CN114255394A - Method, device and processor for adjusting operation parameters of agricultural machine - Google Patents
Method, device and processor for adjusting operation parameters of agricultural machine Download PDFInfo
- Publication number
- CN114255394A CN114255394A CN202010954222.2A CN202010954222A CN114255394A CN 114255394 A CN114255394 A CN 114255394A CN 202010954222 A CN202010954222 A CN 202010954222A CN 114255394 A CN114255394 A CN 114255394A
- Authority
- CN
- China
- Prior art keywords
- learning model
- machine learning
- agricultural machine
- model
- crop image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000010801 machine learning Methods 0.000 claims abstract description 172
- 238000011156 evaluation Methods 0.000 claims abstract description 83
- 238000003306 harvesting Methods 0.000 claims abstract description 47
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims description 70
- 239000012535 impurity Substances 0.000 claims description 50
- 239000010813 municipal solid waste Substances 0.000 claims description 35
- 238000002372 labelling Methods 0.000 claims description 23
- 238000013467 fragmentation Methods 0.000 claims description 16
- 238000006062 fragmentation reaction Methods 0.000 claims description 16
- 230000006698 induction Effects 0.000 claims description 12
- 235000013339 cereals Nutrition 0.000 description 37
- 241000209140 Triticum Species 0.000 description 33
- 235000021307 Triticum Nutrition 0.000 description 33
- 238000010586 diagram Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 12
- 238000004590 computer program Methods 0.000 description 11
- 240000008042 Zea mays Species 0.000 description 10
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 10
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 10
- 235000005822 corn Nutrition 0.000 description 10
- 239000010902 straw Substances 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000010191 image analysis Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 206010063385 Intellectualisation Diseases 0.000 description 4
- 244000062793 Sorghum vulgare Species 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 235000017060 Arachis glabrata Nutrition 0.000 description 2
- 244000105624 Arachis hypogaea Species 0.000 description 2
- 235000010777 Arachis hypogaea Nutrition 0.000 description 2
- 235000018262 Arachis monticola Nutrition 0.000 description 2
- 240000002791 Brassica napus Species 0.000 description 2
- 235000004977 Brassica sinapistrum Nutrition 0.000 description 2
- 240000008620 Fagopyrum esculentum Species 0.000 description 2
- 235000009419 Fagopyrum esculentum Nutrition 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 2
- 244000020551 Helianthus annuus Species 0.000 description 2
- 235000003222 Helianthus annuus Nutrition 0.000 description 2
- 240000005979 Hordeum vulgare Species 0.000 description 2
- 235000007340 Hordeum vulgare Nutrition 0.000 description 2
- 235000004431 Linum usitatissimum Nutrition 0.000 description 2
- 240000006240 Linum usitatissimum Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 244000046052 Phaseolus vulgaris Species 0.000 description 2
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 2
- 235000004443 Ricinus communis Nutrition 0.000 description 2
- 235000011684 Sorghum saccharatum Nutrition 0.000 description 2
- 240000004922 Vigna radiata Species 0.000 description 2
- 235000010721 Vigna radiata var radiata Nutrition 0.000 description 2
- 235000011469 Vigna radiata var sublobata Nutrition 0.000 description 2
- 240000001417 Vigna umbellata Species 0.000 description 2
- 235000011453 Vigna umbellata Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 235000019713 millet Nutrition 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 235000020232 peanut Nutrition 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 239000003981 vehicle Substances 0.000 description 2
- 208000003643 Callosities Diseases 0.000 description 1
- 206010020649 Hyperkeratosis Diseases 0.000 description 1
- 241001124569 Lycaenidae Species 0.000 description 1
- 240000000528 Ricinus communis Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 235000019198 oils Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 235000015099 wheat brans Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Agronomy & Crop Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method, a device, a processor, agricultural machinery and a storage medium for adjusting operation parameters of the agricultural machinery, which are applied to the agricultural machinery, wherein the method comprises the following steps: acquiring a crop image to be detected, wherein the crop image to be detected is obtained by shooting crops collected by agricultural machinery; inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model; obtaining a detection result output by the machine learning model, and determining the evaluation index value of the agricultural machine according to the detection result; and adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value, and adjusting the operation parameters of the agricultural machine in time so as to improve the harvesting quality of crops.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to a method, a device, a processor, an agricultural machine and a storage medium for adjusting operation parameters of the agricultural machine.
Background
When crops are mature, the agricultural harvesting machine can enter a farmland to harvest, and the harvesting methods of the crops are different according to the conditions of the crops and the farmland and the operation efficiency. In a traditional harvesting mode, an agricultural mechanical arm needs to fully know the variety, height, maturity, moisture content of stems and grains and lodging conditions of crops before mechanical harvesting so as to make necessary adjustment on a machine, and the adjustment needs to be made in real time according to the conditions in the harvesting process.
For example, in most of the existing grain harvesters, parameters of components such as a fan, a roller and the like are set according to manual experience before harvesting operation, and are not adjusted in the harvesting process; the adjustment of parameters of parts such as the header is generally manually performed by a manual operator according to personal experiences of the operator in the process of harvesting operation, such as evaluation of impurity-containing conditions, breakage conditions, loss conditions and the like of the harvest. The parameters are adjusted manually and according to experience, on one hand, the labor intensity of manpower is high, time and labor are wasted, and the operation efficiency is not high, on the other hand, the calculation error probability is high due to the fact that the parameters are adjusted completely depending on the personal experience of manual work, the harvesting quality is easy to be unstable, and the integral level is not high.
At present, China is still in the transition stage from traditional agriculture to modern agriculture, and high-efficiency and accurate agriculture is realized by depending on intellectualization and unmanned agriculture of agricultural machinery. The realization of intellectualization and unmanned aerial vehicle is one of the main directions of future development of agricultural harvesting machinery, and the automatic control is the key for realizing the intellectualization and unmanned aerial vehicle. In the field operation of the agricultural harvesting machine, the automatic control execution component completes the optimal parameter setting and the optimal state adjustment, which are the core contents of intellectualization, and in this respect, the development of the current agricultural harvesting machine is extremely slow, and the mechanical harvesting quality is also to be improved urgently.
Disclosure of Invention
An object of an embodiment of the present invention is to provide a method, an apparatus, a processor, an agricultural machine, and a storage medium for adjusting an operation parameter of an agricultural machine, which can adjust the operation parameter of the agricultural machine in time to improve the harvest quality of crops.
In order to achieve the above object, a first aspect of the present invention provides a method for adjusting an operating parameter of an agricultural machine, comprising:
acquiring an image of a crop to be detected, wherein the image of the crop to be detected is obtained by shooting the crop collected by agricultural machinery;
inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model;
obtaining a detection result output by the machine learning model, and determining an agricultural machine evaluation index value according to the detection result;
and adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value.
In an embodiment of the invention, the method further comprises: acquiring a test crop image, wherein the test crop image carries preset marking information; inputting the image of the test crop into a machine learning model, and acquiring a test result output by the machine learning model; and adjusting the model parameters of the machine learning model according to the test result and the preset marking information.
In the embodiment of the present invention, adjusting the model parameters of the machine learning model according to the test result and the preset labeling information includes: calculating the intersection ratio of the test result and a preset marking result to determine the test accuracy of the machine learning model; and under the condition that the test accuracy is not within the preset threshold range, adjusting the model parameters of the machine learning model.
In an embodiment of the present invention, the agricultural machine evaluation index value includes at least one of a trash content and a breakage rate.
In an embodiment of the invention, the machine learning model comprises at least one of a clutter-containing model and a fragmentation model;
inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model, wherein the method comprises the following steps: inputting the crop image to be detected into a trash model, and analyzing the trash content of the crop image to be detected through the trash model; and inputting the crop image to be detected into the crushing model, and analyzing the crushing rate of the crop image to be detected through the impurity-containing model.
In an embodiment of the present invention, the agricultural machine evaluation index value includes a harvest yield; the adjustment of the operation parameters of the agricultural machine according to the agricultural machine evaluation index value comprises the following steps: determining the used capacity of a grain tank of the agricultural machine according to the harvest capacity; and adjusting the operation parameters of the agricultural machine according to the used capacity when the used capacity reaches the preset capacity.
In an embodiment of the present invention, the agricultural machine evaluation index value includes a loss rate; the method further comprises the following steps: acquiring a pressure induction value of a crop corresponding to a crop image to be detected through a loss sensor; and determining the loss rate of the agricultural machine according to a preset proportion system, the pressure induction value and a preset empirical statistic value.
In an embodiment of the invention, the machine learning model is trained by: obtaining a crop image sample, wherein the crop image sample carries sample labeling information; inputting the crop image sample into a machine learning model to train the machine learning model; obtaining a sample prediction result output by a machine learning model; calculating the intersection ratio of the sample prediction result and the sample marking information; and determining to obtain the trained machine learning model under the condition that the intersection ratio of the sample prediction result and the sample marking information is within a preset threshold range. In an embodiment of the invention, the machine learning model includes at least one of a clutter-containing model and a fragmentation model; inputting crop image samples into a machine learning model to train the machine learning model comprises: inputting the crop image sample into a model containing impurities so as to train the model containing impurities; and inputting the crop image sample into the crushing model to train the crushing model.
In an embodiment of the present invention, the operational parameters include at least one of: header height, reel rotating speed, reel height, fan rotating speed, sieve sheet aperture and agricultural machine moving speed.
In an embodiment of the present invention, adjusting the operation parameter of the agricultural machine according to the agricultural machine evaluation index value includes: under the condition that the agricultural machine evaluation index value is determined to be not in accordance with the preset standard threshold value, generating a corresponding control instruction according to the agricultural machine evaluation index value; and adjusting the operation parameters of the agricultural machine according to the control command.
A second aspect of the invention provides a processor programmed when executed to perform a method for adjusting a work parameter of an agricultural machine according to any one of the preceding claims.
In a third aspect, the present invention provides an apparatus for adjusting operating parameters of an agricultural machine, comprising:
the image acquisition equipment is configured to acquire an image of a crop to be detected; and
such as the processor described above.
A fourth aspect of the present invention provides an agricultural machine, comprising: the device for adjusting the operation parameters of the agricultural machine.
A fifth aspect of the invention provides a machine-readable storage medium having instructions stored thereon for causing a machine to perform the above-described method for adjusting a work parameter of an agricultural machine.
According to the technical scheme, the acquired image of the crop to be detected is input into the machine learning model, the corresponding detection result is output through the machine learning model, so that the evaluation index value of the agricultural machine is determined, and corresponding adjustment can be timely carried out on the operation parameter of the agricultural machine according to the evaluation index value of the agricultural machine.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
FIG. 1 schematically illustrates a flow diagram of a method for adjusting operating parameters of an agricultural machine according to an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow diagram for machine learning model optimization according to an embodiment of the invention;
FIG. 3 schematically shows a flow diagram of the training steps of a machine learning model according to an embodiment of the invention;
FIG. 4 is a block diagram schematically illustrating the structure of an apparatus for adjusting the operating parameters of an agricultural machine according to an embodiment of the present invention;
FIG. 5 schematically shows a block diagram of an image analysis module according to an embodiment of the present invention;
FIG. 6 is a block diagram schematically illustrating the structure of an apparatus for adjusting the working parameters of an agricultural machine according to another embodiment of the present invention;
FIG. 7 is a block diagram schematically illustrating the construction of an agricultural machine according to an embodiment of the present invention;
fig. 8 schematically shows an internal structure diagram of a computer apparatus according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
Fig. 1 schematically shows a flow diagram of a method for adjusting a work parameter of an agricultural machine according to an embodiment of the present invention. In one embodiment of the present invention, as shown in fig. 1, there is provided a method for adjusting operating parameters of an agricultural machine, comprising the steps of:
And 102, inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model.
And 103, acquiring a detection result output by the machine learning model, and determining an agricultural machine evaluation index value according to the detection result.
And 104, adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value.
The crop image to be detected refers to an image obtained by acquiring an image of a crop which is acquired by the agricultural machine in real time through image acquisition equipment in the operation process of the agricultural machine, and examples of the image acquisition equipment may include, but are not limited to, a video camera, a still camera, a video camera, or various electronic devices with a photographing function. Agricultural machinery refers to various machines used in crop cultivation and animal husbandry production processes, as well as in the primary processing and treatment of agricultural and animal products, and further, agricultural machinery refers to agricultural harvesting machinery, and specifically includes, but is not limited to, harvesting machinery for harvesting the following several types of crops: the first kind is all grain crops such as rice, wheat, corn, millet, sorghum, buckwheat, highland barley and the like; the second kind is bean crops such as soybean, mung bean, red bean and the like; the third kind is oil crops such as rapeseed, sunflower, castor-oil plant, flax, peanut, etc.; and other crops requiring evaluation of trash content, breakage rate, loss rate.
In the operation process of the agricultural machine, in the description of the example, the crops mainly take wheat as an example, but the crops actually harvested can also be all grain crops such as rice, wheat, corn, millet, sorghum, buckwheat, highland barley and the like; bean crops such as soybean, mung bean and red bean, and oil crops such as rapeseed, sunflower, castor, flax and peanut. The corresponding impurity rate, breakage rate and loss rate of the crops can be differentiated according to the different crops. For example, when wheat is harvested, the impurity content is the proportion of impurities except wheat grains such as wheat straw and wheat bran contained in the harvested wheat; when the corn is harvested, the impurity content is the proportion of the harvested corn to the impurities except the corn kernels such as corn stalks, corn cobs and bracts. The same applies to the breakage rate, which is the ratio of the number of broken wheat particles in the harvested wheat when the wheat is harvested; when the corn is harvested, the number of broken corns in the harvested corn is the ratio.
The agricultural machine processor can input the acquired crop image to be detected into the machine learning model, analyze the crop image to be detected through the machine learning model and acquire the detection result output by the machine learning model, so that an agricultural machine evaluation index value can be determined according to the detection result, and the operation parameter of the agricultural machine is adjusted according to the determined agricultural machine evaluation index value. The agricultural machine evaluation index value is an evaluation value of the agricultural machine itself for the harvest performance when the agricultural machine is operating.
In one embodiment, the operational parameters include at least one of: header height, reel rotating speed, reel height, fan rotating speed, sieve sheet aperture and agricultural machine moving speed.
In one embodiment, the agricultural machine evaluation index value includes at least one of a trash content and a breakage rate.
The trash content is a space ratio of the trash contained in the harvested agricultural products to the whole harvested agricultural products within a certain range. The breakage rate is the ratio of the number of broken grains of harvested crop to the total harvested crop in a certain range. For example, when a certain mu of wheat farmland is harvested, the trash content is the space ratio of the wheat straw contained in the harvested wheat to all the wheat grains. The breakage rate is the ratio of the number of broken wheat grains to the total number of wheat grains in the harvested wheat.
Specifically, the agricultural machine comprises a plurality of components, such as a header, a reel, a fan, a roller, a sieve sheet and other agricultural machine harvesting execution components. Since the evaluation index value of the agricultural machine is determined by the plurality of components in common, if the evaluation index value of the agricultural machine is to be increased, it is necessary to adjust the operation parameters of the respective components. When each evaluation index value of the agricultural machine is determined according to the detection result output by the machine learning model, the operation parameters of the agricultural machine can be adjusted in real time according to the determined evaluation index value of the agricultural machine. Furthermore, in order to improve the harvesting performance of the agricultural machine, the evaluation values corresponding to various indexes of the agricultural machine can be calculated in real time according to the current harvesting condition of the agricultural machine, so that the operation parameters to be adjusted by various harvesting components of the agricultural machine can be determined.
In one embodiment, the method further comprises: acquiring a test crop image, wherein the test crop image carries preset marking information; inputting the image of the test crop into a machine learning model, and acquiring a test result output by the machine learning model; and adjusting the model parameters of the machine learning model according to the test result and the preset marking information.
Since the agricultural machine evaluation value is determined according to the detection result output by the machine learning model, if the accuracy of the evaluation index value of the agricultural machine is to be ensured, the prediction accuracy of the machine learning model needs to be determined first, that is, the model parameters of the machine learning model can be adjusted to improve the prediction accuracy of the machine learning model. Specifically, a test crop image can be obtained first, and the test crop image is essentially not different from a crop image to be detected, and belongs to an image corresponding to a crop contained in a field collected in real time in the operation process of agricultural machinery. The test crop image is mainly used for testing the prediction accuracy of the machine learning model, so that the test crop image contains preset labeling information. The preset labeling information refers to information obtained by manually labeling the image in advance, and the labeled information can comprise broken wheat grains, wheat straws and the like. After the machine learning model identifies and predicts the input test crop image and outputs the corresponding test result, the test result determined by the machine learning model can be compared with the preset marking information, so that the accuracy of the machine learning model can be determined. When the accuracy of the machine learning model is low, the model parameters of the machine learning model can be adjusted to improve the prediction accuracy of the machine learning model.
In one embodiment, the adjusting the model parameters of the machine learning model according to the test result and the preset labeling information includes: calculating the intersection ratio of the test result and a preset marking result to determine the test accuracy of the machine learning model; and under the condition that the test accuracy is not within the preset threshold range, adjusting the model parameters of the machine learning model.
After the test crop image is input into the machine learning model and the test result output by the machine learning model is obtained, the intersection ratio of the test result and the preset labeling result can be calculated and taken as the prediction accuracy of the machine learning model, and under the condition that the test accuracy is not within the preset threshold range, the prediction accuracy of the machine learning model can be determined to be low, and model parameters of the machine learning model need to be adjusted to improve the prediction accuracy of the machine learning model. This process may also be referred to as an optimization process of the model. As shown in the flow diagram of model optimization shown in fig. 2, a machine learning model is deployed first, and an acquired test crop image is input into the machine learning model to determine an evaluation value of the machine learning model, that is, a score of the machine learning model is determined by calculating an intersection ratio of a test result and a preset labeling result. If the evaluation value of the machine learning model is low, the model parameters of the machine learning model can be correspondingly adjusted and optimized.
In one embodiment, the machine learning model includes at least one of a clutter-containing model and a fragmentation model. Inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model, wherein the method comprises the following steps: inputting the crop image to be detected into a trash model, and analyzing the trash content of the crop image to be detected through the trash model; and inputting the crop image to be detected into the crushing model, and analyzing the crushing rate of the crop image to be detected through the impurity-containing model.
The agricultural machine evaluation index value includes at least one of impurity content and breakage rate. In order to improve the accuracy of the determination of the evaluation index value of the agricultural machine, the machine learning model may include a model containing impurities or a fragmentation model, and different evaluation index values may be determined and predicted by different models. That is, when the agricultural machine evaluation index value includes both the impurity percentage and the breakage percentage, the machine learning model may include both the impurity percentage model and the breakage model, and the impurity percentage of the agricultural machine may be confirmed by the impurity percentage model and the breakage percentage of the agricultural machine may be confirmed by the breakage model.
Further, when the crop image to be detected is input into the machine learning model and analyzed through the machine learning model, the crop image to be detected is actually input into the impurity-containing model, and the impurity content of the crop image to be detected is analyzed through the impurity-containing model so as to determine the impurity content corresponding to the crop image to be detected; and inputting the crop image to be detected into the crushing model, and analyzing the crushing rate of the crop image to be detected through the impurity-containing model so as to determine the crushing rate corresponding to the crop image to be detected.
Specifically, the cross-over ratio ═ Σ (S)i∩Ei)/(Si∪Ei). When the impurity rate corresponding to the crop image to be detected is determined through the impurity model, SiDetermining the region containing the trash (such as wheat straw) in the input image of the crop to be detected for the trash model, EiThe preset marking information of the crop image to be detected is marked as an area containing sundry chips (such as wheat straws). When the corresponding breakage rate of the crop image to be detected is determined through the breakage model, SiDetermining for the fragmentation model the number of fragmented particles (e.g. fragmented wheat grains) contained in the input image of the crop to be examined, EiIn the preset marking information of the crop image to be detectedLabeled as containing the number of broken particles (e.g., broken wheat grains). In this way, the impurity content and the breakage rate corresponding to the crop image to be detected can be respectively calculated. Furthermore, the intersection ratio of the impurity-containing model and the crushing model can be respectively calculated, and the prediction effect of the model is evaluated according to the value of the intersection ratio.
In one embodiment, the agricultural machine evaluation index value comprises a harvest yield; the adjustment of the operation parameters of the agricultural machine according to the agricultural machine evaluation index value comprises the following steps: determining the used capacity of a grain tank of the agricultural machine according to the harvest capacity; and adjusting the operation parameters of the agricultural machine according to the used capacity when the used capacity reaches the preset capacity.
The agricultural machine evaluation index value may include at least one of impurity content, breakage rate, and yield. The harvest amount refers to the current corresponding harvest amount of the crops in the image of the crops to be detected, and the currently used capacity of the grain tank of the agricultural machine, namely the amount of grains contained in the grain tank of the agricultural machine, can be determined according to the harvest amount of the crops. Specifically, the image acquisition device can be installed at a proper position selected in the grain tank of the agricultural machine in advance, and the camera parameters of the image acquisition device are corrected, so that the image corresponding to the crop piled in the grain tank of the agricultural machine can be acquired through the installed image acquisition device. Specifically, agricultural machine can accomodate it in agricultural machine's grain tank after reaping crops, consequently can utilize the image acquisition equipment of installation in the grain tank to shoot this part crops that have reaped, obtains the corresponding crop image that detects to detect, and will detect that detect the crop image input to machine learning model in, can confirm the harvest yield that detects the crop correspondence according to machine learning model, can determine the used capacity of agricultural machine grain tank according to the harvest yield of crop. The preset capacity is a threshold value preset by a technician, the preset capacity can be set to be close to the total capacity of the grain tank, and then under the condition that the used capacity of the grain tank reaches the preset capacity, the grain tank of the agricultural machine is indicated to be in a full state, the harvesting operation of the agricultural machine is indicated to be stopped, the crops in the grain tank can be firstly unloaded, so that the situation that the crops in the grain tank overflow or the grain tank is full to cause that the agricultural machine cannot continuously harvest is avoided. Therefore, the operation parameters of the agricultural machine can be adjusted according to the used capacity, namely, the operation parameters of the agricultural machine can be adjusted to stop operation, such as the rotating speed of the reel, the rotating speed of the fan, the moving speed of the agricultural machine and the like, and the operation can be suspended by adjusting the operation parameters to 0.
In one embodiment, the agricultural machine evaluation index value comprises a loss rate. The method further comprises the following steps: acquiring a pressure induction value of a crop corresponding to a crop image to be detected through a loss sensor; and determining the loss rate of the agricultural machine according to a preset proportion system, the pressure induction value and a preset empirical statistic value.
In this embodiment, the agricultural machine evaluation index value may include at least one of a trash content, a breakage rate, a yield, and a loss rate. Further, can install loss sensor in advance at agricultural machine's grain outlet department, when reaping the crops that contain in the farmland region that detects the crop image correspondence of detecting, during crops process this loss sensor, the pressure value of the crops that the loss sensor can sense the reaping promptly determines the pressure induction value of the crop that detects the crop image correspondence promptly to can calculate corresponding loss rate. The loss rate K is K × K (P/M), where K is a preset ratio system, P is a pressure sensing value of the grain outlet, and M is a preset empirical statistical value, such as the weight of 100 wheat grains on average. When the loss rate is high, the agricultural machine may not well harvest crops completely, and the operation parameters of the agricultural machine need to be adjusted so as to avoid waste of the crops.
In one embodiment, for the trash content, a visual image feature of wheat not higher than 2% (national standard) may be used as a normal trash content standard, and a visual image feature of wheat higher than 2% may be used as an excessively high trash content standard, that is, when the trash content corresponding to the crop image to be detected is lower than 2%, the trash content may be considered to be within a normal range, and when the trash content is higher than 2%, the trash content may be considered to be excessively high, and the operation parameters of the agricultural machine need to be adjusted. For the breakage rate, the visual image characteristics of the wheat which are not higher than 1 percent (national standard) are taken as the normal standard of the breakage rate, and the visual image characteristics of the wheat which are higher than 1 percent are taken as the overhigh standard of the breakage rate; that is, when the breakage rate corresponding to the crop image to be detected is lower than 1%, the breakage rate can be considered to be within a normal range, and when the breakage rate is higher than 1%, the breakage rate is considered to be too high, and the operation parameters of the agricultural machine need to be adjusted. For the loss rate, the data characteristic of the wheat loss sensor which is not higher than 1.2 percent (national standard) can be taken as the normal standard of the loss rate, and the data characteristic of the wheat loss sensor which is higher than 1.2 percent can be taken as the overhigh standard of the loss rate. That is, when the loss rate corresponding to the crop image to be detected is lower than 1.2%, the loss rate is considered to be within the normal range, and when the loss rate is higher than 1.2%, the loss rate is considered to be too high, and the operation parameters of the agricultural machine need to be adjusted. The visual image features are obtained by extracting the features of the crop image to be detected.
In one embodiment, adjusting the operation parameter of the agricultural machine according to the agricultural machine evaluation index value comprises: under the condition that the agricultural machine evaluation index value is determined to be not in accordance with the preset standard threshold value, generating a corresponding control instruction according to the agricultural machine evaluation index value; and adjusting the operation parameters of the agricultural machine according to the control command.
After the evaluation index values corresponding to various evaluations of the agricultural machine are determined, the operation parameters of the agricultural machine can be adjusted according to the agricultural machine evaluation index values. And when the evaluation index value of the agricultural machine does not meet the preset standard threshold value, indicating that the operation parameters of the agricultural machine need to be adjusted correspondingly. When the operation parameters are adjusted, the processor can generate a corresponding control instruction according to each agricultural machine evaluation index value, and the control instruction is sent to each execution component in the agricultural machine, so that the operation parameters of the agricultural machine can be adjusted. Specifically, when the impurity rate is too high, the adjusted control instruction may include: the height of the cutting table is increased, the height of the reel is increased, the rotating speed of a fan is increased, the opening degree of the sieve sheet is reduced, the travelling speed is reduced and the like; when the crushing rate is too high, adjusting the control command may include: reducing the rotating speed of the roller and the like; when the loss rate is too high, adjusting the control instructions may include: the height of the reel is increased, the rotating speed of the reel is reduced, the rotating speed of the fan is reduced, the opening of the sieve sheet is increased, the running speed of the agricultural machine is reduced, and the like. And each execution component in the agricultural machine can automatically adjust harvesting components such as a header, a reel, a fan, a roller and a sieve sheet and the driving speed of the agricultural machine according to a control instruction sent by the processor, so as to finish automatic harvesting of crops.
In one embodiment, as shown in FIG. 3, the machine learning model is trained by:
And step 303, obtaining a sample prediction result output by the machine learning model.
And step 304, calculating the intersection ratio of the sample prediction result and the sample marking information.
And 305, determining to obtain the trained machine learning model under the condition that the intersection ratio of the sample prediction result and the sample marking information is within a preset threshold range.
Before the machine learning model is put into practical use, the machine learning model can be trained in advance, and the trained machine learning model can effectively guarantee the prediction accuracy of the image. Firstly, a crop image sample can be obtained, and a test crop image is input into a machine learning model, so that the machine learning model can automatically learn the image characteristics in the test crop image, and determine the impurity rate, the breakage rate and the like corresponding to the test crop image. The crop image sample has no essential difference from the image to be predicted and the image of the tested crop, and the name is only distinguished for convenience of description. In order to determine the accuracy of the machine learning model, sample labeling information may be manually added to the crop image samples in advance, that is, broken crop particles or included impurities and the like are manually labeled in advance in each crop image sample. After the crop image samples are input into the machine learning model, the sample prediction results output by the machine learning model can be obtained, the intersection ratio of the sample prediction results and the sample labeling information is calculated, and the intersection ratio is used as the prediction accuracy of the machine learning model during training.
In one embodiment, the machine learning model includes at least one of a clutter model and a fragmentation model. Inputting crop image samples into a machine learning model to train the machine learning model comprises: inputting the crop image sample into a model containing impurities so as to train the model containing impurities; and inputting the crop image sample into the crushing model to train the crushing model.
The agricultural machine evaluation index value includes at least one of impurity content and breakage rate. In order to improve the accuracy of judging the evaluation index value of the agricultural machine, the machine learning model may include a hybrid model or a fragmentation model, so as to judge and predict different evaluation index values through different models. When crop image samples are input into a machine learning model for training, the miscellaneous model and the fragmentation model can be trained.
Cross-over ratio ═ Σ (S)i∩Ei)/(Si∪Ei). When determining the impurity rate corresponding to the crop image sample through the impurity model contained in the machine learning model, SiDetermining areas containing trash (e.g. straw) in the input crop image sample for the trash-containing model, EiThe sample labeling information of the crop image sample is labeled as a region containing trash (such as wheat straw). When the corresponding breakage rate of the crop image sample is determined through the breakage model contained in the machine learning model, SiDetermining for the fragmentation model the number of fragmented particles, e.g. crushed wheat grains, contained in the input sample of the crop imageiThe sample labeling information of the crop image sample is labeled to include the number of broken grains (such as broken wheat grains). In this way, the prediction accuracy of the machine learning model on the impurity rate and the breakage rate of the crop image sample in the training process can be calculated.
When the intersection ratio of the sample prediction result and the sample marking information is within a preset threshold range, namely the prediction accuracy of the machine learning model is within the preset threshold range, the trained machine learning model can be determined; if the intersection ratio of the sample prediction result and the sample marking information is not within the preset threshold range, the machine learning model needs to be trained continuously.
According to the method for adjusting the agricultural machine operation parameters, the acquired images of the crops to be detected are input into the machine learning model, the corresponding detection results are output through the machine learning model, so that the evaluation index values of the agricultural machines are determined, and the operation parameters of the agricultural machines can be adjusted correspondingly according to the evaluation index values of the agricultural machines in time.
In one embodiment, as shown in fig. 4, there is provided an apparatus 400 for adjusting working parameters of an agricultural machine, comprising an image acquisition module, an image analysis module, an evaluation index value confirmation module, and a working parameter adjustment module, wherein:
the image acquisition module 401 is configured to acquire an image of a crop to be detected, where the image of the crop to be detected is obtained by shooting a crop collected by an agricultural machine.
And the image analysis module 402 is configured to input the crop image to be detected into the machine learning model, and analyze the crop image to be detected through the machine learning model.
And an evaluation index value confirmation module 403 configured to acquire the detection result output by the machine learning model and determine an agricultural machine evaluation index value according to the detection result.
And the operation parameter adjusting module 404 is configured to adjust the operation parameters of the agricultural machine according to the agricultural machine evaluation index value.
In one embodiment, as shown in fig. 4, the apparatus 400 for adjusting working parameters of an agricultural machine further includes a model optimization module 405 configured to obtain a test crop image, where the test crop image carries preset labeling information; inputting the test crop image to a machine learning model; obtaining a test result output by a machine learning model; and adjusting the model parameters of the machine learning model according to the test result and the preset marking information.
In one embodiment, the model optimization module 405 is further configured to calculate an intersection ratio of the test result and a preset labeling result to determine a test accuracy of the machine learning model; and under the condition that the test accuracy is not within the preset threshold range, adjusting the model parameters of the machine learning model.
In one embodiment, the agricultural machine evaluation index value includes at least one of a trash content and a breakage rate.
In one embodiment, as shown in FIG. 5, image analysis module 402 includes a clutter analysis module 402A and a crush analysis module 402B; the impurity-containing analysis module 402A is configured to input the crop image to be detected to the impurity-containing model, and analyze the impurity-containing rate of the crop image to be detected through the impurity-containing model; the crushing analysis module 402B is configured to input the crop image to be detected to the crushing model, and analyze the crushing rate of the crop image to be detected by the impurity-containing model.
In one embodiment, the agricultural machine evaluation index value comprises a harvest yield; as shown in fig. 5, the image analysis module 402 further includes a harvest-quantity confirmation module 402C configured to determine a used capacity of a grain tank of the agricultural machine based on the harvest quantity. The work parameter adjustment module 404 is further configured to adjust a work parameter of the agricultural machine based on the used capacity if the used capacity has reached the preset capacity.
In one embodiment, the agricultural machine evaluation index value comprises a loss rate; as shown in fig. 5, the image analysis module 402 further includes a loss analysis module 402D configured to obtain a pressure sensing value of a crop corresponding to the image of the crop to be detected through a loss sensor; and determining the loss rate of the agricultural machine according to a preset proportion system, the pressure induction value and a preset empirical statistic value.
In one embodiment, the apparatus 400 for adjusting the working parameters of the agricultural machine further includes a model training module (not shown in the figure) configured to obtain a crop image sample, where the crop image sample carries sample labeling information; inputting the crop image sample into a machine learning model to train the machine learning model; obtaining a sample prediction result output by a machine learning model; calculating the intersection ratio of the sample prediction result and the sample marking information; and determining to obtain the trained machine learning model under the condition that the intersection ratio of the sample prediction result and the sample marking information is within a preset threshold range.
In one embodiment, the machine learning model includes at least one of a clutter model and a fragmentation model; the model training module is further configured to input crop image samples into the hybrid model to train the hybrid model; and inputting the crop image sample into the crushing model to train the crushing model.
In one embodiment, the operational parameters include at least one of: header height, reel rotating speed, reel height, fan rotating speed, sieve sheet aperture and agricultural machine moving speed.
In one embodiment, the operation parameter adjustment module 404 is further configured to generate a corresponding control instruction according to the agricultural machine evaluation index value in case that the agricultural machine evaluation index value is determined not to meet the preset standard threshold; and adjusting the operation parameters of the agricultural machine according to the control command.
The device for adjusting the working parameters of the agricultural machine comprises a processor and a memory, wherein the modules are stored in the memory as program units, and the processor executes the program modules stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the operation parameters of the agricultural machinery can be adjusted by adjusting the kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
Embodiments of the present invention provide a storage medium having a program stored thereon, which when executed by a processor, implements the above-described method for adjusting a work parameter of an agricultural machine.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program is used for executing the method for adjusting the operation parameters of the agricultural machine during running.
In one embodiment, as shown in fig. 6, there is provided an apparatus 600 for adjusting a work parameter of an agricultural machine, the apparatus comprising:
the image acquisition device 601 is configured to acquire an image of a crop to be detected.
A processor 602 configured to perform the above-described method for adjusting a work parameter of an agricultural machine.
In one embodiment, as shown in fig. 7, there is provided an agricultural machine 700 comprising: the apparatus 600 for adjusting the operating parameters of an agricultural machine is described above.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor a01, an interface a02, a memory (not shown in the figure), and a database (not shown in the figure) connected through a system bus. Wherein processor a01 of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises an internal memory a03 and a non-volatile storage medium a 04. The non-volatile storage medium a04 stores an operating system B01, a computer program B02, and a database (not shown in the figure). The internal memory a03 provides an environment for the operation of the operating system B01 and the computer program B02 in the nonvolatile storage medium a 04. The database of the computer equipment is used for storing relevant data such as the image of the crop to be detected. The interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program B02 is executed by the processor A01 to implement a method for adjusting a work parameter of an agricultural machine.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps: acquiring an image of a crop to be detected, wherein the image of the crop to be detected is obtained by shooting the crop collected by agricultural machinery; inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model; obtaining a detection result output by the machine learning model, and determining an agricultural machine evaluation index value according to the detection result; and adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value.
In one embodiment, the method further comprises: acquiring a test crop image, wherein the test crop image carries preset marking information; inputting the test crop image to a machine learning model; obtaining a test result output by a machine learning model; and adjusting the model parameters of the machine learning model according to the test result and the preset marking information.
In one embodiment, the adjusting the model parameters of the machine learning model according to the test result and the preset labeling information includes: calculating the intersection ratio of the test result and a preset marking result to determine the test accuracy of the machine learning model; and under the condition that the test accuracy is not within the preset threshold range, adjusting the model parameters of the machine learning model.
In one embodiment, the agricultural machine evaluation index value includes at least one of a trash content and a breakage rate.
In one embodiment, the machine learning model includes at least one of a clutter-containing model and a fragmentation model; inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model, wherein the method comprises the following steps: inputting the crop image to be detected into a trash model, and analyzing the trash content of the crop image to be detected through the trash model; and inputting the crop image to be detected into the crushing model, and analyzing the crushing rate of the crop image to be detected through the impurity-containing model.
In one embodiment, the agricultural machine evaluation index value comprises a harvest yield; the adjustment of the operation parameters of the agricultural machine according to the agricultural machine evaluation index value comprises the following steps: determining the used capacity of a grain tank of the agricultural machine according to the harvest capacity; and adjusting the operation parameters of the agricultural machine according to the used capacity when the used capacity reaches the preset capacity.
In one embodiment, the agricultural machine evaluation index value comprises a loss rate; the method further comprises the following steps: acquiring a pressure induction value of a crop corresponding to a crop image to be detected through a loss sensor; and determining the loss rate of the agricultural machine according to a preset proportion system, the pressure induction value and a preset empirical statistic value.
In one embodiment, the machine learning model is trained by: obtaining a crop image sample, wherein the crop image sample carries sample labeling information; inputting the crop image sample into a machine learning model to train the machine learning model; obtaining a sample prediction result output by a machine learning model; calculating the intersection ratio of the sample prediction result and the sample marking information; and determining to obtain the trained machine learning model under the condition that the intersection ratio of the sample prediction result and the sample marking information is within a preset threshold range.
In one embodiment, the machine learning model includes at least one of a clutter model and a fragmentation model; inputting crop image samples into a machine learning model to train the machine learning model comprises: inputting the crop image sample into a model containing impurities so as to train the model containing impurities; and inputting the crop image sample into the crushing model to train the crushing model.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: acquiring an image of a crop to be detected, wherein the image of the crop to be detected is obtained by shooting the crop collected by agricultural machinery; inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model; obtaining a detection result output by the machine learning model, and determining an agricultural machine evaluation index value according to the detection result; and adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value.
In one embodiment, the method further comprises: acquiring a test crop image, wherein the test crop image carries preset marking information; inputting the test crop image to a machine learning model; obtaining a test result output by a machine learning model; and adjusting the model parameters of the machine learning model according to the test result and the preset marking information.
In one embodiment, the adjusting the model parameters of the machine learning model according to the test result and the preset labeling information includes: calculating the intersection ratio of the test result and a preset marking result to determine the test accuracy of the machine learning model; and under the condition that the test accuracy is not within the preset threshold range, adjusting the model parameters of the machine learning model.
In one embodiment, the agricultural machine evaluation index value includes at least one of a trash content and a breakage rate.
In one embodiment, the machine learning model includes at least one of a clutter-containing model and a fragmentation model; inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model, wherein the method comprises the following steps: inputting the crop image to be detected into a trash model, and analyzing the trash content of the crop image to be detected through the trash model; and inputting the crop image to be detected into the crushing model, and analyzing the crushing rate of the crop image to be detected through the impurity-containing model.
In one embodiment, the agricultural machine evaluation index value comprises a harvest yield; the adjustment of the operation parameters of the agricultural machine according to the agricultural machine evaluation index value comprises the following steps: determining the used capacity of a grain tank of the agricultural machine according to the harvest capacity; and adjusting the operation parameters of the agricultural machine according to the used capacity when the used capacity reaches the preset capacity.
In one embodiment, the agricultural machine evaluation index value comprises a loss rate; the method further comprises the following steps: acquiring a pressure induction value of a crop corresponding to a crop image to be detected through a loss sensor; and determining the loss rate of the agricultural machine according to a preset proportion system, the pressure induction value and a preset empirical statistic value.
In one embodiment, the machine learning model is trained by: obtaining a crop image sample, wherein the crop image sample carries sample labeling information; inputting the crop image sample into a machine learning model to train the machine learning model; obtaining a sample prediction result output by a machine learning model; calculating the intersection ratio of the sample prediction result and the sample marking information; and determining to obtain the trained machine learning model under the condition that the intersection ratio of the sample prediction result and the sample marking information is within a preset threshold range.
In one embodiment, the machine learning model includes at least one of a clutter model and a fragmentation model; inputting crop image samples into a machine learning model to train the machine learning model comprises: inputting the crop image sample into a model containing impurities so as to train the model containing impurities; and inputting the crop image sample into the crushing model to train the crushing model.
In addition, as will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (14)
1. A method for adjusting operating parameters of an agricultural machine, applied to an agricultural machine, the method comprising:
acquiring a crop image to be detected, wherein the crop image to be detected is obtained by shooting crops collected by agricultural machinery;
inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model;
obtaining a detection result output by the machine learning model, and determining the evaluation index value of the agricultural machine according to the detection result;
and adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value.
2. The method of claim 1, further comprising:
acquiring a test crop image, wherein the test crop image carries preset marking information;
inputting the test crop image to the machine learning model;
obtaining a test result output by the machine learning model;
and adjusting the model parameters of the machine learning model according to the test result and preset labeling information.
3. The method of claim 2, wherein the adjusting the model parameters of the machine learning model according to the test result and preset labeling information comprises:
calculating the intersection ratio of the test result and the preset marking information to determine the test accuracy of the machine learning model;
and under the condition that the test accuracy is not within the range of a preset threshold value, adjusting the model parameters of the machine learning model.
4. The method according to claim 1, wherein the agricultural machine evaluation index value includes at least one of a trash content and a breakage rate; the machine learning model comprises at least one of a clutter-containing model and a fragmentation model;
the inputting the crop image to be detected into a machine learning model, and analyzing the crop image to be detected through the machine learning model includes:
inputting the crop image to be detected into the impurity-containing model, and analyzing the impurity content of the crop image to be detected through the impurity-containing model;
and inputting the crop image to be detected into the crushing model, and analyzing the crushing rate of the crop image to be detected through the impurity-containing model.
5. The method according to claim 1, wherein the agricultural machine evaluation index value includes a harvest yield; the adjusting the operation parameters of the agricultural machine according to the agricultural machine evaluation index value comprises the following steps:
determining the used capacity of a grain tank of the agricultural machine according to the harvest amount;
and adjusting the operation parameters of the agricultural machine according to the used capacity when the used capacity reaches the preset capacity.
6. The method according to claim 1, wherein the agricultural machine evaluation index value includes a loss rate; the method further comprises the following steps:
acquiring a pressure induction value of a crop corresponding to the image of the crop to be detected through a loss sensor;
and determining the loss rate of the agricultural machine according to a preset proportional system, the pressure induction value and the preset empirical statistic value.
7. The method of claim 1, wherein the machine learning model is trained by:
obtaining a crop image sample, wherein the crop image sample carries sample labeling information;
inputting the crop image samples into the machine learning model to train the machine learning model;
obtaining a sample prediction result output by the machine learning model;
calculating the intersection ratio of the sample prediction result and the sample marking information;
and determining to obtain the trained machine learning model under the condition that the intersection ratio of the sample prediction result and the sample marking information is within the preset threshold range.
8. The method of claim 7, wherein the machine learning model includes at least one of a clutter model and a fragmentation model;
the inputting the crop image samples into the machine learning model to train the machine learning model comprises:
inputting the crop image sample into the hybrid model to train the hybrid model;
inputting the crop image sample into the crushing model to train the crushing model.
9. The method of claim 1, wherein the operational parameter comprises at least one of:
header height, reel wheel speed, reel wheel height, fan speed, sieve piece aperture and agricultural machine's translation rate.
10. The method of claim 1, wherein adjusting the work parameter of the agricultural machine based on the agricultural machine evaluation index value comprises:
under the condition that the agricultural machine evaluation index value is determined to be not in accordance with a preset standard threshold, generating a corresponding control instruction according to the agricultural machine evaluation index value;
and adjusting the operation parameters of the agricultural machine according to the control command.
11. A processor configured to perform a method for adjusting a work parameter of an agricultural machine according to any one of claims 1 to 10.
12. An apparatus for adjusting operating parameters of an agricultural machine, the apparatus comprising:
the image acquisition equipment is configured to acquire an image of a crop to be detected; and
the processor of claim 11.
13. An agricultural machine, comprising:
an apparatus for adjusting operating parameters of an agricultural machine according to claim 12.
14. A machine-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, cause the processor to be configured to perform a method for adjusting a work parameter of a farm machine according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010954222.2A CN114255394A (en) | 2020-09-11 | 2020-09-11 | Method, device and processor for adjusting operation parameters of agricultural machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010954222.2A CN114255394A (en) | 2020-09-11 | 2020-09-11 | Method, device and processor for adjusting operation parameters of agricultural machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114255394A true CN114255394A (en) | 2022-03-29 |
Family
ID=80788081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010954222.2A Pending CN114255394A (en) | 2020-09-11 | 2020-09-11 | Method, device and processor for adjusting operation parameters of agricultural machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255394A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114938736A (en) * | 2022-05-11 | 2022-08-26 | 农业农村部南京农业机械化研究所 | Grain-saving and loss-reducing early warning method for grain combine harvester |
| CN115399139A (en) * | 2022-08-12 | 2022-11-29 | 中联农业机械股份有限公司 | Method, apparatus, storage medium, and processor for determining crop yield |
-
2020
- 2020-09-11 CN CN202010954222.2A patent/CN114255394A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114938736A (en) * | 2022-05-11 | 2022-08-26 | 农业农村部南京农业机械化研究所 | Grain-saving and loss-reducing early warning method for grain combine harvester |
| CN115399139A (en) * | 2022-08-12 | 2022-11-29 | 中联农业机械股份有限公司 | Method, apparatus, storage medium, and processor for determining crop yield |
| CN115399139B (en) * | 2022-08-12 | 2024-04-26 | 中联农业机械股份有限公司 | Method, apparatus, storage medium and processor for determining crop yield |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8954224B2 (en) | Creation of image databases for image evaluation | |
| RU2569958C2 (en) | Method of setting of at least one working body of self-propelled harvesting machine | |
| RU2350999C2 (en) | Method of optimising controlled machine parameters | |
| CN114255394A (en) | Method, device and processor for adjusting operation parameters of agricultural machine | |
| CN105806751A (en) | On-line monitoring system and method for crushing of cereals in grain tank of combine harvester | |
| Zannou et al. | Sorghum yield prediction using machine learning | |
| Mahirah et al. | Monitoring harvested paddy during combine harvesting using a machine vision-Double lighting system | |
| CN115511219A (en) | Intelligent prediction method and system for growth state of wheat crop | |
| Chen et al. | Online field performance evaluation system of a grain combine harvester | |
| CN115564280A (en) | Data management system for measuring insects in granary based on Internet of things | |
| CN110414859B (en) | 5T evaluation method for rice storage operation based on Internet of things technology | |
| CN116297249A (en) | Silage quality grading method, silage quality grading device and storage medium | |
| CN115292334A (en) | Intelligent planting method and system based on vision, electronic equipment and storage medium | |
| CN117589767B (en) | Tobacco leaf harvesting time determining method, electronic equipment and storage medium | |
| Rasmussen et al. | Anchor tuning in Faster R-CNN for measuring corn silage physical characteristics | |
| CN117391482B (en) | Greenhouse temperature intelligent early warning method and system based on big data monitoring | |
| Wang et al. | Multi-sensor signal acquisition and data processing analysis of combine harvester. | |
| US11785889B2 (en) | System and method for determining an indicator of processing quality of an agricultural harvested material | |
| US20220279720A1 (en) | System and method for identifying lengths of particles | |
| CN110569990A (en) | Operation and maintenance system and operation and maintenance method suitable for marine nuclear power platform | |
| CN115205060A (en) | Agricultural meteorological insurance loss assessment method, system, storage medium and equipment | |
| CN114267005A (en) | Harvesting method, device, processor and agricultural machine for crops | |
| CN115399139B (en) | Method, apparatus, storage medium and processor for determining crop yield | |
| Jin et al. | Design of sampling device for rice grain impurity sensor in grain-bin of combine harvester. | |
| CN117409403B (en) | Rice spike maturity estimation method based on deep learning |
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 |