1987results about "Thermometers using physical/chemical changes" patented technology

The invention relates to the technical field of industrial safety, and discloses an electrolytic aluminum short circuit port operation safety early warning system based on multi-parameter collaborative awareness and intelligent diagnosis, and the system comprises a parameter collaborative awareness module, a dynamic diagnosis module, an early warning decision module, and an execution feedback module. By constructing a multi-dimensional parameter collaborative sensing mechanism, fusing temperature field distribution, current balance degree and insulation state multi-source data in real time and dynamically capturing early abnormal symptoms of a short circuit port, the hysteresis problem of traditional single-parameter threshold monitoring is solved, conversion from passive response to active defense is achieved, and the comprehensiveness and timeliness of operation state monitoring are improved; and meanwhile, based on a historical fault database and a real-time evolution model, a health index is generated and a fault path is predicted, so that maintenance personnel can pre-judge a development trend and a time window of potential risks in advance, and sudden equipment accidents are avoided.

The invention relates to the technical field of power transformer state monitoring, and discloses a main transformer winding temperature rise on-line monitoring method and system, and the method comprises the steps: obtaining the calibration flight time of ultrasonic waves through an acoustic sensor array disposed on the outer wall of an oil tank in a quasi-isothermal state of a transformer; calculating a structure additional time delay which is caused by an internal fixed structure and does not change along with the temperature, and establishing an acoustic fingerprint for the transformer; during on-line monitoring, oil way net propagation time reflecting temperature change of the insulating oil is obtained from on-line flight time measured in real time; and then, based on the net propagation time of the oil way, an acoustic tomography algorithm is adopted to reconstruct internal two-dimensional or three-dimensional temperature field distribution, and the winding hot-spot temperature is finally and accurately calculated in combination with the real-time load current. According to the invention, through the acoustic fingerprint correction technology, the measurement interference of an internal fixed structure is eliminated, and non-intrusive, high-precision and visual online monitoring of the winding hot-spot temperature is realized.

The invention discloses a safety monitoring system of a high transverse support system for cable-stayed bridge man-shaped tower column construction, and relates to the technical field of bridge construction monitoring, the system comprises a creeping formwork integrated sensing module used for generating a point cloud model by using a mechanical arm integrated on a hydraulic creeping formwork platform and a laser radar scanning tower column curved surface, combining with a preset building information model coordinate, adaptively adjusting the mounting posture of the sensor, and outputting the mounting coordinate position of the sensor; the optical fiber sensing network module is used for collecting original strain and temperature data by using a distributed optical fiber sensor deployed along a main stress path of the support truss; an inertial navigation fusion positioning module; a digital twinning early warning module; and an edge calculation relay module. According to the invention, a full-process monitoring chain from data acquisition to risk early warning is constructed through cooperation of multiple modules, full-period and multi-dimensional dynamic control of construction of the human-shaped tower column high transverse support system is realized, and timely perception and overall control of potential risks are ensured.

The invention provides a rock-soil body multi-field coupling intelligent monitoring system comprising a multi-field sensing device configured to monitor parameters of a deformation field, a seepage field, a temperature field and a stress field of a rock-soil body; the edge calculation and transmission device is configured to perform preprocessing and real-time transmission on the multi-field sensing data; and the intelligent decision-making device is configured to analyze the preprocessed data based on a multi-field coupling model and generate disaster early warning information. According to the rock-soil body multi-field coupling monitoring system and method provided by the invention, synchronous monitoring of a deformation field, a seepage field, a temperature field and a stress field is realized through the multi-field sensing device; real-time data processing is performed in combination with an edge calculation and transmission device, and a dynamic early warning mechanism is established by using an intelligent decision-making device, so that the technical problems of multi-field data space-time correlation failure, insufficient multi-source data fusion precision and poor early warning mechanism adaptability are effectively solved, and the geological disaster early warning method has the remarkable advantages of improving the geological disaster early warning accuracy and timeliness.

The invention relates to the technical field of industrial temperature measurement, in particular to a high-temperature heating body hearth temperature distribution measurement method, which comprises the following steps of: establishing a quantitative mapping relation model between real-time input electric power and theoretical heating intensity of a heating body; a limited number of temperature sensor arrays are arranged at key positions of the internal space of the hearth; synchronously acquiring a real-time temperature measurement value of the temperature sensor array and real-time input electric power data of the heating body; calculating and generating theoretical temperature field distribution covering the three-dimensional geometric model; obtaining a corrected temperature value; calculating the temperature residual error of the corrected temperature value and the theoretical temperature field distributed at the corresponding position of the sensor; expanding the discrete temperature residual error into a full-space three-dimensional residual error distribution field; and outputting the three-dimensional real-time temperature distribution field of the hearth. Dynamic lag compensation and convective heat transfer compensation algorithms are adopted, lag and errors in measured values can be corrected in real time, and it is ensured that measured data at high temperature have high response speed and accuracy.

The invention relates to the field of on-line monitoring of electrical equipment, in particular to an on-line monitoring method of the electrical equipment, which comprises the following steps: acquiring multi-dimensional monitoring parameters of the electrical equipment, including an electrical parameter, a temperature parameter and an insulation parameter; performing feature extraction on the collected multi-dimensional monitoring parameters to obtain feature parameters corresponding to the monitoring parameters, and constructing a feature vector set; based on historical normal operation data and real-time acquisition data of the electrical equipment, establishing a dynamic threshold model, and calculating a threshold corresponding to the characteristic parameter through the dynamic threshold model; feature parameters in the feature vector set are compared with corresponding thresholds output by the dynamic threshold model, and whether the electrical equipment is abnormal or not is judged; when the abnormity exists, outputting an abnormity monitoring result; and if not, returning to S1. According to the invention, by collecting multi-dimensional parameters, calibrating, correcting, de-noising and extracting features, and combining historical and real-time data to build a model and verify, data preprocessing, threshold adaptation and anomaly judgment are realized, and the monitoring reliability is improved.

The invention provides a multi-sensor fusion welding temperature monitoring method and a related device, and the method comprises the steps: dividing a welding region into a plurality of sub-regions according to the spatial distribution of the welding region, and obtaining the initial temperature data corresponding to each sub-region according to various temperature sensors; performing time alignment on the initial temperature data through difference resampling of different sampling points to generate a time sequence temperature matrix; performing real-time quality detection on the time sequence temperature matrix to generate a real-time quality score, and performing weighted combination on the real-time quality score and a preset confidence coefficient parameter table to obtain a dynamic confidence coefficient result set; fusing the effective temperature data exceeding a preset confidence threshold in the dynamic confidence result set according to a fusion rule corresponding to each sub-region to obtain a fused temperature result; and the fusion temperature results of the sub-regions are subjected to time sequence splicing to obtain a global temperature curve of the welding process, so that the accuracy of temperature detection in the welding process can be effectively improved.

The invention relates to a power cable insulation state real-time monitoring and alarm device, and belongs to the technical field of power equipment state monitoring. Comprising a multi-source sensing unit which is installed at a cable body and a joint; the edge computing terminal is fixed in the cable well or the ring main unit; and the cloud early warning platform receives the processing data and outputs an alarm instruction. According to the invention, multi-parameter deep fusion is realized, four-dimensional monitoring of grounding current, temperature, partial discharge and humidity is initiated for the first time, and limitation of a single parameter is broken through; and an insulation health index IHI is proposed, and the insulation deterioration degree is quantitatively evaluated. According to the method, tan delta and IHI are calculated on site through an edge-cloud collaborative architecture edge terminal, so that the data transmission quantity is reduced; the cloud dynamic threshold value is adjusted, and the alarm accuracy is improved. According to the invention, intelligent early warning mechanism three-level alarm linkage protection equipment is arranged; and the self-calibration function ensures long-term reliability.

The utility model discloses an intelligent early warning cable, which comprises a power line insulation wire core arranged in a first belting layer, the power line insulation wire core comprises a conductor and an insulation layer coated outside the conductor, and a temperature measuring element is arranged in the conductor; an armor layer is arranged outside the first belting layer, and a vibration measuring element is arranged in the armor layer; and an isolating layer is arranged between the first belting layer and the armor layer. The temperature measuring element with the temperature measuring function is arranged on the outermost layer of the conductor, so that the temperature of the cable conductor can be monitored more accurately; the vibration measurement element with the vibration measurement function is arranged in the armor layer, and the isolation layer is arranged between the first belting layer and the armor layer, so that an electromagnetic field generated by the cable in the first belting layer under the conditions of high voltage and large current can be isolated, and the problem that the electromagnetic field interferes optical signal transmission in the vibration optical fiber is avoided; the vibration signal can be accurately detected, and the detection accuracy is prevented from being influenced by deviation.

The invention provides a parameter monitoring method and system in a composite material preparation process based on optical fiber sensing, computer equipment and a medium, and belongs to the field of composite material detection. Center wavelength signals in the resin diversion stage are continuously collected through optical fiber strain sensors in a distributed optical fiber grating sensing array, and the distributed optical fiber grating sensing array is embedded into the multiple layers of dry carbon fiber cloth in the fiber preform in advance; the flowing position and time of the resin in the fiber prefabricated body are determined according to the minimum value of the central wavelength signal offset in the resin flow guide stage, and the flowing front edge of the composite material is constructed according to the flowing positions and time of the resin corresponding to the optical fiber strain sensors in the fiber prefabricated body. According to the method, the change of the structure state of the composite material in the resin diversion process can be continuously monitored in a complex variable-temperature environment, and the accurate monitoring of the three-dimensional resin flowing front edge in the composite material liquid forming process is realized.

The invention relates to the technical field of remote sensing image intelligent processing, in particular to a multi-scale progressive surface temperature fusion downscaling method and device, and the method comprises the steps: preprocessing a surface temperature image in a multi-scale image library; constructing a multi-scale training data set containing the surface temperature and at least one auxiliary parameter; constructing a surface temperature downscaling network based on multi-parameter fusion, and constructing a domain transformation network based on heterogeneous high-frequency information guidance; training a surface temperature downscaling network and a domain transformation network based on a progressive dual-network joint training strategy; finely adjusting the downscaling model meeting a preset low-medium resolution condition; and performing low-medium-high progressive downscaling on the low-resolution surface temperature image to be processed to generate a multi-scale progressive surface temperature meeting a target high-resolution condition. The method fully considers the problem of descending scale difference of different resolutions, achieves the maintenance of the physical characteristics of the surface thermal field, and improves the processing efficiency of large-area remote sensing data.

A multifunctional thermal exposure indicator can provide immediate reversible indications of overtemperature as well as irreversible indications of excessive thermal loading. Additionally, the multifunctional thermal exposure indicator can provide semi-reversible indications of undertemperature thermal loading, such as exposure to temperatures below the freezing point of water.

The present disclosure relates to a system (100) for acoustically detecting a temperature change, the system (100) comprising: at least one conversion element (10) for converting a temperature change into a characteristic sound; an acoustic sensor (40) configured to be mechanically connected to the structure (50) at a distance from the at least one conversion element (10); and a processor (42, 62) coupled to the acoustic sensor (40), in which the at least one conversion element (10) comprises an actuation portion (20) having at least one material having thermal expansion properties such that a change in temperature causes a movement of the actuation portion (20) that causes the conversion element (10) to generate a characteristic sound and conduct the characteristic sound into the structure (50), the acoustic sensor (40) is configured to record a characteristic sound generated by the conversion element (10) as a structural sound propagating through the structure (50), and the processor (42, 62) is configured to detect a temperature change based on the characteristic sound recorded by the acoustic sensor (40).

A distributed composite geotechnical sensor disclosed by the present invention comprises a multi-core cable, an optical fiber sensing member, at least two composite sensing members and a plurality of connectors, the multi-core cable is used for transmitting charge signals, and the optical fiber sensing member and the multi-core cable are arranged in parallel and at an interval and are used for monitoring temperature and stress. The at least two composite sensing pieces are sequentially arranged at intervals along the length direction of the optical fiber sensing piece, are arranged in the same core with the optical fiber sensing piece and are used for monitoring dynamic stress waves or vibration, and the plurality of connecting bodies are respectively arranged at two ends of the composite sensing pieces and are connected with the multi-core cable, the optical fiber sensing piece and the composite sensing pieces. The electric connector is used for electrically connecting the multi-core cable with the composite sensing piece. According to the invention, the problems of relatively single monitoring index and incapability of positioning due to the fact that a traditional piezoelectric geotechnical cable can only monitor external disturbance information and cannot realize distributed monitoring can be effectively solved.

The invention discloses a signal reconstruction and noise suppression method and system for a distributed Raman temperature measurement sensing system, and the method comprises the steps: obtaining original anti-Stokes light and Stokes light time domain signals of the distributed Raman temperature measurement sensing system, and constructing a space-time signal matrix; performing preprocessing and data enhancement on the space-time signal matrix; constructing a dual-path feature fusion network for Raman signal reconstruction and noise suppression, and initializing the network; defining a loss function fusing temperature physical constraints, and training the dual-path feature fusion network; and inputting an original Raman signal to be processed into the trained network, outputting the reconstructed anti-Stokes and Stokes signals with the high signal-to-noise ratio, and carrying out temperature demodulation according to the anti-Stokes and Stokes signals with the high signal-to-noise ratio. While the spatial resolution is maintained or improved, the noise of the Raman temperature measurement system is effectively suppressed, especially the real signal of a temperature abrupt change point can be recovered, the temperature demodulation precision, stability and reliability are improved, and reliable data are provided for infrastructure safety monitoring.

The invention discloses a cable temperature detection method, which comprises the following steps: laying distributed optical fibers along a to-be-monitored cable, synchronously obtaining whole-line temperature, vibration sound wave signals and load current data, and carrying out dynamic compensation and correction on a temperature measurement value; on the basis of multi-source information fusion, abnormal points are accurately positioned, a cable multi-physical field digital twinborn model is constructed, a health index reflecting the insulation condition is calculated in real time, and quantitative evaluation of local and overall states is achieved; further simulating different load scenes to predict the time when the insulation performance is degraded to a failure threshold value, so as to output probability distribution of the remaining service life of the cable; according to the method, the whole-process intelligentization from accurate temperature measurement and abnormal positioning to state evaluation and life prediction is realized, and the perspectiveness and reliability of cable operation and maintenance are remarkably improved.

The invention, which relates to the technical field of power transmission, discloses a high-power intelligent temperature control cable comprising a conductor, a first insulating layer, a temperature control system, an early warning system and a protective sleeve. The conductor is made of a high-conductivity material, and the conductor is coated with a first insulating layer; the temperature control system comprises a liquid cooling pipe and a plurality of temperature sensors, and cooling liquid is suitable for flowing in the liquid cooling pipe; the early warning system comprises a temperature sensing optical fiber which is distributed along the axial direction of the conductor, and the temperature sensing optical fiber is connected with a fault early warning module; the protection sleeve wraps the conductor, the temperature control system and the temperature sensing optical fiber and comprises an electromagnetic shielding layer, a mechanical protection layer and a safety protection layer. The temperature sensor and the fault early warning module are used for connecting the control unit. The operating temperature of the cable is adjusted in real time through the temperature control system, and thermal fatigue of the conductor is effectively inhibited; high-strength electromagnetic shielding, mechanical tensile strength and bending resistance are provided through the protective sleeve; and the temperature and strain states of the cable are monitored in real time through the early warning system, so that the operation safety is improved.

The invention relates to the technical field of optical fiber performance analysis, in particular to a multi-core fiber grating multi-parameter decoupling method based on improved CNN-LSTM. According to the method, a multi-core fiber grating temperature, vibration and three-dimensional deformation detection system is built, center wavelength data under the action of different physical loads are collected, and the center wavelength data are matched with corresponding real physical quantities to build a supervised learning data set. After abnormal value elimination, filtering noise reduction and normalization processing are carried out on collected signals, stratified sampling and data enhancement are adopted to construct a training set and a test set. An improved CNN-LSTM model is established, multi-parameter nonlinear mapping and feature focusing are realized in combination with convolutional feature extraction, time sequence modeling and an attention mechanism, training is performed by taking RMSE as a loss function and an Adam optimizer, and an early stop mechanism is set to prevent overfitting. After training is completed, wavelength data to be measured are input into the model, and temperature, vibration and three-dimensional deformation results after decoupling can be output.

The invention provides a coal storage temperature detection method and device, electronic equipment and a storage medium. An ultrasonic generator is arranged on the upper portion of the ground of a coal yard and transmits an ultrasonic signal to a coal pile; an ultrasonic signal receiver is arranged at the lower part of a ceiling of a coal yard to receive an ultrasonic signal penetrating through a coal pile and obtain propagation time and energy attenuation information of the ultrasonic signal, and temperature distribution of each area in the coal pile can be calculated based on the propagation time and the energy attenuation information in combination with a preset corresponding relation between ultrasonic sound velocity and temperature; and when the temperature of any area of the coal pile exceeds the preset coal ignition point threshold value, an alarm signal is triggered and position information of the corresponding high-temperature area is output, so that the problems that in the prior art, due to the fact that heat cannot be dissipated in time after coal is stacked, temperature distribution conditions of the middle and lower layers of the coal seam are difficult to master and early warning cannot be performed in time are solved. The spontaneous combustion of the coal is easily caused.

The invention belongs to the technical field of temperature characterization, and discloses a semiconductor device temperature characterization method and system. The semiconductor device temperature characterization scheme provided by the invention comprises the following steps: bearing a semiconductor device and adjusting the position of the semiconductor device by using a device bearing and adjusting unit; respectively emitting detection laser and heating laser by using a detection laser emitting unit and a pumping laser emitting unit, and irradiating the detection laser and the heating laser to a test area of the semiconductor device; collecting and recording a temperature measurement signal reflected by the semiconductor device by using a temperature measurement unit; the device operation control unit is used for providing an electric signal for the semiconductor device and synchronously triggering the temperature measurement unit to record a temperature measurement signal so as to ensure the synchronization of online work and temperature measurement of the semiconductor device; and obtaining transient temperature characterization information of the semiconductor device based on the temperature measurement signal by using the main control unit. According to the invention, temperature characterization of nanosecond-level time and submicron-level spatial resolution of the semiconductor device can be realized.

The invention belongs to the technical field of communication, and provides a communication optical cable state real-time online monitoring method and system. Calculating the vibration displacement of the optical cable based on the original back scattering light signal, and calculating the real strain and temperature of the optical cable based on a Brillouin scattering signal and a Raman scattering signal obtained by separating the original back scattering light signal; carrying out filtering, denoising, normalization and time-space alignment processing on the vibration displacement of the optical cable, the real strain of the optical cable and the temperature, and binding the vibration displacement and the real strain with the obtained geographic coordinates; obtaining time domain, frequency domain and time-frequency domain features based on the preprocessed vibration displacement, real strain and temperature data to form a multi-dimensional feature vector, inputting the feature vector into a pre-trained event recognition model, and outputting an abnormal event classification result; and judging and triggering abnormal event early warning based on an output result of the event recognition model and a preset dynamic threshold.

The invention discloses a Raman distributed optical fiber temperature sensing signal denoising method and device, and relates to the technical field of optical fiber sensing, and the method comprises the steps: inputting a received original Raman signal into a trained wavelet guide dense residual network; carrying out channel feature enhancement and feature reuse enhancement based on wavelet decomposition on the original Raman signal in parallel by adopting an expansion convolutional dense network and a standard convolutional dense network, and correspondingly generating an expansion output feature and a standard output feature; after the expansion output features and the standard output features are spliced, the spliced features are input into a cascaded fusion convolution module and a channel attention module for feature processing, and original signal noise is determined; and subtracting the original signal noise from the original Raman signal to determine a de-noised Raman signal. Based on the scheme, the processing advantages of dense connection, residual learning and attention enhancement are fused under the guidance of the explicit frequency domain provided by wavelet decomposition, and the signal denoising reliability is improved.

The invention relates to the crossing field of mechanical engineering and intelligent manufacturing, and discloses a real-time monitoring, regulating and controlling method for the manufacturing process of an automobile lightweight component. According to the method, a distributed fiber bragg grating sensing array is embedded in a mold, and a three-dimensional strain field at the flowing front edge of resin is obtained in real time; a multi-scale pore generation kinetic model is combined to perform online inversion on an unwetted area and pore distribution; and the pressure gradient and the mold temperature field of the hot press are adaptively regulated and controlled, and the flow path is dynamically corrected. The system comprises a sensing embedding module, a strain demodulation module, a pore inversion module, a regulation and control instruction generation module and a multi-zone execution module. According to the method, closed-loop precise control over the porosity being lower than 0.5% is achieved, and the consistency and reliability of the mechanical property of the component are remarkably improved.

The invention belongs to the technical field of electrical equipment safety monitoring, and provides an intelligent wire and cable distributed optical fiber temperature measurement early warning method and system, and the method comprises the steps: laying a distributed optical fiber temperature sensor network along a cable, and synchronously demodulating the temperature and strain information based on a distributed optical fiber sensing principle; the temperature, the strain information and the load current are uploaded to a cloud platform through a wireless communication module; operating a time-space fusion diagnosis model driven by a cable physical mechanism on a cloud platform to distinguish and position an abnormal overheating section caused by a current Joule heating effect, insulation loss or contact resistance dramatic increase; and after the abnormity is confirmed, the cloud platform generates a control instruction for the abnormal overheating section to cut off power supply, and an intelligent self-healing process can be started. According to the invention, physical root identification, accurate positioning and safe self-healing of the cable overheating fault are realized, and the safety of cable operation is greatly improved.

A fibre-optic sensor for measuring a physical quantity, such as a pressure, force, acceleration or tilt, includes an optical fibre having a measurement section for measuring a strain in the fibre, and first and second structural members. The optical fibre is connected to a first fibre connection section of the first structural member and to a second fibre connection section of the second structural member. The first and second connection sections are arranged on opposite sides of the measurement section, such that at least the measurement section is suspended between the first and second fibre connection sections. At least one of the structural members is movable relative to the other in dependence of the physical quantity that is measured. The structural members are made from materials having different coefficients of thermal expansion such that a temperature induced strain in said optical fibre due to a temperature change is reduced.

The invention discloses a PINN and optical fiber sensing fusion-based line icing prediction method, and belongs to the technical field of overhead line icing monitoring, and the method comprises the steps: building a line state constraint between a reference working condition and a current working condition, and providing a physical constraint for PINN model training; measuring to obtain an overhead line vibration signal, performing selective weighting on a low frequency, extracting a main modal frequency, and constructing a low-frequency feature vector; using the temperature mean value as the temperature value of the overhead line, constructing a Brillouin spectrum data residual error, and inverting the temperature and strain; brillouin frequency shift features are extracted, and Brillouin frequency shift feature vectors are generated; inputting the low-frequency feature vector and the Brillouin frequency shift feature vector as conditions into a PINN model, and training the model; carrying out backtracking correction on prediction in a past time window by taking an on-site overhead line icing value as an anchor point; and predicting an icing thickness result of a future time domain output by the optimized PINN model. The overhead line icing thickness prediction precision can be improved, and the line operation and maintenance efficiency can be improved.

The invention provides an FPI optical fiber temperature sensor based on a PDMS filled capillary glass tube, which comprises a capillary glass tube, one end of the capillary glass tube is filled with cured polydimethylsiloxane, the other end of the capillary glass tube is inserted with a single-mode optical fiber, in the capillary glass tube, the end surface of the polydimethylsiloxane is a concave surface, and the end surface of the single-mode optical fiber is a convex surface. The end face of the single-mode optical fiber is a plane, the end face of the polydimethylsiloxane and the end face of the single-mode optical fiber form two reflecting faces of the Fabry-Perot cavity, light input is carried out in the single-mode optical fiber, and light output is carried out in the Fabry-Perot cavity. Displacement of the end face of the polydimethylsiloxane as a function of a temperature change causes an interference wavelength in the Fabry-Perot cavity to be adjusted to map the temperature change. The invention provides the PDMS-filled SCT-based micro-air cavity FPI optical fiber sensor which is simple in structure, easy to manufacture, low in cost, small in size and ultrahigh in precision, and is used for high-precision temperature detection.

The embodiment of the invention provides a high-precision temperature field real-time monitoring method and device based on multi-sensor fusion, and the method and device achieve the effective collection of data through the innovative design of a sensor deployment system and the arrangement of an optimization and calibration mechanism. And a fusion processing mechanism is constructed, and reliable temperature estimation is established in combination with filtering analysis and weight calculation. And reconstruction optimization is introduced, and monitoring comprehensiveness is ensured through an interpolation algorithm and a compensation function. According to the method, the defects of the traditional technology in the aspects of sensor deployment, data fusion, temperature field reconstruction and the like are effectively overcome, and technical guarantee is provided for temperature field monitoring.

The application discloses a kind of EFPI optical fiber sensor multi-sensor multiplexing temperature-pressure demodulation system and method, including ASE broadband laser, optical circulator, EFPI optical fiber sensor, 2-way wavelength division multiplexer, N-way wavelength division multiplexer, N-way wavelength division demultiplexer, photoelectric detector, FBG, 1*2 optical fiber coupler, optical spectrometer, data processing system;The input port input of the optical circulator is connected with ASE broadband laser, the output port cir2 is connected with two cascaded FBGs, the output port cir3 is connected with EFPI optical fiber sensor, the input port of 2-way wavelength division multiplexer is connected with the output port cir4 of optical circulator, and the output port is connected with N-way wavelength division multiplexer;N-way wavelength division multiplexer is accessed via the input port of 1*2 optical fiber coupler, and outputs two-way signals, one-way is connected with N-way wavelength division demultiplexer via N-way photoelectric detector and data processing system, and the other way is connected with optical spectrometer;N channels are connected by cascaded FBG, and the cascade of N EFPI optical fiber sensors is realized.

A thermal measurement system enables high-resolution sub-surface temperature monitoring during additive manufacturing processes through machine learning demodulation of chirped fiber Bragg grating (C-FBG) sensors. An optical sensing subsystem includes a C-FBG sensor that encodes spatial temperature information in wavelength for high-temperature operation. A neural network model transforms complex reflection spectra into spatial temperature profiles with micrometer-scale resolution, overcoming limitations of traditional demodulation methods. A calibration subsystem generates synchronized spectral and thermal imaging data for training the neural network using controlled thermal profiles. The system captures steep thermal gradients and rapid cooling rates during laser powder bed fusion operations. A fiber embedding technique maintains the sensor in a strain-free condition at controlled sub-surface depths. The integration of high-temperature C-FBG sensors with machine learning signal processing achieves significant improvement in spatial resolution compared to traditional fiber optic thermal measurement approaches.