A control method, system, equipment and medium for a pond trawl fishing device.

Abstract

This invention relates to the field of aquaculture technology, specifically to a control method, system, equipment, and medium for a pond trawl fishing device. The method includes: determining whether to trigger a highest-priority interrupt signal based on real-time acquired measured tension values ​​using a threshold judgment method; when the highest-priority interrupt signal is not triggered, identifying the position information of pond obstacles and net float lines based on real-time acquired image data of the far end of the trawl, predicting collision risks, and determining whether to execute a dynamic obstacle avoidance strategy based on the prediction results; calculating the actual trawl speed and actual driving tension based on real-time acquired trawl power data, determining the optimized trawl speed using a fuzzy control strategy, and executing it. By designing feedback control logic for dynamic resistance during trawl, the adaptability to complex pond fishing conditions is improved, achieving a dynamic balance between equipment safety and fishing efficiency, and an intelligent upgrade of pond trawl fishing operations.

Description

Technical Field

[0001] This invention relates to the field of aquaculture technology, specifically to a control method, system, equipment, and medium for a pond trawl fishing device. Background Technology

[0002] Aquatic products are a high-quality and safe source of animal protein, and pond farming is the most common and important form of aquaculture. However, traditional pond farming has low levels of mechanical equipment and intelligence, and the development of different stages is unbalanced. Mechanical operations are mainly concentrated in the oxygenation and feeding stages, but the harvesting and other stages still rely on manual operations, resulting in low work efficiency.

[0003] To address this, existing technologies have proposed trawling solutions for pond aquaculture, such as Chinese patent CN102027892A, a simple trawling system for aquaculture ponds. This system uses stakes and steel wire guides on both sides of the pond, employing a trawl winch and tractor power to pull the net for retrieval, thus mechanizing pond trawling operations. However, although the trawling operation in this patent is completed by a tractor-driven winch, ponds vary in size, and operators located at one end of the pond find it difficult to directly observe the actual state of the trawl at the other end (e.g., whether the net is stuck in silt or has come into contact with obstacles). This means that when the bottom line of the net gets stuck in silt, the sudden increase in resistance is not detected in time, leading to net damage or motor overload. Alternatively, when the net approaches obstacles at the edge of the pond, operators cannot intervene in time, resulting in reduced retrieval efficiency or equipment damage, affecting normal trawling operations.

[0004] Although Chinese patent CN103626069A, a constant tension winch control system for trawlers, proposes a technical solution to control the winch and maintain the tension balance of the towing line by using a PLC, frequency converter, tension sensor, and rotary encoder, this patent is designed for marine trawler operations and is applied to open marine environments where wind and waves cause interference. The core control object is the tension balance of the left and right towing lines. It is difficult to apply to closed pond environments where silt and fixed obstacles cause interference. Moreover, this patent only relies on tension sensors to monitor the tension of the towing line and cannot predict the risk of collision between the net and obstacles. When the bottom line of the net sinks into the silt and causes a sudden change in resistance, adjusting the winch through tension feedback will result in a response delay, which may still cause motor overload or net tearing, leading to a reduction in fishing efficiency. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention proposes a control method, system, equipment, and medium for a pond trawl fishing device. The aim is to improve the adaptability to complex pond fishing conditions by designing feedback control logic for dynamic resistance during trawl fishing, thereby achieving a dynamic balance between equipment safety and fishing efficiency, and upgrading pond trawl fishing operations to an intelligent level.

[0006] In a first aspect, this application provides a control method for a pond trawl fishing device, comprising the following steps:

[0007] Real-time acquisition of measured tensile force values ​​of the trawl rope, image data of the far end of the trawl net, and trawl net dynamic data;

[0008] Based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal;

[0009] When the highest priority interrupt signal is not triggered, the location information of pond obstacles and net float lines can be identified based on the image data from the far end of the trawl net.

[0010] Based on the location information of obstacles in the pond and the floating lines of the fishing net, the collision risk is predicted, and the decision on whether to implement a dynamic obstacle avoidance strategy is made based on the prediction results.

[0011] When the highest priority interrupt signal is not triggered, or the system restarts after an interrupt, or the dynamic obstacle avoidance strategy is not executed, the actual trawling speed and actual driving force are calculated based on the trawling power data.

[0012] Based on the actual trawling speed and actual driving force, a fuzzy control strategy is used to determine and execute the optimized trawling speed.

[0013] In some embodiments, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal based on the measured tensile force value, including:

[0014] The measured tensile force value is compared with the preset tensile force threshold. When the measured tensile force value is greater than or equal to the preset tensile force threshold, the highest priority interruption signal is triggered to control the interruption of the trawler power and issue an overload alarm.

[0015] In some embodiments, based on the positional information of pond obstacles and fishing net lines, collision risks are predicted, and based on the prediction results, it is determined whether to implement a dynamic obstacle avoidance strategy, including:

[0016] Based on the location information of pond obstacles and fishing net lines, the actual distance between the fishing net lines and obstacles is calculated.

[0017] The actual distance is compared with a preset safe distance threshold. When the actual distance is less than or equal to the preset safe distance threshold, a collision risk prediction is obtained, and a dynamic obstacle avoidance strategy is executed based on the collision risk prediction.

[0018] In some embodiments, the execution of the dynamic obstacle avoidance strategy includes:

[0019] Trigger a secondary priority interrupt signal, and use an S-shaped speed curve to control the trawling power to decelerate to the first speed threshold before controlling the interruption of the trawling power.

[0020] The reverse control trawling power releases the trawling rope at a second speed threshold until the preset slack length of the trawling rope is reached, at which point the trawling power is interrupted and an obstacle alarm is issued.

[0021] In some embodiments, the optimized trawl speed is determined using a fuzzy control strategy based on the actual trawl speed and the actual driving force, including:

[0022] Calculate the third velocity threshold v l,s Compared with the actual trawling speed v k The difference is used to obtain the speed deviation e. v ;

[0023] The formula for calculating the tensile safety margin ΔL is:

[0024] ΔL=L k -P r,k -R·n

[0025] Among them, L k P represents the actual driving force. r,k This represents the measured tensile force value, R represents the drag rope resistance, and n represents the preset safety factor;

[0026] With speed deviation e v Using the tension safety margin ΔL as the input variable, and with the constraints of the actual driving tension being less than the preset tension threshold and ΔL≤0, a fuzzy control strategy is adopted to output the speed adjustment coefficient k. v ;

[0027] The product of the speed adjustment coefficient and the third speed threshold is used as the optimized trawling speed.

[0028] In some embodiments, the input speed deviation e v The fuzzy set is {negative large (NB), negative small (NS), zero (ZO), positive small (PS), positive large (PB)};

[0029] The fuzzy set of the input tensile safety margin ΔL is {SAFE, WARN, DANGER};

[0030] Output speed adjustment coefficient k v If the fuzzy set is {Stop (STP), Decelerate (DEC), Hold (HOLD), Accelerate (INC), Accelerate (INC-L)}, then the fuzzy control strategy includes:

[0031] When e v When PB = ΔL = SAFE, output k v =INC-L;

[0032] When e vWhen =PS and ΔL =SAFE, output k v =INC;

[0033] When e v When ZO = ΔL = SAFE, the output k is... v =HOLD;

[0034] When e v When NS = ΔL = WARN, output k. v =DEC;

[0035] When e v When NB = ΔL = DANGER, output k v =STP.

[0036] In some embodiments, the following steps are also included:

[0037] Based on real-time acquired image data from the far end of the trawl net, the visual shape of the net's floating line is identified;

[0038] Based on the visualized shape of the fishing line, the distance between the centers of adjacent floats and the curvature of the fishing line are determined.

[0039] The net morphology anomaly index is calculated based on the distance between the centers of adjacent floats and the curvature of the buoy line.

[0040] The optimized trawling speed is recorded as the first target trawling speed. When the net shape abnormality index is within the first deviation threshold range, the first target trawling speed is reduced to the second target trawling speed.

[0041] When the abnormality index of the net shape exceeds the first deviation threshold, the control will interrupt the trawling power and issue a serious deviation alarm for the floating steel line.

[0042] Secondly, this application provides a control system for a pond trawl fishing device, including a trawl motor for providing power to the trawl net, a tension sensor, an image monitoring module, a wheel encoder, and a control module. The trawl motor, tension sensor, image monitoring module, and wheel encoder are all connected to the control module, wherein:

[0043] Tension sensor, used to acquire the measured tension value of the trawl rope in real time;

[0044] The image monitoring module is used to acquire image data from the remote end of the trawl net in real time.

[0045] Wheel encoders are used to acquire real-time trawl net power data;

[0046] The control module is used to perform the following steps:

[0047] Based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal;

[0048] When the highest priority interrupt signal is not triggered, the location information of pond obstacles and net float lines can be identified based on the image data from the far end of the trawl net.

[0049] Based on the location information of obstacles in the pond and the floating lines of the fishing net, the collision risk is predicted, and the decision on whether to implement a dynamic obstacle avoidance strategy is made based on the prediction results.

[0050] When the highest priority interrupt signal is not triggered, or the system restarts after an interrupt, or the dynamic obstacle avoidance strategy is not executed, the actual trawling speed and actual driving force are calculated based on the trawling power data.

[0051] Based on the actual trawling speed and actual driving force, a fuzzy control strategy is used to determine and execute the optimized trawling speed.

[0052] Thirdly, an electronic device including a processor and a memory;

[0053] The processor is connected to the memory;

[0054] The memory is used to store executable program code;

[0055] The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, in order to execute a control method for a pond trawl fishing device as described above.

[0056] Fourthly, a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the control method for a pond trawl fishing device as described above.

[0057] The beneficial technical effects of the present invention include at least the following:

[0058] 1. A control method, system, equipment, and medium for a pond trawl fishing device are adopted. Overload risk is assessed using mechanical signals (measured tensile force), obstacle avoidance is achieved using visual signals (actual distance between the net's float line and obstacles), and the actual speed is calibrated using motion signals (optimized trawl speed). This is combined with a hierarchical control logic of "overload shutdown (hardware interrupt) > obstacle avoidance (software interrupt) > adaptive speed adjustment (efficiency optimization)." These three elements are integrated to form a closed-loop optimization of the control method, ensuring a timely and safe response in emergencies. Within a safe range, optimal trawl efficiency is maintained through adaptive speed adjustment, thereby achieving a dynamic balance between equipment safety and fishing efficiency. Simultaneously, cross-validation of sensors effectively distinguishes the causes of overload. Therefore, to avoid misjudgment of obstacle resistance or silt resistance, targeted overload shutdown or dynamic obstacle avoidance strategies are implemented, improving the reliability of dynamic resistance feedback control during trawls, enhancing adaptability to complex pond fishing conditions, and realizing the intelligent upgrade of pond trawl operations. The synergistic effect of its technical units not only enhances single functions (such as tension monitoring), but more importantly, through the deep integration of data and dynamic resistance, the system possesses full-chain intelligent capabilities of "perception-analysis-decision-execution", ultimately achieving the comprehensive effect of improving trawl efficiency, reducing equipment wear and tear, and reducing reliance on manual labor. It creatively solves the three major problems existing in the current technology: the remote status is not visible, the resistance adaptive capability is lacking, and reliance on manual labor.

[0059] 2. The dynamic obstacle avoidance strategy in this application systematically solves the three major pain points of traditional trawl systems in obstacle response: lag, abrupt shutdown, and low recovery efficiency, through the coordinated use of visual-mechanical fusion perception, hardware acceleration interruption, and adaptive release control technology units. Specifically, compared with the step-like interruption of trawl power in traditional trawl systems, this application controls the trawl power to enter a slow-stop mode based on the collision risk predicted by image recognition. It uses an S-shaped speed curve to control the trawl power to decelerate to the first speed threshold and then controls the interruption of trawl power. Furthermore, it combines the trawl rope slack program to reduce the tension of the net by releasing the trawl rope in the reverse direction. This can reduce the probability of collision between the net and obstacles, while significantly reducing the impact force of the float line and preventing the float line from breaking. This achieves safe, efficient, and intelligent obstacle avoidance operation in complex pond environments.

[0060] 3. In existing technologies, when the bottom line of the net sinks into silt, causing a sudden change in resistance, the traditional PID adjustment of the winch based solely on tension feedback can easily lead to response delays, resulting in motor overload or net tearing. To address this, this application resolves the contradiction between efficiency and safety in existing trawl operations through the synergistic effect of fuzzy-PID composite control, dynamic resistance feedback, and multi-level safety protection. It achieves reliable and intelligent optimization of trawl speed in complex pond environments. Specifically, this application combines a fuzzy control strategy that integrates speed deviation and tension safety margin to quickly predict the direction of speed adjustment and achieve fuzzy feedforward compensation. This effectively solves the technical problem of lag in traditional PID response and simultaneously enables load-adaptive speed regulation. It dynamically increases speed in low-resistance areas to improve trawl operation efficiency, reduces speed in high-resistance areas to reduce average motor power consumption, and triggers shutdown protection in the event of sudden resistance to prevent equipment damage.

[0061] 4. Existing technologies only guarantee tension balance and cannot predict fish escape caused by uncontrolled net shape, resulting in decreased fishing efficiency. To address this, this application uses image recognition to visualize the float line shape and calculates the net shape anomaly index. When the net shape anomaly index deviates from the threshold, the trawl speed is dynamically reduced to stabilize the net shape and achieve closed-loop repair, or the system is stopped to trigger a serious deviation alarm of the float line. By coupling visual shape monitoring with dynamic speed regulation, the system has the ability to monitor net shape, avoiding fish escape caused by excessive bending of the float line, and effectively improving the overall trawl fishing effect.

[0062] Other features and advantages of the present invention will be disclosed in detail in the following detailed description and accompanying drawings. Attached Figure Description

[0063] The invention will be further described below with reference to the accompanying drawings:

[0064] Figure 1 This is a flowchart of the control method for a pond trawl fishing device according to an embodiment of the present invention.

[0065] Figure 2 This is a schematic diagram of the control system structure of the pond trawl fishing device according to an embodiment of the present invention.

[0066] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be explained and described below with reference to the accompanying drawings. However, the following embodiments are only preferred embodiments of the present invention and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments in the implementation methods without creative effort are all within the protection scope of the present invention.

[0068] In the following description, terms such as “inner,” “outer,” “upper,” “lower,” “left,” and “right” are used only to indicate orientation or positional relationship for the convenience of describing the embodiments and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0069] Please see the appendix Figure 1 , Figure 1 A schematic flowchart of a control method for a pond trawl fishing apparatus provided in one embodiment of this specification is shown.

[0070] like Figure 1 As shown, the control method for this pond trawl fishing device may include at least the following steps:

[0071] Step 101: Real-time acquisition of the measured tensile force value of the trawl rope, image data of the far end of the trawl net, and trawl net dynamic data.

[0072] Understandably, after the operator completes the preparatory work for trawl net retrieval, including installing the wire guide rope, guide pulley, trawl rope, tension sensor, net, image monitoring module, and wheel encoder, the control system is activated. Based on a preset relationship between the appropriate traction speed and the trawl motor's rotation speed, the control system controls the trawl motor's speed and torque, thereby driving the rope drum to reel in the trawl rope. Once the trawl rope is taut, it pulls the remote guide pulley, image monitoring module, and net to move synchronously. Simultaneously, the control module begins to acquire in real-time the measured tension value collected by the tension sensor, the image data collected by the image monitoring module, and the trawl power data collected by the wheel encoder, and sends this data to the control module of the control system for data processing.

[0073] Furthermore, for the measured tensile force values ​​acquired at high frequencies, preprocessing operations can be performed first, such as removing missing values ​​and outliers, and using the recursive average filtering method to eliminate noise interference, so that the preprocessed measured tensile force values ​​can be used for subsequent control logic.

[0074] Step 102: Based on the measured tensile force value, use the threshold judgment method to determine whether to trigger the highest priority interrupt signal;

[0075] Specifically, in this embodiment, based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal, including:

[0076] The measured tensile force value is compared with the preset tensile force threshold. When the measured tensile force value is greater than or equal to the preset tensile force threshold, the highest priority interruption signal is triggered to control the interruption of the trawler power and issue an overload alarm.

[0077] It is understood that in this embodiment, when the measured tensile force value is less than the preset tensile force threshold, the highest priority interrupt signal is not triggered.

[0078] The preset tension threshold is the maximum allowable tension threshold for the motor. A highest-priority interrupt signal is triggered to immediately cut off the motor power supply, controlling the motor's speed and torque output to zero, thereby avoiding adverse situations such as motor overload burnout or mesh tearing caused by response lag in existing technologies.

[0079] Step 103: When the highest priority interrupt signal is not triggered, the location information of pond obstacles and net float lines is identified based on the image data of the far end of the trawl net.

[0080] The YOLO algorithm can be used to identify the position information of the trawl net's float line and obstacles in real time. Specifically, a pre-trained YOLOv8-seg model can be used, taking an image of the far end of the trawl net as input, and outputting the coordinate information of the trawl net's float line segmentation mask and the detection boxes of obstacles (such as aerators, poles, etc.). The operation method of the pre-trained YOLOv8-seg model is similar to that of the pre-trained YOLO model in the prior art, and will not be described in detail here.

[0081] Step 104: Based on the location information of obstacles in the pond and the floating line of the net, predict the collision risk and determine whether to implement a dynamic obstacle avoidance strategy based on the prediction results.

[0082] Specifically, in this embodiment, based on the positional information of pond obstacles and fishing net lines, collision risks are predicted, and based on the prediction results, it is determined whether to implement a dynamic obstacle avoidance strategy, including:

[0083] Step 201: Based on the location information of pond obstacles and net float lines, calculate the actual distance between the net float lines and obstacles.

[0084] Specifically, the pixel coordinates of the obstacle detection box center and the Euclidean distance of the mesh float line segmentation mask edge are first calculated, and then the actual distance d between the mesh float line and the obstacle is calculated based on the actual distance corresponding to the image width (the unit can be meters).

[0085] Step 202: Compare the actual distance with the preset safe distance threshold D. min For comparison, when the actual distance d is less than or equal to the preset safe distance threshold (i.e., d≤D), min When a collision risk is predicted, a dynamic obstacle avoidance strategy is executed based on that prediction.

[0086] It is understandable that in this embodiment, when d > D min If a prediction is obtained that there is no risk of collision, the dynamic obstacle avoidance strategy will not be executed.

[0087] Furthermore, in this embodiment, the execution of the dynamic obstacle avoidance strategy includes:

[0088] Step 2021: Trigger a secondary priority interrupt signal, and use an S-shaped speed curve to control the trawler's power to decelerate to the first speed threshold before interrupting the trawler's power.

[0089] Understandably, based on the prediction of a collision risk, a secondary priority interrupt signal is triggered first to enable the motor to receive a slow-stop command.

[0090] Specifically, the S-shaped velocity curve v(t) of the trawl net decelerating to the first speed threshold can be expressed as:

[0091]

[0092] Among them, v k The current actual trawling speed is represented by k, the preset deceleration slope is represented by t0, and the deceleration start time is represented by t0. The speed v is monitored in real time based on the trawling power data collected by the wheel encoder. k When v k When the speed decreases to the first speed threshold, the trawler's power is interrupted.

[0093] Step 2022: Reverse control the trawl power to release the trawl rope at the second speed threshold until the preset slack length Δs of the trawl rope is reached, then control to interrupt the trawl power and issue an obstacle alarm.

[0094] Understandably, the second speed threshold, i.e., the preset low speed, after the slow stop is completed, the motor switches to reverse mode, releasing the trawl rope Δs meters at the preset low speed, and then the trawl power is interrupted and an obstacle alarm is issued. This embodiment also includes an obstacle avoidance recovery mechanism, i.e., after the image data recognition result at the far end of the trawl confirms that the obstacle has been removed, the trawl operation is automatically restarted, and the trawl power speed is restored to the preset appropriate trawl speed.

[0095] Furthermore, this embodiment may also include a tension feedback termination mechanism. Specifically, if the measured tension value has dropped to the tension safety threshold during the reverse release of the trawl rope, the reverse release will be stopped in advance, the trawl power will be interrupted, and an obstacle alarm will be issued to avoid excessive slack causing the net to become entangled. The secondary risk is reduced through adaptive reverse release.

[0096] Understandably, this can be achieved by adjusting D. min The Δs parameter can be extended to adapt to different types of pond nets, such as deep-water nets and purse seines.

[0097] The dynamic obstacle avoidance strategy in this embodiment systematically solves the three major pain points of traditional trawl systems in obstacle response: lag, abrupt shutdown, and low recovery efficiency, through the coordinated use of visual-mechanical fusion perception, hardware-accelerated interruption, and adaptive release control. Specifically, compared to the step-like interruption of trawl power in traditional trawl systems, this embodiment controls the trawl power to enter a slow-stop mode based on the collision risk predicted by image recognition. It uses an S-shaped speed curve to control the trawl power to decelerate to the first speed threshold before controlling the interruption of trawl power. Furthermore, it combines the trawl rope slack program to reduce net tension by releasing the trawl rope in the reverse direction. This can reduce the probability of collision between the net and obstacles while significantly reducing the impact force on the float line and preventing float line breakage. This achieves safe, efficient, and intelligent obstacle avoidance operations in complex pond environments.

[0098] Step 105: When the highest priority interrupt signal is not triggered, or the system restarts after an interruption, or the dynamic obstacle avoidance strategy is not executed, the actual trawling speed and actual driving force are calculated based on the trawling power data.

[0099] The trawl power data includes, but is not limited to, the number of pulses m of the wheel encoder, wheel radius r, number of encoder lines N, and motor torque T within the acquisition interval Δt. k If so, then the actual trawling speed v k and actual driving force L k It can be represented as:

[0100]

[0101] Where i represents the preset reduction ratio.

[0102] Step 106: Based on the actual trawl speed and the actual driving force, a fuzzy control strategy is used to determine the optimized trawl speed v. k And execute.

[0103] The optimized trawling speed can be achieved by having the motor receive the v output from the fuzzy control strategy. k The stepless speed regulation is achieved by adjusting the PWM duty cycle, while the wheel encoder provides feedback on the actual trawling speed for calibration.

[0104] Furthermore, in this embodiment, based on the actual trawling speed and the actual driving force, a fuzzy control strategy is used to determine the optimized trawling speed, including:

[0105] Step 301, calculate the third velocity threshold v l,s Compared with the actual trawling speed v k The difference is used to obtain the speed deviation e. v .

[0106] The third speed threshold is the preset suitable trawling speed.

[0107] Step 302, calculate the tensile safety margin ΔL, the expression is:

[0108] ΔL=L k -P r,k -R·n

[0109] Among them, L k P represents the actual driving force. r,k This represents the measured tensile force value, where n represents the empirical safety factor, used to provide a safety margin for the control system to prevent overload caused by tensile force safety margin errors or sudden resistance, and R represents the drag rope resistance. Where S represents the length of the traction rope, and g represents the weight per unit length of the traction rope. The coefficient of frictional resistance can be obtained through experimental measurement or updated according to actual conditions, such as adjusting for seasonal variations or different pond bottom materials (silt, sand, etc.). The value is adjusted to adapt to changes in different pond environments.

[0110] Step 303, with speed deviation e v The tensile safety margin ΔL is used as an input variable, with the actual driving tensile force L. k With constraints of less than a preset tension threshold and ΔL≤0, a fuzzy control strategy is used to output the speed adjustment coefficient k. v .

[0111] It is understandable that the preset tension threshold is the maximum allowable tension threshold of the motor. When the tension exceeds the limit, i.e., L... k When the tension is greater than or equal to the preset tension threshold, the highest priority interrupt signal is triggered to immediately control and interrupt the trawler's power, and an overload alarm is issued.

[0112] In this embodiment, the fuzzy control strategy is used to accelerate the net to improve efficiency when the actual trawling speed is lower than the preset suitable trawling speed and the tension is safe (i.e., ΔL<0), and to decelerate or stop the net when the tension approaches the safety threshold (i.e., ΔL approaches 0 or ΔL=0) to avoid overload.

[0113] Step 304, adjust the speed adjustment coefficient k v With the third velocity threshold v l,s The product of these two values ​​is used as the optimized trawling speed v. k ′.

[0114] Furthermore, in this embodiment, the input speed deviation e v The fuzzy set is {negative large (NB), negative small (NS), zero (ZO), positive small (PS), positive large (PB)}, for example, the range is [-0.5, 0.5] m / s;

[0115] The fuzzy set of the input tensile force safety margin ΔL is {SAFE, WARN, DANGER}, for example, the range is [-200, 0]N;

[0116] Output speed adjustment coefficient k v The fuzzy set is {Stop (STP), Decelerate (DEC), Hold (HOLD), Accelerate (INC), Accelerate Significantly (INC-L)}, for example, with a range of [0, 1.5]. Then the fuzzy control strategies include:

[0117] When e v When PB = ΔL = SAFE, output k v =INC-L, for example, k v =1.5;

[0118] When e v When =PS and ΔL =SAFE, output k v =INC, for example, k v =1.2;

[0119] When e v When ZO = ΔL = SAFE, the output k is... v =HOLD, for example, k v =1.0;

[0120] When e v When NS = ΔL = WARN, output k. v =DEC, for example, k v =0.5;

[0121] When e v When NB = ΔL = DANGER, output k v =STP, for example, k v =0.

[0122] In existing technologies, when the bottom line of the trawl net becomes stuck in silt, causing a sudden change in resistance, simply adjusting the winch using traditional PID control based on tension feedback can easily lead to response delays, causing motor overload or net tearing. Therefore, this embodiment resolves the contradiction between efficiency and safety in existing trawl operations through the synergistic effect of fuzzy-PID composite control, dynamic resistance feedback, and multi-level safety protection. It achieves reliable and intelligent optimization of trawl speed in complex pond environments. Specifically, this embodiment combines speed deviation e... vThe fuzzy control strategy with tension safety margin ΔL quickly predicts the direction of speed adjustment and realizes fuzzy feedforward compensation, which effectively solves the technical problem of lag in traditional PID response. At the same time, it realizes load adaptive speed regulation, dynamically speeds up in the low resistance area to improve the efficiency of trawling operation, reduces speed in the high resistance area to reduce the average power consumption of the motor, and triggers shutdown protection to avoid equipment damage when sudden resistance occurs.

[0123] In summary, this embodiment uses mechanical signals (measured tensile force values) to determine overload risk, visual signals (actual distance between the net's float line and obstacles) to avoid obstacles, and motion signals (optimized trawl speed) to calibrate the actual speed. Combined with a hierarchical control logic of "overload shutdown (hardware interrupt) > obstacle avoidance (software interrupt) > adaptive speed adjustment (efficiency optimization)," these three elements are integrated to form a closed-loop optimization of the control method. This ensures a timely and safe response in emergencies and maintains optimal trawl efficiency within a safe range through adaptive speed adjustment. This achieves a dynamic balance between equipment safety and fishing efficiency, while also enabling cross-validation of sensors to effectively distinguish the causes of overload and avoid obstacle resistance or... Misjudgment of silt resistance allows for targeted overload shutdown or dynamic obstacle avoidance strategies, improving the reliability of dynamic resistance feedback control during trawls and enhancing adaptability to complex pond fishing conditions. This achieves an intelligent upgrade of pond trawl operations. The synergistic effect of its technical units not only enhances single functions (such as tension monitoring) but, more importantly, through the deep integration of data and dynamic resistance, enables the system to possess full-chain intelligent capabilities of "perception-analysis-decision-execution." Ultimately, this achieves a comprehensive effect of improving trawl efficiency, reducing equipment wear and tear, and minimizing reliance on manual labor. It creatively solves the three major problems existing in current technologies: the invisibility of remote status, the lack of resistance adaptive capability, and reliance on manual labor.

[0124] In yet another embodiment of this specification, the control method for a pond trawl fishing apparatus may further include the following steps:

[0125] Step 107: Based on the real-time acquired image data of the far end of the trawl net, the visual shape of the net's floating line is identified.

[0126] The method for obtaining the visual shape of the buoy line of the trawl net based on image data recognition at the far end of the trawl net in this embodiment is similar to the method for image recognition processing using a pre-trained YOLO model in the prior art, and will not be described again in this embodiment.

[0127] Step 108: Based on the visualized shape of the net's buoyancy line, determine the center distance between adjacent floats and the curvature of the buoyancy line.

[0128] Understandably, the coordinates of key points such as the center of the float and the intersection of the connecting ropes can be obtained based on the visualized shape of the float line, thereby determining the distance between the centers of adjacent floats, and the curvature of the float line can be determined by fitting a cubic spline curve of the center point of the float.

[0129] Step 109: Based on the center distance between adjacent floats and the curvature of the buoy line, the net shape anomaly index is calculated. The net shape anomaly index E can be expressed as:

[0130]

[0131] Where, d i d represents the distance between the centers of the i-th adjacent floats. avg C represents the mean distance between the centers of all adjacent floats, M represents the total number of floats, and C represents the mean distance between the centers of all adjacent floats. max C represents the maximum curvature of the float line. th α represents the preset float line curvature threshold, α represents the preset float spacing weight, and β represents the preset curvature weight.

[0132] Step 110, adjust the optimized trawling speed v k ′ is denoted as the first target trawling speed. When the net shape abnormality index E is within the first deviation threshold range, the first target trawling speed is reduced to the second target trawling speed.

[0133] When the abnormality index of the net shape exceeds the first deviation threshold, the control will interrupt the trawling power and issue a serious deviation alarm for the floating steel line.

[0134] For example, taking a first deviation threshold range of [0.5, 1) as an example, the implementation method of this embodiment is as follows: if the net morphology abnormality index E < 0.5, then maintain the first target traction speed v. k If 0.5 ≤ E < 1, then the first target's traction speed v will be... k Reduce to the second target trawling speed v k "" to stabilize the shape of the floating line; if E≥1, the motor power supply will be forcibly cut off to control the interruption of the trawl net power and issue an alarm indicating that the floating steel line is seriously deviated.

[0135] Existing technologies only guarantee tension balance and cannot predict fish escape due to uncontrolled net morphology, leading to decreased fishing efficiency. To address this, this embodiment uses image recognition to visualize the float line morphology and calculates a net morphology anomaly index. When the anomaly index deviates from a threshold, the trawl speed is dynamically reduced to stabilize the net morphology, achieving closed-loop repair, or the system is stopped to trigger a severe float line deviation alarm. This coupling of visual morphology monitoring and dynamic speed control enables the system to monitor net morphology, preventing fish escape caused by excessive float line bending and effectively improving overall trawl fishing results.

[0136] Please see the appendix Figure 2 , Figure 2 This is a schematic diagram of the control system structure of a pond trawl fishing device, which is provided as another embodiment of this specification.

[0137] Before describing the control system of a pond trawl fishing device provided in this embodiment, the application scenario, namely the structure of a pond trawl fishing device in the prior art, will be explained first:

[0138] Existing pond trawl fishing devices typically include a wire guide rope, a guide pulley, and a trawl motor to provide power to the trawl net. Figure 2 (Not shown in the image) trawl rope and net. The two ends of the wire guide rope are connected to the uprights at both ends of the pond. The trawl motor is connected to the near end of the trawl rope. The guide pulley is slidably connected to the wire guide rope. A buckle can be set at the lower end of the guide pulley. One end of the buckle is connected to the far end of the trawl rope, and the other end of the buckle is connected to the net via a tension sensor. The net usually includes a floating steel line and several floats located on the floating steel line (such as the top line and floats shown in Chinese Patent CN210869483U).

[0139] like Figure 2 As shown, the control system of this pond trawl fishing device may include at least a trawl motor for providing power to the trawl net, a tension sensor, an image monitoring module, a wheel encoder, and a control module. Figure 2 (Not shown in the image), the trawl motor, tension sensor, image monitoring module, and wheel encoder are all connected to the control module, wherein:

[0140] Tension sensor, used to acquire the measured tension value of the trawl rope in real time;

[0141] The image monitoring module is used to acquire image data from the remote end of the trawl net in real time.

[0142] Wheel encoders are used to acquire real-time trawl net power data;

[0143] The control module is used to perform the following steps:

[0144] Based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal;

[0145] When the highest priority interrupt signal is not triggered, the location information of pond obstacles and net float lines can be identified based on the image data from the far end of the trawl net.

[0146] Based on the location information of obstacles in the pond and the floating lines of the fishing net, the collision risk is predicted, and the decision on whether to implement a dynamic obstacle avoidance strategy is made based on the prediction results.

[0147] When the highest priority interrupt signal is not triggered, or the system restarts after an interrupt, or the dynamic obstacle avoidance strategy is not executed, the actual trawling speed and actual driving force are calculated based on the trawling power data.

[0148] Based on the actual trawling speed and actual driving force, a fuzzy control strategy is used to determine and execute the optimized trawling speed.

[0149] For example, a trawl motor providing power to the trawl net may include a motor and a rope drum. The motor output shaft is connected to the rope drum shaft. One end of the trawl rope is fixed to the rope drum and wound around it. The other end of the trawl rope passes through a rope guide and a wheel encoder on the outside of the rope drum, and finally connects to a loop fastener at the lower end of a guide pulley suspended on a guide wire rope. Both the wheel encoder and the motor are connected to a control module.

[0150] For example, the image monitoring module may include a housing, pulley blocks, a self-stabilizing gimbal, a camera, an image data transmission unit, a battery, etc. The housing of the image monitoring module is connected to the guide pulley mechanism via a movable thin rod to achieve synchronous movement between the image monitoring module and the guide pulley. Two pulley blocks are located at the middle of the upper part of the housing along the direction of the steel wire guide rope. Each pulley block consists of three pulleys symmetrically installed in a triangular pattern. The steel wire guide rope of the mechanical trawl net passes through these blocks. When the trawl rope is pulled, it drives the entire image monitoring module to move along the steel wire guide rope. One end of the tension sensor is connected to the buckle at the lower end of the guide pulley of the mechanical trawl net, and the other end of the tension sensor is connected to the net. At the same time, the tension sensor is connected to the control module. The self-stabilizing gimbal includes a connector, which is connected to the housing's bracket by screws and fixed to the bottom of the housing. The lower part of the connector has a motor-driven yaw axis for horizontal control. Below the yaw axis is an L-shaped connecting rod. The horizontal end of the L-shaped connecting rod has a roll axis, and the other end has a U-shaped connecting rod. Pitch axes are located on both sides of the opening of the U-shaped connecting rod, and the pitch axes have mounting holes for connecting a camera. The camera is mounted at the mounting holes of the self-stabilizing gimbal and connected to the image data transmission unit via a transmission line. The image data transmission unit is located inside the housing and is used to acquire video data from the camera and transmit it to the receiving end of the control module via an antenna unit.

[0151] It is understood that the technical concept of the control system of the pond trawl fishing device provided in this embodiment is similar to the technical concept of the control method of the aforementioned pond trawl fishing device, and will not be repeated here.

[0152] Please see the appendix Figure 3 , Figure 3 This is a schematic diagram of an electronic device structure provided as another embodiment of this specification.

[0153] like Figure 3As shown, the electronic device 300 may include at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0154] The communication bus 302 can be used to realize the connection and communication of the above components.

[0155] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0156] The network interface 304 may include, but is not limited to, Bluetooth modules, NFC modules, Wi-Fi modules, etc.

[0157] The processor 301 may include one or more processing cores. The processor 301 connects to various parts within the electronic device 300 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of DSP, FPGA, or PLA. The processor 301 may integrate one or more of the following: CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0158] The memory 305 may include RAM or ROM. Optionally, the memory 305 may include a non-transitory computer-readable medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. As a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface module, and application programs. The processor 301 may be used to call the application programs stored in the memory 305 and execute the methods in one or more of the above embodiments.

[0159] Another embodiment of this specification provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform one or more steps in the above embodiments. The constituent modules of the above-described electronic device, if implemented as software functional units and used as independent downstream task predictions or applications, can be stored in the computer-readable storage medium.

[0160] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0161] The above description is merely a preferred embodiment disclosed in this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of protection involved in this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0162] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

Claims

1. A control method for a pond trawl fishing device, characterized in that, Includes the following steps: Real-time acquisition of measured tensile force values ​​of the trawl rope, image data of the far end of the trawl net, and trawl net dynamic data; Based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal; When the highest priority interrupt signal is not triggered, the location information of pond obstacles and net float lines can be identified based on the image data from the far end of the trawl net. Based on the location information of obstacles in the pond and the floating lines of the fishing net, the collision risk is predicted, and the decision on whether to implement a dynamic obstacle avoidance strategy is made based on the prediction results. When the highest priority interrupt signal is not triggered, or the system restarts after an interrupt, or the dynamic obstacle avoidance strategy is not executed, the actual trawling speed and actual driving force are calculated based on the trawling power data. Based on the actual trawling speed and actual driving force, a fuzzy control strategy is used to determine and execute the optimized trawling speed. When implementing a dynamic obstacle avoidance strategy, the following are included: Trigger a secondary priority interrupt signal, and use an S-shaped speed curve to control the trawling power to decelerate to the first speed threshold before controlling the interruption of the trawling power. The reverse control trawling power releases the trawling rope at a second speed threshold until the preset slack length of the trawling rope is reached, at which point the trawling power is interrupted and an obstacle alarm is issued.

2. The control method for a pond trawl fishing device as described in claim 1, characterized in that, Based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal, including: The measured tensile force value is compared with the preset tensile force threshold. When the measured tensile force value is greater than or equal to the preset tensile force threshold, the highest priority interruption signal is triggered to control the interruption of the trawler power and issue an overload alarm.

3. The control method for a pond trawl fishing device as described in claim 1, characterized in that, Based on the location information of obstacles in the pond and the floating lines of the fishing nets, the collision risk is predicted, and based on the prediction results, it is determined whether to implement a dynamic obstacle avoidance strategy, including: Based on the location information of pond obstacles and fishing net lines, the actual distance between the fishing net lines and obstacles is calculated. The actual distance is compared with a preset safe distance threshold. When the actual distance is less than or equal to the preset safe distance threshold, a collision risk prediction is obtained, and a dynamic obstacle avoidance strategy is executed based on the collision risk prediction.

4. The control method for a pond trawl fishing device as described in claim 1, characterized in that, Based on the actual trawling speed and actual driving force, a fuzzy control strategy is used to determine the optimized trawling speed, including: Calculate the third velocity threshold Compared with actual trawling speed The difference is used to obtain the speed deviation; Calculate the safety margin of tensile force The expression is: ， in, Indicates the actual driving force. This represents the measured tensile force value, R represents the drag rope resistance, and n represents the preset safety factor; With speed deviation Using the tension safety margin as an input variable, the actual driving tension is less than the preset tension threshold and As constraints, a fuzzy control strategy is used to output the speed adjustment coefficient. ; The product of the speed adjustment coefficient and the third speed threshold is used as the optimized trawling speed.

5. The control method for a pond trawl fishing device as described in claim 4, characterized in that, Input speed deviation The fuzzy set is {negative large (NB), negative small (NS), zero (ZO), positive small (PS), positive large (PB)}; Input tensile safety margin The fuzzy set is {SAFE, WARN, DANGER}; Output speed adjustment coefficient If the fuzzy set is {Stop (STP), Decelerate (DEC), Hold (HOLD), Accelerate (INC), Accelerate (INC-L)}, then the fuzzy control strategy includes: when and When, output ; when and When, output ; when and When, output ; when and When, output ; when and When, output .

6. The control method for a pond trawl fishing device as described in claim 1, characterized in that, It also includes the following steps: Based on real-time acquired image data from the far end of the trawl net, the visual shape of the net's floating line is identified; Based on the visualized shape of the fishing line, the distance between the centers of adjacent floats and the curvature of the fishing line are determined. The net morphology anomaly index is calculated based on the distance between the centers of adjacent floats and the curvature of the buoy line. The optimized trawling speed is recorded as the first target trawling speed. When the net shape abnormality index is within the first deviation threshold range, the first target trawling speed is reduced to the second target trawling speed. When the abnormality index of the net shape exceeds the first deviation threshold, the control will interrupt the trawling power and issue a serious deviation alarm for the floating steel line.

7. A control system for a pond trawl fishing device, characterized in that, The system includes a trawl motor for providing power to the trawl net, a tension sensor, an image monitoring module, a wheel encoder, and a control module. The trawl motor, tension sensor, image monitoring module, and wheel encoder are all connected to the control module. Tension sensor, used to acquire the measured tension value of the trawl rope in real time; The image monitoring module is used to acquire image data from the remote end of the trawl net in real time. Wheel encoders are used to acquire real-time trawl net power data; The control module is used to perform the following steps: Based on the measured tensile force value, a threshold judgment method is used to determine whether to trigger the highest priority interrupt signal; When the highest priority interrupt signal is not triggered, the location information of pond obstacles and net float lines can be identified based on the image data from the far end of the trawl net. Based on the location information of obstacles in the pond and the floating lines of the fishing net, the collision risk is predicted, and the decision on whether to implement a dynamic obstacle avoidance strategy is made based on the prediction results. When the highest priority interrupt signal is not triggered, or the system restarts after an interrupt, or the dynamic obstacle avoidance strategy is not executed, the actual trawling speed and actual driving force are calculated based on the trawling power data. Based on the actual trawling speed and actual driving force, a fuzzy control strategy is used to determine and execute the optimized trawling speed. When the control module executes the dynamic obstacle avoidance strategy, it performs the following steps: Trigger a secondary priority interrupt signal, and use an S-shaped speed curve to control the trawling power to decelerate to the first speed threshold before controlling the interruption of the trawling power. The reverse control trawling power releases the trawling rope at a second speed threshold until the preset slack length of the trawling rope is reached, at which point the trawling power is interrupted and an obstacle alarm is issued.

8. An electronic device, characterized in that, Including the processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to execute the control method of a pond trawl fishing device according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the control method of the pond trawl fishing device according to any one of claims 1 to 6.

Images