Optical layout determination method and system

Abstract

The invention relates to the technical field of regional illumination determination, and provides an optical layout determination method and system.The optical layout determination method comprises the steps that sensors are arranged at the brightest point, the darkest point and the center point of a to-be-detected region respectively, initial illumination data are collected, and the optical layout is determined according to the inverse square ratio law and the change trend of the initial illumination data; preliminarily deducing the light source orientation; obtaining illumination data near the non-transparent body based on the initial illumination data and the degree of the included angle between the light and the normal, and solving the illumination data near the non-transparent body based on a least square method; s3, in combination with the logarithmic distance path loss model, performing weighted calculation on the basic illuminance of each light source direction, determining a first optical layout, dynamically adjusting a weight matrix by adopting a supervised Hebb learning rule, adjusting the first optical layout based on the weight matrix, defining an error function through a least square method, and obtaining a second optical layout; and removing abnormal data in the second optical layout and optimizing the estimated value of the illuminance of the light source to obtain the second optical layout.

Description

Technical Field

[0001] The present invention relates to the technical field of regional illuminance determination, and particularly to an optical layout determination method and system. Background Art

[0002] The determination of the regional illuminance of a lighting system is a key link in achieving efficient lighting design. In the prior art, it is usually the practice of configuring a sensor beside each LED lamp, and accumulating the illuminances of each light source through the simple illuminance superposition principle to construct the overall optical layout. Specifically, a large number of sensors are arranged in the lighting area, one is set beside each lighting device, and then the illuminance data measured by each sensor are simply added together to determine the illuminance distribution of the entire area.

[0003] However, this method has an obvious drawback, that is, a large number of sensors are required, which undoubtedly increases the cost and complexity of the system. Taking a 30-square-meter laboratory as an example, the traditional algorithm may require arranging a 3×3 array of sensors, a total of 9 sensors. The arrangement of a large number of sensors not only consumes manpower and material resources, but also may have data redundancy and instability in the process of data acquisition, transmission and processing, thus affecting the accuracy and reliability of the final optical layout. Summary of the Invention

[0004] Aiming at the above defects, the purpose of the present invention is to propose an optical layout determination method and system, aiming to fit the illuminance data of a single point into the illuminance data within a certain area by introducing the basic optical law, reduce the excessive dependence on a large number of sensor points, and significantly improve the stability and accuracy of the data.

[0005] To achieve this purpose, the present invention adopts the following technical solutions:

[0006] An optical layout determination method, the optical layout determination method includes the following steps:

[0007] S1: Set a sensor at the brightest point, the darkest point and the center point of the area to be measured respectively, collect the initial illuminance data, and preliminarily infer the light source orientation according to the inverse square law and the change trend of the initial illuminance data;

[0008] S2: Obtain the illuminance data near the non-transparent object in the area to be measured based on the initial illuminance data and the included angle degree between the light ray and the normal line, and solve a number of illuminance data near the non-transparent object based on the least square method to obtain the fitting parameters;

[0009] S3: Combine the logarithmic distance path loss model, calculate the basic illuminance in the direction of each light source by weighted calculation, determine the first optical layout, dynamically adjust the weight matrix using the supervised Hebb learning rule, adjust the first optical layout based on the weight matrix, define an error function by the least squares method, eliminate the abnormal data in the second optical layout and optimize the estimated value of the light source illuminance to obtain the second optical layout.

[0010] Preferably, in step S1, after setting a sensor at the brightest point, the darkest point and the center point of the area to be measured respectively, it includes eliminating the illuminance data within one meter of the non-transparent object in the initial illuminance data.

[0011] Preferably, in step S2, it includes:

[0012] Calculate the internal and external illuminance of the non-transparent object according to the inverse square law, and analyze the influence range of the light source through mathematical transformation;

[0013] The inverse square law satisfies the relation: where E represents the illumination intensity, r represents the distance from the light source, c represents the proportionality constant, and L represents the luminous intensity of the light source;

[0014] The mathematical transformation satisfies the relation:

[0015] Convert the illuminance data inside the non-transparent object by I(θ) = I0cosθ, and superimpose the illuminance data outside the non-transparent object with the illuminance data inside the object to obtain the illuminance data near the non-transparent object, satisfying E total = E out + I0cosθ;

[0016] where θ represents the angle between the light ray and the normal, I0 represents the initial intensity at the position of the non-transparent object, E total represents the illuminance data near the non-transparent object, E out represents the illuminance data outside the non-transparent object, and I0cosθ represents the illuminance data inside the non-transparent object.

[0017] Preferably, in step S2, use several illumination intensity data near the non-transparent object to construct an equation set by the inverse square law and adopt the least squares method to obtain the fitting parameters and

[0018] Preferably, in step S3, combine the logarithmic distance path loss model, calculate the basic illuminance E final satisfying the relation:

[0019]

[0020] where, wi Represents the sensor weight, E i Represents the illuminance in a certain light source direction;

[0021] Subsequently, the least squares method is used to fit the basic illuminance in each light source direction, and an error function is constructed: where E measuredi Represents the light intensity measured by the i-th sensor.

[0022] Preferably, in step S3, the weight matrix satisfies the relational expression:

[0023]

[0024] where, w new Represents the adjusted weight matrix, w old Represents the weight matrix before adjustment, η represents the learning rate used to control the step size of weight adjustment, O1 represents the optical layout vector before adjustment, O2 represents the optical layout vector after adjustment, O1 = [o 11 , o 12 , …, o 1n , O2 = [o 21 , o 22 , …, o 2n ;

[0025] Let the data vector measured by the sensor be S = [s1, S2, …, S m , adjust the weight matrix, and the adjustment result satisfies: R = W1 * S T , R represents the light-related result vector, and W1 represents the adjusted weight matrix.

[0026] Preferably, in step S3, it includes:

[0027] By Integrating the data of multiple sensors, when the sensor data is abnormal, the abnormal data can be identified and discarded by comparing the data of multiple sensors;

[0028] Construct the equation Combined with the error function to obtain the estimated value of E0, satisfying the relational expression:

[0029]

[0030] where, E0 represents the original illuminance of the light source, E i Represents the illuminance data of the i-th sensor, d i Represents the distance from the i-th sensor to the light source.

[0031] An optical layout determination system, which is applied to the optical layout determination method as described above. The optical layout determination system includes:

[0032] A position inference module, which is used to set a sensor at the brightest point, the darkest point and the center point of the area to be measured respectively, collect initial illuminance data, and preliminarily infer the light source orientation according to the inverse square law and the change trend of the initial illuminance data.

[0033] A fitting module, which is used to obtain the illuminance data near the non-transparent object in the area to be measured based on the initial illuminance data and the included angle between the light ray and the normal line, and solve a number of illuminance data near the non-transparent object based on the least square method to obtain fitting parameters.

[0034] A layout adjustment and optimization module, which is used to combine the logarithmic distance path loss model, weighted calculate the basic illuminance in each light source direction, determine the first optical layout, dynamically adjust the weight matrix using the supervised Hebb learning rule, adjust the first optical layout based on the weight matrix, define an error function through the least square method, eliminate abnormal data in the second optical layout and optimize the estimated value of the light source illuminance to obtain the second optical layout.

[0035] One of the above technical solutions has the following advantages or beneficial effects:

[0036] In the present invention, sensors are respectively set at the brightest point, the darkest point and the center point of the area to be measured, and the light source orientation is preliminarily inferred by using the inverse square law and the change trend of the initial illuminance data, reducing the number of sensors used and the system cost; based on the initial illuminance data and the included angle between the light ray and the normal line, the illuminance data near the non-transparent object is calculated, and the least square method is used to solve the fitting parameters, which can improve the accuracy and reliability of the data. Combining the logarithmic distance path loss model to weighted calculate the basic illuminance in each light source direction, determine the initial optical layout, and using the supervised Hebb learning rule to dynamically adjust the weight matrix, eliminate abnormal data and optimize the estimated value of the light source illuminance to obtain a more accurate optical layout. The present invention helps to reduce the dependence on sensors, reduce the system complexity and cost, and at the same time improve the authenticity and stability of optical layout determination. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0038] Figure 1It is a flowchart of the optical layout determination method provided by an embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of sensor settings for the optical layout determination method provided by an embodiment of the present invention;

[0040] Figure 3 It is a schematic diagram of optical layout adjustment for the optical layout determination method provided by an embodiment of the present invention;

[0041] Figure 4 It is a comparison diagram of the supervised hebb learning rule and the traditional method for the optical layout determination method provided by an embodiment of the present invention;

[0042] Figure 5 It is a schematic structural diagram of the optical layout determination system provided by an embodiment of the present invention. Detailed implementation manners

[0043] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0044] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "axial", "radial", "circumferential", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for facilitating the description of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.

[0045] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "a plurality" means two or more.

[0046] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0047] An optical layout determination method, as Figure 1 shown, in a preferred embodiment of the present invention, the optical layout determination method includes the following steps:

[0048] S1: Respectively set a sensor at the brightest point, the darkest point, and the center point of the area to be measured, collect the initial illuminance data, and preliminarily infer the light source orientation according to the inverse square law and the change trend of the initial illuminance data;

[0049] Specifically, using the inverse square law, that is, the illuminance is inversely proportional to the square of the distance from the light source, by setting sensors at the key points (the brightest point, the darkest point, and the center point, as Figure 2 shown) of the area to be measured to collect the initial illuminance data and analyzing the change trend of these data, the general orientation of the light source can be preliminarily inferred. This is because the illuminance difference at different positions can reflect the light source direction. For example, the brightest point is often close to the light source direction, while the darkest point may be far from the light source or blocked, and the center point provides an overall reference. Combining the data changes of them can effectively narrow the range of the light source orientation and lay a foundation for more accurate optical layout determination in the follow-up. Among them, the inverse square law is a basic law of optics, which is used to establish a relationship model between illuminance and distance to help extract light source orientation information from the initial data.

[0050] S2: Based on the initial illuminance data and the included angle between the light ray and the normal line, obtain the illuminance data near the non-transparent object in the area to be measured, and solve a number of illuminance data near the non-transparent object based on the least square method to obtain the fitting parameters;

[0051] Based on the initial illuminance data obtained in step S1, further consider the influence of the included angle between the light ray and the normal line on the illuminance near the non-transparent object. Since the light ray will undergo reflection, refraction and other phenomena when encountering the non-transparent object, resulting in illuminance changes, by combining the included angle between the light ray and the normal line and using relevant optical principles, calculate the illuminance data near the non-transparent object. Then use the least square method to solve these data to obtain the fitting parameters to more accurately describe the illuminance distribution law of this area and provide more detailed data support for more comprehensive optical layout analysis in the follow-up.

[0052] Among them, non-transparent objects refer to those that cannot allow light to pass through and will change the propagation path and illuminance distribution of light in the optical layout; the angle between the light ray and the normal reflects the angle at which the light ray is incident on the surface of the non-transparent object, affecting the reflection and refraction effects of light and thus changing the surrounding illuminance; the illuminance data is the light intensity information of each point in this area and is a key indicator for analyzing the optical layout; the fitting parameters are used to construct a mathematical model describing the illuminance distribution, making the model more conform to the actual measurement data, thereby improving the description accuracy of the optical layout.

[0053] Step S2 can deeply analyze the influence of non-transparent objects on the optical layout, making the obtained illuminance data and fitting parameters more accurately reflect the actual light situation, providing more comprehensive and detailed basic data for the subsequent comprehensive determination of the optical layout, and helping to improve the accuracy and reliability of the entire optical layout determination.

[0054] S3: Combine the log-distance path loss model, calculate the basic illuminance in each light source direction with weights, determine the first optical layout, dynamically adjust the weight matrix using the supervised Hebb learning rule, adjust the first optical layout based on the weight matrix, define an error function by the least squares method, eliminate abnormal data in the second optical layout and optimize the estimated value of the light source illuminance to obtain the second optical layout.

[0055] Specifically, combine the log-distance path loss model, calculate the basic illuminance in each light source direction with weights, and determine the first optical layout. The log-distance path loss model can consider the attenuation law of light during propagation, making the illuminance calculation more in line with the actual situation. On this basis, use the supervised Hebb learning rule to dynamically adjust the weight matrix, continuously optimize the weight distribution of the illuminance in each light source direction according to the actual measurement data to more accurately reflect the contribution of different light sources to the overall optical layout, as Figure 4 shown. At the same time, define an error function by the least squares method, eliminate abnormal data in the second optical layout, and further optimize the estimated value of the light source illuminance, so as to obtain a more accurate and stable second optical layout and complete the fine adjustment and optimization of the optical layout.

[0056] Among them, the logarithmic distance path loss model is a mathematical model that describes the attenuation of optical signals as the transmission distance increases, and is used to calculate the illuminance at different distances more precisely; the basic illuminance refers to the basic light intensity of each light source in different directions, and is the original data for constructing the optical layout; the first optical layout is a preliminary optical layout scheme obtained based on initial calculations and models; the supervised Hebb learning rule is a method that draws on the neural network learning mechanism and is used to dynamically adjust the weight matrix according to actual data to make the model more conform to the actual situation; the weight matrix is used to represent the relative importance or contribution degree of the illuminance in each light source direction in the overall optical layout, and its adjustment directly affects the accuracy of the optical layout; the error function is used to quantify the difference between the model calculation value and the actual measurement value, and the model parameters are optimized by minimizing the error function; abnormal data refers to measurement data that significantly deviates from the normal range or is inconsistent with other data, and may be caused by factors such as sensor failures and environmental interference; the second optical layout is a more accurate optical layout scheme obtained after removing abnormal data and optimizing the estimated values.

[0057] Preferably, in step S1, after setting a sensor at the brightest point, the darkest point, and the center point of the area to be measured respectively, it includes removing the illuminance data within one meter of the non-transparent object from the initial illuminance data.

[0058] Specifically, the principle of setting sensors at the brightest point, the darkest point, and the center point of the area to be measured and removing the illuminance data within one meter of the non-transparent object is that the brightest point and the darkest point can reflect the distribution characteristics of the strength of the light source, the center point provides an overall reference benchmark, and the data within one meter of the non-transparent object is removed because the data in this area is greatly affected by the non-transparent object and may be distorted, interfering with the accurate inference of the light source orientation. In this way, the quality and reliability of the initial illuminance data can be improved, and more accurate basic data can be provided for subsequent steps.

[0059] Preferably, in step S2, it includes:

[0060] Calculating the internal and external illuminance of the non-transparent object according to the inverse square law, and analyzing the influence range of the light source through mathematical transformation;

[0061] The inverse square law satisfies the relationship: where E represents the illuminance, r represents the distance from the light source, c represents the proportionality constant, and L represents the luminous intensity of the light source;

[0062] The mathematical transformation satisfies the relationship:

[0063] Converting the illuminance data inside the non-transparent object from I(θ) = I0cosθ, and superimposing the illuminance data outside the non-transparent object with the illuminance data inside the object to obtain the illuminance data near the non-transparent object, satisfying E total = Eout +I0cosθ;

[0064] where θ represents the degree of the angle between the light ray and the normal line, I0 represents the initial intensity at the position of the non-transparent body, and E total represents the illuminance data near the non-transparent body, and E out represents the illuminance data outside the non-transparent body, and I0cosθ represents the illuminance data inside the non-transparent body.

[0065] Among them, is used to analyze the illuminance relationship at different positions, so as to infer the influence range of the light source. The degree of the angle θ between the light ray and the normal line affects the reflection and refraction effects of the light ray, and thus changes the illuminance distribution; the initial intensity I0 is the initial illuminance at the position of the non-transparent body and is used to calculate the illuminance data inside the body; the illuminance data E out outside the non-transparent body and the illuminance data I0cosθ inside the body respectively represent the illuminance outside and inside the non-transparent body, and the total illuminance E near the non-transparent body is obtained by superposition total .

[0066] Generally speaking, based on the inverse square law and mathematical transformation, combined with the influence of the angle between the light ray and the normal line, the illuminance inside and outside the non-transparent body is calculated, and the influence range of the light source can be analyzed. By superimposing the illuminance data outside the non-transparent body and the illuminance data inside the body through these calculations, the illuminance data near the non-transparent body is obtained. This process can more accurately describe the influence of the non-transparent body on light, enabling the subsequent optimization of the optical layout to more effectively reflect the actual lighting situation, thereby realizing the determination of an efficient and accurate optical layout.

[0067] Preferably, in step S2, a system of equations is constructed using the inverse square law with several illumination intensity data near the non-transparent body, and the least squares method is used to obtain the fitting parameters and

[0068] The fitting parameters and respectively represent the estimated values of the proportionality constant and the light intensity of the light source, and are used to describe the characteristics of the light source and fit the illuminance data. This process can effectively fit the illuminance distribution near the non-transparent body and reduce the discreteness and error of the data.

[0069] Preferably, in step S3, combined with the logarithmic distance path loss model, the basic illuminance E in each light source direction is weighted and calculated final satisfies the relationship:

[0070]

[0071] where w i represents the sensor weight, and E i represents the illuminance in a certain light source direction;

[0072] Subsequently, the least squares method is used to fit the basic illuminance in the directions of each light source, and an error function is constructed: where E measuredi represents the light intensity measured by the i-th sensor.

[0073] Among them, the basic illuminance E i is the basic light intensity in the directions of each light source and is the original data for constructing the final illuminance model; the final illuminance E final is the comprehensive illuminance obtained by weighted calculation using the logarithmic distance path loss model and sensor data; the error function Error1 is used to quantify the difference between the model calculation value and the actual measurement value, and the model parameters are optimized by minimizing the error function; the least squares method can improve the accuracy of the optical layout.

[0074] Preferably, in step S3, the weight matrix satisfies the relational expression:

[0075]

[0076] where w new represents the adjusted weight matrix, w old represents the weight matrix before adjustment, η represents the learning rate for controlling the step size of weight adjustment, O1 represents the optical layout vector before adjustment, O2 represents the optical layout vector after adjustment, O1 = [o 11 , o 12 , …, o 1n , O2 = [o 21 , o 22 , …, o 2n ;

[0077] Let the data vector measured by the sensor be S = [s1, S2, …, S m , adjust the weight matrix, and the adjustment result satisfies: R = W1 * S T , R represents the light-related result vector, W1 represents the adjusted weight matrix, and its adjustment process is as Figure 3 shown.

[0078] Among them, the weight matrix w represents the relative importance of the illuminance in the directions of each light source in the overall optical layout. Dynamically adjusting the weight matrix can optimize the calculation of the optical layout; the learning rate η controls the step size of weight adjustment and determines the convergence speed of the learning process; the optical layout vector O represents the state of the optical layout, including the illuminance information in the directions of each light source; the sensor data vector S is the light intensity data collected by the sensor; the light-related result vector R is the final light result after adjusting the weight matrix, which can more accurately reflect the actual light situation and can improve the accuracy and adaptability of the optical layout.

[0079] Preferably, in step S3, it includes:

[0080] By integrating the data of multiple sensors, when the sensor data is abnormal, the abnormal data can be identified and discarded by comparing the data of multiple sensors;

[0081] Construct an equation Combined with the error function to obtain an estimated value of E0, satisfying the relationship:

[0082]

[0083] where E0 represents the original illuminance of the light source, E i represents the illuminance data of the i-th sensor, and d i represents the distance from the i-th sensor to the light source.

[0084] Specifically, the original illuminance E0 of the light source is the common reference value of all sensor data, representing the illuminance of the light source without occlusion and attenuation; the illuminance data E of the sensor i is the illuminance value actually measured by each sensor, reflecting the illuminance change of the light source at different positions; the distance d from the sensor to the light source i is a key factor affecting the illuminance, and the illuminance is inversely proportional to the square of the distance; the error term ∈i represents the error in the measurement data due to factors such as environmental interference and sensor accuracy. The error term ∈i is affected by factors such as distance and the original illuminance of the light source, ensuring that the finally obtained data is highly reliable and stable; the error function Error2 is used to quantify the difference between the model calculated value and the actual measured value, and the optimal parameter estimation value can be obtained by minimizing the error function.

[0085] An optical layout determination system, as Figure 5 shown, the optical layout determination system is applied to the optical layout determination method as described above. The optical layout determination system includes:

[0086] A position inference module, which is used to set a sensor at the brightest point, the darkest point and the center point of the area to be measured respectively, collect the initial illuminance data, and preliminarily infer the light source orientation according to the inverse square law and the change trend of the initial illuminance data;

[0087] A fitting module, which is used to obtain the illuminance data near the non-transparent object in the area to be measured based on the initial illuminance data and the included angle degree between the light ray and the normal line, and solve for the fitting parameters based on the least squares method for several illuminance data near the non-transparent object;

[0088] The layout adjustment and optimization module is used to combine the logarithmic distance path loss model, calculate the basic illuminance in the directions of each light source by weighted calculation, determine the first optical layout, dynamically adjust the weight matrix by using the supervised Hebb learning rule, adjust the first optical layout based on the weight matrix, define an error function by the least squares method, eliminate abnormal data in the second optical layout and optimize the estimated value of the light source illuminance, so as to obtain the second optical layout.

[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0090] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

Claims

1. An optical layout determination method, characterized in that, The optical layout determination method includes the following steps: S1: Set a sensor at the brightest point, the darkest point, and the center point of the area to be measured respectively, collect the initial illuminance data, and preliminarily infer the light source orientation according to the inverse square law and the change trend of the initial illuminance data; S2: Obtain the illuminance data near the opaque object in the area to be measured based on the initial illuminance data and the included angle between the light ray and the normal line, and solve several illuminance data near the opaque object based on the least squares method to obtain the fitting parameters; S3: Combine the logarithmic distance path loss model, calculate the basic illuminance in each light source direction by weighting, determine the first optical layout, dynamically adjust the weight matrix using the supervised Hebb learning rule, adjust the first optical layout based on the weight matrix, define the error function by the least squares method, eliminate the abnormal data in the second optical layout and optimize the estimated value of the light source illuminance to obtain the second optical layout.

2. The method for determining an optical layout according to claim 1, wherein In step S1, after setting a sensor at the brightest point, the darkest point, and the center point of the area to be measured respectively, it includes eliminating the illuminance data within one meter of the opaque object in the initial illuminance data.

3. The method for determining an optical layout according to claim 1, wherein In step S2, it includes: Calculate the internal and external illuminance of the opaque object according to the inverse square law, and analyze the influence range of the light source through mathematical transformation; The inverse square law satisfies the relation: where E represents the light intensity, r represents the distance from the light source, c represents the proportionality constant, and L represents the luminous intensity of the light source; The mathematical transformation satisfies the relation: Convert the illuminance data inside the non-transparent body from I(θ) = I0cosθ, and superimpose the illuminance data outside the non-transparent body with the illuminance data inside the body to obtain the illuminance data near the non-transparent body, satisfying E total = E out + I0cosθ; Where, θ represents the angle between the light ray and the normal, I0 represents the initial intensity at the position of the non-transparent body, E total represents the illuminance data near the non-transparent body, and E out represents the illuminance data outside the non-transparent body, and I0cosθ represents the illuminance data inside the non-transparent body.

4. The method for determining an optical layout according to claim 1, wherein In step S2, several illumination intensity data near the opaque object are used to construct an equation set by the inverse square law, and the least squares method is adopted to obtain the fitting parameters and 5. The method for determining an optical layout according to claim 1, wherein In step S3, combined with the log-distance path loss model, the basic illuminance E in each light source direction is calculated by weighting final Satisfy the relational expression: Among them, w i represents the sensor weight, and E i represents the illuminance in a certain light source direction; Subsequently, the least squares method is used to fit the basic illuminance in each light source direction, and an error function is constructed: where E measuredi represents the light intensity measured by the i-th sensor.

6. The method for determining an optical layout according to claim 1, characterized in that In step S3, the weight matrix satisfies the relational expression: Among them, w new represents the adjusted weight matrix, w old represents the weight matrix before adjustment, η represents the learning rate used to control the step size of weight adjustment, O1 represents the optical layout vector before adjustment, O2 represents the optical layout vector after adjustment, O1 = [o 11 , o 12 , …, o 1n , O2 = [o 21 , o 22 , …, o 2n ; Let the data vector measured by the sensor be S = [s1, s2, …, s m , and adjust the weight matrix, and the adjustment result satisfies: R = W1 * S T , where R represents the illumination-related result vector and W1 represents the adjusted weight matrix.

7. The method for determining an optical layout according to claim 1, wherein In step S3, it includes: By integrating the data of multiple sensors, when the sensor data is abnormal, the abnormal data can be identified and discarded by comparing the data of multiple sensors; Construct an equation Combined with the error function, an estimated value of E0 is obtained, satisfying the relation: Among them, E0 represents the original illuminance of the light source, and E i represents the illuminance data of the i-th sensor, and d i represents the distance from the i-th sensor to the light source.

8. An optical layout determination system, characterized in that, The optical layout determination system is applied to the optical layout determination method described in any one of claims 1-7. The optical layout determination system includes: A position inference module, which is used to set a sensor at the brightest point, the darkest point, and the center point of the area to be measured respectively, collect the initial illuminance data, and preliminarily infer the light source orientation according to the inverse square law and the change trend of the initial illuminance data; A fitting module, which is used to obtain the illuminance data near the opaque object in the area to be measured based on the initial illuminance data and the included angle between the light ray and the normal line, and solve several illuminance data near the opaque object based on the least squares method to obtain the fitting parameters; A layout adjustment and optimization module, which is used to combine the logarithmic distance path loss model, calculate the basic illuminance in each light source direction by weighting, determine the first optical layout, dynamically adjust the weight matrix using the supervised Hebb learning rule, adjust the first optical layout based on the weight matrix, define the error function by the least squares method, eliminate the abnormal data in the second optical layout and optimize the estimated value of the light source illuminance to obtain the second optical layout.

Images