Theater light adaptive regulation and control method and system

Abstract

The invention relates to the technical field of light control, in particular to a theater light self-adaptive regulation and control method and system, and the method comprises the following steps: extracting the story line change and stage setting information uploaded by a sensor in real time from a theater, initializing a Bayesian network, capturing and simulating the dynamic environment of the theater, and carrying out the self-adaptive regulation and control of the theater light. And according to the data acquired in real time, adjusting top layer nodes of the Bayesian network, and generating a theater situation model. According to the invention, by capturing and simulating the dynamic environment of the theater, the light can be adjusted more accurately to adapt to the real-time change in the theater, and the response speed and precision of the light system are improved. Furthermore, the ideal illumination intensity of each lighting device is selected through continuous iterative calculation and probability distribution analysis, and the consistency of the overall lighting effect and the visual aesthetic feeling of the stage are improved. A conditional random field model is introduced to map the fault probability and the interdependence between the lighting devices, and the accuracy and the timeliness of fault detection are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting control, and in particular to a method and system for adaptively controlling theatre lighting. Background Art

[0002] The field of lighting control technology involves methods and systems that use electronic and mechanical devices to manage and adjust lighting. The field covers everything from basic dimmers and switches to complex automation systems and intelligent lighting control solutions. It is widely used in residential, commercial, industrial and urban lighting to achieve precise control of light intensity, color and direction. By controlling the light, energy use can be optimized, scene-specific lighting effects can be achieved, and the flexibility and efficiency of light use can be improved. Intelligent lighting systems may also integrate sensors and network technologies to achieve remote control and environmental adaptation functions.

[0003] Among them, the theater lighting adaptive control method is a lighting control technology designed for theaters and other performance venues. It can automatically adjust lighting parameters according to the performance dynamics on the stage. The method uses sensors and software to monitor the performance process to automatically adjust the brightness, color, direction and effect of the lights to ensure that the stage lighting is perfectly matched with the performance content. It not only enhances the visual appeal and emotional expression of the performance, but also improves the efficiency and ease of operation of the lighting system.

[0004] Although existing technologies can automatically adjust lighting parameters according to the performance dynamics, most of them rely on basic sensors and software monitoring, and fail to deeply analyze the interdependence between lighting equipment or predict potential failures, resulting in unexpected lighting failures during theater performances, affecting the continuity of the performance and the audience's viewing experience. In addition, existing technologies are usually not sensitive enough when dealing with real-time changes, and it is difficult to accurately adjust to the optimal lighting intensity in real time, affecting the overall presentation of stage effects, resulting in a decrease in the perfect combination of visual effects and performing arts, and ultimately reducing audience satisfaction. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a theater lighting adaptive control method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for adaptively controlling theater lighting, comprising the following steps:

[0007] Extract the plot changes and stage setting information uploaded by sensors in real time from the theater, initialize the Bayesian network, capture and simulate the dynamic environment of the theater, and adjust the top nodes of the Bayesian network according to the real-time data to generate a theater situation model;

[0008] According to the theater situation model, the state of the lighting equipment is adjusted, and the ideal light intensity of each lighting equipment is selected through continuous iterative calculation and probability distribution analysis to generate an optimized lighting configuration;

[0009] Taking the optimized lighting configuration as a basis, introducing a conditional random field model, initializing model parameters, inputting historical fault data and real-time performance indicators of the lighting, updating and adjusting the conditional random field model, mapping the fault probability and interdependency between lighting devices, and generating a fault prediction model;

[0010] The fault prediction model is used to continuously monitor the lighting, identify and locate potential fault areas, adjust the corresponding lighting equipment according to the optimized lighting configuration, and generate lighting control results.

[0011] As a further solution of the present invention, the steps of acquiring the theater situation model are specifically as follows:

[0012] Collect data from theater sensors in real time, including plot changes and stage setting information, using the formula:

[0013]

[0014] Calculate the information entropy of the current state of the theater and generate the data entropy value IG;

[0015] Among them, p i represents the probability of the i-th data point, n is the total number of data points, α is the adjustment coefficient used to enhance the influence of the data point, and i is used to index the data point;

[0016] Based on the data entropy value IG, the formula is adopted:

[0017]

[0018] Determine the weight of each data type and get the weight value W of the j-th data j ;

[0019] Among them, λ is a tuning parameter used to control the influence of entropy value, IG j represents the information gain of the jth class of data, γ is a weighted adjustment factor used to balance the variability of information gain, represents the average information gain of all data, k is the index in the summation, and e represents the base of the natural logarithm;

[0020] According to the weight value W of the j-th type of data j , initialize and update the top nodes of the Bayesian network, merge the data sources through the weighted average method, and use the formula:

[0021]

[0022] Update the state N of the top node of the Bayesian network top , generate a theater situation model;

[0023] Among them, X j is the observed value of the jth type of data, β is the minimum adjustment factor, and min represents the function of taking the minimum value.

[0024] As a further solution of the present invention, the step of obtaining the state of the lighting device is specifically as follows:

[0025] Using the state N of the top node of the Bayesian network top , the ideal light intensity of each lighting device is evaluated using the formula:

[0026]

[0027] Calculate the light intensity I required for each lighting device m m ;

[0028] Among them, m represents the number of the lighting equipment, C m is the configuration parameter corresponding to the mth lighting device, δ1 is the adjustment coefficient, which controls the sensitivity of temperature influence, T1 is the current temperature of the theater, T ref1 is the reference temperature, e represents the base of the natural logarithm, used for exponential operations;

[0029] Based on the illumination intensity I required by each lighting device m m The value of is, using the formula:

[0030]

[0031] Adjust the light output of each lighting device m to get the current setting status S of the lighting device m ;

[0032] Among them, V total is the total light resource, Indicates that for all lighting equipment m' q The ideal light intensity is summed, q is used as the index of the summation, and n is the total number of data points.

[0033] As a further solution of the present invention, the step of obtaining the optimized lighting configuration is specifically as follows:

[0034] According to the current setting state S of the lighting device m , using the formula:

[0035]

[0036] Calculate the deviation of each lighting device from the average ideal light intensity and obtain the deviation value D of lighting device mm ;

[0037] Where V is the total lighting resource, n is the total number of data points, b is the adjustment amplitude, cos is the cosine function used to simulate periodic changes, and ω is the adjustment frequency;

[0038] Based on the deviation value D of the lighting device m m , using the formula:

[0039]

[0040] Adjust the light intensity and calculate the ideal light intensity L after the light equipment m is adjusted m ;

[0041] Among them, λ is the adjustment factor used to control the adjustment amplitude, exp is the exponential function used to adjust the response sensitivity, k is the response sensitivity parameter, and μ is the threshold of deviation adjustment;

[0042] Analyze the ideal light intensity L after adjusting the lighting equipment m m Whether the optimal configuration is achieved, the formula is:

[0043]

[0044] Calculate the deviation G between the adjusted overall effect and the ideal state to obtain the optimized lighting configuration.

[0045] As a further solution of the present invention, the acquisition step of updating and adjusting the conditional random field model is specifically:

[0046] Input historical fault data F a and real-time performance index P b , using the formula:

[0047] H c =α1·F a +β1·P b

[0048] Construct a dataset H that reflects the current state c ;

[0049] Among them, α1 is the weight coefficient of historical fault data, and β1 is the weight coefficient of real-time performance indicators;

[0050] Based on the dataset H c The deviation value G of the adjusted overall effect from the ideal state is calculated using the formula:

[0051]

[0052] Update the conditional random field model to reflect the current lighting equipment status and predict the failure probability, and obtain the updated model parameters θ d ;

[0053] Among them, γ1 is the coefficient for adjusting the model update, and log is the natural logarithm function used to convert the ratio to the logarithmic scale.

[0054] As a further solution of the present invention, the steps of acquiring the fault prediction model are specifically as follows:

[0055] Using the updated model parameters θ d , using the formula:

[0056] P e =1-exp(-σ1·θ d )

[0057] Calculate the failure probability of the lighting equipment and obtain the failure probability value P e ;

[0058] Among them, σ1 is a scaling factor used to adjust the calculation sensitivity of the failure probability, and exp is an exponential function used to calculate the probability decay, reflecting the rate at which the failure probability changes with the model parameters;

[0059] According to the failure probability value P e , using the formula:

[0060]

[0061] Analyze and map the interdependencies between each lighting device to obtain the dependency strength A of another device r r ;

[0062] Among them, φ mr is the lighting equipment characteristic factor, describing the influence of lighting equipment m on the properties of another lighting equipment r, ω mr is the mutual influence weight between lighting devices, quantifying the influence of lighting device m on device r, m' represents the total number of lighting devices, and v is used to iterate and accumulate each φ mr ·ω mr The value of

[0063] The dependency strength A of the rth device r The data integration is done by using the formula:

[0064]

[0065] Calculate the probability M of normal operation of all lighting equipment f , and obtain the fault prediction model;

[0066] Among them, r represents the index, which is used to iterate each (1-Ar ) value.

[0067] As a further solution of the present invention, the step of obtaining the lighting control result is specifically as follows:

[0068] Based on the probability M that all lighting equipment is operating normally f , using the formula:

[0069]

[0070] Calculate the deviation value Z for each lighting device m ;

[0071] Among them, L m is the current light intensity of the mth lighting device, is the ideal light intensity of the mth lighting device predicted based on the current environmental conditions and other relevant inputs, T m is the current temperature of the mth lighting device, α m is the adjustment coefficient and temperature sensitivity coefficient for the mth lighting device;

[0072] According to the deviation value Z of each lighting device r , using the formula:

[0073]

[0074] Set the threshold θ of the mth lighting device m , identify the faulty lighting equipment, and obtain the value Y of the mth lighting equipment exceeding the threshold m ;

[0075] According to the optimized lighting configuration and the value Y of the mth lighting device exceeding the threshold m , using the formula:

[0076]

[0077] Adjust the corresponding lighting equipment to obtain the adjusted light intensity B of the mth lighting equipment m ;

[0078] Among them, L opt，m is the optimized ideal light intensity of the mth lighting device, L fault，m is the adjusted light intensity of the mth lighting device when it is in a fault state, Y m is the fault mark of the mth lighting device, Y avg is the average value of all lighting equipment fault marks, σ m is the adjustment factor used to adjust Y m With the mean fault mark Y avgThe impact of the difference between |Y m -Y avg | is an absolute value function, which calculates the difference between the fault mark of the mth lighting device and the average value of the fault marks of all lighting devices.

[0079] A theater lighting adaptive control system, the theater lighting adaptive control system is used to execute the theater lighting adaptive control method, the system comprises:

[0080] The situation modeling module analyzes plot changes and stage settings based on data uploaded by sensors in the theater, adjusts the top nodes of the Bayesian network, captures the dynamic environment of the theater in real time, and generates a theater situation model;

[0081] The lighting configuration module selects the ideal lighting intensity of each lighting device based on the theater scenario model, calculates the lighting distribution of the lighting device, iteratively optimizes the configuration until it matches the scene requirements, and generates an optimized lighting configuration;

[0082] The model initialization module inputs historical fault data and real-time performance indicators based on the optimized lighting configuration, initializes model parameters, and generates a conditional random field model;

[0083] The fault mapping module updates parameters based on the conditional random field model, maps the fault probabilities and dependencies between multiple lighting devices, and generates a fault prediction model;

[0084] The monitoring and control module continuously monitors the lighting equipment based on the fault prediction model, identifies potential fault areas, adjusts the lighting equipment according to the optimized lighting configuration, and generates a lighting control result.

[0085] Compared with the prior art, the advantages and positive effects of the present invention are:

[0086] In the present invention, by capturing and simulating the dynamic environment of the theater, the lighting can be adjusted more accurately to adapt to the real-time changes in the theater, and the response speed and accuracy of the lighting system can be improved. Furthermore, the ideal light intensity of each lighting device is selected through continuous iterative calculation and probability distribution analysis, which improves the consistency of the overall lighting effect and the aesthetics of the stage vision. The conditional random field model is introduced to map the failure probability and interdependence between lighting devices, which effectively improves the accuracy and timeliness of fault detection, reduces maintenance costs and the risk of unexpected shutdowns, and improves the stability and reliability of the entire lighting system. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0088] Figure 2 is a flow chart of the steps of obtaining the theater situation model of the present invention;

[0089] Figure 3 A flow chart of the steps for obtaining the state of a lighting device according to the present invention;

[0090] Figure 4 A flow chart of the steps for obtaining the lighting configuration optimized for the present invention;

[0091] Figure 5 A flowchart of the acquisition steps for updating and adjusting the conditional random field model of the present invention;

[0092] Figure 6 A flowchart of the steps of acquiring the fault prediction model of the present invention;

[0093] Figure 7 The figure is a flow chart of the steps for obtaining the lighting control results of the present invention. DETAILED DESCRIPTION

[0094] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0095] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing 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 therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0096] See also Figure 1 The present invention provides a technical solution: a method for adaptively controlling theater lighting, comprising the following steps:

[0097] S1: Extract the plot changes and stage setting information uploaded by sensors in real time from the theater, initialize the Bayesian network, capture and simulate the dynamic environment of the theater, and adjust the top nodes of the Bayesian network according to the real-time data to generate a theater situation model;

[0098] S2: According to the theater situation model, adjust the state of lighting equipment, select the ideal light intensity of each lighting equipment through continuous iterative calculation and probability distribution analysis, and generate the optimized lighting configuration;

[0099] S3: Taking the optimized lighting configuration as the basis, the conditional random field model is introduced, the model parameters are initialized, the historical fault data and real-time performance indicators of the lighting are input, the conditional random field model is updated and adjusted, the fault probability and interdependency between lighting devices are mapped, and the fault prediction model is generated;

[0100] S4: Use the fault prediction model to continuously monitor the lighting, identify and locate potential fault areas, adjust the corresponding lighting equipment according to the optimized lighting configuration, and generate lighting control results;

[0101] The theater situation model includes dynamic change nodes of stage settings, real-time update nodes of plot progression, and probabilistic nodes of the impact of changes on lighting settings. The optimized lighting configuration includes the brightness level, color temperature range selection and beam projection angle of lighting equipment adjustments. The fault prediction model includes the functional dependency diagram of lighting equipment, historical failure rate data and probabilistic evaluation of current performance indicators. The lighting control results include adjusted light intensity, color matching and projection direction optimization.

[0102] See also Figure 2 ,The specific steps for obtaining the theater situation model are:

[0103] S111: Collect data from theater sensors in real time. The data includes plot changes and stage setting information. The formula is:

[0104]

[0105] Calculate the information entropy of the current state of the theater and generate the data entropy value IG;

[0106] Among them, p i represents the probability of the i-th data point, n is the total number of data points, α is the adjustment coefficient used to enhance the influence of the data point, and i is used to index the data point;

[0107] S112: Based on the data entropy value IG, the formula is:

[0108]

[0109] Clarify the weight of each data type and get the weight value W of the j-th data j ;

[0110] Among them, λ is a tuning parameter used to control the influence of entropy value, IG j represents the information gain of the jth class of data, γ is a weighted adjustment factor used to balance the variability of information gain, represents the average information gain of all data, k is the index in the summation, and e represents the base of the natural logarithm;

[0111] S113: Based on the weight value W of the j-th type of data j, initialize and update the top nodes of the Bayesian network, merge the data sources through the weighted average method, and use the formula:

[0112]

[0113] Update the state N of the top node of the Bayesian network top , generate a theater situation model;

[0114] Among them, X j is the observed value of the jth type of data, β is the minimum adjustment factor, which is used to strengthen the influence of the lowest data point, and min represents the function of taking the minimum value.

[0115] The calculation process is as follows:

[0116] For the formula:

[0117]

[0118] Assume there are five data points and the probability distribution is assumed to be, p = [0.1, 0.2, 0.3, 0.2, 0.2];

[0119] Set the adjustment coefficient α to 0.5.

[0120] The first part of calculating information entropy:

[0121]

[0122] The second part of calculating information entropy:

[0123]

[0124] IG=1.85+0.235=2.085

[0125] This value indicates that the current state of the theater has a high information entropy, showing greater uncertainty and change.

[0126] For the formula:

[0127]

[0128] Assuming λ=1,γ=0.1, the previous IG j The IG value calculated in the previous step is 2.085. is the average information gain assumed to be 2.

[0129] Calculate a single weight W j :

[0130]

[0131] The weight reflects the importance of this type of data relative to other data.

[0132] For the formula:

[0133]

[0134] Assume β = 0.05, and assume that X j The values ​​of are [3, 5, 2, 4, 6].

[0135] Calculate the network top-level node status N top :

[0136] N top =0.115·(3+5+2+4+6)+0.05·2=0.115·20+0.1=2.3+0.1=2.4

[0137] This value indicates the comprehensive state of the entire network taking into account the effects of all input data and the minimum value.

[0138] See also Figure 3 , the specific steps to adjust the lighting device status are:

[0139] S121: Use the state N of the top node of the Bayesian network top , the ideal light intensity of each lighting device is evaluated using the formula:

[0140]

[0141] Calculate the light intensity I required for each lighting device m m ;

[0142] Among them, m represents the number of the lighting equipment, C m is the configuration parameter corresponding to the mth lighting device, δ1 is the adjustment coefficient, which controls the sensitivity of temperature influence, T1 is the current temperature of the theater, T ref1 is the reference temperature, e is the base of the natural logarithm,

[0143] For exponential operations;

[0144] S122: Based on the required illumination intensity I of each lighting device m m The value of is, using the formula:

[0145]

[0146] Adjust the light output of each lighting device m to get the current setting status S of the lighting device m ;

[0147] Among them, V total is the total light resource, Indicates that for all lighting equipment m' qThe ideal light intensity is summed, q is used as the index of the summation, and n is the total number of data points.

[0148] The calculation process is as follows:

[0149] For the formula:

[0150]

[0151] Assumptions:

[0152] N top =2.4 (top-level node status, which can be understood as the comprehensive score given by the theater situation model);

[0153] C m =0.8 (configuration parameter of the lighting device, indicating the baseline adjustment number of the lighting intensity of the lighting device);

[0154] δ1=0.1 (adjustment coefficient, affecting the sensitivity of temperature to light);

[0155] T1 = 25°C (current theater temperature);

[0156] T ref1 =20℃(reference temperature);

[0157] Calculate the effect of temperature differences:

[0158]

[0159] Calculate the ideal light intensity:

[0160] The ideal light intensity of lighting device m is about 1.196, which means that given the theater situation model and the current temperature conditions, the lighting device should adjust its light output to an intensity close to 1.2 to match the ideal setting.

[0161] For the formula:

[0162]

[0163] Assumptions:

[0164] I m =1.196 (calculated previously);

[0165] V total =100 (total system lighting resources, in lumens);

[0166] Assume there are 5 lighting devices, each m' q Same, 1.196;

[0167] Calculate the ideal sum of light intensity for all lighting devices:

[0168]

[0169] Calculate the actual output state:

[0170]

[0171] The actual output state of lighting device m should be adjusted to 44.7 lumens. This indicates that in order to achieve the ideal light intensity, the lighting device needs a relatively low light output under the total system resources, which may be because the lighting device is closer to the ideal state than other lighting devices or other lighting devices require more light resources.

[0172] See also Figure 4 , the steps to obtain the optimized lighting configuration are as follows:

[0173] S211: According to the current setting status of the lighting equipment S m , using the formula:

[0174]

[0175] Calculate the deviation of each lighting device from the average ideal light intensity and obtain the deviation value D of lighting device m m ;

[0176] Where V is the total lighting resource, n is the total number of data points, b is the adjustment amplitude, cos is the cosine function used to simulate periodic changes, and ω is the adjustment frequency;

[0177] S212: Deviation value D based on lighting device m m , using the formula:

[0178]

[0179] Adjust the light intensity and calculate the ideal light intensity L after the light equipment m is adjusted m ;

[0180] Among them, λ is the adjustment factor used to control the adjustment amplitude, exp is the exponential function used to adjust the response sensitivity, k is the response sensitivity parameter, and μ is the threshold of deviation adjustment;

[0181] S213: Analyze the ideal light intensity L after adjusting the lighting equipment m m Whether the optimal configuration is achieved, the formula is:

[0182]

[0183] Calculate the deviation value G between the adjusted overall effect and the ideal state to obtain the optimized lighting configuration;

[0184] The calculation process is as follows:

[0185] For the formula:

[0186]

[0187] Assume S m =50 lumens, V = 1000 lumens, n = 10, b = 5, ω = 0.5, u = 1;

[0188] Calculate the average ideal light intensity for each light fixture:

[0189]

[0190] Calculate the adjustment factor:

[0191] b·cos(ω·u)=5·cos(0.5·1)≈5·0.877=4.385

[0192] Calculate the deviation:

[0193] D m =|50-(100+4.385)|=|50-104.385|=54.385 lumens

[0194] The deviation of lighting device m is 54.385 lumens, which means that the actual light intensity of the lighting device is about 54 lumens lower than the ideal state.

[0195] For the formula:

[0196]

[0197] Assume λ = 0.1, k = 0.01, μ = 50;

[0198] Calculate the value of the exponential part:

[0199] exp(-k·(D m -μ))=exp(-0.01·(54.385-50))=exp(-0.04385)≈0.9566

[0200] Calculate and adjust the light intensity:

[0201]

[0202] The ideal light intensity of light device m after adjustment is 47.22 lumens, indicating that excessive light is reduced through adjustment.

[0203] For the formula:

[0204]

[0205] Compute the absolute value of a square root:

[0206]

[0207] Calculate the contribution of each light fixture:

[0208]

[0209] Calculate the total deviation:

[0210] G=10·7.26=72.6

[0211] The total deviation value is 72.6, which is a unit of measurement that indicates the deviation of the overall effect of the entire system after adjustment from the ideal state.

[0212] See also Figure 5 , the acquisition steps for updating and adjusting the conditional random field model are as follows:

[0213] S221: Input historical fault data F a and real-time performance index P b , using the formula:

[0214] H c =α1·F a +β1·P b

[0215] Construct a dataset H that reflects the current state c ;

[0216] Among them, α1 is the weight coefficient of historical fault data, and β1 is the weight coefficient of real-time performance indicators;

[0217] S222: Based on data set H c The deviation value G of the adjusted overall effect from the ideal state is calculated using the formula:

[0218]

[0219] Update the conditional random field model to reflect the current lighting equipment status and predict the failure probability, and obtain the updated model parameters θ d ;

[0220] Among them, γ1 is the coefficient for adjusting the model update, and log is the natural logarithm function used to convert the ratio to the logarithmic scale;

[0221] The calculation process is as follows:

[0222] For the formula:

[0223] H c =α1·F a +β1·P b

[0224] Assume that the historical failure data F a =75(number of failures);

[0225] Real-time performance index P b =85(performance score);

[0226] Weight coefficients α1 = 0.4, β1 = 0.6;

[0227] H c =0.4·75+0.6·85H c =30+51=81

[0228] H c =81 represents a weighted indicator of the current system status, combining historical faults and real-time performance indicators.

[0229] For the formula:

[0230]

[0231] Assume that the adjustment coefficient γ1 = 2.5:

[0232]

[0233] Model parameter θ d = 0.265 indicates how much the model parameters should be updated given the weights and biases.

[0234] See also Figure 6 , the specific steps for obtaining the fault prediction model are:

[0235] S311: Use the updated model parameters θ d , using the formula:

[0236] P e =1-exp(-σ1·θ d )

[0237] Calculate the failure probability of the lighting equipment and obtain the failure probability value P e ;

[0238] Among them, σ1 is a scaling factor used to adjust the calculation sensitivity of the failure probability, and exp is an exponential function used to calculate the probability decay, reflecting the rate at which the failure probability changes with the model parameters;

[0239] S312: According to the failure probability value P e , using the formula:

[0240]

[0241] Analyze and map the interdependencies between each lighting device to obtain the dependency strength A of another device r r ;

[0242] Among them, φ mr is the lighting equipment characteristic factor, describing the influence of lighting equipment m on the properties of another lighting equipment r, ω mr is the mutual influence weight between lighting devices, quantifying the influence of lighting device m on device r, m' represents the total number of lighting devices, and v is used to iterate and accumulate each φ mr ·ω mr The value of

[0243] S313: Set the dependency strength A of the rth device r The data integration is done by using formula;

[0244]

[0245] Calculate the probability M of normal operation of all lighting equipment f , and obtain the fault prediction model;

[0246] Among them, r represents the index, which is used to iterate each (1-A r ) value, if all A r A higher value indicates that the corresponding lighting equipment is more likely to fail, thus reducing M f If all A r They are all small, indicating that the probability of failure of each lighting device is low and the probability of stable operation is high.

[0247] The calculation process is as follows:

[0248] For the formula:

[0249] P e =1-exp(-σ1·θ d )

[0250] Assume σ1 = 3, θ d =0.265;

[0251] The part that computes the exponential function:

[0252] -σ1·θ d =-3×0.265=-0.795

[0253] Use the exponential function to calculate:

[0254] exp(-0.795)≈0.452

[0255] Calculate the probability of failure: P e =1-0.452=0.548

[0256] Failure probability P e = 0.548 or 54.8% indicates that under the current system conditions and model parameters, the probability of system failure is high, and this result can be used to prioritize maintenance and inspection work to reduce the risk of actual failure.

[0257] For the formula:

[0258]

[0259] Assume P e =0.548, m=5;

[0260] φ mr =[0.2, 0.3, 0.2, 0.15, 0.15]

[0261] The impact factor of each device on device r.

[0262] ω mr =[1, 0.8, 0.5, 0.4, 0.3]

[0263] The mutual influence weight between devices.

[0264] Calculate the dependency strength between devices:

[0265]

[0266] Multiply by the probability of failure:

[0267] A r =0.548×0.645=0.354

[0268] A r =0.354 means that the dependence intensity of device r in the system is 0.354, which reflects the relative importance of device r in the system and its contribution to the system failure probability.

[0269] For the formula:

[0270]

[0271] Assumption A r =[0.354, 0.300, 0.250, 0.400, 0.450];

[0272] Calculate the failure prediction model for the entire system:

[0273] M f =(1-0.354)×(1-0.300)×(1-0.250)×(1-0.400)×(1-0.450)M f

[0274] =0.646×0.700×0.750×0.600×0.550≈0.071

[0275] The value of the model M f =0.071 indicates that the overall failure probability of the entire system under the current conditions is very low, indicating that the design and maintenance of the system perform well in preventing failures.

[0276] See also Figure 7 , the specific steps for obtaining the lighting control results are:

[0277] S321: Based on the probability M that all lighting equipment is operating normally f , using the formula:

[0278]

[0279] Calculate the deviation value Z for each lighting device m ;

[0280] Among them, L m is the current light intensity of the mth lighting device, is the ideal light intensity of the mth lighting device predicted based on the current environmental conditions and other relevant inputs, T m is the current temperature of the mth lighting device, α m is the adjustment coefficient and temperature sensitivity coefficient for the mth lighting device;

[0281] S322: Based on the deviation value Z of each lighting device r , using the formula:

[0282]

[0283] Set the threshold θ of the mth lighting device m , identify the faulty lighting equipment, and obtain the excess value Y of the mth lighting equipment relative to the threshold m ;

[0284] S323: Based on the optimized lighting configuration and the excess value Y of the mth lighting device relative to the threshold m , using the formula:

[0285]

[0286] Adjust the corresponding lighting equipment to obtain the adjusted light intensity B of the mth lighting equipment m ;

[0287] Among them, L opt，m is the optimized ideal light intensity of the mth lighting device, Lfault，m is the adjusted light intensity of the mth lighting device when it is in a fault state, Y m is the fault mark of the mth lighting device, Y avg is the average value of all lighting equipment fault marks, σ m is the adjustment factor used to adjust Y m With the mean fault mark Y avg The impact of the difference between |Y m -Y avg | is an absolute value function, which calculates the difference between the fault mark of the mth lighting device and the average value of the fault marks of all lighting devices.

[0288] The calculation process is as follows:

[0289] L m : Actual light intensity = 500lx

[0290] Predicted light intensity = 520lx

[0291] T m :Current temperature = 25℃

[0292] T ref : Reference temperature = 20°C

[0293] λ m :Adjustment coefficient = 0.1

[0294] α m :Temperature sensitivity coefficient = 0.05

[0295] θ m : Deviation threshold = 10

[0296] m': total number of lighting devices = 50

[0297] L opt，m : Optimized light intensity = 550lx

[0298] L fault，m : Fault state light intensity = 450lx

[0299] σ m : Adjustment factor = 0.2

[0300] Y avg :Fault mark average value = 0.05

[0301] For the formula:

[0302]

[0303] |-20|=20lx

[0304] Tm -T ref =25℃-20℃=5℃

[0305]

[0306] λ m 0.7788 = 0.1 = 0.07788

[0307]

[0308] Z m ≈20lx, indicating the deviation between the light intensity and the predicted value.

[0309] For the formula:

[0310]

[0311] Calculation process:

[0312] Because Z m =20lx is greater than θ m =10lx, so max(0,10-20)=0;

[0313] Assuming that all 50 cells have the same Z value, the sum is 0;

[0314]

[0315] Y m =0, indicating that no lighting device deviation exceeds the threshold and no fault mark is present.

[0316] For the formula:

[0317]

[0318] Calculation process:

[0319] Y m =0 and Y avg =0.05;

[0320] |Y m -Y avg |=|0-0.05|=0.05

[0321] 1+σ m 0.05 = 1 + 0.2 0.05 = 1.01

[0322]

[0323] B m ≈545lx, indicating the adjusted light intensity, which is close to the optimized light level. Since there is no fault mark, the light remains at the optimized level.

[0324] A theater lighting adaptive control system, which is used to execute the theater lighting adaptive control method, comprises:

[0325] The situation modeling module analyzes plot changes and stage settings based on data uploaded by sensors in the theater, adjusts the top nodes of the Bayesian network, captures the dynamic environment of the theater in real time, and generates a theater situation model;

[0326] The lighting configuration module selects the ideal lighting intensity of each lighting device based on the theater scenario model, calculates the lighting distribution of the lighting device, iterates and optimizes the configuration until it matches the scene requirements, and generates the optimized lighting configuration;

[0327] The model initialization module inputs historical fault data and real-time performance indicators based on the optimized lighting configuration, initializes model parameters, and generates a conditional random field model;

[0328] The fault mapping module updates parameters based on the conditional random field model, maps the fault probabilities and dependencies among multiple lighting devices, and generates a fault prediction model;

[0329] The monitoring and control module continuously monitors lighting equipment based on the fault prediction model, identifies potential fault areas, adjusts lighting equipment according to the optimized lighting configuration, and generates lighting control results.

[0330] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for adaptively controlling theater lighting, characterized in that: The following steps are involved: Extract the plot changes and stage setting information uploaded by sensors in real time from the theater, initialize the Bayesian network, capture and simulate the dynamic environment of the theater, and adjust the top nodes of the Bayesian network according to the real-time data to generate a theater situation model; According to the theater situation model, the state of the lighting equipment is adjusted, and the ideal light intensity of each lighting equipment is selected through continuous iterative calculation and probability distribution analysis to generate an optimized lighting configuration; Taking the optimized lighting configuration as a basis, introducing a conditional random field model, initializing model parameters, inputting historical fault data and real-time performance indicators of the lighting, updating and adjusting the conditional random field model, mapping the fault probability and interdependency between lighting devices, and generating a fault prediction model; The fault prediction model is used to continuously monitor the lighting, identify and locate potential fault areas, adjust the corresponding lighting equipment according to the optimized lighting configuration, and generate lighting control results.

2. The theater lighting adaptive control method according to claim 1, characterized in that: The steps for obtaining the theater situation model are specifically as follows: Collect data from theater sensors in real time, including plot changes and stage setting information, using the formula: Calculate the information entropy of the current state of the theater and generate the data entropy value IG; Among them, p i represents the probability of the i-th data point, n is the total number of data points, α is the adjustment coefficient used to enhance the influence of the data point, and i is used to index the data point; Based on the data entropy value IG, the formula is adopted: Determine the weight of each data type and get the weight value W of the j-th data j ; Among them, λ is a tuning parameter used to control the influence of entropy value, IG j represents the information gain of the jth class of data, γ is a weighted adjustment factor used to balance the variability of information gain, represents the average information gain of all data, k is the index in the summation, and e represents the base of the natural logarithm; According to the weight value W of the j-th type of data j , initialize and update the top nodes of the Bayesian network, merge the data sources through the weighted average method, and use the formula: Update the state N of the top node of the Bayesian network top , generate a theater situation model; Among them, X j is the observed value of the jth type of data, β is the minimum adjustment factor, and min represents the function of taking the minimum value.

3. The theater lighting adaptive control method according to claim 2, characterized in that: The steps for obtaining the state of the lighting device are as follows: Using the state N of the top node of the Bayesian network top , the ideal light intensity of each lighting device is evaluated using the formula: Calculate the light intensity I required for each lighting device m m ; Among them, m represents the number of the lighting equipment, C m is the configuration parameter corresponding to the mth lighting device, δ1 is the adjustment coefficient, which controls the sensitivity of temperature influence, T1 is the current temperature of the theater, T ref1 is the reference temperature, e represents the base of the natural logarithm, used for exponential operations; Based on the illumination intensity I required by each lighting device m m The value of is, using the formula: Adjust the light output of each lighting device m to get the current setting status S of the lighting device m ; Among them, V total is the total lighting resource, Indicates that for all lighting equipment m' q The ideal light intensity is summed, q is used as the index of the summation, and n is the total number of data points.

4. The theater lighting adaptive control method according to claim 3 is characterized in that: The steps for obtaining the optimized lighting configuration are specifically as follows: According to the current setting state S of the lighting device m , using the formula: Calculate the deviation of each lighting device from the average ideal light intensity and obtain the deviation value D of lighting device m m ; Where V is the total lighting resource, n is the total number of data points, b is the adjustment amplitude, cos is the cosine function used to simulate periodic changes, and ω is the adjustment frequency; Based on the deviation value D of the lighting device m m , using the formula: Adjust the light intensity and calculate the ideal light intensity L after the light equipment m is adjusted m ; Among them, λ is the adjustment factor used to control the adjustment amplitude, exp is the exponential function used to adjust the response sensitivity, k is the response sensitivity parameter, and μ is the threshold of deviation adjustment; Analyze the ideal light intensity L after adjusting the lighting equipment m m Whether the optimal configuration is achieved, the formula is: Calculate the deviation G between the adjusted overall effect and the ideal state to obtain the optimized lighting configuration.

5. The theater lighting adaptive control method according to claim 4, characterized in that: The acquisition steps of updating and adjusting the conditional random field model are specifically as follows: Input historical fault data F a and real-time performance index P b , using the formula: H c =α1·F a +β1·P b Construct a dataset H that reflects the current state c ; Among them, α1 is the weight coefficient of historical fault data, and β1 is the weight coefficient of real-time performance indicators; Based on the dataset H c The deviation value G of the adjusted overall effect from the ideal state is calculated using the formula: Update the conditional random field model to reflect the current lighting equipment status and predict the failure probability, and obtain the updated model parameters θ d ; Among them, γ1 is the coefficient for adjusting the model update, and log is the natural logarithm function used to convert the ratio to the logarithmic scale.

6. The theater lighting adaptive control method according to claim 5, characterized in that: The steps for obtaining the fault prediction model are specifically as follows: Using the updated model parameters θ d , using the formula: P e =1-exp(-σ1·θ d ) Calculate the failure probability of the lighting equipment and obtain the failure probability value P e ; Among them, σ1 is a scaling factor used to adjust the calculation sensitivity of the failure probability, and exp is an exponential function used to calculate the probability decay, reflecting the rate at which the failure probability changes with the model parameters; According to the failure probability value P e , using the formula: Analyze and map the interdependencies between each lighting device to obtain the dependency strength A of another device r r ; Among them, φ mr is the lighting equipment characteristic factor, describing the influence of lighting equipment m on the properties of another lighting equipment r, ω mr is the mutual influence weight between lighting devices, quantifying the influence of lighting device m on device r, m′ represents the total number of lighting devices, and v is used to iterate and accumulate each φ mr ·ω mr The value of The dependency strength A of the rth device r The data integration is done by using the formula: Calculate the probability M of normal operation of all lighting equipment f , and obtain the fault prediction model; Among them, r represents the index, which is used to iterate each (1-A r ) value.

7. The theater lighting adaptive control method according to claim 6, characterized in that: The steps for obtaining the lighting control result are specifically as follows: Based on the probability M that all lighting equipment is operating normally f , using the formula: Calculate the deviation value Z for each lighting device m ; Among them, L m is the current light intensity of the mth lighting device, is the ideal light intensity of the mth lighting device predicted based on the current environmental conditions and other relevant inputs, T m is the current temperature of the mth lighting device, α m is the adjustment coefficient and temperature sensitivity coefficient for the mth lighting device; According to the deviation value Z of each lighting device r , using the formula: Set the threshold θ of the mth lighting device m , identify the faulty lighting equipment, and obtain the value Y of the mth lighting equipment exceeding the threshold m ; According to the optimized lighting configuration and the value Y of the mth lighting device exceeding the threshold m , using the formula: Adjust the corresponding lighting equipment to obtain the adjusted light intensity B of the mth lighting equipment m ; Among them, L opt,m is the optimized ideal light intensity of the mth lighting device, L fault,m is the adjusted light intensity of the mth lighting device when it is in a fault state, Y m is the fault mark of the mth lighting device, Y avg is the average value of all lighting equipment fault marks, σ m is the adjustment factor used to adjust Y m With the mean fault mark Y avg The impact of the difference between |Y m -Y avg | is an absolute value function, which calculates the difference between the fault mark of the mth lighting device and the average value of the fault marks of all lighting devices.

8. A theater lighting adaptive control system, characterized in that: According to any one of claims 1 to 7, the theater lighting adaptive control method, the system comprising: The situation modeling module analyzes plot changes and stage settings based on data uploaded by sensors in the theater, adjusts the top nodes of the Bayesian network, captures the dynamic environment of the theater in real time, and generates a theater situation model; The lighting configuration module selects the ideal lighting intensity of each lighting device based on the theater scenario model, calculates the lighting distribution of the lighting device, iteratively optimizes the configuration until it matches the scene requirements, and generates an optimized lighting configuration; The model initialization module inputs historical fault data and real-time performance indicators based on the optimized lighting configuration, initializes model parameters, and generates a conditional random field model; The fault mapping module updates parameters based on the conditional random field model, maps the fault probabilities and dependencies between multiple lighting devices, and generates a fault prediction model; The monitoring and control module continuously monitors the lighting equipment based on the fault prediction model, identifies potential fault areas, adjusts the lighting equipment according to the optimized lighting configuration, and generates a lighting control result.

Images