Agricultural instrument and control method thereof

Abstract

The invention discloses an agricultural instrument and a control method thereof. The method comprises the steps that working condition information before abnormity and working condition information after abnormity of an abnormal agricultural instrument are acquired, and environment information of the environment where the abnormal agricultural instrument is located is acquired; target abnormal information is determined from instrument abnormal information included in an abnormal condition database based on the abnormal working condition information; determining an initial control strategy matched with the exception of the abnormal agricultural instrument based on the working condition information before the exception and the target exception information; updating the initial control strategy based on the environment information to obtain a target control strategy; and according to the target control strategy, the ant colony algorithm is utilized to control the plurality of agricultural instruments, so that the control strategy matched with the abnormal condition of the abnormal agricultural instrument can be accurately determined, and the control strategy is fed back to the ant colony algorithm used for realizing multi-machine cooperation, and therefore, the abnormal condition of the abnormal agricultural instrument can be handled in time, and meanwhile, the multi-machine cooperation can be realized. And the influence on multi-machine collaborative operation of agricultural instruments is reduced.

Description

Technical Field

[0001] The present application relates to the field of equipment control technology, and in particular to an agricultural machine and a control method thereof. Background Art

[0002] In modern agriculture, to improve the level of agricultural automation, a large number of agricultural machines are often used. However, agricultural operations often involve harsher conditions, which increases the probability of machine malfunctions. For example, straw recycling equipment often needs to cut or even crush straw, which can easily allow straw debris to enter the machine and cause malfunctions. Pesticide spraying equipment typically sprays large amounts of liquid with high pesticide content, which can easily cause some of the liquid to splash onto the machine, leading to malfunctions.

[0003] On the other hand, modern agriculture usually emphasizes the coordinated operation of multiple machines. When there are abnormal agricultural machinery, it is easy to affect the precise control of the coordinated operation of multiple machines. Summary of the Invention

[0004] In order to solve the above technical problems, the embodiments of the present application provide an agricultural appliance and a control method thereof.

[0005] In a first aspect, an embodiment of the present application provides a method for controlling an agricultural machine, comprising: Determining that an abnormal agricultural appliance exists among the plurality of agricultural appliances, obtaining pre-abnormal operating condition information and post-abnormal operating condition information of the abnormal agricultural appliance, and obtaining environmental information of an environment in which the abnormal agricultural appliance is located; Based on the post-abnormal working condition information, determining target abnormality information from the device abnormality information included in the abnormality database; Determining an initial control strategy that matches the abnormality of the abnormal agricultural machine based on the pre-abnormal operating condition information and the target abnormality information; Updating the initial control strategy based on the environmental information to obtain a target control strategy; According to the target control strategy, the plurality of agricultural implements are controlled using an ant colony algorithm.

[0006] Optionally, the environmental information includes at least one of temperature information and humidity information corresponding to the environment.

[0007] Optionally, the device abnormality information includes at least one device abnormality sub-information, and the abnormal situation database further includes at least one abnormality sub-vector corresponding to the at least one device abnormality sub-information, and the abnormality sub-vector is obtained by converting the corresponding device abnormality sub-information; The determining target abnormality information from the device abnormality information included in the abnormality database based on the abnormality post-operating condition information includes: generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information; Determining a target abnormal sub-vector that matches the post-abnormal operating condition vector from the at least one abnormal sub-vector included in the abnormal situation database; The device abnormality sub-information corresponding to the target abnormality sub-vector is acquired from the at least one device abnormality sub-information included in the abnormal situation database to serve as the target abnormality information.

[0008] Optionally, generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information includes: Decomposing the post-abnormal operating condition information into multiple information sequences, wherein different information sequences correspond to different abnormal categories; The post-abnormal operating condition vector is generated based on the multiple information sequences.

[0009] Optionally, generating the post-abnormal operating condition vector based on the multiple information sequences includes: determining, from the plurality of information sequences, all information sequences characterized as abnormal; Convert each of the information sequences characterized as abnormalities into a sequence vector; The sequence vectors are concatenated to obtain the post-abnormal operating condition vector.

[0010] Optionally, any of the abnormality categories is associated with at least one of the at least one device abnormality sub-information.

[0011] Optionally, determining an initial control strategy that matches the abnormality of the abnormal agricultural machine based on the pre-abnormal operating condition information and the target abnormality information includes: Calling a pre-trained abnormal control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information; Among them, the abnormal control model is an artificial intelligence model obtained by training sample operating condition data, and the sample operating condition data includes first sample operating condition information and second sample operating condition information. The first sample operating condition information is suitable for indicating the operating condition of the test equipment when it is in a set abnormal state, and the second sample operating condition information is suitable for indicating the operating condition of the test equipment at the moment before entering the set abnormal state.

[0012] Optionally, calling a pre-trained abnormal regulation model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information includes: inputting the target abnormality information into the abnormality control model so that the abnormality control model generates a first device control strategy; The pre-abnormal operating condition information is input into the abnormal control model, so that the abnormal control model adjusts the first device control strategy to obtain the second device control strategy based on the comparison result between the pre-abnormal operating condition information and the target abnormal information, and outputs the second device control strategy as the initial control strategy.

[0013] Optionally, updating the initial control strategy based on the environmental information to obtain a target control strategy includes: Determining code information corresponding to the initial control strategy; Converting the environmental information into environmental text, and adjusting the environmental text according to keywords of the environmental text and a directory tree of a code database matching the abnormal agricultural equipment; The code information and the adjusted environment text are input into the abnormality control model, so that the abnormality control model updates the code information according to the adjusted environment text to obtain updated code information for indicating the target control strategy.

[0014] In a second aspect, an embodiment of the present application provides an agricultural implement, comprising: A controller is configured to execute any of the above methods.

[0015] In summary, the embodiments of the present application have at least the following beneficial effects: According to an embodiment of the present application, by determining that there is an abnormal agricultural appliance among a plurality of the agricultural appliances, the pre-abnormal operating condition information and post-abnormal operating condition information of the abnormal agricultural appliance are obtained, and the environmental information of the environment in which the abnormal agricultural appliance is located is obtained; based on the post-abnormal operating condition information, target abnormality information is determined in the appliance abnormality information included in the abnormal situation database; based on the pre-abnormal operating condition information and the target abnormality information, an initial control strategy matching the abnormality of the abnormal agricultural appliance is determined; based on the environmental information, the initial control strategy is updated to obtain a target control strategy; according to the target control strategy, an ant colony algorithm is used to control the plurality of the agricultural appliances, so that when an abnormal agricultural appliance appears in the agricultural appliances, a control strategy that is compatible with the abnormal situation of the abnormal agricultural appliance can be accurately determined, and the control strategy can be fed back to the ant colony algorithm for realizing multi-machine collaboration, thereby timely handling the abnormal situation of the abnormal agricultural appliance while reducing the impact on the collaborative operation of multiple agricultural appliances. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 11 is a flow chart of a control method for agricultural machinery provided in an embodiment of the present application; Figure 2 is a schematic diagram of an agricultural appliance provided in an embodiment of the present application; Figure 3 is a schematic diagram of a computer device provided in an embodiment of the present application; Figure 4 Schematic diagram of a control device for agricultural machinery provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, "multiple" means two or more. In the description of this application, the term "including" and its variations are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments".

[0019] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0020] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the art. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit this application. Those of ordinary skill in the art will understand the specific meanings of the above terms in this application in specific circumstances.

[0021] The agricultural machinery involved in the embodiments of the present application may include but is not limited to straw recycling equipment and / or pesticide spraying equipment.

[0022] First, see Figure 1 , shows a flow chart of a control method for agricultural machinery provided by an embodiment of the present application, the method including steps S101-S105, specifically as follows: S101 , determining that there is an abnormal agricultural appliance among the plurality of agricultural appliances, obtaining pre-abnormal operating condition information and post-abnormal operating condition information of the abnormal agricultural appliance, and obtaining environmental information of the environment in which the abnormal agricultural appliance is located.

[0023] In one example, the abnormality moment is when an abnormality is detected in the agricultural machinery. The pre-abnormality operating condition information may include: the operating condition information of the abnormal agricultural machinery at the moment before the abnormality moment. The post-abnormality operating condition information may include: the operating condition information of the abnormal agricultural machinery at the abnormality moment, and / or the operating condition information of the abnormal agricultural machinery at the moment after the abnormality moment.

[0024] In one example, the operating condition information described in any embodiment of the present application may include at least one of the following information of the corresponding agricultural equipment: temperature, operating current, operating voltage, motor noise, motor speed, motor vibration, motor power factor, etc.

[0025] in: Detecting the current and / or voltage of agricultural machinery during operation can help understand whether the agricultural machinery is operating under rated conditions and whether there is an overload or undervoltage condition.

[0026] Detecting the actual speed of the motor and comparing it with the rated speed of the motor can reflect the working efficiency and load condition of the motor, thereby characterizing the working condition of the agricultural machinery.

[0027] Although noise is not a factor that directly affects motor performance, changes in noise levels can indirectly reflect the wear of the motor's mechanical components or other potential problems, thereby characterizing the working conditions of agricultural equipment.

[0028] Power factor is an important parameter to measure the efficiency of motor power utilization. A low power factor means higher energy consumption and lower efficiency.

[0029] In one example, the environmental information may include at least one of the following: temperature information, humidity information, environmental images, etc. corresponding to the environment where the abnormal agricultural equipment is located. It should be understood that the above environmental information can be collected by corresponding sensors of the environment where the abnormal agricultural equipment is located.

[0030] In one example, before step S101 , the method may further include: detecting in real time whether a plurality of agricultural implements have abnormalities, wherein whether an abnormality has occurred may be determined by detecting current operating condition information of the agricultural implements.

[0031] In one example, after step S101 and before step S102, the method may further include: Pushing a notification message suitable for indicating the detected abnormality to a user terminal corresponding to each of the agricultural appliances, for example, the user terminal may include a control terminal corresponding to each of the agricultural appliances; receiving a first user instruction fed back by the user terminal in response to the notification message, wherein the first user instruction is adapted to indicate an adjustment intention of a user using the user terminal with respect to the detected anomaly represented by the notification message; At this time, step S102 may include: adjusting the post-abnormal operating condition information based on the first user instruction, and using the adjusted post-abnormal operating condition information as new post-abnormal operating condition information.

[0032] S102, based on the post-abnormal operating condition information, determining target abnormality information from the device abnormality information included in the abnormality database; In one example, various types of equipment abnormality information are pre-stored in the abnormality database. At this time, target abnormality information can be determined based on one or more equipment abnormality information with the highest similarity to the post-abnormal working condition information.

[0033] Continuing with the above example, in one case, the device abnormality information with the highest similarity can be directly used as the target abnormality information.

[0034] Continuing with the above example, in multiple cases, the multiple pieces of equipment abnormality information with the highest similarity can be directly combined into target abnormality information, or the multiple pieces of equipment abnormality information with the highest similarity can be subjected to data processing (such as fusion processing, group screening processing, etc.) to obtain target abnormality information.

[0035] It should be noted that the similarity described in any one or more embodiments of the present application can be calculated by at least one of the following methods: cosine similarity, Euclidean distance, Manhattan distance, Pearson correlation coefficient, etc. It should be understood that the implementation of the similarity is only an example and does not limit the present application.

[0036] In one example, the machine abnormality information may include: first machine abnormality information obtained by processing historical abnormality data of the agricultural machine, where different first machine abnormality information may represent different abnormal conditions that have occurred in the past with the corresponding agricultural machine; and / or second machine abnormality information obtained by testing the test machine under various preset abnormal conditions, where different second motor abnormality information may represent information obtained by testing the test machine under different preset abnormal conditions (or subsequently set abnormal conditions). The test machine is typically of the same type as the corresponding agricultural machine.

[0037] S103, determining an initial control strategy that matches the abnormality of the abnormal agricultural machine based on the pre-abnormal operating condition information and the target abnormality information; In one example, the above-mentioned abnormal situation database may also store the equipment control strategies corresponding to each type of equipment abnormality information. At this time, step S103 may include: obtaining the equipment control strategy corresponding to the target abnormality information from the abnormal situation database, and adjusting the obtained equipment control strategy using the working condition information before the abnormality to obtain an initial control strategy, wherein the obtained equipment control strategy can be used to indicate the working condition that the abnormal agricultural equipment is expected to achieve. At this time, the part of the working condition that deviates greatly from the working condition information before the abnormality can be adjusted to obtain the initial control strategy. For example, when the motor speed of the abnormal agricultural equipment represented by the working condition exceeds a certain safety threshold of the speed indicated by the working condition information before the abnormality, the speed can be appropriately reduced so that the speed indicated by the initial control strategy does not exceed the certain safety threshold of the speed indicated by the working condition information before the abnormality.

[0038] In one example, after step S103 and before step S104, the method may further include: Pushing the initial control strategy to a user terminal corresponding to the agricultural implement, for example, the user terminal may include a control terminal corresponding to the agricultural implement; receiving a second user instruction fed back by the user terminal with respect to the initial control strategy, wherein the second user instruction is adapted to indicate an adjustment intention of the user using the user terminal with respect to the initial control strategy; At this time, step S104 may include: updating the initial control strategy based on the second user instruction and the environmental information to obtain a target control strategy.

[0039] S104, updating the initial control strategy based on the environmental information to obtain a target control strategy; In one example, environmental information may include an environmental image, which can be used to characterize the type of operation currently being performed by the abnormal agricultural implement. For example, if the current operation is determined to be straw cutting or even shredding, an update strategy related to this type can be obtained to update the initial control strategy (e.g., appropriately increasing the motor torque of the abnormal agricultural implement to overcome cutting resistance). Alternatively, if the current operation is determined to be spraying a liquid containing pesticide, an update strategy related to this type can be obtained to update the initial control strategy. This allows the target control strategy to be more accurately adapted to the situation indicated by the environmental information.

[0040] In one example, the initial control strategy can be updated based on at least one of temperature, humidity, air pressure, and electromagnetic information corresponding to the environment to obtain a target control strategy. For example, if the current ambient temperature is too high, the current ambient humidity is too high, the current air pressure is too low, and / or the current ambient electromagnetic interference is strong, the performance indicators of the motor in the abnormal agricultural equipment corresponding to the initial control strategy can be appropriately reduced to adapt to the environment unfavorable for motor operation.

[0041] In one example, after step S104 , the method may further include: pushing the target control strategy to a user terminal corresponding to the motor of the agricultural implement. For example, the user terminal may include a control terminal corresponding to the agricultural implement.

[0042] S105 , controlling the plurality of agricultural machines using an ant colony algorithm according to the target control strategy.

[0043] In one example, the target control strategy can be used to indicate the subsequent adjustments and controls that need to be made to the abnormal agricultural machinery due to the abnormality that has occurred. In this way, the target control strategy can be fed back to the ant colony algorithm as a basis for algorithm processing, so that when the ant colony algorithm is used to perform multi-machine collaborative control of multiple agricultural machinery, the subsequent situation of the abnormal agricultural machinery can also be fully considered to achieve more accurate multi-machine collaborative control, thereby facilitating the control of other normal agricultural machinery to fill in the blank areas left by the abnormal agricultural machinery due to the abnormality, so as to improve the reliability of multi-machine collaborative operation of agricultural machinery.

[0044] In one example, controlling the plurality of agricultural implements using an ant colony algorithm may include: performing path planning for the plurality of agricultural implements using the ant colony algorithm, so as to control the plurality of agricultural implements according to the path planning results.

[0045] In one example, the target control strategy may be used to indicate at least one of the following: a target current, a target voltage, a target motor speed, a target motor power factor, and the like.

[0046] In an optional implementation, the environmental information includes at least one of temperature information and humidity information corresponding to the environment.

[0047] In some cases, modern agricultural machinery often integrates a large number of motors to achieve equipment automation, thereby improving the level of agricultural automation. However, agricultural operations often experience harsh conditions, which increases the probability of motor failure in agricultural machinery. For example, straw recycling equipment often requires cutting or even crushing straw, which can easily cause large amounts of straw debris to adhere to the motor and cause failures. Pesticide spraying equipment typically requires spraying large amounts of liquid with a high pesticide content, which can easily splash onto the motor and cause failures, resulting in a high probability of agricultural machinery failure.

[0048] In view of the above situation, in one example, the environmental information may include at least one of temperature information, humidity information, air pressure information, and electromagnetic information corresponding to the environment. Updating the initial control strategy based on the environmental information to obtain the target control strategy may include: Based on at least one of the temperature information, humidity information, air pressure information, and electromagnetic information, the motor speed and / or motor torque of the abnormal agricultural implement indicated by the initial control strategy is updated to obtain the target control strategy.

[0049] In one example, since the motor may overheat at high temperatures, causing accelerated aging of the insulation material and even damage to the motor, if the current ambient temperature represented by the temperature information is too high, the motor speed and / or motor torque indicated by the initial control strategy can be appropriately reduced to avoid increased heating.

[0050] In one example, since high humidity may cause short circuits or corrosion in electrical components, affecting the safety and reliability of the motor, if the current ambient humidity represented by the humidity information is too high, the motor speed and / or motor torque indicated by the initial control strategy can be appropriately reduced, thereby reducing the working intensity of the motor to reduce potential risks.

[0051] In one example, changes in atmospheric pressure affect air density, thereby affecting motor cooling efficiency and load capacity. Therefore, if the current air pressure represented by the air pressure information is too low, the motor heat dissipation efficiency decreases due to the thin air. Therefore, the motor speed and / or motor torque indicated by the initial control strategy can be appropriately reduced. On the contrary, in a high-pressure environment, the motor can operate more efficiently, allowing the motor speed and / or motor torque to be slightly increased.

[0052] In one example, because ambient electromagnetic interference can affect the stability and accuracy of a motor control system, if the electromagnetic information indicates strong environmental interference, the impact of this interference on the motor control system can be mitigated by adjusting the PWM frequency indicated by the initial control strategy or employing filtering techniques. Furthermore, the motor speed and torque are appropriately adjusted based on the level of interference to ensure stable system operation.

[0053] It can be understood that the above-mentioned embodiments related to temperature information, humidity information, air pressure information, and electromagnetic information can select one or more of them to complete the update processing. For example, when the current ambient temperature is too high and the current ambient humidity is too high at the same time, the motor speed and / or motor torque indicated by the initial control strategy can be reduced, so that the reduced motor speed and / or motor torque are lower than the motor speed and / or motor torque obtained by adjusting when only the current ambient temperature is too high or the current ambient humidity is too high.

[0054] In one example, updating the initial control strategy (or the motor speed and / or motor torque indicated therein) may include performing the updating process using a pre-trained update model, wherein each round of multiple rounds of iterative training of the pre-trained update model may include: Acquire multiple sample motor control strategies and their respective corresponding sample environment information and labeled control strategies; acquire a sample motor control strategy from the multiple sample motor control strategies; based on the sample motor control strategy and its corresponding sample environment information, call the update model to be trained to obtain an adjustment strategy; based on the difference between the labeled control strategy corresponding to the sample motor control strategy and the adjustment strategy, determine the current round loss value, so as to perform the current round training on the update model to be trained according to the current round loss value; wherein, the sample environment information may include sample temperature information, sample humidity information, sample air pressure information and / or sample electromagnetic information.

[0055] In an optional embodiment, the device abnormality information includes at least one device abnormality sub-information, and the abnormal situation database further includes at least one abnormality sub-vector corresponding to the at least one device abnormality sub-information, and the abnormality sub-vector is obtained by converting the corresponding device abnormality sub-information; In one example, the at least one device abnormality sub-information may correspond to several abnormality categories, wherein the several abnormality categories may include at least one of the following: electrical abnormality category (e.g., overcurrent, under / overvoltage, phase imbalance in three-phase motors), mechanical abnormality category (e.g., motor bearing abnormality, rotor imbalance, coupling abnormality), thermal abnormality category (cooling abnormality category), control abnormality category, environment-related abnormality category (e.g., high humidity environment abnormality), and other abnormality categories (e.g., motor noise abnormality, motor vibration exceeding standard abnormality).

[0056] In one example, each abnormal sub-vector can be obtained by performing vectorized conversion on the corresponding instrument abnormal sub-information.

[0057] The determining target abnormality information from the device abnormality information included in the abnormality database based on the abnormality post-operating condition information includes: A corresponding post-abnormal operating condition vector is generated according to the post-abnormal operating condition information; in one example, the corresponding post-abnormal operating condition vector can be obtained by performing vectorization conversion on the post-abnormal operating condition information.

[0058] Among the at least one abnormal sub-vector included in the abnormal situation database, a target abnormal sub-vector that matches the post-abnormal operating condition vector is determined; in one example, the target abnormal sub-vector that matches the post-abnormal operating condition vector can be determined by calculating the similarity between vectors, wherein the target abnormal sub-vector can be one or more abnormal sub-vectors with the highest similarity to the post-abnormal operating condition vector.

[0059] The device abnormality sub-information corresponding to the target abnormality sub-vector is acquired from the at least one device abnormality sub-information included in the abnormal situation database to serve as the target abnormality information.

[0060] In this embodiment, a target abnormality sub-vector that matches the post-abnormal operating condition vector is obtained directly through a matching query between vectors, and further, based on the preset correspondence between the equipment abnormality sub-information and the abnormal sub-vector stored in the abnormal situation database, the motor abnormality sub-information corresponding to the target abnormality sub-vector is obtained from the database as the target abnormality information, thereby improving the efficiency of database query so that after an abnormality occurs in agricultural machinery, a more timely response can be made to the abnormality in multi-machine collaborative operation.

[0061] In an optional implementation, generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information includes: The post-abnormal operating condition information is decomposed into multiple information sequences, wherein different information sequences correspond to different abnormal categories. In one example, the several abnormal categories are specifically multiple abnormal categories, and the post-abnormal operating condition information can be decomposed according to the multiple abnormal categories, thereby decomposing the post-abnormal operating condition information into multiple information sequences corresponding one-to-one to the multiple abnormal categories.

[0062] Generating the post-abnormal operating condition vector based on the multiple information sequences. In one example, generating the post-abnormal operating condition vector based on the multiple information sequences may include: determining all information sequences characterized as abnormal from the multiple information sequences; constructing a sequence graph structure using all information sequences characterized as abnormal as nodes and the associations between the abnormal categories corresponding to all information sequences characterized as abnormal as edges; and converting the sequence graph structure into the post-abnormal operating condition vector through graph embedding or graph representation learning. The associations are suitable for indicating the relative priorities between abnormal categories.

[0063] In an optional implementation, generating the post-abnormal operating condition vector based on the multiple information sequences includes: determining, from the plurality of information sequences, all information sequences characterized as abnormal; Convert each of the information sequences characterized as abnormalities into a sequence vector; The sequence vectors are concatenated to obtain the post-abnormal operating condition vector.

[0064] In this embodiment, since different information sequences correspond to different abnormality categories, and not every category of operating conditions in the post-abnormal operating condition information has abnormalities, this embodiment can select information sequences characterized as abnormalities from multiple information sequences decomposed from the post-abnormal operating condition information, thereby knowing which categories have abnormalities, making the post-abnormal operating condition vector obtained thereby more compact, and thus facilitating the improvement of subsequent matching accuracy and matching efficiency in the abnormal situation database, thereby improving the response speed of subsequent collaborative control.

[0065] In an optional embodiment, any of the abnormality categories is associated with at least one of the at least one device abnormality sub-information.

[0066] It can be understood that under each abnormality category, there may be one or more degrees of abnormality. Therefore, any abnormality category can be associated with at least one of all device abnormality sub-information, and different device abnormality sub-information associated with the abnormality category represents different degrees of abnormality under the abnormality category.

[0067] In an optional embodiment, determining an initial control strategy that matches the abnormality of the abnormal agricultural machine based on the pre-abnormal operating condition information and the target abnormality information includes: Calling a pre-trained abnormal control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information; Among them, the abnormal control model is an artificial intelligence model obtained by training sample operating condition data, and the sample operating condition data includes first sample operating condition information and second sample operating condition information. The first sample operating condition information is suitable for indicating the operating condition of the test equipment when it is in a set abnormal state, and the second sample operating condition information is suitable for indicating the operating condition of the test equipment at the moment before entering the set abnormal state.

[0068] In one example, the artificial intelligence model may include a neural network model, a deep learning model, a reinforcement learning model, a machine learning model, a graph neural network model, etc. Preferably, when the post-abnormal operating condition vector is obtained by converting a sequence graph structure, the artificial intelligence model is preferably a graph neural network model to match the post-abnormal operating condition vector.

[0069] In one example, the test equipment may be an equipment of the same type as the agricultural equipment, and is used to test operating condition data under various set abnormal conditions.

[0070] In one example, the abnormal control model is obtained by iteratively training an artificial intelligence model using sample operating condition data, wherein each round of iterative training may include: Obtain the sample operating condition data and its corresponding labeling strategy; input the first sample operating condition information into the artificial intelligence model, so that the artificial intelligence model generates a first sample control strategy; input the second sample operating condition information into the artificial intelligence model, so that the artificial intelligence model adjusts the first sample control strategy to obtain a second sample control strategy based on the comparison between the second sample operating condition information and the first sample operating condition information; based on the difference between the second sample control strategy and the labeling strategy, perform the current round of training on the artificial intelligence model.

[0071] In an optional embodiment, calling a pre-trained abnormality control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information includes: inputting the target abnormality information into the abnormality control model so that the abnormality control model generates a first device control strategy; The pre-abnormal operating condition information is input into the abnormal control model, so that the abnormal control model adjusts the first device control strategy to obtain the second device control strategy based on the comparison result between the pre-abnormal operating condition information and the target abnormal information, and outputs the second device control strategy as the initial control strategy.

[0072] In one example, the abnormal control model can obtain the comparison result between the pre-abnormal working condition information and the target abnormal information by comparing the differences between the various equipment performance indicators indicated by the pre-abnormal working condition information and the various equipment performance indicators indicated by the target abnormal information.

[0073] In one example, the abnormal control model can obtain the corresponding comparison result by calculating the similarity between the pre-abnormal operating condition information and the target abnormality information.

[0074] In an optional embodiment, the updating of the initial control strategy based on the environmental information to obtain a target control strategy includes: Determining code information corresponding to the initial control strategy; Converting the environmental information into environmental text, and adjusting the environmental text according to keywords in the environmental text and a directory tree of a code database that matches the abnormal agricultural tool, so that the adjusted environmental text matches the directory structure of the code database; The code information and the adjusted environment text are input into the abnormality control model, so that the abnormality control model updates the code information according to the adjusted environment text to obtain updated code information for indicating the target control strategy.

[0075] The updated code information can be sent to the abnormal agricultural machine, causing it to execute the target control strategy. In this embodiment, because the adjusted environment text better matches the directory structure of the abnormal agricultural machine's code database, the abnormal control model can accordingly update the code information to the updated code information that better matches the abnormal agricultural machine's code database, facilitating more efficient call of relevant codes by the abnormal agricultural machine.

[0076] Second, see Figure 2 , shows a schematic structural diagram of an agricultural appliance provided in an embodiment of the present application, the agricultural appliance comprising: The controller 201 is configured to execute any of the above methods.

[0077] In a third aspect, an embodiment of the present application provides a computer device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the steps of the agricultural machinery motor control method described in any one of the above items are implemented.

[0078] See also Figure 3 The computer device of this embodiment includes: a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301, such as a control program for an agricultural machine motor. When the processor 301 executes the computer program, the steps of the above-mentioned various agricultural machine motor control method embodiments are implemented, such as Figure 1 Steps S101-S105 are shown.

[0079] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0080] The computer device may be a desktop computer, laptop, PDA, cloud server, or other computing device. The computer device may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that the schematic diagram is merely an example of a computer device and does not limit the computer device. The computer device may include more or fewer components than shown, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, and the like.

[0081] The processor 301 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor 301 may be any conventional processor. The processor 301 is the control center of the computer device, connecting various parts of the entire computer device using various interfaces and lines.

[0082] The memory 302 can be used to store the computer programs and / or modules. The processor 301 implements the various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 302 and accessing the data stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 302 may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0083] If the module / unit integrated into the computer device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 301, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium.

[0084] In a fourth aspect, accordingly, an embodiment of the present application further provides a control device for an agricultural machine motor, which can implement all processes of the control method for an agricultural machine motor provided in the above embodiment.

[0085] See also Figure 4 , shows a schematic structural diagram of a control device for agricultural machinery provided in an embodiment of the present application, the control device for agricultural machinery comprising: The information acquisition module 401 is configured to determine whether an abnormal agricultural appliance exists among the plurality of agricultural appliances, obtain operating condition information before and after the abnormality of the abnormal agricultural appliance, and obtain environmental information of the environment in which the abnormal agricultural appliance is located; A database query module 402 is configured to determine target abnormality information from the device abnormality information included in the abnormality database based on the post-abnormal operating condition information; An initial control strategy determination module 403 is configured to determine an initial control strategy that matches the abnormality of the abnormal agricultural implement based on the pre-abnormal operating condition information and the target abnormality information; The target control strategy determination module 404 is configured to update the initial control strategy based on the environmental information to obtain a target control strategy; The control module 405 is configured to control the plurality of agricultural implements using an ant colony algorithm according to the target control strategy.

[0086] In an optional implementation, the environmental information includes at least one of temperature information and humidity information corresponding to the environment.

[0087] In an optional embodiment, the device abnormality information includes at least one device abnormality sub-information, and the abnormal situation database further includes at least one abnormality sub-vector corresponding to the at least one device abnormality sub-information, and the abnormality sub-vector is obtained by converting the corresponding device abnormality sub-information; The determining target abnormality information from the device abnormality information included in the abnormality database based on the abnormality post-operating condition information includes: generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information; Determining a target abnormal sub-vector that matches the post-abnormal operating condition vector from the at least one abnormal sub-vector included in the abnormal situation database; The device abnormality sub-information corresponding to the target abnormality sub-vector is acquired from the at least one device abnormality sub-information included in the abnormal situation database to serve as the target abnormality information.

[0088] In an optional implementation, generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information includes: Decomposing the post-abnormal operating condition information into multiple information sequences, wherein different information sequences correspond to different abnormal categories; The post-abnormal operating condition vector is generated based on the multiple information sequences.

[0089] In an optional implementation, generating the post-abnormal operating condition vector based on the multiple information sequences includes: determining, from the plurality of information sequences, all information sequences characterized as abnormal; Convert each of the information sequences characterized as abnormalities into a sequence vector; The sequence vectors are concatenated to obtain the post-abnormal operating condition vector.

[0090] In an optional embodiment, any of the abnormality categories is associated with at least one of the at least one device abnormality sub-information.

[0091] In an optional embodiment, determining an initial control strategy that matches the abnormality of the abnormal agricultural machine based on the pre-abnormal operating condition information and the target abnormality information includes: Calling a pre-trained abnormal control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information; Among them, the abnormal control model is an artificial intelligence model obtained by training sample operating condition data, and the sample operating condition data includes first sample operating condition information and second sample operating condition information. The first sample operating condition information is suitable for indicating the operating condition of the test equipment when it is in a set abnormal state, and the second sample operating condition information is suitable for indicating the operating condition of the test equipment at the moment before entering the set abnormal state.

[0092] In an optional embodiment, calling a pre-trained abnormality control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information includes: inputting the target abnormality information into the abnormality control model so that the abnormality control model generates a first device control strategy; The pre-abnormal operating condition information is input into the abnormal control model, so that the abnormal control model adjusts the first device control strategy to obtain the second device control strategy based on the comparison result between the pre-abnormal operating condition information and the target abnormal information, and outputs the second device control strategy as the initial control strategy.

[0093] In an optional embodiment, the updating of the initial control strategy based on the environmental information to obtain a target control strategy includes: Determining code information corresponding to the initial control strategy; Converting the environmental information into environmental text, and adjusting the environmental text according to keywords of the environmental text and a directory tree of a code database matching the abnormal agricultural equipment; The code information and the adjusted environment text are input into the abnormality control model, so that the abnormality control model updates the code information according to the adjusted environment text to obtain updated code information for indicating the target control strategy.

[0094] In summary, the embodiments of the present application have at least the following beneficial effects: According to an embodiment of the present application, by determining that there is an abnormal agricultural appliance among a plurality of the agricultural appliances, the pre-abnormal operating condition information and post-abnormal operating condition information of the abnormal agricultural appliance are obtained, and the environmental information of the environment in which the abnormal agricultural appliance is located is obtained; based on the post-abnormal operating condition information, target abnormality information is determined in the appliance abnormality information included in the abnormal situation database; based on the pre-abnormal operating condition information and the target abnormality information, an initial control strategy matching the abnormality of the abnormal agricultural appliance is determined; based on the environmental information, the initial control strategy is updated to obtain a target control strategy; according to the target control strategy, an ant colony algorithm is used to control the plurality of the agricultural appliances, so that when an abnormal agricultural appliance appears in the agricultural appliances, a control strategy that is compatible with the abnormal situation of the abnormal agricultural appliance can be accurately determined, and the control strategy can be fed back to the ant colony algorithm for realizing multi-machine collaboration, thereby timely handling the abnormal situation of the abnormal agricultural appliance while reducing the impact on the collaborative operation of multiple agricultural appliances.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary hardware platform, and of course, it can also be implemented entirely through hardware. Based on this understanding, all or part of the contribution of the technical solution of the present application to the background technology can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments.

[0096] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A method for controlling agricultural machinery, characterized in that: include: Determining that an abnormal agricultural appliance exists among the plurality of agricultural appliances, obtaining pre-abnormal operating condition information and post-abnormal operating condition information of the abnormal agricultural appliance, and obtaining environmental information of an environment in which the abnormal agricultural appliance is located; Based on the post-abnormal working condition information, determining target abnormality information from the device abnormality information included in the abnormality database; Determining an initial control strategy that matches the abnormality of the abnormal agricultural machine based on the pre-abnormal operating condition information and the target abnormality information; Updating the initial control strategy based on the environmental information to obtain a target control strategy; According to the target control strategy, the plurality of agricultural implements are controlled using an ant colony algorithm.

2. The method according to claim 1, characterized in that The environmental information includes at least one of temperature information and humidity information corresponding to the environment.

3. The method according to claim 1, characterized in that The device abnormality information includes at least one device abnormality sub-information, and the abnormal situation database also includes at least one abnormality sub-vector corresponding to the at least one device abnormality sub-information, and the abnormality sub-vector is obtained by converting the corresponding device abnormality sub-information; The determining target abnormality information from the device abnormality information included in the abnormality database based on the abnormality post-operating condition information includes: generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information; Determining a target abnormal sub-vector that matches the post-abnormal operating condition vector from the at least one abnormal sub-vector included in the abnormal situation database; The device abnormality sub-information corresponding to the target abnormality sub-vector is acquired from the at least one device abnormality sub-information included in the abnormal situation database to serve as the target abnormality information.

4. The method according to claim 3, characterized in that Generating a corresponding post-abnormal operating condition vector according to the post-abnormal operating condition information includes: Decomposing the post-abnormal operating condition information into multiple information sequences, wherein different information sequences correspond to different abnormal categories; The post-abnormal operating condition vector is generated based on the multiple information sequences.

5. The method according to claim 4, characterized in that The generating the post-abnormal operating condition vector based on the multiple information sequences includes: determining, from the plurality of information sequences, all information sequences characterized as abnormal; Convert each of the information sequences characterized as abnormalities into a sequence vector; The sequence vectors are concatenated to obtain the post-abnormal operating condition vector.

6. The method according to claim 4, characterized in that Any of the abnormality categories is associated with at least one of the at least one device abnormality sub-information.

7. The method according to claim 1, characterized in that The determining of an initial control strategy that matches the abnormality of the abnormal agricultural machinery based on the pre-abnormal operating condition information and the target abnormality information includes: Calling a pre-trained abnormal control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information; Among them, the abnormal control model is an artificial intelligence model obtained by training sample operating condition data, and the sample operating condition data includes first sample operating condition information and second sample operating condition information. The first sample operating condition information is suitable for indicating the operating condition of the test equipment when it is in a set abnormal state, and the second sample operating condition information is suitable for indicating the operating condition of the test equipment at the moment before entering the set abnormal state.

8. The method according to claim 7, characterized in that The calling of the pre-trained abnormal control model to generate the initial control strategy based on the pre-abnormal operating condition information and the target abnormality information includes: inputting the target abnormality information into the abnormality control model so that the abnormality control model generates a first device control strategy; The pre-abnormal operating condition information is input into the abnormal control model, so that the abnormal control model adjusts the first device control strategy to obtain the second device control strategy based on the comparison result between the pre-abnormal operating condition information and the target abnormal information, and outputs the second device control strategy as the initial control strategy.

9. The method according to claim 7, characterized in that The updating of the initial control strategy based on the environmental information to obtain a target control strategy includes: Determining code information corresponding to the initial control strategy; Converting the environmental information into environmental text, and adjusting the environmental text according to keywords of the environmental text and a directory tree of a code database matching the abnormal agricultural equipment; The code information and the adjusted environment text are input into the abnormality control model, so that the abnormality control model updates the code information according to the adjusted environment text to obtain updated code information for indicating the target control strategy.

10. An agricultural implement, characterized in that: include: A controller configured to execute the method according to any one of claims 1 to 9.

Images