CN110597165A - Steel piling monitoring system and steel piling monitoring method - Google Patents
Steel piling monitoring system and steel piling monitoring method Download PDFInfo
- Publication number
- CN110597165A CN110597165A CN201910816923.7A CN201910816923A CN110597165A CN 110597165 A CN110597165 A CN 110597165A CN 201910816923 A CN201910816923 A CN 201910816923A CN 110597165 A CN110597165 A CN 110597165A
- Authority
- CN
- China
- Prior art keywords
- steel
- monitoring
- image
- subnet
- piling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
- G05B19/054—Input/output
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the invention provides a steel pile monitoring system, which relates to the field of steel pile monitoring and comprises a monitoring subnet, a control subnet and a central controller; the central controller is respectively connected with the monitoring subnet and the control subnet; the monitoring subnet is used for acquiring a red steel image and extracting characteristic parameters based on the red steel image, and the central controller generates a control command according to the characteristic parameters sent by the monitoring subnet and sends the control command to the control subnet; the monitoring subnet comprises a plurality of visible light monitoring nodes and a plurality of infrared monitoring nodes; the control sub-network is connected with external equipment in a steel rolling area and used for controlling the external equipment to process a steel piling accident site. Compared with manual monitoring, the steel piling monitoring method provided by the invention can be used for monitoring whether steel piling accidents occur or not for a long time under the unattended condition, so that the labor burden is greatly reduced, and the influence of human factors is avoided.
Description
Technical Field
The invention relates to the field of steel pile monitoring, in particular to a steel pile monitoring system and a steel pile detection method.
Background
Currently, the monitoring of the existing steel pile mainly depends on manual monitoring. When steel piling occurs, a field worker presses the emergency stop switch to stop the steel rolling production line. Or when the steel pile is generated, the steel pile collides with an external object to generate a signal to give an alarm, or a non-contact loop monitor is adopted to monitor the steel rolling process, and then the monitoring result is transmitted to a PLC controller, and then the PLC carries out corresponding accident handling.
Manual monitoring, however, often fails to respond in a timely manner due to inattention or fatigue of personnel in the field. The sensor is required to be installed close to a steel rolling area by adopting the existing automatic monitoring scheme, and the sensor is easily damaged due to the physical collision of red steel due to the high temperature of steel rolling, so that the monitoring system per se needs to be maintained regularly, and the maintenance cost is increased. In addition, the existing monitoring scheme needs to be accessed into a PLC controller, a PLC program needs to be changed, and long debugging and transformation time is needed for installing a monitoring system on a common steel rolling production line, so that production is influenced.
Disclosure of Invention
In order to solve the above-mentioned problems in the background art, an embodiment of the present invention provides a steel pile monitoring system and a steel pile monitoring method.
The invention provides a steel piling monitoring system, which comprises a monitoring subnet, a control subnet and a central controller, wherein the monitoring subnet is connected with the central controller;
the central controller is respectively connected with the monitoring sub-network and the control sub-network; the monitoring subnet is used for collecting red steel images and extracting characteristic parameters based on the red steel images, and the central controller generates control commands according to the characteristic parameters sent by the monitoring subnet and sends the control commands to the control subnet; the monitoring subnet comprises a plurality of visible light monitoring nodes and a plurality of infrared monitoring nodes; and the control subnet is connected with external equipment, and the external equipment is controlled to be used for processing the steel piling accident site.
Furthermore, the monitoring subnet and the central controller are in communication connection through a transmission protocol which is TCP/IP.
Further, the control sub-network and the central controller are in communication connection through an Ethercat industrial Ethernet transmission protocol.
Furthermore, the central controller is an upper computer, and each visible light monitoring node is provided with a first lower computer and a high-speed industrial camera.
Furthermore, the central controller is an upper computer, and each infrared monitoring node is provided with a second lower computer and a far infrared imager.
Further, the first lower computer and the second lower computer are industrial personal computers.
Further, the field device includes a warning light and a flying shear.
The embodiment of the invention also provides a steel pile monitoring method, which uses the steel pile monitoring system to monitor steel pile, and comprises the following steps:
acquiring the red steel image; wherein the red steel image comprises a visible light image collected by the high-speed industrial camera and an infrared light image collected by the far infrared imager;
carrying out image processing on the red steel image to obtain an image to be detected; the image processing comprises the steps of carrying out region-of-interest division and image segmentation processing on the red steel image;
carrying out steel piling phenomenon identification based on the image to be detected so as to determine a steel rolling area corresponding to the steel piling accident of the image to be detected;
and controlling the external equipment to carry out steel piling accident site treatment based on the steel piling phenomenon.
Further, the step of identifying the steel piling phenomenon based on the image to be detected to determine the steel rolling area corresponding to the steel piling accident of the image to be detected comprises the following steps:
performing region boundary crossing detection on the image to be detected to obtain a first stacked steel phenomenon identification result;
detecting the arrival time of the image to be detected to obtain a second steel piling phenomenon identification result;
and determining a steel rolling area corresponding to the steel piling accident of the image to be detected based on the first steel piling phenomenon identification result and the second steel piling phenomenon identification result.
Further, still include:
obtaining the red steel shape characteristic information of the image to be detected;
and constructing a steel piling monitoring model by adopting a machine learning method based on the red steel shape characteristic information, the first steel piling phenomenon identification result and the second steel piling phenomenon identification result so as to predict the occurrence of steel piling accidents.
Compared with manual monitoring, the steel piling monitoring system and the steel piling monitoring method provided by the invention can monitor whether steel piling accidents occur or not for a long time under the unattended condition, greatly reduce the labor burden and are not influenced by human factors. Compared with the existing automatic monitoring scheme, the visual sensor can be placed in a region far away from steel rolling, is not influenced by high temperature and physical collision of steel rolling, and has long working time. In addition, system signals are judged without passing through the PLC, the influence on the existing control system is small, the construction is convenient, and the production is not influenced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic structural topology diagram of a steel pile monitoring system provided by a first embodiment of the invention;
FIG. 2 is a schematic flow chart of a monitoring method for steel pile according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating ROI area division in a steel pile monitoring method according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating detection of region boundary crossing in a steel pile monitoring method according to a second embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating the change of red steel areas of different exposure windows in a steel pile monitoring method according to a second embodiment of the present invention;
fig. 6 is a schematic diagram of arrangement of monitoring points in a monitoring method for steel pile provided by a second embodiment of the invention.
Icon: 1-high speed industrial cameras; 2-a first lower computer; 3-a far infrared imager; 4-a second lower computer; 5-a central controller; 6-control subnet; 7-an alarm lamp; 8-flying shears.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, a first embodiment of the present invention provides a steel pile monitoring system, which includes a monitoring subnet, a control subnet 6 and a central controller 5;
the central controller 5 is respectively connected with the monitoring subnet and the control subnet 6; the monitoring subnet is used for collecting red steel images and extracting characteristic parameters based on the red steel images, and the central controller 5 generates a control command according to the characteristic parameters sent by the monitoring subnet and sends the control command to the control subnet 6; the monitoring subnet comprises a plurality of visible light monitoring nodes and a plurality of infrared monitoring nodes; the control sub-network 6 is connected with external equipment in a steel rolling area and used for controlling the external equipment to process a steel piling accident site.
In the implementation, the monitoring sub-network is responsible for red steel data acquisition, feature extraction and partial monitoring and alarming functions of a steel rolling area. The monitoring nodes are of two types, namely visible light monitoring nodes and infrared monitoring nodes. The two types of monitoring nodes receive the command of the central controller 5, collect the red steel image of the steel rolling area under the control of the central controller, perform image segmentation, extract the characteristic parameters of the red steel and transmit the characteristic parameters to the central controller 5.
Further, in a preferred embodiment of the present invention, the central controller 5 is an upper computer, each of the visible light monitoring nodes is provided with a first lower computer 2 and a high-speed industrial camera 1, and the high-speed industrial camera 1 is responsible for capturing red steel images at a rate of more than 50 frames per second. And each infrared monitoring node is provided with a second lower computer 4 and a far infrared imager 3, and the acquisition rate of the far infrared imager 3 is 27 frames/s.
In this embodiment, the high-speed industrial camera 1 adopts an industrial camera with a USB3.0 interface, and can acquire red steel images at a rate of 90 frames per second at a resolution of 1080 × 1024, so as to capture the dynamic characteristics of red steel. However, the interference of the visible light image due to uncertain factors is large, and a red indicator light may cause the misjudgment. Therefore, the invention also adopts the far infrared imager 3 to image the red steel. The far infrared imager 3 can image the temperature of an object within the range of 0-1200 ℃, so that the red steel of 900 ℃ can be separated from the background through an algorithm. This embodiment utilizes the imaging device of two kinds of different principles, carries out data acquisition to the red steel, has further ensured data acquisition and follow-up image analysis's accuracy.
Further, the first lower computer 2 and the second lower computer 4 are industrial personal computers. The industrial personal computer is an industrial control computer, and has the properties and characteristics of a computer, such as a computer mainboard, a CPU, a hard disk, a memory, peripherals and interfaces, an operating system, a control network and a protocol, computing capability and a friendly human-computer interface. Therefore, the industrial personal computer monitoring the two types of nodes of the subnet can be used for carrying out image segmentation and extraction of the red steel characteristic parameters on the red steel image, and the extracted red steel characteristic parameters are transmitted to the upper computer through a transmission protocol between the upper computer and the lower computer to identify the steel piling phenomenon.
In the embodiment, the red steel image acquired by the high-speed industrial camera 1 and the far infrared imager 3 can be transmitted to the first lower computer 2 and the second lower computer 4 through the USB3.0 interface to be subjected to image segmentation and red steel image characteristic parameter extraction, the specific steps include image segmentation after region of interest (ROI) division is carried out on the red steel image, and after the red steel image is separated from the background, the acquired red steel characteristic parameters are ensured to be contained in the ROI region, and the data transmitted by the image are reduced through the defined ROI region, so that the operation of the industrial personal computer is reduced, and the efficiency is improved.
Furthermore, the monitoring subnet and the central controller 5 are in communication connection through a transmission protocol which is TCP/IP, that is, the first lower computer 2 of the monitoring subnet sends the red steel image and the red steel characteristic parameter which are processed by the image to the central controller 5 through the TCP/IP transmission protocol. And the central controller 5 receives the red steel image and the red steel characteristic parameters sent by the monitoring subnet, carries out comprehensive analysis again, and judges whether the steel piling phenomenon occurs or not. If the steel piling phenomenon occurs, when the alarm is started, a corresponding control command is generated and sent to the control sub-network 6, and the control sub-network 6 controls external equipment in a steel rolling area to process the steel piling accident site. In the embodiment, the central controller 5 adopts a Beckman industrial personal computer to operate the Twincat real-time environment, so that the high reliability of the Twincat real-time environment is ensured.
In addition, in this embodiment, in order to ensure that the monitoring subnet and the central controller 5 can normally operate without system failure, the central controller 5 is generally placed in a monitoring room, the operating environment is good, and a real-time modified industrial personal computer is adopted, so that the reliability of the industrial personal computer is high, and the industrial personal computer is not easy to crash. In addition, the first lower computer 2 and the second lower computer 4 of the monitoring subnet need to be arranged on a monitoring site, the environment is severe, and a certain possibility of crash exists. Therefore, the industrial personal computer system for monitoring the subnet adopts two means of software and hardware to ensure the reliability. From the hardware, select the totally closed no fan industrial computer that the reliability is high, the guarantee can not have iron fillings to get into the industrial computer inside, causes the harm to the industrial computer. And in terms of software, each industrial personal computer monitoring the subnet sends a network signal to the central controller 5 at regular time to feed the dogs in a software watchdog mode, and after the central controller 5 receives the dog feeding signal and times out, the central controller 5 sends a corresponding industrial personal computer forcibly restarting the monitoring subnet.
Further, the control subnet 6 and the central controller 5 are in communication connection via an ethernet, which is an ethernet transport protocol. Ethercat is master-slave mode network, and central controller 5 can regard as Ethercat master station, and control subnet 6 is then as the slave station, and control subnet 6 can include one or more in bus coupling terminal, Profinet bus conversion module, IO input/output module. The slave station module can be directly connected to a production line control network of a steel rolling area or replace an emergency stop switch through an IO module, the production line is not required to be greatly modified, the production is stopped firstly, and then external equipment is controlled to carry out steel piling accident field treatment, so that the speed is higher. Wherein, in this embodiment, the external device includes a warning lamp 7 and a flying shear 8, the warning lamp 7 is used for reminding a worker of the occurrence of the steel piling phenomenon, and the flying shear 8 is used for treating the steel piling phenomenon.
Further, the high-speed industrial camera 1 and the far infrared imager 3 are sleeved with transparent protective covers. The reason is that the steel rolling field environment is severe and may affect the industrial camera and the thermal imager, so the far infrared imager 3 is protected by a customized water cooling cover, and in order to avoid the influence of iron filings on the industrial camera, a protective cover is also needed to be customized to protect the camera.
Compared with manual monitoring, the steel piling monitoring system provided by the first embodiment of the invention can monitor whether steel piling accidents occur or not for a long time under the unattended condition, greatly reduces the labor burden and is not influenced by human factors. Compared with the existing automatic monitoring scheme, the visual sensor can be placed in a region far away from steel rolling, is not influenced by high temperature and physical collision of steel rolling, and has long working time. In addition, system signals are judged without passing through the PLC, the influence on the existing control system is small, the construction is convenient, and the production is not influenced.
Referring to fig. 2, a second embodiment of the present invention provides a steel pile monitoring method, which uses the above steel pile monitoring system to perform steel pile monitoring, which can be respectively performed by industrial personal computer devices of a monitoring subnet and a central controller 5, and at least includes the following steps:
s201, acquiring the red steel image; wherein the red steel image comprises a visible light image collected by the high-speed industrial camera 1 and an infrared light image collected by the far infrared imager 3.
In this embodiment, the difficulty of monitoring the steel pile is to segment the red steel from the background, so in this embodiment, the monitoring subnet of the steel pile monitoring system adopts two image capturing sensors to capture the red steel image. The two sensors are respectively a high-speed industrial camera 1 and a far infrared imager 3, and are respectively used for acquiring visible light images and infrared light images of red steel images. The industrial personal computer equipment for controlling the image acquisition sensors to acquire the red steel image is industrial personal computer equipment in a monitoring subnet and comprises a first lower computer 2 and a second lower computer 4. The embodiment utilizes two imaging devices with different principles to acquire images of the red steel, and further ensures the accuracy of image acquisition and subsequent image processing analysis.
S202, carrying out image processing on the red steel image to obtain an image to be detected; the image processing comprises the steps of carrying out region-of-interest division and image segmentation on the red steel image.
In the red steel image acquired by the image acquisition equipment, most of the image area of the red steel image is an environmental image which is irrelevant to steel piling monitoring. The presence of these environmental images can interfere with the segmentation of the red steel from the background and add an additional unnecessary computational burden to the image processing. Therefore, it is necessary to define a region of interest (ROI) before image segmentation to reduce the processed data and improve the operation efficiency.
In a preferred embodiment of the present invention, referring to fig. 3, the step of dividing the region of interest of the red steel image includes:
segmenting the red steel image by adopting a Gaussian mixture model image segmentation algorithm to mark a red steel area;
converting the red steel image processed by a Gaussian mixture model image segmentation algorithm into a binary image; wherein the background is 0, and the red steel area is 1;
the red steel image processed by a Gaussian mixture model image segmentation algorithm is processed by adopting Hough transform to fit a straight line through which the red steel passes;
and expanding a certain region threshold value on the red steel image based on the straight line to obtain the ROI region.
The Gaussian mixture model image segmentation (GMM) is a nonlinear learning model, and the image is learned according to image samples to obtain a nonlinear segmentation model for segmentation. However, the learning sample of the algorithm needs to be manually calibrated, so that the operation can be realized only by inputting the sample before the operation of the steel pile monitoring system. In addition, because the installation positions of the high-speed industrial camera 1 and the far infrared imager 3 are fixed, the region of interest defined by the steps can be used for a period of time in the subsequent red steel image, and the region of interest of the red steel image obtained in the period of time can be used for the previously divided region of interest by setting a time threshold, so that the operation is reduced, and the efficiency is improved. After the time threshold is exceeded, the region of interest is divided again, and errors caused by possible deviation of the positions of the lenses of the high-speed industrial camera 1 and the far infrared imager 3 due to gravity are avoided.
In this embodiment, after the red steel image defines the region of interest, in order to segment the red steel from the background of the region of interest, the embodiment further performs image segmentation on the red steel image defining the region of interest by using one or more of three segmentation algorithms, namely gaussian mixture model image segmentation, color space segmentation and temperature threshold segmentation.
The color space segmentation is a simpler segmentation algorithm, the algorithm utilizes the color characteristic of red steel, and the red steel and the background can be separated because the red steel has no similar color in the environment around the red steel. The operation process is that the image is firstly converted from RGB color space to HSI color space, and binary segmentation is carried out by utilizing H (tone) layer. The color segmentation speed is high, the segmentation effect is good near red steel, but the red steel is influenced by ambient light at a position slightly far away from the red steel, so that the algorithm can be used for obtaining red steel segmentation in a visible light image.
The temperature threshold segmentation needs to be carried out by relying on a far infrared imager 3, because the temperature of the red steel exceeds 800 ℃ and is far higher than the ambient temperature. By setting a certain threshold, red steel can be separated from background, and the image segmentation method is simple and quick and is therefore considered as a final segmentation standard.
By selecting one or more of the three segmentation algorithms and matching the segmentation result of the visible light image with the segmentation result of the infrared light image, a relatively accurate red steel segmentation image can be obtained.
On the basis of the above embodiments, in a preferred embodiment of the present invention, the image segmentation step of the red steel image includes:
performing image segmentation on the infrared light image by adopting a temperature threshold segmentation algorithm to obtain a first segmentation image;
performing image segmentation on the visible light image by adopting a Gaussian mixture model image segmentation algorithm or a color space segmentation algorithm to obtain a second segmentation image;
and matching the first segmentation image and the second segmentation image to obtain an image to be detected.
S203, identifying a steel piling phenomenon based on the image to be detected so as to determine a steel rolling area corresponding to the steel piling accident of the image to be detected.
Further, the step of identifying the steel piling phenomenon based on the image to be detected to determine the steel rolling area corresponding to the steel piling accident of the image to be detected comprises the following steps:
performing region boundary crossing detection on the image to be detected to obtain a first stacked steel phenomenon identification result;
detecting the arrival time of the image to be detected to obtain a second steel piling phenomenon identification result;
and determining a corresponding steel rolling area of the image to be detected in which the steel piling accident occurs based on the first steel piling phenomenon recognition result and the second steel piling phenomenon recognition result.
In the embodiment, the steel piling phenomenon of the image to be detected is identified through two algorithms, then the two identification results are used for finally judging whether the steel piling accident occurs through the central controller 5, then the steel rolling area where the steel piling accident occurs is found, and a control command is generated and sent to the control sub-network 6 for processing. The two algorithms are respectively an area boundary crossing detection algorithm and an arrival time sequence (speed characteristic) monitoring algorithm.
The basic idea of the region out-of-range detection algorithm is to determine the normal active range of red steel in advance through initialization monitoring, as shown in fig. 4, when the steel pile detection system is in a pre-operation phase, a monitoring subnet collects the red steel area of a red steel window in real time as a ' (not shown), and after a period of time, the accumulated a ' is subjected to and operation to obtain a central region a as shown in fig. 4, namely a ' u aThereby setting B as the normal red steel moving area. When the steel piling detection system is switched to the operation stage from the pre-operation, the area where the real-time collected image A 'exceeds B is C, and C is A' -B. The area of the C area can be used as an index for monitoring the steel pile. When C exceeds the threshold value T, the steel piling accident is considered to be sent, and therefore the first steel piling phenomenon identification result can be obtained.
In the region out-of-range detection algorithm of the embodiment, the threshold T is a key parameter of the algorithm, and if T is too large, although the steel piling phenomenon can be detected, the sensitivity is low, and the effect is limited. If T is too small, it is not guaranteed that the steel piling phenomenon can be detected. Therefore, the steel pile monitoring method also adopts a threshold optimization algorithm to perform self-adaption of threshold selection. In the initial state, a relatively rough threshold Ti is selected to ensure that the steel pile can be detected, after the steel pile is detected for one time, the threshold is updated to a slightly smaller value Ti +1, the two thresholds are detected in parallel, and the steps are repeated in a circulating way until the missed detection occurs in one threshold, and the optimal threshold is considered to be close. And the system restores the original threshold value and enters a normal running state.
In this embodiment, the red steel image collected in real time is as shown in fig. 6, and the color block in the center of the black background is the window where the red steel is exposed. The time series (velocity profile) monitoring algorithm may count the area S of the red steel in the window, with the area S of each different exposed window varying with respect to time t as the red steel passes as shown in fig. 5.
In the coordinate system of fig. 5, the abscissa is time, the ordinate is exposed red steel area, and the three coordinate systems respectively correspond to three different exposed windows. The differential operation is performed to obtain the time point t of the jump of the area SiI belongs to {1.. n }, t of different windowsiAnd carrying out difference operation to obtain a time difference sequence: ni ═ t2-t1，t3-t2，....tn-tn-1}; this time sequence reflects the dynamic properties of the red steel. Wherein, N is singleiOnly reflecting the observation condition of a certain monitoring node, when all the monitoring nodes extract NiThen, the central controller 5 integrates the time series characteristics of each monitoring node to obtain the time series of the arrival of the whole production line. The views of the monitoring nodes are overlapped (as shown in fig. 6), the monitoring nodes are sorted according to positions, the local time sequence of each monitoring node is collected to the central controller 5, and a long global time sequence N is formedgWherein Ng ═ N1∪N2....∪NiAnd obtaining a second steel piling phenomenon recognition result by judging whether the global time sequence is normal or not. When one of the time sequences is distinguished, a steel rolling area where the steel piling accident occurs can be found according to the red steel position corresponding to the time sequence, so that the central controller 5 sends a control command to the control sub-network 6, and the control sub-network 6 controls external equipment to process the control command.
It should be noted that, in this step, the detection of the area boundary crossing detection and the arrival time detection may be analyzed by the monitoring subnet, or may be analyzed by the central controller 5, but the identification results of the both may be comprehensively analyzed by the central controller 5 to determine whether the steel piling phenomenon occurs, so as to ensure the accuracy. In addition, in fig. 6, each monitoring node is provided with a high-speed industrial camera 1 and a far infrared imager 3, so that the accuracy of collecting the red steel area is guaranteed.
And S204, controlling the external equipment to process based on the steel piling phenomenon.
Further, still include:
obtaining the red steel shape characteristic information of the image to be detected;
and constructing a steel piling monitoring model by adopting a machine learning method based on the red steel shape characteristic information, the first steel piling phenomenon identification result and the second steel piling phenomenon identification result so as to predict the occurrence of steel piling accidents.
The red steel shape characteristic information of the image to be detected can be obtained by an industrial personal computer monitoring the subnet or industrial personal computer equipment of the central controller 5. In the preferred embodiment of the present invention, the industrial personal computer device monitoring the subnet first performs image processing on the red steel image to obtain four morphological characteristics of change of an included angle between the red steel and the horizontal direction, change of curvature of the red steel, change of gravity center position of the red steel and change of exposure area of the red steel, and sends the obtained characteristics to the central controller 5. The shape feature information, the first stacking phenomenon recognition result and the second stacking phenomenon recognition result form a stacking accident learning sample. The sample is used for machine learning to obtain a non-linear model for monitoring the steel pile. By utilizing the model, whether the steel piling accident happens or not can be predicted in real time according to the shape characteristics, so that the early warning time is greatly advanced.
According to the steel piling monitoring method provided by the second embodiment of the invention, the system adopts two image acquisition sensors and three image segmentation algorithms for parallel operation to monitor the steel piling. The key technology is that the image segmentation and the feature extraction of the red steel are carried out, analysis and judgment are carried out according to the extracted features, once 'steel piling' is found, an alarm is sent out in time, corresponding upper-stream flying shears 8 are automatically controlled to act, the phenomenon that a large amount of red steel flees out to cause equipment or other accidents is avoided, and loss is reduced to the maximum extent. In addition, the steel piling monitoring system can automatically store accident images, and machine learning is carried out by taking the accident images as sample materials, so that self-evolution of the system is realized, and the sensitivity and reliability of accident prediction are improved.
It should be noted that the above-described device or module embodiments are only schematic, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A steel piling monitoring system is characterized by comprising a monitoring subnet, a control subnet and a central controller;
the central controller is respectively connected with the monitoring sub-network and the control sub-network; the monitoring subnet is used for collecting red steel images and extracting characteristic parameters based on the red steel images, and the central controller generates control commands according to the characteristic parameters sent by the monitoring subnet and sends the control commands to the control subnet; the monitoring subnet comprises a plurality of visible light monitoring nodes and a plurality of infrared monitoring nodes; and the control subnet is connected with external equipment, and the external equipment is controlled to be used for processing the steel piling accident site.
2. The steel pile monitoring system according to claim 1, wherein the monitoring sub-network and the central controller are in communication connection through a transmission protocol of TCP/IP.
3. The steel pile monitoring system of claim 2, wherein the control sub-network and the central controller are communicatively connected via a transmission protocol of an Ethercat industrial ethernet.
4. The steel stack monitoring system according to claim 3, wherein the central controller is an upper computer, and each visible light monitoring node is provided with a first lower computer and a high-speed industrial camera.
5. The steel stack monitoring system according to claim 4, wherein the central controller is an upper computer, and each infrared monitoring node is provided with a second lower computer and a far infrared imager.
6. The steel pile monitoring system according to claim 5, wherein the first lower computer and the second lower computer are industrial personal computers.
7. The reactor steel monitoring system of claim 6, wherein the field devices comprise a warning light and flying shears.
8. A method for monitoring steel pile, which is characterized by using the steel pile monitoring system as claimed in claim 7 for monitoring steel pile, and comprises the following steps:
acquiring the red steel image; wherein the red steel image comprises a visible light image collected by the high-speed industrial camera and an infrared light image collected by the far infrared imager;
carrying out image processing on the red steel image to obtain an image to be detected; the image processing comprises the steps of carrying out region-of-interest division and image segmentation processing on the red steel image;
carrying out steel piling phenomenon identification based on the image to be detected so as to determine a steel rolling area corresponding to the steel piling accident of the image to be detected;
and controlling the external equipment to carry out steel piling accident site treatment based on the steel piling phenomenon.
9. The method for monitoring the steel pile according to claim 8, wherein the step of identifying the steel pile-up phenomenon based on the image to be detected to determine the steel rolling area corresponding to the steel pile-up accident on the basis of the image to be detected comprises the following steps:
performing region boundary crossing detection on the image to be detected to obtain a first stacked steel phenomenon identification result;
detecting the arrival time of the image to be detected to obtain a second steel piling phenomenon identification result;
and determining a steel rolling area corresponding to the steel piling accident of the image to be detected based on the first steel piling phenomenon identification result and the second steel piling phenomenon identification result.
10. The method of monitoring steel pile up according to claim 9, characterized by further comprising:
obtaining the red steel shape characteristic information of the image to be detected;
and constructing a steel piling monitoring model by adopting a machine learning method based on the red steel shape characteristic information, the first steel piling phenomenon identification result and the second steel piling phenomenon identification result so as to predict the occurrence of steel piling accidents.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910816923.7A CN110597165B (en) | 2019-08-30 | 2019-08-30 | Steel piling monitoring system and steel piling monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910816923.7A CN110597165B (en) | 2019-08-30 | 2019-08-30 | Steel piling monitoring system and steel piling monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110597165A true CN110597165A (en) | 2019-12-20 |
| CN110597165B CN110597165B (en) | 2021-04-27 |
Family
ID=68857007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910816923.7A Active CN110597165B (en) | 2019-08-30 | 2019-08-30 | Steel piling monitoring system and steel piling monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110597165B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340027A (en) * | 2020-03-05 | 2020-06-26 | 中冶赛迪重庆信息技术有限公司 | Steel pile identification method and system, electronic equipment and medium |
| CN111523429A (en) * | 2020-04-16 | 2020-08-11 | 中冶赛迪重庆信息技术有限公司 | Deep learning-based steel pile identification method |
| CN116523893A (en) * | 2023-05-16 | 2023-08-01 | 华院计算技术(上海)股份有限公司 | Flying steel detection system and method based on machine vision |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2234400C1 (en) * | 2003-05-22 | 2004-08-20 | Общество с ограниченной ответственностью "Интермет-Инжиниринг" | Method of manufacturing bimetal steel stack |
| JP3839018B2 (en) * | 2003-12-03 | 2006-11-01 | Ｎｅｃ東芝スペースシステム株式会社 | Dental tomography apparatus, dental arch model used therefor, distortion display method and distortion correction method |
| CN1974040A (en) * | 2006-12-08 | 2007-06-06 | 广州珠江钢铁有限责任公司 | Rolling process of hot rolled steel sheet |
| CN201532585U (en) * | 2009-11-24 | 2010-07-21 | 青岛钢铁控股集团有限责任公司 | Temperature control system for easily cut steel |
| CN201793675U (en) * | 2010-09-17 | 2011-04-13 | 莱芜钢铁股份有限公司 | Device for rapidly stacking annealed steel coils |
| CN102836883A (en) * | 2011-06-23 | 2012-12-26 | 宝山钢铁股份有限公司 | Control method for upward and downward head bending of plate blank |
| WO2013017162A1 (en) * | 2011-08-01 | 2013-02-07 | Endress+Hauser Conducta Gesellschaft Für Mess- Und Regeltechnik Mbh+Co. Kg | Arrangement for the in-situ measurement of at least the oxygen content within a solid waste dump |
| CN202893830U (en) * | 2012-11-16 | 2013-04-24 | 武汉钢铁(集团)公司 | Misinformation-prevented folding defect monitoring device for high speed wire rods |
| CN203227670U (en) * | 2013-03-29 | 2013-10-09 | 安阳市合力高速冷轧有限公司 | Steel-piling detecting and scrap steel collecting device for cold-rolled wire rods |
| CN203606860U (en) * | 2013-10-28 | 2014-05-21 | 天津市罗伯特数控设备制造有限公司 | A steel bar count checking instrument |
| WO2014141534A1 (en) * | 2013-03-13 | 2014-09-18 | 日本電気株式会社 | Comparison system, terminal device, server device, comparison method, and program |
| CN105472343A (en) * | 2015-12-20 | 2016-04-06 | 天津博普科技有限公司 | High-speed rolling line video analyzing and monitoring system for continuously rolled rod |
| CN205232378U (en) * | 2015-12-20 | 2016-05-11 | 天津博普科技有限公司 | A image acquisition device that under is used for high temperature, dust environment |
| CN205232379U (en) * | 2015-12-20 | 2016-05-11 | 天津博普科技有限公司 | Rod rolls line video monitoring image acquisition device |
| CN205386573U (en) * | 2016-03-25 | 2016-07-20 | 刘波 | Steel detection device is piled to H shaped steel continuous rolling mill train rolled piece |
| CN106040752A (en) * | 2016-06-22 | 2016-10-26 | 江苏永钢集团有限公司 | Detection system for high-speed wire rod steel heaping and judgment method |
| CN106311749A (en) * | 2016-08-31 | 2017-01-11 | 重庆钢铁集团电子有限责任公司 | High-speed wire rolling fault processing method |
| CN107377635A (en) * | 2017-07-19 | 2017-11-24 | 江苏永钢集团有限公司 | A kind of high-speed rod piling of steel detection method |
| CN108431563A (en) * | 2015-12-24 | 2018-08-21 | 株式会社Posco | Material cooled region detection device and wire rod cooled region detection method |
| CN109029507A (en) * | 2018-06-24 | 2018-12-18 | 新疆八钢铁股份有限公司 | Piling of steel detection sensor |
| CN110102581A (en) * | 2019-04-03 | 2019-08-09 | 姚国辉 | A kind of cold-rolled wire piling of steel detection method based on Internet of Things |
| CN209238688U (en) * | 2018-12-20 | 2019-08-13 | 山东鑫华特钢集团有限公司 | A kind of steel rolling card is disconnected to cut device |
-
2019
- 2019-08-30 CN CN201910816923.7A patent/CN110597165B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2234400C1 (en) * | 2003-05-22 | 2004-08-20 | Общество с ограниченной ответственностью "Интермет-Инжиниринг" | Method of manufacturing bimetal steel stack |
| JP3839018B2 (en) * | 2003-12-03 | 2006-11-01 | Ｎｅｃ東芝スペースシステム株式会社 | Dental tomography apparatus, dental arch model used therefor, distortion display method and distortion correction method |
| CN1974040A (en) * | 2006-12-08 | 2007-06-06 | 广州珠江钢铁有限责任公司 | Rolling process of hot rolled steel sheet |
| CN201532585U (en) * | 2009-11-24 | 2010-07-21 | 青岛钢铁控股集团有限责任公司 | Temperature control system for easily cut steel |
| CN201793675U (en) * | 2010-09-17 | 2011-04-13 | 莱芜钢铁股份有限公司 | Device for rapidly stacking annealed steel coils |
| CN102836883A (en) * | 2011-06-23 | 2012-12-26 | 宝山钢铁股份有限公司 | Control method for upward and downward head bending of plate blank |
| WO2013017162A1 (en) * | 2011-08-01 | 2013-02-07 | Endress+Hauser Conducta Gesellschaft Für Mess- Und Regeltechnik Mbh+Co. Kg | Arrangement for the in-situ measurement of at least the oxygen content within a solid waste dump |
| CN202893830U (en) * | 2012-11-16 | 2013-04-24 | 武汉钢铁(集团)公司 | Misinformation-prevented folding defect monitoring device for high speed wire rods |
| WO2014141534A1 (en) * | 2013-03-13 | 2014-09-18 | 日本電気株式会社 | Comparison system, terminal device, server device, comparison method, and program |
| CN203227670U (en) * | 2013-03-29 | 2013-10-09 | 安阳市合力高速冷轧有限公司 | Steel-piling detecting and scrap steel collecting device for cold-rolled wire rods |
| CN203606860U (en) * | 2013-10-28 | 2014-05-21 | 天津市罗伯特数控设备制造有限公司 | A steel bar count checking instrument |
| CN105472343A (en) * | 2015-12-20 | 2016-04-06 | 天津博普科技有限公司 | High-speed rolling line video analyzing and monitoring system for continuously rolled rod |
| CN205232378U (en) * | 2015-12-20 | 2016-05-11 | 天津博普科技有限公司 | A image acquisition device that under is used for high temperature, dust environment |
| CN205232379U (en) * | 2015-12-20 | 2016-05-11 | 天津博普科技有限公司 | Rod rolls line video monitoring image acquisition device |
| CN108431563A (en) * | 2015-12-24 | 2018-08-21 | 株式会社Posco | Material cooled region detection device and wire rod cooled region detection method |
| CN205386573U (en) * | 2016-03-25 | 2016-07-20 | 刘波 | Steel detection device is piled to H shaped steel continuous rolling mill train rolled piece |
| CN106040752A (en) * | 2016-06-22 | 2016-10-26 | 江苏永钢集团有限公司 | Detection system for high-speed wire rod steel heaping and judgment method |
| CN106311749A (en) * | 2016-08-31 | 2017-01-11 | 重庆钢铁集团电子有限责任公司 | High-speed wire rolling fault processing method |
| CN107377635A (en) * | 2017-07-19 | 2017-11-24 | 江苏永钢集团有限公司 | A kind of high-speed rod piling of steel detection method |
| CN109029507A (en) * | 2018-06-24 | 2018-12-18 | 新疆八钢铁股份有限公司 | Piling of steel detection sensor |
| CN209238688U (en) * | 2018-12-20 | 2019-08-13 | 山东鑫华特钢集团有限公司 | A kind of steel rolling card is disconnected to cut device |
| CN110102581A (en) * | 2019-04-03 | 2019-08-09 | 姚国辉 | A kind of cold-rolled wire piling of steel detection method based on Internet of Things |
Non-Patent Citations (3)
| Title |
|---|
| MOHAMMED H.HAFIZ: "Steel Piling Corrosion Management of Al-Zubare Harbor", 《AMERICAN JOURAL OR ENGINEERING AND APPLIED SCIENCE》 * |
| 周丽萍: "红外测量技术在钢铁轧制中的应用", 《江苏省计量测试学术论文集》 * |
| 徐科: "基于线型激光的热轧带钢表面在线检测***", 《北京科技大学学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340027A (en) * | 2020-03-05 | 2020-06-26 | 中冶赛迪重庆信息技术有限公司 | Steel pile identification method and system, electronic equipment and medium |
| CN111523429A (en) * | 2020-04-16 | 2020-08-11 | 中冶赛迪重庆信息技术有限公司 | Deep learning-based steel pile identification method |
| CN116523893A (en) * | 2023-05-16 | 2023-08-01 | 华院计算技术(上海)股份有限公司 | Flying steel detection system and method based on machine vision |
| CN116523893B (en) * | 2023-05-16 | 2023-12-26 | 华院计算技术(上海)股份有限公司 | Flying steel detection system and method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110597165B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898514B (en) | Multi-target visual supervision method based on target detection and action recognition | |
| CN108446630B (en) | Intelligent monitoring method for airport runway, application server and computer storage medium | |
| CN110597165B (en) | Steel piling monitoring system and steel piling monitoring method | |
| KR101748121B1 (en) | System and method for detecting image in real-time based on object recognition | |
| CN110263686A (en) | A kind of construction site safety of image cap detection method based on deep learning | |
| CN110414400B (en) | Automatic detection method and system for wearing of safety helmet on construction site | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN113793234B (en) | Wisdom garden platform based on digit twin technique | |
| CN112623919B (en) | Escalator intelligent monitoring management system based on computer vision | |
| CN113283344A (en) | Mining conveying belt deviation detection method based on semantic segmentation network | |
| CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
| CN111523386B (en) | High-speed railway platform door monitoring and protecting method and system based on machine vision | |
| CN114155472A (en) | Method, device and equipment for detecting abnormal state of factory scene empty face protection equipment | |
| Wang et al. | Worker’s helmet recognition and identity recognition based on deep learning | |
| CN114005088A (en) | Safety rope wearing state monitoring method and system | |
| CN113314230A (en) | Intelligent epidemic prevention method, device, equipment and storage medium based on big data | |
| CN116403162B (en) | Airport scene target behavior recognition method and system and electronic equipment | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| CN116147697B (en) | Unattended monitoring method and system for aluminum hydroxide | |
| CN115909168A (en) | Auxiliary control data analysis system and method for intelligent substation | |
| CN114314243A (en) | Elevator overload alarm system and method based on video identification technology | |
| CN114332695A (en) | Method and device for identifying opening and closing of elevator door and storage medium | |
| CN115314401B (en) | Contact net state monitoring method and device, electronic equipment and storage medium | |
| CN116311029B (en) | Construction operation violation identification system and method based on big data | |
| CN117975372B (en) | Construction site safety detection system and method based on YOLOv and transducer encoder |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ren Wen Inventor after: Gong Junfeng Inventor before: Gong Junfeng Inventor before: Ren Wen |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |