Self-adaptive cutting control method of wheel-bucket excavator based on fuzzy algorithm

Abstract

An adaptive cutting control method for bucket wheel excavators based on fuzzy algorithms, relating to the field of bucket wheel excavator control technology, includes the following steps: Step S1, setting up data acquisition components on the bucket wheel excavator for collecting cutting force, vibration velocity, and material moisture data, including pressure sensors, vibration sensors, and microwave moisture meters; Step S2, data preprocessing; Step S3, fuzzification processing; Step S4, establishing a fuzzy rule base; Step S5, performing fuzzy inference operations based on the input fuzzy set and the established fuzzy rule base; Step S6, defuzzifying the obtained output fuzzy set using the centroid method; Step S7, parameter adjustment and execution. This method can perceive the excavation conditions in real time and dynamically adjust the cutting parameters of the bucket wheel excavator according to factors such as material properties, achieving adaptive cutting control, thereby improving excavation efficiency and reducing equipment wear.

Description

Technical Field

[0001] This invention relates to the field of bucket wheel excavator control technology, specifically to an adaptive cutting control method for bucket wheel excavators based on fuzzy algorithms. Background Technology

[0002] Bucket wheel excavators are key equipment in open-pit mining operations, and their cutting efficiency and quality directly affect the progress and cost of the entire project. In actual excavation, the properties of the materials being excavated (such as hardness and moisture content) vary significantly. Traditional bucket wheel excavator control methods often use fixed cutting parameter settings, which are difficult to adapt to these changes. For example, when encountering materials with low moisture content and high hardness, continuing to operate at the conventional cutting speed and force may lead to low cutting efficiency or even damage to the cutting bucket teeth. Conversely, when the material has high moisture content and low hardness, failing to adjust the cutting parameters in a timely manner will prevent the bucket wheel excavator from fully utilizing its digging capabilities, resulting in energy waste.

[0003] Existing adaptive cutting control methods for bucket wheel excavators, such as the "Adaptive Control Method for Excavators" disclosed in patent application CN102071717A, focus their control logic on the action priority of actuators such as the boom and stick, completely neglecting the coordinated control of the core bucket wheel cutting speed and the receiving arm rotation speed. They only collect a single indirect parameter—hydraulic system pressure—resulting in a severely insufficient sense of operational conditions. They employ threshold-based switching control, failing to achieve refined and smooth parameter adjustments. Furthermore, they lack data storage and rule update mechanisms, resulting in poor long-term adaptability.

[0004] For example, the invention patent application CN113216311A discloses an "Adaptive Control Method, Device, and Excavator for Excavators." This control method uses the displacement and angle of the electric control handle to identify the current working condition, and then adjusts the control parameters of the target excavator based on the current working condition. This achieves automatic adjustment of control parameters as the current working condition changes, improving the control efficiency of the excavator. However, the results are easily affected by subjective factors such as the operator's experience and habits, resulting in low reliability. It only adjusts the pump current and priority gain of the hydraulic system, without directly controlling the core execution parameters of the bucket wheel cutting operation, and cannot fundamentally solve the core problems of bucket tooth overload for hard materials and energy waste for soft materials. At the same time, it lacks multi-source data fusion capabilities and intelligent nonlinear algorithm support, resulting in insufficient robustness when facing complex working conditions.

[0005] For example, the invention patent application CN115437239A, which discloses "A method for coordinated control of excavator position and force based on adaptive impedance control," achieves precise single-point trajectory tracking and contact force control at the bucket end. This method is suitable for high-precision operation scenarios such as fine excavation and slope trimming, but it does not match the core operation objectives of bucket wheel excavators, such as large-area continuous cutting and efficient material stripping. Its control effect is highly dependent on a pre-established precise mathematical model, and the control accuracy drops significantly in open-pit mine scenarios where material characteristics change randomly and drastically. Furthermore, the working condition assessment dimensions are incomplete, and a cloud data iteration mechanism is not designed, making it difficult to adapt to the differentiated needs of different mining areas.

[0006] Therefore, there is an urgent need to develop an adaptive cutting control method specifically designed for the continuous cutting operations of bucket wheel excavators. This method should be able to comprehensively sense material characteristics and equipment operating status, employ nonlinear intelligent control algorithms, and possess data-driven continuous optimization capabilities. Summary of the Invention

[0007] The purpose of this invention is to provide an adaptive cutting control method for bucket wheel excavators based on fuzzy algorithms. This method can sense the excavation conditions in real time and dynamically adjust the cutting parameters of the bucket wheel excavator according to factors such as material properties, thereby achieving adaptive cutting control, improving excavation efficiency, and reducing equipment wear.

[0008] To achieve the above objectives, the present invention provides the following technical solution: the adaptive cutting control method for a bucket wheel excavator based on fuzzy algorithm, the key technical points of which include the following steps: Step S1, setting up a data acquisition component on the bucket wheel excavator for collecting cutting force, vibration speed and material moisture data, the data acquisition component includes a pressure sensor, a vibration sensor and a microwave moisture meter; Step S2, data preprocessing: The collected cutting force data, vibration velocity data, and material moisture data are first filtered to remove signal interference and make the data smoother and more accurate; then normalization is performed to unify them to a standard range to facilitate subsequent fuzzy inference processing. Step S3, fuzzification processing: Convert the preprocessed cutting force, vibration velocity, and material humidity data into fuzzy linguistic variables, perform three-level fuzzy classification, and determine the fuzzy set affiliation of each data by membership function; Step S4, Establish a fuzzy rule base: Establish a fuzzy rule base based on expert experience and a large amount of field test data; Step S5: Perform fuzzy inference operations based on the input fuzzy set and the established fuzzy rule base. Step S51: Match the input fuzzy set with each rule in the fuzzy rule base, and determine the activation degree of each rule based on the degree of matching; Step S52: Integrate the effects of all activation rules to obtain the output fuzzy set; Step S6: Defuzzify the obtained output fuzzy set using the centroid method: convert it into executable bucket wheel frequency converter or rotary frequency converter parameter value P1; Step S7, Parameter Adjustment and Execution: Adjust the operating frequency of the bucket wheel motor or slewing motor in real time according to the parameter value P1 to achieve adaptive cutting control of the bucket wheel excavator.

[0009] Furthermore, the data acquisition component also includes a rotary encoder mounted on the output shaft of the receiving arm rotation mechanism for acquiring the rotation angle and speed of the receiving arm, and a pitch encoder mounted on the shaft of the receiving arm pitch mechanism for acquiring the pitch angle of the receiving arm.

[0010] Furthermore, step S3 includes the following steps: Step S31, determine the input and output fuzzy linguistic variables according to the actual needs of the bucket excavator cutting operation; Step S32: Map the preprocessed data from step S2 onto the corresponding fuzzy linguistic variables to form fuzzy sets; Step S33: The cutting force data is divided into three fuzzy sets: soft, medium, and hard; the vibration velocity data is divided into three fuzzy sets: light, medium, and heavy; and the material moisture data is divided into three fuzzy sets: dry, medium, and wet. Step S34: Determine the membership degree of each fuzzy linguistic variable and determine which fuzzy set the data belongs to.

[0011] Furthermore, the fuzzy rule base in step S4 contains multiple fuzzy rules: IF low material moisture AND hard cutting force AND severe motor reducer vibration THEN reduce cutting speed AND decrease rotation speed; IF high material moisture AND soft cutting force AND mild motor reducer vibration THEN increase cutting speed AND increase rotation speed.

[0012] The beneficial effects of this invention are as follows: In the field of cutting operations of bucket wheel excavators, traditional control methods are often constrained by complex and ever-changing working conditions and are difficult to flexibly adapt to different material characteristics. However, the adaptive cutting control method for bucket wheel excavators based on fuzzy algorithms of this invention has achieved a comprehensive breakthrough in operational efficiency and economy through innovative technical logic and functional design.

[0013] With strong adaptability, this invention is based on multi-dimensional data acquisition, comprehensively capturing key data such as material properties and operating status during cutting operations, and then relying on fuzzy algorithms to perform in-depth comprehensive processing of massive amounts of information. Thanks to the algorithm's strong adaptability, the system can automatically and dynamically optimize and adjust cutting parameters according to the material's differentiated characteristics such as hardness, humidity, and viscosity, completely solving the poor adaptability problem caused by the "one-size-fits-all" approach of traditional control methods, allowing the bucket wheel excavator to maintain stable operating performance under various complex working conditions.

[0014] With high cutting efficiency, the system can respond to changes in working conditions in real time and precisely adjust core operating parameters such as cutting speed and receiving arm rotation speed for materials with different characteristics. Whether facing hard ore or soft soil, the bucket wheel excavator can always operate at the optimal rhythm, significantly reducing ineffective working time, significantly improving cutting efficiency, and helping to shorten the overall excavation period of the project.

[0015] Protecting the cutting bucket teeth is crucial, as they are a core, easily worn component of bucket wheel excavators, and their wear directly impacts operating costs and efficiency. This control method features intelligent monitoring and protection functions. When it detects that the material hardness exceeds the normal range, or when the cutting device experiences severe vibrations or other abnormalities, it automatically reduces the cutting speed and rotation speed. This reduces the instantaneous impact force and continuous load on the bucket teeth, effectively preventing breakage and premature wear due to excessive stress, and significantly extending the service life of the cutting bucket teeth.

[0016] To reduce energy consumption, traditional control methods rely on fixed parameters, which often lead to energy waste due to parameter redundancy when excavating soft materials. This method, however, dynamically adjusts cutting parameters based on actual working conditions, achieving precise energy matching and efficient utilization. By avoiding unnecessary energy consumption, it reduces fuel and electricity costs for bucket excavators and minimizes maintenance expenses incurred from high-load operation, thus lowering operating costs for projects from multiple perspectives.

[0017] Highly scalable, this control method employs a dynamic update mechanism for the fuzzy rule base to address the ever-changing demands of work sites and operating conditions in engineering projects. The system continuously iterates and optimizes the fuzzy rule base based on information such as material characteristics and changes in the working environment of new sites, constantly expanding its adaptability. Whether in open-pit mines, water conservancy projects, or urban infrastructure projects, it can quickly adapt to new working conditions, maintain stable and efficient operating performance, and possesses extremely strong scalability.

[0018] Data storage is secure and efficient. At the data management level, this invention uses an IoT gateway to upload all control parameters and actual operating data of the bucket excavator to a cloud server in real time. Leveraging the powerful functions of the cloud platform, on the one hand, remote real-time monitoring of the equipment's operating status is achieved, facilitating timely understanding of equipment operation by management personnel, enabling precise scheduling and fault warnings. On the other hand, the cloud platform can securely store massive amounts of operating data, providing ample data support for continuous updates to the fuzzy rule base, algorithm optimization, and subsequent improvements to operational plans, thus achieving secure and efficient data management. Attached Figure Description

[0019] Figure 1 This is a diagram of the PLC control system architecture of the present invention.

[0020] Figure 2 This is a control flowchart of the cutting control method of the present invention. Detailed Implementation

[0021] The following combination Figures 1-2 The specific content of the present invention will be described in detail through specific embodiments. Figure 1 As shown, the adaptive cutting control method based on fuzzy algorithm in this embodiment is based on the following system architecture: mainly including a sensing input layer, a core control layer, an execution output layer, and a human-machine interaction and remote monitoring layer. A Siemens S7-1500 series PLC is used as the core controller. Field devices interact with the PLC in real time via the PROFINET protocol, with a communication cycle set to 1ms to ensure the determinism and real-time transmission of control commands and sensor data.

[0022] The sensing input layer equipment mainly includes an encoder, vibration sensor, pressure sensor, rangefinder, and microwave moisture meter. The encoder, mounted on the output shaft of the receiving arm rotation mechanism, is an absolute encoder with 16-bit resolution, used to detect the angle φ between the receiving arm and the track's forward direction in real time, with a detection accuracy of ±0.1°. The vibration sensor is preferably a piezoelectric accelerometer, mounted at the bucket wheel drive bearing seat, with a sampling frequency of 1kHz, used to collect vibration amplitude data when the bucket wheel cuts material. The pressure sensor is mounted at the torque detection end of the bucket wheel drive motor's output shaft, used to indirectly measure the actual cutting force of the bucket wheel. The microwave moisture meter is preferably a non-contact microwave resonant sensor, mounted 1.5m from the front end of the receiving arm at the bucket wheel, with a detection range of 0~100% and an accuracy of ±0.5%, used to detect the moisture content of the material to be excavated in real time. The laser rangefinder is mounted at the front end of the bucket wheel boom, used to detect the excavation depth and the distance to the material pile.

[0023] The main output layer equipment includes a bucket wheel motor, a bucket wheel frequency converter, a slewing motor, and a slewing frequency converter. Among these, the bucket wheel frequency converter and the slewing frequency converter are preferably Siemens G120 series frequency converters, supporting PROFINET communication, and their power ratings are matched to the rated power of the bucket wheel motor and the slewing motor, respectively. The bucket wheel motor and the slewing motor are preferably dedicated three-phase asynchronous motors with a rated frequency of 50Hz.

[0024] The human-machine interface and remote monitoring layer includes a touchscreen and a cloud platform. The touchscreen is installed in the excavator's operator's cab for local parameter setting and status monitoring. The cloud platform connects to the PLC via an industrial gateway, enabling remote data upload and remote control.

[0025] like Figure 2 As shown, the bucket wheel motor and slewing motor of the bucket wheel excavator are adaptively controlled through the full-link adaptive control logic of "given input - multi-source perception - fuzzy decision-precise execution - real-time feedback". The specific principle is as follows.

[0026] The comparator in the deviation calculation system performs difference calculations between the preset work setpoints (including basic control parameters such as the rated operating frequency of the bucket wheel at 50Hz and the reference frequency of the receiving arm rotation) and the real-time working condition data fed back by the sensors to obtain the deviation between the current actual working condition and the expected working condition, which serves as the core input basis for subsequent fuzzy control.

[0027] The fuzzification entry module receives multi-source sensor data (such as cutting force, bucket wheel reducer vibration, and material moisture) and deviation calculation results after filtering and normalization. It maps precise physical quantity values ​​to preset fuzzy language variables: cutting force is divided into three fuzzy sets: soft, medium, and hard; vibration data is divided into three fuzzy sets: light, medium, and heavy; and material moisture is divided into three fuzzy sets: dry, medium, and wet. The module also determines the fuzzy set affiliation of each data point through a membership function, thus completing the conversion from precise numerical values ​​to fuzzy semantics.

[0028] The PLC controller (fuzzy controller) is the core computing unit of the entire control system. It receives external input control parameters (such as fuzzy rule base update parameters, frequency adjustment upper and lower limits ±10%), and performs rule matching and activation degree calculation on the input fuzzy set based on the fuzzy rule base established by expert experience and field test data. Through matrix synthesis operation of three variables, cutting force, vibration and humidity, the output fuzzy set is finally obtained.

[0029] The clarification output module uses the discrete centroid method to transform the fuzzy set output by the PLC into a specific, executable, and precise control quantity, namely the percentage change in frequency of the bucket wheel inverter and the slewing inverter (adjustable within -10% to +10% of the rated value), thus completing the conversion from fuzzy semantics to digital control instructions.

[0030] The actuator receives the cleared frequency control command and drives the bucket wheel motor and the rotary motor respectively through the bucket wheel frequency converter and the rotary frequency converter, so as to adjust the bucket wheel cutting speed and the receiving arm rotation speed in real time, thereby realizing adaptive cutting operation for the current working conditions.

[0031] During the operation of the closed-loop feedback loop actuator, the actual working conditions of the cutting operation are collected in real time by sensing devices such as pressure sensors, vibration sensors, and microwave moisture meters. The "sensor feedback data" is then transmitted back to the front-end comparator and compared in real time with the given value, forming a complete closed-loop control loop to ensure the real-time performance, accuracy, and stability of the control process.

[0032] Combining the above adaptive control system, the adaptive cutting control method for a bucket wheel excavator based on fuzzy algorithm specifically includes the following steps: Step S1, setting up a data acquisition component on the bucket wheel excavator for collecting cutting force, vibration speed, and material moisture data, the data acquisition component includes a pressure sensor, vibration sensor, microwave moisture meter, rotary encoder, pitch encoder, and rangefinder.

[0033] The system includes: a pressure sensor to provide feedback on the cutting force experienced by the bucket wheel during operation; a vibration sensor to detect the vibration speed of the bucket wheel motor reducer bearings, which measures the hardness of the excavated material; a microwave moisture meter, mounted on the receiving arm belt, to detect the moisture content of the excavated material; a rangefinder, preferably a laser or radar ultrasonic rangefinder; a rotary encoder, mounted on the output shaft of the receiving arm's rotary mechanism, to acquire the receiving arm's rotation angle and speed; and a pitch encoder, mounted on the shaft of the receiving arm's pitch mechanism, to acquire the receiving arm's pitch angle.

[0034] Step S2, data preprocessing: The collected cutting force data, vibration velocity data, and material humidity data are first filtered to remove signal interference and make the data smoother and more accurate; then normalization is performed to unify them to a standard range to facilitate subsequent fuzzy inference processing. Before the bucket wheel excavator officially begins digging operations, theoretical and empirical control parameters are input into the PLC (Programmable Logic Controller) via a touchscreen. For example, the bucket wheel operating frequency is 50Hz, and the maximum rotation frequency of the receiving arm is 50Hz. When running, it automatically operates according to the formula 1 / cosφ (φ is the angle between the receiving arm and the track forward direction). When inputting a given value for fuzzy control, three discrete quantities are selected as input variables: cutting force e1, vibration data e2, and material moisture e3. Their domains of discourse are determined to be [NB, NS, N0, PS, PB] (NB: Negative Big, NS: Negative Small, N0: Zero, PS: Positive Small, PB: Positive Big). The frequency change uc of the bucket wheel inverter and the rotation inverter is used as the output variable, and its domain of discourse is determined to be [-10, -5, 0, 5, 10], in %, meaning that the frequency can be adjusted within ±10% of the rated value.

[0035] The preferred PLC is the Siemens S7-1500 series, which is the most powerful type of controller among Siemens PLCs. It reads and writes real-time data from the microwave moisture meter, encoder, and frequency converter through the PROFINET protocol (Process Field Network, an open industrial Ethernet standard) to achieve adaptive cutting control of the bucket excavator.

[0036] Step S3, Fuzzification Processing: Step S31, Determine the input and output fuzzy linguistic variables based on the actual needs of the bucket excavator's cutting operation; Step S32: Map the preprocessed data from step S2 onto the corresponding fuzzy linguistic variables to form fuzzy sets; Step S33: The cutting force data is divided into three fuzzy sets: soft, medium, and hard; the vibration sensor data is divided into three fuzzy sets: light, medium, and heavy; and the material moisture content is divided into three fuzzy sets: dry, medium, and wet. Step S34: Determine the membership degree of each fuzzy linguistic variable and determine which fuzzy set the data belongs to.

[0037] Based on the fuzzy rule base, the following query table is obtained after calculation by multiple fuzzy rules (the initial division of membership degree in Tables 1, 2 and 3 is based on the summary of expert experience and feedback from a large number of on-site human operation history records, and will be updated regularly as the amount of running data increases).

[0038] Table 1 Membership of Cutting Force

[0039] Table 2 Vibration velocity membership

[0040] Table 3 Membership of Material Humidity

[0041] Step S4, Establish a fuzzy rule base: Establish a fuzzy rule base based on expert experience and a large amount of field test data, containing multiple fuzzy rules: IF Low material moisture AND Hard cutting force AND Heavy motor reducer vibration THEN Reduce cutting speed AND Decrease rotation speed; IF High material moisture AND Soft cutting force AND Mild motor reducer vibration THEN Increase cutting speed AND Increase rotation speed; The aforementioned fuzzy rules comprehensively consider the impact of various factors such as material humidity, cutting force, and vibration of the cutting device on the cutting operation, thereby providing reasonable suggestions for adjusting cutting parameters according to different working conditions.

[0042] Step S5: Perform fuzzy inference operations based on the input fuzzy set and the established fuzzy rule base: match the input fuzzy set with each rule in the fuzzy rule base, and determine the activation degree of each rule based on the matching degree. Integrate the effects of all activated rules to obtain the output fuzzy set.

[0043] The above three variable matrices—cutting force, vibration velocity, and material moisture—are combined into a new set through fuzzy reasoning relationships: FOR #i := 1 TO 5 DO FOR #j := 1 TO 5 DO #temp_matrix[#i, #j] := 0; FOR #k := 1 TO 5 DO #temp_matrix[#i, #j]:= #temp_matrix[#i, #j]+ #matrix_e1[#i, #k] * #matrix_e2[#k, #j]; END_FOR; END_FOR; END_FOR; FOR #i := 1 TO 5 DO FOR #j := 1 TO 5 DO #uc_matrix_result[#i, #j] := 0; FOR #k := 1 TO 5 DO #uc_matrix_result[#i, #j] := #uc_matrix_result[#i, #j]+ #temp_matrix[#i, #k] * #matrix_e3[#k, #j]: END_FOR; END_FOR; END_FOR; The first loop synthesizes the fuzzy input matrices of the cutting force e1 and the vibration data e2 to obtain the intermediate temporary matrix #temp_matrix.

[0044] The second loop: The intermediate matrix is ​​synthesized again with the fuzzy input matrix of material humidity e3 to finally obtain the membership matrix #uc_matrix_result of the output fuzzy set.

[0045] Extract the membership degrees e1-e5 corresponding to the 5 output discrete points from #uc_matrix_result, and substitute them into this formula to calculate the accurate uc value.

[0046] Step S6: Defuzzify the obtained output fuzzy set using the centroid method: using the discrete centroid method formula... (uc is the final output precise control quantity, i.e., the percentage change in frequency of the bucket wheel inverter or slewing inverter; j is the index of the discrete point in the output universe of discourse, with a value of 1-5; ucj is the precise value of the j-th discrete point in the output universe of discourse, uc1=-10, uc2=-5, uc3=0, uc4=5, uc5=10; ej is the membership value (between 0 and 1) corresponding to the j-th discrete point, which is the result of the fuzzy inference operation in step S5, representing the degree to which the discrete value is activated), defuzzification yields the clear given value, and the obtained output fuzzy set is defuzzified using the centroid method: transformed into specific parameter values ​​P1 such as executable bucket wheel inverter (cutting speed) or slewing inverter (receiving arm rotation speed).

[0047] For example, suppose that after a certain fuzzy inference, the membership degrees of the five points in the output domain are as follows.

[0048] Table 4 Defuzzified Membership Degrees

[0049] Substitute the membership values ​​mentioned above into the centroid method formula for discrete quantities.

[0050] uc=[(-10×0.1)+(-5×0.3)+(0×0.6)+(5×0.2)+(10×0.0)] / (0.1+0.3+0.6+0.2+0.0)=-1.5 / 1.2=-1.25%, meaning the operating frequency of the bucket wheel or rotary motor will be reduced by 1.25% from the basic given value.

[0051] Step S7, Parameter Adjustment and Execution: Adjust the operating frequency of the bucket wheel motor or slewing motor in real time according to the parameter value P1 to achieve adaptive cutting control of the bucket wheel excavator.

Claims

1. An adaptive cutting control method for a bucket wheel excavator based on a fuzzy algorithm, characterized in that, Includes the following steps: Step S1: Install a data acquisition component on the bucket wheel excavator to collect data on cutting force, vibration speed, and material moisture content. The data acquisition component includes a pressure sensor, a vibration sensor, and a microwave moisture meter. Step S2, data preprocessing: The collected cutting force data, vibration velocity data, and material moisture data are first filtered to remove signal interference and make the data smoother and more accurate; then normalization is performed to unify them to a standard range to facilitate subsequent fuzzy inference processing. Step S3, fuzzification processing: Convert the preprocessed cutting force, vibration velocity, and material humidity data into fuzzy linguistic variables, perform three-level fuzzy classification, and determine the fuzzy set affiliation of each data by membership function; Step S4, Establish a fuzzy rule base: Establish a fuzzy rule base based on expert experience and a large amount of field test data; Step S5: Perform fuzzy inference operations based on the input fuzzy set and the established fuzzy rule base. Step S51: Match the input fuzzy set with each rule in the fuzzy rule base, and determine the activation degree of each rule based on the degree of matching; Step S52: Integrate the effects of all activation rules to obtain the output fuzzy set; Step S6: Defuzzify the obtained output fuzzy set using the centroid method: convert it into executable bucket wheel frequency converter or rotary frequency converter parameter value P1; Step S7, Parameter Adjustment and Execution: Adjust the operating frequency of the bucket wheel motor or slewing motor in real time according to the parameter value P1 to achieve adaptive cutting control of the bucket wheel excavator.

2. The adaptive cutting control method for a bucket wheel excavator based on fuzzy algorithm according to claim 1, characterized in that: The data acquisition component also includes a rotary encoder mounted on the output shaft of the receiving arm rotation mechanism for acquiring the rotation angle and speed of the receiving arm, and a pitch encoder mounted on the shaft of the receiving arm pitch mechanism for acquiring the pitch angle of the receiving arm.

3. The adaptive cutting control method for a bucket wheel excavator based on fuzzy algorithm according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Determine the input and output fuzzy linguistic variables based on the actual needs of the bucket wheel excavator's cutting operation; Step S32: Map the preprocessed data from step S2 onto the corresponding fuzzy linguistic variables to form fuzzy sets; Step S33: The cutting force data is divided into three fuzzy sets: soft, medium, and hard; the vibration velocity data is divided into three fuzzy sets: light, medium, and heavy; and the material moisture data is divided into three fuzzy sets: dry, medium, and wet. Step S34: Determine the membership degree of each fuzzy linguistic variable and determine which fuzzy set the data belongs to.

4. The adaptive cutting control method for a bucket wheel excavator based on fuzzy algorithm according to claim 1, characterized in that: The fuzzy rule base in step S4 contains multiple fuzzy rules: If the material has low moisture content, the cutting force is hard, and the motor and reducer vibrate severely, then reduce the cutting speed and decrease the rotation speed. If the material has high moisture content, the cutting force is soft, and the motor and reducer vibration is slight, then increase the cutting speed and increase the rotation speed.

Images