CN114859839A - Coal production safety monitoring system and method - Google Patents
Coal production safety monitoring system and method Download PDFInfo
- Publication number
- CN114859839A CN114859839A CN202210522475.1A CN202210522475A CN114859839A CN 114859839 A CN114859839 A CN 114859839A CN 202210522475 A CN202210522475 A CN 202210522475A CN 114859839 A CN114859839 A CN 114859839A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- safety
- model
- alarm information
- alarm
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/34—Director, elements to supervisory
- G05B2219/34457—Emit alarm signal
-
- 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
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a coal production safety monitoring system and a method, relating to the technical field of safety monitoring, wherein the system comprises a knowledge base module, an intelligent sensing module and a service processing module; the knowledge base module stores security knowledge content and a security knowledge map; the intelligent sensing module is used for carrying out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content and sending alarm information to the service processing module when abnormal conditions are monitored; the service processing module is used for eliminating the received alarm information according to the safety knowledge content and the safety knowledge map; and the knowledge base module is used for updating the safety knowledge information according to the processing result of the alarm information by the service processing module. The invention reduces manual intervention and improves the automation level and the intelligence level in the coal production process.
Description
Technical Field
The invention relates to the technical field of safety monitoring, in particular to a coal production safety monitoring system and a coal production safety monitoring method.
Background
In the production process of the coal industry, safety is a relatively complex problem, the arrangement of a pipe network type and a nearly closed structure of a coal mine underground excavation production system are adopted, and various disaster factors such as gas, ground pressure, water, fire, coal dust and the like coexist in the coal mine, so that various disaster accidents are easily caused in the coal mine. Once a disaster accident occurs, other disasters are easily caused to accompany or couple, so that emergency treatment and rescue become complicated and difficult. Therefore, it is very important and necessary to improve the level of automation and safety control in the coal industrial production process.
In recent years, with the development of deep learning technology and the continuous improvement of automation level, more and more intelligent monitoring devices are used in the coal production process for intelligently monitoring and identifying the coal production process. However, in most of the systems, the automation level and the intelligence level of the security monitoring are still low.
Disclosure of Invention
The invention aims to provide a coal production safety monitoring system and a coal production safety monitoring method, which aim to improve the automation level and the intelligent level in the coal production process.
In a first aspect, the embodiment of the invention provides a coal production safety monitoring system, which comprises a knowledge base module, an intelligent sensing module and a service processing module; the knowledge base module stores safety knowledge information, and the safety knowledge information comprises safety knowledge content and a safety knowledge map;
the intelligent sensing module is used for carrying out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content and sending alarm information to the service processing module when abnormal conditions are monitored;
the service processing module is used for eliminating the received alarm information according to the safety knowledge content and the safety knowledge map;
and the knowledge base module is used for updating the safety knowledge information according to the processing result of the alarm information by the service processing module.
Further, the business processing module comprises a risk management and control model, a hidden danger management model and an accident management model; the service processing module is specifically configured to:
the risk control model generates a first control instruction corresponding to the alarm information according to an initial emergency plan in the safety knowledge content, and eliminates the alarm information through the first control instruction;
after the processing of the risk control model, when the alarm information is not eliminated, the hidden danger management model infers the reason of the alarm according to the safety knowledge map, generates a second control instruction according to the inference result, and eliminates the alarm information through the second control instruction;
and after the hidden danger treatment model is processed, when the alarm information is not eliminated, the accident management model analyzes and summarizes the abnormal conditions to generate a new emergency plan, and provides the new emergency plan for the risk management and control model until the alarm information is eliminated.
Further, the alarm information comprises one or more of belt deviation alarm, belt no-load alarm, belt tearing alarm, belt coal piling alarm, foreign matter alarm, water coal alarm, bulk coal alarm and personnel violation alarm.
Furthermore, the intelligent sensing module is also used for acquiring a first feedback result of the user on the safety monitoring result and optimizing the corresponding recognition model according to the first feedback result; the business processing module is further used for obtaining a second feedback result of the decision output by the user on the risk management and control model, the hidden danger management model and the accident management model, and optimizing the risk management and control model, the hidden danger management model and the accident management model according to the second feedback result.
Further, the knowledge base module is specifically used for performing adaptive dynamic optimization on the safety knowledge information according to the processing result of the service processing module on the alarm information and the second feedback result; automatically associating and supplementing unknown security problems according to the first feedback result so as to realize self-learning of security knowledge information; and tracking the hotspot knowledge according to the statistical result of the knowledge reference degree, and maintaining the fragment knowledge so as to realize the self-evolution of the safety knowledge information.
Further, the safety knowledge information also comprises a safety knowledge scene constructed on the basis of the safety knowledge content and the safety knowledge graph, and the safety knowledge scene is used for being called by the intelligent perception module and the service processing module.
Furthermore, the intelligent sensing module is specifically used for acquiring one or more of real-time data of personnel, equipment and environment in the coal production process through a digital device, and performing identification processing on abnormal conditions on the real-time data through a pre-trained identification model, wherein the digital device comprises one or more of a wearable device, a positioning device, a sensor and a camera device.
In a second aspect, an embodiment of the present invention further provides a coal production safety monitoring method, which is applied to the coal production safety monitoring system in the first aspect, and the coal production safety monitoring method includes:
the intelligent sensing module carries out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content, and sends alarm information to the service processing module when monitoring that an abnormal condition occurs;
the service processing module carries out elimination processing on the received alarm information according to the safety knowledge content and the safety knowledge map;
and the knowledge base module updates the safety knowledge information according to the processing result of the alarm information by the service processing module.
Further, the business processing module comprises a risk management and control model, a hidden danger management model and an accident management model; the service processing module eliminates and processes the received alarm information according to the safety knowledge content and the safety knowledge map, and comprises the following steps:
the risk control model generates a first control instruction corresponding to the alarm information according to an initial emergency plan in the safety knowledge content, and eliminates the alarm information through the first control instruction;
after the processing of the risk control model, when the alarm information is not eliminated, the hidden danger management model infers the reason of the alarm according to the safety knowledge map, generates a second control instruction according to the inference result, and eliminates the alarm information through the second control instruction;
and after the hidden danger treatment model is processed, when the alarm information is not eliminated, the accident management model analyzes and summarizes the abnormal conditions to generate a new emergency plan, and provides the new emergency plan for the risk management and control model until the alarm information is eliminated.
Further, the coal production safety monitoring method further comprises the following steps:
the intelligent sensing module acquires a first feedback result of a user on a safety monitoring result, and optimizes a corresponding recognition model according to the first feedback result;
and the business processing module acquires a second feedback result of the decision output by the user on the risk management and control model, the hidden danger management model and the accident management model, and optimizes the risk management and control model, the hidden danger management model and the accident management model according to the second feedback result.
In the coal production safety monitoring system and the method provided by the embodiment of the invention, the coal production safety monitoring system comprises a knowledge base module, an intelligent sensing module and a service processing module; the knowledge base module stores safety knowledge information, and the safety knowledge information comprises safety knowledge content and a safety knowledge map; the intelligent sensing module is used for carrying out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content and sending alarm information to the service processing module when abnormal conditions are monitored; the service processing module is used for eliminating the received alarm information according to the safety knowledge content and the safety knowledge map; and the knowledge base module is used for updating the safety knowledge information according to the processing result of the alarm information by the service processing module. Therefore, the safety knowledge map is introduced into the coal production safety monitoring system, the automatic elimination processing of the alarm information transmitted by the intelligent sensing module is realized on the basis of the safety knowledge content and the safety knowledge map, and meanwhile, the knowledge base module can also automatically update the safety knowledge information, so that the manual intervention is reduced, and the automation level and the intelligence level in the coal production process are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic structural diagram of a coal production safety monitoring system according to an embodiment of the present invention;
FIG. 2 is a block diagram of an overall architecture of a library with three rings according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a self-optimizing knowledge base according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a closed loop of a human-machine cooperative decision control according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a single-service-link closed loop according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a knowledge base and AI enabling process provided by an embodiment of the invention;
fig. 7 is a schematic diagram of a closed loop of a full service chain according to an embodiment of the present invention;
fig. 8 is a schematic flow chart of a coal production safety monitoring method according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the coal production process, it is very necessary to monitor the whole production process safely and effectively. In recent years, with the continuous improvement of deep learning technology, more and more enterprises apply the image video processing technology based on deep learning to automatic monitoring so as to automatically monitor the whole production process. Although the automation level is improved to a certain extent in this way, most of the existing systems only stay in the aspect of intelligent perception, the degree of "intelligence" is far from enough, when there is a potential security risk or when a security accident occurs, judgment and prediction cannot be automatically performed, and still manual judgment and decision making are required, and the automation and intelligence level of security management and control is low and a complete system is not formed. In order to solve the above problems, embodiments of the present invention provide a coal production safety monitoring system and method, which introduces a knowledge map into an intelligent monitoring technology based on deep learning, and constructs a complete intelligent safety control system including an intelligent sensing module and a service processing module for implementing intelligent decision, intelligent tracing and the like based on the knowledge map and a rule engine and based on deep learning and a related artificial intelligence algorithm as main technical means.
For the convenience of understanding the embodiment, a detailed description will be given to a coal production safety monitoring system disclosed in the embodiment of the present invention.
Referring to the schematic structural diagram of a coal production safety monitoring system shown in fig. 1, the coal production safety monitoring system includes a knowledge base module 110, an intelligent sensing module 120 and a business processing module 130; the knowledge base module 110 stores security knowledge information, wherein the security knowledge information comprises security knowledge content and a security knowledge map; the intelligent sensing module 120 is configured to perform real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content, and send alarm information to the service processing module 130 when an abnormal condition is monitored; the service processing module 130 is configured to perform elimination processing on the received alarm information according to the security knowledge content and the security knowledge map; the knowledge base module 110 is used for updating the safety knowledge information according to the processing result of the alarm information by the service processing module.
According to the coal production safety monitoring system provided by the embodiment of the invention, the safety knowledge map is introduced into the coal production safety monitoring system, the automatic elimination processing of the alarm information transmitted by the intelligent sensing module is realized on the basis of the safety knowledge content and the safety knowledge map, and meanwhile, the knowledge base module can also automatically update the safety knowledge information, so that the manual intervention is reduced, and the automation level and the intelligence level in the coal production process are improved.
In the coal production safety monitoring system provided by the embodiment of the invention, a knowledge base is a foundation, an artificial intelligence technology is a means, and the coal production safety monitoring system has the core characteristics of one base and three rings, wherein the one base refers to the construction of the knowledge base, the safety knowledge content, the safety knowledge map and the corresponding safety knowledge scene are used as priori knowledge to construct the brain of the whole system, and the brain is used for comprehensively analyzing, predicting, making decision, reasoning and tracing the data transmitted by the sensing layer where the intelligent sensing module 120 is located, and running through the whole production process; the three-loop is closed-loop operation in three production processes formed on the basis of a knowledge base, namely a man-machine cooperative decision control closed loop, a single service link closed loop and a full service chain closed loop. Through the design of the system architecture and the functions, good automatic safety control can be realized for each link in the production process, and the whole process is a complete link.
In order to implement the above functions, the present embodiment mainly relates to the following contents: intelligent sensing, intelligent processing, intelligent decision making, and knowledge base construction and optimization. The main core part is the construction of a knowledge base and the combination of an Artificial Intelligence (AI) module, so that a one-base three-ring framework is formed, and control decisions are continuously optimized under the guidance of a rule base.
The present embodiment mainly relates to the following parts: digitalization of personnel, equipment and environment, construction of an AI module and a knowledge base, man-machine cooperative decision control closed loop, single service link closed loop and full service chain closed loop, which are specifically as follows:
1) the digitization of personnel, equipment and environment is realized more comprehensively. Real-time data of the person, the device and the environment can be acquired through a wearable device (corresponding to the person), a positioning device (corresponding to the person), a sensor (corresponding to the device and/or the environment), a camera device (corresponding to one or more of the person, the device and the environment), and the like, which is a data base of the whole system.
2) And (5) building a self-optimized knowledge base. The knowledge base is the brain of the whole system, stores a large amount of information and rules, and comprises a major hazard source information base, an enterprise safety standardization information base, a safety production accident hidden danger information base, a safety knowledge base and an operation standard process base. Compared with the knowledge base in the traditional sense, the knowledge base provided by the embodiment is not static, can be continuously updated and self-optimized in the decision making process according to the interaction between the AI model and the personnel, and is dynamic.
3) And (3) controlling closed loop by man-machine cooperative decision based on a knowledge base. In the existing methods, the decision is often made by a machine or a person, the decision made by the machine mainly depends on a fixed rule and cannot be changed according to the change of the environment and the actual situation; human decision making is largely empirical, lacking assistance from machines and efficient data analysis. Therefore, the embodiment provides a control method for cooperatively making decisions by a machine and a person, and the decisions made by the machine based on a rule base and the decisions specified by the person are mutually optimized, so that an optimal control decision is obtained.
4) The single service link is closed loop. For the management links of a single service in the production process, closed loops are realized in a plurality of service links such as risk control (a risk management and control model), hidden danger treatment (a hidden danger treatment model), emergency and accident management (an accident management model), namely, the service links in each management link are closed loops.
5) The full service chain is closed. The method mainly realizes the coordination processing of risk management and control, hidden danger management and accident management of a plurality of services (such as belt deviation alarm, belt no-load alarm and the like).
Next, the overall architecture of the system is introduced, and a "one-library three-loop" in the scheme is explained from the overall framework and the flow, so that the automated design of the system is clearly understood; the details of the various parts of the modules in the architecture are then described in detail.
The overall architecture of the system is shown in fig. 2, and as can be seen from fig. 2, the overall architecture follows the logic of "PDCA" on the basis of the knowledge base. Specifically, in "D (execution)", firstly, real-time monitoring of people, equipment and environment in production is realized by using a pre-trained AI model, for example, detection and recognition of foreign matters in a belt, water and coal, belt deviation, belt tearing, illegal operation of people, and the like, i.e., intelligent perception is realized by using a detection model (recognition model) based on deep learning. When the abnormal condition is detected, the alarm is given immediately, and meanwhile, automatic control can be performed. For example, after the belt deviation is detected by the belt deviation model, an alarm is given and a suggested decision of stopping is given. Note that the proposed decision to shutdown here is given in "P (plan)".
Next, the smart sensor module 120 transmits the deviation warning information to the service processing module 130 (i.e., "AI risk management and control, AI hidden danger control" … … in fig. 2). The service processing module 130 performs a series of operations such as risk management and control, hidden danger management, accident management, and the like on the alarm information, and gives a final decision. For example, for belt deviation abnormal alarm information, a risk control model gives a preliminary control instruction, and if the instruction does not remove the alarm information, a hidden danger treatment link is entered at the moment; in the hidden danger management link, the hidden danger management model combines the knowledge map in the knowledge base module 110 to reason the reasons which may cause abnormal alarm (for example, the found reasons are caused by different rotating speeds of the left and right machines), and gives a corresponding control instruction according to the reasoning result, if the alarm information is not released at the moment, the accident management link is entered; in the accident management link, the accident management model analyzes and summarizes the abnormal conditions and provides a final decision scheme of the AI model.
Then, in the step C, the influence of the decision scheme in the actual production process is evaluated by indexes in the knowledge base, and then in the step A, the system optimizes the decision according to the evaluation result.
Based on this, the service processing module 130 includes a risk management and control model, a hidden danger management and control model, and an accident management model; the service processing module 130 is specifically configured to:
the risk control model generates a first control instruction corresponding to the alarm information according to an initial emergency plan in the safety knowledge content, and eliminates the alarm information through the first control instruction;
after the processing of the risk control model, when the alarm information is not eliminated, the hidden danger management model infers the reason of the alarm according to the safety knowledge map, generates a second control instruction according to the inference result, and eliminates the alarm information through the second control instruction;
and after the hidden danger treatment model is processed, when the alarm information is not eliminated, the accident management model analyzes and summarizes the abnormal conditions to generate a new emergency plan, and provides the new emergency plan for the risk management and control model until the alarm information is eliminated.
The intelligent sensing module 120 is further configured to obtain a first feedback result of the user on the safety monitoring result, and perform optimization of the corresponding recognition model according to the first feedback result; the service processing module 130 is further configured to obtain a second feedback result of the decision output by the user on the risk management and control model, the hidden danger management model, and the accident management model, and optimize the risk management and control model, the hidden danger management model, and the accident management model according to the second feedback result.
The functions of the various parts are described in detail below:
(1) intelligent sensing
The part is mainly to realize the monitoring of important component elements in the production processes of personnel, belts, equipment and the like through wearable equipment, positioning equipment, sensors, camera equipment and the like. The real-time processing of video images and the like in the production process is mainly realized through an AI (artificial intelligence) recognition algorithm, and intelligent perception is realized. For example, the identification and monitoring of the follow-up frame moving process, the straightening of the scraper, the hydraulic support side protection state, the tail scraper running state, the belt foreign matter, the belt tearing, the personnel crossing into the dangerous area and the like are realized through an AI identification algorithm. Wherein, move a process discernment with the machine and indicate: intelligently identifying the working procedure connection states of the position and the running direction of a coal mining machine, the coal quantity and the speed of a scraper conveyor, the folding and unfolding of a rib spalling plate and a rib protecting plate and the like in a coal mining operation area, and reminding centralized control personnel to intervene by abnormal acousto-optic alarm; the scraper straightening identification finger: intelligently identifying the working face scraper straightening condition, and directly ensuring that the working face is three straight and two flat as far as possible in the current coal mining process; monitoring of the state of the hydraulic support protective wall is as follows: the hydraulic support side protection state of the working face is intelligently identified, the side protection plate is found to be abnormal, centralized control personnel are reminded of processing the abnormal side protection plate in time, and large-area side wall spalling caused by the fact that the side protection plate cannot protect the side is avoided; the tail scraper blade running state monitoring indicates: abnormal states such as lack of scraper blade, broken chain, oblique chain in the operation of intelligent recognition working face scraper conveyor inform maintainer in time to handle.
Based on this, the intelligent sensing module 120 is specifically configured to obtain real-time data of one or more of personnel, equipment, and an environment in a coal production process through a digital device, and perform identification processing on the real-time data of an abnormal situation through a pre-trained identification model, where the digital device includes one or more of a wearable device, a positioning device, a sensor, and a camera device.
(2) Self-optimizing knowledge base
The knowledge base is an important component of a one-base three-loop system, contains various rules and knowledge in the production link, is equivalent to the brain of the whole system, and is a decision maker of the whole system. In the traditional approach, the knowledge base is static and is not updated. For example, the belt deviation model stops when it detects a deviation value exceeding a specified value, and this rule knowledge is constant in any case. Even if this situation is a belt deviation model false alarm, the whole system will perform. Obviously, such a static knowledge base is not reasonable.
Thus, in this embodiment, a dynamic self-optimizing knowledge base is constructed. As shown in fig. 3, the knowledge base content mainly includes three main components, namely, security knowledge content, security knowledge graph, and security knowledge scene. The safety knowledge content introduces business related knowledge, namely examination training, operation standards, risk management and control, safety regulation and regulations and the like (for example, when a belt runs, a worker cannot enter a specified dangerous area). The safety knowledge graph mainly refers to a relationship network among all services, and includes causal relationships among events, so that the cause (tracing) of the occurrence of the safety event and the subsequent possible results are found according to the causal relationships, and a corresponding solution is provided. The safety knowledge scene is constructed on the basis of the safety knowledge content and the safety knowledge map and is used for realizing risk management and control, hidden danger treatment, accident management, emergency management and the like of a specific application scene. Meanwhile, the risk management and control, hidden danger treatment, accident management and emergency management can feed corresponding results back to the knowledge base to update the related contents of the safety knowledge content, the safety knowledge map and the safety knowledge scene, so that the dynamic update of the knowledge base is realized.
Based on this, the above-mentioned security knowledge information further includes a security knowledge scene constructed on the basis of the security knowledge content and the security knowledge graph, and the security knowledge scene is used for being invoked by the smart sensing module 120 and the service processing module 130.
The self-optimization knowledge base means that the knowledge base can realize the functions of self-optimization, self-learning, self-evolution and the like. The three functions are to update the knowledge base according to the corresponding feedback results of 'risk management and control, hidden danger management, accident management and emergency management' of abnormal events.
1. Self-optimization
The self-optimization refers to the self-adaptive dynamic optimization of the knowledge base based on the feedback results of key activities such as risk management and control, hidden danger management, accident management and the like. For example, taking belt deviation as an example, after the belt deviation identification error identifies deviation and sends alarm information, in a man-machine cooperation decision link described below, a person can give corresponding feedback to a deviation identification model according to a real situation, so that a knowledge base is also updated at any time.
2. Self-learning
Self-learning refers to automatic association and supplementation of unknown security problems, gradual maintenance of knowledge arrays, and formation of knowledge maps and knowledge sediments. The automatic association refers to that two events which originally do not have any relationship (namely are not connected) in the knowledge graph are associated by finding a certain relationship between the two events through a feedback result of the key activity. For example, assume that the following relationships exist in the original knowledge graph: the 'belt overload' causes 'the life of the belt to be shortened', 'the belt to be scratched by a large stone' causes 'the belt to be torn', 'the belt to be torn' and 'the life of the belt to be shortened' have a causal relationship with each other, and the 'belt overload' and 'the belt to be scratched by a large stone' have no relationship with each other; however, when the system issues a "belt tearing" anomaly alarm, and a series of traceability findings are made to indicate that the belt is overloaded, the knowledge map is updated to establish a connection between the belt and the knowledge map.
3. Self-evolution
"self-evolution" refers to tracking hotspot knowledge and maintaining fragment knowledge based on the statistical result of knowledge reference degree. For example, if the abnormal condition of belt tearing is counted according to the reason causing the abnormal condition to occur in a given period, the ratio of safety knowledge of belt use time being too long is quoted to reach 80%, the safety knowledge of belt use time being too long belongs to hot spot knowledge, and we keep track of the hot spot knowledge for a long time and learn the change trend of the hot spot knowledge in the connection of the knowledge map; the safety knowledge that the belt is scratched and torn by a large coal mine only accounts for 1%, the belt belongs to knowledge fragments, and people only need to maintain the connection between the belt and the belt tearing, and do not need to learn specially.
Based on this, the knowledge base module 110 is specifically configured to perform adaptive dynamic optimization on the safety knowledge information according to the processing result of the service processing module 130 on the alarm information and the second feedback result; automatically associating and supplementing unknown security problems according to the first feedback result so as to realize self-learning of security knowledge information; and tracking the hotspot knowledge according to the statistical result of the knowledge reference degree, and maintaining the fragment knowledge so as to realize the self-evolution of the safety knowledge information.
(3) Man-machine cooperative decision control closed loop
With the development of the AI technology, discovery and alarm of potential safety hazards are realized mainly by using the mode of the AI technology and a static knowledge base, and autonomous decision is made. For ease of understanding, we will describe the monitoring of anomalies in the belt and the automatic control as examples. The method comprises the steps of firstly, detecting and identifying the deviation, foreign matters, large coal mines, water coal, personnel violation, belt tearing and the like in the belt by utilizing a pretrained AI identification algorithm based on deep learning, and realizing intelligent sensing. And when the monitoring value obtained by the AI identification algorithm exceeds the value specified in the knowledge base, alarming and performing corresponding autonomous control. For example, in the belt deviation identification, the belt deviation amount, the alarm value and the stop value are set based on a belt machine deviation identification model, the system alarms in time after identifying that the belt machine deviation value reaches the defined alarm value, and the system is linked with the belt centralized control system to stop after identifying that the belt machine deviation value reaches the defined stop value. It should be noted that the belt deviation, the alarm value and the stop value are specified (unchanged) in the knowledge base, and the automatic control decisions such as stop and the like are also executed according to the static knowledge in the rule base which is set in advance, that is, when the AI model detects that the deviation exceeds the specified range, the operation of stop is simply and roughly performed. This simple "shutdown" is not an optimal control strategy, as the shutdown process also involves significant energy consumption and is detrimental to the efficiency of the production process. Therefore, for risk management and control in the production process, the mode of relying on only manual work or only "AI technology + static knowledge base" is not the optimal choice.
In this embodiment, we combine human and AI technologies to realize "man-machine cooperative decision control closed loop". The closed loop is a mode of 'AI technology + dynamic knowledge base', namely, the learning ability of an AI model and the rules and execution strategies in the knowledge base are continuously optimized by using the experience and operation of people, so that the dynamic knowledge base in the decision making process is realized. The whole process is realized by reinforcement learning, and the specific principle is as follows: if the recognition result and the decision suggestion of the AI model are accurate, the person gives positive feedback; if the recognition result is false report or false report, or the decision suggestion is not optimal or wrong at present, negative feedback is given to the recognition result and the decision suggestion by a person and is sent to the AI model, and the AI model modifies and optimizes the recognition model and the decision suggestion according to the feedback result, so that the recognition accuracy and the execution strategy are continuously improved. And repeating the steps in the whole decision making process.
As shown in fig. 4, the machine (AI model) analyzes and warns the results of the intelligent perception, and makes decision suggestions. After receiving the decision suggestion, the person judges whether the alarm information output by the sensing model of the intelligent sensing module 120 belongs to 'false alarm and missed alarm' according to the experience of the person and the actual situation of the field, if so, the information is fed back to the identification model of the intelligent sensing module 120, and a decision for maintaining the existing situation is made. If not, the decision suggestion given by the perception model is judged to be the most optimal decision by combining the experience of the user and the actual field situation, if so, the decision suggestion of the perception model is received, if not, the decision of the user is given, and the decision of the perception model is replaced by the decision of the user. And then, after the perception model receives the control instruction and feedback information of 'false alarm and missing report', the factors influencing model identification are checked in time, the identification efficiency is improved, and the execution strategy is optimized according to the final decision. Then, the identification, the early warning and the decision are carried out again, and the human-computer interaction process is repeated. It should be noted that, in the whole human-computer interaction process, the identification and decision strategies of the rules and the AI models in the whole knowledge base are not static, but in the human-computer interaction process of the AI technology, the decision strategies are dynamically changed, and the knowledge base and the rule engine are continuously dynamically optimized in the collaborative strategy process.
For better understanding, the belt deviation is still taken as an example for explanation. And after the belt deviation model identifies that the deviation value exceeds the stop value, sending a decision suggestion of stopping. At the moment, when people observe that the early warning belongs to false alarm, negative feedback is given, a decision of normal operation is made, a control instruction of the normal operation is sent, and false alarm is fed back to the recognition model. After the identification model receives the instruction, checking factors influencing model identification in time, and optimizing an identification result; if the early warning is observed to belong to correct recognition, positive feedback is given, and if the halt belongs to more correct decision for the current situation, positive feedback is also given to the decision suggestion; if the person feels that the selection is better than the halt according to own experience, the decision process of the person is used for replacing the decision suggestion given by the perception model, and the rules in the knowledge base are updated. Thus, the dynamic process of the whole cooperative decision is completed.
(4) Single service link closed loop
As shown in fig. 5, in the risk management and control portion, the smart sensor module 120 first identifies and alarms abnormal conditions, and performs automatic control, and if the alarm information is eliminated, the management and control is successful, otherwise, the management and control is failed. And if the control fails, entering a hidden danger management link, mainly presuming the cause-and-effect relationship among the events according to the established knowledge graph, and finding out the possible reason of the abnormal event, thereby triggering a control module of the risk control part and eliminating the alarm information. If the alarm information is still not released, the hidden danger treatment fails, and the hidden danger treatment is converted into an accident, so that the treatment is carried out according to the sequence in the accident management link. The accident management model gives an emergency plan to treat the hidden danger, the hidden danger treatment gives a corresponding control instruction to the wind control link, and the whole link is removed until the alarm information is removed. As can be seen from fig. 5, the three links of risk management and control, hidden danger management and accident management are changed and fastened, and for a single service, the process of finding the cause of the occurrence of the abnormality and processing the abnormality is traceable in the whole process according to the cause-and-effect relationship between events given in the knowledge graph, so that perfect closed loop is realized.
A specific implementation of this section is shown in fig. 6. The knowledge base provides control rules for the inference engine based on priori knowledge, the model base provides intelligent sensing and intelligent control for the rules based on a mathematical model, and the inference engine completes scene-based inference service based on the priori knowledge base, the model base and a sensing source and enables a safety control process.
The specific innovation of the part is as follows: 1. the risk management and control, the hidden danger management, the accident management and the like are all driven by different AI models in combination with the knowledge graph to be automatically completed without excessive manual intervention. The method specifically comprises the following steps: the platform provides a visual scene recognition rule engine tool and is internally provided with a decision function. The user can build scene recognition requirements as needed using the rules engine tool. After the construction is successful, the system executes perception analysis, alarm treatment and linkage control according to needs. 2. In the hidden danger management and accident management part, the causes and solutions of abnormal events are gradually checked according to the causal relationship among the events in the knowledge graph.
(5) Full service chain closed loop
As shown in fig. 7, the part aims at covering a closed loop of a security management and control service chain, constructs a management and control chain in advance, in advance and after the events based on big data analysis, and continuously optimizes the closed loop of a security management system by following the PDCA method in fig. 2.
As can be seen from fig. 7, the overall logic of this portion is similar to that in the "single service chain closed loop". The risk management and control are carried out on the abnormal conditions, if the management and control fail, a hidden danger management link is entered, and if the hidden danger management fail, an accident link is entered. Different from a single-service chain closed loop, the input of the part is the exception of multiple services, so that the coordination processing of risk management and control, hidden danger management and accident management of the multiple services is realized. The risk control belongs to the prior, and the part mainly utilizes AI intelligent perception to timely discover, alarm and automatically control abnormal conditions; the hidden danger treatment belongs to the field of affairs, and the part mainly utilizes a knowledge base, a knowledge graph and an AI center to find out the reasons causing abnormal conditions; accident management belongs to 'after the fact', and through analyzing and summarizing the accident, the accident is seen to be caused by the fact that knowledge is lacked in a rule base or rules are unreasonable, and a causal chain of the accident is found. And finally, updating the safety management rule or the knowledge base in the whole link so as to realize the closed loop of the whole service chain.
For example, when abnormal conditions such as belt deviation and belt no-load occur simultaneously, the corresponding alarm and automatic control modules are started to send out corresponding control instructions. If the alarm information is not released, the hidden danger treatment stage is started. In the stage, a knowledge base and a knowledge map are used as a basis, source tracing, investigation and reasoning are simultaneously carried out on two abnormal conditions of belt deviation and belt no-load, and then a corresponding control instruction is sent out according to a source tracing result. If the alarm information is not released, the accident management stage is entered, and some technical means (as shown in fig. 5) in the accident management stage are used for finding out and solving the final cause of the abnormal event.
Based on the alarm information, the alarm information can be alarm information of single-service abnormity or alarm information of multi-service abnormity, and the alarm information can comprise one or more of belt deviation alarm, belt no-load alarm, belt tearing alarm, belt coal piling alarm, foreign matter alarm, water coal alarm, bulk coal alarm and personnel violation alarm.
The embodiment of the invention also provides a coal production safety monitoring method, which is applied to the coal production safety monitoring system, and is shown in a flow schematic diagram of the coal production safety monitoring method shown in fig. 8, wherein the coal production safety monitoring method mainly comprises the following steps of S802-S806:
and S802, carrying out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process by the intelligent sensing module according to the safety knowledge content, and sending alarm information to the service processing module when monitoring that an abnormal condition occurs.
Step S804, the service processing module carries out elimination processing on the received alarm information according to the safety knowledge content and the safety knowledge map.
And step S806, the knowledge base module updates the safety knowledge information according to the processing result of the alarm information by the service processing module.
Further, the business processing module comprises a risk management and control model, a hidden danger management model and an accident management model; step S804 may be implemented by the following procedure: the risk control model generates a first control instruction corresponding to the alarm information according to an initial emergency plan in the safety knowledge content, and eliminates the alarm information through the first control instruction; after the processing of the risk control model, when the alarm information is not eliminated, the hidden danger management model infers the reason of the alarm according to the safety knowledge map, generates a second control instruction according to the inference result, and eliminates the alarm information through the second control instruction; and after the hidden danger treatment model is processed, when the alarm information is not eliminated, the accident management model analyzes and summarizes the abnormal conditions to generate a new emergency plan, and provides the new emergency plan for the risk management and control model until the alarm information is eliminated.
Further, the coal production safety monitoring method further comprises the following steps: the intelligent sensing module acquires a first feedback result of a user on a safety monitoring result, and optimizes a corresponding recognition model according to the first feedback result; and the business processing module acquires a second feedback result of the decision output by the user on the risk management and control model, the hidden danger management model and the accident management model, and optimizes the risk management and control model, the hidden danger management model and the accident management model according to the second feedback result.
The coal production safety monitoring method provided by the embodiment has the same implementation principle and technical effect as the coal production safety monitoring system embodiment, and for brief description, reference may be made to the corresponding contents in the coal production safety monitoring system embodiment for the portions that are not mentioned in the coal production safety monitoring method embodiment.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A coal production safety monitoring system is characterized by comprising a knowledge base module, an intelligent sensing module and a service processing module; the knowledge base module stores safety knowledge information, and the safety knowledge information comprises safety knowledge content and a safety knowledge map;
the intelligent sensing module is used for carrying out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content, and sending alarm information to the service processing module when abnormal conditions are monitored;
the service processing module is used for eliminating the received alarm information according to the safety knowledge content and the safety knowledge map;
and the knowledge base module is used for updating the safety knowledge information according to the processing result of the alarm information by the service processing module.
2. The coal production safety monitoring system according to claim 1, wherein the business processing module comprises a risk management and control model, a hidden danger management model and an accident management model; the service processing module is specifically configured to:
the risk control model generates a first control instruction corresponding to the alarm information according to an initial emergency plan in the safety knowledge content, and the alarm information is eliminated through the first control instruction;
after the alarm information is processed by the risk control model and is not eliminated, the hidden danger management model infers the reason of the alarm according to the safety knowledge map, generates a second control instruction according to the inference result, and eliminates the alarm information through the second control instruction;
and after the hidden danger treatment model is processed, when the alarm information is not eliminated, the accident management model analyzes and summarizes the abnormal conditions to generate a new emergency plan, and the new emergency plan is provided for the risk management and control model until the alarm information is eliminated.
3. The coal production safety monitoring system of claim 2, wherein the alarm information includes one or more of a belt off-tracking alarm, a belt no-load alarm, a belt tearing alarm, a belt coal piling alarm, a foreign matter alarm, a water coal alarm, a bulk coal alarm, and a personnel violation alarm.
4. The coal production safety monitoring system according to claim 2 or 3, wherein the intelligent sensing module is further configured to obtain a first feedback result of the user on the safety monitoring result, and perform optimization of the corresponding recognition model according to the first feedback result; the business processing module is further configured to obtain a second feedback result of the decision output by the user on the risk management and control model, the hidden danger management model and the accident management model, and optimize the risk management and control model, the hidden danger management model and the accident management model according to the second feedback result.
5. The coal production safety monitoring system of claim 4, wherein the knowledge base module is specifically configured to perform adaptive dynamic optimization on the safety knowledge information according to the processing result of the service processing module on the alarm information and the second feedback result; automatically associating and supplementing unknown security problems according to the first feedback result so as to realize self-learning of the security knowledge information; and tracking the hotspot knowledge according to the statistical result of the knowledge reference degree, and maintaining the fragment knowledge so as to realize the self-evolution of the safety knowledge information.
6. The coal production safety monitoring system of claim 5, wherein the safety knowledge information further comprises a safety knowledge scenario constructed based on the safety knowledge content and the safety knowledge graph, and the safety knowledge scenario is used for being called by the intelligent sensing module and the business processing module.
7. The coal production safety monitoring system according to claim 1, wherein the intelligent sensing module is specifically configured to acquire real-time data of one or more of personnel, equipment and an environment in a coal production process through a digital device, and perform identification processing of abnormal conditions on the real-time data through a pre-trained identification model, and the digital device includes one or more of a wearable device, a positioning device, a sensor and a camera device.
8. A coal production safety monitoring method applied to the coal production safety monitoring system according to any one of claims 1 to 7, the coal production safety monitoring method comprising:
the intelligent sensing module carries out real-time safety monitoring on one or more of personnel, equipment and environment in the coal production process according to the safety knowledge content, and sends alarm information to the service processing module when abnormal conditions are monitored;
the service processing module carries out elimination processing on the received alarm information according to the safety knowledge content and the safety knowledge map;
and the knowledge base module updates the safety knowledge information according to the processing result of the alarm information by the service processing module.
9. The coal production safety monitoring method according to claim 8, wherein the business processing module comprises a risk management and control model, a hidden danger management model and an accident management model; the service processing module eliminates the received alarm information according to the safety knowledge content and the safety knowledge map, and comprises the following steps:
the risk control model generates a first control instruction corresponding to the alarm information according to an initial emergency plan in the safety knowledge content, and the alarm information is eliminated through the first control instruction;
after the alarm information is processed by the risk control model and is not eliminated, the hidden danger management model infers the reason of the alarm according to the safety knowledge map, generates a second control instruction according to the inference result, and eliminates the alarm information through the second control instruction;
and after the hidden danger treatment model is processed, when the alarm information is not eliminated, the accident management model analyzes and summarizes the abnormal conditions to generate a new emergency plan, and the new emergency plan is provided for the risk management and control model until the alarm information is eliminated.
10. The coal production safety monitoring method according to claim 9, further comprising:
the intelligent sensing module acquires a first feedback result of a user on a safety monitoring result, and optimizes a corresponding recognition model according to the first feedback result;
and the business processing module acquires a second feedback result of the decision output by the user on the risk management and control model, the hidden danger management model and the accident management model, and optimizes the risk management and control model, the hidden danger management model and the accident management model according to the second feedback result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210522475.1A CN114859839B (en) | 2022-05-13 | 2022-05-13 | Coal production safety monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210522475.1A CN114859839B (en) | 2022-05-13 | 2022-05-13 | Coal production safety monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114859839A true CN114859839A (en) | 2022-08-05 |
| CN114859839B CN114859839B (en) | 2023-01-24 |
Family
ID=82636551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210522475.1A Active CN114859839B (en) | 2022-05-13 | 2022-05-13 | Coal production safety monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114859839B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757484A (en) * | 2023-08-23 | 2023-09-15 | 山东全员本安教育咨询有限公司 | Enterprise safety hidden danger monitoring and tracing method, device, equipment and storage medium |
| CN117035456A (en) * | 2023-08-14 | 2023-11-10 | 武汉集远数字科技有限公司 | Intelligent building site monitoring and management method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008044647A (en) * | 2006-08-17 | 2008-02-28 | Chugoku Electric Power Co Inc:The | In-bunker granule level alarm |
| KR20130000975A (en) * | 2011-06-24 | 2013-01-03 | 주식회사 포스코 | Material transfer apparatus and operating method thereof |
| CN107885170A (en) * | 2016-09-30 | 2018-04-06 | 珠海优特电力科技股份有限公司 | The method of safety in production control device, system and management and control of keeping the safety in production |
| CN112446605A (en) * | 2020-11-20 | 2021-03-05 | 航天精一(广东)信息科技有限公司 | Emergency plan management method and system based on knowledge reasoning and simulation drilling |
| CN113869712A (en) * | 2021-09-26 | 2021-12-31 | 海南锋利气体有限公司 | Intelligent system for large-scale industrial gas production |
-
2022
- 2022-05-13 CN CN202210522475.1A patent/CN114859839B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008044647A (en) * | 2006-08-17 | 2008-02-28 | Chugoku Electric Power Co Inc:The | In-bunker granule level alarm |
| KR20130000975A (en) * | 2011-06-24 | 2013-01-03 | 주식회사 포스코 | Material transfer apparatus and operating method thereof |
| CN107885170A (en) * | 2016-09-30 | 2018-04-06 | 珠海优特电力科技股份有限公司 | The method of safety in production control device, system and management and control of keeping the safety in production |
| CN112446605A (en) * | 2020-11-20 | 2021-03-05 | 航天精一(广东)信息科技有限公司 | Emergency plan management method and system based on knowledge reasoning and simulation drilling |
| CN113869712A (en) * | 2021-09-26 | 2021-12-31 | 海南锋利气体有限公司 | Intelligent system for large-scale industrial gas production |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117035456A (en) * | 2023-08-14 | 2023-11-10 | 武汉集远数字科技有限公司 | Intelligent building site monitoring and management method and system |
| CN117035456B (en) * | 2023-08-14 | 2024-02-27 | 武汉集远数字科技有限公司 | Intelligent building site monitoring and management method and system |
| CN116757484A (en) * | 2023-08-23 | 2023-09-15 | 山东全员本安教育咨询有限公司 | Enterprise safety hidden danger monitoring and tracing method, device, equipment and storage medium |
| CN116757484B (en) * | 2023-08-23 | 2023-11-24 | 山东全员本安教育咨询有限公司 | Enterprise safety hidden danger monitoring and tracing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114859839B (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114859839B (en) | Coal production safety monitoring system and method | |
| CN113344326B (en) | System and method for identifying dynamic hidden danger and evaluating risk of special operation site | |
| CN103823458A (en) | Remote diagnosis device, method and system for equipment | |
| US20110166912A1 (en) | Plant analysis system | |
| EP1727009B1 (en) | System for displaying alarms and related information for supporting process operation | |
| CN116228186A (en) | Ship cabin intelligent operation and maintenance system based on human engineering | |
| CN107682454A (en) | A kind of emergency disposal device based on remote support | |
| CN114169568A (en) | Prophet model-based power distribution line current prediction and heavy overload early warning and system | |
| CN112651642A (en) | Hydraulic engineering field personnel safety management system based on multi-device perception | |
| CN116010886A (en) | Security monitoring method, device, electronic equipment and storage medium | |
| JP2019018979A (en) | Elevator system | |
| US20180307212A1 (en) | System and method for the maintenance of an industrial plant | |
| CN117215940A (en) | Intelligent operation and maintenance emergency processing system | |
| CN117010696A (en) | Miner individual safety instant navigation early warning system and method thereof | |
| CN107909159A (en) | A kind of municipal rail train emergence treating method | |
| CN111675257B (en) | Remote centralized control method and system for sewage treatment plant | |
| CN107798398A (en) | A kind of networking decision support and emergency disposal system | |
| CN104977870A (en) | Auxiliary treating system for workshop equipment accidents and method thereof | |
| CN210514972U (en) | Belt conveyor safety monitoring and control system based on vision AI | |
| Jharko | Critical information infrastructure objects: operator support systems | |
| CN113642487A (en) | Artificial intelligence-based method and system applied to safety production | |
| Zaky | Risk analysis using fuzzy system based risk matrix methodology | |
| Alexandru et al. | An architectural system solution for technical diagnosis | |
| Wang | Coal Mine Safety Risk Intelligent control and information decision analysis system | |
| KR20240063347A (en) | System and method of prediction anomalous signs in smart factory using ensemble learning and kalman filter |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230614 Address after: No. 8 Andingmen Outer Street, Dongcheng District, Beijing, 100011 Patentee after: China Coal Information Technology (Beijing) Co.,Ltd. Patentee after: JINGYING DIGITAL TECHNOLOGY Co.,Ltd. Address before: 030000 7th floor, block a, sunshine international business center, 103 Changzhi Road, Xiaodian District, Taiyuan City, Shanxi Province Patentee before: JINGYING DIGITAL TECHNOLOGY Co.,Ltd. |