33results about How to "Unified operating standards" patented technology

A railway wagon bottom floor damage fault detection method belongs to the technical field of railway wagon safety detection. The invention aims to solve the problems of poor reliability and low efficiency due to the adoption of manual image inspection for safety detection of the bottom floor of the existing rail wagon. The method comprises: collecting and processing whole-wagon linear array imagesof the bottom of a running railway wagon under different conditions to obtain a sample data set; constructing a semantic segmentation neural network model based on an encoder and a decoder, performing training by adopting a sample data set, finding an optimal weight coefficient, and updating the semantic segmentation neural network model; and then collecting a current whole-train linear array image at the bottom of the running rail wagon, obtaining a current to-be-detected target area by adopting the updated semantic segmentation neural network model, carrying out pre-judgment, and carrying out fault detection on the current to-be-detected target area which is pre-judged to have a fault by adopting a single-stage ssd model. According to the invention, automatic identification of bottom floor damage is realized.

The invention discloses a railway wagon swing bolster spring jump-out fault image recognition method, relates to the technical field of freight train detection, and aims to solve the problem of low detection accuracy of a manual detection mode in the prior art. The method comprises the following steps: 1, obtaining a passing wagon image, and carrying out the coarse positioning to obtain a coarse positioning gray image set; 2, marking the coarse positioning grayscale image set to obtain a marked image set; 3, training a deep learning network model by using the marked image set and the originalimage; and 4, segmenting the swing bolster spring by using the trained deep learning network model, and judging whether a swing bolster spring jump-out fault occurs or not according to a segmentationresult. According to the invention, manual detection is replaced by an image automatic recognition mode, vehicle faults can be automatically identified and alarmed, the operation standard is unified,the influence of different experience, understanding and cognition degrees of detected vehicle personnel is avoided, and the detection efficiency and accuracy are improved.

The invention discloses a railway wagon small part bearing stop key nut looseness and loss fault detection method, and belongs to the technical field of freight train detection. The objective of the invention is to solve the problems of high cost, low efficiency and the like of a current detection mode depending on manual image viewing and the problem of low accuracy of detection by an existing image automatic processing technology. The method comprises the following steps: acquiring an image, extracting a bearing blocking key region image, constructing a sample data set, and training a deep learning network by using the sample data set to obtain a trained deep learning network; extracting a bearing blocking key area image for a real vehicle passing image, and obtaining a three-value segmentation image by using the trained deep learning network; carrying out fault detection by utilizing the three-value segmentation image, and if no nut exists in a bolt area, indicating that the stop key nut is lost; if partial area of the bolt is above the nut, indicating that the stop key nut is loosened; and if the situation is detected, carrying out fault alarming. The method is mainly used forbearing stop key nut looseness and loss fault detection.

A truck bearing damage detection method belongs to the technical field of freight train detection. The objective of the invention is to solve the problems of long consumed time and low efficiency of manual truck bearing damage detection and the problem of low accuracy of truck bearing damage detection based on images. The method comprises the following steps: acquiring an image and extracting an image corresponding to a truck bearing area as a truck bearing area image to be identified; inputting a to-be-identified truck bearing area image into the trained Mask-RCNN network for speculation, andobtaining a prediction result of each image, the prediction result comprising categories of a plurality of ROIs, frame coordinates, segmentation coordinates and confidence scores; and combining faultposition prior information and bearing auxiliary category information to further detect truck bearing damage according to the confidence coefficient score of the fault. The method is mainly used fortruck bearing damage detection.

The invention relates to the field of cable maintenance, in particular to a line repair device. The line repair device includes a repair shell; a line connector is arranged in the repair shell; the line connector includes a middle connecting piece and two lock nuts; the two lock nuts are connected to both ends of the middle connecting piece in a threaded manner; each lock nut is provided with a tapered elastic sleeve; the entrance of a wire insertion hole is a corresponding tapered expansion structure; the upper surface of the repair shell is provided with a glue injection hole, and the liquidrepair glue can be injected into the repair shell through the glue injection hole; and the repair glue and repair shell together form a line repair insulation layer after the repair glue solidifies.The beneficial effects of the line repair device are as follows: the wire connection at the cable connection location is firm and reliable, and has a large current flow area; and the repair shell andthe solidified repair glue together form the repair insulation layer at the cable connection location; therefore, the water and moisture resistance is good, the strength is high and not easy to break,the cable can run effectively for a long time after connecting, and the service life of the cable is prolonged.

The invention relates to a railway wagon fault image recognition method, in particular to an image recognition method for breaking faults of a wagon brake beam strut. The objective of the invention isto solve the problems of low fault detection accuracy and poor stability of a brake beam strut of an existing rail wagon. The method comprises the steps of 1, establishing a sample data set; 2, finding an optimal weight coefficient based on the sample data set to obtain a trained SSD deep learning network; initializing a weight coefficient in a random mode; performing feature extraction on the sample data set; generating a default box; pretreating marks; adopting an SSD target loss function; performing weight optimization through an optimizer Adam; and calculating a new weight coefficient through a loss function and the optimizer, and repeatedly executing to obtain a trained SSD deep learning network; inputting a real vehicle passing image into the trained SSD deep learning network, and judging the breaking faults of the brake beam strut. The method is applied to the field of fault image recognition.

The invention relates to a method for preparing pure sweet potato starch noodle, comprising the following steps: preparing the raw material; refining, depositing; extracting the starch; de-watering; stirring; boiling; cooling; shaping; and drying. The method for preparing the pure sweet potato noodle provided by the invention has simple preparation method, can be mechanically operated, and reduces the labor. The noodle has yellow and crystal clear appearance, smooth taste, and toughness while being bitten. The noodle has high nutrition value, and the noodle is not rotten after being boiled and not broken while being evaporated, so it is welcomed by the people.

The invention provides a drawing method for an MEP topographic map of a pharyngeal motor cortex area, and further relates to a method for an MEP location map of the pharyngeal motor cortex area. According to the method, an electrode in the pharyngeal cavity is utilized to be inserted into the pharynx of the human body through the nasal cavity and the oral cavity to achieve the effect of accuratelyrecording electromyographic signals of the deep muscle of the pharynx, a positioning cap provided with multiple lattices of smaller sizes is utilized to cover the corresponding brain area to finallyachieve the effect of accurately drawing the MEP topographic map of the pharyngeal motor cortex area, and the drawing method is utilized to measure and draw multiple subjects to finally obtain the MEPlocation map of the pharyngeal motor cortex area of healthy people.

The invention provides a locomotive running part equipment detection system and belongs to the detection of locomotive running parts. The locomotive running part equipment detection system is to solvethe problem that false checking and missed checking are easily caused because the checking of an existing locomotive running part depends on manual operation. The locomotive running part equipment detection system comprises trackside equipment and engine room equipment; the trackside equipment comprises a wheel sensor and an image collection device; the engine room equipment comprises a locomotive information collection unit, an image collection control unit, a storage unit and a fault recognition unit; the wheel sensor collects a wheel signal and transmits the wheel signal to the locomotiveinformation collection unit when a locomotive passes; the locomotive information collection unit calculates a locomotive speed and a wheel base; the image collection control unit controls a starting time of the image collection device and a shooting frequency of the image collection device according to the locomotive speed and correspondingly shoots images of a speed sensor, a machine sensing coiland an electronic label; the storage unit stores the images shot by the image collection device; and the fault recognition unit recognizes faults of the images stored in the storage unit. The locomotive running part equipment detection system is used for checking railway locomotives.

The invention discloses a wagon sleeper beam hole carrying foreign matter detection method, and belongs to the technical field of image detection. According to the invention, the problems of low detection accuracy and low detection efficiency when whether foreign matters are carried in the sleeper beam hole area or not is judged by adopting a manual detection mode are solved. According to the invention, imaging equipment is carried around a truck track by using fixed equipment, and whole-truck linear array image data of a to-be-detected running truck is acquired. A rectangular area containingthe sleeper beam hole and a small part of the bogie below the sleeper beam hole is obtained from the whole vehicle image; a sleeper beam hole in the image is approximately horizontally centered; by performing overturning and linear combination on images, accurate positioning of semi-elliptical sleeper beam holes and subsequent recognition of the relationship between foreign matters and shadows thereof in image shooting, alarm output is performed on pictures carrying the foreign matters, station workers are assisted in quickly detecting train components, and the train operation safety is ensured. The method can be applied to the technical field of image detection.

A railway wagon sleeper beam hole foreign matter detection method belongs to the technical field of railway wagon detection. The invention aims to solve the problems of poor stability and low precision of a manual detection method and the problem of high false alarm rate of an existing deep learning method. The method comprises: acquiring a sleeper beam hole position image as an image D; predicting the image D by using the trained segmentation model network; if no foreign matter exists in the image, processing the next image; otherwise, carrying out corrosion expansion operation, and marking the foreign matter prediction binary image as B; positioning the sleeper beam hole part according to the image D to obtain a positioned binary image, namely an image A; multiplying the pixel value points of the foreign matter prediction binary image B and the positioning binary image A, and adding to obtain a value c; and carrying out judgment, if c is not larger than the foreign matter judgment threshold m, proving that no foreign matter exists in the sleeper beam hole area, and otherwise proving that no foreign matter exists in the sleeper beam hole area. The method is mainly used for foreignmatter detection of railway wagon sleeper beam holes.

The invention discloses a multi-degree-of-freedom adjustment and detection device for a liquid crystal module. The device comprises a module bearing assembly, a pressure head assembly and a pressure connection assembly; the module bearing assembly comprises a bottom plate, a base plate, a rotation base and a module supporting frame; the pressure head assembly comprises a base and a pressure head which is located on the base and can move upward relative to the base in the X-axis direction; the pressure connection assembly comprises a supporting base which is oppositely fixed to the bottom plateand a pressure connection part which is located on the supporting base; the base is slidingly matched with the supporting base, and the pressure head assembly can move upward relative to the supporting base in the Z-axis direction; the pressure connection part comprises a part which is located in the Z-axis direction and used for downward pressing the pressure head assembly. According to the multi-degree-of-freedom adjustment and detection device for the liquid crystal module, angle adjustment functions in the X-axis direction, the Y-axis direction and the Z-axis direction and in a horizontalplane can be provided for detection of the liquid crystal module to be detected, adjustments in all dimensions are conducted independently and do not influence one another, and the basis is providedfor precise and flexible adjustment and detection of the liquid crystal module.

A deep learning-based image recognition method and system for bearing saddle dislocation faults of railway freight cars belongs to the technical field of freight train detection. The present invention aims to solve the problems of low efficiency in the current detection method relying on manual viewing of images, and the problem of low detection accuracy in the existing automatic image processing technology. The invention uses a U-shaped deep learning network to predict the image to be detected, predicts the bearing saddle contour area, and obtains the predicted binary image; determines the upper edge line of the bearing saddle outline area according to the binary image, and passes the angle of the upper edge straight line Change to judge whether it is a fault: if the upper edge linear angle deviation is greater than the preset threshold, a fault alarm will be issued for this part of the bearing saddle; if the upper edge linear angle deviation is less than or equal to the set threshold, the next step will be processed. Zhang bears saddle images. The invention is mainly used for bearing saddle dislocation fault image recognition.

The method for quickly detecting foreign objects in triangular holes of railway wagons relates to the technical field of fault diagnosis of railway vehicles. In the prior art, manual inspection is used to judge whether foreign objects are carried in the triangular hole area, which is prone to missed detection and wrong detection, and it is difficult to guarantee the accuracy of detection. For the problem of accuracy and high efficiency, use automatic image recognition instead of manual inspection, the operation standard is unified, no longer affected by personnel quality and responsibility, effectively improve the quality of operation, improve the stability and accuracy of detection, and improve the health of staff , improve the detection efficiency, the results predicted by the image recognition algorithm cannot be completely guaranteed to be located in the triangular hole, and there is a chance of false positives. At this time, according to the location characteristics of the triangular hole, template matching based on the shadow can effectively find the location of the triangular hole. The template used in this paper is a circular template, which can effectively assist in the positioning of the foreign matter located in the shadow and the position of its shadow.

The invention relates to a fault image recognition method for a broken railway freight car brake beam pillar, and the invention relates to a fault image recognition method for a railway freight car. The purpose of the invention is to solve the problems of low detection accuracy and poor stability of the existing railway freight car brake beam pillar fault detection. The process is: 1. Establish a sample data set; 2. Find the optimal weight coefficient based on the sample data set to obtain a trained SSD deep learning network; the process is: initialize the weight coefficient in a random manner; perform feature extraction on the sample data set ;default frame generation; mark preprocessing; SSD target loss function; optimize the weight through the optimizer Adam; after the loss function and the optimizer, calculate the new weight coefficient, repeat the execution, and get the trained SSD deep learning network. 3. Input the real passing car image into the trained SSD deep learning network to identify the breakage of the brake beam pillar. The invention is used in the field of fault image recognition.

The invention relates to a method for detecting foreign matter carried in a corbel hole of a railway freight car, which belongs to the technical field of image detection. The invention solves the problems of low detection accuracy and detection efficiency when the manual inspection method is used to judge whether foreign matter is carried in the corbel hole area. The invention uses fixed equipment to carry imaging equipment around the track of the truck to collect the linear array image data of the whole truck to be detected. Obtain a rectangular region containing the corbel hole and a small portion of the bogie below it from the full vehicle image. The corbel hole in the image is roughly horizontally centered. Through flipping and linear combination of the image, precise positioning of the semi-elliptical corbel hole, and follow-up identification of the relationship between the foreign object and its shadow in the image shooting, the final identification of the foreign object is confirmed. The pictures are used for alarm output to assist the station staff to quickly detect train components to ensure the safety of train operation. The invention can be applied to the technical field of image detection.

The invention relates to a method for detecting foreign matter in a railway train axle box rotating arm, in particular to a method for detecting foreign matter in an axle box rotating arm. The purpose of the present invention is to solve the problems of low accuracy and efficiency of fault detection in the existing manual fault detection method. Step 1, collect the line array image data of the whole train; Step 2, perform rough positioning on the line array image data of the whole train collected in step 1, and obtain the position image of the axle box arm; Step 3, use the acquired axle box arm Position image, establish a sample data set; step 4, select the detection network model; step 5, use the sample data set established in step 3 to train the detection network model, and obtain a trained detection network; step 6, use the trained detection network The network is used to judge the foreign object fault of the axlebox arm. The invention belongs to the field of fault image recognition.

The invention discloses a method for detecting foreign matter in a corbel hole of a railway freight car, belonging to the technical field of railway freight car detection. The purpose of the present invention is to solve the problems of poor stability and low precision in the manual detection method, as well as the high false alarm rate in the existing deep learning method. The present invention first acquires the image of the corbel hole position, which is recorded as image D; then uses the trained segmentation model network to predict image D; if there is no foreign matter in the image, the next image is processed; otherwise, the erosion and expansion operation is performed, Mark the foreign object prediction binary image as B; locate the corbel hole for image D, and obtain the positioned binary image, that is, image A; finally, combine the foreign object prediction binary image B with the pixels of the positioning binary image A Value points are multiplied and added to obtain the value c; judge, if c is not greater than the foreign object judgment threshold m, it proves that there is no foreign object in the corbel hole area, otherwise it proves that there is a foreign object in the corbel hole area. It is mainly used for foreign object detection in corbel holes of railway wagons.

The embodiment of the invention provides a batch job starting and stopping method and device, computer equipment and a storage medium, which can be applied to the technical field of big data or other fields. The method comprises the following steps: receiving an Entegor batch starting request of an automatic production system; judging whether the batch job corresponding to the request is repeatedly started according to the batch name in the request; if the batch jobs are not started repeatedly, reading the executing conditions of the batch jobs, and determining whether the batch jobs meet the executing conditions or not; and if the batch jobs meet the executing conditions, triggering an Entegor server to start the batch jobs; and when the batch job stops working, reading a stop condition of the batch job, judging whether the batch job meets the stop condition or not, and if so, stopping the batch job and informing the Entegor server. According to the scheme, the operation efficiency is improved, and the data error rate is reduced.

The invention discloses a damage detection method for freight car bearings, which belongs to the technical field of freight train detection. The invention aims to solve the problems of long time consumption and low efficiency in manual-based truck bearing damage detection and low accuracy in image-based truck bearing damage detection. The present invention collects images and extracts images corresponding to the truck bearing area as the image of the truck bearing area to be identified; inputs the image of the truck bearing area to be identified into the trained Mask-RCNN network for speculation, and obtains the prediction of each picture The results include: multiple ROI categories, frame coordinates, segmentation coordinates, and confidence scores; combined with the prior information of the fault location and the bearing auxiliary category information, the confidence score of the fault is further realized to detect the damage of the truck bearing. It is mainly used for damage detection of truck bearings.

The invention relates to a railway train axle box tumbler foreign matter detection method, in particular to an axle box tumbler foreign matter detection method. The objective of the invention is to solve the problems of low accuracy and low efficiency of fault detection in an existing manual fault detection method. The method comprises the steps of 1, collecting whole train linear array image data of a train; 2, performing coarse positioning on the whole vehicle linear array image data acquired in the step 1 to obtain an axle box tumbler position image; 3, establishing a sample data set by utilizing the obtained axle box tumbler position image; 4, selecting a detection network model; 5, training a detection network model by using the sample data set established in the step 3 to obtain a trained detection network; and 6, performing axle box tumbler foreign matter fault judgment by utilizing the trained detection network. The invention belongs to the field of fault image recognition.

The invention discloses a railway wagon triangular hole foreign matter rapid detection method, relates to the technical field of railway vehicle fault diagnosis, and aims at solving the problems thatin the prior art, when whether foreign matter is carried in a triangular hole area or not is judged through manual inspection, missing detection and wrong detection are likely to happen, and the detection accuracy and efficiency are difficult to guarantee. Manual detection is replaced with an automatic image recognition mode, the operation standard is unified and is not affected by personnel quality and responsibility any more, the operation quality is effectively improved, the detection stability and accuracy are improved, the health of workers is improved, and the detection efficiency is improved. A result predicted by an image recognition algorithm cannot completely guarantee that the result is certainly located at a triangular hole part and has a false alarm probability, and at the moment, according to the position characteristics of the triangular hole part, template matching is carried out according to shadows, so that the hole position of the triangular hole can be effectively found, the adopted template is an annular template, and positioning of foreign matters at the shadow and the position of the shadow can be effectively assisted.

The invention relates to a method for preparing pure sweet potato starch noodle, comprising the following steps: preparing the raw material; refining, depositing; extracting the starch; de-watering; stirring; boiling; cooling; shaping; and drying. The method for preparing the pure sweet potato noodle provided by the invention has simple preparation method, can be mechanically operated, and reduces the labor. The noodle has yellow and crystal clear appearance, smooth taste, and toughness while being bitten. The noodle has high nutrition value, and the noodle is not rotten after being boiled and not broken while being evaporated, so it is welcomed by the people.

The invention discloses an installing device for an assembly type street passage. The installing device comprises a longitudinal butt-joint guide device and a transverse butt-joint guide device. The longitudinal butt-joint guide device comprises a support frame I, and the bottom of the support frame I is provided with a universal wheel I. The two sides of the top end of the support frame I are provided with a high-position guide block and a low-position guide block correspondingly. The bottom ends of the high-position guide block and the low-position guide block are connected with a distance adjusting screws I through rotary shafts. The top ends of the high-position guide block and the low-position guide block are each provided with a limiting shaft. The two sides of the top end of the support frame I are each provided with a connecting rod. The bottom ends of the connecting rods are rotationally connected with the support frame I. The top ends of the connecting rods are connected withthe limiting shafts in a limiting clamping mode. The transverse butt-joint guide device comprises a support frame II, and the bottom of the support frame II is provided with a universal wheel II. Atleast one end of the support frame II is provided a transverse guide plate. The longitudinal butt-joint guide device is used for corresponding up-down splicing of top frames and bottom frames. The transverse butt-joint guide device is used for corresponding horizontal splicing between the bottom frames. Operation standard are unified, and work efficiency is improved greatly.

The invention provides a manufacturing method of vermicelli, and belongs to the field of vermicelli manufacturing. The method comprises the following concrete steps: (1) material preparation: selecting sweet potatoes, corn, and rhizomes of fourleaf paris; (2) material treatment: putting cleaned sweet potatoes, corn, and rhizomes of fourleaf paris into a pulverizer, and conducting crushing; (3) material steaming: ladling a stirred stiff mixture into a food steamer, after steaming, putting vermicelli cakes into cold water for soaking and cooling, and after soaking and cooling, conducting refrigeration; (4) material drying and cutting: putting obtained vermicelli cakes into a drying oven, conducting drying, and conducing cutting with a machine; and (5) vermicelli shaping: subjecting dried sheet jelly strips to filament planing with a filament planing machine. The method adopts mechanization in a manufacturing process with uniform operating standards so as to prepare the vermicelli uniform in appearance and mouth feel. The method reduces manpower and raises production and processing efficiency. The obtained vermicelli is rich in nutrients, contains no chemical substances, and is a safe and green food. Moreover, the dying step can guarantee that the vermicelli is fixed in shape and convenient for storage.