Power station field operation risk management and control method and device based on time interconnection

Abstract

The invention provides a power station field operation risk management and control method and device based on time interconnection, and the method comprises the steps: building a safety management and control task of operation content, operation equipment and operation environment corresponding to the operation time of each stage, building a power station full-dimensional data deep fusion model, extracting decision attributes, and carrying out the safety management and control task. And performing decision fusion based on the decision attributes to obtain a deep fusion result, establishing a multi-dimensional time sequence model based on the deep fusion result, obtaining perception and identification data of each operation device in the operation content in the operation time of each stage according to the multi-dimensional time sequence model, and performing risk early warning based on the perception and identification data. Safety identification is carried out on operation equipment and an operation environment related to the operation content based on risk early warning, and human body behavior risks of all stages of operation time of the operation content are identified based on the risk early warning. According to the invention, the deep data fusion technology is applied to the risk early warning of the field operation of the power station, and the safety monitoring and risk early warning of the whole process are realized by constructing the multi-dimensional time sequence model.

Description

Technical Field

[0001] The present invention relates to the technical field of power station field operations, and in particular to a method and device for risk control of power station field operations based on time-of-day interconnection. Background Art

[0002] With the rapid development of the power industry, power stations, as core facilities for energy conversion and supply, have a safe and stable operation that is of great significance to ensuring social and economic life. However, the on-site operating environment of power stations is complex and changeable, involving multiple dangerous factors such as high voltage, high temperature, and high radiation. In addition, the uncertainty of operator behavior and the potential risks of equipment operation make the safety management of power station on-site operations an extremely challenging task. At present, in the field of risk control of power station on-site operations, the traditional risk management method based on manual inspections and experience judgment can no longer meet the safety management needs of modern power stations. This method is not only inefficient, but also easily interfered by human factors, resulting in untimely and inaccurate risk warnings, and even safety accidents.

[0003] In recent years, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, digital and intelligent means have gradually been introduced into the risk management of power plant site operations. For example, by deploying sensor networks to collect equipment operation data, using big data analysis technology to explore potential risks, and applying artificial intelligence algorithms for risk warning and intelligent decision-making, these methods have shown great potential in improving the safety management level of power plants. However, most of the existing digital and intelligent methods for risk management of power plant site operations remain at the optimization of a single data dimension or local processes, and lack a systematic and closed-loop management mechanism. Summary of the invention

[0004] In view of the deficiencies in the prior art, the object of the present invention is to provide a method and device for risk management of power plant on-site operations based on time-based interconnection.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for risk control of power station field operations based on time interconnection, comprising the following steps:

[0007] Establish safety control tasks for the work content, work equipment and work environment corresponding to the work time at each stage, where the work time at each stage includes before, during and after the work;

[0008] Establish a deep fusion model of the power plant's full-dimensional data, extract decision attributes from the operation content, operation equipment, and operation environment of each stage of operation time, and perform decision fusion based on the decision attributes to obtain deep fusion results;

[0009] Establish a multi-dimensional time series model based on the deep fusion results;

[0010] According to the multi-dimensional time series model, the perception and recognition data of each operation equipment in the operation content at each stage of the operation time are obtained, and risk warning is carried out based on the perception and recognition data;

[0011] Based on risk warning, the work equipment and work environment related to the work content are safely identified. At the same time, based on risk warning, the human behavior risks during the working time at each stage of the work content are identified.

[0012] Furthermore, the perception and recognition data of each operating device during the operation time of each stage of the operation content are obtained according to the multidimensional time series model. The method for risk warning based on the perception and recognition data is as follows:

[0013] Extract multidimensional time series data of terminal sensors of each operation equipment during the operation time of each stage of the operation content in the multidimensional time series model;

[0014] Extract multidimensional time series data of terminal sensors of each operation equipment during the operation time of each stage of the operation content in the multidimensional time series model;

[0015] Obtain operational risk event information based on multi-dimensional time series data;

[0016] According to the operation risk event information, the signal of the target mobile terminal is extracted and sent to the target monitoring terminal, which then issues a risk warning.

[0017] Through the pre-set expert knowledge base, the standardized operation process of the corresponding emergency plan is obtained for the risk warning, and the corresponding emergency operation procedures are determined according to the standardized operation process;

[0018] Send emergency operation information about risk warning and the location of the on-site emergency accident to the corresponding target operating station, so that the corresponding operators can complete the emergency operation procedures according to the emergency handling information.

[0019] Furthermore, according to the operation risk event information, the signal of the target mobile terminal is extracted, and the signal is sent to the target monitoring terminal. The method for the target monitoring terminal to perform risk warning is as follows:

[0020] Combined with the working environment, before the operation, the operator's human behavior image recognition or the workflow sequence selection corresponding to the work content is analyzed for perception problems;

[0021] According to the operation characteristics of different operation tools, determine the type of human-machine collaboration data set to be collected, and at the same time, determine the data set to be obtained according to the action characteristics, and pre-process the data set;

[0022] By adding time-related weights to the data loss function, the data loss function can be expressed as:

[0023]

[0024] in, represents the probability of category k at time t, Q represents the total number of categories; e -t represents the weight associated with time t, and T represents the total number of times;

[0025] Make judgments based on the results obtained from the data loss function, output the human intentions of the relevant time steps, process the data length, find the optimal judgment results, and set risk warnings based on the optimal judgment results.

[0026] Furthermore, through the pre-set expert knowledge base, the standardized operation process of the corresponding emergency plan is obtained for the risk warning, and the method of determining the corresponding emergency operation procedure according to the standardized operation process is as follows:

[0027] Extract the expert knowledge index that meets the actual situation from the expert knowledge base;

[0028] Formulate various operating procedures required in the emergency response process based on the professional knowledge index;

[0029] Acquire all mobile terminal devices associated with each workflow, and acquire at least one mobile terminal as a target mobile terminal of the workflow from all mobile terminal devices;

[0030] An operating target closest to the on-site emergency accident location is determined based on the target mobile terminal, and a corresponding emergency operation procedure is determined based on the operating target.

[0031] Furthermore, the pre-job work includes:

[0032] Select the model elements of the job ticket according to the job standard, complete the overall configuration of the job ticket template, and form a job ticket template library for selection when creating a work order;

[0033] The work content is divided into planned tasks and emergency tasks. For planned tasks, the corresponding task work order can be directly selected through the work ticket template, and for emergency tasks, a customized task work order can be created online;

[0034] After completing the task work order creation, select the approver to conduct the online approval process and record and archive it;

[0035] After approval is completed, the task order will be automatically classified in the execution list and issued.

[0036] Furthermore, the assignments in the assignment include:

[0037] Safety identification and control of work locations;

[0038] Identification of human behavior risks during the operation process.

[0039] Furthermore, the safe identification and control of the working location includes RFID tag equipment identification and on-site passive smart locks;

[0040] Human behavior risk identification during the operation process includes safety helmet identification, work clothes identification, safety belt identification and smoking identification.

[0041] A power station field operation risk control device based on time interconnection, comprising:

[0042] The safety control task establishment module is used to establish the safety control tasks of the operation content, operation equipment and operation environment corresponding to the operation time at each stage, where the operation time at each stage includes before the operation, during the operation and after the operation;

[0043] The first model building module is used to build a deep fusion model of the full-dimensional data of the power station, extract decision attributes from the operation content, operation equipment and operation environment of each stage of operation time, and perform decision fusion based on the decision attributes to obtain a deep fusion result;

[0044] The second model building module is used to build a multi-dimensional time series model based on the deep fusion result;

[0045] The risk warning acquisition module is used to obtain the perception and recognition data of each operating equipment in the operation content of each stage of operation time according to the multi-dimensional time series model, and to issue risk warnings based on the perception and recognition data;

[0046] The identification module is used to safely identify the work equipment and work environment related to the work content based on risk warnings, and to identify the human behavior risks during the work time at each stage of the work content based on risk warnings.

[0047] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for risk control of power station field operations based on time-based interconnection when executing the program.

[0048] A non-transitory computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned power station on-site operation risk management method based on time-based interconnection.

[0049] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0050] Based on the comprehensive status information platform of the power plant, the present invention determines a digital on-site operation risk warning closed-loop mode, which can ensure the stability of the on-site operation of the power plant and the risk warning results. Digital operation is based on closed-loop management, which upgrades and integrates the scattered resources and sectors, and finally forms a three-in-one digital closed-loop operation safety management mode.

[0051] The present invention constructs a closed-loop model for digital operation safety management. The data generated by the all-round integrated status of the power station creates a new closed-loop structure, changing the previous single architecture. Its core contents are two: First, a digital operation safety business chain consisting of risk warning + risk type + operation risk information is established, with closed loops complementing each other and coexisting in parallel; second, digital collaborative services constitute a closed-loop management innovation, which is mainly reflected in the diversification of human-machine operation safety management and control in power stations.

[0052] The present invention realizes all-round and intelligent early warning and control of the risks of power station site operations. Based on the comprehensive status information platform of the power station, the method integrates advanced technologies such as deep learning and big data analysis, realizes the deep integration and intelligent analysis of the full-dimensional data of the power station, and provides a new solution for the safety management of power station site operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0054] Figure 1 This is a flow chart of a method for risk control of power station field operations based on time interconnection according to the present invention;

[0055] Figure 2 A schematic diagram of a digital collaborative service closed-loop model of the present invention;

[0056] Figure 3 This is a full-dimensional data deep fusion model diagram of a power station according to the present invention;

[0057] Figure 4 It is a multi-dimensional time series model diagram of the present invention;

[0058] Figure 5 This is a safety control flow chart before operation of the present invention;

[0059] Figure 6 It is the execution process of the pre-work preparation stage in the operation of the present invention;

[0060] Figure 7 This is the task execution process in the operation of the present invention. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0062] Example 1

[0063] Example 1 provides a method for risk management and control of power plant field operations based on time-based interconnection, such as Figure 1 As shown, the following steps are included:

[0064] Step S1: Establishing safety control tasks for operation content, operation equipment and operation environment corresponding to each stage of operation time, wherein each stage of operation time includes before operation, during operation and after operation;

[0065] Step S2: Establish a deep fusion model of the full-dimensional data of the power station, extract decision attributes for the operation content, operation equipment and operation environment of each stage of operation time, and perform decision fusion based on the decision attributes to obtain a deep fusion result;

[0066] Step S3: Establish a multi-dimensional time series model based on the deep fusion results;

[0067] Step S4: acquiring the perception and recognition data of each operation equipment in the operation content in each stage of the operation time according to the multidimensional time series model, and performing risk warning based on the perception and recognition data;

[0068] Step S5: Based on the risk warning, the operating equipment and operating environment related to the operating content are safely identified, and at the same time, the human behavior risks during the operating time at each stage of the operating content are identified based on the risk warning.

[0069] There are significant deficiencies in the current risk management and control technology for power plant on-site operations, which are mainly reflected in the single digital collaborative business closed-loop model and the lack of dynamic adaptability, as well as insufficient human-machine collaboration; the data deep fusion technology is limited by low data quality and lack of spatiotemporal correlation; the risk warning system has problems of lag and low intelligence, and lacks knowledge base support to enhance the accuracy of warnings; the accuracy of human behavior recognition technology during operations is limited, the management and control methods are single, and data records are incomplete.

[0070] In view of the above technical problems, this embodiment provides a method for risk control of power station site operations based on time interconnection. First, the safety control tasks of the operation content, operation equipment and operation environment corresponding to each stage of operation time (before, during and after the operation) are established, and then the full-dimensional data deep fusion model of the power station is established. The decision attributes of the operation content, operation equipment and operation environment of each stage of operation time are extracted, and the decision fusion is performed based on the decision attributes to obtain the deep fusion result. The perception and recognition data of each operation equipment in the operation content of each stage of operation time are obtained in combination with the multidimensional time series model. Based on the perception and recognition data, risk warning is performed, and the operation equipment and operation environment related to the operation content are safely identified based on the risk warning. At the same time, the human behavior risks of the operation content at each stage of operation time are identified based on the risk warning. Based on the comprehensive status information platform of the power station, a digital on-site operation risk warning closed-loop mode is determined, which can ensure the stability of the on-site operation and risk warning results of the power station. Digital operation is based on closed-loop management, which upgrades and integrates scattered resources and sectors, and finally forms a three-in-one digital closed-loop operation safety management mode.

[0071] This embodiment builds a closed-loop model for digital operation safety management, such as Figure 2 As shown in the figure, the data generated by the all-round integrated status of the power station has created a new closed-loop structure, changing the previous single architecture. Its core content is twofold: first, a digital operation safety business chain consisting of risk warning level + risk type + operation risk information has been established, with closed loops complementing each other and coexisting in parallel; second, digital collaborative services constitute a closed-loop management innovation, which is mainly reflected in the diversification of human-machine operation safety management and control in power stations.

[0072] This embodiment realizes all-round and intelligent early warning and control of the risks of power station site operations. Based on the comprehensive status information platform of the power station, this method integrates advanced technologies such as deep learning and big data analysis, realizes the deep integration and intelligent analysis of the full-dimensional data of the power station, and provides a new solution for the safety management of power station site operations.

[0073] In step S2 of this embodiment, Figure 3 As shown in the figure, a deep fusion model of the full-dimensional data of the power station is established. In order to improve the peaks caused by the aggregation of signal components of the massive data of the power station, the full-dimensional data is fused using the data deep fusion method. Assume that the data x i The decision attribute is ki, and the corresponding maximum confidence gain function is maxg i (k i ), then:

[0074]

[0075] In formula (1), n ​​represents the number of decisions, and i represents the i-th decision. Therefore, the decision attributes are normalized and merged, and the formula is:

[0076]

[0077] Assume that the data x i The deep fusion decision attribute value of the power station is determined, and the power station full-dimensional data deep fusion model constructed by this is as shown in the attached Figure 2 shown.

[0078] By the attached Figure 2 It can be seen that by fully considering the interconnection and feedback between each level of the hybrid fusion structure of deep learning, the data is deeply integrated to make up for the fact that the traditional fusion process is easily affected by data loss, incompleteness, and uncertainty factors, so that the fusion model has good robustness.

[0079] In step S3 of this embodiment, the deep fusion results are obtained through the device sensors and video monitoring nodes. There is a certain correlation between the dimensions of these deep fusion results. The deep fusion results also evolve over time and can be regarded as a multidimensional time series. The multidimensional time series model is as follows: Figure 4 shown.

[0080] Depend on Figure 4 It can be seen that the key scenario risk warning model based on space and time is based on space and time. Before, during and after the operation, the operator is actively warned throughout the entire process to effectively control the safety of the personnel before, during and after the operation, thereby ensuring the safety of the operator's operation. The constructed multi-dimensional time series model can well solve the problems of large amount of power station monitoring data and complex data types. It combines the power station's full-dimensional data deep fusion model to perform intelligent analysis of the data, and provide effective data support for the safe operation of on-site operators. At the same time, in response to the problem that on-site risks cannot be warned in a timely manner, the intelligent analysis results are interactively retrieved with the knowledge base to actively identify potential dangers on site, actively enhance awareness, ensure the safety of operators, improve operation quality, and complete the deep integration of operation safety management and control functions in production and operation and maintenance services, as well as the intelligent perception and identification of potential risks during the operation process.

[0081] In step S4 of this embodiment, the perception and recognition data of each operating device during the operation time of each stage of the operation content is obtained according to the multidimensional time series model, and the method for risk warning based on the perception and recognition data is as follows:

[0082] Step S401: extracting multidimensional time series data of terminal sensors of each operation equipment within the operation time of each stage of the operation content in the multidimensional time series model;

[0083] Step S402: Acquire operation risk event information based on multi-dimensional time series data;

[0084] Step S403: extracting the signal of the target mobile terminal according to the operation risk event information, sending the signal to the target monitoring terminal, and the target monitoring terminal issues a risk warning;

[0085] Step S404: Obtaining a standardized operation process of a corresponding emergency plan for the risk warning through a pre-set expert knowledge base, and determining a corresponding emergency operation procedure according to the standardized operation process;

[0086] Step S405: Send emergency operation information about risk warning and the location of the on-site emergency accident to the corresponding target operation station, so that the corresponding operator can complete the emergency operation procedure according to the emergency handling information.

[0087] In step S403 of this embodiment, the equipment or operating machines involved in the on-site operation process are operated under a fixed procedure, and basically no abnormal situation will occur, but the operator's human behavior intention will change with the working environment. Therefore, the early warning judgment of the target monitoring terminal (including equipment sensors, monitoring cameras, and mobile terminals) is the judgment of human behavior intention. The detailed judgment process is as follows:

[0088] The target mobile terminal is an operator. According to the operation risk event information, the signal of the target mobile terminal is extracted and sent to the target monitoring terminal. The method for the target monitoring terminal to perform risk warning is as follows:

[0089] Step S4031: Based on the working environment, before the operation, the operator's human behavior image recognition or the workflow sequence selection corresponding to the work content is analyzed for perception problems;

[0090] Step S4032: according to the operation characteristics of different operation tools, determine the type of human-machine collaboration data set to be collected, and at the same time, according to the action characteristics, determine the data set to be obtained, and pre-process the data set;

[0091] Step S4033: Add a time-related weight to the data loss function. The data loss function can be expressed as:

[0092]

[0093] in, represents the probability of category k at time t, Q represents the total number of categories; e -t represents the weight associated with time t, and T represents the total number of times.

[0094] Step S4034: Make a judgment based on the results obtained from the data loss function, output the human intention of the relevant time step, process the data length, find the optimal judgment result, and set a risk warning based on the optimal judgment result.

[0095] Among them, risk warning includes risk type, level, and on-site information.

[0096] In step S404 of this embodiment, the standardized operation process of the corresponding emergency plan is obtained by reviewing the risk accidents and the pre-set expert knowledge base, and the corresponding emergency operation procedures are determined according to the standardized operation steps. For example, the target operation console is a mobile terminal connected to the switch field operation safety management system, which includes a variety of operation processes completed by different operators, and the detailed process is as follows:

[0097] Step S4041: extracting expert knowledge indexes that conform to the actual situation from the expert knowledge base;

[0098] Step S4042: Formulate various operating procedures required in the emergency handling process based on the professional knowledge index;

[0099] Step S4043: Acquire all mobile terminal devices associated with each workflow, and obtain at least one mobile terminal as a target mobile terminal of the workflow from all mobile terminal devices;

[0100] Step S4044: Determine an operation target that is closest to the on-site emergency accident location based on the target mobile terminal, and determine a corresponding emergency operation procedure based on the operation target.

[0101] For example, the mobile terminal device currently bound to the operation process can be detected through online detection, and an operation target closest to the on-site emergency accident can be determined, so that on-site operation risk accidents can be handled quickly.

[0102] In step S1 of this embodiment, Figure 5As shown in the figure, before the operation, in order to ensure the safety of the workers entering the site, the safety conditions for the workers entering the site are set by adopting the safety control technology for the workers entering and leaving the site, so that the workers entering the site are allowed to work only under safe conditions. Safety conditions include personnel qualifications not being met, personnel protection not being in place, special tools not being fully prepared, maintenance content not being planned according to the maintenance regulations, and safety briefing not being implemented. Before the operation, it is necessary to issue a work ticket first. By associating the content of the work ticket with the actual operation technology on site, the invoicing process automatically determines whether the invoicing content conforms to the logical relationship of the hydropower business operation and whether it conforms to the on-site operation sequence, so as to ensure that the work ticket is issued correctly. After the work ticket is issued, the system automatically generates a list of tools and keys for this operation. The workers only need to collect the tools and keys according to the list, avoiding the omission of tools and keys. In addition, by adopting the safety control technology for the workers entering and leaving the site, the safety conditions for the workers entering the site are set. When the relevant conditions are not met, an alarm prompt will pop up automatically.

[0103] like Figure 5 As shown, the pre-job work includes:

[0104] Generate a job ticket template library: select the model elements that make up the job ticket according to the job standard, complete the overall configuration of the job ticket template, and form a job ticket template library for selection when creating task work orders, so as to facilitate the rapid generation of job tasks.

[0105] Create task work orders: Divide the work content into planned tasks and emergency tasks. For planned tasks, directly select the corresponding task work order through the job ticket template. For emergency tasks, create a customized task work order online.

[0106] The sources of tasks for creating task work orders mainly include equipment defect information, maintenance plans, inspection plans, etc. of the site equipment monitoring system. Confirm the operation information, select the inspection task, operation ticket, and work ticket to create the task work order entry to enter the task creation scene. You can directly select the corresponding task work order through the operation ticket template (for planned tasks), or you can create a custom task work order online (for sudden tasks). The custom task work order is implemented by assigning control personnel, assigning executors, associating equipment, creating task steps, etc.; according to the operation ticket process information, you can fill in the task information, creator information, and add safety measures, tools and other related information involved in the operation content. The safety control points, risk points, and key points in the operation process can be automatically matched according to the task work order, and can be customized by the person in charge. Then select the relevant permitter, person in charge, executor, etc., to generate a new operation ticket. The work ticket model can be retained for later modification or reuse on this basis.

[0107] Task work order approval: After completing the creation of the task work order, select the approver to conduct the online approval process and record and archive it;

[0108] Task work order issuance: After approval is completed, the task work order will be automatically classified in the execution list and issued.

[0109] In step S1 of this embodiment, the operation content in the operation includes:

[0110] Safety identification and control of work locations;

[0111] Identification of human behavior risks during the operation process.

[0112] The following is a detailed description of the safe identification and control of the work location.

[0113] During the on-site work preparation stage of the power plant, operators need to accept / view tasks through the mobile terminal and clarify the relevant work content, identify related risks and confirm tools and equipment to avoid operators' misoperation and omissions, which may cause serious safety accidents. After the authorized operator arrives at the site, he / she will identify the RFID tag and check whether it is consistent with the work point on the work order. Then, he / she will scan the QR code on the App to obtain the smart lock information, click on the Bluetooth key, and scan the pairing of the smart lock and the key. The lock can only be unlocked after the pairing is successful. If it is unsuccessful, the lock will be refused to be unlocked and the operator will be reminded by issuing an alarm. At the same time, the system records the unlocking status of the electronic key and the work status of the operator, so that the opening and closing of the lock are recorded and the operation process has a basis to rely on. The process is as follows Figure 6 shown.

[0114] In RFID tag equipment identification, in the process of operation position identification, RFID tags are used as a tool to identify the operation channel. The location installation includes two parts. One is installed on the switch room or the switch station door (belonging to the large range of the operation area), and the other part is installed on the equipment interval (belonging to the operation target equipment). The RFID tag contains the asset coding information of the current equipment. After scanning the QR code above or the NFC identification tag, the current equipment asset code can be identified.

[0115] The information exchange of RFID (Radio Frequency Identification) system is realized through the non-contact method of spatial coupling, completing the reading and writing operation of the identification target information. In the Internet of Things system, the radio frequency identification technology is used to effectively collect and exchange data on the target items. The reader, electronic tag, and system high level are the three main components of the RFID system, as shown in the attached figure. Figure 6 shown.

[0116] For on-site passive smart locks, combined with the actual situation at the power plant operation site, since there are no conditions for padlocking on the power plant cabinet, the lock is hung on the switch room or the switch station door for security and authority control. Operators with unlocking authority can unlock and perform tasks.

[0117] The passive smart lock control system software has the function of authorizing unlocking in advance. The process of opening the passive smart lock involves the key collection business process, including key collection, department, smart lock to be opened, recipient, selection of collection time period, and App login to open Bluetooth to collect the corresponding key process. The specific method is as follows:

[0118] Step S101: The operator collects the key in the background;

[0119] Step S102: Enter the key collection interface, select the department to be authorized to unlock, and select the information of the lock to be opened;

[0120] Step S103: Select the staff member who needs to unlock the door;

[0121] Step S104: Select the time to unlock the door. The time can be selected according to the current day or a custom time period;

[0122] Step S105: Confirm key collection information;

[0123] Step S106: The recipient user logs in to the system on the App side, can view the unlocking tasks that need to be done, select the smart lock that needs to be opened, turn on Bluetooth at the same time, and connect the Bluetooth key. After the connection is successful, the key can be collected to perform the task.

[0124] 2) Identification of human behavior risks during the operation

[0125] After unlocking the door and entering the work site, the operation control system connects to the on-site video surveillance system to conduct all-round, real-time monitoring of the work site, record and analyze the operation process; and combined with high-definition cameras to achieve real-time video monitoring of the work site, realize automatic identification and early warning of unsafe factors and behaviors in the work, such as "two wearing and one wearing" (i.e. safety helmet, work clothes, safety belt), and smoking, to improve the accuracy and efficiency of safety supervision.

[0126] During the execution of the task, the execution process of each single step will be recorded and the execution video will be uploaded in real time for the PC-side control personnel to view the execution results. During the operation and inspection process, based on the high-definition cameras deployed on site, the video monitoring screen and background model are obtained through image deep learning, and the automatic identification of unsafe factors and behaviors such as "two wearing and one wearing" and smoking of personnel within the screen range is detected, and an alarm signal is issued to remind relevant personnel to pay attention. After all steps are completed, the task completion confirmation needs to be made by the PC-side control personnel or administrator.

[0127] The method of "two wearing and one wearing" identification is as follows:

[0128] Step S111: image preprocessing;

[0129] Step S112: color segmentation;

[0130] Step S113: morphological operation;

[0131] Step S114: contour detection and recognition;

[0132] Step S115: Determine the wearing condition.

[0133] The image preprocessing method in step S111 is specifically as follows:

[0134] Step S1111: reading video frames;

[0135] Continuously capture image frames from a video stream and select one of them as the input for the current processing, which usually involves operations such as video decoding and frame synchronization;

[0136] Technical details: Use a video processing library to read a video file or video stream and process it frame by frame.

[0137] Step S1112: noise reduction.

[0138] The Gaussian filter denoising algorithm is used to smooth the image by calculating the weighted average of the pixels at the pixel and its neighborhood.

[0139] For each pixel (x, y) in the image, its filtered value I'(x, y) can be calculated by the following formula:

[0140]

[0141] Where M is the sum of all weights in the neighborhood (for a Gaussian filter, this is equal to the normalization constant), G′(m,n) is the value of the Gaussian kernel at position (m,n), and I(x+m,y+n) is the pixel value of the original image at position (x+m,y+n).

[0142] Step S1113: Color space conversion

[0143] Convert the image from RGB color space to HSV color space for better color-based image segmentation. Algorithm: Color space conversion involves mapping RGB values ​​to corresponding values ​​in HSV space. Specific formula:

[0144] ① Calculate the maximum and minimum values: Find the maximum value max and the minimum value min among the three RGB components.

[0145] ②Calculate brightness (V): V = max

[0146] ③ Calculate saturation (S): If max is equal to 0, then S = 0; otherwise, S = (max-min) / max

[0147] ④Calculate hue (H):

[0148] If max is red, H = 60*((GB) / (max-min)) (where G and B are the green and blue components)

[0149] If max is green, H = 60*(2+(BR) / (max-min)) (where R is the red component)

[0150] If max is blue, H = 60*(4+(RG) / (max-min))

[0151] The result H needs to be between 0° and 360°, and may need to be adjusted (such as adding 360° and taking the modulus).

[0152] The specific method of color segmentation in step S112 is:

[0153] Step S1121: Define the color range.

[0154] According to the actual colors of the helmet, work clothes and safety belt, the corresponding color range is defined in the HSV color space. The HSV color space separates brightness (V) from color information (H and S), making color segmentation more robust and less susceptible to changes in lighting.

[0155] By taking multiple helmet samples under different lighting conditions, different materials and colors, and then analyzing the color distribution of these samples in the HSV space, a suitable color range can be determined.

[0156] Step S1122: Color threshold processing.

[0157] The specific method of color threshold processing is: for each pixel in the image, check whether its HSV value falls within the previously defined color range of the helmet, work clothes or safety belt.

[0158] The specific algorithm is:

[0159] ① Traverse pixels: traverse each pixel in the image.

[0160] ② Color check: For each pixel, get its HSV value (H, S, V).

[0161] ③ Range match: Check whether the HSV value meets any of the following conditions.

[0162] Safety Helmet

[0163] HSV color range matching:

[0164] lower_H_hat≤H1≤upper_H_hat and lower_S_hat≤S1≤upper_S_hat and lower_V_hat≤V1≤

[0165] upper_V_hat

[0166] Among them, lower\_H\_hat, upper\_H\_hat, lower\_S\_hat, upper\_S\_hat, lower\_V\_hat, upper\_V\_hat are the lower and upper bounds of the HSV color range defined for the helmet, H1 is the H color parameter of the helmet, S1 is the S color parameter of the helmet, and V1 is the V color parameter of the helmet.

[0167] Work Clothes

[0168] HSV color range matching:

[0169] lower_H_clothes≤H2≤upper_H_clothes and lower_S_clothes≤S2≤upper_S_clothes and

[0170] lower_V_clothes≤V2≤upper_V_clothes

[0171] Among them, lower\_H\_clothes,upper\_H\_clothes,lower\_S\_clothes,upper\_S\_clothes,lower\_V\_clothes,upper\_V\_clothes are the lower and upper bounds of the HSV color range defined for work clothes, H2 is the H color parameter of work clothes, S2 is the S color parameter of work clothes, and V2 is the V color parameter of work clothes.

[0172] Safety Belt

[0173] HSV color range matching:

[0174] lower_H_belt≤H3≤upper_H_belt and lower_S_belt≤S3≤upper_S_belt and lower_V_belt≤V3≤upper_V_belt

[0175] Among them, lower\_H\_belt, upper\_H\_belt, lower\_S\_belt, upper\_S\_belt, lower\V\_belt, upper\V\_belt are the lower and upper bounds of the HSV color range defined for the seat belt, H3 is the H color parameter of the seat belt, S3 is the S color parameter of the seat belt, and V3 is the V color parameter of the seat belt.

[0176] Morphological operations are shape-based operations in digital image processing that use structural elements (also called kernels or templates) to detect and modify shapes in images. These operations are useful for improving image segmentation results, removing noise, and filling holes.

[0177] The method of morphological operation in step S113 is specifically as follows:

[0178] Step S1131: corrosion.

[0179] By sliding the structural element on the image, the foreground pixel at that position is retained only when the structural element is completely inside the foreground object. The erosion operation is often used to remove small white noise points and separate adhered objects.

[0180] Algorithm formula: Let the original image be A and the structural element be B, then the corrosion operation Defined as:

[0181]

[0182] Wherein, (B)z represents the set after the origin of the structural element B is translated to point z.

[0183] Step S1132: Dilation

[0184] The dilation operation is the reverse process of erosion, which makes the foreground objects in the image larger. By sliding the structure element on the image, as long as the structure element is in contact with the foreground object, the position is retained as a foreground pixel. The dilation operation is often used to fill holes, cracks, and expand the boundary outward.

[0185] Let the original image be A and the structural element be B, then the dilation operation Defined as:

[0186]

[0187] in, is the reflection of B (i.e. symmetry about the origin), Indicates that The set after the origin is translated to point z.

[0188] Step S1133: Opening

[0189] Opening is a process of erosion followed by dilation. It is often used to remove small white noise while keeping the overall position and shape of foreground objects unchanged. Opening can smooth the boundaries of larger objects while removing smaller objects.

[0190] Let the original image be A and the structural element be B, then the opening operation Defined as:

[0191]

[0192] Step S1134: Closing operation.

[0193] Closing is a process of dilation followed by erosion. It is often used to fill small black areas or holes while keeping the overall position and shape of the foreground object unchanged. Closing can connect adjacent objects while smoothing their boundaries.

[0194] Let the original image be A and the structural element be B, then the closing operation A·B is defined as:

[0195]

[0196] In image processing, contour detection and recognition are important steps to extract the boundaries of objects in an image and classify them. This process usually involves finding and screening contours and identifying them based on the features of helmets, safety belts, and work clothes.

[0197] The specific method of contour detection and recognition in step S114 is:

[0198] Step S1141: contour search.

[0199] Contour finding is the first step to identify the boundaries of objects in an image. In OpenCV, the findContours function is the main tool for performing this task. This function searches for contours in a binary image and returns a set of coordinate points of the found contours.

[0200] The method is: convert the morphologically processed image into a binary image.

[0201] Use findContours function to find all contours in an image.

[0202] Step S1142: contour screening.

[0203] Contour filtering is to filter out uninteresting contours based on certain shape features, retaining contours that may be target objects (safety helmets, work clothes, safety belts). These features may include area, perimeter, circularity (or shape factor, i.e. 4π*area / perimeter) 2, for a circle it is 1), aspect ratio, etc.

[0204] The specific method is:

[0205] ①Traverse all found contours.

[0206] ② Calculate the area, perimeter and other features of each contour.

[0207] ③Filter contours according to preset thresholds or conditions (such as area range, circularity threshold, aspect ratio limit).

[0208] Step S1143: contour recognition.

[0209] Contour recognition is the process of further determining which category a contour belongs to based on the filtered contour. This usually relies on more complex feature analysis or machine learning models.

[0210] step:

[0211] (1) Extract the features of each filtered contour.

[0212] (2) Use the trained classifier to classify the feature vector and determine which category the contour belongs to (safety helmet, work clothes, safety belt, or other).

[0213] The method for judging the wearing condition in step S115 is:

[0214] The process of evaluating whether the worker is wearing the helmet, work clothes and safety belt correctly based on the results of contour detection and recognition. This process involves a comprehensive analysis of the contour position, shape and integrity to determine whether the wear meets safety regulations.

[0215] Step S1151: Position determination.

[0216] Position judgment is to check whether the contour is located at the appropriate position of the human body in the image. This usually relies on prior knowledge of the human body structure in the image or a predefined position template.

[0217] (1) Define the location area: the helmet area is located in the upper center of the image, the work clothes area covers the middle and upper part of the image, and the safety belt area is located near the waist.

[0218] Contour Position Matching: For each detected contour, calculate the position of its centroid or bounding box and compare it with the position area of ​​the corresponding worn object.

[0219] Position judgment: If the position of the contour matches the defined position area, the wearable item is considered to be in the appropriate position; otherwise, a warning of improper position may be issued.

[0220] Step S1152: Integrity determination.

[0221] Completeness is the process of checking if the outline is complete, without breaks or unusually shaped parts. This helps identify if the item is damaged or not worn correctly.

[0222] Contour continuity check: This is achieved by traversing the pixels of the contour and checking the connectivity between adjacent points.

[0223] Shape consistency check: Compare the detected contours with predefined standard shapes of hard hats, safety belts, and work clothes to check if there are significant shape differences.

[0224] Completeness judgment: If the outline is continuous and the shape is consistent with the template, the wearable article is considered complete; otherwise, a warning of insufficient integrity may be issued.

[0225] The specific method of smoking identification is:

[0226] Step S121: preprocessing stage.

[0227] Image preprocessing is the first step in the image processing pipeline. Its main purpose is to improve the image quality and make it more suitable for subsequent image analysis tasks. Through preprocessing, noise can be reduced, image features can be enhanced, image data can be standardized, etc., thereby improving the accuracy and efficiency of subsequent processing steps.

[0228] Step S122: cigarette stick shape recognition.

[0229] Step S123: Identify the red temperature point when smoking.

[0230] Step S124: Identify the smoke white layer.

[0231] Step S125: The recognition results of the three conditions of cigarette stick shape, temperature red dot and smoke white layer are integrated, and a comprehensive judgment is made according to the preset rules (such as at least two of the three conditions of cigarette stick shape, temperature red dot and smoke white layer are met) to determine whether there is smoking behavior.

[0232] The specific method of the pre-processing stage of step S121 is:

[0233] Step S1211: Video frame extraction.

[0234] Video frame extraction refers to extracting images frame by frame from a continuous surveillance video stream at fixed time intervals (such as extracting one frame per second) or based on other strategies (such as motion detection triggering).

[0235] The specific method is:

[0236] ①Use the video decoding library to read video files or video streams.

[0237] ②Traverse each frame in the video and decode it into image format.

[0238] ③Store or process these image frames.

[0239] Step S1212: Grayscale.

[0240] Grayscale is the process of converting a color image into a grayscale image. Grayscale images only contain brightness information, not color information, so the amount of calculation for subsequent processing can be greatly reduced.

[0241] The specific method is: according to the different sensitivities of the human eye to different colors, different weights are assigned to the red, green and blue channels, and then the grayscale value is obtained by summing them up. In this solution, the weights used are 0.299 for red, 0.587 for green and 0.114 for blue.

[0242] Grag=0.299×R+0.587×G+0.114×B

[0243] Among them, R, G, B are the pixel values ​​of the red, green and blue channels respectively, and Gray is the converted grayscale value.

[0244] Step S1213: noise removal.

[0245] Noise removal is an important step in image preprocessing, which is used to reduce random interference points or noise in the image and improve image quality. The commonly used noise removal method uses median filtering, which is a nonlinear filtering technique that replaces the value of each pixel in the image with the median of the pixel values ​​in the neighborhood of the point.

[0246] Pixel new =median(Pixel neighbors )

[0247] Among them, Pixel new is the processed pixel value, Pixel neighbors It is the set of pixel values ​​in the neighborhood of the pixel point, and the median() function is used to calculate the median of these pixel values.

[0248] The specific method of step S122 for identifying the shape of the cigarette stick is:

[0249] Step S1221: edge detection: using the Canny edge detection algorithm to extract edge information in the image;

[0250] Step S1222: Shape analysis:

[0251] Apply Hough Transform to detect straight lines or circles (assuming the cigarette stick is a long strip or cylindrical shape).

[0252] Based on the detected straight line or circular features, its aspect ratio, area and other parameters are calculated to determine whether it is in the shape of a cigarette stick.

[0253] The form of Hough transform detection straight line is:

[0254] ρ=xcosθ+ysinθ

[0255] Here, (ρ, θ) is a point in parameter space and (x, y) is a point in image space.

[0256] In the task of identifying the temperature red spot when smoking, color space conversion and color threshold segmentation are two key steps to accurately identify the red area representing the burning point of the cigarette from the image. The following is a detailed explanation of these two steps and the corresponding algorithm logic.

[0257] The specific method of identifying the red temperature point during smoking in step S123 is:

[0258] Step S1231: Color space conversion.

[0259] Convert the grayscale image to HSV color space so that the colors in the image can be identified and segmented based on hue (H), saturation (S), and value (V).

[0260] The conversion method is:

[0261] Use an image processing library such as OpenCV to convert the image from RGB color space to HSV color space. In OpenCV, this is usually achieved through the cv2.cvtColor() function.

[0262] Step S1232: Color space conversion.

[0263] In the HSV color space, the red area in the image is extracted by setting the threshold range of the hue (H), saturation (S), and brightness (V) of the red area.

[0264] (1)Threshold setting:

[0265] For red, the hue (H) in HSV space is roughly distributed in two intervals: 0° to 10° (the transition between red and yellow) and 170° to 180° (the transition from purple to red). However, since hue is cyclic and affected by factors such as lighting conditions and camera settings, these values ​​may need to be adjusted.

[0266] The thresholds of saturation (S) and brightness (V) also need to be set according to the specific situation to ensure that the red area can be accurately extracted while avoiding misjudging the non-red area as red.

[0267] (2) Algorithm logic:

[0268] Sets the threshold range for the red region in HSV. This is usually a list of tuples containing two lower bounds (lower_bound) and an upper bound (upper_bound), since there are two possible ranges for hue.

[0269] Color segmentation using these thresholds is usually achieved by comparing the H, S, V values ​​of each pixel in the HSV image with the set threshold range. This can be done by writing a loop to compare pixel by pixel, but a more efficient method is to use functions provided by image processing libraries, such as OpenCV's cv2.inRange().

[0270] The method for identifying the smoke white layer in step S124 is:

[0271] Step S1241: Brightness detection.

[0272] Calculates the brightness value of each pixel in the image.

[0273] Step S1242: Threshold segmentation.

[0274] Set a brightness threshold (RT), usually determined empirically or experimentally.

[0275] Pixels with brightness values ​​above the threshold are considered as smoke areas.

[0276] Step S1243: Regional connectivity analysis.

[0277] Analyze the connected white areas to determine whether their shape, size, and motion characteristics are consistent with smoke characteristics.

[0278] The algorithm is:

[0279] Brightness threshold segmentation can be expressed as: I ≥ R T

[0280] Where I is the brightness value of the pixel, R T is the threshold value.

[0281] In step S1 of this embodiment, for the post-operation work content, after the personnel have finished the work, it is necessary to promptly and thoroughly clean up the personnel and tools left on the scene, and close the safety lock according to the specifications. In order to ensure that no personnel and tools are left on the scene after the operation is completed, and to close the safety lock according to regulations, and to ensure the normal operation of the power station business, the personnel and tools left on the scene are checked by intelligent tool inventory, and compared with the tool list at the time of entering the site. When the two do not correspond, an alarm prompt will pop up until the two completely correspond. The system automatically performs on-site personnel left-behind detection to ensure that the on-site personnel are completely cleared before closing the switch and closing the safety lock.

[0282] Example 2

[0283] Embodiment 2 provides a power station field operation risk control device based on time interconnection, such as Figure 7 As shown, including:

[0284] The safety control task establishment module is used to establish the safety control tasks of the operation content, operation equipment and operation environment corresponding to the operation time at each stage, where the operation time at each stage includes before the operation, during the operation and after the operation;

[0285] The first model building module is used to build a deep fusion model of the full-dimensional data of the power station, extract decision attributes from the operation content, operation equipment and operation environment of each stage of operation time, and perform decision fusion based on the decision attributes to obtain a deep fusion result;

[0286] The second model building module is used to build a multi-dimensional time series model based on the deep fusion result;

[0287] The risk warning acquisition module is used to obtain the perception and recognition data of each operating equipment in the operation content of each stage of operation time according to the multi-dimensional time series model, and to issue risk warnings based on the perception and recognition data;

[0288] The identification module is used to safely identify the work equipment and work environment related to the work content based on risk warnings, and to identify the human behavior risks during the work time at each stage of the work content based on risk warnings.

[0289] Example 3

[0290] Embodiment 3 provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the above-mentioned method for risk management and control of power plant site operations based on time-to-space interconnection is implemented.

[0291] Example 4

[0292] Embodiment 4 provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned power station field operation risk management method based on time interconnection is implemented.

[0293] It should be understood that the parts not elaborated in detail in this specification belong to the prior art. The above description of the preferred embodiment is relatively detailed, but it cannot be regarded as a limitation on the scope of patent protection of the present invention. Under the enlightenment of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which all fall within the scope of protection of the present invention. The scope of protection requested for the present invention shall be based on the attached claims.

[0294] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for risk management and control of power station field operations based on time-based interconnection, characterized in that: The following steps are involved: Establish safety control tasks for the work content, work equipment and work environment corresponding to the work time at each stage, where the work time at each stage includes before, during and after the work; Establish a deep fusion model of the power plant's full-dimensional data, extract decision attributes from the operation content, operation equipment, and operation environment of each stage of operation time, and perform decision fusion based on the decision attributes to obtain deep fusion results; Establish a multi-dimensional time series model based on the deep fusion results; According to the multi-dimensional time series model, the perception and recognition data of each operation equipment in the operation content at each stage of the operation time are obtained, and risk warning is carried out based on the perception and recognition data; Based on risk warning, the work equipment and work environment related to the work content are safely identified. At the same time, based on risk warning, the human behavior risks during the working time at each stage of the work content are identified.

2. The method for risk management and control of power station field operations based on time-based interconnection according to claim 1 is characterized in that: According to the multi-dimensional time series model, the perception and recognition data of each operating equipment during the operation time of each stage of the operation content are obtained. The method for risk warning based on the perception and recognition data is as follows: Extract multidimensional time series data of terminal sensors of each operation equipment during the operation time of each stage of the operation content in the multidimensional time series model; Extract multidimensional time series data of terminal sensors of each operation equipment during the operation time of each stage of the operation content in the multidimensional time series model; Obtain operational risk event information based on multi-dimensional time series data; According to the operation risk event information, the signal of the target mobile terminal is extracted and sent to the target monitoring terminal, which then issues a risk warning. Through the pre-set expert knowledge base, the standardized operation process of the corresponding emergency plan is obtained for the risk warning, and the corresponding emergency operation procedures are determined according to the standardized operation process; Send emergency operation information about risk warning and the location of the on-site emergency accident to the corresponding target operating station, so that the corresponding operators can complete the emergency operation procedures according to the emergency handling information.

3. The method for risk control of power station field operations based on time-based interconnection according to claim 2 is characterized in that: According to the operation risk event information, the signal of the target mobile terminal is extracted and sent to the target monitoring terminal. The method for the target monitoring terminal to issue a risk warning is as follows: Combined with the working environment, before the operation, the operator's human behavior image recognition or the workflow sequence selection corresponding to the work content is analyzed for perception problems; According to the operation characteristics of different operation tools, determine the type of human-machine collaboration data set to be collected, and at the same time, determine the data set to be obtained according to the action characteristics, and pre-process the data set; By adding time-related weights to the data loss function, the data loss function can be expressed as: in, represents the probability of category k at time t, Q represents the total number of categories; e -t represents the weight associated with time t, and T represents the total number of times; Make judgments based on the results obtained from the data loss function, output the human intentions of the relevant time steps, process the data length, find the optimal judgment results, and set risk warnings based on the optimal judgment results.

4. The method for risk management and control of power station field operations based on time-based interconnection according to claim 2 is characterized in that: Through the pre-set expert knowledge base, the standardized operation process of the corresponding emergency plan is obtained for the risk warning, and the method of determining the corresponding emergency operation procedure according to the standardized operation process is as follows: Extract the expert knowledge index that meets the actual situation from the expert knowledge base; Formulate various operating procedures required in the emergency response process based on the professional knowledge index; Acquire all mobile terminal devices associated with each workflow, and acquire at least one mobile terminal as a target mobile terminal of the workflow from all mobile terminal devices; An operating target closest to the on-site emergency accident location is determined based on the target mobile terminal, and a corresponding emergency operation procedure is determined based on the operating target.

5. The method for risk management and control of power station field operations based on time-based interconnection according to claim 1 is characterized in that: The pre-job work includes: Select the model elements of the job ticket according to the job standard, complete the overall configuration of the job ticket template, and form a job ticket template library for selection when creating a work order; The work content is divided into planned tasks and emergency tasks. For planned tasks, the corresponding task work order can be directly selected through the work ticket template, and for emergency tasks, a customized task work order can be created online; After completing the task work order creation, select the approver to conduct the online approval process and record and archive it; After approval is completed, the task order will be automatically classified in the execution list and issued.

6. The method for risk control of power station field operations based on time-based interconnection according to claim 1 is characterized in that: The assignments in the course include: Safety identification and control of work locations; Identification of human behavior risks during the operation process.

7. The method for risk management and control of power station field operations based on time-based interconnection according to claim 1 is characterized in that: Safety identification and control of work locations include RFID tag equipment identification and on-site passive smart locks; Human behavior risk identification during the operation process includes safety helmet identification, work clothes identification, safety belt identification and smoking identification.

8. A power station on-site operation risk management and control device based on time interconnection, characterized in that: include: The safety control task establishment module is used to establish the safety control tasks of the operation content, operation equipment and operation environment corresponding to the operation time at each stage, where the operation time at each stage includes before the operation, during the operation and after the operation; The first model building module is used to build a deep fusion model of the full-dimensional data of the power station, extract decision attributes from the operation content, operation equipment and operation environment of each stage of operation time, and perform decision fusion based on the decision attributes to obtain a deep fusion result; The second model building module is used to build a multi-dimensional time series model based on the deep fusion result; The risk warning acquisition module is used to obtain the perception and recognition data of each operating equipment in the operation content of each stage of operation time according to the multi-dimensional time series model, and to issue risk warnings based on the perception and recognition data; The identification module is used to safely identify the work equipment and work environment related to the work content based on risk warnings, and to identify the human behavior risks during the work time at each stage of the work content based on risk warnings.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for risk control of power plant field operations based on time-based interconnection as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for risk management and control of power plant field operations based on time-to-space interconnection as described in any one of claims 1 to 7 is implemented.

Images