WO2023168899A1 - 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质 - Google Patents

圆锥破碎机排料口尺寸智能调整方法、装置及可读介质 Download PDF

Info

Publication number
WO2023168899A1
WO2023168899A1 PCT/CN2022/110878 CN2022110878W WO2023168899A1 WO 2023168899 A1 WO2023168899 A1 WO 2023168899A1 CN 2022110878 W CN2022110878 W CN 2022110878W WO 2023168899 A1 WO2023168899 A1 WO 2023168899A1
Authority
WO
WIPO (PCT)
Prior art keywords
aggregate
cone crusher
size
discharge opening
average
Prior art date
Application number
PCT/CN2022/110878
Other languages
English (en)
French (fr)
Inventor
王英俊
张宝裕
黄骁民
杨建红
黄文景
魏朝明
庄汉强
Original Assignee
福建南方路面机械股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 福建南方路面机械股份有限公司 filed Critical 福建南方路面机械股份有限公司
Publication of WO2023168899A1 publication Critical patent/WO2023168899A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
    • B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
    • B02C2/00—Crushing or disintegrating by gyratory or cone crushers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
    • B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
    • B02C23/00—Auxiliary methods or auxiliary devices or accessories specially adapted for crushing or disintegrating not provided for in preceding groups or not specially adapted to apparatus covered by a single preceding group
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
    • B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
    • B02C25/00—Control arrangements specially adapted for crushing or disintegrating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W30/00—Technologies for solid waste management
    • Y02W30/50—Reuse, recycling or recovery technologies
    • Y02W30/91—Use of waste materials as fillers for mortars or concrete

Definitions

  • the invention relates to the field of cone crusher discharge opening adjustment field, and specifically relates to a cone crusher discharge opening size intelligent adjustment method, device and readable medium.
  • cone crusher is also a popular crushing equipment at present. It is often used in the crushing and processing of various ores. Due to its outstanding advantages such as high output, stable performance, and long service life, cone crushers are widely used in the market.
  • one of the factors that affects the output of the cone crusher is the adjustment of the discharge port. The operator must be proficient in adjusting the size of the discharge port to ensure smooth production and ensure the finished bone output from the discharge port. The particle size of the material meets the requirements. Different sizes of discharge openings of cone crushers produce different particle sizes of finished aggregates.
  • the traditional method of adjusting the discharge port is for the observer to observe the size of the aggregate particles near the discharge port, judge the opening size of the discharge port, and then manually adjust the size of the discharge port.
  • the wear-resistant lining plate wears more, the change in the size of the aggregate particle size is visible to the naked eye.
  • the observer observes the change in the size of the aggregate particle size, and there is already a large hysteresis.
  • Another method is based on the detection method of coarse aggregate particle size. This method requires sampling to a coarse aggregate detector for aggregate particle size detection. At this time, the offline detection speed of sampling and re-inspection is slow, and the size of the discharge port cannot be adjusted in time.
  • the above two methods require manual participation and are inefficient.
  • the purpose of the embodiments of the present application is to propose a method, device and readable medium for intelligently adjusting the size of the discharge opening of a cone crusher to solve the technical problems mentioned in the background technology section above.
  • embodiments of the present application provide a method for intelligently adjusting the size of the discharge port of a cone crusher, which includes the following steps:
  • the first aggregate parameters include the first average aggregate particle size, the first aggregate gradation curve area difference, the first average aggregate needle-likeness and the first average One or more types of aggregates;
  • S3 construct a cone crusher discharge opening size prediction model, input the first aggregate parameters into the cone crusher discharge opening size prediction model, and output the cone crusher discharge opening size prediction value;
  • the construction of a cone crusher discharge opening size prediction model in step S3 specifically includes:
  • the second aggregate parameters are obtained according to the second segmentation result, and the second aggregate parameters include the second average aggregate particle size, the second aggregate gradation curve area difference, the second average aggregate needle-likeness and the second average aggregate one or more of the numbers;
  • Characteristic variables of _ , ⁇ is the parameter vector, ⁇ i is the random error term;
  • the multivariate nonlinear regression model is converted into a multivariate linear model, and the least squares method is used in conjunction with the second aggregate parameters to calculate each regression coefficient in the multivariate linear model, and a cone crusher discharge opening size prediction model is obtained.
  • the first average aggregate particle size and the second average aggregate particle size are average values of the aggregate particle sizes within a period of time.
  • the area difference between the first aggregate gradation curve and the second aggregate gradation curve is the area difference between the current aggregate gradation curve and the standard aggregate gradation curve, where the standard aggregate grade
  • the grading curve is the average aggregate grading curve over a period of time calculated based on the aggregate image of the finished aggregate produced by the cone crusher after the discharge port has just been adjusted.
  • the current aggregate grading curve is based on the aggregate image before the current time.
  • the average aggregate grading curve is calculated from the aggregate images over a period of time.
  • the first average needle-likeness and the second average needle-likeness are the average needle-likeness of all aggregates within a period of time
  • the needle-likeness of the aggregate is the average needle-likeness of each aggregate particle size.
  • the ratio of the long diameter to the short diameter, the first average number of aggregates and the second average number of aggregates are the average number of aggregates contained in each aggregate image within a period of time.
  • the fixed cone assembly control system includes a PLC, a hydraulic motor and a fixed cone assembly.
  • the PLC controls the hydraulic motor to drive the fixed cone assembly to move to change the size of the cone crusher discharge opening.
  • the instance segmentation model is a trained Mask-RCNN network model.
  • embodiments of the present application provide an intelligent device for adjusting the size of the discharge opening of a cone crusher, including: an instance segmentation module, a parameter calculation module, a size prediction module, a size adjustment module, a circulation module, and a device adapted thereto.
  • Fixed cone assembly control system including: an instance segmentation module, a parameter calculation module, a size prediction module, a size adjustment module, a circulation module, and a device adapted thereto.
  • the instance segmentation module is configured to obtain the first aggregate image of the finished aggregate outside the discharge port of the cone crusher in real time, use the instance segmentation model to segment the first aggregate image, and obtain the first segmentation result;
  • the parameter calculation module is configured to obtain the first aggregate parameter according to the first segmentation result.
  • the first aggregate parameter includes the first average aggregate particle size, the first aggregate gradation curve area difference, and the first average aggregate needle shape.
  • degree and first average aggregate number One or more of the following: degree and first average aggregate number;
  • the size prediction module is configured to build a cone crusher discharge opening size prediction model, input the first aggregate parameter into the cone crusher discharge opening size prediction model, and output a cone crusher discharge opening size prediction value;
  • the size adjustment module is configured to compare the predicted value of the cone crusher discharge opening size with the cone crusher discharge opening size threshold, obtain adjustment instructions based on the comparison results and send them to the fixed cone assembly control system, which is controlled by the fixed cone assembly
  • the control system adjusts the size of the cone crusher discharge port, and changes the particle size of the aggregate through the adjusted cone crusher discharge port size;
  • the loop module is configured to repeatedly execute the instance segmentation module to the size adjustment module until the predicted value of the cone crusher discharge opening size is within the cone crusher discharge opening size threshold range.
  • embodiments of the present application provide an electronic device, including one or more processors; a storage device for storing one or more programs. When the one or more programs are executed by one or more processors, , causing one or more processors to implement the method described in any implementation manner in the first aspect.
  • embodiments of the present application provide a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.
  • the present invention has the following beneficial effects:
  • the present invention can obtain the first aggregate image outside the discharge port of the cone crusher in real time, and use the instance segmentation model to segment the first aggregate image, and calculate the first aggregate parameters based on the segmentation results.
  • the material parameters are combined with the cone crusher discharge opening size prediction model to predict the cone crusher discharge opening size, and further adjust the cone crusher discharge opening size according to the predicted value, which is more real-time and more efficient in adjustment. Human intervention is required.
  • the present invention uses average aggregate particle size, aggregate gradation curve area difference, average aggregate acicularity and average aggregate number as characteristic parameters to construct a cone crusher discharge opening size prediction model, so the prediction obtained The values are more accurate and comprehensive.
  • the intelligent adjustment method of the cone crusher discharge opening size of the present invention is more intelligent than the traditional cone crusher discharge opening adjustment method. It adopts the aggregate particle size online detection method combined with the cone crusher discharge opening intelligent adjustment device, This makes the adjustment of the cone crusher discharge port more efficient, more precise and more convenient.
  • Figure 1 is an exemplary device architecture diagram in which an embodiment of the present application can be applied
  • Figure 2 is a schematic flow chart of an intelligent adjustment method for the size of the cone crusher discharge opening according to an embodiment of the present invention
  • Figure 3 is a diagram showing the results before and after segmentation of an example segmentation model of the cone crusher discharge opening size intelligent adjustment method according to the embodiment of the present invention
  • Figure 4 is a schematic diagram of the fixed cone assembly control system of the cone crusher discharge opening size intelligent adjustment method according to the embodiment of the present invention
  • Figure 5 is a schematic diagram of an intelligent adjustment device for the discharge port size of a cone crusher according to an embodiment of the present invention
  • FIG. 6 is a schematic structural diagram of a computer device suitable for implementing an electronic device according to an embodiment of the present application.
  • Figure 1 shows an exemplary device architecture 100 to which the intelligent adjustment method for cone crusher discharge opening size or the intelligent adjustment device for cone crusher discharge opening size according to the embodiment of the present application can be applied.
  • the device architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105.
  • the network 104 is a medium used to provide communication links between the terminal devices 101, 102, 103 and the server 105.
  • Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
  • Terminal devices 101, 102, 103 Users can use terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc.
  • Various applications can be installed on the terminal devices 101, 102, and 103, such as data processing applications, file processing applications, etc.
  • the terminal devices 101, 102, and 103 may be hardware or software.
  • the terminal devices 101, 102, and 103 may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and so on.
  • the terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, software or software modules used to provide distributed services), or as a single software or software module. There are no specific limitations here.
  • the server 105 may be a server that provides various services, such as a background data processing server that processes files or data uploaded by the terminal devices 101, 102, and 103.
  • the background data processing server can process the acquired files or data and generate processing results.
  • the intelligent adjustment method for the cone crusher discharge opening size provided by the embodiment of the present application can be executed by the server 105 or by the terminal devices 101, 102, 103.
  • the cone crusher discharge opening size The intelligent adjustment device can be installed in the server 105 or in the terminal devices 101, 102, and 103.
  • terminal devices, networks and servers in Figure 1 is only illustrative. Depending on implementation needs, there can be any number of end devices, networks, and servers.
  • the above device architecture may not include a network, but only a server or terminal device.
  • Figure 2 shows an intelligent adjustment method for the discharge port size of a cone crusher provided by an embodiment of the present application, which includes the following steps:
  • the instance segmentation model is a trained Mask-RCNN network model.
  • the Mask-RCNN network model is trained by downloading the pre-training weights on the COCO training set and combining it with the training set collected and labeled under actual working conditions on site. , the trained Mask-RCNN network model is obtained, and the prediction results are shown in Figure 3.
  • Figure 3(a) is the first aggregate image
  • Figure 3(b) is the first segmentation result.
  • the Mask-RCNN network model is inception_v2, but it is not limited to this.
  • the first aggregate parameters include the first average aggregate particle size, the first aggregate gradation curve area difference, the first average aggregate needle-likeness and the first average One or more types of aggregates.
  • the first aggregate image is an aggregate image of the finished aggregate outside the discharge port of the cone crusher collected in real time. Instance segmentation is performed through the instance segmentation model to obtain each aggregate on the first aggregate image. According to the mask of each aggregate, aggregate parameters such as aggregate particle size, average acicularity of aggregate and aggregate gradation curve are calculated.
  • the first average aggregate particle size is the average aggregate particle size over a period of time.
  • the area difference of the first aggregate gradation curve is the area difference between the current aggregate gradation curve and the standard aggregate gradation curve.
  • the standard aggregate gradation curve is produced by the cone crusher after the discharge port has just been adjusted. The average aggregate gradation curve within a period of time calculated from the aggregate image of the finished aggregate.
  • the current aggregate gradation curve is the average aggregate gradation curve calculated from the aggregate image within a period of time before the current time. .
  • the first average needle-like degree is the average needle-like degree of all aggregates within a period of time, and the needle-like degree of aggregate is the ratio of the long diameter to the short diameter of each aggregate particle size.
  • the first average number of aggregates is the average number of aggregates contained in each aggregate image within a period of time.
  • S3 construct a cone crusher discharge opening size prediction model, and input the first average aggregate particle size, the first aggregate gradation curve area difference, the first average aggregate needle-likeness and the first average aggregate number into the cone
  • the crusher discharge opening size prediction model outputs the cone crusher discharge opening size prediction value.
  • the construction of a cone crusher discharge opening size prediction model in step S3 specifically includes:
  • the second aggregate parameters are obtained according to the second segmentation result, and the second aggregate parameters include the second average aggregate particle size, the second aggregate gradation curve area difference, the second average aggregate needle-likeness and the second average aggregate One or more of the numbers;
  • x i1 is the second average aggregate particle size
  • x i2 is the area difference of the second aggregate gradation curve
  • x i3 is the second average aggregate needle shape
  • x i4 is the second average aggregate number
  • ⁇ is the parameter vector
  • ⁇ i is the random error term
  • the multivariate nonlinear regression model is converted into a multivariate linear model, and the least squares method is used in conjunction with the second aggregate parameters to calculate each regression coefficient in the multivariate linear model, and a cone crusher discharge opening size prediction model is obtained.
  • the second average aggregate particle size is an average of the aggregate particle sizes over a period of time.
  • the area difference of the second aggregate gradation curve is the area difference between the current aggregate gradation curve and the standard aggregate gradation curve.
  • the standard aggregate gradation curve is produced by the cone crusher after the discharge port has just been adjusted.
  • the average aggregate gradation curve within a period of time calculated from the aggregate image of the finished aggregate.
  • the current aggregate gradation curve is the average aggregate gradation curve calculated from the aggregate image within a period of time before the current time. .
  • the second average needle-like degree is the average needle-like degree of all aggregates within a period of time, and the needle-like degree of aggregate is the ratio of the long diameter to the short diameter of each aggregate particle size.
  • the second average number of aggregates is the average number of aggregates contained in each aggregate image within a period of time.
  • the second aggregate image of the finished aggregate under different discharge opening sizes is calculated, the second aggregate parameters are obtained, and the second aggregate is established.
  • the multiple nonlinear regression model between the material parameters and different discharge opening sizes is further transformed into a multiple linear regression model.
  • the least squares method is used to calculate each regression parameter in the multiple linear regression model, and finally the cone crusher is obtained.
  • Machine discharge opening size prediction model is the average number of aggregates contained in each aggregate image within a period of time.
  • the second aggregate image is to collect the aggregate image of the finished aggregate under different discharge opening sizes of the cone crusher.
  • Particle sizes vary, so a linear relationship is established.
  • a multiple nonlinear regression model is established, and the multiple nonlinear regression model is further transformed into a multiple linear regression model.
  • the multiple nonlinear regression model is calculated based on the second average aggregate particle size, the second average aggregate gradation curve area difference, the second average aggregate needle-likeness and the second average aggregate individuality calculated based on the second aggregate image. It is established by one or more of the numbers and then further converted into a multivariate linear model to obtain the cone crusher discharge opening size prediction model.
  • the first aggregate parameters corresponding to the first aggregate collected in real time are input into the cone crusher discharge opening size prediction model, and the cone crusher discharge opening size prediction value is output.
  • a binary quadratic model including interaction terms is used to describe the relationship between the discharge opening size and two factors:
  • y is the regression value, indicating the size of the discharge opening
  • x 1 and x 2 are two independent variables, indicating factor 1 and factor 2 respectively.
  • the binary quadratic nonlinear regression model is transformed into a quintuple linear regression model, from two independent variables to five independent variables.
  • the data format is shown in Table 2:
  • y a+b 1 x 1 +b 2 x 2 +b 3 x 3 +b 4 x 4 +b 5 x 5 ;
  • the predicted value of the cone crusher discharge opening size is compared with the cone crusher discharge opening size threshold. If the predicted value of the cone crusher discharge opening size is greater than the cone crusher discharge opening size threshold, then the cone crusher is reduced. Machine discharge opening size. If the predicted value of the cone crusher discharge opening size is less than the cone crusher discharge opening size threshold, then increase the cone crusher discharge opening size.
  • the adjustment of the cone crusher discharge opening size is to obtain the corresponding adjustment instructions based on the comparison results, and send the adjustment instructions to the fixed cone assembly control system.
  • the fixed cone assembly control system includes PLC, hydraulic motor and fixed cone assembly. The PLC controls the hydraulic motor to drive the fixed cone assembly to move to change the size of the cone crusher discharge port. The fixed cone assembly can be lowered or raised.
  • a camera 1 is installed on the conveyor belt 2 outside the discharge port of the cone crusher.
  • the camera 1 is used to collect the aggregate image of the finished aggregate 3 on the conveyor belt 2, and transmit the collected aggregate image to the industrial control
  • the industrial computer 4 performs instance segmentation on the collected aggregate images, predicts the mask of each aggregate, and calculates the equivalent particle size of the aggregate, the average needle-likeness of the aggregate, the aggregate gradation curve and other characteristics. Predict the size of the discharge opening through the cone crusher discharge opening size prediction model. If the predicted value of the cone crusher discharge opening size is greater than the cone crusher discharge opening size threshold, the discharge opening adjustment information is sent to PLC 5, and PLC 5 controls the hydraulic pressure.
  • the motor 6 lowers the fixed cone assembly 7 relative to the moving cone 8 to reduce the size of the discharge opening, and vice versa, ultimately achieving online automatic adjustment of the discharge opening of the cone crusher.
  • the size of the discharge opening is within the threshold range. If so, stop adjusting. Otherwise, continue to adjust the size of the cone crusher discharge opening in a loop until the size of the cone crusher discharge opening is within the threshold range.
  • this application provides an embodiment of an intelligent device for adjusting the size of the discharge port of a cone crusher.
  • the device embodiment is the same as the method embodiment shown in Figure 2
  • this device can be used in various electronic equipment to adjust the cone crusher discharge opening ruler through the fixed cone assembly control system.
  • the embodiment of the present application provides an intelligent adjustment device for the size of the discharge opening of a cone crusher, including:
  • the instance segmentation module 1 is configured to obtain the first aggregate image of the finished aggregate outside the discharge port of the cone crusher in real time, use the instance segmentation model to segment the first aggregate image, and obtain the first segmentation result;
  • the parameter calculation module 2 is configured to obtain the first aggregate parameters according to the first segmentation result.
  • the first aggregate parameters include the first average aggregate particle size, the first aggregate gradation curve area difference, the first average aggregate needle One or more of shape and first average aggregate number;
  • the size prediction module 3 is configured to build a cone crusher discharge opening size prediction model, input the first aggregate parameter into the cone crusher discharge opening size prediction model, and output a cone crusher discharge opening size prediction value;
  • the size adjustment module 4 is configured to compare the predicted value of the cone crusher discharge opening size with the cone crusher discharge opening size threshold, obtain the adjustment instruction according to the comparison result and send it to the fixed cone assembly control system, which is controlled by the fixed cone assembly.
  • the integrated control system adjusts the size of the discharge port of the cone crusher, and changes the particle size of the aggregate through the adjusted size of the discharge port of the cone crusher;
  • the loop module 5 is configured to repeatedly execute the instance segmentation module 51 to the size adjustment module 54 until the predicted value of the cone crusher discharge opening size is within the cone crusher discharge opening size threshold range.
  • the matching fixed cone assembly control system includes a PLC, a hydraulic motor and a fixed cone assembly.
  • the PLC controls the hydraulic motor to drive the fixed cone assembly to move to change the size of the cone crusher discharge opening.
  • the fixed cone assembly The cost can go down or up.
  • FIG. 6 shows a schematic structural diagram of a computer device 600 suitable for implementing an electronic device (such as the server or terminal device shown in FIG. 1 ) according to an embodiment of the present application.
  • the electronic device shown in FIG. 6 is only an example and should not impose any restrictions on the functions and usage scope of the embodiments of the present application.
  • the computer device 600 includes a central processing unit (CPU) 601 and a graphics processor (GPU) 602, which can be loaded into random access memory according to a program stored in a read-only memory (ROM) 603 or from a storage portion 609.
  • the program in the memory (RAM) 604 executes various appropriate actions and processes.
  • RAM 604 various programs and data required for the operation of the device 600 are also stored.
  • CPU 601, GPU 602, ROM 603 and RAM 604 are connected to each other through bus 605.
  • An input/output (I/O) interface 606 is also connected to bus 605 .
  • the following components are connected to the I/O interface 606: an input section 607 including a keyboard, a mouse, etc.; an output section 608 including a liquid crystal display (LCD), etc., a speaker, etc.; a storage section 609 including a hard disk, etc.; and a LAN card such as a LAN card. , modem, etc., communication portion 610 of the network interface card.
  • the communication section 610 performs communication processing via a network such as the Internet.
  • Driver 611 may also be connected to I/O interface 606 as needed.
  • Removable media 612 such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive 611 as needed, so that a computer program read therefrom is installed into the storage portion 609 as needed.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communications portion 610 and/or installed from removable media 612 .
  • the computer program is executed by the central processing unit (CPU) 601 and the graphics processor (GPU) 602, the above-mentioned functions defined in the method of the present application are performed.
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable medium, or any combination of the above two.
  • the computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus or device, or any combination thereof. More specific examples of computer readable media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), erasable programmable Read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution apparatus, apparatus, or device.
  • the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than computer-readable media that can transmit, propagate, or transport a program for use by or in connection with an instruction execution apparatus, apparatus, or device.
  • Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for performing the operations of the present application may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional A procedural programming language—such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as an Internet service provider through Internet connection
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based means that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the modules involved in the embodiments described in this application can be implemented in software or hardware.
  • the modules described can also be provided in the processor.
  • this application also provides a computer-readable medium.
  • the computer-readable medium may be included in the electronic device described in the above embodiments; it may also exist independently without being assembled into the electronic device. middle.
  • the above computer-readable medium carries one or more programs.
  • the electronic device obtains the first aggregate image of the finished aggregate outside the discharge port of the cone crusher in real time, Use the instance segmentation model to segment the first aggregate image to obtain the first segmentation result; obtain the first aggregate parameters according to the first segmentation result, and the first aggregate parameters include the first average aggregate particle size, the first aggregate grade Match one or more of the curve area difference, the first average aggregate needle-likeness and the first average aggregate number; construct a cone crusher discharge opening size prediction model, and input the first aggregate parameters into the cone crusher
  • the discharging opening size prediction model outputs the cone crusher discharging opening size prediction value; compares the cone crusher discharging opening size prediction value with the cone crusher discharging opening size threshold, obtains adjustment instructions based on the comparison results and sends
  • the present invention is an intelligent adjustment method, device and readable medium for the size of the discharge port of a cone crusher.
  • the cone crusher By acquiring the image of the finished aggregate outside the discharge port of the cone crusher in real time and constructing a prediction model for the size of the discharge port of the cone crusher, the cone crusher can be obtained The predicted value of the machine discharge opening size is then compared with the cone crusher discharge opening size threshold, the cone crusher discharge opening size is adjusted according to the comparison result, and the aggregate particle size is changed through the adjusted cone crusher discharge opening size.
  • the invention is suitable for a variety of cone crushers, and can adjust the size of the discharge opening of the cone crusher efficiently, accurately and conveniently.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Food Science & Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Mathematics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Geometry (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Robotics (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mechanical Engineering (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Disintegrating Or Milling (AREA)

Abstract

一种圆锥破碎机排料口尺寸智能调整方法、装置及可读介质，通过实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对第一骨料图像进行分割，得到第一分割结果；根据第一分割结果获取第一骨料参数，第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；构建圆锥破碎机排料口尺寸预测模型，将第一骨料参数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值比较，根据比较结果调整圆锥破碎机排料口尺寸。

Description

圆锥破碎机排料口尺寸智能调整方法、装置及可读介质 技术领域
本发明涉及圆锥破碎机排料口调整领域，具体涉及一种圆锥破碎机排料口尺寸智能调整方法、装置及可读介质。
背景技术
随着建筑业的迅速发展，各种规格的石料种类随之增多，圆锥破碎机作为非常重要的设备之一，也是目前流行的破碎设备。常用于处理各种矿石的破碎加工环节，由于该设备产量高，性能稳定，使用寿命长等优点比较突出，因此市场上圆锥破碎机的应用较多。日常的操作中，影响圆锥破碎机的产量的因素之一就是排料口的调整，操作人员必须熟练掌握排料口的调整大小，才能保证顺利的生产，并且保证排料口产出的成品骨料的粒径满足要求。不同的圆锥破碎机排料口的尺寸所产出的成品骨料的粒径不同。
排料口的调整的传统方法是由观察员观察排料口附近的骨料粒径大小，判断排料口的开口大小，然后再手动进行排料口尺寸大小的调整。在此情况下，当耐磨衬板磨损较多时，骨料粒径的大小变化才肉眼可见，此时观察员观测到骨料粒径变化，已经存在较大的滞后性。另外一种方法是基于粗骨料粒径的检测方法，该方法需要先取样到粗骨料检测仪进行骨料粒径检测。此时取样再检测的离线检测速度慢，不能及时调整排料口的尺寸大小，且以上两种方法均需人工参与，效率低。
发明内容
针对上述提到的背景技术存在的问题。本申请的实施例的目的在于提出了一种圆锥破碎机排料口尺寸智能调整方法、装置及可读介质，来解决以上背景技术部分提到的技术问题。
第一方面，本申请的实施例提供了一种圆锥破碎机排料口尺寸智能调整方法，包括以下步骤：
S1，实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对第一骨料图像进行分割，得到第一分割结果；
S2，根据第一分割结果获取第一骨料参数，第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；
S3，构建圆锥破碎机排料口尺寸预测模型，将第一骨料参数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；
S4，将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；
S5，重复步骤S1-S4，直至圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
在具体的实施例中，步骤S3中的构建圆锥破碎机排料口尺寸预测模型，具体包括：
获取圆锥破碎机在不同排料口尺寸下的成品骨料的第二骨料图像；
采用实例分割模型对第二骨料图像进行分割，得到第二分割结果；
根据第二分割结果获取第二骨料参数，第二骨料参数包括第二平均骨料粒径、第二骨料级配曲线面积差、第二平均骨料针状度和第二平均骨料个数中的一种或多种；
将第二骨料参数作为特征变量并建立多元非线性回归模型：y i＝f(x i,β)+ε i；
其中，向量y i为不同的排料口尺寸，i＝1,2,...,n，向量x i＝(x i1，x i2，x i3，x i4)为不同排料口尺寸影响下的特征变量，x i1为第二平均骨料粒径，x i2为第二骨料级配曲线面积差，x i3为第二平均骨料针状度，x i4为第二平均骨料个数，β为参数向量，ε i为随机误差项；
将多元非线性回归模型转化为多元线性模型，并利用最小二乘法结合第二骨料参数计算多元线性模型中的各个回归系数，得到圆锥破碎机排料口尺寸预测模型。
在具体的实施例中，第一平均骨料粒径和第二平均骨料粒径为一段时间内骨料粒径的平均值。
在具体的实施例中，第一骨料级配曲线面积差和第二骨料级配曲线面积差为当前骨料级配曲线与标准骨料级配曲线的面积差，其中，标准骨料级配曲线为根 据排料口刚调整完成后的圆锥破碎机所生产的成品骨料的骨料图像计算出的一段时间内的平均骨料级配曲线，当前骨料级配曲线为根据当前时间之前的一段时间内的骨料图像计算出的平均骨料级配曲线。
在具体的实施例中，第一平均针状度和第二平均针状度为一段时间内的所有骨料的针状度的平均值，骨料的针状度为每个骨料粒径的长径与短径之比，第一平均骨料个数和第二平均骨料个数为一段时间内每张骨料图像所包含的骨料个数的平均值。
在具体的实施例中，定锥总成控制系统包括PLC、液压马达和定锥总成，通过PLC控制液压马达驱动定锥总成移动以改变圆锥破碎机排料口尺寸。
在具体的实施例中，实例分割模型为经训练的Mask-RCNN网络模型。
第二方面，本申请的实施例提供了一种圆锥破碎机排料口尺寸智能调整装置，包括：实例分割模块、参数计算模块、尺寸预测模块、尺寸调整模块、循环模块，以及与其适配的定锥总成控制系统；
实例分割模块，被配置为实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对第一骨料图像进行分割，得到第一分割结果；
参数计算模块，被配置为根据第一分割结果获取第一骨料参数，第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；
尺寸预测模块，被配置为构建圆锥破碎机排料口尺寸预测模型，将第一骨料参数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；
尺寸调整模块，被配置为将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；
循环模块，被配置为重复执行实例分割模块至尺寸调整模块，直至圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
第三方面，本申请的实施例提供了一种电子设备，包括一个或多个处理器；存储装置，用于存储一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如第一方面中任一实现方式描述的 方法。
第四方面，本申请的实施例提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如第一方面中任一实现方式描述的方法。
相比于现有技术，本发明具有以下有益效果：
(1)本发明可以实时获取圆锥破碎机排料口外的第一骨料图像，并采用实例分割模型对第一骨料图像进行分割，根据分割结果计算出第一骨料参数，通过第一骨料参数结合圆锥破碎机排料口尺寸预测模型对圆锥破碎机排料口尺寸大小进行预测，更进一步根据预测值调整圆锥破碎机排料口尺寸，实时性更强，调整的效率更高，不需要人工参与。
(2)本发明采用平均骨料粒径、骨料级配曲线面积差、平均骨料针状度和平均骨料个数作为特征参数构建圆锥破碎机排料口尺寸预测模型，因此得到的预测值更加准确，更加全面。
(3)本发明的圆锥破碎机排料口尺寸智能调整方法相对传统的圆锥破碎机排料口调整方法更加智能化，采用骨料粒径在线检测方法结合圆锥破碎机排料口智能调整装置，使得圆锥破碎机排料口的调整更高效、更精确、更方便。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简要介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请的一个实施例可以应用于其中的示例性装置架构图；
图2为本发明的实施例的圆锥破碎机排料口尺寸智能调整方法的流程示意图；
图3为本发明的实施例的圆锥破碎机排料口尺寸智能调整方法的实例分割模型的分割前后结果图；
图4为本发明的实施例的圆锥破碎机排料口尺寸智能调整方法的定锥总 成控制系统的示意图；
图5为本发明的实施例的圆锥破碎机排料口尺寸智能调整装置的示意图；
图6是适于用来实现本申请实施例的电子设备的计算机装置的结构示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
图1示出了可以应用本申请实施例的圆锥破碎机排料口尺寸智能调整方法或圆锥破碎机排料口尺寸智能调整装置的示例性装置架构100。
如图1所示，装置架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种应用，例如数据处理类应用、文件处理类应用等。
终端设备101、102、103可以是硬件，也可以是软件。当终端设备101、102、103为硬件时，可以是各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块(例如用来提供分布式服务的软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103上传的文件或数据进行处理的后台数据处理服务器。后台数据处理服务器可以对获取的文件或数据进行处理，生成处理结果。
需要说明的是，本申请实施例所提供的圆锥破碎机排料口尺寸智能调整方法可以由服务器105执行，也可以由终端设备101、102、103执行，相应地，圆锥破碎机排料口尺寸智能调整装置可以设置于服务器105中，也可以设置于终端设备101、102、103中。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。在所处理的数据不需要从远程获取的情况下，上述装置架构可以不包括网络，而只需服务器或终端设备。
图2示出了本申请的实施例提供的一种圆锥破碎机排料口尺寸智能调整方法，包括以下步骤：
S1，实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对第一骨料图像进行分割，得到第一分割结果。
在具体的实施例中，实例分割模型为经训练的Mask-RCNN网络模型，通过下载COCO训练集上的预训练权重，结合现场实际工况采集并标注的训练集对Mask-RCNN网络模型进行训练，获得经训练的Mask-RCNN网络模型，预测结果如图3所示，图3(a)为第一骨料图像，图3(b)为第一分割结果。具体地，Mask-RCNN网络模型为inception_v2，但是不限于此。
S2，根据第一分割结果获取第一骨料参数，第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种。
在具体的实施例中，第一骨料图像为实时采集到的圆锥破碎机排料口外成品骨料的骨料图像，通过实例分割模型进行实例分割，得到第一骨料图像上每个骨料的掩膜，根据每个骨料的掩膜计算骨料粒径、骨料的平均针状度和骨料级配曲线等骨料参数。第一平均骨料粒径为一段时间内骨料粒径的平均值。第一骨料级配曲线面积差为当前骨料级配曲线与标准骨料级配曲线的面积差，其中，标准骨料级配曲线为根据排料口刚调整完成后的圆锥破碎机所生产的成品骨料的骨料图像计算出的一段时间内的平均骨料级配曲线，当前骨料级配曲线为根据当前时间之前的一段时间内的骨料图像计算出的平均骨料级配曲线。第一平均针状度为一段时间内的所有骨料的针状度的平均值，骨料的针状度为每个骨料粒径的长径 与短径之比。第一平均骨料个数为一段时间内每张骨料图像所包含的骨料个数的平均值。在实时获取圆锥破碎机排料口外成品骨料的第一骨料图像之时，圆锥破碎机排料口实际尺寸未知，需要进行进一步预测得到。
S3，构建圆锥破碎机排料口尺寸预测模型，将第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值。
在具体的实施例中，步骤S3中的构建圆锥破碎机排料口尺寸预测模型，具体包括：
获取圆锥破碎机在不同排料口尺寸下的成品骨料的第二骨料图像；
采用实例分割模型对第二骨料图像进行分割，得到第二分割结果；
根据第二分割结果获取第二骨料参数，第二骨料参数包括第二平均骨料粒径、第二骨料级配曲线面积差、第二平均骨料针状度和第二平均骨料个数中的一种及多种；
将第二骨料参数作为特征变量并建立多元非线性回归模型：y i＝f(x i,β)+ε i；
其中，向量y i为不同的排料口尺寸，i＝1,2,…,n，向量x i＝(x i1,x i2,x i3,x i4)为不同排料口尺寸影响下的特征变量，x i1为第二平均骨料粒径，x i2为第二骨料级配曲线面积差，x i3为第二平均骨料针状度，x i4为第二平均骨料个数，β为参数向量，ε i为随机误差项；
将多元非线性回归模型转化为多元线性模型，并利用最小二乘法结合第二骨料参数计算多元线性模型中的各个回归系数，得到圆锥破碎机排料口尺寸预测模型。
在具体的实施例中，第二平均骨料粒径为一段时间内骨料粒径的平均值。第二骨料级配曲线面积差为当前骨料级配曲线与标准骨料级配曲线的面积差，其中，标准骨料级配曲线为根据排料口刚调整完成后的圆锥破碎机所生产的成品骨料的骨料图像计算出的一段时间内的平均骨料级配曲线，当前骨料级配曲线为根据当前时间之前的一段时间内的骨料图像计算出的平均骨料级配曲线。第二平均针状度为一段时间内的所有骨料的针状度的平均值，骨料的针状度为每个骨料粒径的长径与短径之比。第二平均骨料个数为一段时间内每张骨料图像所包含的骨料个数的平均值。此时在圆锥破碎机不同的排料口尺寸大小已知的情况下，计算得 到在不同排料口尺寸下的成品骨料的第二骨料图像，获取第二骨料参数，建立第二骨料参数与不同的排料口尺寸大小之间的多元非线性回归模型，再进一步转化为多元线性回归模型，最后通过最小二乘法对多元线性回归模型中的各个回归参数进行计算，最终得到圆锥破碎机排料口尺寸预测模型。
具体地，第二骨料图像为采集圆锥破碎机不同的排料口尺寸大小下的成品骨料的骨料图像，根据不同的排料口尺寸大小的圆锥破碎机所产出的成品骨料的粒径大小不同，因此建立线性关系。首先建立多元非线性回归模型，进一步将多元非线性回归模型转化为多元线性回归模型。该多元非线性回归模型是根据第二骨料图像所计算得到的第二平均骨料粒径、第二骨料级配曲线面积差、第二平均骨料针状度和第二平均骨料个数中的一种或多种所建立的，再进一步转换为多元线性模型，得到圆锥破碎机排料口尺寸预测模型。最终将实时采集到的第一骨料所对应的第一骨料参数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值。
多元非线性回归模型转换为多元线性模型的具体转换的过程如下：
假设现在只考虑第二平均骨料粒径、第二骨料级配曲线面积差、第二平均骨料针状度和第二平均骨料个数中的其中两个因素：
采用一个包含交互项的二元二次模型来描述排料口尺寸与两个因素的关系：
Figure PCTCN2022110878-appb-000001
其中，y为回归值，表示排料口尺寸，x 1，x 2为两个自变量，分别表示因素1和因素2。实验获得如下实验数据：
表1因素1和因素2与排料口尺寸的实验数据
数据序号 x1 x2 y
1 -99.24 1.75 30
2 100.5 1.73 30
3 -319.22 1.74 30
4 -79.64 1.78 31
5 212.49 1.77 31
6 199.24 1.75 31
7 123.5 1.77 32
8 309.22 1.78 32
9 279.64 1.77 32
将二元二次非线性回归模型转变成一个五元一次线性回归模型，由两个自变量变成五个自变量，数据格式如表2所示：
y＝a+b 1x 1+b 2x 2+b 3x 3+b 4x 4+b 5x 5；
表2五个自变量与排料口尺寸的实验数据
Figure PCTCN2022110878-appb-000002
通过Excel“数据分析”功能中的回归方式，得到五元一次线性回归模型为：
y＝-757.8-0.00006x 1+869.5x 2+0.001x 3+0.000003x 4-239.5x 5；
将其还原回去，即得二元二次回归模型为：
Figure PCTCN2022110878-appb-000003
S4，将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；
具体地，将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，若圆锥破碎机排料口尺寸预测值大于圆锥破碎机排料口尺寸阈值，则减小圆锥破碎机排料口尺寸，若圆锥破碎机排料口尺寸预测值小于圆锥破碎机排料口尺寸阈值，则增大圆锥破碎机排料口尺寸。圆锥破碎机排料口尺寸的调整是根据比较结果获取对应的调整指令，并将调整指令发送至定锥总成控制系统。定锥总成控制系统包括PLC、液压马达和定锥总成，通过PLC控制液压马达驱动定锥总成移动以改变圆锥破碎机排料口尺寸，定锥总成可以下降或上升。
参考图4，在圆锥破碎机排料口外的输送皮带2上安装一个摄像头1，该摄像头1用于采集输送皮带2上成品骨料3的骨料图像，并将采集的骨料图像传送到工控机4上，通过工控机4对采集的骨料图像进行实例分割，预测每个骨料的掩模，计算骨料等效粒径、骨料平均针状度、骨料级配曲线等特征，通过圆锥破碎机排料口尺寸预测模型预测排料口大小，若圆锥破碎机排料口尺寸预测值大于圆锥破碎机排料口尺寸阈值，发送排料口调节信息给PLC 5，PLC 5控制液压马达6使定锥总成7相对于动锥体8下降，以减小排料口大小，反之亦然，最终实现圆锥破碎机的排料口在线自动调整。
S5，重复步骤S1-S4，直至圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
具体地，每次调整圆锥破碎机排料口尺寸后，继续获得第一骨料参数，得到圆锥破碎机排料口尺寸预测值，并判断圆锥破碎机排料口尺寸预测值是否在圆锥破碎机排料口尺寸阈值范围内，若是，则停止调整，否则继续循环调整圆锥破碎机排料口尺寸，直至圆锥破碎机排料口尺寸在阈值范围内。通过实时检测骨料的粒径并结合圆锥破碎机排料口尺寸预测值，循环调整圆锥破碎机排料口尺寸，不仅实现骨料粒径的在线检测，并且能够更加高效、更加精确、更加方便地调整圆锥破碎机排料口尺寸，减少人力成本，实现自动化调整。
进一步参考图5，作为对上述各图所示方法的实现，本申请提供了一种圆锥破碎机排料口尺寸智能调整装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中，通过定锥总成控制系统调整圆锥破碎机排料口尺。
本申请实施例提供了一种圆锥破碎机排料口尺寸智能调整装置，包括：
实例分割模块1，被配置为实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对第一骨料图像进行分割，得到第一分割结果；
参数计算模块2，被配置为根据第一分割结果获取第一骨料参数，第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；
尺寸预测模块3，被配置为构建圆锥破碎机排料口尺寸预测模型，将第一骨料参数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；
尺寸调整模块4，被配置为将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；
循环模块5，被配置为重复执行实例分割模块51至尺寸调整模块54，直至圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
参考图4，与其适配的定锥总成控制系统，包括PLC、液压马达和定锥总成，通过PLC控制液压马达驱动定锥总成移动以改变圆锥破碎机排料口尺寸， 定锥总成可以下降或上升。
下面参考图6，其示出了适于用来实现本申请实施例的电子设备(例如图1所示的服务器或终端设备)的计算机装置600的结构示意图。图6示出的电子设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示，计算机装置600包括中央处理单元(CPU)601和图形处理器(GPU)602，其可以根据存储在只读存储器(ROM)603中的程序或者从存储部分609加载到随机访问存储器(RAM)604中的程序而执行各种适当的动作和处理。在RAM 604中，还存储有装置600操作所需的各种程序和数据。CPU 601、GPU602、ROM 603以及RAM 604通过总线605彼此相连。输入/输出(I/O)接口606也连接至总线605。
以下部件连接至I/O接口606：包括键盘、鼠标等的输入部分607；包括诸如、液晶显示器(LCD)等以及扬声器等的输出部分608；包括硬盘等的存储部分609；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分610。通信部分610经由诸如因特网的网络执行通信处理。驱动器611也可以根据需要连接至I/O接口606。可拆卸介质612，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器611上，以便于从其上读出的计算机程序根据需要被安装入存储部分609。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分610从网络上被下载和安装，和/或从可拆卸介质612被安装。在该计算机程序被中央处理单元(CPU)601和图形处理器(GPU)602执行时，执行本申请的方法中限定的上述功能。
需要说明的是，本申请所述的计算机可读介质可以是计算机可读信号介质或者计算机可读介质或者是上述两者的任意组合。计算机可读介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的装置、装置或器件，或者任意以上的组合。计算机可读介质的更具体的例子可以包括但 不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行装置、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行装置、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本申请各种实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能 而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的装置来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的模块也可以设置在处理器中。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对第一骨料图像进行分割，得到第一分割结果；根据第一分割结果获取第一骨料参数，第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；构建圆锥破碎机排料口尺寸预测模型，将第一骨料参数输入圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；将圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；重复以上步骤，直至圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
工业实用性
本发明一种圆锥破碎机排料口尺寸智能调整方法、装置及可读介质，通过实时获取圆锥破碎机排料口外成品骨料的图像、构建圆锥破碎机排料口尺寸预测模型，获取圆锥破碎机排料口尺寸预测值，再与圆锥破碎机排料口尺寸阈值比 较，根据比较结果调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径。本发明适用于多种圆锥破碎机，可以高效、精确、方便的调整圆锥破碎机排料口尺寸。

Claims (11)

  1. 一种圆锥破碎机排料口尺寸智能调整方法，其特征在于，包括以下步骤：
    S1，实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对所述第一骨料图像进行分割，得到第一分割结果；
    S2，根据所述第一分割结果获取第一骨料参数，所述第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；
    S3，构建圆锥破碎机排料口尺寸预测模型，将所述第一骨料参数输入所述圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；
    S4，将所述圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由所述定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；
    S5，重复步骤S1-S4，直至所述圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
  2. 根据权利要求1所述的圆锥破碎机排料口尺寸智能调整方法，其特征在于，所述步骤S3中的构建圆锥破碎机排料口尺寸预测模型，具体包括：
    获取所述圆锥破碎机在不同排料口尺寸下的成品骨料的第二骨料图像；
    采用实例分割模型对所述第二骨料图像进行分割，得到第二分割结果；
    根据所述第二分割结果获取第二骨料参数，所述第二骨料参数包括第二平均骨料粒径、第二骨料级配曲线面积差、第二平均骨料针状度和第二平均骨料个数中的一种或多种；
    将所述第二骨料参数作为特征变量并建立多元非线性回归模型：y i＝f(x i,β)+ε i；
    其中，向量y i为不同的排料口尺寸，i＝1,2,…,n，向量x i＝(x i1,x i2,x i3,x i4)为不同排料口尺寸影响下的特征变量，x i1为第二平均骨料粒径，x i2为第二骨料级配曲线面积差，x i3为第二平均骨料针状度，x i4为第二平均骨料个数，β为参数向量，ε i为随机误差项；
    将所述多元非线性回归模型转化为多元线性模型，并利用最小二乘法结合所 述第二骨料参数计算所述多元线性模型中的各个回归系数，得到圆锥破碎机排料口尺寸预测模型。
  3. 根据权利要求2所述的圆锥破碎机排料口尺寸智能调整方法，其特征在于，所述第一平均骨料粒径和第二平均骨料粒径为一段时间内骨料粒径的平均值。
  4. 根据权利要求2所述的圆锥破碎机排料口尺寸智能调整方法，其特征在于，所述第一骨料级配曲线面积差和第二骨料级配曲线面积差为当前骨料级配曲线与标准骨料级配曲线的面积差，其中，所述标准骨料级配曲线为根据排料口刚调整完成后的圆锥破碎机所生产的成品骨料的骨料图像计算出的一段时间内的平均骨料级配曲线，所述当前骨料级配曲线为根据当前时间之前的一段时间内的骨料图像计算出的平均骨料级配曲线。
  5. 根据权利要求2所述的圆锥破碎机排料口尺寸智能调整方法，其特征在于，所述第一平均针状度和第二平均针状度为一段时间内的所有骨料的针状度的平均值，所述骨料的针状度为每个骨料粒径的长径与短径之比，所述第一平均骨料个数和第二平均骨料个数为一段时间内每张骨料图像所包含的骨料个数的平均值。
  6. 根据权利要求1-5中任一项所述的圆锥破碎机排料口尺寸智能调整方法，其特征在于，所述定锥总成控制系统包括PLC、液压马达和定锥总成，通过所述PLC控制所述液压马达驱动所述定锥总成移动以改变圆锥破碎机排料口尺寸。
  7. 根据权利要求1-5中任一项所述的圆锥破碎机排料口尺寸智能调整方法，其特征在于，所述实例分割模型为经训练的Mask-RCNN网络模型。
  8. 一种圆锥破碎机排料口尺寸智能调整装置，其特征在于，包括：
    实例分割模块、参数计算模块、尺寸预测模块、尺寸调整模块、循环模块，以及与其适配的定锥总成控制系统；
    实例分割模块，被配置为实时获取圆锥破碎机排料口外成品骨料的第一骨料图像，采用实例分割模型对所述第一骨料图像进行分割，得到第一分割结果；
    参数计算模块，被配置为根据所述第一分割结果获取第一骨料参数，所述第一骨料参数包括第一平均骨料粒径、第一骨料级配曲线面积差、第一平均骨料针状度和第一平均骨料个数中的一种或多种；
    尺寸预测模块，被配置为构建圆锥破碎机排料口尺寸预测模型，将所述第一 骨料参数输入所述圆锥破碎机排料口尺寸预测模型，输出圆锥破碎机排料口尺寸预测值；
    尺寸调整模块，被配置为将所述圆锥破碎机排料口尺寸预测值与圆锥破碎机排料口尺寸阈值进行比较，根据比较结果获取调整指令并发送至定锥总成控制系统，由所述定锥总成控制系统调整圆锥破碎机排料口尺寸，通过调整后的圆锥破碎机排料口尺寸改变骨料的粒径；
    循环模块，被配置为重复执行实例分割模块至尺寸调整模块，直至所述圆锥破碎机排料口尺寸预测值在圆锥破碎机排料口尺寸阈值范围内。
  9. 根据权利要求8一种圆锥破碎机排料口尺寸智能调整装置，其特征在于，所述定锥总成控制系统包括PLC、液压马达和定锥总成，通过所述PLC控制所述液压马达驱动所述定锥总成相对动锥体移动以改变圆锥破碎机排料口尺寸。
  10. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一所述的方法。
  11. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-7中任一所述的方法。
PCT/CN2022/110878 2022-03-08 2022-08-08 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质 WO2023168899A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210218020.0A CN114768922A (zh) 2022-03-08 2022-03-08 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质
CN202210218020.0 2022-03-08

Publications (1)

Publication Number Publication Date
WO2023168899A1 true WO2023168899A1 (zh) 2023-09-14

Family

ID=82424188

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/110878 WO2023168899A1 (zh) 2022-03-08 2022-08-08 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质

Country Status (2)

Country Link
CN (1) CN114768922A (zh)
WO (1) WO2023168899A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114768922A (zh) * 2022-03-08 2022-07-22 福建南方路面机械股份有限公司 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质
CN115592819B (zh) * 2022-12-15 2023-03-17 福建南方路面机械股份有限公司 基于深度学习的搅拌站卸料口尺寸调整方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105478220A (zh) * 2016-01-19 2016-04-13 中国黄金集团内蒙古矿业有限公司 矿石破碎系统及破碎机的控制方法
CN107894379A (zh) * 2017-11-14 2018-04-10 沈阳聚德视频技术有限公司 一种基于智能视觉的高性能矿石粒度视觉检测系统
WO2020111370A1 (ko) * 2018-11-27 2020-06-04 삼영플랜트주식회사 골재 이미지 분리 시스템 및 방법
CN111375457A (zh) * 2020-04-22 2020-07-07 世邦工业科技集团股份有限公司 排矿通道的尺寸调节系统及其使用方法
CN111582161A (zh) * 2020-05-07 2020-08-25 中国矿业大学 一种基于断口特征判据的矿物解离系统
CN113553712A (zh) * 2021-07-22 2021-10-26 华侨大学 基于多元回归的粉末冶金混合材料配方建模及控制方法
CN114768922A (zh) * 2022-03-08 2022-07-22 福建南方路面机械股份有限公司 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105478220A (zh) * 2016-01-19 2016-04-13 中国黄金集团内蒙古矿业有限公司 矿石破碎系统及破碎机的控制方法
CN107894379A (zh) * 2017-11-14 2018-04-10 沈阳聚德视频技术有限公司 一种基于智能视觉的高性能矿石粒度视觉检测系统
WO2020111370A1 (ko) * 2018-11-27 2020-06-04 삼영플랜트주식회사 골재 이미지 분리 시스템 및 방법
CN111375457A (zh) * 2020-04-22 2020-07-07 世邦工业科技集团股份有限公司 排矿通道的尺寸调节系统及其使用方法
CN111582161A (zh) * 2020-05-07 2020-08-25 中国矿业大学 一种基于断口特征判据的矿物解离系统
CN113553712A (zh) * 2021-07-22 2021-10-26 华侨大学 基于多元回归的粉末冶金混合材料配方建模及控制方法
CN114768922A (zh) * 2022-03-08 2022-07-22 福建南方路面机械股份有限公司 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
BAO, JINZHONG: "Research and Application of Mathematical Model of Product Grain-size Feature of Secondary Crusher", MODERN MINING, CN, no. 1, 31 January 2005 (2005-01-31), CN, pages 28 - 30, XP009548908, ISSN: 1674-6082 *

Also Published As

Publication number Publication date
CN114768922A (zh) 2022-07-22

Similar Documents

Publication Publication Date Title
WO2023168899A1 (zh) 圆锥破碎机排料口尺寸智能调整方法、装置及可读介质
WO2023142262A1 (zh) 基于深度学习的混凝土配方调整方法、装置及可读介质
CN110880036B (zh) 神经网络压缩方法、装置、计算机设备及存储介质
CN117218118B (zh) 基于图像序列的坍落度监测方法、装置及可读介质
US20210049414A1 (en) Deep graph de-noise by differentiable ranking
CN110009014A (zh) 一种融合相关系数与互信息的特征选择方法
CN114496083A (zh) 细胞类型确定方法、装置、设备以及存储介质
Kwasniewska et al. Deep learning optimization for edge devices: Analysis of training quantization parameters
CN117195083A (zh) 基于电流曲线的坍落度预测方法、装置及可读介质
CN114565838A (zh) 一种基于渣土图像的配方调节控制方法、装置及可读介质
CN114067415A (zh) 回归模型的训练方法、对象评估方法、装置、设备和介质
CN117422709B (zh) 基于rgb图像和深度图像的坍落度预测方法及装置
CN116689133B (zh) 基于深度学习的再生骨料质量控制方法、装置及可读介质
CN115860147A (zh) 基于非平衡集成学习的报关单预判模型训练方法及装置
CN112598259A (zh) 产能测算方法、装置及计算机可读存储介质
CN112003887A (zh) 一种面向工业互联网时序数据预测的云端-边缘协同深度学习装置
Lu et al. Deep correlation and precise prediction between static features of froth images and clean coal ash content in coal flotation: An investigation based on deep learning and maximum likelihood estimation
CN116678885B (zh) 基于深度学习的水洗粗骨料含泥检测控制方法及装置
CN115878783B (zh) 文本处理方法、深度学习模型训练方法以及样本生成方法
CN114936310B (zh) 图表显示方法、装置、电子设备和计算机可读介质
CN113361712B (zh) 特征确定模型的训练方法、语义分析方法、装置及电子设备
CN115592819B (zh) 基于深度学习的搅拌站卸料口尺寸调整方法及装置
CN117195163A (zh) 基于混凝土配方的坍落度预测方法、装置及可读介质
WO2023226064A1 (zh) 椭圆定位数据处理方法、装置、设备、介质和程序产品
Hallatschek et al. Collective fluctuations in models of adaptation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22930528

Country of ref document: EP

Kind code of ref document: A1