CN115303950A - A driving automatic feeding system with AI recognition - Google Patents

Abstract

The invention belongs to the technical field of electromechanical automation devices, in particular to a driving automatic feeding system with AI recognition. Aiming at the problem of low safety performance of the existing crane, the following scheme is proposed, which includes a crane, an anti-sway control system, PLC system, low-voltage distribution system, host computer system and zero point mechanism; the present invention adds an anti-sway control system; periodically forcibly returns to zero to calibrate the initial zero point; adopts AI recognition technology to increase safety; Positioning with spatial coordinates, and programming to realize the automatic operation of the crane, reducing the labor intensity of workers; realizing the three-dimensional real-time display of the material pit and the crane, intuitive and clear, and many other means, greatly improving the automatic operation level of the crane, which has obvious effects on enterprises. economic value.

Description

A driving automatic feeding system with AI recognition

technical field

The invention relates to the technical field of electromechanical automation devices, in particular to an automatic driving feeding system with AI recognition.

Background technique

Cranes are widely used in the field of waste incineration. As a general-purpose equipment that can improve work efficiency, it has been widely used for a long time. However, the crane is managed according to special equipment, and the operation also requires qualified operators. Due to the inconsistent operation level of the workers, there are potential safety hazards and safety accidents are extremely prone to occur. If the automatic control level of the crane can be improved and the workers can be gradually replaced, it will not only improve the operating efficiency, reduce the cost of the enterprise, but also make it safer and more reliable.

Contents of the invention

A driving automatic feeding system with AI recognition proposed by the present invention solves the problems raised in the above-mentioned background technology.

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

A driving automatic loading system with AI recognition, including crane, anti-sway control system, PLC system, low-voltage distribution system, host computer system and zero-point mechanism, in which:

The anti-swing control system includes sensors, encoders, limit switches and radars;

The low-voltage distribution system includes an air switch, a contactor and a frequency converter;

The PLC system includes a power supply, a CPU, an IO module, a relay and a safety barrier;

The upper computer system includes an industrial computer and software;

Preferably, the zero point mechanism includes a crossbeam and a crane, on which a track for the movement of the crane is installed, on the crossbeam a process tank is opened, and a photoelectric switch is installed in the process tank.

Preferably, the limit switch is electrically connected to the encoder, the sensor is electrically connected to the encoder, and the sensor is electrically connected to the radar.

Preferably, the frequency converter is electrically connected to the contactor, the contactor is electrically connected to the air switch, and the air switch is electrically connected to the safety barrier.

Preferably, the power supply is electrically connected to the CPU, the CPU is electrically connected to the IO module, the IO module is electrically connected to the relay, and the relay is electrically connected to the safety barrier.

Preferably, the industrial computer is electrically connected to the software, the software is electrically connected to the frequency converter, and the frequency converter is electrically connected to the limit switch.

Preferably, AI recognition cameras are installed on the local operation console and the central control operation console in the crane.

Preferably, the following steps are included:

S101: A detection probe is installed at the bottom of the crane for the material level;

S102: In the standby state, monitor the material level elevation in the previous grabbing zone in real time through the detection probe, and comprehensively calculate the average material level elevation in the zone after eliminating bad values;

S103: Through the radar to accurately detect the material level elevation in the zone, realize the three-dimensional modeling of the material accumulation situation, as the data support for the automatic loading of the vehicle, and display it on the screen through the three-dimensional graphics, as the staff monitor the actual situation.

Preferably, the following steps are included:

S201: Set up several partitions in the storage pit, and the operator makes partitions;

S202: After the loading instruction is given, the crane automatically executes the instruction, automatically moves to the designated partition, and puts down the grab bucket;

S302: Lift up after grabbing, automatically move to the discharge hopper, put down the grab, open the grab to drop, after an action is completed, it will automatically return to the original position and enter a new round of standby state

Beneficial effect:

1. The present invention adds an anti-sway control system, which can automatically eliminate the sway of the hanging objects during operation, and can complete the transfer of the hanging objects faster, especially the automatic crane with positioning function, which can make Crane operation becomes more efficient and safer.

2. In the present invention, the crown crane is set to automatically return to zero, and it runs regularly to the design zero point, and compares it with the absolute position generated by the encoder to confirm whether there is an offset. If the offset exceeds the design range, it will automatically increase or decrease the offset. Return to zero to solve the current problem of the deviation of the positioning distance of the cart.

3. In the present invention, the on-site operation console and the central control console are equipped with AI recognition cameras, which can not only identify whether the operator has the qualification to operate the crane, but also give the operation authority, and can not operate without the operation authority, and automatically switch the operation authority at the same time. The local operation authority is the highest level; in addition, at night, it can also identify whether the operating workers are awake and whether there are potential safety hazards, and give timely reminders.

4. The crane in the present invention adds a fully automatic feeding function. Several partitions are set in the storage pit, and the operator specifies the partitions. After giving the loading instruction, the crane automatically executes the instruction, automatically moves to the designated partition, and puts down the grab Bucket, lift after grabbing material, automatically move to the discharge hopper, put down the grab bucket, open the grab bucket to drop material, after an action is completed, it will automatically return to the original position and enter a new round of standby state.

5. In the present invention, a material level detection probe is installed at the bottom of the crane, and in the standby state, real-time monitoring is carried out on the material level elevation in the previous grabbing partition. After eliminating bad values, the average material level elevation in the partition is comprehensively calculated, and at the same time Real-time display in the 3D modeling system, intuitive and clear.

Description of drawings

Fig. 1 is a structural schematic diagram of a driving automatic feeding system with AI recognition proposed by the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

Referring to Figure 1, a driving automatic loading system with AI recognition includes a crane, an anti-swing control system, a PLC system, a low-voltage distribution system, a host computer system and a zero point mechanism, in which:

The anti-swing control system includes sensors, encoders, limit switches and radars;

The low-voltage distribution system includes an air switch, a contactor and a frequency converter;

The PLC system includes a power supply, a CPU, an IO module, a relay and a safety barrier;

The upper computer system includes an industrial computer and software; through the acceleration and deceleration adjustment functions of the control system, the large swing of the grab in the start and stop stages is controlled, and the frequency conversion has an acceleration and deceleration adjustment function, which can be set from static to The highest speed acceleration time and acceleration curve are used to control the swing range of the crane grab during the start-up phase, and the swing range of the grab bucket is controlled by setting the deceleration time and deceleration curve from the running state to a standstill; the crane is on the track When moving up to the photoelectric switch, the photoelectric switch is turned on, automatically confirmed, zeroed, and compared with the absolute position generated by the encoder to confirm whether there is an offset, if the offset exceeds the design range, automatically increase or decrease the offset , reset to zero, to solve the current problem of the deviation of the positioning distance of the cart; through the radar to accurately detect the material level elevation in the partition, realize the three-dimensional modeling of the material accumulation situation, as the data support for the automatic loading of the driving, and display it in the three-dimensional graph On the screen, as the staff monitors the actual situation, bad values are eliminated. Because during the elevation measurement process, for example, a tree trunk is inserted in the material pit, the elevation is obviously higher than the surrounding values, and the gap is large, so it can be defaulted to bad values.

The zero-point mechanism includes a beam and a crane. The beam is equipped with a track for the crane to move. There is a process tank on the beam, and a photoelectric switch is installed in the process tank. The crane moves through the track on the beam, and the crane moves to the photoelectric switch. When the time is off, the photoelectric switch is turned on, so as to automatically confirm, set to zero, and at the same time regularly run to the design zero point, compare it with the absolute position generated by the encoder, and confirm whether there is any offset. If the offset exceeds the design range, automatically increase or decrease the offset. The amount of displacement is reset to zero, which solves the problem of the deviation of the positioning distance of the cart at present.

The limit switch is electrically connected to the encoder, the sensor is electrically connected to the encoder, and the sensor is electrically connected to the radar; the encoder and the sensor are controlled by the limit switch, and the radar transmits the signal to the sensor after detecting the corresponding object. Then the signal is sent to the encoder for processing, so as to judge whether it is consistent with the set value.

The frequency converter is electrically connected to the contactor, the contactor is electrically connected to the air switch, and the air switch is electrically connected to the safety barrier; the contactor and the frequency converter are controlled by the air switch.

The power supply is electrically connected to the CPU, the CPU is electrically connected to the IO module, the IO module is electrically connected to the relay, and the relay is electrically connected to the safety barrier; the power supply provides working power for the CPU, the IO module and the relay.

The industrial computer is electrically connected to the software, the software is electrically connected to the frequency converter, and the frequency converter is electrically connected to the limit switch; the software controls the industrial computer.

Both the local operation console and the central control console in the crane are equipped with AI recognition cameras; not only can it identify whether the operator has the qualification to operate the crane, but also give the operation authority, and the operator cannot operate without the operation authority, and at the same time, the operation is automatically switched Authority, with local operation authority as the highest level; in addition, at night, it can also identify whether the operator is awake or not, and whether there is a potential safety hazard, and give a timely reminder.

S101: A detection probe is installed at the bottom of the crane for the material level;

S102: In the standby state, monitor the material level elevation in the previous grabbing zone in real time through the detection probe, and comprehensively calculate the average material level elevation in the zone after eliminating bad values;

S103: Through the radar to accurately detect the material level in the zone, realize the three-dimensional modeling of the material accumulation situation, as the data support for the automatic loading of the vehicle, and display it on the screen through the three-dimensional graphics, as the monitoring of the actual situation by the staff;

S201: Set up several partitions in the storage pit, and the operator makes partitions;

S202: After the loading instruction is given, the crane automatically executes the instruction, automatically moves to the designated partition, and puts down the grab bucket;

S302: Lift up after grabbing, automatically move to the discharge hopper, put down the grab, open the grab to drop, after one action is completed, automatically return to the original position, and enter a new round of standby state;

Working principle: The large swing of the grab in the start and stop stages is controlled by the acceleration and deceleration adjustment functions of the control system. The frequency conversion has its own acceleration and deceleration adjustment functions, and the acceleration time and acceleration curve from static to highest speed can be set. To control the swing range of the driving bucket at the start-up stage, the swing range of the grab bucket at the stop stage of the driving bucket is controlled by setting the deceleration time and deceleration curve from the running state to the stationary state; when the crane moves to the photoelectric switch on the track, the photoelectric The switch is turned on, automatically confirmed, zeroed, and compared with the absolute position generated by the encoder to confirm whether there is an offset. If the offset exceeds the design range, the offset will be automatically increased or decreased, and reset to zero to solve the current large The vehicle positioning distance deviation problem; through the radar to accurately detect the material level elevation in the zone, realize the three-dimensional modeling of the material accumulation situation, as the data support for the automatic loading of the vehicle, and display it on the screen through the three-dimensional graphics, as a staff member for the actual Monitor the situation and eliminate bad values. Because during the elevation measurement process, for example, a tree trunk is inserted in the material pit, the elevation is obviously higher than the surrounding values, and the gap is large, so it can be defaulted as a bad value.

In describing the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", " Orientation indicated by rear, left, right, vertical, horizontal, top, bottom, inside, outside, clockwise, counterclockwise, etc. The positional relationship is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, Therefore, it should not be construed as limiting the invention.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, a feature defined as "first" and "second" may explicitly or implicitly include one or more of these features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

The above is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto, any person familiar with the technical field within the technical scope disclosed in the present invention, according to the technical solution of the present invention Any equivalent replacement or change of the inventive concepts thereof shall fall within the protection scope of the present invention.

Claims (9)

1. A driving automatic loading system with AI recognition, characterized in that it includes a crane, an anti-swing control system, a PLC system, a low-voltage distribution system, a host computer system and a zero point mechanism, wherein: The anti-swing control system includes sensors, encoders, limit switches and radars; The low-voltage distribution system includes an air switch, a contactor and a frequency converter; The PLC system includes a power supply, a CPU, an IO module, a relay and a safety barrier; The upper computer system includes an industrial computer and software. 2. A driving automatic feeding system with AI recognition according to claim 1, characterized in that, the zero point mechanism includes a crossbeam and a crane, a rail for the crane to move is installed on the crossbeam, and a A process tank, a photoelectric switch is installed in the process tank. 3. The driving automatic feeding system with AI recognition according to claim 1, wherein the limit switch is electrically connected to the encoder, the sensor is electrically connected to the encoder, and the sensor is electrically connected to the radar. connect. 4. The driving automatic feeding system with AI recognition according to claim 1, characterized in that, the frequency converter is electrically connected to the contactor, the contactor is electrically connected to the air switch, and the air switch is electrically connected to the safety barrier. electrical connection. 5. The driving automatic feeding system with AI recognition according to claim 1, wherein the power supply is electrically connected to the CPU, the CPU is electrically connected to the IO module, and the IO module is electrically connected to the relay, The relay is electrically connected with the safety barrier. 6. The driving automatic feeding system with AI recognition according to claim 1, characterized in that, the industrial computer is electrically connected to the software, the software is electrically connected to the frequency converter, and the frequency converter is electrically connected to the limit switch. sexual connection. 7. A driving automatic loading system with AI recognition according to claim 1, characterized in that AI recognition cameras are installed on the local console and the central control console in the crane. 8. A driving automatic feeding system with AI recognition according to claim 1, characterized in that it comprises the following steps: S101: A detection probe is installed at the bottom of the crane for the material level; S102: In the standby state, monitor the material level elevation in the previous grabbing zone in real time through the detection probe, and comprehensively calculate the average material level elevation in the zone after eliminating bad values; S103: Through the radar to accurately detect the material level elevation in the zone, realize the three-dimensional modeling of the material accumulation situation, as the data support for the automatic loading of the vehicle, and display it on the screen through the three-dimensional graphics, as the staff monitor the actual situation. 9. A driving automatic feeding system with AI recognition according to claim 1, characterized in that it comprises the following steps: S201: Set up several partitions in the storage pit, and the operator makes partitions; S202: After the loading instruction is given, the crane automatically executes the instruction, automatically moves to the designated partition, and puts down the grab bucket; S302: Lift up after grabbing materials, automatically move to the discharge hopper, put down the grab bucket, open the grab bucket to drop materials, after one action is completed, it will automatically return to the original position and enter a new round of standby state.

Images