Intelligent Analysis Method and System for Port Bulk Cargo Moisture Content Based on Distributed Monitoring

Abstract

This invention provides a method and system for intelligent analysis of moisture content in port bulk cargo based on distributed monitoring. The method includes: converting collected temperature, humidity, and dielectric constant data of the ore into digital signals; dynamically calibrating the dielectric constant of the digital signals; constructing a target loss function based on the calibrated dielectric constant; and dynamically compensating and correcting the moisture content measurements using a dynamic calibration formula to obtain a moisture content compensation prediction value; generating and storing a moisture content change trend graph based on the moisture content compensation prediction value; and controlling the spraying operation of the ore based on the comparison between the moisture content change trend graph and a preset threshold. The dynamic compensation formula uses a meta-network to generate weights, enabling the weights to adapt to environmental changes in real time and enhancing anti-interference capabilities. Simultaneously, the target loss function includes feature decoupling loss, which further corrects errors and improves the prediction accuracy of moisture content.

Description

Technical Field

[0001] This invention relates to the field of ore moisture content monitoring technology, and in particular to a method and system for intelligent analysis of moisture content of bulk cargo in ports based on distributed monitoring. Background Technology

[0002] In dust suppression of ore stockpiles at bulk cargo ports, moisture content is the most critical parameter affecting dust suppression effectiveness. The moisture content of bulk cargoes such as ore directly impacts key aspects such as loading and unloading efficiency, storage safety, and dust emissions. Excessive moisture content can lead to ore agglomeration, affecting the normal operation of loading and unloading equipment; conversely, insufficient moisture content increases dust generation, adversely affecting the port environment and the health of surrounding residents. Therefore, accurate monitoring of the moisture content of ore stockpiles is crucial for optimizing port operations and environmental protection.

[0003] Currently, in the field of moisture content monitoring, both domestic and international methods for monitoring the moisture content of bulk cargo in ports mainly rely on traditional sensors and basic measurement technologies. Domestically, traditional measurement methods are generally represented by the MD series pin-type moisture analyzer. This method involves inserting a pin into an ore stack to collect resistance signals and calculating the moisture content using a fixed correlation between resistance and moisture content, thus only achieving basic resistance measurement. Some devices require manual conversion of the collected analog signals into data and rely on periodic manual calibration, lacking automatic data processing and dynamic adjustment capabilities, resulting in low accuracy in moisture content prediction. While foreign devices integrate pin-type and inductive technologies and support density and temperature compensation, and DELMHORST has developed portable pin-type devices with integrated Bluetooth data transmission, these devices offer slightly improved intelligence compared to domestic devices. However, their core measurement logic remains based on fixed parameter correlation and uses fixed compensation coefficients, making it unable to simultaneously handle complex interferences such as temperature and humidity fluctuations and sensor drift.

[0004] In summary, existing technologies for analyzing the moisture content of bulk cargo in ports suffer from poor environmental adaptability and low accuracy in moisture content prediction. Therefore, it is essential to design an intelligent analysis method and system for the moisture content of bulk cargo in ports based on distributed monitoring to improve environmental adaptability and the accuracy of moisture content prediction. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for intelligent analysis of moisture content of bulk cargo in ports based on distributed monitoring. By dynamically correcting and compensating for errors in the collected temperature, humidity and dielectric constant data, the method can improve environmental adaptability and the accuracy of moisture content prediction.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] The intelligent analysis method for moisture content of bulk cargo in ports based on distributed monitoring includes the following steps:

[0008] Temperature and humidity data and dielectric constant data of the ore are collected by temperature and humidity sensors and microwave sensors, and the collected data are converted into digital signals.

[0009] The dielectric constant of the digital signal is dynamically calibrated.

[0010] A dielectric constant-moisture content relationship model is constructed based on the calibrated dielectric constant, and dynamic compensation and error correction are performed on the measured moisture content values ​​to obtain the compensated moisture content prediction values, specifically including:

[0011] Using the calibrated dielectric constant and the temperature and humidity data as inputs, and the compensated moisture content as output, a dielectric constant-moisture content relationship model is constructed by combining the ideas of meta-learning and dynamic feature decoupling.

[0012] The input dielectric constant and the temperature and humidity data are feature-encoded to obtain private feature codes and shared feature codes;

[0013] Construct a target loss function based on the private feature encoding and the shared feature encoding;

[0014] The main sensor error and global compensation amount are calculated based on the private feature encoding and the shared feature encoding.

[0015] According to the main sensor error and the global compensation amount The moisture content is dynamically compensated, and the specific calculation formula is as follows:

[0016]

[0017] in, This is the predicted moisture content after compensation. It is the raw moisture content data measured by the sensor, weighted and Generated by the meta-network G, the expression is:

[0018] ;

[0019] in, It is a dielectric constant shared feature encoding. It is a temperature-specific feature encoding;

[0020] The moisture content after compensation is corrected for error based on the target loss function to obtain the moisture content compensation prediction value;

[0021] Generate and store a moisture content change trend chart based on the predicted moisture content compensation value;

[0022] The spraying operation is controlled based on the comparison between the moisture content change trend chart and the preset threshold.

[0023] Optionally, dynamic dielectric constant calibration of the digital signal includes:

[0024] Temperature compensation is applied to the temperature and humidity data to obtain the dielectric constant calibration coefficient; the formula for calculating the dielectric constant calibration coefficient is as follows: ;in, It is the baseline correction coefficient It is the temperature compensation coefficient. It is the humidity compensation coefficient. This is a reference temperature. This is the current temperature. This is a reference humidity level. This is the current humidity;

[0025] The dielectric constant data is output-calibrated according to the dielectric constant calibration coefficient to obtain the calibrated dielectric constant; the formula for calculating the calibrated dielectric constant is: ;in, It is the calibrated dielectric constant. It is the original dielectric constant;

[0026] The calibrated dielectric constant is converted into a data format using the Convert algorithm.

[0027] Optionally, the step of collecting temperature and humidity data and dielectric constant data of the ore using temperature and humidity sensors and microwave sensors includes: deploying micro probes integrating the temperature and humidity sensors in a distributed array at different vertical depth points in the ore stack, wherein the vertical depth points at least cover the surface, middle layer and deep layer of the ore stack; and deploying the microwave sensors in a one-to-one correspondence with each of the micro probes, so that the temperature and humidity data and dielectric constant data at the same collection time and the same spatial point form a spatiotemporally matched collection dataset.

[0028] Optionally, the step of converting the two types of acquired data into digital signals includes: performing anti-interference preprocessing on the two types of acquired data; using an analog-to-digital converter to perform analog-to-digital conversion on the preprocessed data, and outputting the digital signal.

[0029] Optionally, the analog-to-digital converter is model ADS1256.

[0030] Optionally, controlling the spraying operation of the ore based on the comparison result between the moisture content change trend graph and the preset threshold includes:

[0031] Two sets of moisture content thresholds are preset, namely a first threshold for triggering spraying and a second threshold for stopping spraying;

[0032] When the average real-time moisture content in the moisture content change trend chart is lower than the first threshold within a continuous preset time, the spraying equipment is started and watering operation is performed according to the first spraying intensity.

[0033] When the real-time average moisture content rises to between the first threshold and the second threshold, the spraying operation should be stopped immediately.

[0034] When the average real-time moisture content is higher than the second threshold, the spray equipment is turned off and the ventilation equipment is turned on.

[0035] The intelligent analysis system for port bulk cargo moisture content based on distributed monitoring, applied to the aforementioned intelligent analysis method for port bulk cargo moisture content based on distributed monitoring, includes:

[0036] The moisture content monitoring module is used to collect temperature and humidity data and dielectric constant data of the ore, and convert the two types of data into digital signals;

[0037] The signal calibration module is used to dynamically calibrate the dielectric constant of digital signals.

[0038] The data compensation module is used to construct a dielectric constant-moisture content relationship model based on the calibrated dielectric constant, and to perform dynamic compensation and error correction on the measured moisture content values ​​to obtain the compensated moisture content prediction values.

[0039] The storage module is used to generate and store a moisture content change trend chart based on the moisture content compensation prediction value;

[0040] The intelligent spraying module is used to control the spraying operation of ore based on the comparison between the moisture content change trend chart and the preset threshold.

[0041] Optionally, the moisture content monitoring module includes: a micro probe and a high-precision sensor unit; the micro probe is made of an alloy material, the surface of the micro probe is treated with diamond-like carbon, and the micro probe has a built-in temperature and humidity sensor, which is used to collect temperature and humidity data; the high-precision sensor unit includes: a microwave sensor and an analog-to-digital converter, the microwave sensor is used to collect dielectric constant data, and the analog-to-digital converter is used to convert the temperature and humidity data and dielectric constant data into digital signals.

[0042] According to specific embodiments provided by the present invention, the following technical effects are disclosed: The present invention provides an intelligent analysis method for the moisture content of bulk cargo in ports based on distributed monitoring. This method includes: collecting temperature and humidity data and dielectric constant data of ore through temperature and humidity sensors and microwave sensors, and converting the collected data into digital signals; dynamically calibrating the dielectric constant of the digital signals; constructing a dielectric constant-moisture content relationship model based on the calibrated dielectric constant, and dynamically compensating and correcting the moisture content measurement values ​​to obtain a moisture content compensation prediction value; generating and storing a moisture content change trend graph based on the moisture content compensation prediction value; and controlling the spraying operation of the ore based on the comparison between the moisture content change trend graph and a preset threshold. The dynamic compensation formula generates weights using a meta-network, enabling the weights to adapt to environmental changes in real time and enhancing anti-interference capabilities. Simultaneously, the objective loss function includes feature decoupling loss, which can further correct errors and improve the prediction accuracy of moisture content, solving the problems of poor environmental adaptability and low moisture content prediction accuracy in existing technologies for analyzing the moisture content of bulk cargo in ports. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of the method for monitoring the moisture content of bulk ore according to an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of the bulk ore moisture content monitoring system according to an embodiment of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] like Figure 1 As shown in the figure, this embodiment of the invention provides an intelligent analysis method for the moisture content of bulk cargo in ports based on distributed monitoring, including the following steps:

[0049] Step 100: Collect temperature and humidity data and dielectric constant data of the ore using temperature and humidity sensors and microwave sensors, and convert the two types of data into digital signals;

[0050] Step 200: Perform dynamic dielectric constant calibration on the digital signal;

[0051] Step 300: Construct a dielectric constant-moisture content relationship model based on the calibrated dielectric constant, and perform dynamic compensation and error correction on the measured moisture content to obtain the compensated moisture content prediction value;

[0052] Step 400: Generate and save a moisture content change trend chart based on the moisture content compensation prediction value;

[0053] Step 500: Control the spraying operation of the ore based on the comparison results between the moisture content change trend chart and the preset threshold.

[0054] Specifically, the micro probes integrating the temperature and humidity sensors are deployed in a distributed array at different vertical depth points in the ore stack, with the vertical depth points covering at least the surface, middle, and deep layers of the ore stack; the microwave sensors are deployed one-to-one with each of the micro probes, so that the temperature and humidity data and dielectric constant data at the same acquisition time and the same spatial point form a spatiotemporally matched acquisition dataset, avoiding data deviation caused by spatiotemporal misalignment.

[0055] In this embodiment, step 100 is implemented as follows: A SHT31 temperature and humidity sensor is used to collect real-time temperature and humidity data of the ore stack, and a HUMIREAD HR200 microwave sensor is used to collect real-time dielectric constant data of the ore stack. This data is then converted into digital signals using an ADS1256 analog-to-digital converter, thus providing the basic data for subsequent dynamic compensation.

[0056] Specifically, in this embodiment, step 200 includes: firstly, temperature compensation is performed on the temperature and humidity data to obtain the dielectric constant calibration coefficient, calculated using the following formula:

[0057] ;

[0058] in, It is the baseline correction coefficient It is the temperature compensation coefficient. It is the humidity compensation coefficient. This is a reference temperature. This is the current temperature. This is a reference humidity level. This is the current humidity. Then, the dielectric constant data is output calibrated according to the dielectric constant calibration coefficient to obtain the calibrated dielectric constant. The calculation formula is:

[0059] ;

[0060] in, It is the calibrated dielectric constant. This is the original dielectric constant. Finally, after the dielectric constant calibration is completed, the data format is converted using the Convert algorithm.

[0061] Specifically, in this embodiment, step 300 includes: processing temperature sensor data... Humidity sensor data Dielectric constant data As input, the compensated moisture content As output, a dielectric constant-moisture content relationship model is constructed by combining meta-learning and dynamic feature decoupling. This model integrates calibrated dielectric constant, temperature data, and humidity data into the input mode. Then, its features are decomposed into modality-specific private features. and shared features , The expression for encoding the total feature of the m-th modality is:

[0062] ;

[0063] ;

[0064] in, It is a private feature encoder. It is a shared feature encoder. It is a multimodal input vector. These are the private feature encoder weights. These are the weights of the shared feature encoder. The optimization objective loss function expression for the shared feature encoder is:

[0065] ;

[0066] in, It is the shared feature encoding of the m-th feature. This is the shared feature encoding of the nth feature. Next, the main sensor error is calculated. and global compensation amount The calculation formulas are as follows:

[0067] ;

[0068] ;

[0069] In this context, MLP stands for Multilayer Perceptron, and softmax is the activation function. and These are the private feature codes for temperature and dielectric constant, respectively, where d is the number of private feature codes. Encode humidity-sharing features. Finally, based on... and The expression for dynamic compensation of moisture content is:

[0070] ;

[0071] in, This is the predicted moisture content after compensation. This is the raw moisture content data measured by the sensor. The weights α and β are generated by the meta-network G, and their expressions are:

[0072] ;

[0073] Then, error correction is performed on the compensated moisture content based on the target loss function to obtain the compensated moisture content prediction value, expressed as:

[0074] ;

[0075] in, This is the actual measured moisture content.

[0076] Specifically, in this embodiment, step 400 stores the predicted moisture content compensation value in a local database and displays it in real time via a 7-inch TFT-LCD touchscreen and a web platform. Simultaneously, the data is visualized to generate a moisture content change trend chart, providing decision support for port managers.

[0077] Specifically, in this embodiment, step 500 automatically controls the working state of the spray dust suppression system based on the moisture content compensation prediction value and the preset threshold. When the moisture content is lower than the set threshold, the system automatically starts the spray equipment to perform water spraying operations until the moisture content returns to a reasonable range. This achieves intelligent linkage between moisture content monitoring and dust suppression, thereby improving the port's environmental protection level and operational efficiency, and solving the technical problem that traditional monitoring methods cannot achieve real-time linkage control.

[0078] For example, two sets of moisture content thresholds are preset, namely a first threshold for triggering spraying and a second threshold for stopping spraying; when the average real-time moisture content in the moisture content change trend chart is lower than the first threshold within a continuous preset time, the spraying equipment is started and watering is performed at the first spraying intensity; when the average real-time moisture content rises to between the first threshold and the second threshold, the spraying operation is stopped immediately; when the average real-time moisture content is higher than the second threshold, the spraying equipment is turned off and the ventilation equipment is started to reduce the surface moisture content of the ore stack through ventilation assistance, so as to prevent the ore from caking due to excessive moisture content.

[0079] like Figure 2 As shown, this embodiment of the invention also provides an intelligent analysis system for the moisture content of port bulk cargo based on distributed monitoring, applied to the aforementioned intelligent analysis method for the moisture content of port bulk cargo based on distributed monitoring, including:

[0080] The moisture content monitoring module is used to collect temperature and humidity data and dielectric constant data of the ore, and convert the two types of data into digital signals;

[0081] The signal calibration module is used to dynamically calibrate the dielectric constant of digital signals.

[0082] The data compensation module is used to construct a dielectric constant-moisture content relationship model based on the calibrated dielectric constant, and to perform dynamic compensation and error correction on the measured moisture content values ​​to obtain the compensated moisture content prediction values.

[0083] The storage module is used to generate and store a moisture content change trend chart based on the moisture content compensation prediction value;

[0084] The intelligent spraying module is used to control the spraying operation of ore based on the comparison between the moisture content change trend chart and the preset threshold.

[0085] Specifically, the moisture content monitoring module includes a miniature probe and a high-precision sensor unit. The miniature probe is made of a high-strength, low-friction alloy material, and its surface is treated with diamond-like carbon (DLC) to enhance wear resistance and corrosion resistance. The probe also integrates a high-precision temperature and humidity sensor for real-time monitoring of ambient temperature and humidity, and is equipped with a miniature stepper motor to enable adjustable insertion depth. The high-precision sensor unit includes a microwave sensor for measuring moisture content and an analog-to-digital converter for data acquisition and signal conversion.

[0086] Furthermore, this embodiment also includes an STM32U5 wireless communication module, which employs LoRa technology for remote wireless data transmission and uses an STM32U5 industrial-grade MCU for data processing and communication control. The signal calibration module uses a high-performance STM32F767 microcontroller, and the data compensation module uses a TMS320F28335 digital signal processor. The overall system power module includes an AC165V~265V power adapter and a 4800mAh lithium battery, ensuring stable power supply in various environments. A touchscreen display and a web platform facilitate user operation and data management. All modules are connected and interact via a high-speed data bus and wireless communication links, ensuring efficient system operation and real-time data transmission.

[0087] The beneficial effects of this invention are as follows:

[0088] 1) Using a miniature moisture content monitoring probe, combined with a temperature and humidity sensor and a microwave sensor, the moisture content data of the ore stack was collected in real time. The environmental factors were corrected by a dynamic compensation algorithm, which achieved high-precision and highly adaptable moisture content monitoring, reduced the interference of environmental factors on the measurement results, and significantly improved the accuracy and efficiency of moisture content monitoring of ore stacks in bulk cargo ports.

[0089] 2) The miniature moisture content monitoring probe is made of high-strength, low-friction alloy material and has undergone DLC surface treatment to enhance its wear resistance and corrosion resistance, enabling it to operate stably for a long time in harsh port environments and adapt to monitoring needs under different seasons and climates.

[0090] 3) The system also supports seamless integration with subsystems such as the dust suppression spraying system and the yard management platform to form a closed-loop intelligent control system. This avoids the problems caused by excessive or insufficient water spraying in traditional methods, optimizes the port's operation process, reduces equipment downtime and maintenance costs, improves the port's throughput efficiency, and enhances the port's level of automation management.

[0091] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0092] Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. Furthermore, those skilled in the art will recognize that, based on the ideas of this invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A port bulk moisture content intelligent analysis method based on distributed monitoring, characterized in that, Comprising the following steps: Collecting the temperature and humidity data and dielectric constant data of the ore through the temperature and humidity sensor and the microwave sensor, and converting the two kinds of data collected into digital signals; Calibrating the dielectric constant of the digital signal dynamically; Based on the calibrated dielectric constant, a dielectric constant-moisture content relationship model is constructed, and the moisture content measurement value is dynamically compensated and error corrected to obtain a moisture content compensation prediction value, specifically including: Taking the calibrated dielectric constant and the temperature and humidity data as input and the compensated moisture content as output, combining meta-learning and dynamic feature decoupling, a dielectric constant-moisture content relationship model is constructed; The input dielectric constant and the temperature and humidity data are feature encoded to obtain private feature encoding and shared feature encoding; The expression is: ； ； wherein, is a private feature encoding, is a shared feature encoding, is a total feature encoding for the m-th modality, is a private feature encoder, is a shared feature encoder, is a multi-modal input vector, is a private feature encoder weight, is a shared feature encoder weight; According to the private feature encoding and the shared feature encoding, a target loss function is constructed; The expression is: ； wherein, is a shared feature encoding of the mth feature, is a shared feature encoding of the nth feature; calculating a master sensor error from the private feature encoding and the shared feature encoding and a global compensation amount ; the calculation formulas are respectively: ； ； wherein MLP is a multi-layer perceptron, softmax is an activation function, and are private feature encodings of temperature and permittivity, respectively, d is the number of private feature encodings, is a humidity shared feature encoding; According to the main sensor error and the global compensation quantity The water content is dynamically compensated, and the specific calculation formula is as follows: wherein, is the compensated water cut prediction value, is the raw water cut data measured by the sensor, the weight and is generated by the meta-network G, and the expression is: ； wherein, is a dielectric constant sharing feature code, is a temperature private feature code; According to the target loss function, the compensated moisture content is error corrected to obtain the moisture content compensation prediction value; According to the moisture content compensation prediction value, a moisture content trend chart is generated and stored; According to the comparison result of the moisture content trend chart and the preset threshold, the ore is controlled for spraying operation.

2. The port bulk moisture content intelligent analysis method based on distributed monitoring according to claim 1, characterized in that, Calibrating the dielectric constant of the digital signal dynamically, including: The temperature and humidity data are temperature-compensated to obtain a dielectric constant calibration coefficient; a calculation formula of the dielectric constant calibration coefficient is: ; wherein, is a reference correction coefficient, is a temperature compensation coefficient, is a humidity compensation coefficient, is a reference temperature, is a current temperature, is a reference humidity, is a current humidity; According to the dielectric constant calibration coefficient, the dielectric constant data is output calibrated to obtain a calibrated dielectric constant; a calculation formula of the calibrated dielectric constant is: ; wherein, is the calibrated dielectric constant, is the original dielectric constant; Converting the calibrated dielectric constant through the Convert algorithm.

3. The intelligent analysis method for port bulk moisture content based on distributed monitoring according to claim 1, characterized in that, The temperature and humidity data and dielectric constant data of the ore are collected through the temperature and humidity sensor and the microwave sensor, including: The miniature probe integrating the temperature and humidity sensor is deployed in a distributed array at different vertical depth points of the ore stack, which covers at least the surface, middle and deep layers of the ore stack; The microwave sensor is deployed one-to-one with each miniature probe to form a spatio-temporal matched data set of temperature and humidity data and dielectric constant data at the same collection time and the same spatial point.

4. The port bulk moisture content intelligent analysis method based on distributed monitoring according to claim 1, characterized in that, The two kinds of data collected are converted into digital signals, including: Anti-interference preprocessing is performed on the collected two kinds of data; Analog-to-digital conversion is performed on the preprocessed data using an analog-to-digital converter, and the digital signal is output.

5. The port bulk moisture content intelligent analysis method based on distributed monitoring according to claim 4, characterized in that, The model of the analog-to-digital converter is ADS1256.

6. The intelligent analysis method for port bulk cargo moisture content based on distributed monitoring according to claim 1, characterized in that, According to the comparison result of the moisture content trend chart and the preset threshold, the ore is controlled for spraying operation, including: Two groups of moisture content threshold values are preset, which are a first threshold value for triggering spraying and a second threshold value for stopping spraying; When the real-time moisture content average in the moisture content trend chart for a continuous preset time is lower than the first threshold value, start the spraying device and perform watering operation at a first spraying intensity; When the real-time moisture content average rises between the first threshold value and the second threshold value, stop the spraying operation immediately; When the real-time moisture content average is higher than the second threshold value, turn off the spraying device and start the ventilation device.

7. The intelligent analysis system for port bulk cargo moisture content based on distributed monitoring, applied to the intelligent analysis method for port bulk cargo moisture content based on distributed monitoring according to any one of claims 1-6, characterized in that, Comprising: A moisture content monitoring module for collecting temperature and humidity data and dielectric constant data of the ore, and converting the two kinds of data collected into digital signals; A signal calibration module for calibrating the dielectric constant of the digital signal dynamically; The data compensation module is configured to construct a dielectric constant-moisture content relationship model based on the calibrated dielectric constant, and to dynamically compensate and correct errors of the moisture content measurement value to obtain a compensated and predicted moisture content value. The storage module is configured to generate a moisture content change trend graph based on the compensated and predicted moisture content value and to store the graph. The intelligent spraying module is configured to control the spraying operation of the ore based on a comparison result of the moisture content change trend graph and a preset threshold.

8. The port bulk moisture content intelligent analysis system based on distributed monitoring according to claim 7, characterized in that, The moisture content monitoring module comprises a micro probe and a high-precision sensor unit. The micro probe is made of an alloy material, and the surface of the micro probe is treated by diamond-like carbon. The micro probe is internally provided with a temperature and humidity sensor, and is configured to collect the temperature and humidity data. The high-precision sensor unit comprises a microwave sensor and an analog-to-digital converter. The microwave sensor is configured to collect the dielectric constant data, and the analog-to-digital converter is configured to convert the temperature and humidity data and the dielectric constant data into the digital signal.

Images