Tubular conveyor belt operation fault intelligent detection alarm system based on ultrasonic ranging

Abstract

The invention relates to the technical field of automatic control, and discloses a tubular conveyor belt operation fault intelligent detection alarm system based on ultrasonic ranging, and the system comprises a data collection assembly which employs a plurality of ultrasonic sensors to monitor the data of the height, width and length of a conveyor belt in real time, and captures the material state and the operation condition of the conveyor belt; environmental factors such as temperature, humidity and air pressure are monitored in real time, and ultrasonic ranging data are compensated automatically; the fault analysis component is used for analyzing real-time and historical data, identifying potential faults and carrying out fault detection through mode identification; intelligent alarm logic is set, and an alarm mode is automatically selected according to preferences and historical responses of the user; the state of the conveying belt is monitored in real time, and trend analysis is conducted; and the user interaction component provides a graphical interface and visually displays fault detection results and trend analysis. According to the invention, the safety and reliability of the equipment are improved, and the maintenance process is optimized.

Description

Technical Field

[0001] The invention relates to the technical field of automatic control, and in particular to an intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging. Background Art

[0002] Tubular conveyor belts are a special type of conveyor belt, which is designed to transport materials inside a tubular structure; this method of conveying can better prevent material spillage, protect materials from contamination in harsh environments, and achieve long-distance transportation. As an efficient and environmentally friendly way of transporting materials, the fault detection and alarm system of tubular conveyor belts is of great significance in ensuring safe, efficient and economical operation. Through real-time monitoring and intelligent alarm, it can effectively prevent and respond to equipment failures, improve production efficiency, reduce operating costs, and provide support for the sustainable development of enterprises. This high-tech management model has become an important part of modern industrial equipment. However, the existing technology has a low degree of intelligence in the detection of operating faults of tubular conveyor belts, and it is impossible to achieve automatic detection and alarm of operating faults, which reduces the service life of tubular conveyor belts to a certain extent.

[0003] Prior art 1, Chinese patent, application number: 202410686498.5 discloses a tubular conveyor belt, which can indirectly drive the rotating rod and the round rod to rotate when the locking block is inserted into the buckle groove through the reinforcing steel bars and sleeves and the serial ropes arranged in the sandwich layer, so that the reinforcing steel bars and sleeves originally stacked close can be pulled up, so that the originally soft area can be switched to a rigid support area, and the locking block and the buckle groove are buckled to ensure that the conveyor belt can maintain a rigidly supported tubular closed state when conveying materials, and can maintain a certain soft interval when loading and unloading the end to facilitate the opening operation. In addition, the adjustment unit is used to adjust the state of the locking block to be separated from the inside of the buckle groove according to the changes in the extrusion force of the roller pressing area and the upper and lower material areas on the conveyor belt, although the locking block can be more quickly and conveniently separated from the inside of the buckle groove. However, there is a lack of technical means for detecting operating failures, and it relies too much on the experience of maintenance personnel, resulting in a low degree of intelligence of the tubular conveyor belt, which affects work efficiency.

[0004] Prior art 2, Chinese patent, application number: 202311121450.1 discloses a method for detecting the rigidity value of a tubular conveyor belt, providing a tubular conveyor belt sample, cutting it into a certain length, and letting it stand; placing the tubular conveyor belt sample on a tubular conveyor belt rigidity testing machine and adjusting it to a balanced state; filling the inner cavity of the sample with a water bag and adjusting it to a balanced state; setting the moving distance and number of cycles of the roller at the top of the tubular conveyor belt rigidity testing machine, starting the test, recording the peak force of each of the 6 points evenly distributed on the upper roller movement and calculating the arithmetic mean Ni; calculating the rigidity value Pi of a single cycle and the rigidity value of the tubular conveyor belt. Although it fills the gap in the rigidity test of the tubular conveyor belt under the condition of transporting and loading materials, it can well simulate the rigidity of the tubular conveyor belt under the condition of transporting and loading materials, and can test the rigidity value of the tubular conveyor belt under different filling ratios, which is of great significance for guiding and predicting the use and pipe forming conditions of the tubular conveyor belt. However, it is not aimed at the detection during the use of the tubular conveyor belt, resulting in poor real-time detection and failure to truly reflect the operating status of the tubular conveyor belt.

[0005] Prior art three, Chinese patent, application number: 202410111753.3 discloses a visual recognition and positioning system for tearing faults of conveyor belts for mining, including: an industrial camera, which is fixedly installed above the return conveyor belt and used to collect crack images on the surface of the conveyor belt; a belt speed sensor, which is used to collect the movement speed of the conveyor belt in real time; an industrial computer, which is connected to the industrial camera and the belt speed sensor, and determines whether the conveyor belt has a tearing fault according to the surface crack image of the conveyor belt collected by the industrial camera, and collects the movement speed of the conveyor belt collected by the belt speed sensor; an industrial frequency converter, which is controlled by a logic controller, and controls the roller motor to align the position where the conveyor belt fails with the maintenance area. Although the fault detection efficiency is improved, it only involves mining belt conveyors and is not suitable for tubular conveyor belts, resulting in a limited scope of application and cannot effectively improve the fault detection efficiency of tubular conveyor belts.

[0006] At present, the existing technologies 1, 2 and 3 have low intelligence levels in operation status monitoring and fault warning, and the automation level needs to be further improved, resulting in poor safety and reliability of the equipment. Therefore, the present invention provides an intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging. Through the synergistic effect of data acquisition components, fault analysis components and user interaction components, the intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging can achieve efficient and accurate operation status monitoring and fault warning. Summary of the invention

[0007] The main purpose of the present invention is to provide an intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging, so as to solve the problem that the intelligence level of operation status monitoring and fault warning in the prior art is low and the automation level needs to be further improved.

[0008] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging, wherein the intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging comprises: a data acquisition component, which is used to use multiple ultrasonic sensors to monitor the height, width and length data of the tubular conveyor belt in real time, and capture the material status and the operation status of the tubular conveyor belt; real-time monitoring of temperature, humidity and air pressure environmental factors, and automatic compensation of ultrasonic ranging data; a fault analysis component, which is used to analyze real-time and historical data, identify potential faults, and perform fault detection through pattern recognition; set intelligent alarm logic, and automatically select the alarm mode according to user preferences and historical reactions; real-time monitoring of the tubular conveyor belt status, and trend analysis; a user interaction component, which is used to provide a graphical interface, and visualize the fault detection results and trend analysis; and a voice assistant function is set to realize the interaction between the user and the system.

[0009] As a further improvement of the present invention, the data acquisition component includes: a position analysis module, which is used to use simulation software, combined with the actual working environment and operating status of the tubular conveyor belt, to build a 3D simulation model for analyzing the influence of different layout positions on the accuracy of measurement data; an area division module, which is used to form a network with multiple layout positions, divide the network into multiple areas, and layout multiple ultrasonic sensors in a certain area. The ultrasonic sensors use time slicing technology to collect data in different time periods, and the data is fused according to the object measured by the ultrasonic sensor to obtain real-time data of the tubular conveyor belt operation; a data storage module is used to store the layout position and implementation data of the ultrasonic sensor.

[0010] As a further improvement of the present invention, the position analysis module includes: an equipment layout submodule, which is used to collect various physical parameters, including the size, shape, material properties, surrounding obstacles and environmental conditions of the conveyor belt; create a three-dimensional model of the conveyor belt, ultrasonic sensor and its environment; arrange the ultrasonic sensor at different positions in the three-dimensional model of the conveyor belt, and preset the working direction and measurement angle; a result acquisition submodule, which is used to set the start, stop, loading and unloading different operating states of the conveyor belt, and obtain the measurement results of the ultrasonic sensor under different states; record the measurement data of the ultrasonic sensor in the simulation and generate corresponding outputs; a strategy generation submodule, which is used to classify and mark each measurement data according to the layout position, sensor characteristics and environmental influencing parameters to form a structured data set; calculate the error between each sensor measurement data and the standard value generated by the actual model, and quantify the deviation using the root mean square error; use data visualization tools to present the measurement accuracy of different positions in the form of charts, and automatically generate sensor layout strategies.

[0011] As a further improvement of the present invention, the strategy generation submodule includes: a fitness calculation unit, which is used to represent each ultrasonic sensor layout position as a chromosome and randomly generate an initial population; calculate the fitness of each chromosome according to the minimized root mean square error; a crossover operation unit, which adopts roulette wheel selection to select chromosomes with high fitness from the current population as parents, and generates new individuals through single-point crossover operation; and an operation median unit, which is used to evaluate the fitness of the new population, replace individuals with low fitness, and repeatedly perform selection, crossover and mutation operations until a preset maximum number of iterations is reached.

[0012] As a further improvement of the present invention, the fault analysis component includes: a feature extraction module, which is used to extract key features from real-time and historical data, including data on the height, width, and length of the conveyor belt, as well as the impact of environmental factors on sensor data; automatically select the most discriminative data features according to changes in real-time data; use a deep learning algorithm to process sensor data, combined with time series data analysis, automatically generate a new fault pattern recognition model, compare the real-time monitoring data with the established fault mode, and perform fault identification; a strategy execution module, which is used to classify the fault type according to the identified fault, including minor faults, serious faults, and emergency faults, and define corresponding alarm strategies for each type; a word multimodal alarm mechanism, which automatically selects the alarm method according to user preferences and historical reactions; a data analysis module, which is used to continuously obtain ultrasonic sensor data, combine compensation for environmental factors, monitor key parameters of conveyor belt operation, establish a time series analysis model, analyze real-time data, predict potential trends and faults, and provide visual charts to understand possible problems.

[0013] As a further improvement of the present invention, the feature extraction module includes: a data collection submodule, which is used to collect the height, width, length and fault category label of the conveyor belt from the ultrasonic sensor; a mutual information calculation submodule, which is used to calculate the joint probability distribution of the feature and the fault category by performing frequency statistics on the data; and simultaneously calculate the marginal probability distribution of the feature and the fault category; using the mutual information formula, substituting the obtained probability value into the formula for calculation to obtain the mutual information between the feature and the fault type; a feature sorting submodule, which is used to sort the features according to the calculated mutual information value, and select the features with high mutual information as the most discriminative data features.

[0014] As a further improvement of the present invention, the feature extraction module also includes: a data capture submodule, which is used to automatically select the most discriminative features, process the ultrasonic sensor data through a bidirectional long short-term memory network, and capture time dependencies; a model training submodule, which is used to divide the ultrasonic sensor data obtained by the bidirectional long short-term memory network to obtain a training set and a validation set, divide the data set into multiple batches, and train the fault pattern recognition model; select the cross entropy loss to measure the difference between the output of the fault pattern recognition model and the true label; and a model evaluation submodule, which is used to use the validation set to evaluate the indicators of the fault pattern recognition model, and the indicators include accuracy, recall rate and F1-score.

[0015] As a further improvement of the present invention, the policy execution module includes: a preference identification submodule, which is used to establish a database for storing user preference settings and response records; set time intervals, automatically update and analyze user feedback and response behaviors, and identify changes in user preferences; a template setting submodule, which is used to build a rule engine to filter out alarm options from a variety of alarm methods based on fault levels and user preferences; design different content templates for each alarm type; a method selection submodule, which is used to generate a priority ranking for each alarm method based on user historical response data analysis; when a new fault occurs, the alarm method is dynamically selected in combination with current environmental factors and the user's real-time status.

[0016] As a further improvement of the present invention, the data analysis module includes: a data partitioning submodule, which is used to divide the data into multiple time windows and convert them into a time series format; select input features related to real-time data as input of the GRU model; the GRU model includes an input gate, a reset gate and an update gate; a parameter updating submodule, which is used to calculate the gradient and update the GRU model parameters using a back propagation algorithm; a real-time prediction submodule, which is used to divide the real-time data into sequences of fixed length and pass them to the trained GRU model; perform real-time prediction based on the current input state and historical state, and output the fault type, fault probability and key parameter prediction results.

[0017] As a further improvement of the present invention, the user interaction component includes: a content display creation module, which is used to create a dashboard containing real-time status and environmental factors of fault type; a trend analysis module, which is used to generate a line graph using trend analysis results to display the changing trend of key parameters and any fault-related indicators; an alarm prompt module, which is used to pop up an intelligent alarm prompt box on the screen when a fault is monitored in real time and the alarm rule is triggered, covering the fault type, occurrence time, possible affected areas and recommended treatment measures; access to fault history records to understand in detail the frequency, duration and solutions of the same fault, and present the time distribution of fault occurrence in the form of charts. Beneficial Effects

[0018] The data acquisition component of the present invention uses multiple ultrasonic sensors to monitor the height, width, length and state of the conveyor belt and the transported materials at different positions in real time; monitors environmental factors such as temperature, humidity and air pressure in real time to provide necessary environmental background information for ranging data; overcomes the influence of environmental factors on ultrasonic ranging through automatic compensation technology to ensure the accuracy of data. The significance achieved: providing high-precision, real-time data support to ensure the reliability of subsequent analysis and decision-making; enabling the system to maintain stable operation under various environmental conditions, and improving the effectiveness of fault warning through the timeliness of data. The fault analysis component analyzes real-time and historical data, uses pattern recognition technology to identify potential faults, and generates fault feature models; sets and adjusts intelligent alarm strategies according to different fault types, and accurately feedbacks fault information; monitors and analyzes the state change trend of the conveyor belt in real time to facilitate the discovery of hidden dangers. The significance achieved: providing timely fault information, reducing the probability of fault occurrence, and preventing losses; through fault analysis and trend prediction, helping maintenance personnel to formulate reasonable maintenance plans before faults occur, and improving equipment reliability. The user interaction component provides an intuitive user interface, visualizes fault detection results and trend analysis data, and helps users understand the system status; realizes interaction with users, and queries information and controls system status through voice commands. Significance achieved: Make it easier for operators to understand and use the system, reduce the learning curve and improve work efficiency; through convenient interactive methods, operators can quickly respond to system feedback and improve the timeliness of fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a functional module diagram of an embodiment of an intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging of the present invention; Figure 2 This is a functional module diagram of a data acquisition component of an embodiment of an intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging of the present invention; Figure 3This is a functional module diagram of a fault analysis component of an embodiment of an intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging of the present invention; Figure 4 This is a functional module diagram of a user interaction component of an embodiment of an intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging of the present invention; Figure 5 It is a structural schematic diagram of an embodiment of an electronic device of the present invention; Figure 6 It is a schematic structural diagram of an embodiment of the storage medium of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0022] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] like Figure 1As shown, this embodiment provides an embodiment of an intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging. In this embodiment, the intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging specifically includes: a data acquisition component, which is used to use multiple ultrasonic sensors to monitor the height, width and length data of the tubular conveyor belt in real time, and capture the material status and the operation status of the tubular conveyor belt; real-time monitoring of environmental factors such as temperature, humidity and air pressure, and automatic compensation of ultrasonic ranging data; a fault analysis component, which is used to analyze real-time and historical data, identify potential faults, and perform fault detection through pattern recognition; set intelligent alarm logic to automatically select the alarm mode according to user preferences and historical reactions; real-time monitoring of the tubular conveyor belt status, and trend analysis; a user interaction component, which is used to provide a graphical interface for visual display of fault detection results and trend analysis; and a voice assistant function is set to achieve interaction between users and the system.

[0024] Preferably, the data acquisition component of this embodiment uses multiple ultrasonic sensors to monitor the height, width, length and state of the transported materials of the tubular conveyor belt in real time at different locations; monitor environmental factors such as temperature, humidity and air pressure in real time to provide necessary environmental background information for ranging data; and overcome the influence of environmental factors on ultrasonic ranging through automatic compensation technology to ensure the accuracy of data. Significance achieved: Provide high-precision, real-time data support to ensure the reliability of subsequent analysis and decision-making; enable the system to maintain stable operation under various environmental conditions, and improve the effectiveness of fault warning through the timeliness of data. The fault analysis component analyzes real-time and historical data, uses pattern recognition technology to identify potential faults, and generates fault feature models; sets and adjusts intelligent alarm strategies according to different fault types, and accurately feedbacks fault information; monitors and analyzes the state change trend of the tubular conveyor belt in real time to facilitate the discovery of hidden dangers. Significance achieved: Provide timely fault information, reduce the probability of faults, and prevent losses; through fault analysis and trend prediction, help maintenance personnel formulate reasonable maintenance plans before faults occur and improve equipment reliability. The user interaction component provides an intuitive user interface, visualizes fault detection results and trend analysis data, and helps users understand the system status; it enables interaction with users, and allows users to query information and control system status through voice commands. The significance achieved: It makes it easier for operators to understand and use the system, reduces the learning curve, and improves work efficiency; through convenient interactive methods, operators can quickly respond to system feedback and improve the timeliness of fault handling.

[0025] In summary, through the synergy of the data acquisition component, the fault analysis component and the user interaction component, the intelligent detection and alarm system for tubular conveyor belt operation faults based on ultrasonic ranging can achieve efficient and accurate operation status monitoring and fault warning. It not only improves the safety and reliability of the equipment, but also optimizes the maintenance process, improves the user's operating experience, and provides scientific support for the production safety and benefits of the enterprise.

[0026] Furthermore, if Figure 2 As shown, the data acquisition component specifically includes: a position analysis module, which is used to use simulation software, combined with the actual working environment and operating status of the tubular conveyor belt, to build a 3D simulation model, which is used to analyze the influence of different layout positions on the accuracy of measurement data; an area division module, which is used to form a network with multiple layout positions, divide the network into multiple areas, and deploy multiple ultrasonic sensors in a certain area. The ultrasonic sensors use time slicing technology to collect data in different time periods, and fuse the data according to the object measured by the ultrasonic sensor to obtain real-time data of the tubular conveyor belt operation; a data storage module, which is used to store the layout position and implementation data of the ultrasonic sensor.

[0027] Preferably, the position analysis module of this embodiment establishes a 3D model of the tubular conveyor belt through simulation software, takes into account the influence of the actual working environment and operating status, and can perform a comprehensive spatial analysis; by performing simulation tests on different layout positions, it can determine the degree of influence of each position on the measurement accuracy and generate a corresponding report. The significance achieved: It enables decision makers to formulate a scientific and reasonable sensor layout plan based on the simulation results, thereby improving the accuracy and reliability of the measurement data; through the early simulation, potential layout problems can be identified, and the risk of failure or inaccuracy that may occur during the later implementation process can be reduced, saving resources and time. The regional division module connects multiple layout positions into a network, divides the entire sensor layout into regions, and improves the coverage of key areas; using time slicing technology, different sensors collect data separately in different time periods, and integrates the data of each sensor through the data fusion algorithm to obtain comprehensive real-time data. The significance achieved: Through regional division and data fusion, the possible errors of a single sensor can be overcome, and a more accurate and comprehensive conveyor belt operation status can be obtained; through the collaborative work of multiple sensors, data anomalies caused by environmental factors or device failures can be effectively resisted, and the robustness of the system can be improved. The data storage module uses an appropriate database structure to store the ultrasonic sensor's location and collected data, ensuring efficient organization and rapid retrieval of data; recording and storing historical data for future use in data analysis, fault detection, and trend prediction. Significance achieved: Provides an important data foundation for subsequent fault analysis, pattern recognition, and decision-making, enhancing the system's intelligence and adaptive capabilities; through effective data storage and backup measures, ensures the security and reliability of important operating data, and avoids data loss or damage.

[0028] In summary, the three modules of this embodiment are interrelated in the data acquisition component, each showing its strengths, and working together on the entire tubular conveyor belt operation fault intelligent detection alarm system based on ultrasonic ranging. The position analysis module provides a scientific basis for sensor layout, the area division module optimizes real-time data acquisition, and the data storage module ensures the persistence and traceability of the data. This effective modular design not only improves the performance of the system, but also provides important support for subsequent analysis, decision-making and fault handling, and ultimately provides a guarantee for the safe and efficient operation of the conveyor belt.

[0029] Furthermore, the location analysis module specifically includes: an equipment layout submodule, which is used to collect various physical parameters, including the size, shape, material properties, surrounding obstacles and environmental conditions (such as humidity, temperature, etc.) of the conveyor belt; create a three-dimensional model of the conveyor belt, ultrasonic sensor and its environment; arrange the ultrasonic sensor at different positions in the three-dimensional model of the conveyor belt, and preset the working direction and measurement angle; a result acquisition submodule, which is used to set different operating states of the conveyor belt, such as start, stop, loading and unloading, and obtain the measurement results of the ultrasonic sensor under different states; record the measurement data of the ultrasonic sensor in the simulation and generate corresponding outputs; a strategy generation submodule, which is used to classify and mark each measurement data according to parameters such as layout location, sensor characteristics and environmental impact, to form a structured data set; calculate the error between each sensor measurement data and the standard value generated by the actual model, and quantify the deviation using the root mean square error; use data visualization tools to present the measurement accuracy of different positions in the form of charts, and automatically generate sensor layout strategies.

[0030] Preferably, the equipment layout submodule of this embodiment ensures that all kinds of influencing factors in the analysis process are fully considered, providing basic data for subsequent measurement and data analysis; through the construction of a three-dimensional model and the reasonable arrangement of sensors, the simulation data is closer to the actual operating environment, improving the validity and reliability of the data, and laying the foundation for subsequent decision-making. The result acquisition submodule sets different operating states of the conveyor belt, such as starting, stopping, loading and unloading, to comprehensively evaluate the measurement effect of the ultrasonic sensor in various states; records the measurement data of the ultrasonic sensor in different states, and generates detailed measurement result output. The significance achieved: Ensure that sufficient measurement data is captured under different operating states, so that subsequent analysis can fully reflect the impact of the working conditions of the conveyor belt on the data; provide key data support for sensor performance under different operating conditions, help identify which states may cause measurement errors, and optimize system design. The strategy generation submodule classifies and labels the measurement data based on multiple parameters such as the deployment location, sensor characteristics, and environmental impact, forming a structured data set to provide a convenient basis for analysis; calculates the error between the measurement data of each sensor and the standard value generated by the actual model, and uses indicators such as the root mean square error (RMSE) to quantify the measurement deviation; uses data visualization tools to display the measurement accuracy of different locations in the form of charts and compares the effectiveness of sensors at each location; automatically generates sensor deployment strategies and gives optimal deployment recommendations. Significance achieved: Provides an empirical basis for the optimal deployment location of sensors, optimizes sensor layout plans, and improves measurement accuracy and stability; reduces the complexity of data analysis and improves analysis efficiency through visualization and structured data sets, providing better support for subsequent optimization and improvement.

[0031] In summary, the various submodules of the location analysis module of this embodiment complement each other and jointly promote the realization of the intelligent monitoring system for tubular conveyor belts based on ultrasonic ranging. The equipment layout submodule provides a solid foundation for subsequent analysis, the result acquisition submodule ensures the reliability of the system under different conditions, and the strategy generation submodule greatly enhances the intelligence level and decision-making ability of the system. This modular design not only improves the overall performance of the system, but also provides strong support for fault detection and early warning mechanisms in practical applications.

[0032] Furthermore, the strategy generation submodule specifically includes: a fitness calculation unit, which is used to represent each ultrasonic sensor layout position as a chromosome and randomly generate an initial population; the fitness of each chromosome is calculated according to the minimized root mean square error; a crossover operation unit, which adopts roulette wheel selection to select chromosomes with high fitness from the current population as parents, and generates new individuals (offspring) through single-point crossover operations; an operation median unit, which is used to evaluate the fitness of the new population, replace individuals with low fitness, and repeatedly perform selection, crossover and mutation operations until the preset maximum number of iterations is reached.

[0033] Preferably, the fitness calculation unit of this embodiment encodes the layout position of each ultrasonic sensor in the form of chromosomes, usually expressed in a coordinate system (such as two-dimensional or three-dimensional coordinates); uses a random algorithm to generate an initial population containing multiple different layout schemes; these schemes are evenly distributed in the feature space to ensure the diversity of algorithm exploration; the fitness of each chromosome is calculated based on the objective function (such as root mean square error RMSE), and the fitness value represents the effectiveness and superiority of each layout scheme. Significance achieved: The initial randomly generated population ensures a wide range of exploration and increases the chance of finding the global optimal solution; the calculated fitness provides a clear criterion for optimization, so that the algorithm can effectively distinguish the advantages and disadvantages of different layout schemes and achieve quantitative evaluation of the goal. The crossover operation unit uses a roulette selection method (or other selection methods) to select an appropriate number of parents from the current population according to the fitness level, ensuring that the better scheme can enhance the quality of the offspring; the characteristics of the two parents are combined through the crossover operation to generate a new individual (offspring). For example, the first half of the chromosomes of the two parents are exchanged with the second half to generate a new potential layout scheme. Significance achieved: The crossover operation can retain the excellent characteristics of the parent generation and combine them to explore new solutions. The recombination mechanism helps the evolution and optimization of the algorithm; by combining existing advantageous solutions, the newly generated offspring usually approach or reach the solution more effectively, improving the search efficiency. In each iteration of the median operation unit, the median operation unit evaluates the fitness of the new offspring and eliminates the poor individuals in time to ensure that the quality of the population remains at a high level; repeatedly performs selection, crossover and mutation operations to continuously improve the population and gradually approach the optimal solution. The unit is also responsible for monitoring the number of iterations and determining whether to stop the optimization process according to preset conditions. Significance achieved: The median operation unit ensures that the algorithm can absorb new information in each iteration, enhance the overall population performance, and thus improve the algorithm's intergenerational transmission ability to find the optimal solution; by selecting the good and the bad in each iteration, the algorithm is prevented from staying only in the local optimal solution, so that it maintains a certain exploration ability, which helps to find a better solution in a complex solution space.

[0034] In summary, the entire strategy generation submodule of this embodiment constructs an evolutionary optimization mechanism through the collaborative work of these three units to achieve effective strategy generation for the deployment of ultrasonic sensors. Its significance lies in: ensuring that the optimization strategy meets the accuracy of the on-site environment and needs, improving monitoring efficiency and accuracy; adapting to complex and changeable practical application needs, and having the ability to dynamically adjust and optimize; through the combination of adaptive learning and genetic mechanisms, new deployment plans are constantly stimulated, enhancing the intelligence and self-evolution capabilities of the system. In summary, each unit plays an irreplaceable technical role in strategy generation, providing strong support and optimization means for the deployment strategy of ultrasonic sensors.

[0035] Furthermore, if Figure 3 As shown in the figure, the fault analysis component specifically includes: a feature extraction module, which is used to extract key features from real-time and historical data, such as the height, width, and length of the conveyor belt, as well as the impact of environmental factors (temperature, humidity, and air pressure, etc.) on sensor data; automatically select the most discriminative data features according to changes in real-time data; use deep learning algorithms to process sensor data, combined with time series data analysis, automatically generate new fault pattern recognition models, compare real-time monitoring data with established fault patterns, and perform fault identification; a strategy execution module, which is used to classify fault types according to identified faults, such as minor faults, serious faults, and emergency faults, and define corresponding alarm strategies for each type; a word multimodal alarm mechanism, which automatically selects the alarm method according to user preferences and historical reactions; a data analysis module, which is used to continuously obtain ultrasonic sensor data, combine compensation for environmental factors, monitor key parameters of conveyor belt operation, establish a time series analysis model, analyze real-time data, predict potential trends and faults, and provide visual charts to understand possible problems.

[0036] Preferably, the feature extraction module of this embodiment extracts key parameters such as the height, width and length of the conveyor belt from real-time and historical data, and statistically analyzes the impact of environmental factors (such as temperature, humidity, air pressure, etc.) on sensor data to ensure the accuracy and validity of the data; uses intelligent algorithms to monitor data changes in real time, and dynamically selects the most discriminative features through feature selection algorithms (such as based on information gain, L1 regularization, etc.) to enhance the performance of the model and reduce the computational complexity; uses deep learning models (such as convolutional neural networks or recurrent neural networks) to analyze sensor data, and combines time series data mining to automatically build and update the fault mode recognition model to ensure continuous adaptation to new operating conditions. Significance: By extracting and selecting the best features, the system can more accurately identify fault modes and reduce the possibility of false alarms and missed alarms; the feature adaptive selection mechanism enables the system to always maintain its detection efficiency and accuracy when the environment changes or the operating conditions change; uses deep learning to automatically generate fault mode models, so that the intelligence level of the system is continuously improved, and it can self-optimize and adapt to the changing industrial environment. The strategy execution module classifies the identified fault types into fine categories (minor faults, serious faults, emergency faults), and defines specific alarm strategies for each type, including response time, alarm mode, etc.; it automatically selects alarm modes (such as visual alarms, sound alarms, mobile phone notifications, message push, etc.) according to user preferences and historical responses to adapt to different environments and user needs. Significance: Refining fault classification and strategy formulation makes fault response faster and more effective, reducing system downtime; through the implementation of multimodal alarm strategies, it meets the needs of different users, improves user acceptance and responsiveness to the alarm system, and increases the practicality of the system; such a design enhances the interactivity between users and the system, and improves users' understanding and attention to fault information. The data analysis module continuously obtains ultrasonic sensor data, combines compensation for environmental factors, monitors the operating status of the conveyor belt in real time, and ensures high reliability of data collection; constructs time series analysis models, such as ARIMA or LSTM, responsible for analyzing and trend prediction of historical data, and identifying potential fault trends; generates visualization charts, and displays fault trends and real-time data in a graphical way to facilitate user understanding and decision-making. Significance: Through time series analysis, potential failure risks can be identified in advance, which helps to implement preventive maintenance and reduce sudden failures and downtime; the data visualization function makes complex data easier to understand, helps managers to quickly diagnose and make decisions, and improves operation and maintenance efficiency; the overall data intelligent analysis and visualization capabilities enable the system to not only respond when a failure occurs, but also actively guide users to formulate maintenance plans, thereby achieving a higher level of automation and intelligence.

[0037] In summary, through the cooperation of the feature extraction module, the policy execution module and the data analysis module, this fault analysis component can form a dynamic, intelligent and adaptive system. This not only improves the operating efficiency and safety of the tubular conveyor belt, but also improves the intelligence level of fault detection and response, and ultimately achieves more efficient operation and maintenance management. The technical effects and characteristics of each module complement each other, promote the overall intelligent process of the system, and create an efficient, reliable and user-friendly monitoring solution for users.

[0038] Furthermore, the feature extraction module specifically includes: a data collection submodule, which is used to collect the height, width, length, etc. of the conveyor belt and the fault category label from the ultrasonic sensor; a mutual information calculation submodule, which is used to calculate the joint probability distribution of the feature and the fault category by performing frequency statistics on the data; and simultaneously calculate the marginal probability distribution of the feature and the fault category; using the mutual information formula, the obtained probability value is substituted into the formula for calculation to obtain the mutual information between the feature and the fault type; the expression of the mutual information formula is: , where Indicates the height, width, length and other characteristics of the conveyor belt and fault category The joint probability distribution of and They are and The marginal probability distribution of The value range of is [0, ∞), where: if ( = 0), then and Independent of each other, No information provided any information.

[0039] if( > 0), then Provides information about The larger the value, the stronger the correlation. right The stronger the predictive ability is; the feature sorting submodule is used to sort the features according to the calculated mutual information value and select the features with high mutual information as the most discriminative data features.

[0040] Preferably, the data collection submodule of this embodiment collects various types of data (such as the height, width, length, etc. of the conveyor belt) and fault category labels from the ultrasonic sensor in real time to ensure the comprehensiveness and accuracy of the data source; data integrity and consistency are controlled through data collection to ensure that subsequent analysis is based on valid data. Significance achieved: Provide multi-dimensional and high-dimensional data for the entire feature extraction process; these data will directly affect the subsequent feature calculation and analysis, ensuring that all information dimensions required for fault analysis can be covered; through continuous data collection, the real-time monitoring of the running status of the conveyor belt can be achieved, so as to timely discover potential problems and enhance the intelligence level of the system. The mutual information calculation submodule calculates the joint probability distribution (p(x,y)) of the feature (X) (such as height, width, length, etc.) and the fault category label (Y) by performing frequency statistics on the data, and further calculates the marginal probability distribution (p(x)) and (p(y)); according to the mutual information formula, the obtained probability value is substituted into the formula for calculation to obtain the mutual information amount (I(X; Y)) between the feature and the fault type, thereby quantifying the relationship between the feature and the target variable. Significance achieved: The calculation of mutual information can help us quantitatively evaluate the relationship between features and fault categories, and reveal which features provide valuable information for fault classification; by quantifying the dependencies between features, the scientificity and accuracy of the feature selection process can be enhanced, thereby effectively reducing potential biases in the feature selection process. The feature sorting submodule sorts the extracted features according to the calculated mutual information values, and selects features with high mutual information as the most discriminative features. This process can identify the feature set that is most helpful for fault classification; the final selected feature subset is output to provide a basis for subsequent feature modeling and model training. Significance achieved: By selecting features with high mutual information, the prediction performance of subsequent models can be significantly improved, the complexity of the model can be reduced, and overfitting can be avoided; reducing feature dimensions can improve the computational efficiency of subsequent algorithms, especially when processing large-scale data, which can speed up model training and reasoning.

[0041] In summary, through the effective cooperation of the above three sub-modules, the feature extraction module of this embodiment can realize the complete process from data collection to feature selection. Ultimately, this method can not only convey intuitive and effective fault information for real-time monitoring and early warning, but also provide solid data support for fault diagnosis and prediction, thereby improving the safety and efficiency of enterprise operations. Through the construction of this module, the following goals can be achieved: with the help of mutual information analysis, ensure that the most discriminative features are paid attention to, and improve the system's fault recognition accuracy; through the extraction and analysis of high-quality features, provide more scientific data support for subsequent accident warnings, maintenance decisions, etc., thereby realizing intelligent management of equipment; lay the foundation for the construction of fault prediction models, and then improve the company's ability to respond to changes in equipment status.

[0042] Furthermore, the feature extraction module specifically includes: a data capture submodule, which is used to automatically select the most discriminative features, process the ultrasonic sensor data through a bidirectional long short-term memory network, and capture time dependencies; a model training submodule, which is used to divide the ultrasonic sensor data obtained by the bidirectional long short-term memory network to obtain a training set and a validation set, divide the data set into multiple batches, and train the fault pattern recognition model; select the cross entropy loss to measure the difference between the output of the fault pattern recognition model and the true label; a model evaluation submodule, which is used to use the validation set to evaluate the indicators of the fault pattern recognition model, and the indicators include accuracy, recall rate and F1-score.

[0043] Preferably, the data capture submodule of this embodiment obtains raw data from the ultrasonic sensor and automatically selects the most discriminative features; processes the input time series data through a bidirectional long short-term memory network (Bi-LSTM) to capture the long-term time dependency of the input data; and extracts effective features from the original time series data through the Bi-LSTM structure. The bidirectional structure allows the model to take into account both past and future information when processing data, thereby improving the accuracy of feature description; converting the data of the ultrasonic sensor into a high-dimensional feature representation makes subsequent model training more effective. Significance: By automatically selecting and extracting the most discriminative features, it is ensured that the data used by the model during training are highly correlated and low-noise features, thereby improving the accuracy of fault identification and the intelligence level of the system; effectively capturing time dependencies is the key to completing time series data analysis, and is crucial to the timeliness and accuracy of fault diagnosis. The model training submodule divides the data set processed by Bi-LSTM into a training set and a validation set, and performs batch segmentation on the data set so that the system can train the fault pattern recognition model; the training set and validation set are divided reasonably to ensure that the algorithm is trained and evaluated on different samples, avoid overfitting, and ensure the generalization ability of the model; the data is divided into batches to speed up the training speed, so that the model can learn parameters in each batch and achieve efficient model training; the cross entropy loss function is selected as the optimization target to directly measure the difference between the model output and the true label to ensure that the model can learn efficiently. Significance: Through appropriate division and batch processing, the model can learn effective features and their corresponding fault modes. This training process enables the model to have strong adaptability and good generalization ability, so as to accurately identify faults in practical applications; the cross entropy loss function provides an effective way to measure the difference between the model output and the actual data, so that the model can be continuously adjusted during training to approach the real situation. The model evaluation submodule uses a pre-divided validation set to evaluate the fault pattern recognition model and calculates indicators such as accuracy, recall, and F1-score to judge the performance of the model; through indicators such as accuracy, recall, and F1-score, the performance of the model on a specific data set is quantified, especially the actual recognition effect of the fault. Significance: Through quantitative performance evaluation, the team can determine whether the model has achieved the expected effect, and thus decide whether it can be applied in the actual production environment or whether it needs further optimization; these evaluation indicators can not only reflect the overall performance of the model, but also point out the potential deficiencies of the model in certain specific fault types, thereby guiding the subsequent model optimization or feature selection process.

[0044] Minor faults in this embodiment: This type of fault has little impact on the operation and output of the equipment, and usually does not cause immediate shutdown, but requires monitoring and maintenance. For example, slight friction or noise of the conveyor belt, slight deviation of sensor data. Severe faults: This type of fault may cause reduced equipment efficiency or even partial shutdown, but it will not threaten the entire system. For example, the speed of the conveyor belt slows down, the sensor readings are distorted and affect normal operation. Emergency faults: This type of fault poses a direct threat to the safety of equipment and personnel and needs to be handled immediately. For example, mechanical failure of the conveyor belt leads to shutdown, overheating or abnormal vibration, leakage of hazardous substances, etc.

[0045] Minor fault alarm strategy, alarm method: SMS or APP push notification to timely notify relevant personnel; Alarm content: Notification information such as "Warning: Minor friction of the conveyor belt has been detected. It is recommended to check during the next maintenance." and provide relevant suggestions; Follow-up actions: Ask the user whether to arrange maintenance, and collect the user's attention to the fault through feedback to optimize the subsequent alarm strategy. Serious fault alarm strategy, alarm method: Multi-channel simultaneous warning, such as SMS, email, voice call, display (such as LED warning light), etc.; Alarm content: Content example "Note: The conveyor belt speed is reduced, the current speed is X meters / second, and it needs to be checked as soon as possible." Attach relevant data charts to help users understand the severity of the problem. Follow-up actions: Set up an alarm escalation mechanism: If the fault is not resolved, remind again after 24 hours; provide a direct maintenance service link or phone number, or dispatch a maintenance team. Emergency fault alarm strategy, alarm method: directly contact the equipment operator's phone, enable alarm sound or vibration so that it will not be ignored; alarm content: content example "Emergency alarm! The conveyor belt has a mechanical failure. The operator must stop and check it immediately." Attach emergency handling procedures such as maintenance procedures or emergency contact numbers; Follow-up actions: automatically generate a fault report, record the fault type, occurrence time, possible causes and other information for subsequent analysis; initiate the preset emergency response plan, and communicate with the maintenance team in real time to ensure a quick response.

[0046] In summary, the various submodules in the feature extraction module of this embodiment work together in the fault pattern recognition system to ensure efficient and accurate fault monitoring in the process of automated recognition. The independent technical effects of each submodule are combined with the overall significance to enhance the intelligence level of the entire system and help users achieve real-time monitoring and fault warning. By rationally designing and optimizing these submodules, the system can better meet the needs of practical applications and improve the safety and reliability of equipment operation.

[0047] Furthermore, the policy execution module specifically includes: a preference identification submodule, which is used to establish a database for storing user preference settings and response records; set time intervals, automatically update and analyze user feedback and response behaviors, and identify changes in user preferences; a template setting submodule, which is used to build a rule engine to filter out appropriate alarm options from a variety of alarm methods based on fault levels and user preferences; design different content templates for each alarm type; a method selection submodule, which is used to generate a priority ranking for each alarm method based on user historical response data analysis; for example, if the user has responded well to SMS alarms in the past two months, set it as a priority option; when a new fault occurs, dynamically select the alarm method based on current environmental factors (such as time, location, etc.) and the user's real-time status (such as whether he is at work).

[0048] Preferably, the preference identification submodule of this embodiment establishes a systematic database to store user preference settings and response records, including response time, processing results, and user feedback for different alarm modes; set regular analysis, such as weekly or monthly, to automatically update user preferences, identify the changing trend of preferences, and ensure the timeliness and accuracy of data. Significance achieved: Through the continuously updated database, the system can provide alarm services that are more in line with the personalized needs of users, improve user satisfaction and participation; collect user historical feedback and response behavior, provide a data basis for subsequent alarm strategies, and promote more scientific decision-making. The template setting submodule builds a flexible rule engine that can filter appropriate alarm modes according to the fault level (minor, serious, emergency) and user preferences; design diversified templates for different types of faults to ensure that the alarm information is clear, concise and targeted, which helps users quickly understand the nature of the fault. Significance achieved: Through accurate and personalized content template design, ensure that users can quickly obtain key information, so as to make timely responses in critical situations; the establishment of the rule engine allows the system to quickly adapt to different fault types, ensure that the alarm strategy conforms to the actual situation, and facilitate subsequent maintenance and processing. The mode selection submodule generates a priority ranking for various alarm modes based on the user's historical response data, and selects the most suitable alarm mode in a timely manner. For example, if a user prefers text messages rather than phone calls, the system will generate a corresponding priority selection based on this; when a new fault occurs, the alarm mode selection is dynamically adjusted based on the current environmental factors and the user's actual status (such as whether he is working) to ensure that the alarm mode is timely and appropriate. Significance achieved: Through priority sorting and dynamic selection mechanisms, ensure that alarm information can be delivered to users in the shortest time, minimize the impact of faults on production and equipment operation; respect user preferences, improve user experience, and encourage users to be more active in subsequent feedback, thereby helping to continuously optimize and improve the system.

[0049] In summary, the entire policy execution module of this embodiment realizes the automation process from the identification of user preferences to the formulation and execution of alarm policies, and improves the intelligence level of the system. Through the synergy of these three sub-modules, it can ensure that when a fault occurs, the system can quickly and effectively identify the problem and respond, which not only improves the safety and reliability of the equipment, but also helps to reduce the unplanned downtime of the production line caused by faults, thereby improving the overall production efficiency and user satisfaction.

[0050] Furthermore, the data analysis module specifically includes: a data partitioning submodule, which is used to divide the data into multiple time windows and convert them into a time series format; select input features related to real-time data as input to the GRU model; the GRU model includes an input gate, a reset gate and an update gate; among them, the reset gate: determines how to combine the new input with the past state; the update gate: determines how much information of the past state to retain; the current state: resets the current state and generates a new candidate state; the final state update: combines the current candidate state and the previous state to update the output state; the parameter update submodule, which is used to calculate the gradient and update the GRU model parameters using the back propagation algorithm; the real-time prediction submodule, which is used to divide the real-time data into sequences of fixed length and pass them to the trained GRU model; perform real-time prediction based on the current input state and historical state, and output results such as fault type, fault probability and key parameter prediction.

[0051] Preferably, the data partitioning submodule of this embodiment divides the continuous time series data into multiple time windows of fixed length. Each time window contains data within a period of time, which can provide contextual information for the model; extract features related to the target to be analyzed (such as fault detection) from the input data. These features may involve multiple sensor data and environmental factors. Significance achieved: Through the division of time windows, the model can better capture the trends and periodic changes in the time series, thereby improving the accuracy of the analysis; selecting features related to real-time data enables the model to focus on important information, avoid redundant data interference, and help the model converge faster. The GRU model determines how to combine new inputs with past states, and the value of the reset gate affects the extent to which the network retains historical information; a dynamic balance is made between maintaining information about past states and introducing new input information. This mechanism enables the model to be updated adaptively; by utilizing the combination of the reset gate and the update gate, a new state is generated, which not only takes into account the current input, but also combines historical information. Significance achieved: Through the design of reset gate and update gate, GRU can effectively store important past information while suppressing unnecessary noise, so as to more accurately reflect the current system status; compared with standard RNN, GRU can reduce the gradient vanishing problem, so as to maintain good performance when processing long time series data. The parameter update submodule uses back propagation to adjust the parameters of the GRU model by calculating the gradient; calculate the gradient of the loss function relative to the model parameters to determine how to update the model. Significance achieved: Through back propagation and gradient update, the model can be continuously optimized, thereby improving the accuracy and stability of prediction; the model can be adaptively adjusted during the training process and gradually learn the best mapping relationship with the input data. The real-time prediction submodule divides the new real-time data into sequences of fixed length to input into the trained GRU model; based on the current input state and historical state, real-time fault type identification and key parameter prediction are performed. Significance achieved: The real-time prediction capability enables the system to quickly identify faults and give early warnings, which helps prevent equipment damage and production stagnation; through accurate fault type and probability prediction, the real-time prediction submodule provides important decision support for operation and maintenance, and promotes effective resource allocation and implementation of response strategies.

[0052] In summary, the design of the entire data analysis module of this embodiment enables the system to effectively and quickly process a large amount of time series data and capture potential fault information. Through reasonable data partitioning, feature selection, GRU model optimization and real-time data prediction, accurate fault detection and prediction can be achieved in large-scale industrial applications, which not only helps to improve the operating efficiency of equipment, but also reduces maintenance costs, improves production safety, and provides strong support for the optimization of enterprise processes and management decisions.

[0053] Furthermore, if Figure 4 As shown in the figure, the user interaction components specifically include: a content display creation module, which is used to create a dashboard containing real-time status and environmental factors of fault types; the real-time status displays the current height, width and length of the tubular conveyor belt, and provides a comparison with the safe range (such as green, yellow, and red indications); the fault type lists the fault type detected in real time, and the status indicator light can display the severity of the current fault (for example, different colors light up to indicate different levels of faults); environmental factors monitor and visualize temperature, humidity and air pressure data in real time, and use dynamic curve graphs to show the impact of changes in these environmental factors on the operating status of the tubular conveyor belt; a trend analysis module is used to generate a line graph using trend analysis results to display key parameters (such as Ultrasonic sensor readings), as well as any fault-related indicators (such as operating frequency and failure rate); set as: interactive charts users can explore historical data by clicking and zooming to obtain more detailed statistical information; time range selection allows users to select different time ranges (real-time, past week, past month, etc.) for comparative analysis; alarm prompt module, when a fault is monitored in real time and the alarm rule is triggered, an intelligent alarm prompt box will pop up on the screen, covering the fault type, occurrence time, possible affected areas and recommended treatment measures; access fault history records to learn more about the frequency, duration and solution of the same fault, and use charts to present the time distribution of fault occurrence.

[0054] Preferably, the content display creation module of this embodiment constructs an integrated user interface to display various key information, including real-time status, fault type and environmental factors, to enhance the user's observation ability; integrate multiple indicators into a visual interface to provide a concise and comprehensive way of information communication. Significance achieved: Users can quickly identify the current status, fault type and environmental conditions of the tubular conveyor belt, helping operators to respond to potential abnormalities in the first time; by centrally displaying various information, users can make effective operational decisions in a short time, improving operational efficiency and safety. The real-time status display shows the current height, width and length, and compares them with the set safety range, using color coding (green, yellow, red) to indicate the status; intuitive feedback is given through the status indicator to indicate the severity of the current fault. Significance achieved: Color identification can effectively help users quickly determine the current status of the conveyor belt, discover potential problems in time, and reduce safety risks; real-time monitoring during equipment operation can promote rapid response and ensure that necessary maintenance measures are taken in time. Environmental factor monitoring and visualization displays changes in environmental factors such as temperature, humidity and air pressure through dynamic curves, allowing users to observe their impact on the operating status of the conveyor belt; data is updated in real time to reflect the impact of environmental changes. Significance achieved: Allows users to analyze the relationship between the changing trend of environmental factors and the status of the conveyor belt, helping to identify potential failures caused by environmental changes; by monitoring environmental factors, enterprises can optimize working conditions and reduce operational risks caused by environmental factors. The trend analysis module uses a line chart to display the changing trend of key parameters, such as ultrasonic sensor readings and other important indicators; users can explore historical data in depth by clicking and zooming. Significance achieved: Through historical trend analysis, it helps users understand the mode and changes of equipment operation and make more accurate fault predictions; users can select different time ranges for comparative analysis to find out the law of equipment performance changes and the direction of improvement. When the alarm prompt module detects a fault and triggers an alarm, a prompt box pops up to provide the fault type, occurrence time, affected area and recommended treatment measures; the fault history can be viewed to understand the frequency, duration and solution of the fault. Significance achieved: Intelligent alarms can ensure that users are notified as soon as a problem occurs, which helps to take quick action and reduce losses caused by faults; by analyzing historical fault data, users can summarize lessons learned, improve daily maintenance and operation processes, and improve the reliability and efficiency of equipment.

[0055] In summary, the various modules of this embodiment together constitute an integrated monitoring and response system, which can track the status of the tubular conveyor belt in real time and detect and handle faults in a timely manner. This not only improves the safety and reliability of the equipment, but also optimizes the operation process and decision support, and promotes the improvement of overall operational efficiency. Through intelligent interaction and visual design, users can more easily obtain, analyze and understand information in a complex data environment, and then make more informed management decisions.

[0056] Furthermore, the trend analysis module specifically includes: a data retrieval submodule, which is used to use SQL query to extract required parameter data in the interface call of the data to be displayed; a data conversion submodule, which is used to format the query results and convert the data into a key-value pair format of a timestamp and a corresponding sensor reading; a graphics creation submodule, which is used to create a line chart using a chart library, setting the X-axis to the timestamp and the Y-axis to the sensor reading; and determining the style of the chart, such as line color, point markings, grid lines, labels, and tooltips.

[0057] Preferably, the data retrieval submodule of this embodiment extracts the required parameter data from the database through SQL query, laying the foundation for subsequent data processing and visualization; by optimizing SQL query (such as index, appropriate WHERE condition, etc.), the speed and performance of data extraction are improved; according to the needs of users, a specific time range and data type are selected to make data retrieval more flexible. The significance achieved: the timeliness and accuracy of the data are ensured, and reliable real-time data support is provided for subsequent analysis; users can quickly obtain the required data according to actual needs, which improves the efficiency of analysis and decision-making. The data conversion submodule converts the original data in the database (usually in row and column format) into a context format suitable for the chart library, usually an object array or a key-value pair; during the conversion process, the data is cleaned and processed (such as removing outliers and filling missing values) to ensure the validity of the data; ensure that the data output structure is consistent, so that the subsequent data display and chart creation are more concise and efficient. The significance achieved ensures that the data can be seamlessly connected to the chart library, thereby improving the speed and accuracy of chart generation; users can obtain clear time series data during visual analysis, helping them better understand trend changes. The graphics creation submodule uses chart libraries (such as D3.js, Chart.js, etc.) to display data in an intuitive way, so that users can quickly obtain trend information; it implements user interaction functions (such as clicking, hovering to display information, zooming, etc.) to enhance the user experience and enable them to explore data more deeply; by setting the visual style of the chart (such as color, line type, mark, layout, etc.), the chart is not only beautiful, but also effectively conveys data information. Significance achieved: Through high-quality data visualization, users can more intuitively understand data trends and promote the formation of insights; the interactive design allows users to obtain more details when exploring data, deepen their understanding of the data, and help make better decisions in experiments or operations.

[0058] In summary, the three submodules of this embodiment effectively complete the whole process from data acquisition to data processing to user visualization analysis through mutual cooperation. Not only the efficiency and accuracy of data processing are improved, but also the user experience is optimized, making the data analysis process not only easy to understand, but also interactive and beautiful. Finally, the implementation of the trend analysis module provides users with a powerful tool for in-depth analysis of real-time and historical data, further supporting decision making.

[0059] like Figure 5 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device includes a processor and a memory coupled to the processor.

[0060] The memory stores program instructions for implementing the intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging in any of the above embodiments.

[0061] The processor is used to execute program instructions stored in the memory to perform intelligent detection and alarm of tubular conveyor belt operation failure based on ultrasonic ranging.

[0062] The processor may also be referred to as a CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0063] Further, Figure 6 This is a schematic diagram of the structure of a storage medium of an embodiment of the present application. The storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0064] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0065] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0066] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. An intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging, characterized in that: The ultrasonic ranging-based intelligent detection and alarm system for tubular conveyor belt operation faults includes: a data acquisition component, which is used to use multiple ultrasonic sensors to monitor the height, width and length data of the tubular conveyor belt in real time, and capture the material status and the operation status of the tubular conveyor belt; real-time monitoring of temperature, humidity and air pressure environmental factors, and automatic compensation of ultrasonic ranging data; a fault analysis component, which is used to analyze real-time and historical data, identify potential faults, and perform fault detection through pattern recognition; set intelligent alarm logic to automatically select an alarm mode according to user preferences and historical reactions; real-time monitoring of the tubular conveyor belt status and trend analysis; a user interaction component, which is used to provide a graphical interface for visual display of fault detection results and trend analysis; and a voice assistant function is set to achieve interaction between users and the system.

2. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 1 is characterized in that: The data acquisition component includes: a position analysis module, which is used to use simulation software, combined with the actual working environment and operating status of the tubular conveyor belt, to build a 3D simulation model, which is used to analyze the influence of different layout positions on the accuracy of measurement data; an area division module, which is used to form a network with multiple layout positions, divide the network into multiple areas, and deploy multiple ultrasonic sensors in a certain area. The ultrasonic sensors use time slicing technology to collect data in different time periods, and the data is fused according to the object measured by the ultrasonic sensor to obtain real-time data of the tubular conveyor belt operation; a data storage module, which is used to store the layout position and implementation data of the ultrasonic sensor.

3. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 2 is characterized in that: The position analysis module includes: an equipment layout submodule, which is used to collect various physical parameters, including the size, shape, material properties, surrounding obstacles and environmental conditions of the conveyor belt; create a three-dimensional model of the conveyor belt, ultrasonic sensor and its environment; arrange the ultrasonic sensor at different positions in the three-dimensional model of the conveyor belt, and preset the working direction and measurement angle; a result acquisition submodule, which is used to set the start, stop, loading and unloading different operating states of the conveyor belt, and obtain the measurement results of the ultrasonic sensor under different states; record the measurement data of the ultrasonic sensor in the simulation and generate corresponding outputs; a strategy generation submodule, which is used to classify and mark each measurement data according to the layout position, sensor characteristics and environmental influencing parameters to form a structured data set; calculate the error between each sensor measurement data and the standard value generated by the actual model, and quantify the deviation using the root mean square error; use data visualization tools to present the measurement accuracy of different positions in the form of charts, and automatically generate sensor layout strategies.

4. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 3 is characterized in that: The strategy generation submodule includes: a fitness calculation unit, which is used to represent each ultrasonic sensor layout position as a chromosome and randomly generate an initial population; the fitness of each chromosome is calculated according to the minimum root mean square error; a crossover operation unit, which adopts roulette selection to select chromosomes with high fitness from the current population as parents and generates new individuals through single-point crossover operation; and an operation median unit, which is used to evaluate the fitness of the new population, replace individuals with low fitness, and repeatedly perform selection, crossover and mutation operations until the preset maximum number of iterations is reached.

5. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 1 is characterized in that: The fault analysis component includes: a feature extraction module, which is used to extract key features from real-time and historical data, including data on the height, width, and length of the conveyor belt, as well as the impact of environmental factors on sensor data; automatically select the most discriminative data features based on changes in real-time data; use deep learning algorithms to process sensor data, combined with time series data analysis, automatically generate new fault pattern recognition models, compare real-time monitoring data with established fault patterns, and perform fault identification; a strategy execution module, which is used to classify fault types into minor faults, serious faults, and emergency faults based on identified faults, and define corresponding alarm strategies for each type; a word multimodal alarm mechanism, which automatically selects the alarm method based on user preferences and historical responses; a data analysis module, which is used to continuously obtain ultrasonic sensor data, combine compensation for environmental factors, monitor key parameters of conveyor belt operation, establish a time series analysis model, analyze real-time data, predict potential trends and faults, and provide visual charts to understand possible problems.

6. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 5 is characterized in that: The feature extraction module includes: a data collection submodule, which is used to collect the height, width, length and fault category labels of the conveyor belt from the ultrasonic sensor; a mutual information calculation submodule, which is used to calculate the joint probability distribution of the feature and the fault category by performing frequency statistics on the data; and simultaneously calculate the marginal probability distribution of the feature and the fault category; using the mutual information formula, substituting the obtained probability value into the formula for calculation to obtain the mutual information between the feature and the fault type; and a feature sorting submodule, which is used to sort the features according to the calculated mutual information value, and select the feature with high mutual information as the most discriminative data feature.

7. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 5 is characterized in that: The feature extraction module also includes: a data capture submodule, which is used to automatically select the most discriminative features, process the ultrasonic sensor data through a bidirectional long short-term memory network, and capture time dependencies; a model training submodule, which is used to divide the ultrasonic sensor data obtained by the bidirectional long short-term memory network into a training set and a validation set, divide the data set into multiple batches, and train the fault pattern recognition model; select the cross entropy loss to measure the difference between the output of the fault pattern recognition model and the true label; and a model evaluation submodule, which is used to evaluate the indicators of the fault pattern recognition model using the validation set, and the indicators include accuracy, recall rate and F1-score.

8. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 5, characterized in that: The policy execution module includes: a preference identification submodule, which is used to establish a database for storing user preference settings and response records; set time intervals, automatically update and analyze user feedback and response behaviors, and identify changes in user preferences; a template setting submodule, which is used to build a rule engine to filter alarm options from a variety of alarm methods based on fault levels and user preferences; design different content templates for each alarm type; a method selection submodule, which is used to generate a priority ranking for each alarm method based on user historical response data analysis; and dynamically select an alarm method in combination with current environmental factors and the user's real-time status when a new fault occurs.

9. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 5, characterized in that: The data analysis module includes: a data partitioning submodule, which is used to divide the data into multiple time windows and convert them into a time series format; select input features related to real-time data as the input of the GRU model; the GRU model includes an input gate, a reset gate and an update gate; a parameter update submodule, which is used to calculate the gradient and update the GRU model parameters using the back propagation algorithm; a real-time prediction submodule, which is used to divide the real-time data into sequences of fixed length and pass them to the trained GRU model; perform real-time prediction based on the current input state and historical state, and output the fault type, fault probability and key parameter prediction results.

10. The intelligent detection and alarm system for tubular conveyor belt operation failure based on ultrasonic ranging as claimed in claim 1, characterized in that: User interaction components include: a content display creation module, which is used to create a dashboard that includes real-time status and environmental factors of fault types; a trend analysis module, which is used to generate a line graph using trend analysis results to display the changing trends of key parameters and any fault-related indicators; an alarm prompt module, which is used to pop up an intelligent alarm prompt box on the screen when a fault is monitored in real time and the alarm rule is triggered, covering the fault type, occurrence time, possible affected areas and recommended treatment measures; access to fault history records to learn in detail the frequency, duration and solutions of the same fault, and present the time distribution of faults in the form of charts.

Images