Picture travel performance equipment linkage control system based on PID-fuzzy self-adaption

Abstract

The invention relates to the technical field of automatic control, in particular to a linkage control system based on PID (Proportion Integration Differentiation)-fuzzy self-adaption for travel performance equipment, which integrates a fuzzy self-adaption mechanism and PID closed-loop control to form a response closed loop with real-time perception-analysis-decision-execution capability. According to the architecture, the cooperative logic among heterogeneous equipment such as lamplight, sound equipment and stage machinery is broken through, and a pre-training optimization and dynamic strategy updating mechanism is introduced, so that the system has cross-drama self-adaption capability. By constructing implicit association between equipment state data flow and performance scene semantics, the system can realize real-time adjustment and optimization of multi-equipment collaborative parameters in an unmanned intervention state, so that the robustness, synchronization precision and scene adaptability of the performance system are remarkably improved; a traditional passive control mode which depends on artificial experience, is long in debugging period and lags in response is thoroughly changed, and an evolvable and high-reliability intelligent underlying support is provided for achieving the immersive performance effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic control, more particularly, it relates to a PID-fuzzy adaptive-based cultural and travel performance equipment linkage control system. BACKGROUND

[0002] In the field of cultural and travel performance, the coordinated control of heterogeneous devices such as lighting, sound, stage machinery, etc. is the key to creating an immersive performance experience. With the increasing demand for personalized and scene-based content from audiences, the linkage of devices needs to closely match the rhythm of the performance scene (act + dramatic mood) and the plot, in order to achieve a deep integration of performance effect and content.

[0003] Current traditional performance equipment linkage systems generally use a static instruction control paradigm, and the core defect is the complete lack of customized adjustment capability for the performance scene (act + dramatic mood): on the one hand, the PID control parameters of traditional systems are mostly dependent on manual experience presets, and once the parameters are determined, they remain fixed and cannot be dynamically adjusted according to the act switching (such as the preparatory nature of the prologue, the high intensity of the climax, and the finishing nature of the epilogue) - the length of different acts and the difference in device motion density are significantly different, and fixed parameters cannot adapt to the coordination needs of each act; on the other hand, traditional systems do not include dramatic mood (such as excitement, relaxation, sadness, and joy) in the control logic, and cannot optimize device parameters according to mood changes (such as rapid changes in light intensity and the increase in sound decibels for an exciting mood, and soft switching of light and low decibel output for a relaxing mood), resulting in a disconnection between device motion and dramatic atmosphere. In addition, traditional systems have a long debugging period and rely on manual intervention, and when faced with multi-source environmental disturbances, the response is lagging, further exacerbating the mismatch between device linkage and scene requirements, making it difficult to meet the pursuit of scene-based and personalized effects in modern cultural and travel performance.

[0004] Therefore, the present application proposes a linkage control system that combines scene semantic analysis and PID-fuzzy adaptive control, specifically addressing the core pain point of the lack of scene customization adjustment in traditional methods, and achieving precise adaptation of device linkage to performance scenes. SUMMARY

[0005] In view of the deficiencies in the prior art, the purpose of the present application is to provide a PID-fuzzy adaptive-based cultural and travel performance equipment linkage control system.

[0006] To achieve the above purpose, the present application provides the following technical solutions: The PID-fuzzy adaptive-based cultural and travel performance equipment linkage control system comprises a multi-source data acquisition and scene semantic analysis module, a PID-fuzzy adaptive control module, a dynamic coordination module based on device state interlocking, and a device coordination control and error feedback module. The multi-source data collection and scene semantic analysis module is configured to collect environmental data, device state data and scene semantic data in a performance scene, complete data preprocessing and scene semantic quantification, and output a fusion data set of environmental data, normalized device state data and scene semantic parameters. The PID-fuzzy adaptive control module is configured to take the fusion data set as input, construct a three-dimensional PID basic parameter library, and perform fuzzy PID adjustment on the scene semantics weighted by the real-time scene semantic parameters in the fusion data set, to finally dynamically generate device real-time control parameters adapted to the current performance scene. The dynamic coordination module based on device state interlocking is configured to construct a formalized model of device linkage relationship, arbitrate based on device real-time state and environmental data, and correct original control instructions to realize closed-loop state coupling control of devices. The device cooperative control and error feedback module is configured to realize protocol conversion and accurate issuance of control instructions, collect device action errors and incrementally update the three-dimensional PID basic parameter library of the PID-fuzzy adaptive control module.

[0007] Further, the scene semantic data includes a scene type and a plot emotion label, and the scene type specifically includes prologue, development, climax and denouement, and the plot emotion label specifically includes excitement, relaxation, sadness and joy.

[0008] Further, the three-dimensional PID basic parameter library is constructed by the following specific method: A multi-dimensional training data set is constructed by collecting environmental data, device state data, scene semantic parameters and optimal PID parameters, wherein the optimal PID parameters are verified by director scores and synchronization error verification historical data of each combination. represents a proportional link parameter, represents an integral link parameter, represents a differential link parameter. Multi-objective optimization training by genetic algorithm: the multi-dimensional training data set is optimized and trained by genetic algorithm to output a three-dimensional PID basic parameter library of environment, scene and device, which is stored as: environment interval, scene label, , , key-value pairs.

[0009] Further, the scene semantic weighted fuzzy PID adjustment is as follows: S1, layered fusion of input quantity: basic input includes deviation e and deviation change rate ec; scene weighted input is realized by scene semantic weight coefficient . S2, three-dimensional fuzzy rule base generation: define the fuzzy subsets and domains of the deviation e, the deviation change rate ec and the scene semantic weight w respectively; adopt the full combination enumeration method, and obtain the PID parameter adjustment amount meeting the constraint condition through control effect simulation test for each combination; S3, control amount calculation: based on the PID basic parameters retrieved from the three-dimensional PID basic parameter library , , , calculate the final PID control parameters , ; Among them, , the scene semantic weight coefficient of the device parameter X under the scene scene, the subscript scene represents the combination of different scenes and emotional types, and the integral interval is the current scene period; , respectively, the proportional link parameter, the integral link parameter and the differential link parameter calculated in real time based on , , , respectively, , the deviation of the device parameter at time t, , the deviation change rate of the device parameter at time t.

[0010] Further, the scene semantic weight coefficient is calculated as follows: ; Among them, , the scene weight, , the emotional mapping coefficient of the device parameter X under the emotion type.

[0011] Further, the scene weight is calculated as follows: ; Among them, , , the longest duration in all scenes, , the maximum action density in all scenes; and are empirical coefficients.

[0012] Further, the emotional mapping coefficient is calculated as follows: Establish an evaluation group, and score the emotional matching degree of each segment for the four emotions of excitement, relaxation, sadness and joy using a 9-point Likert scale; For each emotion type, the device parameter set is linearly fitted with the average subjective score, the device parameter interval with a score greater than a preset threshold is selected, the ratio of the average value of the device parameters in the interval to the reference value is calculated as the emotion mapping coefficient, and the specific formula is as follows: ; Among them, corresponding to the excited, relaxed, sad and happy emotions respectively; is the average value of the effective interval of the device parameter X under the four emotion types.

[0013] Further, the dynamic coordination module based on device state interlocking has the following specific process: Formal modeling of linkage relationship: through interlocking condition definition, interlocking action definition and interlocking rule matrix construction, the coordination logic between devices is converted from natural language description to machine executable structured data; Arbitration based on real-time state: real-time reading of the current state feedback and environmental data of all related devices to form the current snapshot of the system; substituting and into the interlocking rule matrix for matching to output the interlocking action set to be executed at present ; according to , the original instruction set is modified to generate the final executable instruction set.

[0014] Compared with the prior art, the present application has the following beneficial effects: 1. Improve the device synchronization accuracy and scene matching degree: in view of the poor adaptability of the static instructions of the traditional system and the dependence on manual debugging, the system adopts the scene semantic weighted fuzzy PID regulation technology, constructs a three-dimensional fuzzy rule base through scene weight calculation and emotion mapping coefficient fitting, dynamically generates PID control parameters adapted to the current scene, realizes real-time optimization of device parameters without manual intervention, and effectively improves the device synchronization accuracy and scene matching degree of the performance content; 2. Enhance the system robustness and running reliability: in view of the lack of device state coordination in the traditional system and the problem of easy failure, the system introduces a device state interlocking mechanism, converts the coordination logic into structured data through formal modeling of linkage relationship, combines real-time device state and environmental data to arbitrate and modify instructions, realizes closed-loop state coupling control of devices, avoids coordination failure caused by different synchronization of device states, and significantly enhances the system robustness and running reliability. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a module block diagram of the PID-fuzzy adaptive travel and performance device linkage control system; Figure 2The implementation flow chart of the scene semantic weighted fuzzy PID regulating unit of the present application; Figure 3 The structural block diagram of the dynamic coordination module based on device state interlocking of the present application. DETAILED DESCRIPTION

[0016] Embodiment, with reference to Figure 1 The PID-fuzzy adaptive based cultural and travel performance equipment linkage control system of the present embodiment comprises a multi-source data acquisition and scene semantic analysis module, a PID-fuzzy adaptive control module, a dynamic coordination module based on device state interlocking, and an equipment coordination control and error feedback module. The multi-source data acquisition and scene semantic analysis module is used to acquire multi-dimensional data in the performance scene, complete data preprocessing and scene semantic quantification, and provide data support for subsequent control and regulation, and specifically comprises the following units: U1, data acquisition unit: Environmental data acquisition: collect on-site environmental parameters through wind speed sensors and temperature and humidity sensors; Device state data acquisition: collect light brightness and color temperature through light controllers, collect stage machinery position and speed through mechanical sensors, and collect sound decibels through sound consoles, with a device data sampling frequency of 10 Hz; Scene semantic data import: import the type of act (including prologue, development, climax, and epilogue) and the plot emotional label (including excitement, relaxation, sadness, and joy) through the performance script, and the import frequency is synchronized with the act switching; U2, scene semantic quantification unit: this unit realizes the quantification of scene semantics through a three-step process to ensure that scene information can directly drive the control logic, and specifically as follows: (1) Determination of the weight coefficient of act rhythm quantification: Data acquisition: collect historical performance data of at least 30 different types of cultural and travel performances, extract the duration of each act and the device action density, and record the duration of each act as , unit: minute; record the device action density as , unit: times / minute, and count the total number of actions of lights, machinery, and sound; Weight model construction: use a linear weighting formula to calculate the act weight of act m , wherein , is the longest duration in all acts, is the maximum action density in all acts; and are empirical coefficients, and in the present embodiment, and are obtained through multiple tests, and the model effect is optimal; Weight coefficient calibration: By segmenting and unifying the mapping, small fluctuations in continuous values ​​are grouped into the same weight segment, effectively filtering out "noise interference" in the scene, as detailed below: Climax: Take The weight of each screen segment is uniformly set to 1.2; Development phase, prologue phase: Take The weight of each screen segment is uniformly set to 1.0; Epilogue: Take The weight of each screen segment is uniformly set to 0.8; (2) Establishment of a mapping table between plot emotions and equipment parameters: Emotional label definition: The emotions of the plot are divided into four categories: exciting, soothing, sad, and joyful. The director or screenwriter shall specify the emotional label of each scene during the script annotation stage. Equipment parameter range collection: For each emotion, record 10 sets of ideal equipment action data under that emotion (such as the actual values ​​of light brightness change rate, mechanical lifting speed, and sound decibel change rate under an excited emotion); take the maximum value of each set of data to obtain the baseline threshold of the equipment parameters under that emotion; map the emotion labels to the corresponding baseline thresholds of the equipment parameters to form a mapping table; U3, Data Preprocessing Unit: This unit uses a Kalman filter algorithm to smooth environmental and equipment status data, eliminating random noise; it also uses the Min-Max normalization formula to map equipment status and environmental data to the [0,1] interval; The rule removes outliers from the equipment status data that exceed the equipment's physical threshold, and uses linear interpolation to fill in missing data. The module ultimately outputs a fused dataset consisting of environmental data S1 (filtered wind speed, temperature and humidity), equipment status data S2 (normalized lighting, sound, and mechanical parameters), and scene semantic parameters S3 (segment weights and emotion mapping values). PID-Fuzzy Adaptive Control Module: This module takes the output of the multi-source data acquisition and scene semantic parsing module as input, and achieves dynamic adaptation of equipment control parameters through pre-trained parameter optimization, fuzzy PID adjustment, and scene semantic weighting. Specifically, it includes the following units: U1, Pre-trained parameter optimization unit: Construction of a multi-dimensional training dataset: Collecting correlation data on different productions across the dimensions of environment, equipment, scene, and parameters, covering: Environmental data: wind speed, temperature, and humidity; Equipment status data: light brightness, mechanical position, sound volume (decibels); Scene semantic parameters: scene type, emotion tag; Optimal PID parameters: Verify historical data using director ratings and synchronization errors. The combination of director's score and the director's score on the matching degree between the equipment action and the scene (out of 100 points) and synchronization error refers to the time difference of action when multiple devices execute the same command; the PID parameters with a director score ≥95 points and synchronization error ≤0.08s are selected as the optimal PID parameters. Genetic Algorithm Multi-Objective Optimization Training: Construct the objective function: Among them, the scene matching degree is quantified by the director's score, and the synchronization error is the time difference of the device actions; In this embodiment, the coefficient is an empirical coefficient. ; Algorithm configuration: Population size 50, number of iterations 120 generations, crossover probability 0.8, mutation probability 0.1; Output: A 3D PID basic parameter library for environment, scene, and device, stored as (environment range, scene label, ...). , , Key-value pairs, supporting fast retrieval; U2, Scene semantic weighted fuzzy PID control unit: like Figure 2 The specific implementation steps are as follows: S1. Input volume hierarchical fusion: Basic input: Deviation ; Deviation change rate , For the current deviation, This represents the deviation from the previous sampling period; Scene-weighted input: The scene semantic weight coefficient of device parameter X in the scene. In this context, the subscript "scene" indicates a combination of different scenes and emotional types. Indicates the weight of the screen segment. The emotion mapping coefficient of device parameter X under emotion type is determined by fitting subjective evaluation experiments with objective data, as follows: (1) Ten cultural tourism performance directors and stage designers were invited to form an evaluation group. They watched 20 performance segments with different equipment parameter combinations for four types of emotions: excitement, relaxation, sadness and joy (such as an exciting segment with a gradient change in light change rate from 50 lux / s to 300 lux / s). The emotional matching degree of each segment was scored using a 9-point Likert scale. (2) For each emotion type, the combination of equipment parameters is linearly fitted to the average subjective score (the average score of 10 judges). The range of equipment parameters with a score ≥ 8 is selected, and the ratio of the mean of the equipment parameters in this range to the baseline value is calculated as the emotion mapping coefficient, as follows: Take the device parameter A as the abscissa, and the average subjective score as the ordinate, perform linear regression analysis, and obtain the regression equation by the least square method. Select the parameter interval with an average subjective score of ≥8 as the effective interval; calculate the mean value of the device data in the effective interval; Repeat the above steps to calculate the effective interval of device parameter A under four types of emotions, and calculate the mean value of device parameters under the emotions of excitement, relaxation, sadness, and joy in the effective interval ; The emotion mapping coefficient of each emotion type is calculated according to the following formula: ; Among them, corresponding to the emotions of excitement, relaxation, sadness, and joy, respectively; S2, three-dimensional fuzzy rule base generation: (1) Fuzzy subset and domain definition: For the deviation e, the domain is: , The maximum deviation of the device is defined as five fuzzy subsets: negative big (NB), negative medium (NM), zero (Z), positive medium (PM), and positive big (PB). The membership function adopts a triangular function; For the change rate of the deviation ec, the domain is: , The maximum change rate of the deviation of the device is defined as five fuzzy subsets: NB, NM, Z, PM, and PB. The membership function adopts a triangular function; For the scene semantic weight w, the domain is: , four fuzzy subsets are defined: 0.8, 0.9, 1.0, and 1.2. The membership function adopts a single-point function, and the membership degree of each subset is 1 only at the corresponding value, and 0 elsewhere; (2) Rule table system construction: All combinations of the five subsets of e, the five subsets of ec, and the four subsets of w are enumerated using the full combination enumeration method. The specific rule generation logic is as follows: Based on the PID basic parameter library of the pre-trained parameter optimization unit, the optimal parameter increment under different e, ec, and w combinations is analyzed, as follows: For each combination, select the that meets the constraint condition (scene matching degree ≥ 95% and synchronization error ≤ 0.08) as the rule output through control effect simulation test. The values ​​are taken until all indicators are qualified, thereby ensuring that the control effect of the rules meets the actual needs of cultural tourism performances; (3) Reasoning and Defuzzification Verification: Reasoning method: The Mamdani reasoning method is adopted, that is, the fuzzy set of the conclusion part is obtained by matching the preconditions of the "if-then" rule; Defuzzification: The centroid method (calculating the centroid of the fuzzy set as the precise output) is used for... The centroid is calculated from the fuzzy outputs to obtain the final precise parameter increments; Verification: Substitute the generated rule base into the simulation environment to verify whether the scene matching degree and synchronization error in the full scenario meet the target. If not, backtrack and adjust the rule parameters until the verification is passed. S3. Control quantity calculation: S31. Retrieve from PID basic parameter library , , ; S32, obtained through reasoning from a three-dimensional fuzzy rule base. ; S33. Calculate real-time PID parameters: ; S34. Substitute the semantic weighted PID formula into the scenario: Among them, the integration interval This refers to the current screen segment.

[0017] A dynamic coordination module based on equipment state interlocking: This module upgrades equipment linkage from open-loop timing planning to closed-loop state coupling control through formal modeling, distributed arbitration, and system-level compensation, such as... Figure 3 As shown, it specifically includes the following units: U1, Formal Modeling Unit for Linkage Relationships: The process of transforming the collaboration logic between devices from natural language descriptions into machine-executable structured data provides a rule-based foundation for dynamic collaboration. The specific process is as follows: Interlock condition definition: Create an interlock condition library, each condition This is a logical expression, where the atomic elements are the real-time status feedback values ​​of the device. or environment variables ; Interlock Action Definition: Create an interlock action library, where each action... Define the modification operations for device control commands. Operation types include: INHIBIT (disable command issuance), MODIFY (modify command parameters), and TRIGGER (trigger a new control command). Interlock rule matrix construction: Establish an interlock rule matrix R, where each rule is a binary tuple ; Condition_Set is the logical combination (AND, OR, NOT) of multiple interlock conditions; Action_Set is a series of interlock actions to be executed when Condition_Set is true; This matrix is predefined according to the needs of performance creation before system deployment, serving as the criteria for linkage control; U2, arbitration unit based on real-time state: Insert a high-priority decision-making layer in the control loop to ensure that all instructions conform to the formalized model of linkage relationships; Instruction preprocessing: The original control instructions from the PID-fuzzy adaptive control module First enter this arbitration unit, which reads the current state feedback of all related devices in real time and environmental data to form the current snapshot of the system; Real-time logical reasoning: Substitute and into the interlock rule matrix R for matching, using an efficient and deterministic rule engine optimized based on the Rete algorithm to quickly complete all rule matching and output the set of interlock actions to be executed ; Instruction synthesis and scheduling: Modify the original instruction set according to to generate the final executable instruction set ; The modification logic is as follows: For INHIBIT actions, set the corresponding instructions to invalid; for MODIFY actions, modify the instruction parameters according to the rules; for TRIGGER actions, add new instructions to ; Finally, is sent to the device collaborative control and error feedback module for issuance; Device collaborative control and error feedback module: This module is used to implement precise issuance of control instructions, real-time feedback of device actions, and dynamic optimization of control models, specifically including the following units: U1, protocol conversion unit: Protocol conversion: Embed multiple device control protocol conversions, where lighting devices use the DMX512 protocol, stage machinery uses the CANopen protocol, and audio devices use the AES3 protocol; U2, feedback and model updating unit: Feedback data acquisition: Collect real-time device action parameters, calculate the error between actual action parameters and target values, and synchronize feedback frequency with device data sampling frequency; Model parameter updating: the feedback error data, the current scene semantic parameter, the environment parameter are added to the training data set, the pre-training parameter optimization unit is updated by using the incremental training mode to update the PID basic parameter library, the update period is set to be after each performance, and the model is adapted to long-term scene changes; in the process of updating the PID basic parameter library by using the incremental training, a sliding window mechanism is used to retain the performance data of the last 30 performances as training samples; each time the update is performed, the similarity between the current environment-scene combination and the corresponding combination of the library parameters is calculated by using a cosine similarity formula, only the basic parameters with a similarity greater than or equal to 90% are adjusted, and the pertinence and stability of the parameter update are ensured.

[0018] Through the detailed introduction of the above embodiments, the PID-fuzzy adaptive-based cultural and tourism performance equipment linkage control system of the present application cooperatively constructs an intelligent collaborative control architecture through four modules. The multi-source data acquisition module provides accurate data basis for the system, the PID-fuzzy adaptive control module relies on scene semantic weighting technology to adapt the control parameters to the scene and the depth of emotion, and the dynamic collaboration module based on equipment state interlocking ensures the safety of equipment collaboration through real-time arbitration. The system completely changes the traditional passive control mode relying on manual experience, can cope with dynamic performance scenes and multi-source interference without complex manual debugging, realizes closed-loop control with high synchronization accuracy and high scene adaptability, effectively supports stable presentation of immersive performance effect, and provides an evolvable and highly reliable solution for intelligent linkage of cultural and tourism performance equipment.

[0019] The above formulas are all dimensionless values calculated, and the preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0020] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0021] It should be understood that the size of the sequence number of each process described above in various embodiments of the present application does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0022] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0023] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0024] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the division of the above-described device embodiments is only a logical function division, and there can be another division manner for actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0025] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various other media that can store program codes.

[0026] The above describes only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive principles, characterized in that, It includes a multi-source data acquisition and scene semantic parsing module, a PID-fuzzy adaptive control module, a dynamic coordination module based on device state interlocking, and a device coordination control and error feedback module; The multi-source data acquisition and scene semantic parsing module is used to collect environmental data, equipment status data and scene semantic data in the performance scene, complete data preprocessing and scene semantic quantization, and output a fused dataset of environmental data, normalized equipment status data and scene semantic parameters. The PID-fuzzy adaptive control module is used to construct a three-dimensional PID basic parameter library with the fusion dataset as input, and then combine the real-time scene semantic parameters in the fusion dataset to perform scene semantic weighted fuzzy PID adjustment, and finally dynamically generate real-time control parameters of the equipment that are adapted to the current performance scene. The dynamic coordination module based on device state interlocking is used to construct a formal model of device linkage relationship, arbitrate based on real-time device status and environmental data, and correct the original control commands to achieve closed-loop state coupling control of the device. The equipment collaborative control and error feedback module is used to realize the protocol conversion and precise issuance of control commands, collect equipment action errors, and incrementally update the three-dimensional PID basic parameter library of the PID-fuzzy adaptive control module.

2. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control as described in claim 1, characterized in that, The scene semantic data includes scene types and plot emotion tags. The scene types specifically include prologue, development, climax, and epilogue. The plot emotion tags specifically include excitement, relaxation, sadness, and joy.

3. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control as described in claim 1, characterized in that, The specific method for constructing the three-dimensional PID basic parameter library is as follows: Construct a multi-dimensional training dataset: collect environmental data, device status data, scene semantic parameters, and optimal PID parameters; among them, the optimal PID parameters are verified using director ratings and synchronization errors in historical data. Obtained through combination; Indicates the parameters of the proportional element. Indicates the parameters of the integral element. Indicates the parameters of the differential element; Genetic Algorithm Multi-Objective Optimization Training: Utilizing a multi-dimensional training dataset, a genetic algorithm is used for optimization training, outputting a 3D PID basic parameter library for the environment, scene, and device, stored as: environment range, scene label, , , Key-value pairs.

4. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control according to claim 1, characterized in that, The scene semantic weighted fuzzy PID adjustment is as follows: S1. Input Layered Fusion: Basic inputs include deviation e and deviation change rate ec; scene-weighted inputs are obtained through scene semantic weight coefficients. accomplish; S2. Generation of 3D fuzzy rule base: Define the fuzzy subsets and universe of discourse for deviation e, deviation change rate ec, and scene semantic weight w respectively; Use the full combination enumeration method to obtain the PID parameter adjustment amount that meets the constraints for each combination through control effect simulation test; S3. Control quantity calculation: based on parameters retrieved from the three-dimensional PID basic parameter library. , , Calculate the final PID control parameters , ; in, This represents the scene semantic weight coefficient of device parameter X within the scene context. The subscript "scene" indicates a combination of different scene segments and emotion types. The integration interval is... This refers to the current screen segment. They represent based on , , Real-time calculation of proportional, integral, and derivative parameters. This represents the deviation of the device parameters at time t. This represents the rate of change of the deviation of the equipment parameters at time t.

5. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control as described in claim 4, characterized in that, The scene semantic weight coefficient The calculation method is as follows: ； in, Indicates the weight of the screen segment. This represents the emotion mapping coefficient of device parameter X under emotion type.

6. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control according to claim 5, characterized in that, The aforementioned segment weights The calculation method is as follows: ； in, , It is the longest duration among all segments. This represents the maximum motion density across all segments. and This is an empirical coefficient.

7. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control according to claim 5, characterized in that, The method for calculating the emotion mapping coefficient is as follows: An evaluation team was established to score the emotional fit of each segment using a 9-point Likert scale, targeting four categories of emotions: excitement, relaxation, sadness, and joy. For each emotion type, a linear fit is performed between the combination of device parameters and the average subjective rating. The range of device parameters with ratings greater than a preset threshold is selected, and the ratio of the mean value of the device parameters within this range to the baseline value is calculated as the emotion mapping coefficient. The specific formula is as follows: ； in, These correspond to the emotions of excitement, relaxation, sadness, and joy, respectively. This represents the mean of device parameter X within the valid interval for the four emotion types.

8. The linkage control system for cultural tourism performance equipment based on PID-fuzzy adaptive control as described in claim 1, characterized in that, The dynamic collaboration module based on device state interlocking operates as follows: Formal modeling of inter-device relationships: By defining interlocking conditions, defining interlocking actions, and constructing an interlocking rule matrix, the collaborative logic between devices is transformed from natural language descriptions into machine-executable structured data; Arbitration based on real-time status: Real-time reading of the current status feedback from all relevant devices. and environmental data This constitutes the current snapshot of the system; and Substitute the values ​​into the interlocking rule matrix for matching, and output the set of interlocking actions that need to be executed. ;according to The original instruction set is modified to generate the final executable instruction set.

Images