Automatic seeder control system and method based on fuzzy pid algorithm
Through fuzzy PID algorithm and deep learning, analyzing seed depth errors and generating adjustment factors, the problem of inconsistent seed depth in traditional seed machines under different soil conditions is solved, the automation and intelligence of seed machine control system is realized, and the uniformity of crop growth is improved and agricultural production benefits.
Patent Information
- Application Number
- CN202411267031.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional seeder control systems are difficult to adapt to different soil conditions, resulting in inconsistent seeding depths, affecting crop growth and agricultural production efficiency.
The seeder automation control system based on the fuzzy PID algorithm is adopted to collect time series data of seeding depth, use artificial intelligence and deep learning algorithms to analyze the seeding depth error and error change rate, generate integral, proportional and differential adjustment factors, and adjust the seeding depth to achieve consistency.
The automation and intelligence of the seed machine control system are improved, the consistency of sowing depth is ensured, and crop growth uniformity and agricultural production efficiency are improved.
Smart Images

Figure CN118938651A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of seed drills, and in particular to an automatic control system and method for seed drills based on a fuzzy PID algorithm. Background Art
[0002] In modern agriculture, the control system of the seed drill is an important part of improving crop yield and quality. The seeding depth directly affects the germination rate, root growth and subsequent crop growth of the crop. Inappropriate seeding depth may lead to slow growth, low germination rate and even death of the crop. Therefore, precise control of seeding depth is essential to ensure healthy growth of crops.
[0003] However, traditional seed drills usually rely on mechanical or simple electronic control systems, which often lack the ability to adapt to different soil conditions and make it difficult to achieve precise control of seeding depth. In other words, traditional seed drills often have difficulty maintaining consistent seeding depths under different soil conditions, resulting in uneven crop growth, which in turn affects overall agricultural production benefits. In addition, mechanical wear and differences in operator skills can also affect seeding quality.
[0004] Therefore, an optimized planter control system is desired. Summary of the invention
[0005] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.
[0006] In the first aspect, the present application provides a seed drill automation control system based on a fuzzy PID algorithm, the system comprising:
[0007] The sowing depth time series data acquisition module is used to obtain the time queue of the sowing depth;
[0008] A sowing depth error multi-order data calculation module is used to calculate the sowing depth error and the error change rate at each predetermined time point in the sowing depth time queue based on the set sowing depth to obtain the sowing depth error time queue and the error change rate time queue;
[0009] A sowing depth error multi-order time series feature extraction module is used to perform time series encoding on the time queue of the sowing depth error and the time queue of the error change rate to obtain a sowing depth error time series associated feature vector and an error change rate time series associated feature vector;
[0010] An error multi-order temporal feature fusion module, used for inputting the sowing depth error temporal correlation feature vector and the error change rate temporal correlation feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector;
[0011] A fuzzy control result generation module, used to generate a fuzzy control result based on the error multi-order fusion representation vector, wherein the fuzzy control result is an integral adjustment factor, a proportional adjustment factor and a differential adjustment factor;
[0012] The control signal calculation module is used to input the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor into a PID controller, and calculate a control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0013] Optionally, the multi-order time series feature extraction module of the sowing depth error is used to: input the time queue of the sowing depth error and the time queue of the error change rate into a sequence encoder based on a bidirectional LSTM model respectively to obtain the sowing depth error time series associated feature vector and the error change rate time series associated feature vector.
[0014] Optionally, the error multi-order temporal feature fusion module includes: a global eigenvalue association matrix calculation unit, which is used to calculate the global eigenvalue association matrix between the sowing depth error temporal association feature vector and the error change rate temporal association feature vector to obtain the sowing depth error multi-order global eigenvalue association matrix; a gating function calculation unit, which is used to input the sowing depth error multi-order global eigenvalue association matrix into a learnable gating function to obtain the sowing depth error multi-order correlation distinguishable weight matrix; a matrix product calculation unit, which is used to use the sowing depth error multi-order correlation distinguishable weight matrix as a fusion mask matrix, and respectively calculate the matrix product between the sowing depth error temporal association feature vector and the error change rate temporal association feature vector and the sowing depth error multi-order correlation distinguishable weight matrix to obtain the differentiated enhanced sowing depth error temporal association feature vector and the differentiated enhanced error change rate temporal association feature vector; a vector fusion unit, which is used to fuse the differentiated enhanced sowing depth error temporal association feature vector and the differentiated enhanced error change rate temporal association feature vector to obtain the error multi-order fusion representation vector.
[0015] Optionally, the global eigenvalue association matrix calculation unit is used to calculate the vector multiplication between the transposed vector of the sowing depth error time series association eigenvalue vector and the error change rate time series association eigenvalue vector to obtain the sowing depth error multi-order global eigenvalue association matrix.
[0016] Optionally, the gating function calculation unit is used to: use the negative number of each position eigenvalue in the sowing depth error multi-order global eigenvalue association matrix as the exponential power, calculate the natural exponential function value with the natural constant e as the base to obtain the sowing depth error multi-order global eigenvalue association class support matrix; calculate the reciprocal of the sum of the eigenvalues at each position in the sowing depth error multi-order global eigenvalue association class support matrix and the constant 1 to obtain the sowing depth error multi-order global eigenvalue association weight matrix; calculate the position point multiplication between the sowing depth error multi-order global eigenvalue association weight matrix and the sowing depth error multi-order global eigenvalue association matrix to obtain the sowing depth error multi-order correlation distinguishable weight matrix.
[0017] Optionally, the vector fusion unit is used to: cascade the time-series correlation feature vector for distinguishing and enhancing the sowing depth error and the time-series correlation feature vector for distinguishing and enhancing the error change rate to obtain the error multi-order fusion representation vector.
[0018] Optionally, the fuzzy control result generation module is used to: input the error multi-order fusion representation vector into a decoder-based fuzzy controller to obtain the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0019] In a second aspect, the present application provides a method for automatic control of a seed drill based on a fuzzy PID algorithm, the method comprising:
[0020] Get the time queue of seeding depth;
[0021] Based on the set sowing depth, calculating the sowing depth error and the error change rate at each predetermined time point in the sowing depth time queue to obtain a sowing depth error time queue and an error change rate time queue;
[0022] Performing time series coding on the time queue of the sowing depth error and the time queue of the error change rate respectively to obtain a sowing depth error time series associated feature vector and an error change rate time series associated feature vector;
[0023] Input the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector;
[0024] Based on the multi-order fusion representation vector of the error, a fuzzy control result is generated, wherein the fuzzy control result is an integral adjustment factor, a proportional adjustment factor and a differential adjustment factor;
[0025] The integral adjustment factor, the proportional adjustment factor and the differential adjustment factor are input into a PID controller, and a control signal is calculated based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0026] Optionally, the time queue of the sowing depth error and the time queue of the error change rate are respectively time-series encoded to obtain the sowing depth error time-series associated feature vector and the error change rate time-series associated feature vector, including: inputting the time queue of the sowing depth error and the time queue of the error change rate into a sequence encoder based on a bidirectional LSTM model respectively to obtain the sowing depth error time-series associated feature vector and the error change rate time-series associated feature vector.
[0027] Optionally, the sowing depth error time-series correlation feature vector and the error change rate time-series correlation feature vector are input into a fine-grained eigenvalue correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector, including: calculating the global eigenvalue correlation matrix between the sowing depth error time-series correlation feature vector and the error change rate time-series correlation feature vector to obtain a sowing depth error multi-order global eigenvalue correlation matrix; inputting the sowing depth error multi-order global eigenvalue correlation matrix into a learnable gating function to obtain a sowing depth error multi-order correlation distinguishable weight matrix; using the sowing depth error multi-order correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix product between the sowing depth error time-series correlation feature vector and the error change rate time-series correlation feature vector and the sowing depth error multi-order correlation distinguishable weight matrix to obtain a distinguished enhanced sowing depth error time-series correlation feature vector and a distinguished enhanced error change rate time-series correlation feature vector; fusing the distinguished enhanced sowing depth error time-series correlation feature vector and the distinguished enhanced error change rate time-series correlation feature vector to obtain the error multi-order fusion representation vector.
[0028] The above technical solution is adopted to collect the sowing depth error and error change rate between the measured data of the sowing depth and the sowing target depth in time series, and introduce data processing and analysis algorithms based on artificial intelligence and deep learning in the back end to perform time series fine-grained collaborative correlation analysis on the sowing depth error and error change rate, so as to learn and capture the multi-order dynamic fusion characteristics of the sowing depth error in the sowing time series, thereby generating the parameters of the PID controller, including the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor. In this way, the sowing depth can be adjusted to achieve consistency in the sowing depth, and the automation level and intelligence level of the seeder control system are improved.
[0029] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:
[0031] Figure 1 It is a block diagram of a seed drill automation control system based on a fuzzy PID algorithm according to an exemplary embodiment.
[0032] Figure 2 It is a flow chart of a method for automatic control of a seed drill based on a fuzzy PID algorithm according to an exemplary embodiment.
[0033] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.
[0034] Figure 4 It is an application scenario diagram of a seed drill automation control system based on a fuzzy PID algorithm according to an exemplary embodiment. DETAILED DESCRIPTION
[0035] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.
[0036] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.
[0037] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0038] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0039] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0040] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0041] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.
[0042] Figure 1 1 is a block diagram of a planter automation control system based on a fuzzy pid algorithm according to an exemplary embodiment. Figure 1 As shown, the system 100 includes:
[0043] A sowing depth time series data acquisition module 101 is used to obtain a time queue of sowing depth;
[0044] A sowing depth error multi-order data calculation module 102 is used to calculate the sowing depth error and the error change rate at each predetermined time point in the sowing depth time sequence based on the set sowing depth to obtain the sowing depth error time sequence and the error change rate time sequence;
[0045] A sowing depth error multi-order time series feature extraction module 103 is used to perform time series coding on the time queue of the sowing depth error and the time queue of the error change rate to obtain a sowing depth error time series associated feature vector and an error change rate time series associated feature vector;
[0046] The error multi-order time series feature fusion module 104 is used to input the sowing depth error time series associated feature vector and the error change rate time series associated feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector;
[0047] A fuzzy control result generating module 105, for generating a fuzzy control result based on the error multi-order fusion representation vector, wherein the fuzzy control result is an integral adjustment factor, a proportional adjustment factor and a differential adjustment factor;
[0048] The control signal calculation module 106 is used to input the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor into a PID controller, and calculate a control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0049] In response to the above technical problems, automatic control technology has gradually been introduced into the design of seed drills. PID (proportional-integral-differential) controllers are widely used in various automation systems due to their simplicity and good control performance. However, the control effect of traditional PID controllers is often limited when faced with complex environments such as nonlinearity, uncertainty and time-varying.
[0050] As an experience-based control method, fuzzy control can effectively handle the uncertainty and ambiguity of the system. The fuzzy controller can dynamically adjust the parameters of the PID controller (such as proportional gain Kp, integral gain Ki and differential gain Kd) according to the real-time sowing status and soil environmental conditions, thereby improving the control performance of the sowing machine. Especially in the sowing depth control, the fuzzy PID controller can flexibly adjust the control parameters according to the real-time measured sowing depth error and error change rate, and generate control signals to adapt to different soil conditions and crop sowing depth requirements.
[0051] Based on this, in the technical solution of the present application, a seed drill automation control system based on fuzzy PID algorithm is proposed, which can collect the seed drill depth measurement data and the seed drill target depth in the time series between the seed drill depth error and error change rate, and introduce the data processing and analysis algorithm based on artificial intelligence and deep learning in the back end to perform time series fine-grained collaborative correlation analysis on the seed drill depth error and error change rate, so as to learn and capture the multi-order dynamic fusion characteristics of the seed drill depth error in the seed drill time series, thereby generating the parameters of the PID controller, including the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor. In this way, the PID controller can calculate the control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor, and drive the actuator (such as a hydraulic system or a motor) of the seed drill based on the control signal to adjust the seed drill depth, thereby achieving consistency of the seed drill depth and improving the automation level and intelligence level of the seed drill control system.
[0052] Specifically, in the technical solution of the present application, first, the time queue of the sowing depth is obtained, and the sowing depth is set. Then, in order to determine the degree of deviation of the current sowing depth from the target value, thereby providing necessary feedback information for the control system, in the technical solution of the present application, the sowing depth error and the error change rate at each predetermined time point in the time queue of the sowing depth are calculated to obtain the time queue of the sowing depth error and the time queue of the error change rate. It is worth mentioning that the error change rate reflects the time series change trend of the sowing depth error, that is, whether the error increases or decreases. This information helps the controller to infer the future development of the sowing depth error and provide a basis for subsequent control.
[0053] Then, the time queue of the sowing depth error and the time queue of the error change rate are respectively input into the sequence encoder based on the bidirectional LSTM model for encoding, so as to extract the forward and backward correlation features of the sowing depth error and the error change rate in the time dimension respectively, thereby obtaining the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector.
[0054] In one embodiment of the present application, the multi-order time series feature extraction module of the sowing depth error is used to: respectively input the time queue of the sowing depth error and the time queue of the error change rate into a sequence encoder based on a bidirectional LSTM model to obtain the sowing depth error time series associated feature vector and the error change rate time series associated feature vector.
[0055] It should be understood that the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector respectively contain the time series feature information about the sowing depth error and the error change rate in the time dimension. The error time series feature reflects the deviation degree of the current sowing depth, while the error change rate reveals the dynamic change trend of the sowing depth deviation. Based on this, in order to more comprehensively understand the time series change and trend of the sowing depth error, so as to more effectively guide the sowing depth control decision, in the technical solution of the present application, the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector are further input into the fine-grained feature value correlation distinguishing attention fusion unit to obtain the error multi-order fusion representation vector. Through the processing of the fine-grained feature value correlation distinguishing attention fusion unit, the sowing depth error time series feature and the error change rate time series feature can be fused to integrate the time series implicit correlation feature information of the two about the error multi-order, enhance the expression ability of the dynamic change feature of the sowing error time series, and form a more comprehensive error multi-order time series feature representation. In addition, the fine-grained feature value relevance distinguishing attention mechanism can adaptively adjust the fusion weights of different features during the feature fusion process according to the importance and contribution of the input error time series dynamic features and change rate time series features to the subsequent decision-making control task, so as to dynamically adjust the focus, so that the model can adapt to changing environments and needs more flexibly. Therefore, the fine-grained feature value relevance distinguishing attention fusion unit can better capture the subtle time series changes in the error and error change rate, which may be crucial to the adjustment of the seeding depth control strategy.
[0056] In one embodiment of the present application, the error multi-order temporal feature fusion module includes: a global eigenvalue association matrix calculation unit, which is used to calculate the global eigenvalue association matrix between the sowing depth error temporal association feature vector and the error change rate temporal association feature vector to obtain a sowing depth error multi-order global eigenvalue association matrix; a gating function calculation unit, which is used to input the sowing depth error multi-order global eigenvalue association matrix into a learnable gating function to obtain a sowing depth error multi-order correlation distinguishable weight matrix; a matrix product calculation unit, which is used to use the sowing depth error multi-order correlation distinguishable weight matrix as a fusion mask matrix, and respectively calculate the matrix product between the sowing depth error temporal association feature vector and the error change rate temporal association feature vector and the sowing depth error multi-order correlation distinguishable weight matrix to obtain a differentiated enhanced sowing depth error temporal association feature vector and a differentiated enhanced error change rate temporal association feature vector; a vector fusion unit, which is used to fuse the differentiated enhanced sowing depth error temporal association feature vector and the differentiated enhanced error change rate temporal association feature vector to obtain the error multi-order fusion representation vector.
[0057] Furthermore, in one embodiment of the present application, the global eigenvalue association matrix calculation unit is used to: calculate the vector multiplication between the transposed vector of the sowing depth error time series association eigenvalue vector and the error change rate time series association eigenvalue vector to obtain the sowing depth error multi-order global eigenvalue association matrix.
[0058] Furthermore, in one embodiment of the present application, the gated function calculation unit is used to: use the negative number of each position eigenvalue in the sowing depth error multi-order global eigenvalue association matrix as the exponential power, calculate the natural exponential function value with the natural constant e as the base to obtain the sowing depth error multi-order global eigenvalue association class support matrix; calculate the reciprocal of the sum of the eigenvalues at each position in the sowing depth error multi-order global eigenvalue association class support matrix and the constant 1 to obtain the sowing depth error multi-order global eigenvalue association weight matrix; calculate the point-by-point multiplication between the sowing depth error multi-order global eigenvalue association weight matrix and the sowing depth error multi-order global eigenvalue association matrix to obtain the sowing depth error multi-order correlation distinguishable weight matrix.
[0059] Furthermore, in one embodiment of the present application, the vector fusion unit is used to: cascade the time-series correlation feature vector for distinguishing and enhancing the sowing depth error and the time-series correlation feature vector for distinguishing and enhancing the error change rate to obtain the error multi-order fusion representation vector.
[0060] Specifically, the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector are input into the fine-grained feature value correlation distinguishing attention fusion unit for processing using the following distinguishable attention fusion formula to obtain the error multi-order fusion representation vector;
[0061] Among them, the distinguishable attention fusion formula is:
[0062] S=(v1) T v2
[0063]
[0064] Wherein, v1 and v2 are the time series correlation feature vector of the sowing depth error and the time series correlation feature vector of the error change rate, respectively; S is the multi-order global eigenvalue correlation matrix of the sowing depth error; exp(·) is the exponential operation with e as the base; W is the multi-order global eigenvalue correlation weight matrix of the sowing depth error; S w is the distinguishable weight matrix of multi-order correlation of seeding depth error, and are the temporal correlation feature vectors for distinguishing and enhancing the seeding depth error and the temporal correlation feature vectors for distinguishing and enhancing the error change rate, [·,·] is the cascade operation of the vectors, and v f is the error multi-order fusion representation vector, (·) T Represents the transposed vector of a vector.
[0065] Then, the error multi-order fusion representation vector is input into the decoder-based fuzzy controller to obtain the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor. That is to say, the multi-order time series fusion characteristics of the sowing depth error are used for decoding regression to generate the fuzzy control result, including the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor. Then, the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor are input into the PID controller to adjust the parameters of the PID controller. For example, if the sowing depth error is large and the rate of change is large, the proportional gain Kp and the differential gain Kd can be controlled to increase the response speed of the system. It is worth mentioning that the PID controller can further calculate the control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor. In this way, the control signal can be used to drive the actuator (such as a hydraulic system or a motor) of the seed drill to adjust the sowing depth, thereby achieving the consistency of the sowing depth and improving the automation level and intelligence level of the seed drill control system.
[0066] In one embodiment of the present application, the fuzzy control result generation module is used to: input the error multi-order fusion representation vector into a decoder-based fuzzy controller to obtain the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0067] In a preferred example, the present application takes into account that the sowing depth error temporal correlation feature vector and the error change rate temporal correlation feature vector respectively represent the short-range and long-range bidirectional temporal correlation features of the sowing depth error and its change rate. Therefore, after performing fine-grained feature value correlation-differentiated attention fusion, the error multi-order fusion representation vector will also cause decoding semantic regression offset due to the difference in temporal correlation-differentiated attention weights, resulting in insufficient offset semantic coverage, thereby causing outlier decoding regression inference mapping deviation, affecting the decoding result obtained by the error multi-order fusion representation vector input into the decoder-based fuzzy controller, that is, the accuracy of the integral adjustment factor, proportional adjustment factor and differential adjustment factor.
[0068] Based on this, when the error multi-order fusion representation vector is input into the decoder-based fuzzy controller to obtain a decoding result, the error multi-order fusion representation vector is optimized, and the optimization process specifically includes:
[0069] Calculating a characteristic mean of the error multi-order fusion representation vector, and dividing the characteristic mean by a difference between a maximum eigenvalue and a minimum eigenvalue of the error multi-order fusion representation vector to obtain an error multi-order fusion representation distribution representation value;
[0070] Subtracting the error multi-order fusion representation distribution characterization value from one and dividing the result by the error multi-order fusion representation distribution characterization value to obtain the error multi-order fusion representation distribution modulation value;
[0071] Activating the error multi-order fusion representation vector through a probabilistic function to obtain a probabilistic error multi-order fusion representation vector;
[0072] After performing point subtraction between the probabilistic error multi-order fusion representation vector and the error multi-order fusion representation distribution modulation value, taking the absolute value and calculating the negative of the logarithmic value with base 2 to obtain the probabilistic error multi-order fusion representation distribution modulation information vector;
[0073] After dividing the error multi-order fusion representation distribution characterization value by one minus the difference of each eigenvalue of the probabilistic error multi-order fusion representation vector, summing all eigenvalues of the probabilistic error multi-order fusion representation vector and dividing by the length of the error multi-order fusion representation vector to obtain a probabilistic error multi-order fusion representation distribution modulation bias value;
[0074] The product of the probabilistic error multi-order fusion representation distribution modulation information vector and the probabilistic error multi-order fusion representation distribution modulation bias value and the weight as a hyperparameter is multiplied to obtain an optimized error multi-order fusion representation vector.
[0075] Among them, the optimization expression of the error multi-order fusion representation vector is:
[0076]
[0077] And among them:
[0078]
[0079] Among them, V is the probabilistic error multi-order fusion representation vector, is the characteristic mean of the error multi-order fusion representation vector, v max is the maximum eigenvalue of the error multi-order fusion representation vector, v min is the minimum eigenvalue of the error multi-order fusion representation vector, p is the distribution representation value of the error multi-order fusion representation, v i is each eigenvalue of the probabilistic error multi-order fusion representation vector, L is the length of the error multi-order fusion representation vector, ε is the weight of the hyperparameter, V ′is the optimized error multi-order fusion representation vector, represents positional subtraction, and ⊕ represents positional addition.
[0080] That is, in the above preferred example, the probability information distribution planning based on the eigenvalue of the error multi-order fusion representation vector is carried out through the Bernoulli probability modulation distribution of the error multi-order fusion representation vector relative to the eigenvalue distribution, and the probability reverse mapping of the probability feature of the error multi-order fusion representation vector as a whole is used as the extended coverage of the set mapping space of the error multi-order fusion representation vector to independently understand the interactive path between the intuitive probability information distribution and the abstract probability space mapping of the error multi-order fusion representation vector, so as to improve the accuracy of the decoding result obtained by the fuzzy controller based on the decoder of the optimized error multi-order fusion representation vector input, that is, the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor by avoiding the counterfactual reasoning mapping of the outlier feature distribution of the error multi-order fusion representation vector to the decoding regression probability. In this way, the parameters of the PID controller can be calculated more accurately, and the control signal can be further calculated based on the parameters of the PID controller to drive the actuator (such as a hydraulic system or a motor) of the seed drill to adjust the seeding depth, thereby achieving the consistency of the seeding depth and improving the automation level and intelligence level of the seed drill control system.
[0081] In summary, the above scheme is adopted to collect the sowing depth error and error change rate between the measured data of the sowing depth and the sowing target depth in time series, and introduce data processing and analysis algorithms based on artificial intelligence and deep learning in the back end to perform time series fine-grained collaborative correlation analysis on the sowing depth error and error change rate, so as to learn and capture the multi-order dynamic fusion characteristics of the sowing depth error in the sowing time series, thereby generating the parameters of the PID controller, including the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor. In this way, the PID controller can calculate the control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor, and drive the actuator (such as a hydraulic system or a motor) of the seeder based on the control signal to adjust the sowing depth, thereby achieving consistency of the sowing depth and improving the automation level and intelligence level of the seeder control system.
[0082] Figure 2 is a flow chart of a method for automatic control of a seed drill based on a fuzzy pid algorithm according to an exemplary embodiment, as shown in Figure 2 As shown, the method includes:
[0083] Step S201, obtaining a time queue of sowing depth;
[0084] Step S202: based on the set sowing depth, calculating the sowing depth error and the error change rate at each predetermined time point in the sowing depth time queue to obtain a sowing depth error time queue and an error change rate time queue;
[0085] Step S203, respectively performing time series coding on the time queue of the sowing depth error and the time queue of the error change rate to obtain a sowing depth error time series associated feature vector and an error change rate time series associated feature vector;
[0086] Step S204, inputting the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector;
[0087] Step S205: generating a fuzzy control result based on the error multi-order fusion representation vector, wherein the fuzzy control result is an integral adjustment factor, a proportional adjustment factor and a differential adjustment factor;
[0088] Step S206: input the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor into a PID controller, and calculate a control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0089] In one embodiment of the present application, the time queue of the sowing depth error and the time queue of the error change rate are respectively time-series encoded to obtain the sowing depth error time-series associated feature vector and the error change rate time-series associated feature vector, including: inputting the time queue of the sowing depth error and the time queue of the error change rate into a sequence encoder based on a bidirectional LSTM model respectively to obtain the sowing depth error time-series associated feature vector and the error change rate time-series associated feature vector.
[0090] In one embodiment of the present application, the sowing depth error temporal correlation feature vector and the error change rate temporal correlation feature vector are input into a fine-grained eigenvalue correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector, including: calculating the global eigenvalue correlation matrix between the sowing depth error temporal correlation feature vector and the error change rate temporal correlation feature vector to obtain a sowing depth error multi-order global eigenvalue correlation matrix; inputting the sowing depth error multi-order global eigenvalue correlation matrix into a learnable gating function to obtain a sowing depth error multi-order correlation distinguishable weight matrix; using the sowing depth error multi-order correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix product between the sowing depth error temporal correlation feature vector and the error change rate temporal correlation feature vector and the sowing depth error multi-order correlation distinguishable weight matrix to obtain a distinguished enhanced sowing depth error temporal correlation feature vector and a distinguished enhanced error change rate temporal correlation feature vector; fusing the distinguished enhanced sowing depth error temporal correlation feature vector and the distinguished enhanced error change rate temporal correlation feature vector to obtain the error multi-order fusion representation vector.
[0091] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0092] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0093] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0094] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.
[0095] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0096] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0097] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0098] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0099] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0100] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".
[0101] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0102] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0103] Figure 4 1 is an application scenario diagram of a seed drill automation control system based on a fuzzy PID algorithm according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, the time queue of the seeding depth is obtained (for example, Figure 4 Then, the time queue of the sowing depth obtained is input to a server (for example, Figure 4 In S) shown in the figure, the server is capable of processing the time queue of the sowing depth based on the seed drill automation control algorithm of the fuzzy pid algorithm to calculate the control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
[0104] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.
[0105] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0106] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.
Claims
1. A seed drill automation control system based on fuzzy pid algorithm, characterized in that: include: The sowing depth time series data acquisition module is used to obtain the time queue of the sowing depth; A sowing depth error multi-order data calculation module is used to calculate the sowing depth error and the error change rate at each predetermined time point in the sowing depth time queue based on the set sowing depth to obtain the sowing depth error time queue and the error change rate time queue; A sowing depth error multi-order time series feature extraction module is used to perform time series encoding on the time queue of the sowing depth error and the time queue of the error change rate to obtain a sowing depth error time series associated feature vector and an error change rate time series associated feature vector; An error multi-order temporal feature fusion module, used for inputting the sowing depth error temporal correlation feature vector and the error change rate temporal correlation feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector; A fuzzy control result generation module, used to generate a fuzzy control result based on the error multi-order fusion representation vector, wherein the fuzzy control result is an integral adjustment factor, a proportional adjustment factor and a differential adjustment factor; The control signal calculation module is used to input the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor into a PID controller, and calculate a control signal based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
2. The planter automation control system based on fuzzy pid algorithm according to claim 1 is characterized in that: The sowing depth error multi-order time series feature extraction module is used to: input the time queue of the sowing depth error and the time queue of the error change rate into a sequence encoder based on a bidirectional LSTM model to obtain the sowing depth error time series associated feature vector and the error change rate time series associated feature vector.
3. The planter automation control system based on fuzzy pid algorithm according to claim 2 is characterized in that: The error multi-order time series feature fusion module includes: A global eigenvalue association matrix calculation unit, used for calculating the global eigenvalue association matrix between the sowing depth error time series association eigenvector and the error change rate time series association eigenvector to obtain a multi-order global eigenvalue association matrix of the sowing depth error; A gating function calculation unit, used for inputting the multi-order global eigenvalue association matrix of the sowing depth error into a learnable gating function to obtain a multi-order correlation distinguishable weight matrix of the sowing depth error; A matrix product calculation unit, used for using the sowing depth error multi-order correlation distinguishable weight matrix as a fusion mask matrix, and respectively calculating the matrix products between the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector and the sowing depth error multi-order correlation distinguishable weight matrix to obtain a distinguished enhanced sowing depth error time series correlation feature vector and a distinguished enhanced error change rate time series correlation feature vector; The vector fusion unit is used to fuse the time-series correlation feature vector of distinguishing and strengthening the sowing depth error and the time-series correlation feature vector of distinguishing and strengthening the error change rate to obtain the error multi-order fusion representation vector.
4. The planter automation control system based on fuzzy pid algorithm according to claim 3 is characterized in that: The global eigenvalue association matrix calculation unit is used to calculate the vector multiplication between the transposed vector of the sowing depth error time series association eigenvector and the error change rate time series association eigenvector to obtain the sowing depth error multi-order global eigenvalue association matrix.
5. The planter automation control system based on fuzzy pid algorithm according to claim 4 is characterized in that: The gating function calculation unit is used to: Taking the negative number of each position eigenvalue in the sowing depth error multi-order global eigenvalue association matrix as the exponential power, calculating the natural exponential function value with the natural constant e as the base to obtain the sowing depth error multi-order global eigenvalue association class support matrix; Calculate the reciprocal of the sum of the eigenvalues of each position in the sowing depth error multi-order global eigenvalue association class support matrix and the constant 1 to obtain a sowing depth error multi-order global eigenvalue association weight matrix; The sowing depth error multi-order global eigenvalue association weight matrix and the sowing depth error multi-order global eigenvalue association matrix are calculated by multiplying them by position points to obtain the sowing depth error multi-order correlation distinguishable weight matrix.
6. The planter automation control system based on fuzzy pid algorithm according to claim 5 is characterized in that: The vector fusion unit is used to: cascade the time-series correlation feature vector for distinguishing and enhancing the sowing depth error and the time-series correlation feature vector for distinguishing and enhancing the error change rate to obtain the error multi-order fusion representation vector.
7. The planter automation control system based on fuzzy pid algorithm according to claim 6 is characterized in that: The fuzzy control result generation module is used to: input the error multi-order fusion representation vector into a decoder-based fuzzy controller to obtain the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
8. A seed drill automation control method based on fuzzy pid algorithm, characterized in that: include: Get the time queue of seeding depth; Based on the set sowing depth, calculating the sowing depth error and the error change rate at each predetermined time point in the sowing depth time queue to obtain the sowing depth error time queue and the error change rate time queue; Sequentially encoding the time queue of the sowing depth error and the time queue of the error change rate to obtain a sowing depth error time series associated feature vector and an error change rate time series associated feature vector; Input the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector; Based on the error multi-order fusion representation vector, a fuzzy control result is generated, wherein the fuzzy control result is an integral adjustment factor, a proportional adjustment factor and a differential adjustment factor; The integral adjustment factor, the proportional adjustment factor and the differential adjustment factor are input into a PID controller, and a control signal is calculated based on the integral adjustment factor, the proportional adjustment factor and the differential adjustment factor.
9. The automatic control method for seed drill based on fuzzy PID algorithm according to claim 8 is characterized in that: The time queue of the sowing depth error and the time queue of the error change rate are respectively time-series encoded to obtain the sowing depth error time-series associated feature vector and the error change rate time-series associated feature vector, including: inputting the time queue of the sowing depth error and the time queue of the error change rate into a sequence encoder based on a bidirectional LSTM model respectively to obtain the sowing depth error time-series associated feature vector and the error change rate time-series associated feature vector.
10. The automatic control method of a seed drill based on fuzzy pid algorithm according to claim 9, characterized in that: Inputting the seeding depth error time series correlation feature vector and the error change rate time series correlation feature vector into a fine-grained feature value correlation distinguishing attention fusion unit to obtain an error multi-order fusion representation vector, including: Calculate the global eigenvalue association matrix between the sowing depth error time series association eigenvector and the error change rate time series association eigenvector to obtain a multi-order global eigenvalue association matrix of the sowing depth error; Inputting the multi-order global eigenvalue association matrix of the sowing depth error into a learnable gating function to obtain a multi-order correlation distinguishable weight matrix of the sowing depth error; Taking the sowing depth error multi-order correlation distinguishable weight matrix as the fusion mask matrix, respectively calculating the matrix product between the sowing depth error time series correlation feature vector and the error change rate time series correlation feature vector and the sowing depth error multi-order correlation distinguishable weight matrix to obtain the distinguished enhanced sowing depth error time series correlation feature vector and the distinguished enhanced error change rate time series correlation feature vector; The time series correlation feature vector for distinguishing and strengthening the sowing depth error and the time series correlation feature vector for distinguishing and strengthening the error change rate are fused to obtain the error multi-order fusion representation vector.
Citation Information
Cited By
Customer resource management system and method based on large model
CN119090193A
Code scanning group entering method and device and electronic equipment
CN119094486A
Seeder operation parameter intelligent optimization method based on machine learning
CN121581572A
