Cotton press remote monitoring system based on Internet of Things

Abstract

The invention discloses a cotton press remote monitoring system based on the Internet of Things, and relates to the technical field of mechanical monitoring, and the system comprises a pressure sensing module which comprises a plurality of pressure sensing units, and the pressure sensing units are configured to collect the real-time pressure data of a cotton press; and the data acquisition module is connected with the pressure sensing module and is used for periodically receiving the pressure data in the digital signal form from the plurality of pressure sensing units. According to the invention, through multi-source cross validation and environment coupling compensation, the problems of signal drift and data missing during calibration caused by dust and high humidity influence on pressure monitoring of a traditional system are solved, and data continuity of non-stop calibration is realized; self-adaptive signal processing and feature domain analysis are adopted, signal distortion caused by real pressure sudden change and sensor or transmission link abnormity is effectively distinguished, and the false alarm rate is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical monitoring, in particular to a cotton baling machine remote monitoring system based on Internet of Things. BACKGROUND

[0002] The cotton baling machine is a key equipment in the cotton processing industry chain, mainly used for compressing loose seed cotton or lint into high-density bales for storage and transportation. With the wide application of Internet of Things technology in the industrial field, traditional cotton baling machines gradually integrate sensors, communication modules and cloud platforms to form a remote monitoring system, which can collect real-time equipment operating parameters and transmit them to the central server through wireless networks to realize functions such as fault warning, energy consumption management and production scheduling. Such systems usually rely on multiple types of sensors to work together, among which the pressure sensing unit is directly related to the quality of baling and the safety of the equipment, and is one of the core monitoring indicators.

[0003] However, although the existing cotton baling machine monitoring system can realize remote transmission of basic data, the pressure monitoring module is easily affected by the environment in long-term continuous operation. The cotton processing environment is dusty and humid, and the instantaneous pressure fluctuates frequently during the baling process, which causes the pressure sensor interface to accumulate lint or be oxidized by moisture, causing signal drift or transmission delay. The existing system mostly uses periodic calibration or redundant sensor design, but data loss during calibration may mask abnormal pressure conditions, and redundant configuration increases hardware cost and system complexity. In addition, some systems try to suppress noise through data filtering algorithms, but it is difficult to distinguish between real pressure mutations and signal distortions, leading to false positives or false negatives on the monitoring platform, affecting the consistency of baling quality and the timeliness of equipment maintenance. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a cotton baling machine remote monitoring system based on Internet of Things, which solves the problem of signal drift caused by dust and high humidity affecting the pressure monitoring of traditional systems and data loss during calibration when compared with the use of traditional systems.

[0005] To achieve the above purpose, the following technical solutions are used: a cotton baling machine remote monitoring system based on Internet of Things, comprising: a pressure sensing module, comprising a plurality of pressure sensing units, the pressure sensing units being configured to collect real-time pressure data of the cotton baling machine; a data acquisition module connected to the pressure sensing module, configured to periodically receive pressure data in the form of digital signals from the plurality of pressure sensing units; The data processing and verification module is connected to the data acquisition module. It performs multi-source cross-verification on the pressure data collected by the multiple pressure sensing units according to preset verification rules to identify and filter out abnormal data points, thereby obtaining preliminary verified pressure data. Based on the preliminary verified pressure data, and combined with the historical operating parameters of the cotton baler and environmental monitoring data, adaptive signal processing is performed to distinguish between real pressure fluctuations and signal drift caused by sensor inherent noise and environmental interference; and to generate verified pressure status data. A communication module, which is connected to the data processing and verification module, is used to transmit the verified pressure status data via a wireless network; The cloud monitoring platform, connected to the communication module, is used to receive the verified pressure status data and generate and present the real-time pressure curve, historical trend chart, and comprehensive operation report of the cotton baler.

[0006] Furthermore, the plurality of pressure sensing units include: a first pressure sensing unit, which is disposed in the main hydraulic cylinder of the cotton baler to collect the main pressure data of the hydraulic system; and a second pressure sensing unit, which is disposed in the baling chamber of the cotton baler to collect the instantaneous extrusion pressure data during cotton bale formation.

[0007] Furthermore, the data processing and verification module compares the pressure data of the first pressure sensing unit and the pressure data of the second pressure sensing unit according to a preset pressure deviation threshold. If the difference between the pressure data is less than or equal to the deviation threshold, the pressure data is determined to be valid synchronous pressure data.

[0008] Furthermore, the data processing and verification module acquires ambient temperature and humidity data; wherein, the adaptive signal processing dynamically calibrates the effective synchronous pressure data based on the ambient temperature and humidity data to compensate for sensor performance drift caused by environmental factors.

[0009] Furthermore, the data processing and verification module analyzes the time-domain and frequency-domain characteristics of the effective synchronized pressure data, including the pressure change rate and signal noise frequency distribution; wherein, the data processing and verification module distinguishes between real pressure abrupt changes and signal distortion caused by sensor or transmission link anomalies based on the time-domain and frequency-domain characteristics.

[0010] Furthermore, the data processing and verification module uses a machine learning model to analyze the current pressure pattern of the cotton baler in real time based on the verified pressure status data; wherein, the machine learning model is pre-trained to identify abnormal pressure patterns that exceed the normal range.

[0011] Furthermore, the data processing and verification module determines the abnormal operating state type of the cotton baler based on the identified abnormal pressure pattern. The abnormal operating state type is hydraulic system overload, baling chamber blockage, insufficient oil pressure, and sensor failure.

[0012] Furthermore, the cloud monitoring platform receives the verified pressure status data and displays the pressure curve, historical trend graph, and abnormal status in real time; if an abnormal operating status is determined, the cloud monitoring platform automatically sends an alarm notification to the preset maintenance personnel terminal device.

[0013] Furthermore, the communication module employs narrowband Internet of Things (NB-IoT) to enable remote transmission of the verified pressure status data, ensuring data coverage and transmission reliability.

[0014] Furthermore, the system also includes a control command issuing module, which is connected to the cloud monitoring platform to receive remote adjustment commands generated by the cloud monitoring platform based on the verified pressure status data; wherein, the control command issuing module sends the remote adjustment commands to the control unit of the cotton baler to remotely adjust the operating parameters of the cotton baler.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention solves the problems of signal drift and data loss during calibration caused by dust and high humidity in traditional pressure monitoring systems through multi-source cross-validation and environmental coupling compensation, achieving data continuity for calibration without downtime; it effectively distinguishes between real pressure surges and signal distortion caused by sensor or transmission link anomalies by employing adaptive signal processing and feature domain analysis, reducing false alarm rates; it improves anomaly identification accuracy through machine learning models and shortens maintenance response time by combining a hierarchical alarm mechanism; it ensures data transmission reliability through NB-IoT communication and enhances environmental adaptability and operational flexibility with remote control functions, reducing hardware costs while ensuring packaging quality stability and equipment operation safety. Attached Figure Description

[0016] Figure 1 This is a system structure diagram of the present invention. Detailed Implementation

[0017] 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.

[0018] Please see Figure 1This invention provides a remote monitoring system for cotton baling machines based on the Internet of Things, comprising: A pressure sensing module, comprising multiple pressure sensing units configured to collect real-time pressure data from a cotton baler; A data acquisition module, which is connected to the pressure sensing module, is used to periodically receive pressure data in the form of digital signals from the plurality of pressure sensing units; The data processing and verification module is connected to the data acquisition module. It performs multi-source cross-verification on the pressure data collected by the multiple pressure sensing units according to preset verification rules to identify and filter out abnormal data points, thereby obtaining preliminary verified pressure data. Based on the preliminary verified pressure data, and combined with the historical operating parameters of the cotton baler and environmental monitoring data, adaptive signal processing is performed to distinguish between real pressure fluctuations and signal drift caused by sensor inherent noise and environmental interference; and to generate verified pressure status data. A communication module, which is connected to the data processing and verification module, is used to transmit the verified pressure status data via a wireless network; The cloud monitoring platform, connected to the communication module, is used to receive the verified pressure status data and generate and present the real-time pressure curve, historical trend chart, and comprehensive operation report of the cotton baler.

[0019] Specifically, the pressure sensing module can use a high-precision strain gauge pressure sensor as the pressure sensing unit. For example, five pressure sensing units can be set in different key parts of the cotton baling machine to monitor the pressure at different locations of the baling machine.

[0020] The data acquisition module uses a microprocessor with high-speed data reception capability and is connected to the pressure sensing module via a wire. It is set to receive pressure data in digital signal form from multiple pressure sensing units every 50 milliseconds to ensure timely acquisition of pressure information.

[0021] The data processing and verification module employs a high-performance embedded processor. The preset verification rules can be set such that when the data deviation collected by multiple pressure sensing units exceeds 10%, it is identified as an abnormal data point and filtered out, thus obtaining preliminary verification pressure data. Adaptive signal processing uses a Kalman filter algorithm, combined with historical operating parameters of the cotton baler and environmental monitoring data. The Kalman filter algorithm formula is as follows: Equations of state: , Measurement equation: , in, Let be the system state vector at time k, representing the pressure state. Let be the state transition matrix, which describes the change of the system state from time k-1 to time k; The control input at time k can be considered as an external factor regulating the pressure. To control the input matrix; The noise is the process noise, with a mean of 0 and a covariance of . The Gaussian distribution represents random disturbances within the system; The measured value at time k is the pressure data collected. The measurement matrix links the system state to the measured values; To measure the noise, it follows a mean of 0 and a covariance of . The Gaussian distribution represents the noise during the sensor measurement process. This algorithm can effectively distinguish between real pressure fluctuations and signal drift caused by inherent sensor noise and environmental interference, generating verified pressure state data.

[0022] The communication module uses narrowband Internet of Things (NB-IoT) to enable the remote transmission of the verified pressure status data.

[0023] The cloud monitoring platform is built using cloud servers. After receiving data, it generates real-time pressure curves through data visualization technology, with the horizontal axis representing time and the vertical axis representing pressure value. Historical trend charts display pressure changes by time dimension, such as day, week, and month. The comprehensive operation report includes the overall status of equipment operation, pressure data statistics, and other content.

[0024] In this embodiment, the plurality of pressure sensing units include: a first pressure sensing unit, which is disposed in the main hydraulic cylinder of the cotton baler to collect the main pressure data of the hydraulic system; and a second pressure sensing unit, which is disposed in the baling chamber of the cotton baler to collect the instantaneous extrusion pressure data during cotton bale formation.

[0025] Specifically, the first pressure sensing unit can be an S-type tension sensor, installed at the oil inlet of the main hydraulic cylinder of the cotton baler and fixed by a threaded connection. It can accurately collect the main pressure data of the hydraulic system, such as monitoring the pressure changes of the hydraulic oil in real time when the main hydraulic cylinder is working. The second pressure sensing unit uses a column-type pressure sensor, embedded in the inner wall of the baling chamber of the cotton baler, flush with the inner wall of the baling chamber to avoid affecting the formation of the cotton bale. It can accurately collect the instantaneous compression pressure data during the formation of the cotton bale, such as capturing the instantaneous pressure value when the cotton enters the baling chamber and is compressed.

[0026] In this embodiment, the data processing and verification module compares the pressure data of the first pressure sensing unit and the pressure data of the second pressure sensing unit according to a preset pressure deviation threshold. If the difference between the pressure data is less than or equal to the deviation threshold, the pressure data is determined to be valid synchronous pressure data.

[0027] Specifically, the pressure deviation threshold preset by the data processing and verification module can be set according to the model and working characteristics of the cotton baler, for example, set to 5% of the full-scale pressure value. During operation, the data processing and verification module acquires in real time the main hydraulic system pressure data collected by the first pressure sensing unit and the instantaneous extrusion pressure data of the cotton bale forming collected by the second pressure sensing unit, and calculates the difference between the two. When the difference is less than or equal to the set pressure deviation threshold, the two sets of pressure data are determined to be valid synchronous pressure data. In this way, the reliability of the pressure data can be improved, providing a more accurate basis for subsequent data processing.

[0028] In this embodiment, the data processing and verification module acquires ambient temperature and humidity data; wherein, the adaptive signal processing dynamically calibrates the effective synchronous pressure data based on the ambient temperature and humidity data to compensate for sensor performance drift caused by environmental factors.

[0029] Specifically, the data processing and verification module can acquire ambient temperature and humidity data by connecting to a temperature and humidity sensor. For example, an integrated temperature and humidity sensor can be installed near the cotton baler, connected to the data processing and verification module via a wired connection to transmit environmental data in real time. During adaptive signal processing for dynamic calibration, the ambient temperature and humidity data can be substituted into a preset calibration formula to correct the effective synchronous pressure data. For instance, when the ambient humidity is high, the sensor may experience some drift. Dynamic calibration can make the pressure data closer to the actual value, effectively compensating for sensor performance drift caused by environmental factors.

[0030] In this embodiment, the data processing and verification module analyzes the time-domain and frequency-domain characteristics of the effective synchronized pressure data, including the pressure change rate and signal noise frequency distribution; wherein, the data processing and verification module distinguishes between real pressure abrupt changes and signal distortion caused by sensor or transmission link anomalies based on the time-domain and frequency-domain characteristics.

[0031] Specifically, when analyzing the time-domain characteristics of valid synchronized pressure data, the data processing and verification module can calculate the pressure change per unit time, i.e., the pressure change rate. For example, if the pressure rises by 5 MPa in 0.1 seconds, the pressure change rate is 50 MPa / s. When analyzing the frequency-domain characteristics, Fourier transform is used to convert the pressure data from the time domain to the frequency domain to obtain the frequency distribution of signal noise. For example, it can identify that the main noise frequencies are concentrated around 10 Hz. When the pressure change rate is within a reasonable range and no abnormal frequency components appear in the frequency domain characteristics, it is determined to be a true pressure change. When the pressure change rate is abnormal and there are obvious abnormal frequencies in the frequency domain characteristics, it is determined to be signal distortion caused by sensor or transmission link abnormalities. In this way, the true pressure change can be more accurately distinguished from signal distortion, improving the accuracy of monitoring.

[0032] In this embodiment, the data processing and verification module uses a machine learning model to analyze the current pressure pattern of the cotton baler in real time based on the verified pressure status data; wherein, the machine learning model is pre-trained to identify abnormal pressure patterns that exceed the normal range.

[0033] Specifically, the data processing and verification module employs a support vector machine (SVM) model. First, a large amount of verified pressure status data from both normal and abnormal operation of the cotton baler is collected to train the model. During training, normal pressure patterns are used as positive samples, and abnormal pressure patterns as negative samples. By continuously adjusting the model parameters, the model can accurately identify different pressure patterns. In real-time analysis, the current verified pressure status data is input into the trained model, which then outputs whether the current pressure pattern exceeds the normal range. For example, when the model detects a significant fluctuation in pressure data within a short period that deviates from normal operating patterns, it is determined to be an abnormal pressure pattern. This method can quickly and accurately identify abnormal situations.

[0034] In this embodiment, the data processing and verification module determines the abnormal operating state type of the cotton baler based on the identified abnormal pressure pattern. The abnormal operating state type is hydraulic system overload, baling chamber blockage, insufficient oil pressure, and sensor failure.

[0035] Specifically, after identifying abnormal pressure patterns, the data processing and verification module determines the type of abnormal operating state based on the characteristics of different abnormal patterns. For example, when the abnormal pressure pattern is characterized by a pressure value that is consistently higher than the normal range and exceeds the set upper limit, it is determined to be an overload of the hydraulic system; when the pressure data shows periodic sudden increases accompanied by irregular fluctuations, and the packing progress slows down significantly, it is determined to be a blockage in the packing chamber; when the pressure value is consistently lower than the normal range and cannot reach the pressure required for normal packing, it is determined to be insufficient oil circuit pressure; when the pressure data shows irregular jumps and does not match other relevant data, it is determined to be a sensor malfunction. By accurately determining the type of abnormal operating state, maintenance personnel can take targeted measures to handle the situation.

[0036] In this embodiment, the cloud monitoring platform receives the verified pressure status data and displays the pressure curve, historical trend chart, and abnormal status in real time; if an abnormal operating status is determined, the cloud monitoring platform automatically sends an alarm notification to the preset maintenance personnel terminal device.

[0037] Specifically, the cloud monitoring platform displays data in a web page format. The left side of the page shows a real-time pressure curve with time on the horizontal axis and pressure value on the vertical axis, and the curve color changes with the pressure value. The middle area displays historical trend charts, allowing users to select different time intervals to view pressure change trends. The right area displays abnormal status information, including the time of occurrence and type of abnormality. When an abnormal operating state is determined, the cloud monitoring platform will automatically send alarm notifications based on preset maintenance personnel terminal device information. For example, it will send the abnormal information to the maintenance personnel's mobile phone via SMS and simultaneously push alarm messages to the maintenance personnel's dedicated APP, ensuring that maintenance personnel are promptly aware of the abnormal situation.

[0038] In this embodiment, the communication module adopts Narrowband Internet of Things (NB-IoT) to realize the remote transmission of the verified pressure status data, ensuring data coverage and transmission reliability.

[0039] Specifically, the communication module employs a communication chip supporting NB-IoT technology. This chip is integrated onto the circuit board of the data processing and verification module, receiving and transmitting signals via an antenna. In environments such as cotton processing plants, NB-IoT technology can leverage existing mobile communication networks to achieve wide coverage, ensuring data transmission even in areas with weak signals. For instance, in a large cotton processing plant area, the communication modules of each cotton baler can reliably transmit verified pressure status data to the cloud monitoring platform without data loss due to distance or obstacles, ensuring data coverage and transmission reliability.

[0040] In this embodiment, the system further includes a control command issuing module, which is connected to the cloud monitoring platform to receive remote adjustment commands generated by the cloud monitoring platform based on the verified pressure status data; wherein, the control command issuing module sends the remote adjustment commands to the control unit of the cotton baler to remotely adjust the operating parameters of the cotton baler.

[0041] Specifically, the control command issuing module uses a microcontroller and connects to the cloud monitoring platform via a wireless network. When the cloud monitoring platform determines that the cotton baler's operating parameters need adjustment based on verified pressure data, it generates a remote adjustment command, such as a command to reduce the hydraulic cylinder pressure when the pressure is too high. Upon receiving this command, the control command issuing module sends it to the cotton baler's control unit via a wired connection. The control unit then adjusts the corresponding operating parameters according to the command, such as adjusting the hydraulic pump's output flow rate, thereby reducing the hydraulic cylinder pressure. This remote adjustment method allows for timely adjustments to the cotton baler's operating status, ensuring normal equipment operation and baling quality.

[0042] In summary, this invention solves the problems of signal drift and data loss during calibration caused by dust and high humidity in traditional pressure monitoring systems through multi-source cross-validation and environmental coupling compensation, achieving data continuity for calibration without downtime. It employs adaptive signal processing and feature domain analysis to effectively distinguish between real pressure surges and signal distortion caused by sensor or transmission link anomalies, reducing false alarm rates. Machine learning models improve anomaly identification accuracy, and a tiered alarm mechanism shortens maintenance response time. NB-IoT communication ensures data transmission reliability, and remote control functionality enhances environmental adaptability and operational flexibility, reducing hardware costs while ensuring stable packaging quality and safe equipment operation.

[0043] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0044] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A remote monitoring system for cotton baling machines based on the Internet of Things, characterized in that, include: A pressure sensing module, comprising multiple pressure sensing units configured to collect real-time pressure data from a cotton baler; A data acquisition module, which is connected to the pressure sensing module, is used to periodically receive pressure data in the form of digital signals from the plurality of pressure sensing units; The data processing and verification module is connected to the data acquisition module. It performs multi-source cross-verification on the pressure data collected by the multiple pressure sensing units according to preset verification rules to identify and filter out abnormal data points, thereby obtaining preliminary verified pressure data. Based on the pressure data from the preliminary verification, and combined with the historical operating parameters of the cotton baler and environmental monitoring data, adaptive signal processing is performed to distinguish between real pressure fluctuations and signal drift caused by sensor inherent noise and environmental interference. And generate verified pressure status data; A communication module, which is connected to the data processing and verification module, is used to transmit the verified pressure status data via a wireless network; The cloud monitoring platform, connected to the communication module, is used to receive the verified pressure status data and generate and present the real-time pressure curve, historical trend chart, and comprehensive operation report of the cotton baler.

2. The remote monitoring system for cotton baling machines based on the Internet of Things according to claim 1, characterized in that, The plurality of pressure sensing units include: a first pressure sensing unit, which is disposed in the main hydraulic cylinder of the cotton baler to collect the main pressure data of the hydraulic system; and a second pressure sensing unit, which is disposed in the baling chamber of the cotton baler to collect the instantaneous extrusion pressure data during cotton bale formation.

3. The remote monitoring system for cotton baling machines based on the Internet of Things according to claim 2, characterized in that, The data processing and verification module compares the pressure data of the first pressure sensing unit and the pressure data of the second pressure sensing unit according to a preset pressure deviation threshold. If the difference between the pressure data is less than or equal to the deviation threshold, the pressure data is determined to be valid synchronous pressure data.

4. The remote monitoring system for cotton baling machines based on the Internet of Things according to claim 1, characterized in that, The data processing and verification module acquires ambient temperature and humidity data; wherein, the adaptive signal processing dynamically calibrates the effective synchronous pressure data based on the ambient temperature and humidity data to compensate for sensor performance drift caused by environmental factors.

5. The remote monitoring system for cotton baling machines based on the Internet of Things according to claim 4, characterized in that, The data processing and verification module analyzes the time-domain and frequency-domain characteristics of the effective synchronized pressure data, including the pressure change rate and signal noise frequency distribution; wherein, the data processing and verification module distinguishes between real pressure abrupt changes and signal distortion caused by sensor or transmission link anomalies based on the time-domain and frequency-domain characteristics.

6. The remote monitoring system for a cotton baling machine based on the Internet of Things according to claim 1, characterized in that, The data processing and verification module uses a machine learning model to analyze the current pressure pattern of the cotton baler in real time based on the verified pressure status data; wherein, the machine learning model is pre-trained to identify abnormal pressure patterns that exceed the normal range.

7. The remote monitoring system for a cotton baling machine based on the Internet of Things according to claim 6, characterized in that, The data processing and verification module determines the abnormal operating state type of the cotton baler based on the identified abnormal pressure pattern. The abnormal operating state types are hydraulic system overload, baling chamber blockage, insufficient oil pressure, and sensor failure.

8. The remote monitoring system for cotton baling machines based on the Internet of Things according to claim 1, characterized in that, The cloud monitoring platform receives the verified pressure status data and displays the pressure curve, historical trend chart, and abnormal status in real time. If an abnormal operating status is determined, the cloud monitoring platform automatically sends an alarm notification to the preset maintenance personnel terminal device.

9. The remote monitoring system for a cotton baling machine based on the Internet of Things according to claim 1, characterized in that, The communication module uses narrowband Internet of Things (NB-IoT) to remotely transmit the verified pressure status data, ensuring data coverage and transmission reliability.

10. The remote monitoring system for a cotton baling machine based on the Internet of Things according to claim 1, characterized in that, The system also includes a control command issuing module, which is connected to the cloud monitoring platform to receive remote adjustment commands generated by the cloud monitoring platform based on the verified pressure status data; wherein, the control command issuing module sends the remote adjustment commands to the control unit of the cotton baler to remotely adjust the operating parameters of the cotton baler.

Images