A risk distribution four-color map management and control method, system, device and storage medium based on a smart power plant

Abstract

The application discloses a risk distribution four-color chart management and control method, system and device based on a smart power plant and a storage medium, relates to the technical field of smart power plant operation safety, and comprises the following steps: unifiedly identifying equipment, operation and environment risk objects in the smart power plant, collecting and structuring multiple-source risk original indexes under the same time reference, and constructing a risk input data set; normalizing the equipment risk, operation risk and environment risk original indexes of each risk object, outputting a comprehensive risk value, determining a fixed risk threshold, and mapping the comprehensive risk value to red, orange, yellow and green four-color risk levels; and generating a risk distribution state of a space node level according to a power plant space topology structure, and performing a management and control operation according to the risk color level corresponding to the space risk node. The application drives the hierarchical management and control operation by the color level, and improves the objectivity of smart power plant risk identification, the consistency of management and control, and the implementability of execution.

Description

Technical Field

[0001] This invention relates to the field of smart power plant operation safety technology, specifically to a risk distribution four-color diagram control method, system, equipment, and storage medium for smart power plants. Background Technology

[0002] As the power industry continues to evolve towards digitalization and intelligence, smart power plants are gradually becoming an important development model in the power generation industry. By introducing industrial internet, IoT sensing, big data analysis, and visualization technologies, smart power plants can monitor equipment operating status, operational activities, and environmental parameters in real time, providing data support for operation management and safety control. In existing technologies, risk management typically relies on online equipment monitoring systems, safety production management systems, or video security systems to identify and alert on equipment anomalies, operational violations, or environmental anomalies. Meanwhile, some systems have attempted to visualize risk status through risk classification and risk diagrams to assist operators in risk identification and decision-making. Overall, existing smart power plant risk management technologies are developing from single-equipment monitoring to multi-source information fusion, and from static alarms to visualized risk presentation.

[0003] However, existing smart power plant risk management technologies still have many shortcomings in practical applications. First, most existing technologies focus on the independent monitoring of equipment operation risks, or treat equipment risks, operational risks, and environmental risks separately, lacking a unified modeling and quantification mechanism for multiple types of risk objects. This makes it difficult to compare and comprehensively evaluate risk information from different sources on the same scale, resulting in a lack of comparability between risk results. Second, existing technologies often use fixed rules or experience thresholds for risk classification during the risk assessment process. Risk thresholds often rely on manual setting or industry experience, making it difficult to adaptively determine them based on the power plant's own operating characteristics and historical risk distribution, thus failing to accurately reflect the true risk level at different operating stages.

[0004] Furthermore, existing risk visualization technologies often remain at the level of alarm lists or simple area identification, lacking a deep connection with the spatial topology of power plants. This makes it difficult to form a risk distribution expression centered on spatial nodes, resulting in operators being unable to intuitively identify the spatial aggregation characteristics and diffusion trends of risks. In addition, existing technologies typically lack a strict one-to-one correspondence between risk classification results and subsequent control measures. Changes in risk levels fail to automatically drive the switching of control strategies, and a closed-loop collaborative mechanism is not formed between risk identification, risk display, and risk handling. Therefore, existing technologies struggle to achieve unified quantification, spatial expression, and hierarchical linkage control of multi-source risks in smart power plants, failing to achieve refined, traceable, and sustainably optimized risk management effects. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is that existing smart power plant risk management methods have problems such as a lack of unified modeling and quantification standards for multi-source risk objects, risk thresholds that rely on experience and are difficult to reflect actual operating characteristics, and a lack of effective linkage between risk results and power plant spatial structure and control measures. The problem is how to achieve unified quantification of multi-dimensional risks of equipment, operation and environment, four-color hierarchical visualization and expression and drive hierarchical control execution.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a risk distribution four-color map control method based on smart power plants, comprising: uniformly identifying equipment, operational, and environmental risk objects within the smart power plant; collecting and structurally storing multi-source original risk indicators under the same time reference to construct a risk input dataset; normalizing the original indicators of equipment risk, operational risk, and environmental risk for each risk object; outputting a comprehensive risk value by combining the maximum risk dominance and the linkage between operations and the environment; determining a fixed risk threshold based on the historical distribution characteristics of the comprehensive risk value; mapping the comprehensive risk value to four risk levels (red, orange, yellow, and green) according to the threshold range; associating the risk color level and handling status of the risk object with spatial coding; generating a spatial node-level risk distribution status based on the power plant's spatial topology; and executing control operations according to the risk color level corresponding to the spatial risk node.

[0008] As a preferred embodiment of the risk distribution four-color map management method based on smart power plants described in this invention, the unified identification of equipment, operation and environmental risk objects in the smart power plant includes assigning a unique object identifier to each risk object based on the power plant equipment coding system, operation management coding system and environmental monitoring point coding system, and establishing a risk object index relationship so that the object identifier corresponds to the corresponding equipment location, operation area or environmental monitoring range.

[0009] As a preferred embodiment of the risk distribution four-color map management method based on smart power plants described in this invention, the step of collecting and structuring the original risk indicators from multiple sources under the same time reference includes: synchronously processing equipment risk data, operational risk data, and environmental risk data using a unified timestamp; selecting original risk indicators that form complete records within a preset risk calculation period for processing; and using risk object identifiers and timestamps as dual indexes to structure and store the original risk indicators from multiple sources.

[0010] As a preferred embodiment of the risk distribution four-color map control method based on smart power plants described in this invention, the normalization of the original indicators of equipment risk, operational risk and environmental risk of each risk object includes: pre-setting corresponding upper and lower bound parameters for the original risk indicators from different sources, and converting the original risk indicators into normalized risk components according to a unified numerical conversion rule.

[0011] As a preferred embodiment of the risk distribution four-color map management method based on smart power plants described in this invention, the step of normalizing the original indicators of equipment risk, operational risk, and environmental risk for each risk object, and outputting a comprehensive risk value by combining the dominant risk and the linkage between operational and environmental risks, includes determining the dominant risk component as the dominant risk item in the normalized risk components, comprehensively considering the compensation contribution of the remaining risk components and the linkage between operational and environmental risks, and generating a comprehensive risk value that reflects the current overall risk level of the risk object.

[0012] As a preferred embodiment of the risk distribution four-color map control method based on smart power plants described in this invention, the step of determining a fixed risk threshold based on the historical distribution characteristics of the comprehensive risk value and mapping the comprehensive risk value to four risk levels (red, orange, yellow, and green) according to the threshold interval includes selecting comprehensive risk values ​​formed within a preset historical time window to form a sample set, sorting and statistically analyzing the sample set, and extracting the corresponding quantile values ​​as risk thresholds according to fixed quantile rules; the risk threshold remains unchanged within the same operating cycle.

[0013] As a preferred embodiment of the risk distribution four-color map control method for smart power plants described in this invention, the step of performing control operations according to the risk color level corresponding to the spatial risk node includes binding the risk color level with the spatial code corresponding to the risk object, and generating a risk distribution state at the spatial node level based on the power plant's spatial topology; if the risk color level corresponding to the spatial node is different, the control operations corresponding to the color level are executed respectively, and the spatial risk state and control execution record are updated synchronously when the risk level changes.

[0014] Another objective of this invention is to provide a risk distribution four-color map control system based on smart power plants. This system can determine a fixed risk threshold based on the historical distribution characteristics of the comprehensive risk value, and map the comprehensive risk value into four risk levels: red, orange, yellow, and green, according to the threshold range. This solves the problem that current smart power plant risk management methods lack effective linkage between risk results and the spatial structure and control measures of the power plant.

[0015] As a preferred embodiment of the risk distribution four-color map control system based on smart power plants described in this invention, the system includes: a risk modeling and data aggregation module, a risk quantification and four-color classification module, and a spatial mapping and hierarchical control module. The risk modeling and data aggregation module is used to uniformly identify equipment, operations, and environmental risk objects within the smart power plant, and to collect, synchronize, and structure-store multi-source risk raw indicators under the same time reference, forming a unified input dataset for risk calculation. The risk quantification and four-color classification module is used to normalize the multi-source risk raw indicators and calculate the comprehensive risk value, determine the risk threshold based on historical distribution, and perform a deterministic mapping of risk objects to red, orange, yellow, and green four-color risk levels. The spatial mapping and hierarchical control module is used to associate the four-color risk levels with the power plant's spatial coding and spatial topology, generate a spatial risk distribution status, and execute corresponding control operations based on different risk color levels.

[0016] Another object of the present invention is to provide a risk distribution four-color map management device based on a smart power plant, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the risk distribution four-color map management method based on a smart power plant.

[0017] Another objective of this invention is to provide a risk distribution four-color diagram management and control storage medium based on a smart power plant, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the risk distribution four-color diagram management and control method based on a smart power plant.

[0018] The beneficial effects of this invention are: The risk distribution four-color map management method based on smart power plants provided by this invention constructs a unified multi-source risk management mechanism for smart power plants, forming a complete, closed and consistent technical chain between risk data acquisition, risk quantification, risk classification and risk disposal.

[0019] First, by uniformly identifying equipment, operations, and environmental risk objects, and collecting and structurally storing multi-source risk raw indicators under the same time benchmark, risk information from different sources and systems is consistently bound in both the object and time dimensions, fundamentally solving the problems of scattered risk data, inconsistent standards, and difficulty in comprehensive analysis in existing technologies.

[0020] Secondly, by normalizing multiple risk indicators and introducing the maximum risk-driven operation-environment linkage, a comprehensive risk value that can truly reflect the overall state of the risk object is output. This ensures that the risk assessment results highlight the main sources of risk while avoiding underestimation of complex high-risk scenarios, thereby improving the engineering rationality and accuracy of the risk quantification results.

[0021] Furthermore, a fixed risk threshold is determined based on the historical distribution characteristics of the comprehensive risk value, and the risk results are mapped to four color levels: red, orange, yellow, and green. This transforms risk classification from experience-driven to data-driven, ensuring the objectivity, stability, and reproducibility of risk level division.

[0022] Finally, by associating risk color levels and handling status with power plant spatial coding and spatial topology, a risk distribution status at the spatial node level is formed. Corresponding control operations are executed according to different color levels, realizing the direct driving of risk identification results to actual control behavior. This enables a consistent linkage between risk assessment, spatial representation and control execution, thereby significantly improving the refinement, standardization and feasibility of risk control in smart power plants. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is an overall flowchart of a risk distribution four-color diagram control method based on a smart power plant, provided in Embodiment 1 of the present invention. Detailed Implementation

[0025] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0026] Example 1, referring to Figure 1 As an embodiment of the present invention, a risk distribution four-color diagram control method based on smart power plants is provided, comprising: S1: By uniformly identifying the equipment, operations, and environmental risk objects within the smart power plant, and collecting and structurally storing multi-source original risk indicators under the same time benchmark, a risk input dataset is constructed.

[0027] Furthermore, in the smart power plant operating environment, the objects involved in risk calculation across the entire plant are first uniformly identified at the system level, forming a risk object set. This risk object set includes equipment objects, operational objects, and environmentally related objects. All three types of objects are numbered based on the power plant's existing coding system, and a unique and non-repeatable risk object identifier is established within the system.

[0028] Each risk object corresponds to only one risk object identifier in the system. This identifier remains unchanged during risk data collection, calculation, and subsequent four-color mapping to ensure the uniqueness and traceability of risk data in both the time and object dimensions.

[0029] For equipment-related risk objects, a fixed data interface is established with the equipment control system and condition monitoring system to collect the status data of the equipment during operation.

[0030] The system processes equipment status data using fixed statistical rules, converting the data within the collection period into a single raw equipment risk indicator value. This indicator serves as the sole input to the equipment risk variable in subsequent mathematical models. This raw equipment risk indicator is represented as a continuous numerical value within the system and is bound and stored along with the corresponding equipment's risk object identifier and timestamp.

[0031] For work-related risk objects, data is collected from the production operation management system to obtain the status information of the work activities. The status information includes whether the work is in execution status, the work category identifier, and the work duration record.

[0032] The system processes job status information numerically according to preset rules, converting the job status into a single raw job risk indicator value. This indicator characterizes the risk level of the job activity at the current moment. The raw job risk indicator is expressed as a continuous numerical value in the system and is bound to the risk object identifier and timestamp corresponding to the job point, ensuring the certainty of job risk data in subsequent calculations.

[0033] For environmentally related risk objects, environmental status data is collected through environmental monitoring devices and security monitoring systems. The environmental status data includes monitoring quantities and abnormal alarm statuses that are directly related to safety risks.

[0034] The system processes the collected environmental status data according to fixed transformation rules, uniformly mapping different types and dimensions of environmental monitoring data into a single raw environmental risk indicator value. This ensures that environmental risk has a consistent expression in numerical space with equipment risk and operational risk. The raw environmental risk indicator is stored together with the corresponding risk object identifier and timestamp.

[0035] It should be noted that the system employs a unified time synchronization strategy for the original indicators of equipment risk, operational risk, and environmental risk. Within each risk calculation cycle, only the original indicators of the three types of risks that were collected and have complete records within the same time window are selected for subsequent calculations. For data records that fail to form complete records of the three types of indicators within a specified time window, the system uses preset missing data handling rules for consistency processing and records the processing results as structured fields.

[0036] After completing the collection and synchronous processing of multi-source risk data, the system uses the risk object identifier as an index to structurally store the original indicators of equipment risk, operational risk, and environmental risk, forming risk data record units with both risk object and timestamp as dual indexes. Each risk data record unit contains at least three types of numerical fields for original risk indicators.

[0037] S2: Normalize the original indicators of equipment risk, operational risk and environmental risk for each risk object, and output a comprehensive risk value based on the maximum risk and the linkage between operations and the environment.

[0038] Furthermore, for each risk object, within a preset risk calculation period, the original equipment risk indicators, original operational risk indicators, and original environmental risk indicators corresponding to the risk object identifier are extracted.

[0039] The above three types of risk indicators are all stored in numerical form and form a complete data record unit under the same timestamp.

[0040] To eliminate the differences in the dimensions and numerical ranges of different original risk indicators, the three types of original risk indicators for each risk object were normalized separately.

[0041] Let the risk object be The time is The original indicators corresponding to equipment risk, operational risk, and environmental risk are respectively denoted as: ,in These represent three types of risk sources: equipment, operations, and environment.

[0042] For each type of risk source, the system pre-sets corresponding lower and upper bounds, and calculates the corresponding normalized risk component according to the following normalization formula: , in, It serves as a unique identifier for the risk object, corresponding to the equipment, area, or work point; Indicates the time point in the risk calculation; Indicates the risk source type identifier, where For equipment risks, For operational risks, For environmental risks; Indicates risk object In time Corresponding risk sources The original risk indicators; Indicates risk source The lower bound parameter; Indicates risk source The upper bound parameter; This represents the normalized risk component.

[0043] Through the above calculations, the original risk indicators from different sources are uniformly mapped to the interval. Inside.

[0044] It should be noted that after the normalization calculation is completed, each risk object corresponds to a unique set of three normalized risk components in any calculation period, which respectively represent the risk level of the risk object in the three dimensions of equipment, operation and environment.

[0045] It should also be noted that, based on the three types of normalized risk components, the system first calculates the maximum risk component of the risk object within the current calculation period, in order to characterize the most prominent risk source of the object in multiple risk dimensions.

[0046] Let the maximum risk component be denoted as The calculation method is as follows: , in, Indicates risk object In time The maximum risk component; This represents the normalized component of equipment risk. This represents the normalized operational risk component. This represents the normalized environmental risk component.

[0047] Based on obtaining the maximum risk component, the comprehensive risk value of the risk object is calculated by further considering the compensation contribution of the remaining risk components and the linkage between operational and environmental risks. Let the risk object be... At any moment The overall risk value is denoted as The calculation method is as follows: , in, Indicates risk object In time The overall risk value, with a range of values ​​being: .

[0048] The overall risk value is determined entirely by the objective values ​​of the three normalized risk components, and the outermost trimming operation ensures that the overall risk value remains within a certain range. Within the range.

[0049] After calculating the comprehensive risk value, the risk object identifier, timestamp, and corresponding comprehensive risk value are stored as a complete risk quantification result, which serves as the sole input for risk level determination and four-color mapping. Each risk object corresponds to only one comprehensive risk value within the same calculation period.

[0050] S3: Determine a fixed risk threshold based on the historical distribution characteristics of the comprehensive risk value, and map the comprehensive risk value into four risk levels: red, orange, yellow, and green, according to the threshold range.

[0051] Furthermore, after calculating the comprehensive risk value for each risk object, for each risk object, within the corresponding risk calculation period, the comprehensive risk value consistent with the risk object's identifier and timestamp is extracted and used as the unique input data for risk level determination and risk color mapping. This comprehensive risk value corresponds to only one definite value within the same calculation period and is no longer involved in numerical calculations after entering the risk level determination stage.

[0052] To ensure the objective basis of risk level classification, the comprehensive risk values ​​generated during historical operation are statistically processed during the initialization or pre-calibration phase. The system selects the comprehensive risk values ​​generated by all risk objects within a preset historical time window in each calculation cycle, constructs a comprehensive risk value sample set, and sorts this sample set. Based on the sorted comprehensive risk value sample set, the system extracts the corresponding quantile values ​​according to a fixed quantile rule, and determines the extracted quantile values ​​as the first risk threshold, second risk threshold, and third risk threshold, respectively. The quantile rule is set as a fixed proportion rule in the system and remains unchanged within the same operating cycle, thereby ensuring that the source of the risk thresholds is clear and reproducible.

[0053] Three risk thresholds are set in the risk level determination process. The thresholds satisfy the following conditions: Furthermore, their values ​​are all derived from the statistical results of the historical distribution of the comprehensive risk value. The risk color level corresponding to any risk object is determined according to the following mapping rule: , in, This represents the first risk threshold, determined by a fixed low quantile in the distribution of historical composite risk values; This represents the second risk threshold, determined by a fixed median quantile in the distribution of historical composite risk values; The third risk threshold is determined by a fixed high quantile in the distribution of historical composite risk values; The color indicates the level of risk.

[0054] It should be noted that after the risk color level is determined, the risk object is handled according to the corresponding color level.

[0055] When a risk object is determined to be at the red risk level, mandatory handling rules are implemented for that risk object, including marking it as a non-negligible state, triggering operation restriction instructions for the work or equipment associated with the risk object, and adding the risk object to the real-time monitoring list to prohibit it from entering the regular operation or work process before the risk level changes.

[0056] When a risk object is determined to be at the orange risk level, key control rules will be implemented for that risk object, including adding it to the high-frequency monitoring list and restricting it from entering new operations or status switching processes. At the same time, it is required to continuously retain its risk status record in subsequent calculation cycles until its comprehensive risk value changes within a range.

[0057] When a risk object is determined to be at the yellow risk level, the regular attention rules are applied to that risk object, including including it in the regular monitoring queue and retaining its risk status record for subsequent trend analysis, while allowing it to maintain its established operation or work status.

[0058] When a risk object is determined to be at the green risk level, the basic monitoring rules are applied to the risk object, and only the necessary status collection and periodic risk calculation records are retained, without imposing additional restrictions on its operation or work status.

[0059] After matching the risk color level with the corresponding operation rule, the risk object identifier, timestamp, comprehensive risk value, risk color level, and corresponding handling operation identifier are associated and stored to form a risk handling record unit. This risk handling record unit serves as the data foundation for subsequent risk distribution map construction, risk status retrospection, and risk handling process tracing, and maintains consistency with the risk object identifier across different risk calculation cycles.

[0060] When the system operating environment or the structure of the risk object changes, a new historical time window is selected within the preset calibration period, and the overall risk value distribution is recalculated according to the same quantile rules, thereby updating the risk threshold. After the threshold is updated, the handling operation rules corresponding to each risk color level remain unchanged; the risk color level and corresponding handling status are dynamically adjusted only by changing the relationship between the overall risk value and the threshold.

[0061] S4: Associate the risk color level and handling status of the risk object with the spatial code, generate the risk distribution status at the spatial node level based on the power plant's spatial topology, and execute control operations according to the risk color level corresponding to the spatial risk node.

[0062] Furthermore, after determining the risk color level of each risk object and matching the corresponding handling rules, the system performs spatial association processing on the risk object based on its identifier and spatial attribute information. The spatial attribute information includes the equipment installation location, work area range, or environmental monitoring coverage area to which the risk object belongs, and is recorded in the system with fixed spatial codes or coordinate information, thereby establishing a one-to-one correspondence between the risk object and the physical space of the power plant.

[0063] During spatial association processing, the risk object identifier is used as an index to bind the resulting risk color level, comprehensive risk value, and disposal status with the corresponding spatial code, forming a spatial risk record unit that includes spatial location, risk level, and disposal status. Each spatial risk record unit corresponds to the current risk status of only one risk object within the same risk calculation cycle.

[0064] After constructing the spatial risk recording unit, based on the power plant's existing spatial topology, the spatial risk recording unit is mapped to a plant-level, system-level, or regional spatial model. During the mapping process, the system assigns the risk color level of the risk object to the corresponding spatial node according to the preset mapping relationship between the spatial code and the model node, so that the spatial node presents a risk color state consistent with its associated risk object within the current calculation cycle.

[0065] When multiple risk objects correspond to the same spatial node, the risk color of that spatial node is uniformly determined according to the established risk color level priority rules. The priority rules are based on the severity of the risk color level, ensuring that when multiple different risk levels exist for the same spatial node, the spatial node only displays the risk color state with the highest severity.

[0066] After determining the risk color of a spatial node, the risk color status of the spatial node, the set of associated risk object identifiers, and the corresponding handling status are recorded together to form a spatial risk status record. During system operation, when the risk color level of a certain risk object changes, the system synchronously updates the spatial risk record unit associated with that risk object and re-executes the spatial node risk color determination process to ensure that the spatial risk status always reflects the latest risk level judgment result. The update process does not change the risk object identifier and spatial code; it only updates the data fields related to the risk color level and handling status.

[0067] It should be noted that after constructing the spatial risk distribution status data, based on the risk color level corresponding to the spatial risk node and the established color-disposal rule mapping relationship, corresponding control operations are performed on the risk object and its associated spatial nodes. These control operations use the risk object identifier and spatial node code as the execution objects, ensuring consistency between control instructions and risk assessment results in both the object and spatial dimensions.

[0068] When a space risk node is at the red risk level, the system performs mandatory control operations on the risk objects associated with that space node, marking the risk object as a controlled state that cannot enter regular operation or work processes, and synchronously updating its disposal status field until its risk color level changes in a subsequent risk calculation cycle. During the period when the red risk status is maintained, the risk status record of the risk object is continuously retained, and no removal or downgrading processing is performed on it.

[0069] When a space risk node is at the orange risk level, the system performs restrictive control operations on the risk objects associated with that space node, imposes preset restrictions on their operation or work status, and includes the risk object in the key monitoring sequence. The system continues to determine the risk status of this risk object throughout subsequent risk calculation cycles until its risk color level changes within a range, at which point the corresponding control status is adjusted.

[0070] When a space risk node is at the yellow risk level, the system performs routine control operations on the risk objects associated with that space node, keeps their original operation or work status unchanged, and includes the risk status record of the risk object in the periodic inspection record.

[0071] When a space risk node is at the green risk level, the system only maintains a basic control status for the risk objects associated with that space node, does not impose additional restrictions on their operation or work processes, and only retains the necessary risk status records.

[0072] After completing the control operations for different risk color levels, the system associates and stores the risk object identifier, spatial node code, risk color level, corresponding control operation type, and execution time information to form a risk control execution record. This risk control execution record is stored in chronological order within the system to construct a complete record chain of the risk control process.

[0073] Upon entering the next risk calculation cycle, the processes of risk data collection, risk calculation, risk level determination, and spatial risk distribution update are re-executed, and the risk color level generated in the new cycle is compared with the risk control execution record of the previous cycle. When the risk color level changes, the system re-executes the corresponding control operations based on the new risk level and creates a new record entry in the risk control execution record, thus forming a closed-loop control process based on changes in risk level.

[0074] Example 2, one embodiment of the present invention, provides a risk distribution four-color map control system based on smart power plants, including a risk modeling and data aggregation module, a risk quantification and four-color classification module, and a spatial mapping and hierarchical control module.

[0075] The risk modeling and data aggregation module is used to uniformly identify equipment, operations, and environmental risk objects within the smart power plant, and to collect, synchronize, and structure and store multi-source risk raw indicators under the same time benchmark, forming a unified input dataset for risk calculation. The risk quantification and four-color classification module is used to normalize the multi-source risk raw indicators and calculate the comprehensive risk value, determine the risk threshold by combining historical distribution, and perform deterministic mapping of risk objects to red, orange, yellow, and green risk levels. The spatial mapping and hierarchical control module is used to associate the four-color risk levels with the power plant's spatial coding and spatial topology, generate the spatial risk distribution status, and execute corresponding control operations according to different risk color levels.

[0076] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the risk distribution four-color diagram control method based on smart power plants proposed in the above embodiment.

[0077] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the risk distribution four-color diagram control method based on smart power plants as proposed in the above embodiments.

[0078] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0080] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0081] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A risk distribution four-color map control method based on smart power plants, characterized in that, include: By uniformly identifying the equipment, operations, and environmental risk objects within a smart power plant, and collecting and structurally storing multi-source original risk indicators under the same time benchmark, a risk input dataset is constructed. The original indicators of equipment risk, operational risk and environmental risk for each risk object are normalized, and a comprehensive risk value is output by combining the maximum risk and the linkage between operation and environment. A fixed risk threshold is determined based on the historical distribution characteristics of the comprehensive risk value, and the comprehensive risk value is mapped to a four-color risk level of red, orange, yellow and green according to the threshold range; The risk color level and handling status of the risk object are associated with the spatial code, and the risk distribution status at the spatial node level is generated according to the spatial topology of the power plant. Control operations are performed according to the risk color level corresponding to the spatial risk node.

2. The risk distribution four-color map control method based on smart power plants as described in claim 1, characterized in that: The unified identification of equipment, operations, and environmental risk objects within a smart power plant includes... Based on the power plant equipment coding system, operation management coding system, and environmental monitoring point coding system, a unique object identifier is assigned to each risk object, and a risk object index relationship is established so that the object identifier corresponds to the corresponding equipment location, operation area, or environmental monitoring range.

3. The risk distribution four-color map management method based on smart power plants as described in claim 1 or 2, characterized in that: The collection and structured storage of multi-source risk raw indicators under the same time reference include, Equipment risk data, operational risk data, and environmental risk data are processed synchronously using a unified timestamp, and original risk indicators that form complete records within the time window are selected for processing within the preset risk calculation period; Using risk object identifiers and timestamps as dual indexes, the original indicators of multi-source risks are stored in a structured manner.

4. The risk distribution four-color map control method based on smart power plants as described in claim 3, characterized in that: The normalization process for the original indicators of equipment risk, operational risk, and environmental risk for each risk object includes... For the original risk indicators from different sources, corresponding upper and lower bound parameters are pre-set, and the original risk indicators are converted into normalized risk components according to a unified numerical conversion rule.

5. The risk distribution four-color diagram control method based on smart power plants as described in any one of claims 1, 2, and 4, characterized in that: The process involves normalizing the original indicators of equipment risk, operational risk, and environmental risk for each risk object, and then outputting a comprehensive risk value based on the maximum risk factor and the interaction between operations and the environment. The maximum risk component is identified as the dominant risk item in the normalized risk components. Taking into account the compensation contribution of the remaining risk components and the linkage between operational risk and environmental risk, a comprehensive risk value reflecting the current overall risk level of the risk object is generated.

6. The risk distribution four-color map control method based on smart power plants as described in claim 5, characterized in that: The process of determining a fixed risk threshold based on the historical distribution characteristics of the comprehensive risk value, and mapping the comprehensive risk value to four risk levels (red, orange, yellow, and green) according to the threshold range, includes: A sample set is formed by selecting comprehensive risk values ​​generated within a preset historical time window, sorting and statistically analyzing the sample set, and extracting the corresponding quantile values ​​as risk thresholds according to fixed quantile rules. The risk threshold remains unchanged within the same operating cycle.

7. The risk distribution four-color diagram control method based on smart power plants as described in any one of claims 1, 2, 4, and 6, characterized in that: The control operations performed based on the risk color level corresponding to the spatial risk node include: The risk color level is bound to the spatial code corresponding to the risk object, and the risk distribution status at the spatial node level is generated based on the power plant's spatial topology. If the risk color levels corresponding to spatial nodes are different, the control operations corresponding to the color levels shall be executed respectively, and the spatial risk status and control execution records shall be updated synchronously when the risk level changes.

8. A risk distribution four-color map control system based on smart power plants, employing the risk distribution four-color map control method based on smart power plants as described in any one of claims 1 to 7, characterized in that: It includes a risk modeling and data aggregation module, a risk quantification and four-color classification module, and a spatial mapping and hierarchical control module; The risk modeling and data aggregation module is used to uniformly identify equipment, operation and environmental risk objects in the smart power plant, and to collect, synchronize and structure and store multi-source risk raw indicators under the same time reference to form a unified input dataset for risk calculation. The risk quantification and four-color classification module is used to normalize the original indicators of multi-source risks and calculate the comprehensive risk value. It combines historical distribution to determine the risk threshold and performs a deterministic mapping of risk objects to red, orange, yellow and green risk levels. The spatial mapping and hierarchical control module is used to associate the four-color risk levels with the power plant's spatial coding and spatial topology to generate a spatial risk distribution status, and to perform corresponding control operations based on different risk color levels.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the risk distribution four-color diagram control method based on smart power plants as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the risk distribution four-color diagram control method based on smart power plants as described in any one of claims 1 to 7.

Images