing and managing system and related method | |
| US20060142990A1 (en) | Information processor, state judging unit and diagnostic unit, information processing method, state judging method and diagnosing method | |
| CN112291735A (en) | UWB-based visual engineering intelligent monitoring system and method | |
| CN105023384A (en) | Fire-fighting safety early warning alarm system and method based on data excavation and data analysis | |
| CN113409546A (en) | Method for evaluating safety state of personnel on construction site of building engineering | |
| CN112357768A (en) | Device and method for monitoring lifting condition of tower material | |
| CN115659673B (en) | Bridge construction process safety monitoring system based on unmanned aerial vehicle image | |
| CN106338275B (en) | A kind of intelligence ocean platform system | |
| WO2024045539A1 (en) | Test method and system for autonomous berthing and unberthing of under-actuated merchant ship | |
| CN115729186A (en) | Safety state multi-mode real-time intelligent control master machine, method and system | |
| CN108762305B (en) | Unmanned aerial vehicle collision avoidance aerial vehicle makes somebody a mere figurehead alternating current power line's early warning device | |
| KR102463138B1 (en) | System and method for warning of accident on agrcultural machinery vehicle | |
| CN113702584A (en) | Method, system and device for remotely monitoring and alarming gas in tunnel construction process and computer readable storage medium | |
| CN115551060B (en) | Low-power-consumption data monitoring method | |
| CN105116851B (en) | Hidden troubles removing information physical emerging system | |
| CN117495157A (en) | Coal mine goaf karst tunnel full-period construction characteristic information fusion and quality tracing system | |
| CN117196296A (en) | Railway weather disaster risk prevention and control method and system | |
| CN113565570B (en) | Index setting method for water damage early warning | |
| CN115550406A (en) | Production emergency command management system and method | |
| CN112519798A (en) | Unmanned system based on 5G network | |
| CN101192336A (en) | Building structure stability monitoring and pre-alarming method, and its device | |
| CN111967188A (en) | Electrical control system with network communication function | |
| AU2020294402A1 (en) | A method and an arrangement for managing and controlling the lifetime of a tree handling system for a forest machine | |
| CN117634895B (en) | Non-coal mine safety dynamic risk assessment system and assessment method thereof | |
| CN115788390B (en) | Remote monitoring method for carbon dioxide fracturing auxiliary pressurizing device |
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 |