CN116030399A - Machine vision-based loader three-item and time online detection system and method - Google Patents
Machine vision-based loader three-item and time online detection system and method Download PDFInfo
- Publication number
- CN116030399A CN116030399A CN202211664889.4A CN202211664889A CN116030399A CN 116030399 A CN116030399 A CN 116030399A CN 202211664889 A CN202211664889 A CN 202211664889A CN 116030399 A CN116030399 A CN 116030399A
- Authority
- CN
- China
- Prior art keywords
- loader
- time
- stage
- image data
- bucket
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Component Parts Of Construction Machinery (AREA)
Abstract
The invention discloses a machine vision-based three-item and time online detection system and method for a loader, and relates to the technical field of online detection, wherein the system comprises a vision capturing camera, an image processing module, a display module and a database module, wherein the vision capturing camera is used for acquiring image data of the loader in a bucket lifting stage, a unloading stage and a descending stage; the image processing module is used for performing image processing on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a bucket unloading stage and a bucket descending stage; obtaining three items and time of the loader according to the starting and stopping points; the display module is used for displaying three items and time of the loader; the database module is used for storing information of each loader and image data, three items and time of each loader. The invention solves the technical problems of large measurement error, high cost, long time consumption and the like of three loading machines and time, and has the advantages of wide application range, high degree of automation, no need of contacting with a measured object, no damage to the measured object and the like.
Description
Technical Field
The invention relates to the technical field of online detection, in particular to a loader three-item and time online detection system and method based on machine vision.
Background
The three items and time of the wheel loader, namely the time of the wheel loader for completing the total three items of loading and unloading actions of lifting, unloading and descending a bucket, are an important index for evaluating the working capacity of the loader, directly determine the working efficiency of the loader, and are a technical index which is necessary to be detected for the output of the loader, so that the precision and the efficiency of the three items and time measurement technology of the wheel loader become particularly important.
At present, three wheel loaders and time measurement technologies are two, namely, manual pinching is utilized to measure time for multiple groups, numerical values with larger individual deviation are removed, and an average value is calculated and is used as a test result to be output. The method is simple to operate and low in cost, and is generally used in occasions with low requirements on the measured time precision occasionally.
The second is to install various sensors such as hydraulic sensor, angle sensor, displacement sensor, etc. on the loader, collect technical data such as hydraulic pressure of the loader, lifting angle of the bucket, position of the bucket movement starting point, etc. of the wheel loader in the processes of lifting, unloading and lowering the bucket, transmit these data into the computer program designed in advance, carry on the data analysis, the test result obtained by the time conversion output, it is three item and time method of the mainstream measuring wheel loader of the enterprise at present, replace the manual work with various sensors, pinch the table, the degree of automation is high, has raised the test efficiency, reduce the cost of labor that the enterprise operates, the measured data result has qualitative leap compared with the first one.
The first method utilizes manual meter pinching timing to measure three items and time of the wheel loader, because manual operation is affected by too many factors, errors are large, and modern large enterprises are eliminated from use.
The three existing wheel loader and time measurement technologies are basically the second, various technical data are obtained based on various sensors, and then the data indexes are transmitted into a computer for processing, so that a test result is obtained. Among these are the following problems and drawbacks:
1. the measurement error is large. The existing wheel loader three-item and time online detection technology has too many and complex working links, more manual participation links and easy error accumulation; various errors are unavoidable in each step in a series of processes from the initial design error, installation error, observation error, and the final input of the computer processing result of the sensor itself for collecting the technical parameters, so that the final obtained result has a larger gap from the actual one.
2. The measurement costs are high. Compared with the measurement by using machine vision, the three-item and time online detection technology of the traditional wheel loader often needs various sensors for obtaining parameters, and the cost of the sensors needed once the measurement accuracy is high. And if the measured object is not capable of being installed and observed due to the design of the measured object, the cost is more expensive if the measured object is specially designed for detecting the parameters of the product.
3. The online detection scheme has long development period and long time consumption in the measurement process. The sensor for detecting the tested object needs to be designed, an installation scheme is selected, field debugging, program development, program debugging and the like, and if the next type of tested object is replaced, the test object needs to be reinstalled and debugged, so that the development period and measurement time are longer.
4. The three existing wheel loader and time online detection technologies are all contact type measurement, so that the safety is low in the installation and detection process, and the loss to a detected object is easy to cause.
The technical problems cannot be solved by measuring three items and time of the wheel loader based on various sensors at present, so that the defects of low measurement precision, high cost, long period, low safety and the like caused by sensor measurement are overcome, and the problems are needed to be solved by the technicians in the field.
Disclosure of Invention
In view of the above, the present invention provides a machine vision-based on-line detection system and method for three items and time of a loader, and a method for measuring three items and time of a loader by using a machine vision technology, which fundamentally solves the above technical problems.
In order to achieve the above object, the present invention provides the following technical solutions:
the utility model provides a three and time on-line measuring system of loader based on machine vision, includes vision capture camera, image processing module, display module, database module, vision capture camera, image processing module, display module connect gradually, database module is connected with vision capture camera, image processing module, display module respectively, wherein:
the visual capturing camera is used for respectively acquiring image data of the loader in a bucket lifting stage, a unloading stage and a descending stage;
the image processing module is used for performing image processing on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a bucket unloading stage and a bucket descending stage; according to the starting points of the bucket lifting stage, the unloading stage and the descending stage, three items and time of the loader are obtained;
the display module is used for displaying three items and time of the loader;
and the database module is used for storing information of each loader and image data, three items and time of each loader.
Optionally, the image processing module includes an application processor and an image processor, an output end of the visual capturing camera is connected with an input end of the image processor, and an output end of the image processor is connected with an input end of the application processor.
Optionally, the display module includes an LED display screen.
Optionally, the LED display screen is used for displaying three items and time of the loader and is also used for carrying out text prompt of operation instructions.
Optionally, the device further comprises a loudspeaker connected with the LED display screen and used for performing voice prompt of the operation instruction.
Optionally, the database module includes a memory, which is a memory bank or a TF card.
A loader three-item and time online detection method based on machine vision comprises the following steps:
respectively acquiring image data of the loader in a bucket lifting stage, a unloading stage and a descending stage;
performing image processing on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a bucket unloading stage and a bucket descending stage; according to the starting points of the bucket lifting stage, the unloading stage and the descending stage, three items and time of the loader are obtained;
displaying three items and time of the loader;
each loader information and its image data, three items and time are stored.
Optionally, when image data is acquired, the loader and the bucket and the movable arm thereof are identified through visual capturing, and the image data of the loader in the bucket lifting stage, the unloading stage and the descending stage are photographed.
Optionally, the image data of the loader during the bucket lifting phase refers to image data of the bucket lifting phase when the loader is loaded.
Optionally, the image data of the loader in the unloading stage and the descending stage refer to the image data of the unloading stage and the descending stage when the loader is empty.
Optionally, the image processing includes: color segmentation, background segmentation, binarization, morphological processing, particle analysis, target feature extraction, gesture analysis, curve generation, curve filtering, gradient and trend analysis, inflection point capturing and timing conversion.
According to the technical scheme, the invention discloses a system and a method for online detection of three items and time of a loader based on machine vision, and compared with the prior art, the system and the method introduce a machine vision processing technology into the online detection of the three items and time of the loader for the first time, and solve the defects in the prior art by optimizing system equipment and process flow, thereby perfectly avoiding the technical problems that the measurement error is larger, the cost is higher, the time is long and the like which are difficult to solve when the three items and time of the loader are measured at present; the device has the advantages of wide application range, high automation degree, no need of contacting with the tested object, no damage to the tested object in the testing process and the like, and has the following specific beneficial effects:
(1) The invention applies the machine vision dynamic tracking and capturing technology in the engineering machinery field for the first time, realizes the detection of three items with high precision and time (the detection precision is 0.0625 s), and overcomes the defects of poor calculation precision and low reliability of manual meter pinching; meanwhile, three items of data are bound and associated with the whole machine number of data, and interference of manual filling to data inaccuracy caused by manual filling is avoided.
(2) According to the invention, a sensor and a sensor mounting position are not required to be designed, and the development period of a measurement scheme is short; and the sensor is not required to be installed and debugged, the whole process is automatically operated, and the measurement time is short.
(3) The invention provides three items and the complete data storage in the detection process, can repeatedly research and analyze the detection process of the product at any time, and provides reliable analysis data for product research and development and quality tracing and data reproduction.
(4) The invention replaces the manpower (only 1 person/station) input of the working procedure, so that the working procedure is changed from the current spot inspection to the full inspection.
(5) The invention adopts visual non-contact measurement, has low cost and high safety, and has no damage to products.
(6) The scheme of the invention has strong portability, can be transplanted to engineering machinery such as an excavator, a bulldozer and the like by modification of a small-amplitude algorithm in the later period, and is used for measuring and calculating the effective working time utilization coefficient of the engineering machinery.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a system architecture of the present invention;
FIG. 2 is a schematic diagram of the method steps of the present invention;
FIG. 3 is a flowchart of the operation of one embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses a machine vision-based three-item and time online detection system of a loader, which is shown in fig. 1 and comprises a vision capturing camera, an image processing module, a display module and a database module, wherein the vision capturing camera, the image processing module and the display module are sequentially connected, and the database module is respectively connected with the vision capturing camera, the image processing module and the display module.
The visual capturing camera is used for respectively acquiring image data of the loader in the bucket lifting stage, the unloading stage and the descending stage.
The image processing module is used for carrying out image processing on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a bucket unloading stage and a bucket descending stage; and obtaining three items and time of the loader according to the starting and stopping points of the bucket lifting stage, the unloading stage and the descending stage.
In one embodiment, the image processing module includes an application processor and an image processor, the output of the visual capture camera is connected to the input of the image processor, and the output of the image processor is connected to the input of the application processor. The image data is firstly transmitted to an image processor for algorithm processing, then the processed image data is transmitted to an application processor, and then the post-processing of the image data is carried out.
The display module comprises an LED display screen and is used for displaying three items and time of the loader, and the display module is also used for carrying out text prompt of operation instructions.
In another embodiment, the LED display screen also comprises a loudspeaker which is connected with the LED display screen and used for carrying out voice prompt of the operation instruction.
The database module comprises a memory, such as a memory bank or a TF card, and is used for storing information of each loader and image data, three items and time thereof.
In another embodiment, a machine vision-based loader three-item and time online detection method is also disclosed, see fig. 2, comprising the steps of:
the method comprises the steps of respectively acquiring image data of a loader in a bucket lifting stage, a unloading stage and a descending stage through visual capturing and identifying the loader and a bucket and a movable arm of the loader;
performing image processing (the image processing process comprises color segmentation, background segmentation, binarization, morphological processing, particle analysis, target feature extraction, gesture (position and angle) analysis, curve generation, curve filtering, gradient and trend analysis, inflection point capturing and timing conversion) on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a discharging stage and a descending stage; according to the starting points of the bucket lifting stage, the unloading stage and the descending stage, three items and time of the loader are obtained;
displaying three items and time of the loader on a display screen;
each loader information and its image data, three items and time are stored.
The following describes the scheme of the present invention with reference to fig. 3 by taking the working flow of the wheel loader for inspection test as an example:
step 1, manually scanning codes to obtain detection authority and related information (including whole machine number data and the like) of a wheel loader to be tested; stopping the wheel loader to be tested to a preset position according to the guide mark on the display screen;
step 2, the driver selects to start a detection flow;
step 3, capturing a target to be tested by a vision capturing camera;
step 4, prompting each operation on a display screen in sequence, and completing the operation by a driver according to the prompting, wherein the specific process is as follows:
step 4.1, lifting time detection: the method comprises the steps of shoveling a load of a wheel loader to be tested, and carrying out lifting and descending actions with the load according to indication of a display screen; simultaneously, the vision capturing camera shoots image data, and lifting time is obtained according to the image data;
step 4.2, judging whether the lifting time is qualified or not, if so, entering the next step, if not, selecting the reworking step 4.1 through the remote controller, repeating for a plurality of times (3 times in the specific embodiment), determining the final lifting time, and entering the next step;
step 4.3, detecting the bucket unloading time and the descending time: the load is removed, the wheel loader to be tested is stopped to a preset position again, and the empty bucket lifting, unloading and descending actions are carried out according to the indication of the display screen; simultaneously, the vision capturing camera shoots image data, and the bucket unloading time and the descending time are obtained according to the image data;
step 4.4, judging whether the bucket unloading time and the descending time are qualified or not, if so, entering the next step, if not, selecting a reworking step 4.3 through a remote controller, repeating for a plurality of times (3 times in the specific embodiment), determining the final bucket unloading time and the descending time, and entering the next step;
step 5, after all detection items are completed, displaying three items and detection results of the wheel loader to be tested, wherein the three items and detection results comprise lifting time, bucket unloading time, descending time and three items and time;
and 6, packaging the detection data and uploading the detection data to a database (memory).
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The utility model provides a three and time on-line measuring system of loader based on machine vision, its characterized in that, including vision capture camera, image processing module, display module, database module, vision capture camera, image processing module, display module connect gradually, database module is connected with vision capture camera, image processing module, display module respectively, wherein:
the visual capturing camera is used for respectively acquiring image data of the loader in a bucket lifting stage, a unloading stage and a descending stage;
the image processing module is used for performing image processing on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a bucket unloading stage and a bucket descending stage; according to the starting points of the bucket lifting stage, the unloading stage and the descending stage, three items and time of the loader are obtained;
the display module is used for displaying three items and time of the loader;
and the database module is used for storing information of each loader and image data, three items and time of each loader.
2. The machine vision-based three-item and time online detection system of claim 1, wherein the image processing module comprises an application processor and an image processor, wherein an output end of the vision capturing camera is connected with an input end of the image processor, and an output end of the image processor is connected with an input end of the application processor.
3. The machine vision-based three-item and time online detection system for the loader of claim 1, wherein the display module comprises an LED display screen for displaying three items and time of the loader and for performing text prompting of operation instructions.
4. The machine vision based three item and time on-line detection system of a loader of claim 3, further comprising a speaker coupled to the LED display for voice prompts of the operating instructions.
5. The machine vision based three item and time on-line detection system of claim 1, wherein the database module comprises a memory, either a memory bank or a TF card.
6. The machine vision-based loader three-item and time online detection method is characterized by comprising the following steps of:
respectively acquiring image data of the loader in a bucket lifting stage, a unloading stage and a descending stage;
performing image processing on the image data to respectively obtain starting and stopping points of a bucket lifting stage, a bucket unloading stage and a bucket descending stage; according to the starting points of the bucket lifting stage, the unloading stage and the descending stage, three items and time of the loader are obtained;
displaying three items and time of the loader;
each loader information and its image data, three items and time are stored.
7. The machine vision-based three-item and time on-line detection method of the loader of claim 6, wherein the image data of the loader in the bucket lifting phase, the unloading phase and the lowering phase are photographed by visually capturing and identifying the loader and the bucket and the boom thereof when the image data is acquired.
8. The machine vision based on-line detection method of three and time of a loader of claim 6, wherein the image data of the loader during the bucket lifting phase is the image data of the bucket lifting phase when the loader is loaded.
9. The machine vision-based three-item and time online detection method for a loader according to claim 6, wherein the image data of the loader in the unloading stage and the descending stage refer to the image data of the unloading stage and the descending stage when the loader is empty.
10. The machine vision based loader three item and time on-line detection method of claim 6, wherein the image processing process comprises: color segmentation, background segmentation, binarization, morphological processing, particle analysis, target feature extraction, gesture analysis, curve generation, curve filtering, gradient and trend analysis, inflection point capturing and timing conversion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211664889.4A CN116030399A (en) | 2022-12-22 | 2022-12-22 | Machine vision-based loader three-item and time online detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211664889.4A CN116030399A (en) | 2022-12-22 | 2022-12-22 | Machine vision-based loader three-item and time online detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116030399A true CN116030399A (en) | 2023-04-28 |
Family
ID=86090590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211664889.4A Pending CN116030399A (en) | 2022-12-22 | 2022-12-22 | Machine vision-based loader three-item and time online detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116030399A (en) |
-
2022
- 2022-12-22 CN CN202211664889.4A patent/CN116030399A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101424520B (en) | Method for detecting partial contour outline of object curved surface | |
| CN107725535B (en) | A kind of excavator hydraulic cylinder leakage detection method and device | |
| CN104359662A (en) | Cylindrical compression spring parameter testing method | |
| CN102435413B (en) | Method for ascertaining correspondence relationship of pressure measuring points of wind tunnel test model | |
| CN102354199A (en) | Programmable test data automatic acquisition analytic system and method | |
| CN114542444A (en) | Intelligent monitoring method and system for air compressor | |
| CN116540682A (en) | Method, system, device, equipment and medium for testing analog single machine | |
| CN114814697A (en) | Automatic calibration system, control method and control terminal for distributed multimeter | |
| CN104390982A (en) | Test method for SMT first article inspection | |
| CN116030399A (en) | Machine vision-based loader three-item and time online detection system and method | |
| CN111948059B (en) | Hydrostatic test method, hydrostatic test device, hydrostatic test equipment and storage medium | |
| CN103218277A (en) | Automatic detection method and device for server environment | |
| CN102058430B (en) | Automatic test equipment (ATE) of multi-parameter monitor and test method thereof | |
| CN115409799A (en) | Automatic pin mark detection method and device for LED chip, medium and electronic equipment | |
| CN217193789U (en) | Rotating disc type workpiece detection device | |
| CN101231250B (en) | Metallic phase all-round measurement method | |
| CN110220455B (en) | Device and method for detecting tire winding process parameters | |
| CN112903211A (en) | Equipment and method for detecting tightness of gas pipeline | |
| US20150041094A1 (en) | Core pin detection | |
| CN112246681A (en) | Detection data processing method and device and product detection equipment | |
| CN101832754B (en) | Test method for detecting coordinate precision of numerical control equipment | |
| CN104076715A (en) | Automobile trunk lock function detecting device | |
| CN202631188U (en) | Full-automatic force overlapping type standardizing machine based on image processing technology | |
| CN116630306B (en) | Defect detection method and device for aircraft semi-circular head rivet | |
| CN106502678A (en) | A kind of software development process reliability pre-detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |