An AI-based method for assessing the visibility of reactor control room panels

Abstract

This invention belongs to the field of reactor control room system design technology, specifically relating to an artificial intelligence-based method for assessing the visibility of reactor control room panels. The invention includes the following steps: obtaining control room panel and environmental design information; establishing a digital model of the control room based on the control room panel design information; collecting control room panel visibility rules and quantifiable indicators; constructing a visibility quantification assessment calculation method to perform multi-dimensional evaluation of the control room panel visibility design results; developing a visibility assessment program, inputting the 3D modeling results of the control room digital model and operator human body model into the program to assess the control room panel visibility; and judging the visibility assessment results. This invention utilizes virtual reality technology to complete the 3D digital modeling of the control room panel and automatically completes the visibility assessment of the control room panel design results using an independently developed program, greatly improving design efficiency and saving economic costs.

Description

Technical Field

[0001] This invention belongs to the field of reactor control room system design technology, specifically relating to an artificial intelligence-based method for assessing the visibility of reactor control room panels. Background Technology

[0002] For reactor system operation, the control room panel is the core component for operators to monitor and control the reactor. The visibility design of its human-machine interface (such as computer screens, panel display instruments, and panel operation buttons) directly affects the operator's decision-making speed, accuracy, and fatigue level. Therefore, system designers need to focus on analyzing and evaluating the visibility of the control room panel during its design.

[0003] Research revealed that current technologies primarily rely on manual evaluation, such as observation by ergonomics experts, simulation testing, or user feedback, to determine the rationality of the panel design's brightness, contrast, color scheme, and layout. However, this method has the following problems:

[0004] Highly subjective: Different evaluators may reach different conclusions based on their personal experience, leading to inconsistencies and disputes in the design evaluation results.

[0005] Time-consuming and labor-intensive: Manual measurement, simulation experiments and iterative feedback require a lot of time and resources, especially with complex tray layouts, involving multiple rounds of prototype modifications.

[0006] Unable to assess in real time: During the design iteration process, changes in the environment (such as lighting conditions, operator perspective) or design adjustments are difficult to quantify and assess in real time.

[0007] Insufficient quantification: The lack of objective quantitative indicators and standardized frameworks makes it difficult to make accurate comparisons with international nuclear safety standards (such as IEC 60964 or IAEA guidelines).

[0008] Ignoring dynamic factors: Traditional methods are difficult to incorporate dynamic simulations, such as operator eye tracking or fatigue simulation, resulting in incomplete design evaluation. Summary of the Invention

[0009] The technical problem solved by this invention is to provide a method for evaluating the visibility of reactor control room panels based on artificial intelligence. This method utilizes virtual reality technology to complete a three-dimensional digital model of the control room panel and uses an independently developed program to automatically evaluate the visibility of the control room panel design results, which greatly improves design efficiency and saves economic costs.

[0010] The technical solution adopted in this invention is as follows:

[0011] An artificial intelligence-based method for assessing the visibility of reactor control room panels includes the following steps:

[0012] S101, Obtain control room panel and environmental design information based on design documents and drawings;

[0013] S102, based on the control room panel design information, uses digital modeling technology and 3D modeling software to establish a digital model of the control room;

[0014] S103, Collect rules and quantifiable indicators for the visibility of control room panels;

[0015] S104, Construct a quantitative evaluation calculation method for visibility, and conduct multi-dimensional evaluation of the visibility design results of the control room panel;

[0016] S105, based on the visibility quantitative evaluation calculation method, develop a visibility evaluation program, and input the three-dimensional modeling results such as the digital model of the control room and the human body model of the operator into the program to evaluate the visibility of the control room panel.

[0017] The Rete intelligent matching algorithm is used to determine whether the rules used to construct the model meet the rules and indicator requirements organized in step S103.

[0018] The score V is calculated using the quantitative calculation method in step 104; a score above 0.85 is considered an excellent design, 0.7-0.85 is considered an acceptable design result, and a score below 0.7 is considered a design result that needs optimization.

[0019] S106: Discrimination of visibility assessment results.

[0020] The control room panel and environment design information includes the panel's external dimensions, the layout of equipment on the panel, and the control room environment.

[0021] The 3D modeling software is Unity 3D.

[0022] The rules and quantifiable indicators for the visibility of the control room panel are as follows:

[0023] We collected and organized specific requirements for the visibility design of control room panels, including lighting layout, brightness, saturation, contrast, horizontal viewing angle, and vertical viewing angle. Each requirement was refined into specific numerical indicators and items, which were then transformed into requirements that could be recognized by matching algorithms.

[0024] The method for constructing a visualization quantitative assessment calculation is as follows:

[0025] Determine the comprehensive visibility assessment index operator:

[0026] V=ω1B+ω2C+ω3S (1)

[0027] Where: ω1, ω2 and ω3 are weighting coefficients; luminance score B; regional contrast score C; saturation score S.

[0028] The formula for calculating the luminance fraction B is:

[0029]

[0030] The formula introduces Gaussian weights to emphasize the optimal brightness I. opt =128, standard deviation δ=50, I i Where N is the pixel brightness value, and I is the total number of pixels. min and I max This is the brightness threshold.

[0031] The formula for calculating the regional contrast score C is as follows:

[0032]

[0033] In the formula, M is the number of image blocks, and I... j,min and I j,max Let be the brightness threshold for pixel j.

[0034] The formula for calculating the saturation fraction S is as follows:

[0035]

[0036] In the formula, S i For pixel saturation, H i This is a hue safety factor; the formula introduces a hue safety deduction factor H. safe The aim is to avoid the overuse of red.

[0037] The weighting coefficients ω1, ω2, and ω3 are determined according to the recommended values ​​in the relevant human-machine interface design specifications, and their sum must be 1.

[0038] The visibility assessment result is determined as follows:

[0039] If the program determines that all design results of the control room panel meet the rules and index requirements, and the calculated result of the comprehensive visibility evaluation index V is greater than or equal to 0.7, then the current design result will be output as the final state.

[0040] If the program determines that any aspect of the control room panel design does not meet the rules and indicators, or that the overall visibility evaluation score is below 0.7, then repeat steps 103 to 105 until the final design meets the requirements.

[0041] The beneficial effects of this invention are:

[0042] (1) This invention provides a method for evaluating the visibility of reactor control room panels based on artificial intelligence, which is characterized by high efficiency, objectivity and intelligence.

[0043] (2) This invention provides a method for evaluating the visibility of reactor control room panels based on artificial intelligence. It uses artificial intelligence to develop the visibility design requirements of control room panels specified in regulations and standards into an independent program, and automatically analyzes whether the design results of control room panels meet the requirements of regulations and standards based on artificial intelligence models. This method can replace the traditional design method that requires separate manufacturing of wooden molds for physical verification, saving design costs and accelerating the iterative efficiency from design to verification.

[0044] (3) This invention provides a method for evaluating the visibility of reactor control room panels based on artificial intelligence. Through artificial intelligence technology, it realizes automated visual design evaluation of control room panels, supports full life cycle optimization from conceptual design to final verification, thereby improving the accuracy and efficiency of control room panel design. Attached Figure Description

[0045] To more clearly illustrate the embodiments of the present invention, the accompanying drawings used in describing the embodiments of the present invention will be briefly described below. Obviously, the drawings described below are merely some embodiments recorded in the present invention. Those skilled in the art can derive other drawings from the following drawings without any creative effort.

[0046] Figure 1 This invention provides a flowchart of a method for assessing the visibility of reactor control room panels based on artificial intelligence. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0048] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., refer to the orientation or positional relationship shown in the accompanying drawings, and are used only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0049] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or a connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0050] like Figure 1 As shown, the present invention provides a method for assessing the visibility of reactor control room panels based on artificial intelligence, comprising the following steps:

[0051] S101. Obtain control room panel and environmental design information based on design documents and drawings; including panel dimensions, equipment layout on the panel, control room environment (lighting brightness, saturation, contrast), etc.

[0052] S102, based on the control room panel design information, uses digital modeling technology and 3D modeling software to establish a digital model of the control room;

[0053] In this embodiment, the obtained design information is used to create a 3D model based on Unity 3D software;

[0054] S103, collect rules and quantifiable indicators for the visibility of control room consoles; specifically: collect and organize specific requirements for the visibility design of control room consoles, including lighting layout, lighting brightness, saturation, contrast, horizontal viewing angle, vertical viewing angle, etc., refine each requirement one by one to obtain specific numerical indicators and items, and transform them into requirements that can be recognized by matching algorithms.

[0055] S104. Construct a quantitative evaluation and calculation method for visibility to conduct a multi-dimensional evaluation of the visibility design results of the control room panel.

[0056] Determine the comprehensive visibility assessment index operator:

[0057] V=ω1B+ω2C+ω3S (1)

[0058] Where: ω1, ω2, and ω3 are weighting coefficients; luminance score B; regional contrast score C; saturation score S;

[0059] The formula for calculating the luminance fraction B is:

[0060]

[0061] The formula introduces Gaussian weights to emphasize the optimal brightness I. opt=128, standard deviation δ=50, I i Where N is the pixel brightness value, and I is the total number of pixels. min and I max The brightness threshold is (0-255).

[0062] The formula for calculating the regional contrast score C is as follows:

[0063]

[0064] In the formula, M is the number of image blocks, and I... j,min and I j,max The brightness threshold (0-255) for pixel j.

[0065] The formula for calculating the saturation fraction S is as follows:

[0066]

[0067] In the formula, S i For pixel saturation, H i This is the hue safety factor. The formula incorporates a hue safety deduction factor H. safe The aim is to avoid the overuse of red.

[0068] The weighting coefficients ω1, ω2, and ω3 are determined according to the recommended values ​​in the relevant human-machine interface design specifications, and their sum must be 1.

[0069] S105, based on the visibility quantitative evaluation calculation method, develop a visibility evaluation program, and input the three-dimensional modeling results such as the digital model of the control room and the human body model of the operator into the program to evaluate the visibility of the control room panel.

[0070] The Rete intelligent matching algorithm is used to determine whether the rules used to construct the model meet the rules and indicator requirements organized in step S103.

[0071] The score V is calculated using the quantitative calculation method in step 104. A score above 0.85 is considered an excellent design, 0.7-0.85 is considered an acceptable design result, and a score below 0.7 is considered a design result that needs optimization.

[0072] S106: Discrimination of visibility assessment results.

[0073] If the program determines that all design results of the control room panel meet the rules and index requirements, and the calculated result of the comprehensive visibility evaluation index V is greater than or equal to 0.7, then the current design result will be output as the final state.

[0074] If the program determines that any aspect of the control room panel design does not meet the rules and indicators, or that the overall visibility evaluation score is below 0.7, then repeat steps 103 to 105 until the final design meets the requirements.

[0075] Example

[0076] Step 1: First, obtain the design information of the control room panel based on the design drawings provided by the designer, including: panel shape, panel dimensions, equipment layout on the panel, and equipment dimensions on the panel. Then, obtain relevant information on the control room environment design based on the control room system design specifications provided by the designer, including: lighting layout, lighting brightness, saturation, and contrast.

[0077] Step 2: Collect and summarize the design requirements for the visibility of the control room panel from various design specifications, and organize the qualitative and quantitative requirements of the design specifications into quantitative rules. For example, the requirement of an average illuminance of 100-500 lx and an illumination uniformity ≥0.7 can be expressed as the rules shown in Table 1.

[0078] Table 1. Visibility Rules (Partial)

[0079]

[0080]

[0081] Step 3: Based on the obtained panel and environment design information, use Unity3D to create a 3D model of the control room panel and environment to obtain the 3D model of the design output and the constructed 3D model.

[0082] Step 4: Write a program to evaluate the visibility of the 3D model. First, compare the 3D model with the quantization rules using the Rete intelligent matching algorithm; after comparing and outputting qualified results, calculate the brightness score B, regional contrast score C, and saturation score S, and calculate the visibility evaluation score V according to the set weight coefficients; the evaluation calculation result shows that V≥0.7, the 3D model has passed two visibility evaluation steps, and the program judges the design as a qualified visibility design.

[0083] While those skilled in the art will recognize that the present invention is not limited to the details of the exemplary embodiments described above, and that it can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention, the embodiments should be considered illustrative and non-limiting in all respects. The scope of the invention is defined by the appended claims rather than the foregoing description, and therefore all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0084] Furthermore, it should be understood that although the present invention is described according to embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A method for assessing the visibility of reactor control room panels based on artificial intelligence, characterized in that, Includes the following steps: S101, Obtain control room panel and environmental design information based on design documents and drawings; S102, based on the control room panel design information, uses digital modeling technology and 3D modeling software to establish a digital model of the control room; S103, Collect rules and quantifiable indicators for the visibility of control room panels; S104, Construct a quantitative evaluation calculation method for visibility, and conduct multi-dimensional evaluation of the visibility design results of the control room panel; S105, based on the visibility quantitative evaluation calculation method, develop a visibility evaluation program, and input the three-dimensional modeling results such as the digital model of the control room and the human body model of the operator into the program to evaluate the visibility of the control room panel. The Rete intelligent matching algorithm is used to determine whether the rules used to construct the model meet the rules and indicator requirements organized in step S103. The score V is calculated using the quantitative calculation method in step 104; a score above 0.85 is considered an excellent design, 0.7-0.85 is considered an acceptable design result, and a score below 0.7 is considered a design result that needs optimization. S106: Discrimination of visibility assessment results.

2. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 1, characterized in that, The control room panel and environment design information includes the panel's external dimensions, the layout of equipment on the panel, and the control room environment.

3. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 1, characterized in that, The 3D modeling software is Unity 3D.

4. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 1, characterized in that, The rules and quantifiable indicators for the visibility of the control room panel are as follows: We collected and organized specific requirements for the visibility design of control room panels, including lighting layout, brightness, saturation, contrast, horizontal viewing angle, and vertical viewing angle. Each requirement was refined into specific numerical indicators and items, which were then transformed into requirements that could be recognized by matching algorithms.

5. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 1, characterized in that, The method for constructing a visualization quantitative assessment calculation is as follows: Determine the comprehensive visibility assessment index operator: V=ω1B+ω2C+ω3S (1) Where: ω1, ω2 and ω3 are weighting coefficients; luminance score B; regional contrast score C; saturation score S.

6. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 5, characterized in that, The formula for calculating the luminance fraction B is: The formula introduces Gaussian weights to emphasize the optimal brightness I. opt =128, standard deviation δ=50, I i Where N is the pixel brightness value, and I is the total number of pixels. min and I max This is the brightness threshold.

7. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 5, characterized in that, The formula for calculating the regional contrast score C is as follows: In the formula, M is the number of image blocks, and I... j,min and I j,max Let be the brightness threshold for pixel j.

8. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 5, characterized in that, The formula for calculating the saturation fraction S is as follows: In the formula, S i For pixel saturation, H i This is a hue safety factor; the formula introduces a hue safety deduction factor H. safe The aim is to avoid the overuse of red.

9. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 5, characterized in that, The weighting coefficients ω1, ω2, and ω3 are determined according to the recommended values ​​in the relevant human-machine interface design specifications, and their sum must be 1.

10. The method for assessing the visibility of reactor control room panels based on artificial intelligence according to claim 1, characterized in that, The visibility assessment result is determined as follows: If the program determines that all design results of the control room panel meet the rules and index requirements, and the calculated result of the comprehensive visibility evaluation index V is greater than or equal to 0.7, then the current design result will be output as the final state. If the program determines that any aspect of the control room panel design does not meet the rules and indicators, or that the overall visibility assessment score is below 0.7, then repeat steps 103 to 105 until the final design result meets the requirements.

Images