阅读说明：本技术 一种基于消抖滤波法计权的鸟类飞行轨迹预测方法 (Bird flight trajectory prediction method based on weight calculation by jitter elimination filtering method ) 是由 张羽 陈益平 蓝伟松 周宇尧 周庆东 甘团杰 吴华标 莫钜槐 张家耀 刘天绍 张 于 2020-06-10 设计创作，主要内容包括：本发明涉及电力系统安全技术领域,更具体地,涉及一种基于消抖滤波法计权的鸟类飞行轨迹预测方法,包括：S1.在驱鸟装置上安装若干雷达；S2.采用无人机模拟鸟类飞行,通过所述无人机触发雷达,使雷达在探测时接收到所述无人机的信号；S3.基于消抖滤波法对所述雷达接收到的信号进行预处理；S4.根据步骤S3得到的数据,构建逻辑回归模型；S5.通过所述逻辑回归模型对鸟类飞行轨迹进行预测。本发明能够支撑对高压杆塔害鸟的跟踪打击驱赶,实现对高压杆塔害鸟高效率、最大空间且有针对性的有效探测。(The invention relates to the technical field of power system safety, in particular to a bird flight trajectory prediction method based on weighting by a jitter elimination filtering method, which comprises the following steps: s1, mounting a plurality of radars on a bird repelling device; s2, simulating bird flight by adopting an unmanned aerial vehicle, and triggering a radar through the unmanned aerial vehicle so that the radar receives a signal of the unmanned aerial vehicle during detection; s3, preprocessing signals received by the radar based on a jitter elimination filtering method; s4, constructing a logistic regression model according to the data obtained in the step S3; and S5, forecasting the bird flight track through the logistic regression model. The invention can support the tracking, striking and driving of the high-voltage tower pest birds, and realizes the efficient, maximum-space and targeted effective detection of the high-voltage tower pest birds.)

1. A bird flight trajectory prediction method based on weight calculation by a jitter elimination filtering method is characterized by comprising the following steps:

s1, mounting a plurality of radars on a bird repelling device;

s2, simulating bird flight by adopting an unmanned aerial vehicle, and triggering a radar through the unmanned aerial vehicle so that the radar receives a signal of the unmanned aerial vehicle during detection;

s3, preprocessing signals received by the radar based on a jitter elimination filtering method;

s4, constructing a logistic regression model according to the data obtained in the step S3;

and S5, forecasting the bird flight track through the logistic regression model.

2. The method for predicting bird flight trajectory based on weight calculation by using the jitter elimination filter method as claimed in claim 1, wherein in step S3, the signal received by the radar is processed by a single chip microcomputer.

3. The method for predicting bird flight trajectory based on weight calculation by using an anti-shake filtering method according to claim 2, wherein the step S3 specifically comprises the following steps:

s31, judging whether the radar receives a signal, if so, executing a step S32, otherwise, continuing to detect;

s32, setting a variable a and accumulating 1, and then executing a step S33;

s33, judging whether the variable a reaches a certain threshold value, if so, executing a step S34, otherwise, executing a step S35;

s34, setting a variable b and accumulating 1, clearing the variable a, and then executing a step S35;

s35, judging whether the variable b reaches a certain threshold value and whether the radar receives signals, if so, executing a step S36, otherwise, executing a step S31;

s36, setting a characteristic weight coefficient alpha_iAnd 1 is accumulated, and the variables a and b are cleared, and then step S37 is executed; wherein i represents the number of radar settings;

s37, judging whether the detection time of the radar reaches a certain threshold value, if so, outputting the characteristic weight coefficient alpha_iOtherwise, step S31 is executed.

4. The method for predicting bird flight trajectory based on weight calculation by using the shivering elimination filter method as claimed in claim 3, wherein in step S4, the logistic regression model is obtained by training with logistic regression algorithm.

5. The method for predicting bird flight trajectory based on weight calculation by using the jitter elimination filter method as claimed in claim 4, wherein in step S4, the logistic equation of the logistic regression model is:

wherein w represents a model weight vector, w^TDenotes the transpose of the model weight vector, x denotes the feature weight acquired by step S3, h_w(x) Indicating the predicted value.

6. The method for predicting bird flight trajectory based on weight calculation by using the de-jittering filtering method as claimed in claim 5, wherein in step S4, the prediction accuracy of the logistic regression model is processed by a loss function and L2 regularization.

7. The method for predicting bird flight trajectory based on weight calculation by using the jitter elimination filter method as claimed in claim 6, wherein in step S5, the calculation formula of bird flight trajectory prediction is:

T＝index[max(margin_i＝w_i·x^T)]；

wherein T represents a prediction direction, w_iA weight vector, x, representing each class in the logistic regression model^TRepresenting the characteristic weight vector, margin, obtained by said radar detection_iA value representing the ith class calculated by the vector matrix is represented, and i represents the number of the radar settings.

8. The method for predicting bird flight trajectory based on weight calculation by using the de-jittering filtering method as claimed in claim 1, wherein in step S5, the logistic regression model predicts the flight direction of the birds every 1-5 seconds.

9. The method for predicting bird flight trajectory based on anti-shake filtering weighting according to claim 1, wherein in step S1, each radar is respectively installed on the non-adjacent surfaces of the bird repelling device.

10. The method of claim 9, wherein the radar is a doppler radar.

Technical Field

The invention relates to the technical field of power system safety, in particular to a bird flight trajectory prediction method based on weighting by a jitter elimination filtering method.

Background

The safe operation of the high-voltage transmission line is important for ensuring uninterrupted power supply of users. The current bird damage accident becomes a hidden danger influencing the safe operation of the high-voltage transmission line, and the attention of the power department is more and more aroused.

The Chinese patent document with the publication number of CN110568435A discloses a bird flight trajectory prediction method suitable for high-voltage poles and towers, and specifically designs a simple and efficient trajectory direction prediction method aiming at the characteristics of the architecture of the high-voltage poles and towers and the nesting habit of harmful birds, so that strong support is provided for driving the harmful birds on the high-voltage poles and towers, and the harmful birds are accurately and effectively driven.

However, in practical application, the scheme only has monotonous radar fixed-point detection and does not carry out experimental simulation data, so that the detection data is single, and the detection range is not wide.

Disclosure of Invention

The invention aims to overcome the defect that the existing prediction method does not have experimental simulation, and provides a bird flight trajectory prediction method based on weighting by an anti-shake filtering method, which can support the tracking, striking and driving of harmful birds on high-voltage towers and realize efficient, maximum-space and targeted effective detection of the harmful birds on the high-voltage towers.

In order to solve the technical problems, the invention adopts the technical scheme that:

the bird flight trajectory prediction method based on weighting by using the jitter elimination filtering method comprises the following steps:

s1, mounting a plurality of radars on a bird repelling device;

s2, simulating bird flight by adopting an unmanned aerial vehicle, and triggering a radar through the unmanned aerial vehicle so that the radar receives a signal of the unmanned aerial vehicle during detection;

s3, preprocessing signals received by the radar based on a jitter elimination filtering method;

s4, constructing a logistic regression model according to the data obtained in the step S3;

and S5, forecasting the bird flight track through the logistic regression model.

The invention relates to a bird flight track prediction method based on weighting by an anti-shake filtering method.

Further, in step S3, the signal received by the radar is processed by the single chip microcomputer.

Further, the step S3 specifically includes the following steps:

s31, judging whether the radar receives a signal, if so, executing a step S32, otherwise, continuing to detect;

s32, setting a variable a and accumulating 1, and then executing a step S33;

s33, judging whether the variable a reaches a certain threshold value, if so, executing a step S34, otherwise, executing a step S35;

s34, setting a variable b and accumulating 1, clearing the variable a, and then executing a step S35;

s35, judging whether the variable b reaches a certain threshold value and whether the radar receives signals, if so, executing a step S36, otherwise, executing a step S31;

s36, setting a characteristic weight coefficient alpha_iAnd 1 is accumulated, and the variables a and b are cleared, and then step S37 is executed; wherein i represents the number of radar settings;

s37, judging whether the detection time of the radar reaches a certain threshold value, if so, outputting the characteristic weight coefficient alpha_iOtherwise, step S31 is executed.

Further, in step S4, the logistic regression model is obtained by training with logistic regression algorithm.

Further, in step S4, the logistic equation of the logistic regression model is:

wherein w represents a model weight vector, w^TDenotes the transpose of the model weight vector, x denotes the feature weight acquired by step S3, h_w(x) Indicating the predicted value.

Further, in step S4, the prediction accuracy of the logistic regression model is processed by a loss function and L2 regularization.

Further, in step S5, the calculation formula of bird flight trajectory prediction is:

T＝index[max(margin_i＝w_i·x^T)]；

wherein T represents a prediction direction, w_iA weight vector, x, representing each class in the logistic regression model^TRepresenting the characteristic weight vector, margin, obtained by said radar detection_iA value representing the ith class calculated by the vector matrix is represented, and i represents the number of the radar settings.

Further, in step S5, the logistic regression model predicts the bird' S flight direction every 1-5 seconds.

Further, in step S1, each radar is respectively installed on the surfaces of the bird repelling devices which are not adjacent to each other.

Further, the radar is a doppler radar.

Compared with the prior art, the invention has the beneficial effects that:

the invention relates to a bird flight track prediction method based on weighting by an anti-shake filtering method.

Drawings

FIG. 1 is a flow chart of a bird flight trajectory prediction method based on weighting by an anti-shake filtering method.

Fig. 2 is a schematic view of the installation of the radar of the present invention.

FIG. 3 is a flowchart of step S3 according to the present invention.

Detailed Description

The present invention will be further described with reference to the following embodiments. Wherein the showings are for the purpose of illustration only and are shown by way of illustration only and not in actual form, and are not to be construed as limiting the present patent; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.

The same or similar reference numerals 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 is an orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", etc. based on the orientation or positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but it is not intended to indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limiting the present patent, and the specific meaning of the terms may be understood by those skilled in the art according to specific circumstances.