Intelligent electric drive method and system for seed drill

Abstract

The present invention provides an intelligent electric drive method and system for a seed drill, wherein the method comprises: step 1: obtaining the seeding task of the target seed drill; step 2: determining the fertilization timing and the sowing timing according to the seeding task; step 3: directly driving the fertilization shaft to work through the fertilization electric drive according to the fertilization timing, and at the same time, driving each row of sowing units to sow through the sowing electric drive according to the sowing timing. An intelligent electric drive method and system for a seed drill of the present invention determines the fertilization timing and the sowing timing according to the acquired seeding task of the target seed drill, and then drives the corresponding shaft bodies to perform sowing and fertilization operations through the fertilization electric drive and the sowing electric drive respectively. The required sowing amount and fertilization amount can be adjusted conveniently and quickly by the manual operation terminal, and the cumbersome operation mode of mechanically adjusting the sowing amount and fertilization amount is no longer required, which is more convenient and humanized.

Description

Technical Field

[0001] The present invention relates to the technical field of crop automation, and in particular to an intelligent electric drive method and system for a seeder. Background Art

[0002] Traditional seeders use a mechanical transmission structure of chain drive or shaft drive. The transmission parts of this structure are complicated and there are various friction resistances during the transmission process, which affects the working speed of the seeder and the accuracy of sowing and fertilization (for example: the ground wheel slips and causes uneven sowing).

[0003] The application of intelligent electric drive methods enables the seeder to provide more uniform and precise sowing effects under various operating conditions. The invention patent with application number: 202310870532.X discloses an electric drive crop sowing and fertilization control method and system, the method includes: first, obtaining the sensor speed data of the sowing and fertilization area; secondly, collecting and processing the image of the sowing and fertilization area, using the CNN model, identifying and analyzing the sowing and fertilization areas in the image, as well as information such as crop growth status; then combining the speed data with the image analysis results, calculating the sowing and fertilization operation parameters of each row area, and analyzing the quality of the seeds, and transmitting the control signal to each row of electric drive seeding and fertilization control unit for sowing and fertilization operations; finally, uploading the parameter information to the host unit and the cloud server to facilitate decision-making, crop monitoring and production management. The above invention accurately identifies and analyzes the sowing and fertilization areas of crops, and performs precise sowing and fertilization control, improves the yield and quality of crops, and reduces labor costs and time waste.

[0004] However, the above-mentioned prior art needs to perform calculations according to the CNN model each time sowing and fertilizing are performed. When adjusting the required sowing amount and fertilization amount, the model parameters also need to be adjusted, which is relatively cumbersome.

[0005] In view of this, there is an urgent need for an intelligent electric drive method and system for a seed drill to at least solve the above-mentioned deficiencies. Summary of the invention

[0006] One of the purposes of the present invention is to provide an intelligent electric drive method and system for a seeder, which determines the fertilization timing and sowing timing according to the sowing task of the target seeder, and then drives the corresponding shafts to perform sowing and fertilization operations through the fertilization electric drive and the sowing electric drive respectively. The required sowing amount and fertilization amount can be adjusted conveniently and quickly by the operator directly through the operation terminal, saying goodbye to the cumbersome mechanical operation method of adjusting the sowing amount and fertilization amount, which is more convenient and user-friendly.

[0007] An embodiment of the present invention provides an intelligent electric drive method for a seed drill, comprising:

[0008] Step 1: Get the seeding task of the target seeding machine;

[0009] Step 2: Determine the timing of fertilization and sowing according to the sowing task;

[0010] Step 3: According to the fertilization timing, the fertilization electric drive directly drives the fertilization shaft to work. At the same time, according to the sowing timing, the sowing electric drive drives each row of sowing units to sow.

[0011] Preferably, step 1: obtaining the sowing task of the target seeder includes:

[0012] Obtain the sowing plan based on the preset operation terminal;

[0013] According to the sowing plan, the sowing task of the target seeder is determined.

[0014] Preferably, step 2: determining the fertilization timing and sowing timing according to the sowing task, includes:

[0015] Obtain the operating parameters of the target planter;

[0016] Parse the seeding task to determine whether there are any operation sequence requirements;

[0017] If there is no operation sequence requirement, determine the fertilization timing and sowing timing for each pit according to the sowing task and operating parameters;

[0018] If there are operation sequence requirements, determine the timing of fertilization and sowing based on the sowing task, operating parameters and operation sequence requirements.

[0019] Preferably, based on a preset operation terminal, obtaining a sowing plan includes:

[0020] Obtaining the plot information of the desired sowing plot; the plot information includes: soil information, plot shape and plot size;

[0021] Obtain planting target information;

[0022] Determine the recommended plan based on the plot information and planting target information;

[0023] The recommended solution is displayed on the preset recommendation interface of the operation terminal and the input personnel of the operation terminal are reminded to view it;

[0024] Get the seeding plan output after the input personnel review the recommended plan.

[0025] Preferably, a recommended plan is determined based on the plot information and the planting target information, including:

[0026] Analyze planting target information and determine the type data of sowing targets;

[0027] Index planting demand information based on species data;

[0028] Match keywords based on planting demand information and plot information to determine target information segments;

[0029] Obtaining semantic layout information of the target information paragraph;

[0030] Determine keyword distribution in semantic layout information;

[0031] Determine the key value of the target information paragraph based on keyword distribution;

[0032] Determine a keyword type set based on the plot information;

[0033] Determine the type comprehensive ratio based on the keyword type and keyword type set of the keyword distribution;

[0034] Multiply the key value and the type comprehensive ratio accordingly to determine the target key value, and determine the recommendation plan based on the target information paragraph whose target key value is greater than or equal to the preset target key value threshold.

[0035] Preferably, keyword matching is performed based on the planting demand information and the plot information to determine the target information paragraph, including:

[0036] Parsing the land parcel information and determining a plurality of first parsing semantics;

[0037] Determine a first semantic type of the first parsed semantics, and remove the first parsed semantics of the target semantic type to obtain a second parsed semantics;

[0038] Determine a second semantic type of the second parsed semantics, and at the same time, calculate the semantic frequency of the second parsed semantics;

[0039] Determining the criticality of the second semantic analysis according to the preset word class weight and semantic frequency corresponding to the second semantic type;

[0040] The second parsed semantics whose criticality is greater than or equal to a preset criticality threshold is used as a keyword;

[0041] According to the planting demand information, determine the information segments to be matched;

[0042] Parse the information paragraph to be matched and obtain the third parsing semantics;

[0043] The third parsed semantics and the keywords are matched in meaning, and if there is a match, the to-be-matched information paragraph corresponding to the third parsed semantics that matches the match is taken as the target information paragraph.

[0044] Preferably, determining the key value of the target information paragraph according to the keyword distribution includes:

[0045] Determine the associated analysis words based on the keywords;

[0046] Based on the preset search rules of the associated analysis words, the associated analysis words are searched according to the layout information and the keyword distribution;

[0047] Obtaining search results for the associated analysis words, the search results including: a corresponding display relationship between the associated analysis words and keywords corresponding to the associated analysis words;

[0048] If the associated analysis word in the search results is empty, the keyword text density is determined according to the layout information and keyword distribution, and the keyword text density is used as the key value;

[0049] If the associated analysis words in the search results are not empty, the target semantics is intercepted according to the search results;

[0050] Determine the associated value based on the target semantics;

[0051] Determine the auxiliary correction value according to the associated value and a preset auxiliary correction value determination table;

[0052] The keyword text density is auxiliary corrected according to the auxiliary correction value to obtain the key value.

[0053] An intelligent electric drive method for a seed drill provided by an embodiment of the present invention further includes:

[0054] Perform fault detection on target axes, including fertilizing axes and sowing axes;

[0055] The target axis fault detection includes:

[0056] Take an image of the seed pit where the target axis has been operated, and perform fault detection based on the image shooting results;

[0057] and / or,

[0058] Detect mechanical fault signals of the target axis.

[0059] Preferably, an image is taken of the seed pit where the target shaft has been operated, and fault detection is performed according to the image shooting result, including:

[0060] According to the image shooting results, the operation image features are determined; the operation image features are the image features of the seed pit image after the sowing and fertilization operation, specifically including: seed color, seed texture, fertilizer color and fertilizer texture;

[0061] According to the operation image features, it is determined whether the target seed pit corresponding to the seed pit image has been completed;

[0062] If not, obtain the missing job items;

[0063] Determine the target storage silo and target discharge port based on the missing operation items;

[0064] Perform data detection on the sensor data of the target storage bin and the target discharge port;

[0065] If the detection result of the data detection is abnormal, outputting a first fault detection result;

[0066] If the detection result of the data detection is normal, a second fault detection result is output.

[0067] An intelligent electric drive system for a seed drill provided by an embodiment of the present invention includes:

[0068] The sowing task acquisition subsystem is used to obtain the sowing task of the target seeder;

[0069] The timing determination subsystem is used to determine the fertilization timing and sowing timing according to the sowing task;

[0070] The electric drive subsystem is used to directly drive the fertilization shaft to work through the fertilization electric drive according to the fertilization timing. At the same time, it drives each row of sowing units to sow through the sowing electric drive according to the sowing timing.

[0071] The beneficial effects of the present invention are:

[0072] The present invention determines the fertilization timing and the sowing timing according to the sowing task of the target seeder, and then drives the corresponding shafts to perform sowing and fertilization operations through the fertilization electric drive and the sowing electric drive respectively. The required sowing amount and fertilization amount can be adjusted conveniently and quickly by the operator directly through the operation terminal, saying goodbye to the cumbersome mechanical operation mode of adjusting the sowing amount and fertilization amount, which is more convenient and user-friendly.

[0073] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the present application documents.

[0074] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0076] Figure 1 A schematic diagram of an intelligent electric drive method for a seed drill according to an embodiment of the present invention;

[0077] Figure 2 Schematic diagram of an intelligent electric drive system for a seed drill in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0079] The embodiment of the present invention provides an intelligent electric drive method for a seed drill, such as Figure 1 As shown, including:

[0080] Step 1: Get the seeding task of the target seeding machine;

[0081] Step 2: Determine the timing of fertilization and sowing according to the sowing task;

[0082] Step 3: According to the fertilization timing, the fertilization electric drive directly drives the fertilization shaft to work. At the same time, according to the sowing timing, the sowing electric drive drives each row of sowing units to sow.

[0083] In this embodiment, the sowing task is determined according to manually input sowing parameters, and the sowing parameters include: sowing depth, sowing spacing, and sowing plot area;

[0084] In this embodiment, the fertilization timing is: the moment when the fertilization electric drive drives the fertilization shaft to fertilize; the fertilization shaft is a rotating component on the target planter for fertilization, which is used to evenly spread the fertilizer into the soil;

[0085] In this embodiment, the sowing time is: the moment when the sowing electric drive drives the sowing shaft to sow; the sowing shaft is a rotating component on the target seeder for sowing, which is used to evenly spread the seeds into the soil;

[0086] In this embodiment, the fertilization electric drive is: an electric drive device that drives the fertilization shaft to rotate;

[0087] In this embodiment, the sowing electric drive is: an electric drive device that drives the sowing shaft to rotate;

[0088] In this embodiment, the sowing unit is an independent unit on the target seeder that is responsible for sowing a row of crops, and each unit is responsible for sowing a row of crops.

[0089] The working principle and beneficial effects of the above technical solution are:

[0090] The present invention determines the fertilization timing and the sowing timing according to the sowing task of the target seeder, and then drives the corresponding shafts to perform sowing and fertilization operations through the fertilization electric drive and the sowing electric drive respectively. The required sowing amount and fertilization amount can be adjusted conveniently and quickly by the operator directly through the operation terminal, saying goodbye to the cumbersome mechanical operation mode of adjusting the sowing amount and fertilization amount, which is more convenient and user-friendly.

[0091] In one embodiment, step 1: obtaining the seeding task of the target seeding machine includes:

[0092] Obtain the sowing plan based on the preset operation terminal;

[0093] According to the sowing plan, the sowing task of the target seeder is determined.

[0094] In this embodiment, the sowing plan is: the sowing suggestions pushed to the operation terminal by big data, such as the sowing depth, sowing spacing and fertilizer amount of watermelon seeds, etc. When pushing, the plan of similar situation is selected from the big data according to the sowing target, the parameters of the target sowing machine and the current cultivated land conditions and applied;

[0095] In this embodiment, the sowing task is: after the operator of the operation terminal checks the sowing plan, the operator actually inputs the sowing task into the operation terminal to instruct the target seeder to execute.

[0096] The working principle and beneficial effects of the above technical solution are:

[0097] The present invention determines the sowing task through the operation terminal, and the manual operation terminal can directly and conveniently and quickly adjust the required sowing amount and fertilization amount, which is more humane.

[0098] In one embodiment, step 2: determining the fertilization timing and the sowing timing according to the sowing task, includes:

[0099] Obtain the operating parameters of the target planter;

[0100] Parse the seeding task to determine whether there are any operation sequence requirements;

[0101] If there is no operation sequence requirement, determine the fertilization timing and sowing timing for each pit according to the sowing task and operating parameters;

[0102] If there are operation sequence requirements, determine the timing of fertilization and sowing based on the sowing task, operating parameters and operation sequence requirements.

[0103] In this embodiment, the operating parameters are: sowing speed range, sowing row spacing range, etc.;

[0104] In this embodiment, the operation sequence requirement is: the sequence requirement of fertilizing and sowing.

[0105] The working principle and beneficial effects of the above technical solution are:

[0106] The present invention introduces the operating parameters of the target seed drill and obtains the operation sequence requirements. According to the different operation sequence requirements, the fertilization timing and the seeding timing are determined respectively, thereby improving the accuracy of determining the feeding time.

[0107] In one embodiment, based on a preset operation terminal, obtaining a seeding plan includes:

[0108] Obtaining the plot information of the desired sowing plot; the plot information includes: soil information, plot shape and plot size;

[0109] Obtain planting target information;

[0110] Determine the recommended plan based on the plot information and planting target information;

[0111] The recommended solution is displayed on the preset recommendation interface of the operation terminal and the input personnel of the operation terminal are reminded to view it;

[0112] Get the seeding plan output after the input personnel review the recommended plan.

[0113] In this embodiment, the soil information includes: soil texture, fertility, pH value, organic matter content and moisture status;

[0114] In this embodiment, the plot shape is: the geometric shape of the sowing plot;

[0115] In this embodiment, the plot size is: the area of ​​the sowing plot;

[0116] In this embodiment, the planting target information includes: the type, density and expected yield of the planted crops;

[0117] In this embodiment, the recommendation scheme is: based on the plot information and planting target information, the sowing suggestions are retrieved through big data.

[0118] The working principle and beneficial effects of the above technical solution are:

[0119] The present invention introduces plot information and planting target information, retrieves sowing suggestions through big data as recommended plans for input personnel to view, obtains the sowing plans output by the input personnel after viewing the recommended plans, and improves the sowing management efficiency.

[0120] In one embodiment, a recommendation scheme is determined based on the plot information and the planting target information, including:

[0121] Analyze planting target information and determine the type data of sowing targets;

[0122] Index planting demand information based on species data;

[0123] Match keywords based on planting demand information and plot information to determine target information segments;

[0124] Obtaining semantic layout information of the target information paragraph;

[0125] Determine keyword distribution in semantic layout information;

[0126] Determine the key value of the target information paragraph based on keyword distribution;

[0127] Determine a keyword type set based on the plot information;

[0128] Determine the type comprehensive ratio based on the keyword type and keyword type set of the keyword distribution;

[0129] Multiply the key value and the type comprehensive ratio accordingly to determine the target key value, and determine the recommendation plan based on the target information paragraph whose target key value is greater than or equal to the preset target key value threshold.

[0130] In this embodiment, the type data of the sowing target is: the type of seeds sown, such as: watermelon seeds;

[0131] In this embodiment, the planting demand information is: planting suggestion information determined according to the type data, such as: planting suggestion information for watermelon;

[0132] In this embodiment, keyword matching is a process of: determining the descriptive semantics of the plot information, and retrieving the descriptive semantics of the plot information in the semantic items of the planting requirement information;

[0133] In this embodiment, the target information paragraph is: a paragraph of planting suggestion information that matches the plot information;

[0134] In this embodiment, the semantic layout information is: the distribution of all semantic items in the target information paragraph;

[0135] In this embodiment, the keyword distribution is: the distribution of the semantic items corresponding to the descriptive semantics of the land parcel information in the target information paragraph among all the semantic items in the target information paragraph;

[0136] In this embodiment, the key value represents the information keyness of the target information paragraph. The denser the keyword distribution, the greater the key value. The key value is calculated as follows: the number of characters of the keyword in the target information paragraph divided by the total number of characters in the target paragraph;

[0137] In this embodiment, the keyword type set is: a set of multiple keyword types describing land plot information, such as: hardness, humidity, and soil type;

[0138] In this embodiment, the type comprehensive ratio is: the result obtained by dividing the number of types of keyword types corresponding to the keyword distribution of the target information paragraph by the number of types in the keyword type set;

[0139] In this embodiment, the preset target key value threshold is preset manually.

[0140] The working principle and beneficial effects of the above technical solution are:

[0141] The present invention indexes planting demand information according to the type data of the sowing target, and determines the target information paragraphs containing keywords in the planting demand information according to the keyword matching results of the planting demand information and the plot information. The semantic layout information of the target information paragraph is obtained, and the key value of the target information paragraph is determined according to the density of the keywords in the semantic layout information; the type comprehensive ratio is determined according to the keyword type and keyword type set of the keyword distribution; the key value of the target information paragraph and the type comprehensive ratio are correspondingly multiplied to determine the target key value of the target information paragraph, and the target information paragraphs whose target key value is greater than or equal to the preset target key value threshold are screened out to determine the recommendation plan, thereby improving the suitability and determination efficiency of the recommendation plan determination process.

[0142] In one embodiment, keyword matching is performed based on the planting requirement information and the plot information to determine the target information segment, including:

[0143] Parsing the land parcel information and determining a plurality of first parsing semantics;

[0144] Determine a first semantic type of the first parsed semantics, and remove the first parsed semantics of the target semantic type to obtain a second parsed semantics;

[0145] Determine a second semantic type of the second parsed semantics, and at the same time, calculate the semantic frequency of the second parsed semantics;

[0146] Determining the criticality of the second semantic analysis according to the preset word class weight and semantic frequency corresponding to the second semantic type;

[0147] The second parsed semantics whose criticality is greater than or equal to a preset criticality threshold is used as a keyword;

[0148] According to the planting demand information, determine the information segments to be matched;

[0149] Parse the information paragraph to be matched and obtain the third parsing semantics;

[0150] The third parsed semantics and the keywords are matched in meaning, and if there is a match, the to-be-matched information paragraph corresponding to the third parsed semantics that matches the match is taken as the target information paragraph.

[0151] In this embodiment, the first parsed semantics is a semantic item obtained by parsing the land parcel information based on the semantic parsing technology;

[0152] In this embodiment, the first semantic type is: the word class corresponding to the first parsed semantics, such as: noun, verb, preposition and article, etc.;

[0153] In this embodiment, the target semantic type is manually set, such as conjunctions, prepositions, etc.;

[0154] In this embodiment, the semantic frequency is: the frequency of the second parsed semantics in the first parsed semantics;

[0155] In this embodiment, the preset word class weight corresponding to the second semantic type is determined by the amount of information that can be expressed by the semantics of the second semantic type, and the weight is quantified in the range of 0-1 according to the amount of information, for example: the word class weight of a conjunction is 0.1, and the word class weight of a noun is 0.8;

[0156] In this embodiment, the criticality is obtained by multiplying the word class weight and the semantic frequency;

[0157] In this embodiment, the preset criticality threshold is preset manually;

[0158] In this embodiment, the information segments to be matched are the results of segmenting the planting demand information;

[0159] In this embodiment, the third parsing semantics is obtained by performing semantic parsing on the information paragraph to be matched.

[0160] The working principle and beneficial effects of the above technical solution are:

[0161] The present invention parses the plot information to obtain the first parsed semantics, determines the first semantic type of the first parsed semantics, and performs a elimination operation on the first parsed semantics of the target semantic type to obtain the second parsed semantics. According to the word class weight preset for the second semantic type corresponding to the second parsed semantics and the semantic frequency of the second parsed semantics, the criticality of the second parsed semantics is determined, and the second parsed semantics with a criticality greater than or equal to a preset criticality threshold is used as a keyword, and subsequent keyword matching is performed based on the keyword, thereby improving the accuracy of keyword determination and further improving the screening efficiency of useful reference information (useful seeding scheme).

[0162] In one embodiment, determining the key value of the target information paragraph according to the keyword distribution includes:

[0163] Determine the associated analysis words based on the keywords;

[0164] Based on the preset search rules of the associated analysis words, the associated analysis words are searched according to the layout information and the keyword distribution;

[0165] Obtaining search results for the associated analysis words, the search results including: a corresponding display relationship between the associated analysis words and keywords corresponding to the associated analysis words;

[0166] If the associated analysis word in the search results is empty, the keyword text density is determined according to the layout information and keyword distribution, and the keyword text density is used as the key value;

[0167] If the associated analysis words in the search results are not empty, the target semantics is intercepted according to the search results;

[0168] Determine the associated value based on the target semantics;

[0169] Determine the auxiliary correction value according to the associated value and a preset auxiliary correction value determination table;

[0170] The keyword text density is auxiliary corrected according to the auxiliary correction value to obtain the key value.

[0171] In this embodiment, the associated analysis words are: words that have been indexed together with the keywords in history;

[0172] In this embodiment, the search rules preset for the associated analysis words are determined according to the part of speech of the associated analysis words, which determines how many characters to search before and / or after the keyword;

[0173] In this embodiment, the target semantics is the semantics between the associated analysis words and the keywords corresponding to the associated analysis words that have a corresponding display relationship;

[0174] In this embodiment, the association value is a quantitative representation of the correlation between the content of the target semantic description and the land parcel information;

[0175] In this embodiment, the preset auxiliary correction value determination table includes the correspondence between multiple manually preset associated values ​​and auxiliary correction values. The higher the associated value, the higher the auxiliary correction value; the auxiliary correction value and the keyword text density are multiplied to obtain the corrected key value.

[0176] The working principle and beneficial effects of the above technical solution are:

[0177] The present invention obtains historically associated analysis words that are indexed together with keywords, introduces retrieval rules for associated analysis words to retrieve associated analysis words, and determines key values ​​according to different retrieval results of associated analysis words; specifically, when the associated analysis words in the retrieval results are empty, the keyword text density is directly determined according to layout information and keyword distribution, and the keyword text density is used as the key value; when the associated analysis words in the retrieval results are not empty, the associated value is determined according to the semantics between the associated analysis words with corresponding display relationships and the keywords corresponding to the associated analysis words, an auxiliary correction value is determined according to the associated value, and the key value is obtained by multiplying the auxiliary correction value and the keyword text density, so that the key value has higher accuracy.

[0178] An embodiment of the present invention provides an intelligent electric drive method for a seed drill, further comprising:

[0179] Perform fault detection on target axes, including fertilizing axes and sowing axes;

[0180] The target axis fault detection includes:

[0181] Take an image of the seed pit where the target axis has been operated, and perform fault detection based on the image shooting results;

[0182] and / or,

[0183] Detect mechanical fault signals of the target axis.

[0184] In this embodiment, the image capture of the seed pit where the target shaft body has been operated is based on the capture of the image by a capture device (such as a camera) preset on the target seeding machine; fault detection based on the image capture result refers to analyzing the captured image to check the sowing and fertilization conditions of the seed pit, such as whether the seeds are correctly sown, whether the sowing depth is appropriate, and whether the fertilizer is added, so as to indirectly judge the working state of the target shaft body;

[0185] In this embodiment, the mechanical fault signal is: abnormal sound, vibration, temperature change or other signals that can be detected by sensors.

[0186] The working principle and beneficial effects of the above technical solution are:

[0187] The present invention introduces two methods to perform fault detection on the fertilizing shaft and the sowing shaft; the first method indirectly judges the working state of the target shaft based on the image shooting results of the seed pit where the target shaft has been operated; the second method directly judges the working state of the target shaft according to the mechanical fault signal of the target shaft; introducing two methods for fault detection improves the comprehensiveness of fault detection.

[0188] In one embodiment, an image is taken of the seed pit where the target shaft has been operated, and fault detection is performed according to the image shooting result, including:

[0189] According to the image shooting results, the operation image features are determined; the operation image features are the image features of the seed pit image after the sowing and fertilization operation, specifically including: seed color, seed texture, fertilizer color and fertilizer texture;

[0190] According to the operation image features, it is determined whether the target seed pit corresponding to the seed pit image has been completed;

[0191] If not, obtain the missing job items;

[0192] Determine the target storage silo and target discharge port based on the missing operation items;

[0193] Perform data detection on the sensor data of the target storage bin and the target discharge port;

[0194] If the detection result of the data detection is abnormal, outputting a first fault detection result;

[0195] If the detection result of the data detection is normal, a second fault detection result is output.

[0196] In this embodiment, the missing operation items include: sowing operation and fertilization operation;

[0197] In this embodiment, the target storage bins are: seed bin and fertilizer bin;

[0198] In this embodiment, the target outlets are: the seed bin outlet and the fertilizer bin outlet;

[0199] In this embodiment, the sensor data is: the sensing data of the sensors preset in the target storage bin and at the target discharge port, such as: flow sensor, gravity sensor, etc.;

[0200] In this embodiment, data detection means that the change of sensor data must conform to the fertilization and sowing logic. For example, if a sowing or fertilization action instruction is generated, the flow sensing data corresponding to the action moment at the discharge port should change. If there is a conflict, the detection result is abnormal.

[0201] In this embodiment, the first fault detection result is: a fault unrelated to the target shaft, such as: a stuck position;

[0202] In this embodiment, the second fault detection result is: a fault related to the target shaft, such as: the target shaft is stuck.

[0203] The working principle and beneficial effects of the above technical solution are:

[0204] The present invention extracts the operation image features of the seed pit image after the sowing and fertilization operation, and judges whether the target seed pit corresponding to the seed pit image has been completed according to the operation image features. If the operation is not completed, the missing operation items are determined, and the sensor data of the corresponding storage bin and the discharge port are detected. When the data detection result is abnormal, the first fault detection result is output, otherwise the second fault detection result related to the target shaft body is output, thereby improving the fault detection efficiency.

[0205] The embodiment of the present invention provides an intelligent electric drive system for a seed drill, such as Figure 2 As shown, including:

[0206] The sowing task acquisition subsystem 1 is used to acquire the sowing task of the target seeder;

[0207] The timing determination subsystem 2 is used to determine the fertilization timing and the sowing timing according to the sowing task;

[0208] The electric drive subsystem 3 is used to directly drive the fertilization shaft to work through the fertilization electric drive according to the fertilization timing, and at the same time, drive each row of sowing units to sow through the sowing electric drive according to the sowing timing.

[0209] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent electric drive method for a seed drill, characterized in that: include: Step 1: Get the seeding task of the target seeding machine; Step 2: Determine the timing of fertilization and sowing according to the sowing task; Step 3: According to the fertilization timing, the fertilization electric drive directly drives the fertilization shaft to work. At the same time, according to the sowing timing, the sowing electric drive drives each row of sowing units to sow; Step 1: Get the seeding task of the target seeding machine, including: Obtain the sowing plan based on the preset operation terminal; According to the sowing plan, determine the sowing task of the target seeder; Based on the preset operation terminal, obtain the sowing plan, including: Obtaining the plot information of the desired sowing plot; the plot information includes: soil information, plot shape and plot size; Obtain planting target information; Determine the recommended plan based on the plot information and planting target information; The recommended solution is displayed on the preset recommendation interface of the operation terminal and the input personnel of the operation terminal are reminded to view it; Get the seeding plan output by the input personnel after reviewing the recommended plan; Determine the recommended plan based on the plot information and planting target information, including: Analyze planting target information and determine the type data of sowing targets; Index planting demand information based on species data; Match keywords based on planting demand information and plot information to determine target information segments; Obtaining semantic layout information of the target information paragraph; Determine keyword distribution in semantic layout information; Determine the key value of the target information paragraph based on keyword distribution; Determine a keyword type set based on the plot information; Determine the type comprehensive ratio based on the keyword type and keyword type set of the keyword distribution; The key value and the type comprehensive ratio are multiplied correspondingly to determine the target key value, and the recommendation plan is determined according to the target information paragraph whose target key value is greater than or equal to the preset target key value threshold; Keyword matching is performed based on planting demand information and plot information to determine the target information paragraph, including: Parsing the land parcel information and determining a plurality of first parsing semantics; Determine a first semantic type of the first parsed semantics, and remove the first parsed semantics of the target semantic type to obtain a second parsed semantics; Determine a second semantic type of the second parsed semantics, and at the same time, calculate the semantic frequency of the second parsed semantics; Determining the criticality of the second semantic analysis according to the preset word class weight and semantic frequency corresponding to the second semantic type; The second parsed semantics whose criticality is greater than or equal to a preset criticality threshold is used as a keyword; According to the planting demand information, determine the information segments to be matched; Parse the information paragraph to be matched and obtain the third parsing semantics; The third parsed semantics and the keyword are matched in word sense, and if there is a match, the to-be-matched information paragraph corresponding to the third parsed semantics that matches the match is taken as the target information paragraph; According to the keyword distribution, determine the key values ​​of the target information paragraph, including: Determine the associated analysis words based on the keywords; Based on the preset search rules of the associated analysis words, the associated analysis words are searched according to the layout information and the keyword distribution; Obtaining search results for the associated analysis words, the search results including: a corresponding display relationship between the associated analysis words and keywords corresponding to the associated analysis words; If the associated analysis word in the search results is empty, the keyword text density is determined according to the layout information and keyword distribution, and the keyword text density is used as the key value; If the associated analysis words in the search results are not empty, the target semantics is intercepted according to the search results; Determine the associated value based on the target semantics; Determine the auxiliary correction value according to the associated value and a preset auxiliary correction value determination table; The keyword text density is auxiliary corrected according to the auxiliary correction value to obtain the key value.

2. The intelligent electric drive method of a seed drill according to claim 1, characterized in that: Step 2: Determine the timing of fertilization and sowing according to the sowing task, including: Obtain the operating parameters of the target planter; Parse the seeding task to determine whether there are any operation sequence requirements; If there is no operation sequence requirement, determine the fertilization timing and sowing timing for each pit according to the sowing task and operating parameters; If there are operation sequence requirements, determine the timing of fertilization and sowing based on the sowing task, operating parameters and operation sequence requirements.

3. The intelligent electric drive method of a seed drill according to claim 1, characterized in that: Also includes: Perform fault detection on target axes, including fertilizing axes and sowing axes; The target axis fault detection includes: Take an image of the seed pit where the target axis has been operated, and perform fault detection based on the image shooting results; and / or, Detect mechanical fault signals of the target axis.

4. The intelligent electric drive method of a seed drill as claimed in claim 3, characterized in that: Take an image of the seed pit where the target axis has been operated, and perform fault detection based on the image shooting results, including: According to the image shooting results, the operation image features are determined; the operation image features are the image features of the seed pit image after the sowing and fertilization operation, specifically including: seed color, seed texture, fertilizer color and fertilizer texture; According to the operation image features, it is determined whether the target seed pit corresponding to the seed pit image has been completed; If not, obtain the missing job items; Determine the target storage silo and target discharge port based on the missing operation items; Perform data detection on the sensor data of the target storage bin and the target discharge port; If the detection result of the data detection is abnormal, outputting a first fault detection result; If the detection result of the data detection is normal, a second fault detection result is output.

5. An intelligent electric drive system for a seed drill, characterized in that: include: The sowing task acquisition subsystem is used to obtain the sowing task of the target seeder; The timing determination subsystem is used to determine the fertilization timing and sowing timing according to the sowing task; The electric drive subsystem is used to directly drive the fertilization shaft to work through the fertilization electric drive according to the fertilization timing, and at the same time, drive each row of sowing units to sow through the sowing electric drive according to the sowing timing; Step 1: Get the seeding task of the target seeding machine, including: Obtain the sowing plan based on the preset operation terminal; According to the sowing plan, determine the sowing task of the target seeder; Based on the preset operation terminal, obtain the sowing plan, including: Obtaining the plot information of the desired sowing plot; the plot information includes: soil information, plot shape and plot size; Obtain planting target information; Determine the recommended plan based on the plot information and planting target information; The recommended solution is displayed on the preset recommendation interface of the operation terminal and the input personnel of the operation terminal are reminded to view it; Get the seeding plan output by the input personnel after reviewing the recommended plan; Determine the recommended plan based on the plot information and planting target information, including: Analyze planting target information and determine the type data of sowing targets; Index planting demand information based on species data; Match keywords based on planting demand information and plot information to determine target information segments; Obtaining semantic layout information of the target information paragraph; Determine keyword distribution in semantic layout information; Determine the key value of the target information paragraph based on keyword distribution; Determine a keyword type set based on the plot information; Determine the type comprehensive ratio based on the keyword type and keyword type set of the keyword distribution; The key value and the type comprehensive ratio are multiplied correspondingly to determine the target key value, and the recommendation plan is determined according to the target information paragraph whose target key value is greater than or equal to the preset target key value threshold; Keyword matching is performed based on planting demand information and plot information to determine the target information paragraph, including: Parsing the land parcel information and determining a plurality of first parsing semantics; Determine a first semantic type of the first parsed semantics, and remove the first parsed semantics of the target semantic type to obtain a second parsed semantics; Determine a second semantic type of the second parsed semantics, and at the same time, calculate the semantic frequency of the second parsed semantics; Determining the criticality of the second semantic analysis according to the preset word class weight and semantic frequency corresponding to the second semantic type; The second parsed semantics whose criticality is greater than or equal to a preset criticality threshold is used as a keyword; According to the planting demand information, determine the information segments to be matched; Parse the information paragraph to be matched and obtain the third parsing semantics; The third parsed semantics and the keyword are matched in word sense, and if there is a match, the to-be-matched information paragraph corresponding to the third parsed semantics that matches the match is taken as the target information paragraph; According to the keyword distribution, determine the key values ​​of the target information paragraph, including: Determine the associated analysis words based on the keywords; Based on the preset search rules of the associated analysis words, the associated analysis words are searched according to the layout information and the keyword distribution; Obtaining search results for the associated analysis words, the search results including: a corresponding display relationship between the associated analysis words and keywords corresponding to the associated analysis words; If the associated analysis word in the search results is empty, the keyword text density is determined according to the layout information and keyword distribution, and the keyword text density is used as the key value; If the associated analysis words in the search results are not empty, the target semantics is intercepted according to the search results; Determine the associated value based on the target semantics; Determine the auxiliary correction value according to the associated value and a preset auxiliary correction value determination table; The keyword text density is auxiliary corrected according to the auxiliary correction value to obtain the key value.

Images