Humic acid automatic detection method and system based on cooperation of sensor and mechanical arm

Abstract

The invention discloses a humic acid automatic detection method and system based on cooperation of a sensor and a mechanical arm, and the method comprises the following steps: obtaining the data of the sensor, determining the sensor based on the concentration range of sample humic acid, fusing the data signals of different sensors through a Kalman filtering algorithm according to the data collected by different sensors, and carrying out the automatic detection of the humic acid. Calibrating an error of the sensor based on an adaptive algorithm; a sensor acquisition and mechanical arm cooperative control model is constructed, a mechanical arm places a sample to a designated position, the angle of the sample is adjusted, and the sensor and the mechanical arm coordinate to work through a feedback mechanism. Multi-modal fusion of the spectrum sensor and the electrochemical sensor is adopted, data of different sensors are effectively fused through a Kalman filtering algorithm, and the accuracy and stability of humic acid detection are remarkably improved. Therefore, the system can better adapt to different environment changes, and the overall detection efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automation detection and intelligent control technology, in particular to a humic acid automatic detection method and system based on sensor and mechanical arm cooperation. BACKGROUND

[0002] Humic acid is a natural organic polymer containing aromatic ring, carboxyl, phenolic hydroxyl and methoxyl groups, with a macromolecular network structure, high cation exchange capacity and strong physical adsorption capacity.

[0003] Humic acid widely exists in soil, wastewater, plants and other natural substances, and is widely used in agriculture, environmental monitoring and water quality treatment fields. Traditional humic acid detection methods rely on manual intervention or manual sampling, which has low efficiency and low precision. Therefore, developing an automatic detection method based on sensor and mechanical arm cooperation can improve the efficiency, precision and automation level of humic acid detection, reduce human error, and has significant technical advantages. Therefore, a humic acid automatic detection method and system based on sensor and mechanical arm cooperation are proposed. SUMMARY

[0004] The purpose of the present application is to provide a humic acid automatic detection method and system based on sensor and mechanical arm cooperation. The purpose is to realize the full-process automation of sample processing, detection and data analysis, improve the detection efficiency and precision, and reduce human intervention to solve one of the problems proposed in the background technology.

[0005] A humic acid automatic detection method based on sensor and mechanical arm cooperation, the main components and principles of this technology are: Sensor technology: sensors are used to detect the concentration of humic acid in the sample, usually using spectral sensors (such as ultraviolet-visible light spectral sensors) or electrochemical sensors to detect the characteristic signals of humic acid.

[0006] Spectral sensor: use the absorption characteristics of humic acid at specific wavelengths for detection. Humic acid has unique absorption peaks in the ultraviolet or visible light region, and the concentration of humic acid can be calculated by measuring these absorption values.

[0007] Electrochemical sensor: based on the reaction of humic acid molecules with the surface of the electrode, the concentration of humic acid is inferred by the change of current or voltage.

[0008] Mechanical arm technology: the mechanical arm is responsible for automatically processing the sample, including sample collection, transmission, placement, stirring and other tasks. In the process of humic acid detection, the mechanical arm can automatically send the sample to the sensor for detection.

[0009] Coordinated Control of Robotic Arm: The coordination between the robotic arm and the sensor is crucial. After real-time detection by the sensor, the robotic arm can automatically adjust the sample position or perform different detection operations (such as changing the sample height, angle, etc.), achieving more comprehensive detection.

[0010] Data Acquisition and Analysis System: The data collected by the sensor is sent to the data analysis system through the interface. This system can process, analyze, and display the data.

[0011] Machine learning or data fitting algorithms are usually used to analyze sensor data, estimate the concentration of humic acid, and generate reports or feedback to the control system.

[0012] The data analysis process can also combine other detection data (such as temperature, humidity, stirring speed, etc.) for multi-parameter optimization to improve detection accuracy.

[0013] Collaborative Workflow: Sample Preparation: The robotic arm automatically takes the sample to be tested from the sample library and performs necessary pretreatment (such as cleaning, weighing, dissolving, etc.).

[0014] Sample Placement: The robotic arm places the sample in front of the sensor or measurement device, ensuring accurate and stable sample positioning.

[0015] Data Acquisition and Detection: The sensor detects the sample (spectral analysis or electrochemical analysis), collects data, and transmits it to the data analysis system.

[0016] The data analysis system processes the data according to the predetermined algorithm, calculates the humic acid concentration, and feeds back the detection results.

[0017] Automatic Feedback and Adjustment: Based on the changes in sensor data, the robotic arm may need to adjust the sample position or angle and continue sampling multiple times to ensure the accuracy of the detection.

[0018] Output Results: Finally, the data analysis system generates a humic acid concentration report and automatically records the detection results.

[0019] Application Fields: Soil Detection: In agriculture, humic acid is a key component of soil health. Through this method, the humic acid content in the soil can be monitored in real time, optimizing soil management.

[0020] Water Quality Monitoring: Humic acid is a type of organic matter in water and can be used for water quality monitoring and quality control during purification processes.

[0021] Environmental protection: In wastewater treatment or environmental monitoring, detecting the concentration of humic acid helps to evaluate the concentration of pollutants and removal effect.

[0022] First aspect: To solve the above technical problems, one technical solution adopted by the present application is: a humic acid automatic detection method based on cooperation of sensors and mechanical arms, comprising the following steps: Obtain sensor data, determine the sensor based on the concentration range of sample humic acid, fuse the data signals of different sensors through Kalman filtering algorithm according to the data collected by different sensors, and calibrate the error of the sensor based on adaptive algorithm; Build a sensor acquisition and mechanical arm cooperative control model, the mechanical arm places the sample at a specified position, adjusts the angle of the sample, the sensor and the mechanical arm work coordinately through a feedback mechanism, and the mechanical arm fine tunes according to the feedback of the sensor through model predictive control and PID control algorithm, so as to determine that the moving track of the sample is consistent with the detection track of the sensor; Based on the sensor, the humic acid concentration data of the sample is collected, the preliminary data processing is carried out on the near-end device where the sensor is located, the data is analyzed and the estimated value of the humic acid concentration is generated; According to the estimated value, a detection report on the humic acid concentration of each sample is automatically generated, a real-time chart, trend analysis and historical data comparison report are generated according to the detection report, and real-time state monitoring and fault warning are carried out during the detection process if error or abnormality occurs; Through historical data training model, the characteristics of different sample types are automatically identified, the sensor acquisition and mechanical arm cooperative control model is optimized, and the detection path is adaptively adjusted according to the characteristics of different samples.

[0023] Further preferably, in the step of obtaining sensor data, determining the sensor based on the concentration range of sample humic acid, and fusing the data signals of different sensors through Kalman filtering algorithm according to the data collected by different sensors, specifically: The different sensors include spectrum sensor, electrochemical sensor and temperature and humidity sensor; The Kalman filtering algorithm optimizes by fusing the input information of different sensors to obtain the predicted value of humic acid concentration, wherein the formula of the Kalman filtering algorithm is as follows: ; ; ; ; Wherein: : estimated humic acid concentration; : state transition matrix; : estimated humic acid concentration at time k-1; : control input matrix; : control input at time k; : process noise; : covariance matrix representing the estimate of the error; : covariance matrix of state estimate at time k-1; : state transition matrix : transpose matrix of : Kalman gain representing the influence of new data on the estimate; : measurement matrix : transpose matrix of : process noise reflecting the uncertainty of the model; : measurement noise reflecting the measurement error of the sensor; : measurement matrix of the sensor; : actual measurement value of the sensor.

[0024] Further preferably, the adaptive algorithm comprises any one or more of Kalman filtering, least square method, neural network and fuzzy logic control.

[0025] Further preferably, the formula of the model predictive control and PID control algorithm is specifically as follows: ; wherein: : motion instruction of the robot arm; : deviation of the target position from the current position; : proportional, integral and differential coefficients; : integral of the error with respect to time; : rate of change of the error.

[0026] Further preferably, the detection report comprises the detection date, the humic acid concentration and the sample type, and the characteristics of the different samples comprise color, humidity and size.

[0027] Second aspect: To solve the above technical problems, another technical solution adopted by the present application is: an automatic humic acid detection method based on cooperation of a sensor and a robot arm, comprising the steps of: Based on the quantum bit sensor, the concentration range of the sample humic acid is detected, and the output of the quantum bit sensor is calibrated in real time by using an adaptive algorithm; By training a deep reinforcement learning model, the detection process of different samples is simulated, and the operation path of the mechanical arm is optimized. An AR interaction interface is constructed, and the spatial distribution of the humic acid concentration is observed in real time through the AR device, and the abnormal area is automatically marked. The data collected by the sensor is transmitted to the local edge computing device for preliminary data analysis and processing.

[0028] Further preferably, the deep reinforcement learning model includes a deep reinforcement learning algorithm, which optimizes the cooperation between the sensor and the mechanical arm through the deep reinforcement learning algorithm, and the control process formula of the deep reinforcement learning algorithm is: ; Among them: : state The value of the action performed next time; : The immediate reward after performing the action in the current state; : Discount factor, used to balance long-term and short-term rewards; : The action at the next time step; : Expectation; : In the next state When all existing next actions .

[0029] Third aspect: To solve the above technical problems, another technical solution adopted by the present application is: an automatic humic acid detection system based on the cooperation of sensors and mechanical arms, comprising: The acquisition module is configured to acquire sensor data, determine the sensor based on the concentration range of the sample humic acid, fuse the data signals of different sensors through the Kalman filtering algorithm according to the data collected by different sensors, and calibrate the error of the sensor based on the adaptive algorithm; The cooperative control module is configured to build a sensor acquisition and mechanical arm cooperative control model, the mechanical arm places the sample at a specified position, adjusts the angle of the sample, the sensor and the mechanical arm work in coordination through a feedback mechanism, and the mechanical arm fine-tunes according to the feedback of the sensor through model predictive control and PID control algorithm, to determine that the movement trajectory of the sample is consistent with the detection trajectory of the sensor; ​An evaluation module is configured to collect humic acid concentration data of the sample based on the sensor, perform preliminary data processing on the proximal device where the sensor is located, analyze the data, and generate an estimated value of the humic acid concentration; A report warning module is configured to automatically generate a detection report on the humic acid concentration of each sample according to the estimated value, generate real-time charts, trend analysis, and historical data comparison reports based on the detection report, and perform real-time state monitoring and fault warning if an error or anomaly occurs during the detection process. A data training module is configured to train the model through historical data, automatically identify the characteristics of different sample types, optimize the sensor collection and robotic arm cooperative control model, and adaptively adjust the detection path according to the characteristics of different samples.

[0030] Fourth aspect: To solve the above technical problems, another technical solution adopted by the present application is: an electronic device comprising a processor, a memory and a communication interface, the memory storing a computer program, and the processor executing the computer program to implement the steps of any of the above humic acid automatic detection methods based on the cooperation of the sensor and the robotic arm.

[0031] Fifth aspect: To solve the above technical problems, another technical solution adopted by the present application is: a computer readable storage medium, the computer readable storage medium storing a computer program, and the computer program being executed by a processor to implement the steps of any of the above humic acid automatic detection methods based on the cooperation of the sensor and the robotic arm.

[0032] The present application has the beneficial effects of: 1. The present application adopts multi-modal fusion of optical spectrum sensors and electrochemical sensors, effectively fuses data from different sensors through Kalman filtering algorithm, significantly improves the accuracy and stability of humic acid detection. This makes the system better adapt to different environmental changes and improves the overall detection efficiency; 2. The present application introduces a multi-level feedback control system, which enables the robotic arm and the sensor to work in real time, ensures accurate positioning of the sample and accurate measurement of the sensor in each detection, and avoids errors caused by misalignment of the sample and the sensor; 3. The present application adopts PID control and model predictive control to ensure the precision and stability of the robotic arm, especially in the processing of complex samples; 4. The present application introduces edge computing, disperses the data processing part to the sensor local or robotic arm control system, reduces the data transmission delay, and realizes real-time humic acid detection and feedback. This method can significantly improve the response speed of the system and reduce the lag in the data processing process, making the detection more efficient. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0034] Figure 1 A flowchart of a humic acid automatic detection method based on cooperation of a sensor and a mechanical arm according to an embodiment of the present application; Figure 2 A flowchart of an embodiment two of the present application; Figure 3 A module diagram of a humic acid automatic detection system based on cooperation of a sensor and a mechanical arm according to an embodiment three of the present application; Figure 4 A structural diagram of an electronic device according to the present application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0036] Figure 1 A flowchart of a humic acid automatic detection method based on cooperation of a sensor and a mechanical arm according to an embodiment of the present application. It should be noted that the method of the present application is not limited to the flow order shown. Figure 1

[0037] At present, this technology combining a sensor and a mechanical arm has not been widely applied in humic acid detection in the market. Most traditional humic acid detection relies on manual sampling and spectral analysis, which is low in efficiency and easy to be affected by human factors. Therefore, the automatic humic acid detection method based on cooperation of a sensor and a mechanical arm has great innovation and application prospect.

[0038] The present scheme provides an innovative, accurate and automatic humic acid detection method based on sensor multi-modal fusion, mechanical arm precise control, edge computing and deep learning and other frontier technologies. This technology has significant innovation and technical breakthrough, can solve the problems in the prior art, and improve the efficiency, accuracy and automation level of humic acid detection. Compared with the existing technology, it not only improves the detection accuracy and stability, but also has stronger adaptability and expansibility, and can be widely applied in multiple industries.​

[0039] Embodiment one As Figure 1 shown, an automatic humic acid detection method based on sensor and robot arm cooperation includes the following steps: S10, obtain sensor data, determine the sensor based on the concentration range of the sample humic acid, fuse the data signals of different sensors through Kalman filtering algorithm according to the data collected by different sensors, and calibrate the error of the sensor based on adaptive algorithm; Specifically: The different sensors include a spectrum sensor, an electrochemical sensor, and a temperature and humidity sensor. The spectrum sensor is used to detect the absorption characteristics of humic acid in the ultraviolet or visible light region, and is suitable for analyzing the concentration range of humic acid.

[0040] The electrochemical sensor is used to accurately detect humic acid in more complex samples, and is particularly suitable for high-sensitivity detection when the humic acid concentration in soil or water samples is low.

[0041] The temperature and humidity sensor monitors the environmental conditions and provides real-time temperature and humidity data for sensor data calibration to ensure the stability of the detection.

[0042] The Kalman filtering algorithm optimizes the input information of different sensors to obtain the predicted value of the humic acid concentration, wherein the formula of the Kalman filtering algorithm is as follows: ; ; ; ; Wherein: : estimated humic acid concentration; : state transition matrix; : estimated humic acid concentration at time k−1; : control input matrix; : control input at time k; : process noise; : covariance matrix, representing the estimate of the error; : covariance matrix of state estimate at time k−1; : transpose matrix of state transition matrix ; : Kalman gain, representing the influence of new data on the estimate; : transpose matrix of measurement matrix ; : process noise, reflecting the uncertainty of the model; : measurement noise, reflecting the measurement error of the sensor; : measurement matrix of the sensor; : actual measurement value of the sensor.

[0043] Specifically, the adaptive algorithm includes any one or more of Kalman filter, least squares method, neural network and fuzzy logic control.

[0044] An adaptive algorithm is used to calibrate the error of the sensor, and the output of the sensor is adjusted in real time according to the change of the environment (such as temperature and humidity change). Through real-time data monitoring, it is ensured that the sensor is always in the best working state; S20, a sensor acquisition and robot collaborative control model is constructed, the robot places the sample to the designated position, adjusts the sample angle, and the sensor and the robot work through the feedback mechanism, through the model predictive control and PID control algorithm, the robot adjusts according to the feedback of the sensor, and determines that the moving track of the sample is consistent with the detection track of the sensor; Specifically, the robot needs to have more than 6 degrees of freedom of movement to ensure that the sample can be accurately placed and its angle adjusted for detection at different positions and angles.

[0045] Equipped with high-precision sensor positioning system, such as laser range finder and visual recognition system, to realize automatic identification and adjustment of sample position.

[0046] A multi-level feedback control system is adopted: the sensor and the robot work through precise feedback mechanism to ensure that the sample is always within the best measurement range of the sensor during each detection; Model predictive control (MPC) and PID control are used to accurately control the movement of the robot, ensuring that the moving track of the sample is completely matched with the detection track of the sensor; Control algorithm formula (PID control): ; Where: : integral of error with respect to time; : rate of change of error; : control input, i.e. action command of the robot.

[0047] : current position error, i.e. deviation between target position and current position.

[0048] PID: Proportional, Integral, and Derivative coefficients used to adjust the response speed and stability of the system; The robotic arm automatically places the sample in the designated position, adjusts the sample angle, and ensures that the sensor can accurately measure.

[0049] After each operation step, the robotic arm fine-tunes based on sensor feedback to ensure accurate measurements each time.

[0050] S30, based on the sensor, the humic acid concentration data of the sample is collected, and preliminary data processing is performed on the near-end device where the sensor is located, the data is analyzed, and the estimated value of the humic acid concentration is generated; The sensor collects the humic acid concentration data of the sample in real time through a multi-channel data acquisition system, ensuring a reliable data source for each measurement.

[0051] High data acquisition frequency ensures sufficient data within each second for accurate analysis; Data processing uses edge computing to perform preliminary data processing on the near-end device where the sensor is located, quickly analyzes the data, and generates an estimated value of the humic acid concentration. Reduces latency and provides real-time feedback.

[0052] After data preprocessing on the edge device, the sensor data is transmitted to the central processing unit (such as a cloud platform) for deep learning analysis and storage, further optimizing the detection results; Based on real-time data, the detection results will be fed back to the robotic arm control system immediately. If the detection results deviate from the predetermined value, the robotic arm will automatically adjust the sample position or angle for secondary detection to ensure accuracy.

[0053] Use dynamic feedback mechanism for adaptive adjustment to avoid error accumulation between sample and sensor, provide continuous detection improvement.

[0054] S40, automatically generate a detection report on the humic acid concentration of each sample based on the estimated value, generate real-time charts, trend analysis, and historical data comparison reports based on the detection report, and in the detection process, if there is an error or anomaly, real-time state monitoring and fault warning; Specifically, the system automatically generates a detection report on the humic acid concentration of each sample, including detection date, humic acid concentration, sample type, and other detailed information.

[0055] Real-time charts, trend analysis, and historical data comparison reports can be generated as needed to facilitate operators to make timely repair decisions; During the detection process, if errors or abnormalities occur, the system will automatically provide correction suggestions to the operator, or even perform automated adjustment operations (such as sample re-measurement or sensor adjustment).

[0056] The system provides real-time status monitoring and fault warning, ensuring the efficiency and accuracy of the detection work.

[0057] S50, through historical data training model, automatic identification of different sample types of characteristics, optimization of sensor acquisition and mechanical arm cooperative control model, according to the characteristics of different samples, adaptive adjustment of detection path; Specifically, through deep learning model for self-optimization, with the increase of the number of detection samples, the deep learning algorithm will continuously adjust the detection algorithm, improve the detection accuracy.

[0058] Through historical data training model, the system can automatically identify the characteristics of different sample types, optimize the cooperative control of sensors and mechanical arms; According to the characteristics of different samples (such as color, humidity, size, etc.), the detection strategy is adaptively adjusted to further improve the detection efficiency and accuracy; Specifically, multi-modal fusion of spectral sensors and electrochemical sensors is adopted, and Kalman filtering algorithm is used to effectively fuse the data of different sensors, which significantly improves the accuracy and stability of humic acid detection. This makes the system better adapt to different environmental changes and improves the overall detection efficiency; By introducing a multi-level feedback control system, the mechanical arm and sensor can work in real time, ensuring accurate positioning of the sample and accurate measurement of the sensor during each detection, avoiding errors caused by misalignment of the sample and sensor.

[0059] PID control and model predictive control are adopted to ensure the accuracy and stability of the mechanical arm action, especially in the processing of complex samples.

[0060] Edge computing is introduced, which disperses the data processing part to the local sensor or mechanical arm control system, reduces the data transmission delay, and realizes real-time humic acid detection and feedback. This method can significantly improve the response speed of the system and reduce the lag in data processing, making the detection more efficient.

[0061] Edge computing enables data to be processed at the source, improving the reliability of the system, especially in large-scale application scenarios, which can avoid the overall system failure caused by network interruption; Deep learning and adaptive algorithms enable the system to automatically adjust detection methods based on the characteristics of different samples, improving the system's learning ability and adaptability. After processing a large number of samples, the system can continuously optimize detection strategies, automatically identify sample types and characteristics, and provide more accurate detection results. Integrating intelligent monitoring and fault warning system, it can feedback to the operator in time when the equipment appears abnormal and automatically correct. Through continuous learning, the system can optimize itself and continuously improve the accuracy and stability of humic acid detection, greatly reducing the need for manual intervention.

[0062] Automatic report generation and correction feedback mechanism further improves the readability and application value of data, making it easier for operators and decision-makers to make more scientific and timely repair decisions. According to different application requirements, different sensors and mechanical arm modules can be flexibly configured, reducing the overall system cost and improving the system's expandability. The low-cost sensor and efficient control system of the system optimize the design, making the technology widely applicable in agriculture, environmental protection, laboratory and other fields. Through multi-sensor fusion and edge computing technology, it can efficiently process multi-dimensional data from different sensors and provide real-time feedback on detection results, greatly improving the accuracy and response speed of detection.

[0063] The system eliminates the error of manual adjustment of sample and sensor position through precise cooperative control of mechanical arm and sensor, ensuring that each sample can be detected in the best state, avoiding error accumulation in traditional methods.

[0064] The introduction of deep learning and adaptive algorithms enables the system to optimize itself in actual operation, improving the accuracy and efficiency of detection, and avoiding the limitations of fixed algorithms in existing technologies.

[0065] Potential application fields: Agriculture: Humic acid is an important indicator of soil health. This automated detection method can quickly monitor soil humic acid content, helping farmers understand soil conditions in real time, optimize fertilization and irrigation management, and improve agricultural production efficiency.

[0066] Water quality monitoring: In wastewater treatment or water resource management, the concentration of humic acid is one of the important water quality indicators. This technology can help environmental protection departments monitor water quality changes in real time, ensuring the health and safety of water resources.

[0067] Environmental monitoring: This system can be widely used in environmental pollution monitoring to help detect humic acid content and assess pollution levels, providing scientific basis for environmental governance.

[0068] Industrial applications: In industrial wastewater treatment, the concentration of humic acid is directly related to the effect of wastewater treatment. This technology can realize real-time monitoring and analysis of humic acid in wastewater, ensuring that industrial wastewater discharge meets environmental protection standards.

[0069] Example two The existing technology generally has problems such as low sensor accuracy, slow system response, and complicated detection process. This scheme combines the most advanced technology, uses quantum sensing technology and deep reinforcement learning, and provides a higher precision and higher efficiency solution for automatic detection of humic acid.

[0070] As Figure 2 shown, to solve the above technical problems, another technical scheme adopted by the present application based on the first embodiment is: An automatic detection method for humic acid based on cooperation of sensors and mechanical arms, comprising the following steps: Step one, based on quantum bit sensor, detect the concentration range of sample humic acid, use adaptive algorithm to calibrate the output of quantum bit sensor in real time; Quantum bit sensor can provide higher sensitivity and accuracy than traditional optical spectrum and electrochemical sensor. Quantum bit sensor uses the superposition and entanglement properties of qubits to improve the noise suppression ability of detection signal, so that it can still provide accurate humic acid concentration measurement in complex environment.

[0071] Quantum interferometer can enhance the sensitivity of the sensor in weak signal, which makes the system still accurately obtain data when the concentration of sample humic acid is very low; Deep reinforcement learning constantly adjusts the operation of mechanical arm through simulation of environment and real-time feedback, so that the mechanical arm can optimize itself in real time when dealing with samples of different shapes and different surface characteristics, and obtain the best detection path.

[0072] DRL (deep reinforcement learning) control process formula: ; Where: : state The value of the action executed next.

[0073] : the immediate reward after executing the action in the current state.

[0074] : discount factor, used to balance long-term and short-term rewards.

[0075] : the action at the next time step;​ : Expectation; : In the next state , the next action .

[0076] Objective: Maximize action value (i.e., find the optimal robot arm action policy).

[0077] Real-time calibration of quantum bit sensor output using adaptive algorithms, automatic adjustment of system parameters to ensure high accuracy under different environmental conditions (such as temperature, humidity, pollutants, etc.).

[0078] Step two, train a deep reinforcement learning model to simulate the detection process of different samples, optimize the operation path of the robot arm; Through training a deep reinforcement learning model, simulate the detection process of different samples, optimize the operation strategy of the robot arm. For example, the system simulates the processing of samples with different morphologies, learns how to adjust the arm angle, position and detection path.

[0079] Based on the reinforcement learning strategy, the system automatically optimizes the action of the robot arm in the detection process to maximize the accurate measurement of humic acid concentration.

[0080] In actual operation, the deep reinforcement learning algorithm adjusts in real time according to sensor data and robot arm feedback, ensuring the coordinated work of the robot arm and the sensor, and continuously optimizing the operation path and action efficiency.

[0081] Step three, build an AR interaction interface, and automatically mark the abnormal area of humic acid concentration through AR equipment; Through augmented reality technology (AR), operators can real-time view the working condition of the robot arm and the readings of the sensor, combine virtual information with the real environment, and enhance the operator's control sense and visualization ability of the detection process.

[0082] AR real-time feedback system: through AR glasses or tablet devices, operators can see real-time images of humic acid concentration distribution, and when detection data deviates from the set standard, the AR system can automatically mark the abnormal area, guide the operator to make further adjustments or processing; improve detection efficiency and accuracy.

[0083] Step four, transmit the data collected by the sensor to the local edge computing device for preliminary data analysis and processing.

[0084] Directly transmit the data collected by the sensor to the local edge computing device (such as a small GPU server) for preliminary data analysis and processing, reduce transmission delay, and improve response speed.

[0085] Through GPU acceleration and data preprocessing algorithms, real-time analysis results of humic acid concentration are generated.

[0086] Multi-sensor data is fused through an edge computing platform, and combined with real-time feedback and historical data for optimization, further improving detection accuracy and stability.

[0087] It also includes the use of adaptive neural networks to adjust the parameters of the robotic arm and sensors, ensuring optimal performance in different environments when they work together. The neural network continuously learns and adjusts to ensure optimal detection results in any environment and conditions.

[0088] As more data accumulates, the system continuously optimizes the deep reinforcement learning algorithm and automatically adjusts the control strategy based on feedback to improve detection accuracy. Specifically, by combining quantum sensing technology, deep reinforcement learning, augmented reality technology, and edge computing, the precision, efficiency, and automation level of the humic acid automatic detection system are greatly improved. Compared with existing technologies, the innovation of this scheme lies in the introduction of quantum sensing technology to improve sensor sensitivity, the use of deep reinforcement learning to optimize robotic arm motion control, and the combination of augmented reality technology to achieve real-time operation feedback, improving the intelligence and operability of the overall system.

[0089] The implementation of the technical solution will greatly improve the adaptability of humic acid detection in complex environments and has broad application prospects, and can be applied in agriculture, environmental protection, industry and other fields, and is expected to promote the technological progress of related industries. Quantum sensors are several orders of magnitude more accurate than traditional optical and electrochemical sensors, and can significantly reduce measurement noise through quantum interference or quantum entanglement principles, making them particularly suitable for precise measurement of low-concentration humic acid samples. Traditional optical sensors often cannot achieve precise measurement when faced with low-concentration humic acid samples and are easily affected by environmental noise.

[0090] As part of the quantum sensor, the quantum interferometer can greatly enhance the enhancement effect of weak signals, ensuring stable and efficient humic acid detection even in complex environments such as soil and wastewater. By introducing deep reinforcement learning (DRL) algorithms to optimize the collaborative work of the robotic arm and sensors, it far exceeds traditional rule-based control systems such as PID controllers. Deep reinforcement learning learns how to automatically adjust the operation strategy of the robotic arm in different operating environments through continuous interaction with the environment, avoiding the limitations of human-set rules and greatly improving the flexibility and adaptability of the system.

[0091] The control formula of DRL (such as Q-learning) enables the robot arm to not only consider real-time data but also predict the optimal action path for the next step when performing the humic acid detection task. This makes the robot arm's actions more intelligent and automated, and especially enables real-time adaptive adjustment for complex environments (such as different forms of samples and constantly changing external conditions).

[0092] The integration of augmented reality (AR) technology into the humic acid detection process greatly improves the operator's operation experience and accuracy. Through AR devices (such as AR glasses, AR tablets, etc.), the operator can view the detection area, detection results, and sensor working status in real time, further improving the visualization of the operation. Real-time operation feedback enables the operator to make immediate adjustments based on detection data, ensuring the accuracy of each detection; By introducing edge computing, the data processing part can be decentralized to the sensor and robot arm control system, avoiding the delay and bandwidth consumption of transmitting large amounts of data to the central server. This enables the system to respond quickly, reducing the lag in the data transmission process, allowing the detection results to be quickly adjusted in real-time feedback.

[0093] Through edge computing and GPU acceleration, not only the response speed of the system is improved, but also the efficiency and stability of humic acid detection are improved through preprocessing and optimization algorithms; Using adaptive neural network technology, the system can continuously learn and optimize during the processing of large-scale samples. Through analysis of sensor data, robot arm feedback, and operating environment, the system can adjust the working parameters of the sensor and robot arm to achieve the best detection effect.

[0094] It has significant technical breakthroughs in precision, efficiency, and intelligence level. Combined with quantum sensing technology, deep reinforcement learning, edge computing, and AR technology, the humic acid detection not only surpasses existing technology in precision, but also makes innovations in flexibility and real-time performance, with significant market competitiveness.

[0095] Embodiment Three As Figure 3 shown to solve the above technical problems, on the basis of embodiment one, another technical solution adopted by the present application is: a humic acid automatic detection system based on cooperation of sensors and robot arms, comprising: An acquisition module is configured to acquire sensor data, determine sensors based on the concentration range of sample humic acid, fuse data signals of different sensors through Kalman filtering algorithm based on data collected by different sensors, and calibrate errors of the sensors based on adaptive algorithm; The cooperative control module is configured to build a sensor collection and robot arm cooperative control model. The robot arm places the sample at a designated position and adjusts the angle of the sample. The sensor and the robot arm work in coordination through a feedback mechanism. Through model predictive control and PID control algorithm, the robot arm fine-tunes according to the feedback of the sensor to determine that the moving track of the sample is consistent with the detection track of the sensor. The evaluation module is configured to collect humic acid concentration data of the sample based on the sensor, perform preliminary data processing on the proximal device where the sensor is located, analyze the data, and generate an estimated value of the humic acid concentration. The report and warning module is configured to automatically generate a detection report on the humic acid concentration of each sample according to the estimated value, generate real-time charts, trend analysis, and historical data comparison reports based on the detection report, and perform real-time state monitoring and fault warning if an error or anomaly occurs during the detection process. The data training module is configured to train the model through historical data, automatically identify the characteristics of different sample types, optimize the sensor collection and robot arm cooperative control model, and adaptively adjust the detection path according to the characteristics of different samples.

[0096] For other details of the implementation of the technical solutions of the modules in the above-mentioned embodiment system, please refer to the description in the above-mentioned embodiment of the humic acid automatic detection method based on the cooperation of the sensor and the robot arm. Here, no further description is given.

[0097] It should be noted that each embodiment in the present specification adopts a progressive description manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between embodiments can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0098] Embodiment Four As Figure 4 A structural schematic diagram of an electronic device is provided for the embodiments of the present disclosure. It shows a structural schematic diagram suitable for implementing the electronic device in the embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present disclosure.

[0099] As Figure 4 shown, an electronic device includes a processor, a memory, and a communication interface. The memory stores a computer program. When the processor executes the computer program, it implements the humic acid automatic detection method based on the cooperation of the sensor and the robot arm of the embodiments of the present disclosure. The electronic device can exchange data with other devices or systems through the communication interface to realize real-time updating and sharing of drug information.

[0100] The processor in the electronic device described above is the core of the electronic device, and is responsible for executing computer programs stored in the memory to realize various functions of the paperless conference terminal intelligent interaction method. The processor can adopt a high-performance multi-core CPU or a dedicated chip to meet the needs of complex calculations and real-time processing. The memory is used to store the operating system, application programs, data and computer programs, etc. In this embodiment, the memory stores a computer program that implements the paperless conference terminal intelligent interaction method. The memory can be RAM, ROM, Flash memory or other types of non-volatile memory. The communication interface is used to connect the electronic device with other devices or networks to realize the transmission and exchange of data. In this embodiment, the communication interface supports multiple communication protocols and interface standards, such as Wi-Fi, Bluetooth, USB, Ethernet, etc., to meet the communication needs in different scenarios.

[0101] Detailed descriptions related to this embodiment can be referred to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0102] Embodiment Five According to an embodiment of the present disclosure, a computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the functions of the above-mentioned sensor and mechanical arm cooperative humic acid automatic detection method.

[0103] The above-mentioned computer readable storage medium includes but is not limited to: optical storage medium (for example: CD-ROM and DVD), magneto-optical storage medium (for example: MO), magnetic storage medium (for example: magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (for example: memory card) and media with built-in ROM (for example: ROM box).

[0104] Detailed descriptions related to this embodiment can be referred to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0105] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.​

Claims

1. A method for automatic detection of humic acid based on cooperation of a sensor and a robot arm, characterized by, The method comprises the following steps: acquiring sensor data, determining the sensor based on the concentration range of sample humic acid, fusing the data signals of different sensors through Kalman filtering algorithm, and calibrating the error of the sensor based on an adaptive algorithm; building a sensor acquisition and robot arm cooperative control model, placing the sample at a specified position by the robot arm, adjusting the angle of the sample, coordinating the work between the sensor and the robot arm through a feedback mechanism, and fine-tuning the robot arm according to the feedback of the sensor through model predictive control and PID control algorithm to determine the moving track of the sample consistent with the detection track of the sensor; based on the sensor, collecting the humic acid concentration data of the sample, preliminarily processing the data on the near-end device where the sensor is located, analyzing the data, and generating an estimated value of the humic acid concentration; generating a detection report on the humic acid concentration of each sample automatically according to the estimated value, generating real-time charts, trend analysis and historical data comparison reports according to the detection report, and performing real-time state monitoring and fault warning during the detection process if an error or anomaly occurs; training the model through historical data, automatically identifying the characteristics of different sample types, optimizing the sensor acquisition and robot arm cooperative control model, and adaptively adjusting the detection path according to the characteristics of different samples.

2. The humic acid automatic detection method based on the cooperation of a sensor and a mechanical arm according to claim 1, characterized in that, In the step of acquiring sensor data, determining the sensor based on the concentration range of sample humic acid, fusing the data signals of different sensors through Kalman filtering algorithm, the specific steps are as follows: The different sensors include a spectrum sensor, an electrochemical sensor and a temperature and humidity sensor. The Kalman filtering algorithm optimizes the input information of different sensors to obtain a predicted value of the humic acid concentration, wherein the formula of the Kalman filtering algorithm is as follows: ； ； ； ； Wherein: : estimated humic acid concentration; : state transition matrix; : estimated humic acid concentration at time k - 1; : control input matrix; : control input at time k; : process noise; : Covariance matrix representing the estimate of the error; : Covariance matrix of the state estimate at time k - 1; : State transition matrix : Transposed matrix of : Kalman gain, representing the influence of new data on the estimate; : measurement matrix : transpose of the measurement matrix; : process noise, reflecting uncertainty of the model; : measurement noise, reflecting the measurement error of the sensor; : measurement matrix of the sensor; : Actual measurement of the sensor.

3. The method according to claim 1, wherein the method is characterized by, The adaptive algorithm includes any one or more of Kalman filtering, least squares method, neural network and fuzzy logic control.

4. The humic acid automatic detection method based on the cooperation of a sensor and a mechanical arm according to claim 1, characterized in that, The formula of the model predictive control and PID control algorithm is as follows: ； Wherein: : movement instructions for the robot arm; : deviation of target position from current position; : proportional, integral and derivative coefficients; : integral of error over time; : rate of change of error.

5. The humic acid automatic detection method based on the cooperation of a sensor and a mechanical arm according to claim 1, characterized in that, The detection report includes the detection date, the humic acid concentration and the sample type, and the characteristics of different samples include color, humidity and size.

6. The humic acid automatic detection method based on the cooperation of a sensor and a mechanical arm according to claim 1, characterized in that, The method further comprises the following steps: Based on the quantum bit sensor, detecting the concentration range of sample humic acid, and calibrating the output of the quantum bit sensor in real time using an adaptive algorithm; Through training a deep reinforcement learning model, simulating the detection process of different samples, and optimizing the operation path of the robot arm; Building an AR interaction interface to observe the spatial distribution of the humic acid concentration in real time through an AR device and automatically marking the abnormal areas; Transmitting the data collected by the sensor to a local edge computing device for preliminary data analysis and processing.

7. The method according to claim 6, wherein the method is characterized by, The deep reinforcement learning model includes a deep reinforcement learning algorithm, which optimizes the cooperative work of the sensor and the robot arm through the deep reinforcement learning algorithm, and the formula of the control process of the deep reinforcement learning algorithm is as follows: ； Wherein: : state : value of the action : value : immediate reward after performing action in current state; : discount factor, used to balance long-term and short-term rewards; : action of next time step; : desired; : In the next state , all existing next actions .

8. A humic acid automatic detection system based on cooperation of a sensor and a mechanical arm, applied to the humic acid automatic detection method based on cooperation of a sensor and a mechanical arm in any one of claims 1-7, characterized in that, Including: The acquisition module is configured to acquire sensor data, determine sensors based on the concentration range of sample humic acid, fuse data signals of different sensors through a Kalman filtering algorithm according to data collected by different sensors, and calibrate errors of the sensors based on an adaptive algorithm; The cooperative control module is configured to construct a sensor acquisition and manipulator cooperative control model, place the sample at a specified position by the manipulator, adjust the angle of the sample, coordinate work between the sensor and the manipulator through a feedback mechanism, and determine a moving track of the sample to be consistent with a detection track of the sensor by the manipulator according to feedback of the sensor through model predictive control and PID control algorithms; The evaluation module is configured to preliminarily process data on a near-end device where the sensor is located based on the sensor to collect humic acid concentration data of the sample, analyze the data, and generate an estimated value of the humic acid concentration; The report and early warning module is configured to automatically generate a detection report about the humic acid concentration of each sample according to the estimated value, generate a real-time chart, trend analysis, and historical data comparison report according to the detection report, and perform real-time state monitoring and fault early warning if an error or an abnormality occurs during detection. The data training module is configured to train a model through historical data, automatically identify characteristics of different sample types, optimize the sensor acquisition and manipulator cooperative control model, and adaptively adjust a detection path according to characteristics of different samples.

9. An electronic device, characterized by The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the humic acid automatic detection method based on cooperation of a sensor and a manipulator according to any one of claims 1 to 7.

10. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the humic acid automatic detection method based on cooperation of a sensor and a manipulator according to any one of claims 1 to 7.

Images