Vibration parameter matching decision-making system for attached vibrator

Abstract

The invention relates to the technical field of building construction, and discloses an attached vibrator vibration parameter matching decision-making system, which comprises a perception execution dual-mode vibrator network, a vibration acoustic fingerprint generation and analysis module, a fingerprint evolution time sequence inference module and a multi-target dynamic decision-making engine, generating a vibration acoustic fingerprint formed by multi-dimensional physical characteristics according to the response signal; the method comprises the following steps: constructing a fingerprint evolution sequential sequence, comparing the fingerprint evolution sequential sequence with a reference database, deducing the performance of a concrete material on line, and further calling a mapping function matched with the performance to evaluate a real-time compactness state; and finally, based on the evaluated compactness, the multi-target dynamic decision engine adopts a model prediction control strategy to generate an optimal dynamic operation instruction for each vibrator node. Closed-loop self-adaptive control of detection, evaluation, decision making and execution is constructed, the optimal vibration parameters can be matched in real time, the vibration quality and uniformity of concrete are remarkably improved, energy consumption is reduced, and dependence on artificial experience is reduced.

Description

Technical Field

[0001] This invention relates to the field of building construction technology, specifically to a decision-making system for matching vibration parameters of an attached vibrator. Background Technology

[0002] Concrete vibration is a crucial step in concrete structure construction. Its purpose is to eliminate air bubbles within the concrete through vibration, reducing internal voids and ensuring the concrete mixture reaches a dense and uniform state. This, in turn, guarantees the strength, durability, and impermeability of the hardened concrete. Attached vibrators, capable of transmitting vibrational energy through formwork to large areas of concrete, are widely used in the construction of walls, dams, tunnel linings, and other components.

[0003] However, the current operation of attached vibrators remains largely an open-loop control process relying on preset parameters and human experience. Operators typically set the vibration frequency and operating time based on construction specifications or personal experience, and subjectively judge whether vibration is complete by observing macroscopic phenomena such as the surface slurry and the escape of air bubbles during vibration. This approach lacks objective and real-time feedback on the evolution of the internal density of the concrete.

[0004] Because it's impossible to accurately perceive the dynamic changes in the internal state of concrete, this traditional operating method is highly susceptible to uncontrollable vibration quality. Insufficient vibration leaves numerous voids within the concrete, resulting in defects such as honeycomb and pitting, severely impacting structural safety. Conversely, excessive vibration causes segregation and stratification of the concrete mix, leading to the settling of coarse aggregates and the floating of cement mortar, similarly deteriorating the concrete's mechanical properties and homogeneity. Furthermore, different batches of concrete may vary in mix proportions and slump, making it difficult for fixed vibration parameters to accommodate these material property fluctuations. The entire process not only heavily relies on the operator's skill and responsibility but also often results in unnecessary energy consumption and extended construction time, failing to meet the stringent requirements of modern, lean construction for quality control and efficiency improvement. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a matching decision system for vibration parameters of an attached vibrator. This system solves the problem that, during the vibration process, the attached vibrator cannot perceive the internal density of the concrete in real time and adaptively adjust the vibration parameters, which leads to the vibration quality being heavily reliant on human experience and making it difficult to guarantee uniformity and consistency.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The first aspect of the present invention provides a decision system for matching vibration parameters of an attached vibrator, comprising: A dual-mode vibrator network is configured to control multiple vibrator nodes within the network to switch between a vibration mode and a detection mode. In the detection mode, at least one designated vibrator node emits a detection signal, and at least one other vibrator node receives the response signal after penetrating the concrete medium. The vibration acoustic fingerprint generation and analysis module is connected to the sensing and execution dual-mode vibrator network and is configured to extract multiple preset physical features from the response signal to generate a vibration acoustic fingerprint characterizing the internal state of the concrete medium. The fingerprint evolution time sequence inference module is connected to the vibration acoustic fingerprint generation and analysis module. It is configured to construct a fingerprint evolution time sequence consisting of the vibration acoustic fingerprints at multiple time points, and based on the fingerprint evolution time sequence, infer the material properties of the concrete medium online and evaluate its density state. A multi-objective dynamic decision engine, connected to the fingerprint evolution time-series inference module, is configured to generate dynamic operation instructions based on the inferred material properties and the evaluated compaction state, aiming to optimize the balance between concrete vibration quality, energy consumption and efficiency, and to send the dynamic operation instructions to the sensing and execution dual-mode vibrator network.

[0007] Preferably, the sensing and executing dual-mode vibrator network employs a time-division multiplexing mechanism, dividing the working time into alternating vibration time slots and detection time slots. During the vibration time slot, all vibrator nodes execute vibration operations according to the dynamic operation instructions; during the detection time slot, the vibrator nodes that transmit detection signals are rotated to achieve a gridded scan of the concrete medium.

[0008] Preferably, the vibration acoustic fingerprint generation and analysis module is specifically configured to extract at least two physical features selected from the following group to generate the vibration acoustic fingerprint: time of flight, energy decay, spectral centroid, phase dispersion, and kurtosis.

[0009] In one specific embodiment, the fingerprint evolution time series inference module includes a benchmark database storing multiple benchmark entries. Each benchmark entry corresponds to a material category and includes: a benchmark fingerprint evolution time series trajectory corresponding to that material category, and a mapping function generated based on experimental data of that material category. The fingerprint evolution time series inference module is specifically configured to: infer the material properties of the concrete medium online by calculating the distance between the current fingerprint evolution time series sequence and each benchmark fingerprint evolution time series trajectory in the benchmark database.

[0010] In one specific embodiment, the fingerprint evolution timing inference module is configured to compare the calculated minimum distance with a preset anomaly threshold, and generate an alarm signal for abnormal material performance when the minimum distance is greater than the anomaly threshold.

[0011] In one specific embodiment, the fingerprint evolution time series inference module is further configured to: determine a material category based on the minimum distance between the fingerprint evolution time series sequence and the benchmark fingerprint evolution time series trajectory; and call the mapping function corresponding to the determined material category in the benchmark database to map the current vibratory acoustic fingerprint to the density state, so as to achieve calibration of the density assessment.

[0012] Preferably, to achieve the balance between optimizing concrete vibration quality, energy consumption, and efficiency, the multi-objective dynamic decision engine is configured to solve a comprehensive cost function to generate the dynamic operation instructions. The comprehensive cost function... Defined as a quality cost item Energy consumption cost item and time cost item Weighted sum: ; in, , , These are the preset weighting coefficients corresponding to the quality, energy consumption, and time cost items, respectively.

[0013] The quality cost item Represented as the density state vector of the current assessment With the target compactness state vector Norm difference between: ; The energy consumption cost item This is represented as the control time interval. Total power consumption of all vibrator nodes: ; in, This represents the total number of nodes in the vibrator. For the first Each vibrator node at time [time] The instantaneous power. The time cost item For a constant This is used to minimize the number of job steps in the optimization solution.

[0014] Preferably, the multi-objective dynamic decision engine employs a model predictive control strategy. At each decision moment, based on the current density state and material properties, it predicts the system evolution within a finite time window and solves the comprehensive cost function in a rolling manner to generate the dynamic operation instructions.

[0015] Preferably, the dynamic operation instructions include personalized operation parameters for each of the vibrator nodes, the operation parameters including at least one of the following: operating mode, vibration frequency, vibration amplitude, and duration.

[0016] A second aspect of the present invention provides a method for matching vibration parameters of an attached vibrator, comprising the following steps: By sensing and executing a dual-mode vibrator network, multiple vibrator nodes within the network are controlled to switch between vibration mode and detection mode. In the detection mode, a detection signal is emitted and a response signal is received after penetrating the concrete medium. Multiple preset physical features are extracted from the response signal to generate a vibration acoustic fingerprint characterizing the internal state of the concrete medium. A fingerprint evolution time series consisting of the vibration acoustic fingerprint at multiple time points is constructed, and based on the fingerprint evolution time series, the material properties of the concrete medium are inferred online, and its density state is evaluated. Based on the inferred material properties and the assessed compaction state, dynamic operation instructions for each vibrator node are generated to optimize the balance between concrete vibration quality, energy consumption and efficiency, and the sensing execution dual-mode vibrator network is controlled to execute.

[0017] This invention provides a decision system for matching vibration parameters of an attached vibrator. It has the following beneficial effects: 1. This invention constructs and analyzes a fingerprint evolution time series consisting of vibration acoustic fingerprints at multiple time points through a fingerprint evolution time series inference module. It then compares this sequence with the baseline fingerprint evolution time series trajectories of different material categories in a benchmark database. This allows for online inference of the actual material properties of the current concrete medium. Based on this inference result, the system can call a specific mapping function corresponding to the material category to evaluate the compaction. This achieves dynamic calibration of the evaluation model, ensuring that control decisions are always based on the true physical properties of the vibrated material, and significantly enhancing the adaptability to on-site material fluctuations.

[0018] 2. This invention sets up a multi-objective dynamic decision engine. This engine generates dynamic work instructions by solving a comprehensive cost function that includes quality cost, energy consumption cost, and time cost. This mechanism enables the system to actively and quantitatively balance energy consumption and work time while pursuing the final vibration quality standard. It avoids energy waste and extended working hours caused by excessive vibration, or quality hazards caused by pursuing speed, thus optimizing the resource utilization rate of the entire work process.

[0019] 3. This invention utilizes a dual-mode vibrator network for sensing and execution, enabling the vibrator itself to function as a detection sensor. Combined with a vibration acoustic fingerprint generation and analysis module, it can continuously and non-invasively acquire characteristic data representing the internal state of concrete. This mechanism transforms the previously invisible evolution of internal density into a real-time monitorable data sequence, providing direct and continuous input for subsequent inferences and decisions. It forms a complete closed loop from internal state perception to external action execution, thereby transforming the traditional open-loop, experience-dependent vibration operation into a data-driven, precise control process. Attached Figure Description

[0020] Figure 1 This is a structural block diagram of the attached vibrator vibration parameter matching decision system of the present invention; Figure 2 This is a schematic diagram of the working timing and scanning mechanism of the sensing and execution dual-mode vibrator network of the present invention; Figure 3 This is a schematic diagram of the process for generating a vibration acoustic fingerprint from a response signal according to the present invention. Figure 4 This is a block diagram illustrating the working principle of the fingerprint evolution timing inference module of the present invention; Figure 5 This is a schematic diagram illustrating the workflow of the multi-objective dynamic decision engine of the present invention employing a model predictive control strategy. Figure 6 This is a flowchart of the attached vibrator vibration parameter matching decision method of the present invention. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] See attached document Figure 1 , Figure 1This is a structural block diagram of an attached vibrator vibration parameter matching decision system according to an embodiment of the present invention. The attached vibrator vibration parameter matching decision system provided by the present invention may include: a sensing and execution dual-mode vibrator network, a vibration acoustic fingerprint generation and parsing module, a fingerprint evolution time-series inference module, and a multi-objective dynamic decision engine.

[0023] A dual-mode vibrator network for construction sensing and execution is used to perform physical world detection and vibration operations. The network is configured to control multiple vibrator nodes within it to switch between vibration and detection modes. In detection mode, the construction network controls at least one designated vibrator node to emit a detection signal and controls at least one other vibrator node to receive a response signal after penetrating the concrete medium. This response signal is output to a vibration acoustic fingerprint generation and analysis module. In vibration mode, the construction network receives dynamic operation instructions from a multi-objective dynamic decision engine and drives each vibrator node to perform vibration operations accordingly.

[0024] The construction vibration acoustic fingerprint generation and analysis module is connected to the construction sensing and execution dual-mode vibrator network. This module extracts multiple preset physical features from the received response signals and combines these features to generate a vibration acoustic fingerprint that characterizes the internal physical state of the concrete medium at the current moment. This vibration acoustic fingerprint is then output to the fingerprint evolution timing inference module.

[0025] The construction fingerprint evolution time-series inference module is connected to the construction vibration acoustic fingerprint generation and analysis module. This module receives and stores vibration acoustic fingerprints generated by the construction vibration acoustic fingerprint generation and analysis module at different time points to construct a fingerprint evolution time-series sequence composed of vibration acoustic fingerprints from multiple time points. Based on this time-series sequence, the module performs two core functions: first, online inference of the material properties of the current concrete medium; and second, online evaluation of its density state. The inferred material properties and the evaluated density state are combined as the system's state output and transmitted to the multi-objective dynamic decision engine.

[0026] A multi-objective dynamic decision-making engine for building construction is connected to a building construction fingerprint evolution time-series inference module and a building construction perception-execution dual-mode vibrator network. The engine receives material properties and compaction status output from the building construction fingerprint evolution time-series inference module and, based on this input, generates dynamic operation instructions aimed at optimizing the balance between concrete vibration quality, energy consumption, and efficiency. To achieve this functionality, the engine is configured to solve a comprehensive cost function. The expression for this function is: ; in, This is the comprehensive cost function; This is a quality cost item; This is an energy consumption cost item; For time cost; These are the preset weighting coefficients corresponding to the quality, energy consumption, and time cost items, respectively.

[0027] The construction engine optimizes the solution to improve the overall cost function. Minimize, thereby generating optimal dynamic operation instructions, and then send these instructions to the construction sensing and execution dual-mode vibrator network for execution.

[0028] In summary, the system in this embodiment acquires signals through a dual-mode vibrator network for building construction perception and execution, generates a state fingerprint through a building construction vibration acoustic fingerprint generation and analysis module, and then completes the inference and evaluation of the internal state of concrete by a building construction fingerprint evolution timing inference module. Finally, the building construction multi-objective dynamic decision engine makes optimization decisions based on the evaluation results and issues control commands, forming a data-driven closed-loop control structure.

[0029] See attached document Figure 2 , Figure 2 This is a schematic diagram illustrating the working timing and scanning mechanism of a sensing-execution dual-mode vibrator network according to an embodiment of the present invention. The sensing-execution dual-mode vibrator network for building construction is the actuator for the interaction between the system of the present invention and the physical world, and its specific structure and operation are as follows.

[0030] In one embodiment, the construction sensing and execution dual-mode vibrator network includes multiple vibrator nodes attached to the formwork and a network control unit. Each vibrator node, in addition to containing an eccentric block for generating vibration and a drive motor, structurally integrates a high-sensitivity vibration sensor, such as a piezoelectric accelerometer. The network control unit is responsible for sending control commands to each vibrator node and receiving signals collected by the vibration sensor.

[0031] The dual-mode nature of construction vibrator nodes is reflected in their two distinct operating modes: vibration mode and detection mode. In vibration mode, the network control unit instructs the vibrator node's drive motor to operate at preset high power and high amplitude parameters, generating strong mechanical vibrations. The purpose of this is to liquefy the concrete, eliminate internal air bubbles, and achieve compaction. In detection mode, the vibrator node operates entirely differently. The network control unit instructs the vibrator selected as the transmitting node to generate a preset detection signal waveform with wideband characteristics, such as a linear frequency modulated signal (Chirp signal), at extremely low power. The energy of this detection signal is controlled to a level that will not significantly affect the compaction state of the concrete. Simultaneously, the network control unit instructs the remaining vibrators selected as receiving nodes to cease all active vibration and only activate their internal vibration sensors to collect the detection signal propagating through the concrete medium.

[0032] The reason for choosing a linear frequency modulated (LFM) signal is that it has good autocorrelation characteristics, and its energy is spread in the time domain, thus achieving a high signal-to-noise ratio while maintaining a low peak power. At the same time, its wideband characteristics allow the response detected by this signal to contain richer information about the absorption and scattering of different frequency components by the medium, which is beneficial for subsequent vibrational acoustic fingerprint feature extraction.

[0033] To coordinate the operation of these two modes, the building construction network control unit adopts a time-division multiplexing mechanism. (See attached document.) Figure 2 The network control unit divides the total working time into periodically alternating vibration time slots. and detection time slot The duration of a tamping interval, For example, for several seconds, during which all vibrator nodes in the network are in tamping mode, executing tamping operations according to instructions issued by the multi-objective dynamic decision engine. Immediately following each tamping time slot is a probe time slot, lasting for, for example, several hundred milliseconds. Before entering the probe time slot, there is a brief silence period to allow macroscopic disturbances generated by tamping to decay.

[0034] During a construction detection time slot, the network control unit performs a gridded scan of the concrete medium. This scan is achieved through a strategy of rotating transmitting nodes. Specifically, within a detection time slot, the network control unit first designates the first vibrator node as the transmitting node, and all other vibrator nodes as receiving nodes. After transmission is completed, the second vibrator node is immediately designated as the transmitting node, and the remaining nodes as receiving nodes. This process continues sequentially until all vibrator nodes in the network have completed one transmission of a detection signal.

[0035] Through the aforementioned rotating scanning strategy, the system can acquire a set of response signals covering multiple different propagation paths within the monitored area in each detection time slot. For example, from the node... Launch, from node The received signal characterizes the path. The acoustic properties of the concrete medium are analyzed. By aggregating the response signals from all paths acquired within a single detection time slot, a raw dataset reflecting the spatial distribution of the internal state of the concrete is formed. This dataset is then transmitted as a whole to the vibration acoustic fingerprint generation and analysis module for further processing.

[0036] See attached document Figure 3 , Figure 3 This is a schematic diagram of the processing flow for generating a vibration acoustic fingerprint from a response signal according to an embodiment of the present invention. The function of the construction vibration acoustic fingerprint generation and analysis module is to convert the raw, unstructured response signal collected by the sensing and executing dual-mode vibrator network into a structured feature vector that can quantitatively characterize the internal state of concrete, i.e., a vibration acoustic fingerprint.

[0037] In one embodiment, the module receives a set of response signals acquired within a probe time slot from a dual-mode vibrator network for building construction sensing. Before feature extraction, the module first performs preprocessing operations on each response signal, including bandpass filtering, whose passband range is matched to the spectral range of the transmitted probe signal (e.g., a linear frequency modulated signal), to filter out environmental and equipment noise; and signal windowing, to extract specific time periods containing valid signals.

[0038] After preprocessing, this module extracts a set of preset physical features from each response signal. These physical features specifically include: Time of Flight (ToF): This characteristic represents the propagation time of a detection signal from the transmitting node through the concrete medium to the receiving node. It is calculated by cross-correlation between the received response signal and the known, baseline original transmitted signal. The time delay corresponding to the peak value of the cross-correlation function is determined as the time of flight. This value is directly related to the propagation speed of sound in the medium, which reflects the elastic modulus and density of the medium.

[0039] Energy Attenuation: This feature quantifies the degree of signal energy loss during propagation. It is calculated by first determining the total energy of the received signal within a preset time window, typically obtained by integrating the square of the signal amplitude. Then, this energy value is compared to the known total energy of the transmitted signal, calculating the ratio or dB difference. The magnitude of energy attenuation is related to the internal damping of the medium and the scattering effects caused by porosity and aggregate.

[0040] Spectral centroid; this feature describes the centroid of the signal's spectral energy distribution. It is calculated by first performing a Fourier transform on the time-domain response signal to obtain its spectrum. Then, the weighted average frequency of the spectrum is calculated, where the weight of each frequency point is its corresponding spectral amplitude. Its mathematical expression is: ; in, This is the final calculation result, usually representing a weighted average or some kind of comprehensive indicator. Frequency point Spectral amplitude at that location Frequency point The frequency values. Because high-frequency components attenuate faster in media such as concrete, changes in the spectral centroid can reflect the selective absorption characteristics of the medium for different frequency components.

[0041] Phase Dispersion: This feature measures the consistency of a signal's phase change across different frequencies. When a signal travels through porous or non-uniform media, the propagation paths and velocities of different frequency components can vary slightly, causing phase discrepancies. This module quantifies this degree of dispersion by analyzing the signal's instantaneous frequencies or performing statistical analysis (e.g., calculating its variance or standard deviation) on the phase spectrum.

[0042] Kurtosis: This characteristic is a statistical moment of the signal amplitude distribution, used to measure the sharpness of its distribution or the thickness of its tail. In the initial stage of compaction, due to a large amount of random scattering and multipath propagation, the amplitude distribution of the received signal tends to be Gaussian. As the compaction density increases, the signal propagation path tends to stabilize, the signal waveform becomes more deterministic, and its kurtosis value will change accordingly.

[0043] After extracting the numerical values ​​of the above physical characteristics, the vibration acoustic fingerprint generation and analysis module combines these values ​​into a multi-dimensional feature vector, which is defined as the vibration acoustic fingerprint at the current moment and along the current propagation path. .For example: ; in, Representing the Time of Flight (ToF) characteristic, it is used to measure the propagation time of signals, such as in ranging applications of ultrasonic and light wave sensors. Attenuation, used to quantify the decrease in signal strength caused by medium loss during propagation. Centroid, used to describe the central location of the data distribution. Represents Dispersion, used to quantify the degree of dispersion of data. It stands for Kurtosis, which is used to measure the kurtosis or tail thickness of a probability distribution.

[0044] This module collects the vibratory acoustic fingerprints of all paths generated within a detection time slot, forms a fingerprint matrix, and outputs it to the fingerprint evolution timing inference module.

[0045] See attached document Figure 4 , Figure 4 This is a block diagram illustrating the working principle of a fingerprint evolution timing inference module according to an embodiment of the present invention. The building construction fingerprint evolution timing inference module is the core computing unit of the system of the present invention. It receives fingerprint data output from the vibration acoustic fingerprint generation and analysis module, and outputs inference results on the concrete material properties and an evaluation value of the compactness state.

[0046] In one embodiment, the module includes a pre-built benchmark database. This benchmark database is generated experimentally in an offline phase. The specific generation process involves: preparing various standard concrete specimens with defined material properties (e.g., different grades, different mix proportions, different slumps); during the entire vibration compaction process of these specimens, response signals are collected at fixed time intervals using the detection mechanism of this invention, generating a vibration acoustic fingerprint, thereby obtaining a complete fingerprint evolution time-series trajectory for each type of standard specimen from its initial state to its fully compacted state; this trajectory is the benchmark fingerprint evolution time-series trajectory. Simultaneously, at multiple key time points during the vibration process, the true compaction value of the specimen at these points is obtained through independent physical measurement methods (e.g., gamma-ray densitometer or core sampling). Based on the fingerprint data collected at multiple time points and the corresponding true compaction values, a specific mapping function is constructed for each type of material through regression analysis (e.g., multinomial regression or training a neural network model), capable of mapping instantaneous vibration acoustic fingerprints to quantified compaction values. Ultimately, the building construction benchmark database stores multiple benchmark entries, each containing an identifier for a material category, its corresponding benchmark fingerprint evolution timeline trajectory, and the associated mapping function.

[0047] In one specific embodiment, the construction mapping function is a multi-layer perceptron (MLP) neural network. The number of input layer nodes in this network is the same as the dimension of the construction vibration acoustic fingerprint, and it receives a fingerprint vector. As input, the network contains at least one hidden layer, using, for example, a rectified linear unit (ReLU) as the activation function. Its output layer is a single node that outputs a scalar value, which is the predicted quantized density value. The network is trained under supervision using offline collected fingerprint density data via backpropagation until the mean squared error loss function between its predicted output and the true density value converges to below a preset threshold.

[0048] During system online operation, this module first performs online inference of material properties. It maintains a current fingerprint evolution time series in memory, composed of vibrational acoustic fingerprints generated in all probe time slots since system startup, arranged chronologically. When a new fingerprint is received, the module appends it to the end of this time series. Subsequently, the module employs the Dynamic Time Warping (DTW) algorithm to calculate the similarity between the current fingerprint evolution time series and each baseline fingerprint evolution time series stored in the baseline database. The DTW algorithm can find the optimal nonlinear alignment path between two unequal time series and calculate the minimum cumulative distance. Its calculation formula is: ; in, It is a dynamically time-normalized distance metric. This is the current fingerprint evolution time sequence. It is the first A baseline trajectory, and These are fingerprint vectors from two sequences, respectively. It is the Euclidean distance between the two fingerprint vectors. This symbol represents all possible matching paths (or matching methods). This summation expression calculates the summation along the matching path. In this context, the sum of squares of the distance (or similarity) measure between all corresponding points is... This represents an alignment path. This is a distance function representing a time series. The Middle Points and Time Series The Middle The measurement between points.

[0049] This module determines the material category corresponding to the baseline fingerprint evolution timeline trajectory with the minimum DTW distance to the current fingerprint evolution timeline as the material property of the concrete currently being vibrated.

[0050] After determining the material category, the module then performs a calibration assessment of the compaction state. Specifically, the module retrieves the specific mapping function corresponding to the newly determined material category from the benchmark database. Then, the latest vibratory acoustic fingerprint vector, output by the vibratory acoustic fingerprint generation and parsing module, is used as input and substituted into the mapping function for calculation. The output of this function is the quantitative compaction state assessment value of the concrete medium at the current moment. This method of first identifying the material and then selecting the corresponding assessment model achieves dynamic calibration of the compaction assessment.

[0051] In addition, this module is also equipped with an abnormal state alarm function. After calculating the DTW distance between the current time series and all reference trajectories, this module will obtain the minimum distance value. With a preset abnormal threshold Compare. If This indicates that the current vibration response behavior of the concrete differs significantly from the behavior of all known standard materials in the database. At this point, the module generates an alarm signal indicating abnormal material properties to alert the operator.

[0052] Pre-set abnormal thresholds in building construction The method for determining the distance is as follows: During the offline construction of the benchmark database, the DTW distance between any two different benchmark fingerprint evolution time-series trajectories in the database is calculated to form an inter-class distance set. The statistical characteristics of this set are then taken, such as the mean plus three standard deviations. Alternatively, the 95th percentile value of the set can be used as the threshold for construction anomalies. This method ensures that the threshold is an objectively set based on the existing data distribution, rather than a subjectively specified one.

[0053] See attached document Figure 5 , Figure 5 This is a schematic diagram illustrating the workflow of a multi-objective dynamic decision engine employing a model predictive control strategy according to an embodiment of the present invention. The multi-objective dynamic decision engine for building construction is the central control and optimization unit of the system of the present invention. It receives the evaluation results of the internal state of the concrete and outputs optimal control commands for the vibrator network.

[0054] In one embodiment, the engine employs a Model Predictive Control (MPC) strategy to generate dynamic job instructions. The core of this strategy is that, at the end of each control cycle (e.g., at the end of each probe time slot), the engine does not only calculate the optimal instruction for the current moment, but also predicts the system behavior within a finite time window (i.e., the prediction time domain) based on a system model, and performs rolling optimization based on this prediction.

[0055] The specific execution process of this MPC strategy includes the following steps: The engine first obtains the current density state vector from the fingerprint evolution time sequence inference module. And the inferred material property parameters. The engine contains a state prediction model that can predict the current density state. Material property parameters, and a set of hypothetical future control input sequences. 1) To predict the system in the future A state evolution sequence with a time step The control input here It is a vector containing the values ​​of all oscillator nodes at time t. The operating parameters (such as frequency and amplitude) are used. This state prediction model can be established offline by systematically identifying experimental data from the same source as the benchmark database.

[0056] In one specific embodiment, the building construction status prediction model is a Long Short-Term Memory (LSTM) network. The input to this LSTM network is the density state at the current moment. With the currently applied control input The network combines various control inputs to learn the temporal evolution of the density state. Through its internal loop structure and gating mechanism, it learns the temporal evolution of the density state under different control inputs. Its output is a prediction of the density state at the next time step. By using the predicted output as input for the next time step, the model is able to predict the future. Autoregressive prediction of state evolution sequences with time steps.

[0057] Rolling optimization: After obtaining the state prediction, the engine solves a problem in the prediction time domain. The open-loop optimization problem within the system aims to find the optimal control sequence. ; in, It is a set representing the optimized or selected sequence of control signals. To control the time domain, so that the comprehensive cost function in the future prediction time domain is minimize, This is a list of elements within a set, representing the sequence from time [time]. Start to control signals , Indicates time The optimal control signal or control input, Indicates time (in The optimal control signal, is a non-negative integer representing the length of the signal sequence or the size of the control time window. In this case, the aforementioned comprehensive cost function is expressed in the prediction time domain as... The cumulative form of the above: ; in, For at any time Predicted time The density state vector; The target compactness state vector; and In the control step Energy and time costs, These are the preset weighting coefficients corresponding to the quality, energy consumption, and time cost items, respectively.

[0058] During the solution process, various constraints must be satisfied, such as the vibration frequency and amplitude of each vibrator node must be within their physically permissible upper and lower limits. This optimization problem can be solved using numerical optimization algorithms such as Sequential Quadratic Programming (SQP).

[0059] Command execution and feedback correction: After calculating the optimal control sequence Subsequently, a key feature of the MPC strategy is that the engine only executes the first control instruction in the sequence. As the final dynamic operation instruction, it is issued to the sensing-execution dual-mode vibrator network for execution. The remainder of the sequence... Then it is discarded. At the next decision-making moment... The system will measure the new actual density state. The engine uses this new measured state as the initial condition and repeats the state prediction and rolling optimization process described above. This feedback correction mechanism based on the latest measured state enables the control process to effectively cope with model mismatch and external disturbances.

[0060] Ultimately, the dynamic operation instructions generated by this engine are a set of instructions containing personalized operating parameters for each vibrator node in the network. These construction operation parameters specifically include the node's operating mode (vibration or standby) in the next vibration time slot, vibration frequency, vibration amplitude, and operation duration. In this way, the engine achieves refined, proactive, and adaptive control of the entire vibration process.

[0061] See attached document Figure 6 , Figure 6 This is a flowchart of a method for matching vibration parameters of an attached vibrator according to an embodiment of the present invention. The overall workflow of the present invention will be described in detail below in conjunction with the aforementioned system structure.

[0062] Step S1: System initialization.

[0063] Before the vibration compaction operation begins, the system is powered on and initialized. This process includes loading a pre-built benchmark database into memory, which contains benchmark fingerprint evolution time-series trajectories and mapping functions corresponding to various material types. Simultaneously, the target compaction state vector is set. and the weighting coefficients of each item in the comprehensive cost function .

[0064] Step S2: Perform a probe scan.

[0065] The system enters its first working cycle. The construction sensing and execution dual-mode vibrator network first enters the detection time slot. After a brief quiet period, the network performs a complete grid scan, that is, by rotating different vibrator nodes as transmitting nodes and the remaining nodes as receiving nodes, it collects a set of response signals covering multiple propagation paths within the monitoring area.

[0066] Step S3: Generate Vibration Acoustic Fingerprint. The dual-mode vibrator network for building construction sensing and execution transmits the collected raw response signals to the vibration acoustic fingerprint generation and analysis module. This module preprocesses each signal and extracts a set of physical features such as time of flight, energy attenuation, and spectral centroid. These features are then combined into a multi-dimensional feature vector, which is the vibration acoustic fingerprint corresponding to each propagation path at the current moment.

[0067] Step S4: Infer material properties and assess density.

[0068] The construction vibration acoustic fingerprint generation and analysis module outputs the newly generated fingerprint matrix to the fingerprint evolution time series inference module. This module first appends the new fingerprint data to the end of the current fingerprint evolution time series sequence being constructed. Then, it calculates the distance between this sequence and each baseline trajectory in the baseline database using the Dynamic Time Warping (DTW) algorithm, determining the current concrete material properties based on the material category corresponding to the minimum distance. Next, it calls a specific mapping function associated with that material category, inputting the latest fingerprint vector to calculate the quantized density state vector at the current moment. .

[0069] Step S5: Perform multi-objective optimization decision-making.

[0070] The construction fingerprint evolution time sequence inference module infers the inferred material performance parameters and the evaluated density state vector. This information is then transmitted to the multi-objective dynamic decision engine. This engine uses... Given the current state, and utilizing its internal state prediction model and model predictive control (MPC) strategy, the optimal control sequence for the next control time domain is calculated by solving the problem of minimizing the comprehensive cost function over a finite prediction time domain. .

[0071] Step S6: Issue and execute dynamic job instructions.

[0072] The multi-objective dynamic decision engine for building construction calculates the optimal control sequence. In the middle, only the first control instruction is extracted. This is then used as a dynamic work instruction for the next vibration time slot and sent to the construction sensing and execution dual-mode vibrator network. The network then enters the vibration time slot and executes the vibration operation precisely according to the working mode, frequency, amplitude, and other parameters set for each vibrator node in the instruction.

[0073] Step S7: Determine if the task is completed and loop.

[0074] After one vibration interval, the system evaluates the current density state vector. With the target compactness state vector Compare. If All components are greater than or equal to If the corresponding component is detected, the vibration operation is considered complete, and the system stops operating. Otherwise, the system will return to step S2, enter the next detection time slot, and begin a new round of detection, evaluation, decision-making, and execution closed-loop control cycle until the operation is completed.

Claims

1. An attached vibrator vibration parameter matching decision system, characterized in that, The system comprises: a perception-execution dual-mode vibrator network configured to control multiple vibrator nodes in the network to switch between a vibration mode and a detection mode, and in the detection mode, to emit a detection signal by at least one designated vibrator node and to receive a response signal after penetrating a concrete medium by at least one remaining vibrator node; a vibration-acoustic fingerprint generation and analysis module connected to the perception-execution dual-mode vibrator network and configured to extract multiple preset physical features from the response signal for generating a vibration-acoustic fingerprint representing an internal state of the concrete medium; a fingerprint evolution time sequence inference module connected to the vibration-acoustic fingerprint generation and analysis module and configured to construct a fingerprint evolution time sequence composed of the vibration-acoustic fingerprints at multiple time points, and to infer material properties of the concrete medium and to evaluate a compactness state of the concrete medium based on the fingerprint evolution time sequence; a multi-target dynamic decision engine connected to the fingerprint evolution time sequence inference module and configured to generate dynamic operation instructions aiming to optimize a balance between concrete vibration quality, energy consumption and efficiency based on the inferred material properties and the evaluated compactness state, and to issue the dynamic operation instructions to the perception-execution dual-mode vibrator network.

2. The attached vibrator vibration parameter matching decision system according to claim 1, characterized in that, The perception-execution dual-mode vibrator network is configured to: divide a working time into alternating vibration time slots and detection time slots using a time division multiplexing mechanism; in the vibration time slots, all vibrator nodes perform vibration operations according to the dynamic operation instructions; in the detection time slots, vibrator nodes emitting detection signals are rotated for grid scanning of the concrete medium.

3. The attached vibrator vibration parameter matching decision system according to claim 1, characterized in that, The vibration-acoustic fingerprint generation and analysis module is specifically configured to extract at least two physical features selected from the following group for generating the vibration-acoustic fingerprint: time of flight, energy attenuation, spectral centroid, phase dispersion and kurtosis.

4. The attached vibrator vibration parameter matching decision system according to claim 1, characterized in that, The fingerprint evolution time sequence inference module further comprises a reference database storing multiple reference entries, one reference entry corresponding to one material category and including a reference fingerprint evolution time sequence corresponding to the material category and a mapping function generated based on experimental data of the material category. The fingerprint evolution time sequence inference module is specifically configured to infer the material properties of the concrete medium by calculating distances between the current fingerprint evolution time sequence and each reference fingerprint evolution time sequence in the reference database.

5. The attached vibrator vibration parameter matching decision system according to claim 4, characterized in that, The fingerprint evolution time sequence inference module is further configured to compare the calculated minimum distance with a preset abnormal threshold, and to generate an abnormal material property alarm signal when the minimum distance is greater than the abnormal threshold.

6. The attached vibrator vibration parameter matching decision system according to claim 4, characterized in that, The fingerprint evolution time sequence inference module is further configured to: determine a material category according to the minimum distance between the fingerprint evolution time sequence and a reference fingerprint evolution time sequence; and call a mapping function corresponding to the determined material category in the reference database to map the current vibration-acoustic fingerprint to the compactness state for calibration of the compactness evaluation.

7. The attached vibrator vibration parameter matching decision system according to claim 1, characterized in that, The multi-objective dynamic decision engine is configured to solve an integrated cost function to generate the dynamic operation instructions, the integrated cost function including a weighted sum of a quality cost term, an energy cost term, and a time cost term.

8. The attached vibrator vibration parameter matching decision system according to claim 7, characterized in that, The multi-objective dynamic decision engine employs a model predictive control strategy, at each decision time instant, predicts the system evolution within a finite time window based on the current density state and the material properties, and solves the integrated cost function on the fly to generate the dynamic operation instructions.

9. The attached vibrator vibration parameter matching decision system according to claim 1, characterized in that, The dynamic operation instructions include individualized operation parameters for each of the vibrator nodes, the operation parameters including at least one of working mode, vibration frequency, vibration amplitude, and duration.

10. An attached vibrator vibration parameter matching decision method, characterized in that, The method comprises the following steps: The perception-execution dual-mode vibrator network is configured to control multiple vibrator nodes within the network to switch between a vibration mode and a detection mode, and in the detection mode, to emit a detection signal and receive a response signal after penetrating the concrete medium; A plurality of preset physical features are extracted from the response signal to generate a vibration-acoustic fingerprint representing the internal state of the concrete medium; A fingerprint evolution time sequence is constructed from the vibration-acoustic fingerprints at multiple time points, and based on the fingerprint evolution time sequence, the material properties of the concrete medium are inferred online, and its density state is evaluated; Based on the inferred material properties and the evaluated density state, dynamic operation instructions for each of the vibrator nodes are generated, aiming to optimize the balance between concrete vibration quality, energy consumption, and efficiency, and the perception-execution dual-mode vibrator network is controlled to execute.

Images