Intelligent measurement and control system and method for square bale press-baler

Abstract

The invention discloses an intelligent measurement and control system and method for a square bale press-baler, and relates to the technical field of square bale press-balers. The method comprises the following steps: acquiring the average operation period duration of one action process of a to-be-monitored operation mechanism of the baler in the normal operation process, acquiring a sequence image of the to-be-monitored operation mechanism from the beginning moment to the end moment of the action process in the average operation period duration at a fixed sampling frequency lambda, and calculating the sequence image of the to-be-monitored operation mechanism in the action process; constructing a displacement data set of a normal operation process according to the displacement from the rth sequence image acquisition moment to the (r + 1) th sequence image acquisition moment, acquiring an action process image of a to-be-monitored operation mechanism in real time, acquiring a real-time displacement, calculating a local outlier factor of the real-time displacement in the displacement data set, and calculating the real-time displacement of the to-be-monitored operation mechanism according to the local outlier factor. And judging the operation state of the action process of the operation mechanism to be monitored by using the obtained local outlier factor, and when the operation state is judged to be abnormal, performing alarm processing.

Description

Technical Field

[0001] The present invention relates to the technical field of square bale balers, and particularly to an intelligent measurement and control system and method for a square bale baler. Background Art

[0002] A square bale baler is a forage harvesting machine that presses dried grass strips into rectangular bales for easy transportation and storage. When the baler is working, the tractor pulls the baler forward across the same grass strip, transmits the power to the baler through the power take-off shaft of the tractor, the spring teeth of the pick-up pick up the forage, and the forage is sent into the feeding chamber by the conveying feeder for pre-pressing and then into the baling chamber. The baling mechanism binds the compressed square bale with plastic ropes and automatically drops it on the ground through the bale discharge plate. Currently, there are many types of balers on the market with different shapes, but their structures basically consist of a pick-up, a conveying feeder, a baling chamber, a baling mechanism, a piston, a transmission system, a frame and other parts.

[0003] Currently, for the performance test of a square bale baler, the commonly adopted method is to install intelligent sensing devices on key mechanical components to collect motion parameters such as force data, displacement data, and rotation angle data during their operating actions, so as to analyze the motion posture and the operating state of the mechanism. However, this method can only reflect the local motion state at the data sampling points and cannot evaluate the overall operating state of the mechanism, resulting in a large deviation between the evaluation result and the actual operating state and being unable to truly reflect the actual operating condition of the baler. For this reason, we propose an intelligent measurement and control system and method for a square bale baler. Summary of the Invention

[0004] The main purpose of the present invention is to provide an intelligent measurement and control system and method for a square bale baler, which can effectively solve the problems in the background art.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] An intelligent measurement and control method for a square bale baler, comprising:

[0007] Obtain the start time t bq and the end time t eq of the q-th action process during the normal operation of the operation mechanism to be monitored of the baler, and calculate the average operation cycle duration Δt of one action process of the operation mechanism to be monitored according to the obtained time data, where Q is the number of action process sampling times, and q = 1, 2,..., Q;

[0008] During normal operation, a plurality of sets of sequential images of the operation mechanism to be monitored from the start time to the end time of the operation process within the average operation cycle duration Δt are acquired at a fixed sampling frequency λ, and the displacement of the operation mechanism to be monitored from the r-th sequential image acquisition time to the (r + 1)-th sequential image acquisition time during the q-th operation process is calculated based on the acquired sequential images r is an integer greater than or equal to 0, and the acquired displacement is used To construct a displacement dataset Δs for the normal operation process r→r+1 , where

[0009] Displacement The acquisition process includes the following steps:

[0010] Select any point on the operation mechanism to be monitored as the calibration point;

[0011] The coordinate values of the calibration point in the r-th sequential image and the (r + 1)-th sequential image during the q-th operation process are respectively obtained and denoted as (x r , y r ), (x r+1 , y r+1 );

[0012] Taking the distance value between the coordinate points as the displacement of the operation mechanism to be monitored from the r-th sequential image acquisition time to the (r + 1)-th sequential image acquisition time during the q-th operation process The calculation formula is:

[0013] The sampling frequency λ and the average operation cycle duration Δt satisfy the following relationship:

[0014] When the movement process trajectory of the operation mechanism to be monitored is a straight line, where Denotes the ceiling operation on ;

[0015] When the movement process trajectory of the operation mechanism to be monitored is a curve, where Denotes the ceiling operation on ; θ represents the angle value swept by the operation mechanism to be monitored during one operation process.

[0016] The movement process images of the operation mechanism to be monitored are acquired in real time, and the real-time displacement from the r-th sequential image acquisition time to the (r + 1)-th sequential image acquisition time is obtained Calculate the real-time displacement The local outlier factor in the displacement dataset Δs r→r+1 is

[0017] The calculation process includes the following steps:

[0018] Step S1: Assume displacement data set Δs r→r+1 In the real-time displacement The kth data point with the smallest distance is Calculate real-time displacement k nearest neighbor distance The calculation formula is: Where k∈Q;

[0019] Step S2: Calculate the displacement data set Δs respectively r→r+1 In the above table, any other data points and real-time displacement The distance is calculated based on the distance value that is less than the k nearest neighbor distance. A collection of data points as the real-time displacement k-distance neighborhood

[0020] Step S3: Get k nearest neighbor distances k-distance neighborhood Real-time displacement at medium distance The maximum value of the distance to the nearest k-th sampling point is used as the real-time displacement With the kth data point The kth reachable distance

[0021] Step S4: Determine the real-time displacement according to the obtained calculation results The local reachable density The calculation formula is:

[0022] Step S5: Determine the real-time displacement according to the calculation result of the local reachable density The local outlier factor The calculation formula is: in, is the kth data point The local reachable density

[0023] The acquired local outlier factor is used to determine the operating state of the action process of the operating mechanism to be monitored at the current moment, and when the operating state of the operating mechanism to be monitored is determined to be abnormal, an alarm process is performed.

[0024] The basis for determining the operating status of the action process of the operating mechanism to be monitored is:

[0025] when When It is abnormal data, indicating that the operating state of the operation process of the to-be-monitored operating mechanism at the current moment is an abnormal state;

[0026] When Then the real-time displacement is normal data, indicating that the operating state of the operation process of the to-be-monitored operating mechanism at the current moment is a normal state.

[0027] An intelligent measurement and control system for a square bale baler includes:

[0028] An action data acquisition module for obtaining the start time t bq and the end time t eq of the qth action process of the to-be-monitored operating mechanism of the baler during normal operation, and calculating the average operation cycle duration Δt of one action process of the to-be-monitored operating mechanism according to the obtained time data, where Q is the number of action process samplings, and q = 1, 2,..., Q;

[0029] An image data acquisition module for obtaining a plurality of groups of sequence images of the to-be-monitored operating mechanism from the start time to the end time of the action process within the average operation cycle duration Δt during normal operation at a fixed sampling frequency λ;

[0030] An image processing module for calculating the displacement of the to-be-monitored operating mechanism from the rth sequence image acquisition time to the (r + 1)th sequence image acquisition time during the qth action process according to the obtained sequence images, where r is an integer greater than or equal to 0, and constructing a displacement data set Δs of the normal operation process using the obtained displacement, where r→r+1 where

[0031] A running state determination module for calculating the real-time displacement in the real-time action process image of the to-be-monitored operating mechanism, the local outlier factor r→r+1 in the displacement data set Δs and using the obtained local outlier factor to determine whether the operating state of the action process of the to-be-monitored operating mechanism at the current moment is a normal state or an abnormal state;

[0032] An abnormal alarm module for performing alarm processing when it is determined that the operating state of the to-be-monitored operating mechanism is abnormal.

[0033] The system includes a memory, a processor, and a computer program stored on the memory and executable on the processor.

[0034] The present invention has the following beneficial effects:

[0035] Compared with the prior art, by obtaining the start time and end time of the q-th action process of the operation mechanism to be monitored of the baler during the normal operation process, calculating the average operation cycle duration of one action process of the operation mechanism to be monitored according to the obtained time data, obtaining a plurality of groups of sequence images of the operation mechanism to be monitored from the start time to the end time of the action process within the average operation cycle duration Δt at a fixed sampling frequency λ during the normal operation process, calculating the displacement amount of the operation mechanism to be monitored from the r-th sequence image acquisition time to the (r + 1)-th sequence image acquisition time during the q-th action process according to the obtained sequence images, constructing a displacement amount data set of the normal operation process by using the obtained displacement amount, collecting the action process images of the operation mechanism to be monitored in real time, obtaining the real-time displacement amount from the r-th sequence image acquisition time to the (r + 1)-th sequence image acquisition time, calculating the local outlier factor of the real-time displacement amount in the displacement amount data set, using the obtained local outlier factor to determine the operation state of the action process of the operation mechanism to be monitored at the current moment, and when it is determined that the operation state of the operation mechanism to be monitored is abnormal, performing an alarm process, and using image acquisition and processing technology to evaluate the overall operation state of the operation mechanism during the operation process, so that the evaluation process and evaluation results are closer to the actual operation state, thereby truly reflecting the real operation situation of the baler. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic flow chart of the intelligent measurement and control method for the square bale baler of the present invention;

[0037] Figure 2 It is a schematic structural diagram of the intelligent measurement and control system for the square bale baler of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The following further describes the present invention in conjunction with specific embodiments. Among them, the drawings are only for illustrative purposes, showing only schematic diagrams, not physical diagrams, and should not be construed as limiting the present invention. In order to better illustrate the specific embodiments of the present invention, some components in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0039] The specific implementation process of the technical solution of the present invention includes the following steps:

[0040] Step 1: Obtain the start time t bq and the end time t eq ;

[0041] Step 2: Calculate the average operation cycle duration Δt of one action process of the operation mechanism to be monitored according to the obtained time data, where, Q is the number of sampling times during the action process, and q = 1, 2,..., Q;

[0042] Step 3: Obtain a number of groups of sequential images of the operation mechanism to be monitored from the start time to the end time of the action process within the average operation cycle duration Δt during the normal operation process at a fixed sampling frequency λ;

[0043] The sampling frequency λ and the average operation cycle duration Δt satisfy the following relational formula:

[0044] When the action process trajectory of the operation mechanism to be monitored is a straight line, where, represents the ceiling operation on ;

[0045] When the action process trajectory of the operation mechanism to be monitored is a curve, where, represents the ceiling operation on ; θ represents the angle value swept by the operation mechanism to be monitored during one action process.

[0046] Step 4: Calculate the displacement of the operation mechanism to be monitored from the acquisition time of the r-th sequential image to the acquisition time of the (r + 1)-th sequential image during the q-th action process according to the obtained sequential images r is an integer greater than or equal to 0; among them, the acquisition process of the displacement includes the following steps:

[0047] Step 41: Select any point on the operation mechanism to be monitored as the calibration point;

[0048] Step 42: Obtain the coordinate values of the calibration point in the r-th sequential image and the (r + 1)-th sequential image during the q-th action process respectively, denoted as (x r , y r ), (x r+1 , y r+1 );

[0049] Step 43: Use the distance value of the coordinate points as the displacement of the operation mechanism to be monitored from the acquisition time of the r-th sequential image to the acquisition time of the (r + 1)-th sequential image during the q-th action process The calculation formula is:

[0050] Step 5: Use the obtained displacement to construct the displacement data set Δs of the normal operation process r→r+1 , where,

[0051] Step 6: Collect the action process images of the operation mechanism to be monitored in real time, and obtain the real-time displacement from the r-th sequence image acquisition moment to the (r + 1)-th sequence image acquisition moment

[0052] Step 7: Calculate the real-time displacement The local outlier factor in the displacement dataset Δs r→r+1 is The calculation process includes the following steps:

[0053] Step S71: Assume that in the displacement dataset Δs r→r+1 , the k-th data point with the smallest distance from the real-time displacement is Calculate the k-nearest neighbor distance of the real-time displacement , and the calculation formula is: where k ∈ Q;

[0054] Step S72: Calculate the distances between the real-time displacement r→r+1 and the remaining arbitrary data points in the displacement dataset Δs respectively. Take the set of data points with distance calculation results less than the k-nearest neighbor distance as the k-distance neighborhood of the real-time displacement

[0055] Step S73: Take the maximum value among the distances from the k-th sampling point closest to the real-time displacement in the k-distance neighborhood as the k-reachable distance between the real-time displacement and the k-th data point

[0056] Step S74: Determine the local reachability density of the real-time displacement based on the obtained calculation results. The calculation formula is:

[0057]

[0058] Step S75: Determine the local outlier factor of the real-time displacement based on the calculation results of the local reachability density. The calculation formula is:

[0059] where is the local reachability density of the k-th data point

[0060] ​​​​Step 8: Use the obtained local outlier factor to determine the operating state of the action process of the to-be-monitored working mechanism at the current moment. When it is determined that the operating state of the to-be-monitored working mechanism is abnormal, alarm processing is performed. Among them, the basis for determining the operating state of the action process of the to-be-monitored working mechanism is as follows:

[0061] When the real-time displacement is abnormal data, indicating that the operating state of the action process of the to-be-monitored working mechanism at the current moment is an abnormal state;

[0062] When the real-time displacement is normal data, indicating that the operating state of the action process of the to-be-monitored working mechanism at the current moment is a normal state.

[0063] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent measurement and control method for a square straw bale baler, characterized in that: include: Get the starting time t of the qth action process of the monitored operating mechanism of the baler during normal operation bq and end time t eq , calculate the average operation cycle duration Δt of an action process of the operating mechanism to be monitored based on the acquired time data, where: Q is the sampling times of the action process, and q=1,2,...,Q; A plurality of groups of sequence images of the monitored operating mechanism from the start time to the end time of the action process within the average operation cycle duration Δt are obtained at a fixed sampling frequency λ during normal operation, and the displacement of the monitored operating mechanism from the rth sequence image acquisition time to the r+1th sequence image acquisition time during the qth action process is calculated based on the acquired sequence images. r is an integer greater than or equal to 0, and the displacement is obtained using Construct the displacement data set Δs during normal operation r→r+1 ,in, Collect the action process images of the operating mechanism to be monitored in real time, and obtain the real-time displacement from the time of collecting the rth sequence image to the time of collecting the r+1th sequence image Calculate real-time displacement In the displacement data set Δs r →r+1 The local outlier factor in The acquired local outlier factor is used to determine the operating state of the action process of the operating mechanism to be monitored at the current moment, and when the operating state of the operating mechanism to be monitored is determined to be abnormal, an alarm process is performed.

2. The intelligent measurement and control method for a square straw bale baler according to claim 1, characterized in that: Local outlier factor The calculation process includes the following steps: Step S1: Assume displacement data set Δs r→r+1 In the real-time displacement The kth data point with the smallest distance is Calculate real-time displacement k nearest neighbor distance The calculation formula is: Among them, k∈Q; Step S2: Calculate the displacement data set Δs respectively r→r+1 In the above table, any other data points and real-time displacement The distance is calculated based on the distance value that is less than the k nearest neighbor distance. A collection of data points as the real-time displacement k-distance neighborhood Step S3: Get k nearest neighbor distances k-distance neighborhood Real-time displacement at medium distance The maximum value of the distance to the nearest k-th sampling point is used as the real-time displacement With the kth data point The kth reachable distance Step S4: Determine the real-time displacement according to the obtained calculation results The local reachable density Step S5: Determine the real-time displacement according to the calculation result of the local reachable density The local outlier factor The calculation formula is: in, is the kth data point The local reachable density of .

3. The intelligent measurement and control method for a square straw bale baler according to claim 1, characterized in that: The basis for determining the operating status of the action process of the operating mechanism to be monitored is: when When is abnormal data, indicating that at the current moment, the operating state of the action process of the operating mechanism to be monitored is abnormal; when The real-time displacement It is normal data, indicating that at the current moment, the operating status of the action process of the operating mechanism to be monitored is normal.

4. The intelligent measurement and control method for a square straw bale baler according to claim 1, characterized in that: Displacement The acquisition process includes the following steps: Select any point on the operating mechanism to be monitored as a calibration point; The coordinate values ​​of the calibration point in the rth sequence image and the r+1th sequence image during the qth action are obtained respectively, and are recorded as (x r ,y r )、(x r+1 ,y r+1 ); The distance value of the coordinate point is taken as the displacement of the monitored operating mechanism from the rth sequence image acquisition time to the r+1th sequence image acquisition time during the qth action process. The calculation formula is:

5. The intelligent measurement and control method for a square straw bale baler according to claim 1, characterized in that: The sampling frequency λ and the average operation cycle duration Δt satisfy the following relationship: When the movement trajectory of the operating mechanism to be monitored is a straight line, in, Expressed as a pair Perform rounding operation upwards; When the motion trajectory of the operating mechanism to be monitored is a curve, in, Expressed as a pair Perform an upward rounding operation; θ represents the angle value swept by the operating mechanism to be monitored during one action process.

6. Intelligent measurement and control system for square straw bale baler, characterized in that: The system is used to implement the steps of the intelligent measurement and control method for a square straw bale baler according to any one of claims 1 to 5, including: The action data acquisition module is used to obtain the starting time t of the qth action process of the monitored operating mechanism of the baler during normal operation. bq and end time t eq , calculate the average operation cycle duration Δt of an action process of the operating mechanism to be monitored based on the acquired time data, where: Q is the sampling times of the action process, and q=1,2,...,Q; An image data acquisition module is used to obtain, at a fixed sampling frequency λ, a plurality of groups of sequential images of the operating mechanism to be monitored from the start time to the end time of the action process within the average operation cycle time Δt during normal operation; The image processing module is used to calculate the displacement of the monitored operating mechanism from the time of collecting the rth sequence image to the time of collecting the r+1th sequence image during the qth action according to the acquired sequence images. r is an integer greater than or equal to 0, and the displacement is obtained using Construct the displacement data set Δs during normal operation r→r+1 ,in, The operation status determination module is used to calculate the real-time displacement in the real-time action process image of the operating mechanism to be monitored. In the displacement data set Δs r→r+1 The local outlier factor in And using the obtained local outlier factor to determine whether the operating state of the action process of the operating mechanism to be monitored is a normal state or an abnormal state at the current moment; The abnormal alarm module is used to perform alarm processing when it is determined that the operating state of the operating mechanism to be monitored is abnormal.

7. The intelligent measurement and control system for a square straw bale baler according to claim 6, characterized in that: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the intelligent measurement and control method for a square hay bale baler as described in any one of claims 1 to 5 when executing the program.

Images