CN111975438A - Machine tool emergency stop method and device based on distance sensor and machine vision - Google Patents

Abstract

The invention discloses a machine tool emergency stop method based on a distance sensor and machine vision, comprising the following steps: before starting the S1 processing, use a machine learning algorithm to train and learn different types of foreign object image data, and obtain a three-jaw chuck when there is no foreign object. The edge points are collected to obtain the center position of the three-jaw chuck; after the S2 processing starts, the current distance measured by the distance sensor and the image around the three-jaw chuck are obtained; S3 compares the current distance and the distance threshold, and judges that the three-jaw chuck is safe Whether there is a foreign object within the distance, if there is a foreign object within the safe distance, enter S5, and if there is no foreign object within the safe distance, enter S4; S4 uses machine vision algorithms to analyze the image to determine whether there is an emergency stop within the safe distance of the three-jaw chuck If there is a foreign object belonging to the emergency stop category within the safety distance, it will enter S5. If there is no foreign object belonging to the emergency stop category within the safety distance, it will enter S2; the S5 machine will immediately alarm and stop working.

Description

Machine tool emergency stop method and device based on distance sensor and machine vision

technical field

The invention relates to the technical field of machine tool safety monitoring, in particular to a machine tool emergency stop method and device based on distance sensors and machine vision.

Background technique

In the production practice of machine tools, safety accidents are caused by improper operation, especially in the three-jaw chuck part of the machine tool. The three-jaw chuck rotates at a high speed, and the operator's hand or hair is close to the high-speed rotating three-jaw chuck due to negligence, and the whole hand or head is strangled by the high-speed rotating three-jaw chuck, causing a major safety accident. When a safety accident occurs, the injured person cannot stop the machine, and when the surrounding people hear the cry for help and press the emergency stop switch, casualties are inevitable.

The existing machine tool braking devices include: a motor braking device when the molybdenum wire of the wire cutting machine tool is broken. The wire cutting machine tool molybdenum wire broken wire detection circuit is composed of a current transformer, a switch tube and a time base circuit. A phase line of the power supply passes through the primary coil of the current transformer, the secondary coil of the current transformer is connected to the rectifier voltage regulator circuit, the rectifier voltage regulator circuit is connected to the switch tube and the time base circuit, and the output end of the time base circuit is connected to the input of the single-chip microcomputer The output end of the single-chip microcomputer is connected to the motor braking circuit. The motor braking circuit includes a switch tube and a relay. The normally open contact of the relay is connected in series with a set of DC power supply and a set of phase lines of the motor AC power supply, which is beneficial The effect is to detect the running current of the molybdenum wire running motor through the molybdenum wire broken detection circuit, and start the molybdenum wire running motor braking circuit in real time when the molybdenum wire is broken, quickly brake the rotation of the motor and protect the molybdenum wire from being affected; An emergency braking device for machine tool equipment, a DC power supply is connected in series on the normally open contact of the machine tool equipment emergency stop contactor, the DC power supply is composed of a transformer and a rectifier circuit, and both ends of the primary coil of the transformer are respectively connected to the motor The two-phase incoming line of the power supply and the upper, both ends of the secondary coil of the transformer are respectively connected to the input contacts of the rectifier circuit. When the emergency stop button is pressed, after the two stator windings of the motor are disconnected from the AC power supply, the two stator windings are immediately connected. It forms a loop with the DC power supply. The DC power supply will generate a static magnetic field in the stator winding. The rotor rotates in this magnetic field to generate an induced electromotive force. The rotor current and the static magnetic field generate an opposite torque. The power produces resistance, forcing the rotor of the motor to stop rotating quickly, and the braking force of the rotor brakes the inertial rotation force of the electromechanical device, thereby completing the entire braking process.

The braking process of the above-mentioned machine tools is controlled by the detection of the internal current to control the motor braking circuit. At present, the existing early warning functions in the machine tools are used to detect whether the placement position of the tool is offset and whether the parts in the machine tool need maintenance, etc. , it cannot solve the problem of accurately controlling the emergency stop of the machine tool in real time according to the surrounding conditions of the three-jaw chuck to avoid safety accidents.

SUMMARY OF THE INVENTION

In view of the above defects or improvement requirements of the prior art, the present invention provides a method and device for emergency stop of a machine tool based on ultrasonic distance sensors and vision. The distance sensors distributed on both sides of the three-jaw chuck are used to detect the current distance, and combined with image analysis Whether there is a foreign object belonging to the emergency stop category within the safety distance of the three-jaw chuck, if it is detected that the current distance of the distance sensor is less than the distance threshold or there is a foreign object belonging to the emergency stop category within the safety distance of the three-jaw chuck, an alarm will be sent to the alarm module. command and send a stop command to the stop module, which solves the problem that the emergency stop of the machine tool cannot be accurately controlled in real time according to the surrounding conditions of the three-jaw chuck to avoid safety accidents.

In order to achieve the above object, the present invention adopts the following technical solutions:

A machine tool emergency stop method based on distance sensor and machine vision, comprising the following steps:

S1: before processing begins, utilize machine learning algorithm to carry out training learning to different types of foreign body image data and obtain the three-jaw chuck edge point set {C _i } when there is no foreign body to obtain the center position C ₀ of the three-jaw chuck;

(C_0x,C_0y)表示三爪卡盘中心位置C₀的位置坐标，(C_ix,C_iy)表示三爪卡盘边缘点集合中单个点C_i的位置坐标，m表示三爪卡盘边缘点的总个数；in

(C _0x , C _0y ) represents the position coordinates of the center position C ₀ of the three-jaw chuck, (C _ix , C _iy ) represents the position coordinates of a single point C _i in the set of edge points of the three-jaw chuck, and m represents the three-jaw chuck the total number of edge points;

S2: After the processing starts, obtain the current distance _h1 measured by the distance sensor and the image around the three-jaw chuck;

S3: Comparing the current distance h ₁ with the distance threshold H ₀ , it is judged whether there is a foreign object within the safety distance of the three-jaw chuck, if there is a foreign object within the safety distance, enter S5, and if there is no foreign object within the safety distance, enter S4;

S4: Use the machine vision algorithm to analyze the image, and judge whether there is a foreign object in the emergency stop category within the safety distance of the three-jaw chuck. Stop the foreign body in the category and enter S2;

S5: The machine tool immediately alarms and stops working.

Further, step S4 includes the following steps:

S41: using a machine vision algorithm to read the abnormal parameter threshold D ₀ , and preprocessing the images around the three-jaw chuck;

S42: Use the difference value between the current image and the foreign-object-free image to determine whether there is a foreign body, if no foreign body is detected, then execute S2; if the foreign body is detected, execute S43;

S43: Use the machine learning model trained in step S1 to identify the foreign object category, if the foreign object category does not belong to the emergency stop category, execute S2, and if the foreign object category belongs to the emergency stop category, execute S44;

S44: use the Sobel operator or the Canny operator to perform image edge detection, obtain the current image edge contour to form the edge point set {G _j }, and remove the three-jaw chuck edge point set {C _i } to calculate the foreign object edge point set {G _k }, where {G _j }={C _i }+{G _k };

S45: Calculate the distance between the center position C ₀ of the three-jaw chuck and the set of foreign object edge points {G _k } to determine whether there is a foreign object within the safety distance of the three-jaw chuck, and this value is determined by the Euclidean distance between the two:

Where (G _kx , G _ky ) represents the position coordinates of a single point G _k in the foreign object edge point set, k∈[1,n], n represents the total number of foreign object edge points;

S46: By comparing the Euclidean distance D _k with the threshold D ₀ parameter, it is judged whether there is a foreign object within the safety distance of the three-jaw chuck, if D _k <D ₀ , there is a foreign object within the safety distance and perform S5, if D _k ≥ D ₀ and k<n, there is no foreign matter entering S45 within the safety distance, and if D _k ≥ D ₀ and k=n, there is no foreign matter entering S2 within the safety distance.

Further, the preprocessing in step S43 includes grayscale conversion, noise reduction and enhancement.

Further, the emergency stop category in the step S4 includes hair and fingers.

Further, the machine learning algorithm is a BP neural network, an RBF neural network, a deep learning algorithm or other related algorithms.

The present invention also provides a machine tool emergency stop device based on distance sensors and machine vision, comprising a main control module, a machine vision analysis and processing server, and an image acquisition module, an alarm module, a shutdown module and a machine vision analysis and processing server connected to the machine vision analysis and processing server. distance sensor;

Among them, the image acquisition module is arranged directly opposite the three-jaw chuck of the machine tool, and is used to collect images around the three-jaw chuck and send it to the machine vision analysis and processing server;

Alarm module: used to send alarm information after receiving the alarm command;

Stop module: used to stop the machine tool after receiving the stop command;

The distance sensor is arranged just above the three-jaw chuck and on both sides of the three-jaw chuck, and is used to measure the distance between the distance sensor and the nearest obstacle, and send the result to the main control module;

The machine vision analysis and processing server includes:

Preprocessing module: used to perform grayscale conversion, noise reduction and enhancement processing on the collected images around the three-jaw chuck;

Foreign body detection module: used to detect whether there is foreign body around the three-jaw chuck, and send the result to the main control module;

Type identification module: used to identify the type of foreign objects and send the result to the main control module;

Safety detection module: By calculating the Euclidean distance between the center position of the three-jaw chuck and the current set of foreign object edge points, and comparing it with the abnormal parameter threshold, it can determine whether there is a foreign object within the safety distance around the three-jaw chuck, and send the result to the main control. Module; the center position of the three-jaw chuck is determined by the mean value of the edge points before the machine tool starts processing and when there is no foreign matter around the three-jaw chuck, and the current foreign object edge point set excludes the edge of the three-jaw chuck from the current image edge point set point set is determined;

Main control module: It is used to connect each module and receive the output results of the foreign object detection module, type identification module, safety detection module and distance sensor; if the current distance of the distance sensor is detected to be less than the distance threshold or the safety distance of the three-jaw chuck exists For foreign objects belonging to the category of emergency stop, an alarm command is issued to the alarm module, and a stop command is issued to the shutdown module.

Further, the foreign object detection module judges whether there is a foreign object by the difference value between the current image and the image without foreign object.

Further, the type identification module identifies the foreign object type through a machine learning model formed by BP neural network, RBF neural network, deep learning algorithm or other related algorithms, and uses Canny operator or Sobel operator to obtain the edge of the current image contour.

The beneficial effects of the present invention are:

The distance sensors distributed on both sides of the three-jaw chuck are used to detect the current distance, and the machine vision algorithm is used to analyze whether there is hair or hands within the safe distance of the three-jaw chuck. If there is a foreign object belonging to the category of emergency stop within the safe distance of the disk, an alarm command will be issued to the alarm module, and a stop command will be issued to the shutdown module to realize the safe production of the machine tool. At the same time, the machine vision algorithm can judge whether the foreign object belongs to the category of emergency stop to avoid The frequent emergency stop of the machine tool is avoided, and the production efficiency is improved on the premise of ensuring safe production.

Description of drawings

1 is a structural diagram of a machine tool emergency stop device body in an embodiment of the present invention;

2 is a schematic flowchart of a method for emergency stop of a machine tool in an embodiment of the present invention;

3 is a schematic flowchart of a machine vision algorithm in an embodiment of the present invention;

4 is a structural diagram of a control system in an embodiment of the present invention;

The accompanying drawings are identified as: 1-three-jaw chuck, 2-distance sensor, 3-image acquisition module.

Detailed ways

The embodiments of the present invention are described below through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the drawings provided in the following embodiments are only used to illustrate the basic idea of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

Among them, the accompanying drawings are only used for exemplary description, and represent only schematic diagrams, not physical drawings, and should not be construed as limitations of the present invention; in order to better illustrate the embodiments of the present invention, some parts of the accompanying drawings will be omitted, The enlargement or reduction does not represent the size of the actual product; it is understandable to those skilled in the art that some well-known structures and their descriptions in the accompanying drawings may be omitted.

The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms “upper”, “lower”, “left” and “right” , "front", "rear" and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must be It has a specific orientation, is constructed and operated in a specific orientation, so the terms describing the positional relationship in the accompanying drawings are only used for exemplary illustration, and should not be construed as a limitation of the present invention. situation to understand the specific meaning of the above terms. . It should be understood that the present invention is not limited to the above-mentioned specific embodiments, and those skilled in the art can make various variations or modifications within the scope of the claims, which do not affect the essential content of the present invention.

As shown in FIG. 2 , an embodiment of the present invention provides a method for emergency stop of a machine tool based on a distance sensor and machine vision, including the following steps:

S1: before processing begins, utilize machine learning algorithm to carry out training learning to different types of foreign body image data and obtain the three-jaw chuck edge point set {C _i } when there is no foreign body to obtain the center position C ₀ of the three-jaw chuck;

(C_0x,C_0y)表示三爪卡盘中心位置C₀的位置坐标，(C_ix,C_iy)表示三爪卡盘边缘点集合中单个点C_i的位置坐标，m表示三爪卡盘边缘点的总个数；in

(C _0x , C _0y ) represents the position coordinates of the center position C ₀ of the three-jaw chuck, (C _ix , C _iy ) represents the position coordinates of a single point C _i in the set of edge points of the three-jaw chuck, and m represents the three-jaw chuck the total number of edge points;

S2: After the processing starts, obtain the current distance _h1 measured by the distance sensor and the image around the three-jaw chuck;

S3: Comparing the current distance h ₁ with the distance threshold H ₀ , it is judged whether there is a foreign object within the safety distance of the three-jaw chuck, if there is a foreign object within the safety distance, enter S5, and if there is no foreign object within the safety distance, enter S4;

S4: Use the machine vision algorithm to analyze the image, and judge whether there is a foreign object in the emergency stop category within the safety distance of the three-jaw chuck. Stop the foreign body in the category and enter S2;

S5: The machine tool immediately alarms and stops working.

In step S1, the machine learning algorithm is a BP neural network, an RBF neural network, a deep learning algorithm or other related algorithms, and in step S1, a Sobel operator or a Canny operator is used to obtain the set of three-jaw chuck edge points {C _i } when there is no foreign matter; The emergency stop category in step S4 includes hair and hands.

As shown in Figure 3, step S4 includes the following steps:

S41: using a machine vision algorithm to read the abnormal parameter threshold D ₀ , and preprocessing the images around the three-jaw chuck;

S42: Use the difference value between the current image and the image without foreign matter to determine whether there is a foreign matter, if no foreign matter is detected, execute S2; if the foreign matter is detected, execute S43;

S43: Use the machine learning model trained in step S1 to identify the foreign object category, if the foreign object category does not belong to the emergency stop category, execute S2, and if the foreign object category belongs to the emergency stop category, execute S44;

S44: use the Sobel operator or the Canny operator to perform image edge detection, obtain the current image edge contour to form the edge point set {G _j }, and remove the three-jaw chuck edge point set {C _i } to calculate the foreign object edge point set {G _k }, where {G _j }={C _i }+{G _k };

S45: Calculate the distance between the center position C ₀ of the three-jaw chuck and the set of foreign object edge points {G _k } to determine whether there is a foreign object within the safety distance of the three-jaw chuck, and this value is determined by the Euclidean distance between the two:

Where (G _kx , G _ky ) represents the position coordinates of a single point G _k in the foreign object edge point set, k∈[1,n], n represents the total number of foreign object edge points;

S46: By comparing the Euclidean distance D _k with the threshold D ₀ parameter, it is judged whether there is a foreign object within the safety distance of the three-jaw chuck, if D _k <D ₀ , there is a foreign object within the safety distance and perform S5, if D _k ≥ D ₀ and k<n, there is no foreign matter entering S45 within the safety distance, and if D _k ≥ D ₀ and k=n, there is no foreign matter entering S2 within the safety distance.

The preprocessing in step S43 includes grayscale conversion, noise reduction and enhancement.

As shown in FIG. 1 and FIG. 4 , based on the above-mentioned machine tool emergency stop method, an embodiment of the present invention further provides a machine tool emergency stop device based on a distance sensor and machine vision, including a main control module, a machine vision analysis and processing server, and an image acquisition module 3, an alarm module, a shutdown module and a distance sensor 2 connected to the machine vision analysis and processing server;

Wherein, the image acquisition module 3 is arranged directly opposite the three-jaw chuck 1 of the machine tool, and is used to collect images around the three-jaw chuck 1 and send it to the machine vision analysis and processing server;

Alarm module: used to send alarm information after receiving the alarm command;

Stop module: used to stop the machine tool after receiving the stop command;

The distance sensor 2 is arranged just above the three-jaw chuck 1 and on both sides of the three-jaw chuck 1, and is used to measure the distance between the distance sensor 2 and the nearest obstacle, and send the result to the main control module;

The machine vision analysis and processing server includes:

Preprocessing module: used to perform grayscale conversion, noise reduction and enhancement processing on the collected images around the three-jaw chuck 1;

Foreign object detection module: used to detect whether there is foreign object around the three-jaw chuck 1, and send the result to the main control module;

Type identification module: used to identify the type of foreign objects and send the result to the main control module;

Safety detection module: By calculating the Euclidean distance between the center position of the three-jaw chuck 1 and the current set of foreign object edge points, and comparing it with the abnormal parameter threshold, it determines whether there is a foreign object within the safety distance around the three-jaw chuck 1, and sends the result to Main control module; the center position of the three-jaw chuck 1 is determined by the average value of the edge points before the machine tool starts processing and when there is no foreign matter around the three-jaw chuck 1, and the current foreign object edge point set is eliminated from the current image edge point set. The set of edge points of jaw chuck 1 is determined;

Main control module: used to connect each module and receive the output results of the foreign object detection module, type identification module, safety detection module and distance sensor 2; if it is detected that the current distance of the distance sensor 2 is less than the distance threshold or the three-jaw chuck 1 is safe If there is a foreign object belonging to the category of emergency stop within the distance, an alarm command will be sent to the alarm module, and a stop command will be sent to the stop module.

The foreign object detection module judges whether there is a foreign object through the difference value between the current image and the foreign object-free image.

The type identification module identifies the foreign object type through a machine learning model formed by BP neural network, RBF neural network, deep learning algorithm or other related algorithms, and uses Canny operator or Sobel operator to obtain the edge of the current image contour.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent substitutions are made without departing from the spirit and scope of the technical solution, and they should all be included in the scope of the claims of the present invention.

Claims (8)

1. a machine tool emergency stop method based on distance sensor and machine vision, is characterized in that, comprises the following steps: S1: before processing begins, utilize machine learning algorithm to carry out training learning to different types of foreign body image data and obtain the three-jaw chuck edge point set {C _i } when there is no foreign body to obtain the center position C ₀ of the three-jaw chuck; in

(C _0x , C _0y ) represents the position coordinates of the center position C ₀ of the three-jaw chuck, (C _ix , C _iy ) represents the position coordinates of a single point C _i in the set of edge points of the three-jaw chuck, and m represents the three-jaw chuck the total number of edge points; S2: After the processing starts, obtain the current distance _h1 measured by the distance sensor and the image around the three-jaw chuck; S3: Comparing the current distance h ₁ with the distance threshold H ₀ , it is judged whether there is a foreign object within the safety distance of the three-jaw chuck, if there is a foreign object within the safety distance, enter S5, and if there is no foreign object within the safety distance, enter S4; S4: Use the machine vision algorithm to analyze the image, and judge whether there is a foreign object belonging to the emergency stop category within the safety distance of the three-jaw chuck. If there is a foreign object belonging to the emergency stop category within the safety distance, enter S5. Foreign objects belonging to the emergency stop category enter S2; S5: The machine tool immediately alarms and stops working. 2. the machine tool emergency stop method based on distance sensor and machine vision according to claim 1, is characterized in that, step S4 comprises the following steps: S41: using a machine vision algorithm to read the abnormal parameter threshold D ₀ , and preprocessing the images around the three-jaw chuck; S42: Use the difference value between the current image and the image without foreign matter to determine whether there is a foreign matter, if no foreign matter is detected, execute S2; if the foreign matter is detected, execute S43; S43: Use the machine learning model trained in step S1 to identify the foreign object category, if the foreign object category does not belong to the emergency stop category, execute S2, and if the foreign object category belongs to the emergency stop category, execute S44; S44: use the Sobel operator or the Canny operator to perform image edge detection, obtain the current image edge contour to form the edge point set {G _j }, and remove the three-jaw chuck edge point set {C _i } to calculate the foreign object edge point set {G _k }, where {G _j }={C _i }+{G _k }; S45: Calculate the distance between the center position C ₀ of the three-jaw chuck and the set of foreign object edge points {G _k } to determine whether there is a foreign object within the safety distance of the three-jaw chuck, and this value is determined by the Euclidean distance between the two:

Where (G _kx , G _ky ) represents the position coordinates of a single point G _k in the foreign object edge point set, k∈[1,n], n represents the total number of foreign object edge points; S46: By comparing the Euclidean distance D _k with the threshold D ₀ parameter, it is judged whether there is a foreign object within the safety distance of the three-jaw chuck, if D _k < D ₀ , there is a foreign object within the safety distance and perform S5, if D _k ≥ D ₀ and k<n, there is no foreign matter entering S45 within the safety distance, and if D _k ≥ D ₀ and k=n, there is no foreign matter entering S2 within the safety distance. 3 . The method for emergency stop of a machine tool based on a distance sensor and machine vision according to claim 2 , wherein the preprocessing in the step S43 includes grayscale conversion, noise reduction and enhancement. 4 . 4 . The method for emergency stop of a machine tool based on a distance sensor and machine vision according to claim 1 , wherein the emergency stop category in the step S4 includes hair and hands. 5 . 5. The machine tool emergency stop method based on distance sensor and machine vision according to claim 1, wherein the machine learning algorithm is BP neural network, RBF neural network, deep learning algorithm or other related algorithms. 6. A machine tool emergency stop device based on any one of claims 1-5, characterized in that, comprising a main control module, a machine vision analysis and processing server, and an image acquisition module connected with the machine vision analysis and processing server , alarm module, shutdown module and distance sensor; Among them, the image acquisition module is arranged directly opposite the three-jaw chuck of the machine tool, and is used to collect images around the three-jaw chuck and send it to the machine vision analysis and processing server; Alarm module: used to send alarm information after receiving the alarm command; Stop module: used to stop the machine tool after receiving the stop command; The distance sensor is arranged directly above the three-jaw chuck and close to the operator side, used to measure the distance between the distance sensor and the nearest obstacle, and send the result to the main control module; The machine vision analysis and processing server includes: Preprocessing module: used to perform grayscale conversion, noise reduction and enhancement processing on the collected images around the three-jaw chuck; Foreign body detection module: used to detect whether there is foreign body around the three-jaw chuck, and send the result to the main control module; Type identification module: used to identify the type of foreign objects and send the result to the main control module; Safety detection module: By calculating the Euclidean distance between the center position of the three-jaw chuck and the current set of foreign object edge points, and comparing it with the abnormal parameter threshold, it can determine whether there is a foreign object within the safety distance around the three-jaw chuck, and send the result to the main control. Module; the center position of the three-jaw chuck is determined by the mean value of the edge points before the machine tool starts processing and when there is no foreign matter around the three-jaw chuck, and the current foreign object edge point set excludes the edge of the three-jaw chuck from the current image edge point set point set is determined; Main control module: It is used to connect each module and receive the output results of the foreign object detection module, type identification module, safety detection module and distance sensor; if the current distance of the distance sensor is detected to be less than the distance threshold or the safety distance of the three-jaw chuck exists For foreign objects belonging to the category of emergency stop, an alarm command is issued to the alarm module, and a stop command is issued to the shutdown module. 7 . The machine tool emergency stop device according to claim 6 , wherein the foreign object detection module judges whether there is a foreign object by a difference value between the current image and the image without foreign objects. 8 . 8. The machine tool emergency stop device according to claim 6 is characterized in that, the type identification module identifies the foreign object type through the machine learning model formed by BP neural network, RBF neural network, deep learning algorithm or other related algorithms, and uses The Canny operator or the Sobel operator obtains the edge point set of the current image contour.

Images