13526results about How to "Reduce in quantity" patented technology

The invention provides a cooperative mechanical arm self-adaptive obstacle avoidance method in a dynamic scene, which comprises the following steps of: 1, setting an initial pose and a target pose according to a work task of a cooperative robot, and performing global path planning in an initial environment; 2, an operator completes an assembly task in an assembly area, and the collaborative robot operates according to a preset route and completes the assembly task in a matched mode; 3, the depth camera obtains a human body skeleton and skeleton node information, and a human body bounding box is generated; 4, whether the distance between the arm bounding box and the robot is smaller than the safety distance or not is judged, and if yes, collision early warning is triggered; 5, a new collision-free track is re-planned based on the self-adaptive obstacle avoidance strategy of the artificial potential field method, and the mechanical arm moves according to the new track to avoid the obstacle; and 6, after the obstacle leaves the safety early warning range, the mechanical arm returns to the global path and finally arrives at the target point.

The invention provides a PCBA surface defect detection method and system based on image recognition, and the method comprises the steps: collecting and constructing a multi-class PCBA overall defect image data set, and carrying out the preprocessing; constructing a pre-training neural network model, and classifying the preprocessed PCBA overall defect image data set; constructing a local target identification method based on a YOLOX network according to an overall defect classification result; and carrying out local defect detection on the PCBA surface based on a local target identification method. According to the method, the overall classification and local detection strategies are comprehensively applied to reduce the burden of the model, and the detection precision and speed are improved. And an attention mechanism is introduced to improve the performance and generalization ability of the model. Data enhancement, consistency processing, classification labeling and the like are carried out on an image data set, and the defect detection effect of the model is improved. And multiple optimization strategies such as structure improvement, loss function improvement and pruning lightweight are adopted for the network model, so that the image target detection performance is effectively improved.

The invention provides a ternary logic gate circuit, a calculation circuit, a chip and electronic equipment. The ternary logic gate circuit provided by the invention can realize addition and subtraction of 1 to an input logic value. Based on the ternary logic gate circuit, 27 univariate functions of ternary logic are utilized, the ternary logic gate circuit is applied to the ternary logic circuit, the purpose of simplifying the structure of the ternary logic circuit can be achieved, the number of transistors in the ternary logic circuit can be reduced, the power consumption of the ternary logic circuit can be reduced, and the reliability of the ternary logic circuit is improved. And the calculation efficiency of the ternary logic circuit is improved.

The invention relates to the technical field of water and fertilizer drip irrigation, in particular to a biogas slurry, water and fertilizer integrated drip irrigation machine. Comprising a filter cartridge which is coaxially arranged in the outer cylinder, a coarse filter screen, a fine filter screen, a first scraper blade and a second scraper blade are arranged in the filter cartridge, water permeable holes are annularly and uniformly formed in the outer side wall of a lower cavity, and a water outlet is formed in the outer side wall of the lower cavity. And a blow-off pipe communicated with the filter cartridge is arranged at the bottom of the outer barrel. By means of multi-layer fine filtering combination, biogas slurry is purified at an irrigation inlet, impurities are reduced, a drip irrigation head is prevented from being blocked, and the irrigation efficiency is improved; the rotary driving mechanism regularly drives the scraping plate to accurately scrape impurities, and automatic cleaning and discharging are achieved by means of the locking opening and closing device and the movable sealing plate; the flow guide cover optimizes biogas slurry dispersion, deals with unstable supply and reduces pipe inlet pressure.

The invention discloses a singular value-based pre-trained visual model parameter fine tuning method, which comprises the following steps of: for a pre-trained visual model, selecting levels which need to be subjected to parameter fine tuning from the visual model according to actual requirements, and respectively performing singular value decomposition on a weight matrix of each layer to be subjected to fine tuning; obtaining an optimal rank-r approximation matrix and a residual matrix used for reconstructing a weight matrix, forming a singular value vector by the first r singular values as a trainable parameter, freezing other model parameters, inputting an image sample in a training sample set into a visual model to update the trainable parameter, and obtaining an optimal rank-r approximation matrix and a residual matrix used for reconstructing the weight matrix; and reconstructing by adopting the updated trainable parameters to obtain a weight matrix. According to the method, singular value decomposition is adopted to initialize the low-rank matrix, learning of downstream tasks on new domain knowledge is enhanced while pre-training information is reserved, the number of trainable parameters is remarkably reduced, the knowledge and adaptability of the model are effectively reserved, and the fine adjustment effect of the model is improved.

The invention provides a fuel cell hydrogen supply system and a hydrogen supply method. The fuel cell hydrogen supply system comprises a liquid hydrogen storage tank, a first gas path connected between the liquid hydrogen storage tank and a fuel cell, a second gas path connected in parallel with the first gas path, and a control assembly, a gasification device is arranged on the first gas path, and a gas storage bottle is arranged on the second gas path; the control assembly comprises a controller and a plurality of control valves; the controller controls the plurality of control valves and can respectively control the connection or disconnection of the first gas path and the second gas path, so that the liquid hydrogen in the liquid hydrogen storage tank is conveyed to the fuel cell through the first gas path, and when the pressure of the gaseous hydrogen in the liquid hydrogen storage tank exceeds a first preset pressure threshold value, the gaseous hydrogen is stored in the gas storage bottle through the second gas path; and hydrogen can be supplied to the fuel cell through the second gas path. According to the fuel cell hydrogen supply system, gaseous hydrogen exceeding the first preset pressure threshold in the liquid hydrogen storage tank can be recycled, so that the release of the gaseous hydrogen to the outside is reduced, and the waste of resources is reduced.

The invention provides an urban inland inundation simulation method based on CPU-GPU heterogeneous parallel calculation, and aims to reduce the number of calculation grids by adopting a self-adaptive non-uniform grid, consider pipe network calculation and improve the calculation efficiency of low-fluctuation urban area flood simulation at the same time, and comprises the following steps: performing one-dimensional pipe network runoff CPU calculation, constructing a rainwater pipe network model, and constructing a rainwater pipe network model. Extracting an overflow process of an overflow node of the pipeline; dividing a non-uniform grid based on the original raster data and a gradient threshold; non-uniform grid parallel calculation is carried out; a CPU-GPU heterogeneous parallel one-dimensional and two-dimensional coupling model is constructed; and coupling water depth calculation. The method can flexibly adapt to topographic changes and reduce the number of computational grids, and solves the limitation that precision and efficiency are difficult to consider in waterlogging simulation of a uniform grid in a low-fluctuation area in combination with CPU-GPU heterogeneous parallel calculation.

The invention discloses a lightweight eye fundus blood vessel image segmentation model based on Mama. The model comprises the following steps: an encoder and a decoder comprise at least four layers of SlimPVM Blocks; gradually downsampling the input feature map through maximum pooling operation; the CCA Bottleneck module is used for calculating the self-attention of the cross-channel in the height dimension and the width dimension of the feature map; the encoder and the decoder carry out feature fusion through selective jump connection, and the selective jump connection carries out weighted selection on features through a channel attention mechanism; the decoder uses SlimPVM Block to refine the features after up-sampling, the model recovers lost spatial dimensions through convolution transpose operation, and coding features from selective jump connection are combined; and the decoder finally outputs a final segmentation mask generated through a 1 * 1 convolution layer, and the segmentation mask can accurately describe the boundary of the target area in the medical image. The method is specially used for retinal vessel segmentation tasks, model parameters are reduced, calculation overhead is reduced, and meanwhile segmentation performance is kept and even improved.

The invention discloses an imaging method and system based on cosmic ray muon transmission, which are applied to a control mechanism, and the control mechanism is electrically connected with at least one detection module. The imaging method based on cosmic ray muon transmission comprises the steps that the response state of at least one detection module is obtained, the detection module comprises a plurality of sensor units, and the sensor units are arranged in a string shape. And preprocessing the response state to obtain muon flux in unit area, unit time and unit solid angle. Based on the topographic data, the landform data and the muon flux, the density distribution in the muon ray irradiation range is reversely deduced through a preset algorithm. And performing visual imaging based on a density distribution result. According to the method, the working efficiency of muon geological imaging is improved, the system complexity is reduced, the adaptability in a narrow working environment is remarkably enhanced, and an efficient and convenient solution is provided for the fields of geological exploration, engineering detection and the like.

The invention discloses a multi-task blood vessel segmentation model construction method based on a hybrid encoder. The encoder is a Swin Transform path multi-layer encoder based on a Mamform module, and the Mamform multi-layer encoder carries out data processing in combination with a W-MSA and an improved Mamba module; the decoder is a multi-task decoder and consists of three independent decoding paths which are respectively used for blood vessel segmentation, contour edge segmentation and blood vessel connectivity segmentation, and each decoding path adopts Swin Transformblock as a construction block and is used for generating feature mapping with the same size as an input image; an attention mechanism is shared, learned features are shared among decoders, the number of model parameters can be reduced, and overfitting is prevented; in the training process, a total loss function is formed through a loss function of a vascular connectivity decoding path, a self-distillation loss function and the like, the total loss function is calculated, model parameters are updated by using a back propagation algorithm, the segmentation performance of the model is gradually optimized, and after training is completed, the model can carry out precision on a vascular image.

The invention discloses a wafer detection scattered light collection objective lens, and relates to the technical field of optical imaging. The scattered light collecting lens is applied to wafer defect detection, the scattered light collecting lens sequentially comprises a first lens group, a second lens group, a third lens group and a fourth lens group from an object plane to an image plane in the optical axis direction of the lens, twelve lenses and an aperture diaphragm, and the twelve lenses and the aperture diaphragm are coaxially arranged; the first lens group is a catadioptric lens group, has positive focal power, and is used for imaging an object plane to an intermediate image plane through two times of reflection. The numerical aperture of the acquisition objective lens provided by the invention is equal to 0.9, the field of view is equal to 2.6 mm, the acquisition objective lens has the characteristics of large field of view, large numerical aperture and small center shielding, the capability of detecting scattered light of defects can be greatly improved, chromatic aberration is corrected by adopting a refraction and reflection mode, and a wider laser bandwidth can be realized compared with a general refraction mode of combining CaF2 and fused quartz.

A buffering hardware hinge outside a cup comprises a hinge cup and a hinge arm, the hinge cup and the hinge arm are connected in a hinged mode through an upper connecting rod and a lower connecting rod, a guide groove penetrating through a body is formed in the bottom of the hinge cup, and a driving plate is installed at the outer bottom of the hinge cup in a covering mode; a sliding block is arranged on the top of the driving plate and installed in the guide groove in a sliding mode. The end, facing the hinge cup, of the upper connecting rod extends outwards to form a driving arm, and when the hinge is closed, the driving arm acts on the sliding block to push the sliding block to slide in the guide groove; a buffer is fixedly mounted at the outer bottom of the hinge arm, a piston rod or a cylinder body part of the buffer is connected with the driving plate, and the buffer has a damping effect on the movement of the driving plate, so that the damping effect when the hinge is closed is realized. The device has the beneficial effects that the buffer is installed outside the hinge arm, through the design of the guide groove and the driving plate, the external space is effectively utilized, and the problem that the internal space is limited is avoided.

The invention discloses an unmanned aerial vehicle full-coverage path planning method, system and device and a storage medium, and relates to the field of unmanned aerial vehicles. The method comprises the following steps: acquiring preset map information of a first target area, and determining a second target area for delivering materials according to the preset map information; determining a relay unmanned aerial vehicle set according to the data information, a preset starting point, a second target area, preset map information, a first communication distance of the first unmanned aerial vehicle and a second communication distance of the relay unmanned aerial vehicle, and determining a second initial path of the second unmanned aerial vehicle according to the first initial path; controlling the first unmanned aerial vehicle and the second unmanned aerial vehicle to fly according to a preset initial path, and adjusting the preset initial path according to the environmental data collected by the first unmanned aerial vehicle; and when the first unmanned aerial vehicle arrives at a preset terminal point, determining flight paths of other unmanned aerial vehicles according to the actual load weights and types of the other unmanned aerial vehicles in the transportation unmanned aerial vehicle group and the environment data. By implementing the technical scheme provided by the invention, the task execution efficiency of the unmanned aerial vehicle group is improved.

The invention belongs to the technical field of display driving, and particularly relates to a display panel, a display driving method and a display device.The display panel comprises N rows of scanning lines, M columns of data lines and 2N rows * 2M columns of pixel circuits; each pixel circuit comprises a pixel unit and a control unit, and when the nth row of scanning line outputs a first scanning signal, a data signal on the mth row of data line controls any one of the control units in the (2m-1) th row and the (2n-1) th row and the control units in the (2m) th row and the (2n-1) th row to be switched on or switched on alternately in a time-sharing manner; when the nth scanning line outputs a second scanning signal, the data signal on the mth data line controls any one of the (2m-1) th and 2nth control units and the 2m and 2nth control units to be switched on or switched on alternately in a time-sharing manner; according to the display panel, the number of the scanning lines and the number of the data lines are reduced by at least half under the display condition of the same resolution, the power consumption and the cost of the panel are reduced, and the refresh rate and the aperture opening rate are improved.

The invention discloses a folding wing structure of an unmanned aerial vehicle, which comprises a rotating shaft embedded in a vehicle body, wherein a lower wing elastic sheet and an upper wing elastic sheet are mounted in an inner cavity of the rotating shaft from bottom to top, a first locking block and a second locking block are respectively arranged at the free ends of the lower wing elastic sheet and the upper wing elastic sheet, the first locking block and the second locking block are respectively matched with a first notch and a second notch which are formed in the rotating shaft, the outer side of the rotating shaft is sequentially sleeved with a lower wing and an upper wing from bottom to top, the upper surface of the lower wing and the lower surface of the upper wing are each provided with a groove, the two grooves are oppositely formed to form a torsional spring groove, a torsional spring is arranged in the torsional spring groove, and the upper inner sides of the lower wingand the upper wing are provided with a first locking groove and a second locking groove correspondingly; and the outer side of the rotating shaft is further sleeved with a roller bearing, a baffle isinstalled at the top of the rotating shaft, and the roller bearing is located between the upper wing and the baffle. The processing cost of the unmanned aerial vehicle is reduced, the folding wing structure is insensitive to the structural size, and the folding wing structure can adapt to a more miniaturized barrel-shooting unmanned aerial vehicle.

The invention relates to the technical field of automobile air conditioners, in particular to a heat management integration module and an automobile air conditioning system. The heat management integration module comprises a compressor, a liquid cooling condenser and a plate type evaporator; the compressor comprises an air suction cover and an exhaust cover which are opposite to each other in the first direction, an air suction port is formed in the air suction cover, and an exhaust port is formed in the exhaust cover. The liquid cooling condenser comprises a condenser sheet bar body. The first end of the condenser plate sheet main body is in contact with an exhaust cover of the compressor, so that an air inlet of the condenser plate sheet main body is directly butted with an exhaust port of the exhaust cover; the plate-type evaporator comprises an evaporator plate sheet main body; the first end of the evaporator plate sheet body makes contact with an air suction cover of the compressor so that an air outlet of the evaporator plate sheet body can be directly in butt joint with an air suction opening of the air suction cover. According to the heat management integrated module, the problems that when an existing heat management integrated module is actually arranged, the design size of the integrated module is large, arrangement of a whole vehicle is not facilitated, installation is complex, and the leakage risk is large are solved.

The invention relates to the technical field of computers, in particular to a model fine-tuning training method based on dynamic low-rank tensor adaptation, a model application method and a related device. The model fine-tuning training method based on dynamic low-rank tensor adaptation in one embodiment comprises the following steps: acquiring a pre-training model; adding fine tuning parameters to model parameters of the pre-training model to obtain fine tuning parameter matrixes of different layers, combining the fine tuning parameter matrixes of multiple layers into a fine tuning parameter tensor and decomposing the fine tuning parameter tensor into a core tensor and two low-rank factor matrixes to obtain to-be-fine-tuned parameters; and performing fine tuning on the pre-training model through the sample data, freezing original parameters of the pre-training model in the fine tuning process, updating the core tensor and the two low-rank factor matrixes in sequence, and performing low-rank adjustment on the slice matrix of the updated core tensor to obtain updated fine tuning parameters. By adopting the scheme of the embodiment, the performance of the obtained model can be further improved while the parameter fine tuning cost is reduced.

The invention discloses a physiological signal fragment analysis method based on an adaptive bidirectional selection state space, and the method specifically comprises the following steps: 1, carrying out the preprocessing of an original ECG signal X in a data set, and dividing the preprocessed data set into a training set Itrain and a test set Itest; step 2, constructing a physiological signal fragment analysis model based on an adaptive bidirectional selection state space, wherein the model comprises a multi-scale feature extraction module, a context encoder module and a classification module; 3, training the model constructed in the step 2 by using the training set Itrain processed in the step 1; and step 4, sending the test set Itest processed in the step 1 into the model trained in the step 3, and finally outputting a classification detection result. By adopting the method provided by the invention, the accuracy of analyzing whether the sleep apnea event occurs in the physiological signal fragment can be improved.

The invention relates to the technical field of chemical process fault diagnosis, in particular to a chemical process fault diagnosis method based on multi-scale spatial-temporal feature fusion, which comprises the following steps: regularly acquiring fault data in a chemical production process, preprocessing the fault data and inputting the preprocessed fault data into an MTS-F model; the MTS-F network comprises a time sequence feature extraction module and a spatial feature extraction module which are parallel, and the time sequence feature extraction module comprises a long short-term memory network, a channel attention mechanism module, a one-dimensional convolution layer and a global maximum pooling layer which are connected in sequence; the spatial feature extraction module comprises a GS-CNN module, a maximum pooling layer, two groups of spatial separable convolution layers and maximum pooling layers, and a global maximum pooling layer which are connected in sequence; and after the outputs of the two parallel networks are spliced, a prediction result of fault classification is output through a discarding layer and a full connection layer. According to the method, the time sequence and space features are extracted simultaneously in a parallel mode, the fault diagnosis capability is improved, the model parameter quantity and the calculation quantity are reduced, and good generalization performance is achieved.

The invention relates to a cut-to-size saw, and belongs to the technical field of wood-working machinery. The cut-to-size saw comprises a cut-to-size saw body which is provided with a workbench, a material pressing mechanism used for pressing and positioning a plate on the workbench, and a saw cutting mechanism used for conducting saw cutting operation on the plate located on the workbench. The side leaning and labeling mechanism is located above the workbench, and the side leaning and labeling mechanism is used for carrying out side leaning and labeling operation on the plates located on the workbench; and the plate pushing mechanism is located on one side of the cut-to-size saw body, connected with the workbench and used for pushing the plates to the workbench. According to the scheme provided by the invention, the structure is novel, the automation degree is high, and the plate machining efficiency and the saw cutting precision can be improved.

The invention relates to the technical field of quality management, in particular to a real-time quality management method and system for a PVC pipe, and the method can be applied to quality management of the PVC pipe, especially real-time defect detection of a high-speed production line. The method comprises the following steps: firstly, acquiring a multi-modal data set of the PVC pipe in real time and preprocessing the multi-modal data set to obtain preprocessed data; secondly, constructing a deep learning model, extracting multi-scale features of the preprocessed data by using depth separable convolution and asymmetric convolution, and reducing parameters of the deep learning model; thirdly, fusing the extracted multi-scale features by using multi-modal fusion, and carrying out feature dimension reduction in combination with global mean pooling; then, training a deep learning model and evaluating the detection performance thereof; and finally, detecting and alarming the surface defects of the PVC pipe in real time. According to the method, the surface defects of the PVC pipe are detected based on the deep learning model, and the detection accuracy is ensured while the real-time performance of detection is improved.

The invention relates to a tunnel ponding early warning method and device, computer equipment and a storage medium. The method comprises the steps that at least two first flow detection units are arranged at an inlet and an outlet of a tunnel, at least one second flow detection unit is arranged at a water outlet of the tunnel, local water accumulation threshold values of a plurality of water accumulation sensitive areas are determined based on historical water accumulation data, and the local water accumulation threshold values are arranged according to the threshold values to obtain a threshold value distribution sequence; dividing the threshold distribution sequence into a first sequence and a second sequence based on a preset proportion, and determining a first global threshold by a local ponding threshold at the boundary of the first sequence and the second sequence; calculating the inlet and outlet flow difference according to the first flow data and the second flow data, and further determining the water accumulation amount; and adjusting a second global threshold value according to the ponding risk index, and starting a corresponding risk early warning strategy when the ponding amount exceeds the first global threshold value or the second global threshold value. Low-cost and high-precision tunnel ponding monitoring is realized based on simplified sensing data, and the safety of tunnel passage is improved.

The invention provides a rapid random model correction method for an active learning type ocean platform structure, and the method comprises the steps: firstly carrying out the selection of correction parameters through considering the sensitivity, then carrying out the design of a test scheme, and building an initial Kriging model; a new correction parameter training sample is found, the frequency corresponding to the new sample is calculated, a Kriging model is reconstructed by adopting a new training set, random model correction is performed based on the reconstructed Kriging model, an objective function is constructed by adopting actually measured frequency data and initial finite element model frequency data, and a correction parameter mean value and a standard deviation are taken as solving objectives. And solving by utilizing an optimization algorithm to obtain a mean value and a standard deviation of correction parameters of the finite element model to be corrected, and repeatedly iterating to realize random correction of the ocean platform structure. According to the method, rapid, efficient and accurate model correction under small samples and noise errors is realized, and higher correction accuracy can be obtained by adopting fewer training samples.

The invention belongs to the field of laser radars, and particularly relates to a detection method based on an OPA laser radar, according to the detection method based on the OPA laser radar, a detection range is scanned and detected to obtain point cloud data, the detection range comprises a contour scanning range and other scanning ranges, and the point cloud data comprises a first point cloud and a second point cloud; the first point cloud is a point cloud corresponding to a contour scanning range, the second point cloud is a point cloud corresponding to other scanning ranges, the contour scanning range is determined based on a target contour in a detection range, and the point cloud density of the first point cloud is greater than the point cloud density of the second point cloud; according to the scheme, the high-flexibility scanning characteristic of the OPA laser radar is fully utilized, fine scanning is carried out in the area where the target contour is located, it is guaranteed that more target description information can be obtained, meanwhile, the number of obtained point clouds is reduced, namely, the data size in the detection process is reduced, and the detection efficiency is improved. Therefore, the rapid operation of the subsequent processing process is facilitated.

The invention discloses an insulator pollution detection method and system based on multispectral fusion, and belongs to the technical field of spectral detection. The method comprises the following steps: firstly, reconstructing a three-dimensional geometric model of a target insulator through a binocular vision method, and calculating the surface area of the target insulator according to the three-dimensional geometric model; the abnormal area of the target insulator is extracted, the optimal detection line is determined according to the three-dimensional coordinate of the central point of the abnormal area, the optimal detection equipment is selected according to the optimal detection line, the workload of multidirectional observation is reduced, and the working efficiency is improved. Second high-frequency spectral images are obtained according to the optimal detection equipment, discharge light spots of the multiple second spectral images are fused to generate a light spot contour and a light spot pixel variance, and the relative discharge position and the actual discharge area are calculated according to the light spot contour; and predicting pollution data of the insulator according to the surface area, the light spot pixel variance, the relative discharge position and the actual discharge area.

The self-adaptive switching control method for the unmanned surface vehicle comprises the following steps: establishing a mathematical model of the unmanned surface vehicle, and determining a control target of the unmanned surface vehicle; designing a virtual control law and a first Lyapunov alternative function for controlling the unmanned surface vehicle based on a backstepping method; designing a second Lyapunov alternative function, establishing an adaptive neural network controller model and a robust controller model, and designing control input of the unmanned surface vehicle switching control system; designing updating laws of an adaptive neural network controller and a robust controller, and designing a third Lyapunov function to perform stability analysis on the system; and testing and simulating the unmanned surface vehicle system in a simulation environment by using the adjusted control strategy. According to the control method, on the premise of ensuring the stability of the system, the path tracking error of the unmanned surface vehicle is reduced, and the energy consumption of the controller is reduced.

The invention relates to a vehicle-mounted radar waveguide antenna structure, which is a waveguide processing piece formed by splicing an upper waveguide processing piece (51) and a lower waveguide processing piece (52) up and down, a first waveguide transmission cavity (1), a waveguide antenna cavity structure, an electromagnetic band gap structure (3) and an electromagnetic band gap avoiding area (4) are arranged in the upper waveguide machining part (51) and the lower waveguide machining part (52). Compared with a conventionally-designed terminal open-circuit waveguide antenna, the vehicle-mounted radar waveguide antenna structure has the advantages that splicing of two layers of waveguide pieces can be achieved, complex waveguide structures are horizontally laid through reasonable design, the distribution characteristics are simplified as much as possible while splicing of the two layers of waveguide pieces is achieved, the machining difficulty is greatly reduced, and the cost is reduced. The cost is reduced while the performance of the commercial vehicle-mounted radar is improved, and the influence of waveguide piece machining errors on the performance can be reduced while the wide impedance bandwidth is kept.

The invention belongs to the field of photoelectric detection, and discloses a germanium-silicon photoelectric detector array and a signal reading method thereof, and the germanium-silicon photoelectric detector array comprises a plurality of macro pixel units which are sequentially arranged side by side according to a set interval; each macro pixel unit comprises a plurality of pixel units and an output bus, the pixel units are sequentially arranged from top to bottom according to a set interval, the output end of each pixel unit is electrically connected with the output bus, and the voltage input end of each pixel unit is connected with a bias voltage output module. Providing a bias voltage for each pixel unit to enable each pixel unit to work in a bias state; inputting an optical signal to a detector of each pixel unit to generate a light current, and performing signal conversion and amplification on the light current to obtain an amplified voltage signal; and the voltage signal is output to the output bus after passing through the driver. According to the technical scheme, layout, wiring and hardware resources can be saved, and meanwhile the adverse effect caused by the power supply crosstalk problem is reduced.

The invention provides a live pig facility breeding hog house ammonia concentration detection system based on a neural network, and the system comprises a hog house environment parameter collection module and a hog house ammonia concentration detection module which are connected in sequence. Wherein the hog house environment parameter acquisition module is used for acquiring ammonia gas information, wind speed information, temperature information and humidity information in a hog house; and the pig house ammonia gas correction fusion sub-module is used for correcting the predicted ammonia gas concentration based on the predicted wind speed, the predicted humidity and the predicted temperature. The method analyzes the influence of pig house ammonia gas on pig health, considers the coupling effect of multiple environment parameters of the pig house, provides a temperature, humidity and wind speed correction fusion method of the pig house ammonia gas concentration, and aims to improve the detection precision of the pig house ammonia gas concentration of pig facility breeding.

The invention relates to the technical field of coal mine safety mining, and discloses a coal rock gas disaster protective layer drilling hierarchical regulation and control method which comprises the following steps: S1, geological survey; s2, drilling and pressure relief; s3, hydraulic fracturing is carried out; s4, gas extraction is carried out; s5, top plate deep hole blasting; s6, advanced cave building energy absorption flexible supporting is carried out; s7, grouting reinforcement is conducted; and S8, continuous regulation and control. According to the protection layer drilling grading regulation and control method for coal rock gas disasters, multiple functions are integrated into a single drilling hole, resource saving, cost reduction and efficiency improvement are achieved, mine environment interference is effectively reduced, meanwhile, the state of a coal rock gas system is continuously regulated and controlled, the timeliness and flexibility of disaster prevention and control are ensured, and the protection layer drilling grading regulation and control method is suitable for popularization and application. The method adapts to different geological conditions, enhances coal mine safety, embodies double benefits of green mining and economic optimization, and marks the leading-edge progress of a coal mine safety technology.