Intelligent mixing and monitoring system and method for waste slurry and muck

Abstract

The invention provides an intelligent mixing monitoring system and method for waste slurry and muck, and belongs to the technical field of monitoring. An intelligent mixing and monitoring system for waste slurry and muck comprises a multi-mode sensing network module used for conducting global monitoring on the state of muck mixing materials in a stirring tank, and a multi-mode sensing network is combined with various sensors of different types to collect data such as the moisture content, the temperature and vibration of the materials; the multi-source heterogeneous data fusion engine module is in communication connection with the multi-mode sensing network and is used for performing feature extraction and weighted fusion processing on the multi-source heterogeneous data acquired by the multi-mode sensing network to generate fusion data reflecting the state of the mixture; and the fuzzy-PID hybrid control module is connected with the multi-source heterogeneous data fusion engine, is used for adjusting the dry soil feeding amount, the opening degree of a hot blast valve and the stirring rotating speed in real time based on the fused data, performs closed-loop control, and has adaptive parameter setting capability.

Description

Technical Field

[0001] This invention belongs to the field of monitoring technology, specifically a smart mixing monitoring system and method for waste slurry and slag. Background Technology

[0002] Existing mixing monitoring technologies have the following drawbacks. First, the sensing technology is too simplistic: single near-infrared monitoring uses a single-point near-infrared probe installed on the top of the mixing tank, which has several problems: First, there are blind spots, as the material at the edge and bottom of the tank cannot be covered, and experiments show that the mixing uniformity error reaches 28%; second, the penetration is insufficient, and for materials with high humidity (moisture content > 30%), the spectral signal attenuation is > 60%, resulting in a serious decrease in data validity; third, there is a defect of offline sampling, which requires periodic shutdowns for sampling and testing, with 2-3 interruptions per batch, reducing equipment utilization by 12%-18%.

[0003] Secondly, there is the issue of feedback control lag: the existing PID control system for the mixer humidity regulation system has inherent defects. On the one hand, the linear model is limited, assuming that the change in moisture content is linearly related to the hot air flow, but in reality it is a nonlinear multivariable coupling, which makes the peak temperature control error reach ±8℃. On the other hand, the actuator response is slow, and the delay time for traditional pneumatic valves to regulate the hot air flow is greater than 12 seconds, which leads to excessive overshoot and instantaneous moisture content fluctuations of ±5%.

[0004] Finally, there is the reliance on manual intervention: Besides inherent limitations such as linear model constraints and slow actuator response, PID-based mixer humidity control systems also suffer from numerous problems in their production process. Operators must visually judge the color and texture of materials every 15 minutes; due to visual biases caused by factors such as dark-colored additives, the subjective misjudgment rate is >40%. In the face of unexpected situations such as material clumping, the response delay is approximately 3-5 minutes, resulting in rework costs exceeding 1.2 million yuan annually.

[0005] Existing waste slurry and slag mixing equipment suffers from significant technological gaps in areas such as sensor coverage, dynamic control precision, and multi-parameter coordination. Especially when dealing with construction waste slurry containing complex impurities and exhibiting highly fluctuating moisture content, traditional technologies struggle to meet the dual requirements of environmental protection and economic efficiency for resource-based disposal. Summary of the Invention

[0006] The purpose of this invention is to address the aforementioned problems in existing technologies by proposing an intelligent mixing and monitoring system and method for waste slurry and slag, which comprehensively improves processing accuracy. This invention enhances the accuracy of controlling the moisture content of slag and slag through a multimodal sensor network combined with various types of sensors.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A smart mixing and monitoring system for waste slurry and slag includes:

[0009] The multimodal sensor network module is used to monitor the state of the slag and soil mixture in the mixing tank. The multimodal sensor network combines various types of sensors to collect data such as the moisture content, temperature, and vibration of the material.

[0010] The multi-source heterogeneous data fusion engine module is communicatively connected to the multimodal sensor network and is used to perform feature extraction and weighted fusion processing on the multi-source heterogeneous data collected by the multimodal sensor network to generate fusion data reflecting the state of the mixture.

[0011] The fuzzy-PID hybrid control module is connected to the multi-source heterogeneous data fusion engine and is used to adjust the dry soil feeding amount, hot air valve opening and mixing speed in real time based on the fused data, and to perform closed-loop control, with adaptive parameter tuning capability.

[0012] The actuator control module is used to control the dry soil feeding amount of the dry soil feeding mechanism, the opening degree of the hot air regulating valve, and the mixing speed of the mixing drive mechanism, respectively.

[0013] An abnormal operating condition detection module is connected to the multi-source heterogeneous data fusion engine and the fuzzy-PID hybrid control module. It is used to automatically identify abnormal operating conditions in the mixing process based on the fused data and to control the actuator to respond quickly.

[0014] In the aforementioned waste slurry and slag mixing monitoring device, the multimodal sensor network module includes a three-dimensional lidar sensor, a Bragg fiber grating sensor, a microwave moisture sensor, a miniature thermal imager, and a piezoelectric vibration sensor.

[0015] In the above-mentioned waste slurry and slag mixing monitoring device, the multimodal sensor network module adopts a three-dimensional layout inside the mixing tank, and is divided into three monitoring areas along the height direction of the mixing tank: upper, middle and lower. Each monitoring area is equipped with multiple sensor nodes. The mixing tank is divided into multiple sectors along its circumference, and each sector is equipped with a group of sensors. The sensor group includes at least one lidar sensor and multiple Bragg fiber grating sensors to achieve 360° all-round monitoring of the inside of the mixing tank.

[0016] In the aforementioned waste slurry and slag mixing monitoring device, the multimodal sensor network adopts anti-interference signal enhancement technology, including frequency division multiplexing synchronous acquisition, which enables signals from different types of sensors to be transmitted at different frequencies to avoid mutual interference; it also includes dynamic benchmark calibration, which periodically collects the sensor background noise under no-load conditions and deducts environmental noise interference in real time.

[0017] In the aforementioned waste slurry and slag mixing monitoring device, the multi-source heterogeneous data fusion engine module includes data preprocessing and multi-dimensional feature extraction and weight allocation. It uses Kalman filtering to fuse multi-sensor data, employs random forest algorithm to dynamically evaluate the importance of extracted features, and combines spatiotemporal feature recognition technology to analyze the temporal change characteristics of the mixed material state.

[0018] In the aforementioned waste slurry and slag mixing monitoring device, the data preprocessing module uses wavelet packet decomposition analysis to extract the power spectrum features of multiple frequency bands for vibration signals, and detects sudden impact events through kurtosis index; it also calculates the volumetric moisture content of slag and slag based on the correspondence between attenuation coefficient and dielectric constant for microwave signals.

[0019] In the above-mentioned waste slurry and slag mixing monitoring device, the fuzzy-PID mixing control module includes an upper fuzzy decision unit and a lower PID control unit. The upper fuzzy decision unit generates a dry soil feeding rate correction factor and a hot air valve opening reference value based on parameters such as target moisture content deviation and temperature gradient. The lower PID control unit adjusts the actuator according to the instructions output by the fuzzy decision unit to control the dry soil feeding rate, hot air valve opening and mixing speed.

[0020] In the aforementioned waste slurry and slag mixing monitoring device, the fuzzy-PID hybrid control module has an adaptive parameter tuning mechanism based on Lyapunov stability theory. It dynamically adjusts the proportional, integral, and derivative coefficients of the PID control unit by calculating system errors and parameter deviations in real time to ensure the stability and rapid response of the control process.

[0021] The aforementioned waste slurry and slag mixing monitoring device also includes a human-machine interface module connected to the fuzzy-PID hybrid control module. This module is used for visual monitoring and interactive operation of the mixing process via an augmented reality (AR) head-mounted display and voice / gesture interaction. This includes displaying a thermal map of the slag mixture status, providing abnormal alarms and maintenance assistance information. The human-machine interface module displays the temperature distribution of the mixed materials in a three-dimensional thermal map format via the AR head-mounted display, overlaying information such as remaining mixing time and mixing uniformity index. When abnormal conditions occur, a voice alarm is triggered, allowing operators to confirm or execute pre-plans via gesture commands. In maintenance mode, the human-machine interface module overlays a three-dimensional model of the key internal components of the device and provides component replacement guidance.

[0022] In the above-mentioned waste slurry and slag mixing monitoring device, the abnormal operating conditions include material blockage, overheating, and foreign object impact.

[0023] A method for intelligent monitoring of waste slurry and slag mixing includes the following steps:

[0024] The condition of the slag and soil mixture in the mixing tank is monitored throughout the entire process.

[0025] Feature extraction and weighted fusion processing are performed on the multi-source heterogeneous data collected by the multimodal sensor network to generate fused data reflecting the state of the mixture.

[0026] Based on the fused data, the dry soil feeding amount, hot air valve opening and mixing speed are adjusted in real time and closed-loop control is performed, with adaptive parameter tuning capability.

[0027] The control operations for dry soil application, hot air supply, and mixing operation are executed separately.

[0028] The system automatically identifies abnormal conditions during the mixing process based on the fused data and coordinates the control mechanism to respond quickly.

[0029] Compared with the prior art, this application has the following advantages:

[0030] This invention comprehensively improves processing accuracy by combining a multimodal sensor network with various types of sensors to enhance the control accuracy of soil moisture content to ±0.8%, reduce the variance of mixing uniformity to 2.3%, and ensure that the homogenization of materials meets the nuclear waste solidification standard through near-infrared dual-wavelength real-time scanning.

[0031] With dual optimization of energy efficiency and resource utilization, significant cost reduction and efficiency improvement are achieved. Based on dynamic hot air scheduling, the energy consumption per ton of slag and soil is reduced. Combined with control of the feeding mechanism for dry soil, the weighing error is reduced and the utilization rate of solidifying agent is improved, resulting in a 39% reduction in the cost per ton of disposal.

[0032] Intelligent closed-loop control and human-machine collaboration drive unmanned upgrades. The fuzzy-PID hybrid control module, combined with the AR holographic guidance system, reduces the frequency of human intervention by 95%. Attached Figure Description

[0033] Figure 1 This is a module diagram of the intelligent mixing and monitoring system for waste slurry and slag in this application;

[0034] Figure 2 This is a flowchart of the intelligent mixing and monitoring method for waste slurry and slag in this application;

[0035] Figure 3 This is a structural diagram of the sensor cluster arrangement in this application;

[0036] Figure 4 This is a diagram showing the arrangement of sensors inside the mixing tank in this application. Detailed Implementation

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0038] like Figure 1 As shown, an intelligent mixing and monitoring system for waste slurry and slag includes:

[0039] The multimodal sensor network module 10 is used to monitor the state of the slag and soil mixture in the mixing tank. The multimodal sensor network combines various types of sensors to collect data such as the moisture content, temperature, and vibration of the material.

[0040] The multi-source heterogeneous data fusion engine module 20 is connected to the multimodal sensor network for feature extraction and weighted fusion processing of multi-source heterogeneous data collected by the multimodal sensor network, generating fusion data that reflects the state of the mixture.

[0041] The fuzzy-PID (Proportional-Integral-Derivative) hybrid control module 30 is connected to the multi-source heterogeneous data fusion engine. It is used to adjust the dry soil feed amount, hot air valve opening and mixing speed in real time based on the fused data, and to perform closed-loop control. It has adaptive parameter tuning capability.

[0042] The actuator control module 40 is used to control the dry soil feeding amount of the dry soil feeding mechanism, the opening degree of the hot air regulating valve, and the mixing speed of the mixing drive mechanism, respectively.

[0043] Closed-loop control refers to the automatic cyclic control and adjustment achieved by controlling the dry soil feeding amount of the soil feeding mechanism, the opening degree of the hot air regulating valve, and the stirring speed of the stirring drive mechanism through the actuator control module 40.

[0044] The abnormal working condition detection module 50 is connected to the multi-source heterogeneous data fusion engine and the fuzzy-PID hybrid control module. It is used to automatically identify abnormal working conditions in the mixing process based on the fused data and to link the control actuators to respond quickly.

[0045] Before starting work, it is necessary to record 30 seconds of vibration and temperature background noise of the mixer (30 rpm) running in the mixing tank under no-load conditions to generate a background signal database; input material characteristic parameters (slag type, density threshold, pollutant type) to trigger the self-learning mode and dynamically adjust the initial weights of the model.

[0046] This invention comprehensively improves processing accuracy by combining a multimodal sensor network with various types of sensors to enhance the control accuracy of soil moisture content to ±0.8% (traditional ±4.5%), reduce the variance of mixing uniformity to 2.3% (original 12.7%), and ensure that the homogenization of materials meets the nuclear waste solidification standard (measured variance <3%) through real-time near-infrared dual-wavelength scanning (ΔR / R0 difference rate).

[0047] With the dual optimization of energy efficiency and resource utilization, significant cost reduction and efficiency improvement have been achieved. Based on the dynamic scheduling of hot air, the energy consumption per ton of slag and soil processing has been reduced from 18.6kWh to 14.2kWh (a 23% reduction in electricity). Combined with the control of the feeding mechanism for dry soil (weighing error ≤0.5kg), the utilization rate of solidifying agent has been increased to 98% (from 85%), resulting in a 39% reduction in the cost per ton of disposal.

[0048] Intelligent closed-loop control and human-machine collaboration drive unmanned upgrades. The fuzzy-PID hybrid control module has a response delay of less than 0.5 seconds. Combined with the AR (Augmented Reality) holographic guidance system (reducing the training cycle from 14 days to 2 days), the frequency of manual intervention is reduced by 95%.

[0049] Specifically, the multimodal sensor network module includes a 3D lidar sensor, a Bragg fiber grating sensor, a microwave moisture sensor, a miniature thermal imager, and a piezoelectric vibration sensor.

[0050] The 3D lidar sensor uses the Beowing AD2-S-X3 3D 256-line high-precision lidar, and the microwave moisture sensor is model HydraProbe-EX2.

[0051] By utilizing the NVIDIA Jetson Orin NX central control board and the aforementioned sensors, a multimodal sensor network covering the entire domain is constructed to achieve real-time monitoring of the state of the mixture (parameters such as moisture content, temperature, and uniformity) in the plate and drum, as well as spatial data reconstruction within the mixing drum.

[0052] Utilizing the computing power redundancy (approximately 58 TOPS) provided by the NVIDIA Jetson Orin NX central control board, the response latency is ≤0.5 seconds.

[0053] Specifically, the multimodal sensor network module adopts a three-dimensional layout inside the mixing tank, divided into three monitoring areas along the height of the mixing tank: upper, middle, and lower. Each monitoring area is equipped with multiple sensor nodes. The mixing tank is also divided into multiple sectors along its circumference, with each sector arranging a sensor cluster. The sensor cluster includes at least one lidar sensor and multiple Bragg fiber grating sensors to achieve 360° all-round monitoring of the inside of the mixing tank.

[0054] The multimodal sensor network topology adopts a three-dimensional layout, dividing the mixing tank into upper, middle, and lower zones along the axial direction. These zones are arranged in circumferential sectors, with a sensor cluster positioned every 120° arc length. Each sensor cluster includes one high-precision lidar sensor and four Bragg fiber grating sensors, totaling three clusters to achieve 360° omnidirectional coverage. Figure 3 and Figure 4 As shown.

[0055] Corresponding monitoring nodes are set up between the upper, middle, and lower zones, each integrating a microwave moisture sensor. The microwave moisture sensor is a dual-frequency transmitter (2.45GHz / 5.8GHz) with a penetration depth ≥30cm. One microwave moisture sensor is arranged every 120° arc length, for a total of six sensors. Figure 4 As shown. The microwave moisture sensor is installed on the side wall of the mixing tank, with an insertion depth of ≥15cm, ensuring insulation from the tank body (dielectric withstand voltage >3kV).

[0056] The miniature thermal imager has a resolution of 64×64 pixels, a temperature measurement range of 0-150℃, and a piezoelectric vibration sensor (bandwidth 0-1kHz, sensitivity 50mV / g). The miniature thermal imager is a fixed-type thermal imager (FLIR-A315), with the lens pointed at the center of the mixing tank, a vertical field of view of 45°, and the imager updates the temperature field distribution map of the entire tank every 5 seconds (resolution 256×192).

[0057] Three sets of piezoelectric vibration sensors (PCB-352C33, range ±500g) are embedded in the surface of the stirring paddle (304 stainless steel) with a spacing of 120° to capture torque fluctuations across the entire angle.

[0058] The microwave moisture sensor emits a detection pulse every 0.2 seconds; the piezoelectric vibration sensor captures acceleration data at a sampling rate of 1 kHz and eliminates high-frequency noise through an FIR low-pass filter (cutoff frequency 200 Hz).

[0059] Specifically, the multimodal sensor network employs anti-interference signal enhancement technology, including frequency division multiplexing synchronous acquisition, which enables signals from different types of sensors to be transmitted at different frequencies to avoid mutual interference; it also includes dynamic benchmark calibration, which periodically collects the sensor background noise under no-load conditions and deducts environmental noise interference in real time.

[0060] Anti-interference signal enhancement technologies include frequency division multiplexing synchronous acquisition, which uses different carrier frequencies (5.8GHz / 10MHz / DC) for microwave, vibration, and temperature signals to avoid mutual interference; and dynamic reference calibration, which collects the sensor's background noise under no-load conditions every 10 seconds and deducts environmental interference in real time, such as vibration signal offset caused by motor vibration.

[0061] Specifically, the multi-source heterogeneous data fusion engine module includes data preprocessing and multi-dimensional feature extraction and weight allocation. It uses Kalman filtering to fuse multi-sensor data, employs random forest algorithm to dynamically evaluate the importance of extracted features, and combines spatiotemporal feature recognition technology to analyze the temporal change characteristics of the mixed material state.

[0062] A real-time decision-making mechanism based on Kalman filter data fusion is established to collaboratively optimize parameters such as material ratio, temperature and humidity, and stirring intensity in the mixing tank, with a response delay of ≤0.5 seconds, and timely generation of fused data reflecting the state of the mixed material.

[0063] The implementation consists of two parts: a data preprocessing pipeline and a multi-dimensional feature extraction and weight allocation algorithm.

[0064] First, data preprocessing is performed. Wavelet packet decomposition analysis is used to analyze the vibration signal to extract the power spectrum features of multiple frequency bands, and sudden impact events are detected by kurtosis index. The volumetric water content of the slag is calculated by inverting the relationship between the attenuation coefficient and the dielectric constant of the microwave signal.

[0065] In terms of vibration signal processing, wavelet packet decomposition is first used to extract the power spectral density of six characteristic frequency bands (0-50Hz, 50-100Hz, ..., 250-300Hz, respectively). Then, the kurtosis index is used to detect sudden impact signals, such as signals generated by the collision of metallic foreign objects. Microwave signal processing is based on the mapping relationship between the attenuation coefficient and the dielectric constant to invert the volume water content.

[0066] Second, a multi-dimensional feature extraction and weight allocation algorithm, and dynamic feature importance assessment: A feature selector based on random forest is constructed to dynamically select key influencing factors from 27 original parameters. These key influencing factors are calculated in real-time using a feature weight matrix, where represents the index of different sensors or data sources in the feature weight matrix, and represents the index of the feature parameters in the feature weight matrix. This matrix is ​​adaptively adjusted according to environmental conditions, as shown in the following formula:

[0067] in, This is the confidence weighting factor for the sensor. This indicates the reliability of the sensor itself (i.e., confidence score). (the degree of influence on the final weight) For parameter sensitivity weighting factors, Indicates sensitivity to systematic errors (i.e.) The degree of influence on the final weight. Score the confidence level of the sensor. This represents the overall system error.

[0068] Table 1 shows the relevant table for 27 monitoring parameters.

[0069] Specifically, the fuzzy-PID hybrid control module includes an upper-level fuzzy decision unit and a lower-level PID control unit. The upper-level fuzzy decision unit generates a dry soil feeding rate correction factor and a hot air valve opening reference value based on parameters such as target moisture content deviation and temperature gradient. The lower-level PID control unit adjusts the actuator according to the instructions output by the fuzzy decision unit to control the dry soil feeding rate, hot air valve opening, and mixing speed.

[0070] This module includes an upper-level fuzzy decision-maker and a lower-level PID controller. The upper-level fuzzy decision-maker takes as input the target moisture content deviation, temperature gradient, and mixing degree level; and outputs the correction factor for the dry soil feeding rate and the reference value for the hot air valve opening.

[0071] Lower-level PID controller: Receives fuzzy instructions from the upper-level PID controller and adjusts the actuator in real time using the following formula:

[0072]

[0073] in, For time steps, The control output represents the execution command generated by the control system at the current moment, used to adjust physical quantities such as the opening degree of the hot air valve, the stirring speed, or the dry soil feeding rate. Error signal. It consists of the difference between the set value output by the fuzzy decision maker and the value detected by the sensor. It is a proportionality coefficient, which amplifies the direct impact of the current error and provides a rapid response to instantaneous deviations. The integral value of accumulated historical errors is used to eliminate steady-state errors of the system (such as long-standing small deviations). It is used to predict the trend of error changes and suppress overshoot and oscillation.

[0074] Specifically, the fuzzy-PID hybrid control module has an adaptive parameter tuning mechanism based on Lyapunov stability theory. It dynamically adjusts the proportional, integral, and derivative coefficients of the PID control unit by calculating system error and parameter deviation in real time to ensure the stability and fast response of the control process.

[0075] This module features adaptive parameter tuning, dynamically adjusting PID parameters based on Lyapunov stability theory. :

[0076] in, This refers to the error signal in the above PID control formula. The learning rate is used to optimize the system's convergence speed through gradient descent.

[0077] The dynamic coupling of key influencing factors and control strategies achieves precise regulation through a multi-level linkage mechanism. The system relies on a feature weight matrix generated in real-time by a multi-source heterogeneous data fusion engine module to construct a full-process control logic that runs through perception, decision-making, and execution. When the spatial variance of moisture content exceeds the 0.05 threshold, the system automatically triggers uniformity compensation control. At this time, the fuzzy decision-maker outputs differentiated speed commands, increasing the speed in the central area of ​​the mixing tank by 5 rpm while decreasing the speed in the edge area by 3 rpm, thus forcibly eliminating material stratification by forming convective vortices. For abnormal operating conditions with a temperature gradient exceeding 8℃ / m, the bottom-level control unit activates the hot air curtain function, dividing the circumference of the mixing tank into eight independently controllable fan-shaped areas. A PID controller finely adjusts the flow rate deviation of the hot air valves in each zone by ±20%, effectively mitigating the risk of localized overheating.

[0078] The system solves the multi-objective optimization function using a sequential quadratic programming algorithm, incorporating key parameters such as moisture content deviation, temperature exceedance, and torque fluctuation into a unified calculation framework. The sequential quadratic programming algorithm is mainly used for constrained optimization problems and is currently recognized as one of the most effective methods for solving constrained nonlinear optimization problems. In this device, it is used to solve the optimal solution of control parameters under the constraints of the weight matrix and functions such as moisture content.

[0079] The system dynamically generates an optimal control vector that includes the dry soil feeding rate, hot air valve opening, and mixing speed. This process deeply integrates vibration spectrum feature analysis technology. When the vibration energy change rate in the 200-300Hz frequency band is detected to be continuously exceeding the standard, the control core completes a three-level response within 0.3 seconds: immediately cutting off the current feeding channel, initiating the reverse rotation program of the mixing shaft, and linking the metal detection module to scan for foreign objects. During this process, the adaptive correction mechanism based on Lyapunov stability theory continues to play a role. By calculating the system error vector and parameter estimation deviation in real time, it dynamically adjusts the proportional, integral, and derivative coefficients of the PID controller to ensure that the actuator action meets the requirements of rapid response while effectively suppressing overshoot.

[0080] Specifically, it also includes a human-machine interface module connected to the fuzzy-PID hybrid control module. This module is used to visualize and interactively monitor the mixing process through an augmented reality (AR) head-mounted display and voice and gesture interaction. This includes displaying a heat map of the slag mixture status, providing abnormal alarms and maintenance assistance information. The human-machine interface module displays the temperature distribution of the mixed materials in a 3D heat map format through the AR head-mounted display, and overlays information such as the remaining mixing time and mixing uniformity index. When abnormal conditions occur, a voice alarm is triggered, allowing operators to confirm or execute the contingency plan through gesture commands. In maintenance mode, the human-machine interface module overlays a 3D model of the key internal components of the equipment and provides component replacement guidance.

[0081] Augmented reality (AR)-based operation guidance utilizes a head-mounted display to project a 3D thermal map of the material (high-risk areas >80℃ are marked in red), virtual marker lines to guide the optimal feeding trajectory at the dry soil inlet, and real-time floating countdown timers and current mixing indexes, providing holographic information. Voice-gesture multimodal interaction is implemented in two ways: First, in emergency responses to hazardous conditions, if a sudden temperature rise or abnormal torque is detected, the system forcibly activates a voice alarm (e.g., "Temperature in Zone C exceeds the limit, requesting emergency cooling!"), and the operator can authorize the execution of the contingency plan through gestures (e.g., waving to the right). Second, in maintenance assistance mode, a 3D model of worn internal components is overlaid (e.g., highlighting the mixing blades with wear >50%), and an automatic animation of spare parts replacement tutorials (less than 15 seconds in length) is generated.

[0082] Specifically, abnormal operating conditions include material blockage, overheating, and impact from foreign objects.

[0083] like Figure 2 As shown, a smart mixing and monitoring method for waste slurry and slag includes the following steps:

[0084] S100. Monitor the condition of the slag and soil mixture in the mixing tank throughout the entire process.

[0085] S200: Perform feature extraction and weighted fusion processing on the collected monitoring data to generate fused data reflecting the state of the mixture.

[0086] The S300 adjusts the dry soil feed rate, hot air valve opening, and mixing speed in real time based on fused data, and performs closed-loop control, with adaptive parameter tuning capability.

[0087] S400, respectively executes the control operations of the dry soil feeding amount of the dry soil feeding mechanism, the opening degree of the hot air regulating valve, and the mixing speed of the mixing drive mechanism.

[0088] The S500 automatically identifies abnormal operating conditions during the mixing process based on the fusion data and coordinates with the control actuators to respond quickly.

[0089] It should be noted that all directional indications in the embodiments of the present invention, such as up, down, left, right, front, back, etc., are only used to explain the relative positional relationship and movement of the components in a specific posture, as shown in the attached figure. If the specific posture changes, the directional indication will also change accordingly.

[0090] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Meanwhile, the word "and / or" throughout the text means including three solutions; for example, "A and / or B" includes solution A, solution B, or a solution that simultaneously satisfies A and B. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0091] All of the above components are general standard parts or components known to those skilled in the art. Their structure and principles can be learned by those skilled in the art through technical manuals or conventional experimental methods.

[0092] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0093] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0094] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0095] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0096] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0097] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0098] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A smart mixing and monitoring system for waste slurry and slag, characterized in that, include: The multimodal sensor network module is used to monitor the state of the slag and soil mixture in the mixing tank. The multimodal sensor network combines various types of sensors to collect data such as the moisture content, temperature, and vibration of the material. The multi-source heterogeneous data fusion engine module is communicatively connected to the multimodal sensor network and is used to perform feature extraction and weighted fusion processing on the multi-source heterogeneous data collected by the multimodal sensor network to generate fusion data reflecting the state of the mixture. The fuzzy-PID hybrid control module is connected to the multi-source heterogeneous data fusion engine and is used to adjust the dry soil feeding amount, hot air valve opening and mixing speed in real time based on the fused data, and to perform closed-loop control, with adaptive parameter tuning capability. The actuator control module is used to control the dry soil feeding amount of the dry soil feeding mechanism, the opening degree of the hot air regulating valve, and the mixing speed of the mixing drive mechanism, respectively. An abnormal operating condition detection module is connected to the multi-source heterogeneous data fusion engine and the fuzzy-PID hybrid control module. It is used to automatically identify abnormal operating conditions in the mixing process based on the fused data and to control the actuator to respond quickly.

2. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 1, characterized in that, The multimodal sensing network module includes a three-dimensional lidar sensor, a Bragg fiber grating sensor, a microwave moisture sensor, a miniature thermal imager, and a piezoelectric vibration sensor.

3. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 2, characterized in that, The multimodal sensor network module adopts a three-dimensional layout inside the mixing tank, divided into three monitoring areas along the height of the mixing tank: upper, middle, and lower. Each monitoring area is equipped with multiple sensor nodes. The mixing tank is also divided into multiple sectors along its circumference, with each sector arranging a sensor cluster. The sensor cluster includes at least one lidar sensor and multiple Bragg fiber grating sensors to achieve 360° all-round monitoring of the interior of the mixing tank.

4. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 3, characterized in that, The multimodal sensor network employs anti-interference signal enhancement technology, including frequency division multiplexing synchronous acquisition, which enables signals from different types of sensors to be transmitted at different frequencies to avoid mutual interference; it also includes dynamic benchmark calibration, which periodically collects the sensor background noise under no-load conditions and deducts environmental noise interference in real time.

5. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 1, characterized in that, The multi-source heterogeneous data fusion engine module includes data preprocessing and multi-dimensional feature extraction and weight allocation. It uses Kalman filtering to fuse multi-sensor data, employs random forest algorithm to dynamically evaluate the importance of extracted features, and combines spatiotemporal feature recognition technology to analyze the temporal change characteristics of the mixed material state.

6. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 5, characterized in that, The data preprocessing module uses wavelet packet decomposition analysis to extract power spectrum features of multiple frequency bands for vibration signals and detects sudden impact events through kurtosis index; it also calculates the volumetric water content of slag and soil by inverting the relationship between attenuation coefficient and dielectric constant for microwave signals.

7. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 1, characterized in that, The fuzzy-PID hybrid control module includes an upper-level fuzzy decision unit and a lower-level PID control unit. The upper-level fuzzy decision unit generates a dry soil feeding rate correction factor and a hot air valve opening reference value based on parameters such as target moisture content deviation and temperature gradient. The lower-level PID control unit adjusts the actuator according to the instructions output by the fuzzy decision unit to control the dry soil feeding rate, hot air valve opening, and mixing speed.

8. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 7, characterized in that, The fuzzy-PID hybrid control module has an adaptive parameter tuning mechanism based on Lyapunov stability theory. It dynamically adjusts the proportional, integral, and derivative coefficients of the PID control unit by calculating system error and parameter deviation in real time to ensure the stability and fast response of the control process.

9. The intelligent mixing and monitoring system for waste slurry and slag as described in claim 1, characterized in that, It also includes a human-machine interface module connected to the fuzzy-PID hybrid control module. This module is used to visualize and interactively monitor the mixing process through an augmented reality (AR) head-mounted display device and voice and gesture interaction. This includes displaying a heat map of the slag mixture status, providing abnormal alarms and maintenance assistance information. The human-machine interface module displays the temperature distribution of the mixed materials in a three-dimensional heat map form through the AR head-mounted display device, and overlays information such as the remaining mixing time and mixing uniformity index. When an abnormal condition occurs, a voice alarm is triggered, allowing the operator to confirm or execute the contingency plan through gesture commands. In maintenance mode, the human-machine interface module overlays a three-dimensional model of the key internal components of the device and provides component replacement guidance.

10. A method for intelligent mixing and monitoring of waste slurry and slag, characterized in that, Includes the following steps: The condition of the slag and soil mixture in the mixing tank is monitored throughout the entire process. Feature extraction and weighted fusion processing are performed on the multi-source heterogeneous data collected by the multimodal sensor network to generate fused data reflecting the state of the mixture. Based on the fused data, the dry soil feeding amount, hot air valve opening and mixing speed are adjusted in real time and closed-loop control is performed, with adaptive parameter tuning capability. The control operations for dry soil application, hot air supply, and mixing operation are executed separately. The system automatically identifies abnormal conditions during the mixing process based on the fused data and coordinates the control mechanism to respond quickly.

Images