Decommissioned wind power blade dust monitoring method and monitoring system

Abstract

The invention discloses a dust monitoring method and monitoring system for an out-of-service wind power blade, and relates to the technical field of dust monitoring. The method comprises the following steps: marking a tracing material on an ex-service wind power blade, establishing a mapping relation between spectral characteristics and blade information, transmitting a coaxial composite light detection light field to a to-be-monitored ex-service wind power blade processing area through a multi-frequency laser synergistic excitation source, receiving a returned multi-mode light response mixed signal, and determining the ex-service wind power blade to be monitored according to the received multi-mode light response mixed signal. The method comprises the following steps: performing multi-spectral feature calculation on a multi-modal light response mixed signal through a sub-channel spectral decoupling mechanism to obtain a component-form-traceability three-dimensional feature set, generating a dust hazard level dynamic quantization matrix through a cross-spatio-temporal data coupling knitting algorithm, and constructing a global dust situation monitoring panoramic map through a virtual-real mapping visualization technology. And a directional traceability regulation and control instruction is generated. The dust risk management and control efficiency and precision in the decommissioning wind power blade treatment process can be improved, and harm of dust to personnel health and the environment is reduced.

Description

Technical Field

[0001] This invention relates to the field of dust monitoring technology, and in particular to a method and system for monitoring dust from decommissioned wind turbine blades. Background Technology

[0002] With the rapid development of the wind power industry, the demand for recycling and processing retired wind turbine blades is becoming increasingly urgent. During the resource recovery process, such as cutting and crushing, complex mixed dust is generated, containing glass fiber / carbon fiber, resin matrix, fillers, and coating residues. This dust is not only highly carcinogenic and respiratory irritant, but its composition and hazard level also vary significantly between different batches and models of blades. Traditional monitoring technologies cannot simultaneously acquire multi-dimensional information on dust composition, morphology, and source tracing, leading to incomplete risk assessments. Furthermore, they rely heavily on end-point monitoring, making dynamic early warning and targeted control difficult. This fails to meet the needs of refined, end-to-end safety management in the processing of retired wind turbine blades, resulting in delayed risk identification and ineffective control measures. Therefore, a new monitoring method integrating elemental analysis, morphological identification, and source tracing is urgently needed. Summary of the Invention

[0003] This invention provides a method for monitoring dust from decommissioned wind turbine blades, comprising: Step S1: Mark tracer materials with differentiated standard fluorescence spectral characteristics on retired wind turbine blades of different types and batches, establish the mapping relationship between spectral characteristics and their corresponding blade information, and form a spectral identity database. Step S2: Using a multi-frequency laser coordinated excitation source, a coaxial composite optical detection field is emitted towards the treatment area of ​​the decommissioned wind turbine blade to be monitored, and the multi-mode optical response mixed signal returned from it is received; Step S3: Based on the spectral identity database, multi-channel spectral decoupling mechanism is used to perform multi-spectral feature calculation on the multimodal optical response mixed signal to obtain a three-dimensional feature set of composition-morphology-origin. Step S4: Based on the three-dimensional feature set of composition-morphology-source tracing, a dynamic quantification matrix of dust hazard level is generated through a cross-temporal and spatial data coupling weaving algorithm; Step S5: Based on the dynamic quantification matrix of dust hazard levels, construct a panoramic map of the entire dust situation monitoring through virtual-real mapping visualization technology, and generate targeted source tracing and control instructions.

[0004] The dust monitoring method for decommissioned wind turbine blades described above includes the following sub-steps: marking tracer materials with differentiated standard fluorescence spectral characteristics on decommissioned wind turbine blades of different types and batches, establishing a mapping relationship between spectral characteristics and their corresponding blade information, and forming a spectral identity database. Step S11: Design multidimensional spectral coding of tracer materials based on the combination of fluorescence spectral characteristics and concentration ratios to mark tracer materials for different types of batches of decommissioned wind turbine blades; Step S12: Automatically bind the blade information with the multidimensional spectral code of the tracer material it is labeled with through Internet of Things technology, establish a spectrum-blade mapping relationship, and form a spectral identity database.

[0005] The dust monitoring method for decommissioned wind turbine blades described above, wherein the process of emitting a coaxial composite optical detection field towards the treatment area of ​​the decommissioned wind turbine blade to be monitored using a multi-frequency laser coordinated excitation source and receiving the returned multimodal optical response mixed signal includes the following sub-steps: Step S21: Based on fluorescence-excited laser, component analysis laser and morphology detection laser, a multi-frequency laser co-excitation source is constructed through a high-precision timing control unit and a beam combining unit; Step S22: Using a multi-frequency laser co-excitation source, a coaxial composite optical detection field is emitted towards the processing area of ​​the decommissioned wind turbine blade to be monitored. The returned signal is synchronously collected by a multi-modal sensor to form a multi-modal optical response mixed signal data packet.

[0006] The dust monitoring method for decommissioned wind turbine blades described above includes the following sub-steps: Based on a spectral identity database and using a channel-based spectral decoupling mechanism, multi-spectral band feature calculation is performed on the mixed multimodal photoresponse signal to obtain a three-dimensional feature set of composition, morphology, and source tracing. Step S31: Based on the spectral identity database, the multimodal optical response mixed signal data packet is decomposed into multiple pure spectra representing different signals and their corresponding concentration coefficients through a channel-based spectral decoupling mechanism, and the composition, morphology, and source information of the dust are calculated respectively. Step S32: Encapsulate the composition, form, and source information of the dust according to spatiotemporal coordinates to form a three-dimensional feature set of composition-form-source.

[0007] The dust monitoring method for decommissioned wind turbine blades described above includes the following sub-steps for generating a dynamic quantification matrix of dust hazard levels based on a three-dimensional feature set of composition, morphology, and source tracing using a cross-temporal data coupling weaving algorithm: Step S41: Based on the spatiotemporal coordinates of the three-dimensional feature set of composition-morphology-source, the hazard index is adaptively assigned to each feature through a cross-spatiotemporal data coupling weaving algorithm, and a fusion calculation is performed to generate a dynamic quantification matrix of dust hazard level that changes over time. Step S42: Based on the airflow field data of the processing area, simulate the diffusion path and risk distribution changes of dust clouds, and deduce and update the dynamic quantification matrix of dust hazard level.

[0008] The dust monitoring method for decommissioned wind turbine blades described above, which constructs a panoramic map of the overall dust situation monitoring based on a dynamic quantification matrix of dust hazard levels and uses virtual-real mapping visualization technology to generate targeted source tracing and control instructions, includes the following sub-steps: Step S51: Align the physical processing area with the coordinates of the digital twin model, and render the data layer by layer according to the basic layer, feature layer, risk layer and source layer through virtual-real mapping visualization technology to form a panoramic map of the entire dust situation monitoring. Step S52: Identify high-risk areas in the panoramic map of dust situation monitoring, automatically match the preset strategy library, and send targeted source tracing and control instructions to the underlying PLC control terminal.

[0009] The present invention also provides a dust monitoring system for decommissioned wind turbine blades, comprising: The spectral feature labeling module marks tracer materials with differentiated standard fluorescence spectral characteristics on decommissioned wind turbine blades of different types and batches, establishes a mapping relationship between spectral features and their corresponding blade information, and forms a spectral identity database. The detection light field emission and acquisition module emits a coaxial composite light detection light field towards the treatment area of ​​the decommissioned wind turbine blade to be monitored through a multi-frequency laser coordinated excitation source, and receives the multi-modal light response mixed signal returned from it; The multimodal optical response mixed signal solution module, based on the spectral identity library and through a channel-based spectral decoupling mechanism, performs multi-spectral feature solution on the multimodal optical response mixed signal to obtain a three-dimensional feature set of composition, morphology, and origin. The dust hazard level dynamic quantification matrix generation module generates a dust hazard level dynamic quantification matrix based on a three-dimensional feature set of composition-morphology-source tracing through a cross-temporal and spatial data coupling weaving algorithm. The monitoring panoramic map and control command generation module, based on the dynamic quantification matrix of dust hazard level, constructs a panoramic map of the entire dust situation through virtual-real mapping visualization technology, and generates targeted source tracing control commands.

[0010] As described above, in a dust monitoring system for decommissioned wind turbine blades, the spectral feature labeling module specifically includes: The multidimensional spectral coding submodule designs multidimensional spectral coding of tracer materials based on a combination of fluorescence spectral characteristics and concentration ratios, enabling the marking of tracer materials for different types and batches of decommissioned wind turbine blades. The spectral identity database submodule automatically binds the leaf information with the multidimensional spectral code of the tracer material it is labeled with through Internet of Things technology, establishes a spectrum-leaf mapping relationship, and forms the spectral identity database.

[0011] As described above, the dust monitoring system for decommissioned wind turbine blades includes a light field emission acquisition module, which specifically comprises: The multi-frequency laser co-excitation source construction submodule is based on fluorescence excitation laser, component analysis laser and morphology detection laser, and constructs a multi-frequency laser co-excitation source through a high-precision timing control unit and beam combining unit; The optical response hybrid signal acquisition submodule emits a coaxial composite optical detection field to the processing area of ​​the decommissioned wind turbine blade to be monitored through a multi-frequency laser collaborative excitation source. The returned signal is synchronously acquired by a multi-modal sensor to form a multi-modal optical response hybrid signal data packet.

[0012] The dust monitoring system for decommissioned wind turbine blades described above includes a multimodal optical response mixed signal processing module, specifically comprising: The dust information calculation submodule, based on the spectral identity library and through a channel-based spectral decoupling mechanism, decomposes the multimodal optical response mixed signal data packet into multiple pure spectra representing different signals and their corresponding concentration coefficients, and calculates the composition, morphology, and source information of the dust respectively. The three-dimensional feature set generation submodule encapsulates the composition, morphology, and source information of dust according to spatiotemporal coordinates to form a three-dimensional feature set of composition-morphology-source.

[0013] The dust monitoring system for decommissioned wind turbine blades described above includes a dust hazard level dynamic quantification matrix generation module, which specifically comprises: The dust hazard level dynamic quantification matrix generation submodule, based on the spatiotemporal coordinates of the three-dimensional feature set of composition-morphology-source tracing, adaptively assigns hazard indices to each feature through a cross-spatiotemporal data coupling weaving algorithm, and performs fusion calculation to generate a dust hazard level dynamic quantification matrix that changes over time. The matrix deduction and update submodule, based on the airflow field data of the processing area, simulates the diffusion path and risk distribution changes of dust clouds, and deduces and updates the dynamic quantification matrix of dust hazard level.

[0014] The dust monitoring system for decommissioned wind turbine blades described above includes, in particular, a panoramic monitoring map and control command generation module, comprising: The panoramic map of the entire dust situation monitoring is formed by aligning the physical processing area with the coordinates of the digital twin model and rendering it in layers according to the basic layer, feature layer, risk layer and source layer through virtual-real mapping visualization technology to form a panoramic map of the entire dust situation monitoring. The targeted source tracing and control command sending submodule identifies high-risk areas in the panoramic map of dust situation monitoring across the entire domain, automatically matches the preset strategy library, and sends targeted source tracing and control commands to the underlying PLC control terminal.

[0015] The beneficial effects achieved by this invention are as follows: This invention can achieve a breakthrough improvement in dust monitoring of decommissioned wind turbine blades, solve the problem that traditional methods cannot accurately trace the source, clarify the core information such as the corresponding blade batch and processing line of the dust, and simultaneously acquire the three-dimensional characteristics of dust composition, morphology, and source tracing. It breaks the limitations of single-indicator monitoring, improves the comprehensiveness and accuracy of risk assessment, promotes the transformation of monitoring from passive perception to active control, significantly improves the efficiency and accuracy of dust risk control in the process of decommissioned wind turbine blade processing, and effectively reduces the harm of dust to human health and the environment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0017] Figure 1 This is a flowchart of a dust monitoring method for decommissioned wind turbine blades provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of a dust monitoring system for decommissioned wind turbine blades provided in Embodiment 2 of this application. Detailed Implementation

[0018] The technical solutions of 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, not all, of the embodiments of the present invention. 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.

[0019] Example 1 like Figure 1 As shown in Embodiment 1 of this application, a method for monitoring dust from decommissioned wind turbine blades is provided. The method includes the following steps: Step S1: Mark tracer materials with differentiated standard fluorescence spectral characteristics on retired wind turbine blades of different types and batches, establish the mapping relationship between spectral characteristics and their corresponding blade information, and form a spectral identity database. Furthermore, by labeling tracer materials with differentiated standard fluorescence spectral characteristics on decommissioned wind turbine blades of different types and batches, establishing a mapping relationship between spectral characteristics and their corresponding blade information, and forming a spectral identity database, the following sub-steps are included: Step S11: Design multidimensional spectral coding of tracer materials based on the combination of fluorescence spectral characteristics and concentration ratios to mark tracer materials for different types of batches of decommissioned wind turbine blades; Specifically, fluorescent materials with stable and differentiated standard fluorescence spectral characteristics are screened. Based on N fluorescent materials and their M controllable concentration gradients, spectral codes are designed according to "material type + concentration ratio + emission wavelength" to generate... A multidimensional spectral coding system is used to form a high-capacity coding space, and the uniqueness of the coding is verified by a spectrometer. Based on the batch, model, manufacturer and other information of the retired wind turbine blades, the corresponding fluorescent material is selected as its tracer material, and the tracer material is sprayed onto the blades by an automated spraying equipment according to preset parameters.

[0020] Step S12: Automatically bind the blade information with the multidimensional spectral code of the tracer material it is labeled with through Internet of Things technology, establish a spectrum-blade mapping relationship, and form a spectral identity database; Specifically, each batch of blades is assigned a unique electronic identification code based on blade information such as blade model, service life, processing line ID, and arrival time. Through Internet of Things (IoT) technology, the multidimensional spectral code of the tracer material marked on the blade, the electronic identification code, and the blade information are automatically bound together to establish a mapping relationship of "electronic identification code - multidimensional spectral code - blade information" and store it in a cloud database to form a spectral identification library. A self-learning mechanism is set in the spectral identification library to automatically collect the spectral characteristics of newly introduced blades to expand the spectral identification library, forming a dynamically expandable spectral identification library.

[0021] Step S2: Using a multi-frequency laser coordinated excitation source, a coaxial composite optical detection field is emitted towards the treatment area of ​​the decommissioned wind turbine blade to be monitored, and the multi-mode optical response mixed signal returned from it is received; Furthermore, by using a multi-frequency laser coordinated excitation source, a coaxial composite optical detection field is emitted towards the treatment area of ​​the decommissioned wind turbine blade to be monitored, and the returned multi-mode optical response mixed signal is received, including the following sub-steps: Step S21: Based on fluorescence-excited laser, component analysis laser and morphology detection laser, a multi-frequency laser co-excitation source is constructed through a high-precision timing control unit and a beam combining unit; Specifically, the high-precision timing control unit generates nanosecond-level precision triggering timing through a field-programmable gate array (FPGA), controlling the fluorescence excitation laser, composition analysis laser, and morphology detection laser to emit in a cyclic sequence of fluorescence pumping → morphology detection → laser-induced breakdown. The fluorescence excitation laser matches the absorption peak of the tracer material, the composition analysis laser is used to induce dust plasma, and the morphology detection laser is used for particle morphology analysis. The beam combining unit combines lasers of different wavelengths using a beam combiner and controls the spot size and divergence angle using a beam expander. By controlling the fluorescence excitation laser, composition analysis laser, and morphology detection laser through the high-precision timing control unit and the beam combining unit, a multi-frequency laser co-excitation source capable of emitting a spatially uniform, energy-stable coaxial composite optical detection field is formed, providing full-coverage excitation of the monitoring area.

[0022] Step S22: Using a multi-frequency laser coordinated excitation source, a coaxial composite optical detection field is emitted towards the treatment area of ​​the decommissioned wind turbine blade to be monitored. The returned signal is synchronously collected by a multi-modal sensor to form a multi-modal optical response mixed signal data packet. Specifically, based on the three-dimensional model of the processing area, a scanning path of a multi-frequency laser co-excitation source is preset. The multi-frequency laser co-excitation source is controlled to emit a coaxial composite light detection field to the area to be monitored along the path. Trigger signals synchronized with the laser emission sequence are sent to multi-modal heterogeneous sensors such as spectrometers, high-speed photodetectors, and polarization cameras through the same field programmable gate array. The returned fluorescence, plasma emission, polarization scattering and other signals are synchronously acquired. The acquired raw data is encapsulated into a multi-modal optical response hybrid signal data packet with a timestamp.

[0023] Step S3: Based on the spectral identity database, multi-channel spectral decoupling mechanism is used to perform multi-spectral feature calculation on the multimodal optical response mixed signal to obtain a three-dimensional feature set of composition-morphology-origin. Furthermore, based on the spectral identity database and through a channel-based spectral decoupling mechanism, multi-spectral band feature calculation is performed on the multimodal optical response mixture signal to obtain a three-dimensional feature set of composition-morphology-origin, including the following sub-steps: Step S31: Based on the spectral identity database, the multimodal optical response mixed signal data packet is decomposed into multiple pure spectra representing different signals and their corresponding concentration coefficients through a channel-based spectral decoupling mechanism, and the composition, morphology, and source information of the dust are calculated respectively. Specifically, the implementation of the channel-specific spectral decoupling mechanism involves separating the multimodal photoresponse mixed signal data packet into three independent data streams based on its physical source: fluorescence mixed spectrum, plasma emission mixed spectrum, and polarization scattering intensity signal. Through the source tracing channel, using a spectral identity database as a priori constraint, the fluorescence mixed spectrum is decoupled from the tracer material's fluorescence spectrum and the background signal of the blade material itself. This is then matched with the spectral identity database, and their proportions are quantified to output dust source tracing information. Through the composition channel, peak identification and elemental quantitative analysis are performed on the plasma emission mixed spectrum to separate atomic emission lines representing different elements. Through linear combination or pattern recognition, material spectral bases such as fiber material spectral bases and resin material spectral bases are synthesized, and their proportions are quantified to output dust composition information. Through the morphology channel, the depolarization ratio of the polarization scattering intensity signal is calculated. Based on a preset threshold, fibrous and spherical particles are distinguished, and their quantity proportions are calculated to output dust morphology information.

[0024] Step S32: Encapsulate the composition, form, and source information of the dust according to spatiotemporal coordinates to form a three-dimensional feature set of composition-form-source. Specifically, the composition ratio, morphological proportion, traceability information and spatiotemporal coordinates of dust are bound and encapsulated to form a standard three-dimensional feature set of "composition-morphology-traceability". The feature set format is {timestamp, spatial coordinates, composition and its proportion, morphology and its proportion, blade batch, production line ID}.

[0025] Step S4: Based on the three-dimensional feature set of composition-morphology-source tracing, a dynamic quantification matrix of dust hazard level is generated through a cross-temporal and spatial data coupling weaving algorithm; Furthermore, based on the three-dimensional feature set of composition, morphology, and source tracing, a dynamic quantification matrix of dust hazard level is generated through a cross-temporal and spatiotemporal data coupling weaving algorithm, including the following sub-steps: Step S41: Based on the spatiotemporal coordinates of the three-dimensional feature set of composition-morphology-source, the hazard index is adaptively assigned to each feature through a cross-spatiotemporal data coupling weaving algorithm, and a fusion calculation is performed to generate a dynamic quantification matrix of dust hazard level that changes over time. Specifically, based on the timestamps and spatial coordinates of each component-morphology-origin 3D feature set, the feature sets are aligned within a unified spatiotemporal framework. The specific implementation of the cross-spatiotemporal data coupling weaving algorithm involves using an adaptive hazard index allocation formula based on the unified component-morphology-origin 3D feature set, business rules, and expert knowledge. A hazard index is adaptively assigned to each feature, where, For the first Each feature is based on the fundamental hazard weight of the business rules. For the first The real-time concentration sensitivity coefficient of each feature For the first Real-time measurement values ​​of each feature For the first Historical monitoring average of each characteristic, For the first The standard deviation of each feature To prevent a zero denominator correction term, The fiber morphology reinforcement coefficient. This represents the proportion of fibrous particles in the dust. To strengthen the exponential function, As the fiber percentage threshold, when hour, ,when hour, , For the first The risk amplification coefficient for a specific batch of features This is a special batch indicator function, used when the calculated blades meet specific conditions. ,otherwise .

[0026] Based on various characteristics, the hazard index is adaptively assigned using a dynamic hazard index fusion formula. Calculate the dust hazard level values ​​for each element, generating a dimension... A dynamic quantitative matrix of dust hazard levels covering the entire site and changing over time. Each element of this matrix represents the comprehensive risk value for a specific grid cell at a specific time. For grid cells At any moment The dust hazard level value, For the number of features, The range of values ​​is , For the first One characteristic in time The adaptive hazard index The spatial attenuation coefficient, For the current grid cell To the The spatial distance is the primary source of this feature. This is the peak risk amplification factor. This represents the maximum hazard index among all characteristics.

[0027] Step S42: Based on the airflow field data of the processing area, simulate the diffusion path and risk distribution changes of dust clouds, and deduce and update the dynamic quantification matrix of dust hazard level. Specifically, the dynamic quantification matrix of dust hazard level is coupled with the airflow field data of the treatment area, and the risk field derivation formula is used. The diffusion path and risk distribution changes of dust clouds over a preset time period are simulated, and future moments are obtained by iteratively calculating all grid cells. Prediction matrix The dynamic quantification matrix of dust hazard levels is updated predictively, among which... For cell mesh At any moment The predicted hazard level value, For grid cells At any moment The dust hazard level value, To predict the time step, For risk migration items carried by airflow, For grid cells volume, For grid cells Number of faces, The range of values ​​is , For the first The airflow velocity component in the normal direction of each surface For the first The upstream risk value of each aspect, when hour, when hour, , In order to be with the first Risk value of adjacent grid cells on each face. For the first The area of ​​each face. Let f be the flux direction correction function, when hour, ,when hour, For the migration term of particulate diffusion risk, , The turbulent diffusion coefficient is... The distance from the current grid center to the adjacent grid center. To address equipment risk sources, , The total number of risk sources, The range of values ​​is , For the first The intensity of each risk source For the risk source location indication function, when the first The risk source is located in the grid cell. The value is 1 if it is true, and 0 otherwise. For the source activity function, when at time... Time The value is 1 when the risk source device is running, and 0 otherwise.

[0028] Step S5: Based on the dynamic quantification matrix of dust hazard levels, construct a panoramic map of the entire dust situation monitoring through virtual-real mapping visualization technology, and generate targeted source tracing and control instructions; Furthermore, based on the dynamic quantification matrix of dust hazard levels, a panoramic map of the entire dust situation is constructed using virtual-real mapping visualization technology, and targeted source tracing and control instructions are generated, including the following sub-steps: Step S51: Align the physical processing area with the coordinates of the digital twin model, and render the data layer by layer according to the basic layer, feature layer, risk layer and source layer through virtual-real mapping visualization technology to form a panoramic map of the entire dust situation monitoring. Specifically, the dynamic quantification matrix of dust hazard level is mapped in real time onto the three-dimensional digital twin model of the decommissioned wind turbine blade processing area, establishing a physical coordinate-digital coordinate mapping relationship, and rendering in layers according to the basic layer, feature layer, risk layer, and source layer. The basic layer displays the equipment layout, the feature layer uses color to distinguish the different components and forms of dust and their proportions, the risk layer uses thermal icons to indicate the hazard level, and the source layer uses different icons to mark the blade source information, forming a panoramic map of the entire dust situation monitoring.

[0029] Step S52: Identify high-risk areas in the panoramic map of dust situation monitoring, automatically match the preset strategy library, and send targeted source tracing and control instructions to the underlying PLC control terminal; Specifically, based on the dynamic quantification matrix of dust hazard levels, high-risk judgment conditions are set. When the risk of a specific area exceeds the standard, risk information is output. The preset strategy library is automatically retrieved, and equipment control parameters and personnel warning information for a specific traceability batch on a specific production line are matched and generated to form a targeted traceability control command. The targeted traceability control command is sent to the underlying PLC control terminal through the industrial bus, and the risk changes after the command is executed are monitored.

[0030] Example 2 like Figure 2 As shown in Embodiment 2 of this application, a dust monitoring system for decommissioned wind turbine blades is provided, comprising: The spectral feature labeling module 21 marks tracer materials with differentiated standard fluorescence spectral features on retired wind turbine blades of different types and batches, establishes the mapping relationship between spectral features and their corresponding blade information, and forms a spectral identity database. Furthermore, the spectral feature labeling module 21 includes the following sub-modules: The multidimensional spectral coding submodule designs multidimensional spectral coding of tracer materials based on a combination of fluorescence spectral characteristics and concentration ratios, enabling the marking of tracer materials for different types and batches of decommissioned wind turbine blades. The spectral identity database submodule automatically binds the leaf information with the multidimensional spectral code of the tracer material it is labeled with through Internet of Things technology, establishes a spectrum-leaf mapping relationship, and forms the spectral identity database. The detection light field emission and acquisition module 22 emits a coaxial composite light detection light field to the processing area of ​​the decommissioned wind turbine blade to be monitored through a multi-frequency laser coordinated excitation source, and receives the multi-mode light response mixed signal returned by it. Furthermore, the detection light field emission acquisition module 22 includes the following sub-modules: The multi-frequency laser co-excitation source construction submodule is based on fluorescence excitation laser, component analysis laser and morphology detection laser, and constructs a multi-frequency laser co-excitation source through a high-precision timing control unit and beam combining unit; The optical response hybrid signal acquisition submodule emits a coaxial composite optical detection field to the processing area of ​​the decommissioned wind turbine blade to be monitored through a multi-frequency laser collaborative excitation source. The returned signal is synchronously acquired by a multi-modal sensor to form a multi-modal optical response hybrid signal data packet. The multimodal optical response mixed signal solution module 23, based on the spectral identity library and through the channel-based spectral decoupling mechanism, performs multi-spectral feature solution on the multimodal optical response mixed signal to obtain a three-dimensional feature set of composition-morphology-origin; Furthermore, the multimodal optical response mixed signal solving module 23 includes the following sub-modules: The dust information calculation submodule, based on the spectral identity library and through a channel-based spectral decoupling mechanism, decomposes the multimodal optical response mixed signal data packet into multiple pure spectra representing different signals and their corresponding concentration coefficients, and calculates the composition, morphology, and source information of the dust respectively. The three-dimensional feature set generation submodule encapsulates the composition, morphology, and source information of dust according to spatiotemporal coordinates to form a three-dimensional feature set of composition-morphology-source. The dust hazard level dynamic quantification matrix generation module 24 generates a dust hazard level dynamic quantification matrix based on a three-dimensional feature set of composition-morphology-source tracing through a cross-temporal and spatial data coupling weaving algorithm. Furthermore, the dust hazard level dynamic quantification matrix generation module 24 includes the following sub-modules: The dust hazard level dynamic quantification matrix generation submodule, based on the spatiotemporal coordinates of the three-dimensional feature set of composition-morphology-source tracing, adaptively assigns hazard indices to each feature through a cross-spatiotemporal data coupling weaving algorithm, and performs fusion calculation to generate a dust hazard level dynamic quantification matrix that changes over time. The matrix deduction and update submodule simulates the diffusion path and risk distribution changes of dust clouds based on the airflow field data of the processing area, and deduces and updates the dynamic quantification matrix of dust hazard level. The monitoring panoramic map and control command generation module 25, based on the dynamic quantification matrix of dust hazard level, constructs a panoramic map of the dust situation monitoring across the entire domain through virtual-real mapping visualization technology, and generates targeted source tracing control commands; Furthermore, the monitoring panoramic map and control command generation module 25 includes the following sub-modules: The panoramic map of the entire dust situation monitoring is formed by aligning the physical processing area with the coordinates of the digital twin model and rendering it in layers according to the basic layer, feature layer, risk layer and source layer through virtual-real mapping visualization technology to form a panoramic map of the entire dust situation monitoring. The targeted source tracing and control command sending submodule identifies high-risk areas in the panoramic map of the whole-domain dust situation monitoring, automatically matches the preset strategy library, and sends targeted source tracing and control commands to the underlying PLC control terminal. Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor is used to run one or more program instructions to execute a method for monitoring dust from decommissioned wind turbine blades.

[0031] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are used by a processor to provide a method for monitoring dust on decommissioned wind turbine blades.

[0032] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions, which, when executed on a computer, cause the computer to perform the aforementioned method for monitoring dust from decommissioned wind turbine blades.

[0033] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0034] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0035] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0036] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0037] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0038] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0039] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0040] 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 description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for monitoring dust from decommissioned wind turbine blades, characterized in that, include: Step S1: Mark tracer materials with differentiated standard fluorescence spectral characteristics on retired wind turbine blades of different types and batches, establish the mapping relationship between spectral characteristics and their corresponding blade information, and form a spectral identity database. Step S2: Using a multi-frequency laser coordinated excitation source, a coaxial composite optical detection field is emitted towards the treatment area of ​​the decommissioned wind turbine blade to be monitored, and the multi-mode optical response mixed signal returned from it is received. Step S3: Based on the spectral identity database, multi-channel spectral decoupling mechanism is used to perform multi-spectral feature calculation on the multimodal optical response mixed signal to obtain a three-dimensional feature set of composition-morphology-origin. Step S4: Based on the three-dimensional feature set of composition-morphology-source tracing, a dynamic quantification matrix of dust hazard level is generated through a cross-temporal and spatial data coupling weaving algorithm; Step S5: Based on the dynamic quantification matrix of dust hazard levels, construct a panoramic map of the entire dust situation monitoring through virtual-real mapping visualization technology, and generate targeted source tracing and control instructions.

2. The method for monitoring dust from decommissioned wind turbine blades as described in claim 1, characterized in that, Using a multi-frequency laser coordinated excitation source, a coaxial composite optical detection field is emitted towards the treatment area of ​​the decommissioned wind turbine blade to be monitored, and the returned multimodal optical response mixed signal is received, including the following sub-steps: Step S21: Based on fluorescence-excited laser, component analysis laser and morphology detection laser, a multi-frequency laser co-excitation source is constructed through a high-precision timing control unit and a beam combining unit; Step S22: Using a multi-frequency laser co-excitation source, a coaxial composite optical detection field is emitted towards the processing area of ​​the decommissioned wind turbine blade to be monitored. The returned signal is synchronously collected by a multi-modal sensor to form a multi-modal optical response mixed signal data packet.

3. The method for monitoring dust from decommissioned wind turbine blades as described in claim 1, characterized in that, Based on the spectral identity database, a channel-based spectral decoupling mechanism is used to perform multi-spectral feature calculation on multimodal optical response mixed signals to obtain a three-dimensional feature set of composition, morphology, and origin tracing. This includes the following sub-steps: Step S31: Based on the spectral identity database, the multimodal optical response mixed signal data packet is decomposed into multiple pure spectra representing different signals and their corresponding concentration coefficients through a channel-based spectral decoupling mechanism, and the composition, morphology, and source information of the dust are calculated respectively. Step S32: Encapsulate the composition, form, and source information of the dust according to spatiotemporal coordinates to form a three-dimensional feature set of composition-form-source.

4. The method for monitoring dust from decommissioned wind turbine blades as described in claim 1, characterized in that, Based on a three-dimensional feature set of composition, morphology, and source tracing, a dynamic quantification matrix of dust hazard level is generated through a cross-spatiotemporal data coupling weaving algorithm, including the following sub-steps: Step S41: Based on the spatiotemporal coordinates of the three-dimensional feature set of composition-morphology-source, the hazard index is adaptively assigned to each feature through a cross-spatiotemporal data coupling weaving algorithm, and a fusion calculation is performed to generate a dynamic quantification matrix of dust hazard level that changes over time. Step S42: Based on the airflow field data of the processing area, simulate the diffusion path and risk distribution changes of dust clouds, and deduce and update the dynamic quantification matrix of dust hazard level.

5. The method for monitoring dust from decommissioned wind turbine blades as described in claim 1, characterized in that, Based on a dynamic quantification matrix of dust hazard levels, a panoramic map of the entire dust situation is constructed using virtual-real mapping visualization technology, and targeted source tracing and control instructions are generated, including the following sub-steps: Step S51: Align the physical processing area with the coordinates of the digital twin model, and render the data layer by layer according to the basic layer, feature layer, risk layer and source layer through virtual-real mapping visualization technology to form a panoramic map of the entire dust situation monitoring. Step S52: Identify high-risk areas in the panoramic map of dust situation monitoring, automatically match the preset strategy library, and send targeted source tracing and control instructions to the underlying PLC control terminal.

6. A dust monitoring system for decommissioned wind turbine blades, characterized in that, include: The spectral feature labeling module marks tracer materials with differentiated standard fluorescence spectral characteristics on decommissioned wind turbine blades of different types and batches, establishes a mapping relationship between spectral features and their corresponding blade information, and forms a spectral identity database. The detection light field emission and acquisition module emits a coaxial composite light detection light field towards the treatment area of ​​the decommissioned wind turbine blade to be monitored through a multi-frequency laser coordinated excitation source, and receives the multi-modal light response mixed signal returned from it; The multimodal optical response mixed signal solution module, based on the spectral identity library and through a channel-based spectral decoupling mechanism, performs multi-spectral feature solution on the multimodal optical response mixed signal to obtain a three-dimensional feature set of composition, morphology, and origin. The dust hazard level dynamic quantification matrix generation module generates a dust hazard level dynamic quantification matrix based on a three-dimensional feature set of composition-morphology-source tracing through a cross-temporal and spatial data coupling weaving algorithm. The monitoring panoramic map and control command generation module, based on the dynamic quantification matrix of dust hazard level, constructs a panoramic map of the entire dust situation through virtual-real mapping visualization technology, and generates targeted source tracing control commands.

7. The dust monitoring system for decommissioned wind turbine blades as described in claim 6, characterized in that, The detection light field emission acquisition module specifically includes: The multi-frequency laser co-excitation source construction sub-module is based on fluorescence excitation laser, component analysis laser and morphology detection laser, and constructs a multi-frequency laser co-excitation source through a high-precision timing control unit and beam combining unit; The optical response hybrid signal acquisition submodule emits a coaxial composite optical detection field to the processing area of ​​the decommissioned wind turbine blade to be monitored through a multi-frequency laser collaborative excitation source. The returned signal is synchronously acquired by a multi-modal sensor to form a multi-modal optical response hybrid signal data packet.

8. The dust monitoring system for decommissioned wind turbine blades as described in claim 6, characterized in that, The multimodal optical response mixed signal processing module specifically includes: The dust information calculation submodule, based on the spectral identity library and through a channel-based spectral decoupling mechanism, decomposes the multimodal optical response mixed signal data packet into multiple pure spectra representing different signals and their corresponding concentration coefficients, and calculates the composition, morphology, and source information of dust respectively. The three-dimensional feature set generation submodule encapsulates the composition, morphology, and source information of dust according to spatiotemporal coordinates to form a three-dimensional feature set of composition-morphology-source.

9. A dust monitoring system for decommissioned wind turbine blades as described in claim 6, characterized in that, The dust hazard level dynamic quantification matrix generation module specifically includes: The dust hazard level dynamic quantification matrix generation submodule, based on the spatiotemporal coordinates of the three-dimensional feature set of composition-morphology-source tracing, adaptively assigns hazard indices to each feature through a cross-spatiotemporal data coupling weaving algorithm, and performs fusion calculation to generate a dust hazard level dynamic quantification matrix that changes over time. The matrix deduction and update submodule simulates the diffusion path and risk distribution changes of dust clouds based on the airflow field data of the processing area, and deduces and updates the dynamic quantification matrix of dust hazard level.

10. A dust monitoring system for decommissioned wind turbine blades as described in claim 6, characterized in that, The monitoring panoramic map and control command generation module specifically includes: The panoramic map of the entire dust situation monitoring is formed by aligning the physical processing area with the coordinates of the digital twin model and rendering it in layers according to the basic layer, feature layer, risk layer and source layer through virtual-real mapping visualization technology to form a panoramic map of the entire dust situation monitoring. The targeted source tracing and control command sending submodule identifies high-risk areas in the panoramic map of dust situation monitoring across the entire domain, automatically matches the preset strategy library, and sends targeted source tracing and control commands to the underlying PLC control terminal.

Images