An Internet of Things-based factory equipment fault early warning system and method

Abstract

This invention discloses an IoT-based factory equipment fault early warning system and method, relating to the field of equipment fault early warning technology. It addresses the problem of low efficiency in detecting risks of conveyor belt wear, abnormal tension, and breakage. By calling conveyor belt transmission information, setting a tolerance key value, acquiring the quality of each conveyor device, detecting equipment data, calculating the quality tolerance ratio, calculating the pressure key value based on the combined quality and tolerance ratio, statistically analyzing the total pressure key value of the conveyor devices and comparing it with the tolerance key value, it determines whether to enter the wear monitoring mechanism. Once in the wear monitoring mechanism, it collects conveyor belt attribute data to calculate the tolerance amount, calculates the tolerance coefficient based on the continuous running time, corrects the tolerance key value according to the tolerance coefficient to generate a tolerance threshold, and then compares it with the total pressure key value to determine whether to send an alarm message to the user terminal. This reduces the risk of breakage or shutdown caused by excessive tension due to prolonged material sensing activation.

Description

Technical Field

[0001] This invention relates to the field of equipment fault early warning technology, and more specifically, to an Internet of Things-based factory equipment fault early warning system and method. Background Technology

[0002] With the continuous improvement of modern industrial automation, the operational safety and stability of conveyor belts and related equipment in factory production lines have become key factors in ensuring production efficiency and product quality. As an important mechanical carrier connecting various processes, the load-bearing capacity and operating status of conveyor belts directly affect the equipment failure rate and the continuity of the production line.

[0003] The existing technology has the following shortcomings:

[0004] Currently, existing fault early warning systems mostly rely on single indicators or static threshold settings, lacking a comprehensive assessment of uneven material distribution, conveyor belt fatigue status, and cumulative running time. Alarm strategies often produce false alarms or lag, resulting in low efficiency in identifying conveyor belt wear, abnormal tension, and breakage risks, and reducing alarm accuracy. Therefore, this paper proposes a factory equipment fault early warning system and method based on the Internet of Things.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a factory equipment fault early warning system and method based on the Internet of Things, which solves the problems mentioned in the background art by using multi-source sensor data fusion and a dynamic fault tolerance coefficient calculation model.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a factory equipment fault early warning method based on the Internet of Things, comprising the following steps:

[0008] Step S1: Call the conveyor belt transmission information, set the bearing key value according to the conveyor belt transmission information, obtain the equipment quality of each conveyor device, detect the equipment data of each conveyor device on the conveyor belt and calculate the quality fault tolerance ratio;

[0009] Step S2: Calculate the pressure key value of the conveyor based on the overall equipment quality and the quality tolerance ratio, count the total pressure key value of the conveyor on the current conveyor belt and compare it with the bearing key value of the conveyor belt, and determine whether to enter the wear monitoring mechanism based on the comparison result.

[0010] Step S3: When entering the wear monitoring mechanism, collect the attribute data of the conveyor belt and calculate the fault tolerance of the conveyor belt. Call the continuous running time of the conveyor belt and calculate the fault tolerance coefficient of the conveyor belt in combination with the fault tolerance.

[0011] Step S4: Correct the conveyor belt's tolerance key value according to the conveyor belt's fault tolerance coefficient and generate a tolerance threshold. Compare the total pressure key value of the conveying equipment on the current conveyor belt with the tolerance threshold, and determine whether to send an alarm message to the user terminal based on the comparison result.

[0012] In a preferred embodiment, in step S1, the conveying information of the conveyor belt is the average pressure borne by the conveyor belt over multiple historical time periods.

[0013] The average bearing pressure in each historical time period is merged into a bearing pressure dataset. Multiple average bearing pressures are randomly selected from the bearing pressure database as pressure benchmarks. Among the pressure benchmarks, the pressure benchmark corresponding to the median value is selected as the bearing pressure key value of the conveyor belt.

[0014] In a preferred embodiment, in step S1, the equipment data is the overlapping area of ​​the contact surface between the conveying equipment and the conveyor belt. When calculating the quality tolerance ratio, the maximum overlapping area of ​​the conveying equipment on the conveyor belt is selected as the calibration area, and the ratio of the overlapping area of ​​each conveying equipment to the calibration area is calculated as the quality tolerance ratio of each conveying equipment.

[0015] In a preferred embodiment, in step S2, the pressure key value of the transmission device is calculated by combining the device quality and quality tolerance ratio of each transmission device: Where m is the equipment mass of the transmission device, z is the mass tolerance ratio of the corresponding transmission device, c is the correction parameter, and Y is the pressure key value of the corresponding transmission device.

[0016] In a preferred embodiment, in step S2, the pressure key values ​​of each conveying device on the current conveyor belt are summed to obtain the total pressure key value;

[0017] If the total pressure key value of all conveying devices on the current conveyor belt exceeds the conveyor belt's bearing capacity key value, it is determined that the pressure of the conveying devices on the current conveyor belt is high, and the wear monitoring mechanism is activated; otherwise, the conveyor belt continues to operate.

[0018] In a preferred embodiment, in step S3, when the wear monitoring mechanism is activated, the property data of the conveyor belt is collected. The property data of the conveyor belt includes the uniformity of the conveyor belt pressure distribution and the motor power influence index.

[0019] The conveyor belt is divided equally from the midpoint to obtain a front half and a back half of the same length. The total pressure of each half is collected by gravity sensors and recorded as the pressure of the front half and the pressure of the back half. The pressure distribution uniformity is calculated by the absolute difference between the pressure of the front half and the pressure of the back half and the average pressure.

[0020] By installing current and voltage sensors at the conveyor belt drive motor, the input current and voltage of the motor are monitored in real time. The motor's power factor is then multiplied to calculate the actual output power of the motor. The inverse of this calculation is then used as an indicator of the motor's power influence.

[0021] In a preferred embodiment, in step S3, the motor power impact index is standardized.

[0022] The standardized motor power influence index and the conveyor belt pressure distribution uniformity are added together to calculate the fault tolerance of the conveyor belt.

[0023] In a preferred embodiment, in step S3, the continuous running time of the conveyor belt is obtained by calling a running time timer.

[0024] The duration of continuous operation will be standardized.

[0025] The fault tolerance coefficient of the conveyor belt is calculated by substituting the standardized continuous running time and the fault tolerance amount into the logistic regression formula. The specific formula is expressed as follows:

[0026] ;

[0027] In the formula, L is the result of logistic regression calculation, i.e., the fault tolerance coefficient of the conveyor belt, e is the natural base, and y is the linear combination term of the logistic regression model, specifically set as follows:

[0028] ;

[0029] In the formula, For bias terms, To accommodate fault tolerance, This refers to the continuous runtime after standardization. as well as These are the regression coefficients for the fault tolerance and the standardized duration of operation, respectively.

[0030] In a preferred embodiment, in step S4, the tolerance key value of the conveyor belt is corrected according to the fault tolerance coefficient of the conveyor belt. The specific correction process is as follows:

[0031] The tolerance coefficient and the tolerance adjustment value are summed and then multiplied with the tolerance key value to obtain the tolerance threshold.

[0032] Compare the total pressure key value of the conveying equipment on the current conveyor belt with the withstand threshold;

[0033] If the total pressure key value of the conveying equipment on the current conveyor belt exceeds the threshold, an alarm message will be generated and sent to the user terminal.

[0034] If the total pressure key value of the conveying equipment on the current conveyor belt is lower than the withstand threshold, no alarm information will be generated, and the conveyor belt will continue to operate.

[0035] An Internet of Things-based factory equipment fault early warning system includes a key value setting module, a key value comparison module, a wear monitoring module, and an evaluation and alarm module;

[0036] The key value setting module is used to call the transmission information of the conveyor belt and set the bearing key value according to the transmission information of the conveyor belt. It collects the equipment quality of each conveyor and detects the equipment data and sends it to the key value comparison module. It sends the bearing key value of the conveyor belt to the key value comparison module and the evaluation alarm module respectively.

[0037] After receiving the equipment quality and equipment data, the key value comparison module calculates the pressure key value of each conveyor, integrates the pressure key values ​​to generate the total pressure key value of the conveyor on the current conveyor belt and sends it to the evaluation and alarm module. The total pressure key value is compared with the conveyor belt's bearing key value. Based on the judgment result, it selects whether to set the wear monitoring signal and send it to the wear monitoring module.

[0038] When the wear monitoring module receives the wear detection signal, it collects the attribute data of the conveyor belt and calculates the fault tolerance of the conveyor belt. It calls the continuous running time of the conveyor belt and calculates the fault tolerance coefficient in combination with the fault tolerance to correct the fault tolerance key value of the conveyor belt and generate the fault tolerance threshold. The fault tolerance threshold is then sent to the evaluation and alarm module.

[0039] The evaluation and alarm module receives the total pressure key value of the conveying equipment on the current conveyor belt and the conveyor belt's bearing threshold, compares them, and selects whether to send alarm information to the user terminal based on the comparison result.

[0040] The technical effects and advantages of this invention are as follows:

[0041] This invention utilizes conveyor belt transmission information to set a bearing key value, acquire the equipment quality of each conveyor, detect the equipment data of each conveyor on the conveyor belt and calculate the quality tolerance ratio, calculate the pressure key value of the equipment by combining the equipment quality and the quality tolerance ratio, and statistically analyze the total pressure key value of the conveyor on the current conveyor belt and compare it with the bearing key value of the conveyor belt to determine whether to enter the wear monitoring mechanism. If the wear monitoring mechanism is entered, the conveyor belt attribute data is collected and the bearing tolerance of the conveyor belt is calculated. The tolerance coefficient is calculated by combining the continuous operation time of the conveyor belt, and the bearing key value of the conveyor belt is corrected according to the tolerance coefficient and a bearing threshold is generated and compared with the total pressure key value of the conveyor equipment again. Based on the comparison result, it is determined whether to send an alarm message to the user terminal. This reduces the problem of excessive tension caused by prolonged material sensing start-up of the conveyor belt, which may lead to conveyor belt breakage or shutdown. It effectively improves the operational safety and stability of the system and significantly reduces the risk of conveyor belt breakage and unplanned downtime. Attached Figure Description

[0042] Figure 1 This is a flowchart of a factory equipment fault early warning method based on the Internet of Things according to the present invention.

[0043] Figure 2 This is a schematic diagram of a factory equipment fault early warning system based on the Internet of Things according to the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] This invention utilizes conveyor belt transmission information to set a bearing key value, acquires the equipment quality of each conveyor, detects equipment data of each conveyor on the conveyor belt and calculates the quality tolerance ratio, calculates the pressure key value of the equipment by combining the equipment quality and the quality tolerance ratio, and statistically analyzes the total pressure key value of the conveyor on the current conveyor belt and compares it with the bearing key value of the conveyor belt to determine whether to enter the wear monitoring mechanism. If the wear monitoring mechanism is entered, it collects the attribute data of the conveyor belt and calculates the bearing tolerance of the conveyor belt, calculates the tolerance coefficient by combining the continuous running time of the conveyor belt, corrects the bearing key value of the conveyor belt according to the tolerance coefficient, generates a bearing threshold, and compares it again with the total pressure key value of the conveyor equipment. Based on the comparison result, it determines whether to send an alarm message to the user terminal, thereby reducing the problem of conveyor belt breakage or shutdown due to excessive tension caused by prolonged material sensing start-up.

[0046] Example 1: A factory equipment fault early warning method based on the Internet of Things, such as... Figure 1 As shown, it includes the following steps:

[0047] Step S1: Call the conveyor belt transmission information, set the bearing key value according to the conveyor belt transmission information, obtain the equipment quality of each conveyor device, detect the equipment data of each conveyor device on the conveyor belt and calculate the quality fault tolerance ratio;

[0048] Step S2: Calculate the pressure key value of the conveyor based on the overall equipment quality and the quality tolerance ratio, count the total pressure key value of the conveyor on the current conveyor belt and compare it with the bearing key value of the conveyor belt, and determine whether to enter the wear monitoring mechanism based on the comparison result.

[0049] Step S3: When entering the wear monitoring mechanism, collect the attribute data of the conveyor belt and calculate the fault tolerance of the conveyor belt. Call the continuous running time of the conveyor belt and calculate the fault tolerance coefficient of the conveyor belt in combination with the fault tolerance.

[0050] Step S4: Correct the conveyor belt's tolerance key value according to the conveyor belt's fault tolerance coefficient and generate a tolerance threshold. Compare the total pressure key value of the conveying equipment on the current conveyor belt with the tolerance threshold, and determine whether to send an alarm message to the user terminal based on the comparison result.

[0051] The specific implementation is as follows:

[0052] In step S1, the material sensing start-up conveyor belt works as follows: when the conveying equipment processes the conveyor belt, the conveyor belt detects the pressure applied by the conveying equipment, the motor controlling the operation of the conveyor belt starts, and the conveyor belt performs conveying.

[0053] When material sensing starts, the conveyor belt will run according to the conveying equipment. When a large number of devices are being conveyed simultaneously on the conveyor belt, the motor controlling the conveyor belt is prone to overload, and the conveyor belt itself is also more likely to break.

[0054] By accessing the historical database, the conveyor belt's transmission information is retrieved. This information represents the average pressure the conveyor belt experiences over multiple historical time periods.

[0055] The average bearing pressure in each historical time period is merged into a bearing pressure dataset. Multiple average bearing pressures are randomly selected from the bearing pressure database as pressure benchmarks. The pressure benchmark corresponding to the median value in each pressure benchmark is selected as the bearing pressure key value of the conveyor belt.

[0056] The weight sensor detects the quality of each conveying device in real time and detects the data of each conveying device on the conveyor belt. The data is the overlapping area of ​​the contact surface between the conveying device and the conveyor belt. When calculating the quality tolerance ratio, the maximum overlapping area of ​​the conveying devices on the conveyor belt is selected as the calibration area. The ratio of the overlapping area of ​​each conveying device to the calibration area is calculated as the quality tolerance ratio of each conveying device.

[0057] The smaller the overlapping area between the contact surface of the conveying equipment and the conveyor belt, the smaller the mass tolerance ratio, the more concentrated the gravity applied to the conveyor belt according to the mass of the equipment, and the more likely the conveyor belt is to break.

[0058] It should be noted that the historical database is a database system that stores and manages past data, including the average pressure that the conveyor belt experienced during multiple past time periods. The weight sensor is a device that measures the weight of an object, and in this example, it is used to detect the equipment quality of each conveyor in real time.

[0059] In step S2, when calculating the pressure key value of each transmission device based on its equipment quality and quality tolerance ratio, correction parameters are added to further improve the accuracy of the pressure key value of the corresponding transmission device. Where m is the equipment mass of the transmission device, z is the mass tolerance ratio of the corresponding transmission device, c is the correction parameter, and Y is the pressure key value of the corresponding transmission device.

[0060] The total pressure key value is obtained by summing the pressure key values ​​of each conveying device on the current conveyor belt. The total pressure key value is then compared with the conveyor belt's bearing capacity key value. The specific steps are as follows:

[0061] If the total pressure key value of all conveying devices on the current conveyor belt exceeds the conveyor belt's bearing capacity key value, it is determined that the pressure of the conveying devices on the current conveyor belt is high, and the wear monitoring mechanism is activated; if the total pressure key value of all conveying devices on the current conveyor belt is lower than the conveyor belt's bearing capacity key value, it is determined that the pressure of the conveying devices on the current conveyor belt is low, and the conveyor belt continues to operate.

[0062] It should be noted that the wear monitoring mechanism detects the current load condition of the conveyor belt, performs a deep correction on the load key value of the transmission belt, and then compares it with the total pressure key value of each conveying device on the current conveyor belt to determine whether to send an alarm message. The correction parameters are set by professionals in this field according to the actual situation, and will not be analyzed here.

[0063] In step S3, when the wear monitoring mechanism is activated, the property data of the conveyor belt is collected to calculate the fault tolerance of the conveyor belt.

[0064] The conveyor belt's attribute data includes the uniformity of pressure distribution and the impact of motor power.

[0065] Conveyor belt pressure distribution uniformity is an indicator used to reflect whether the pressure distribution of materials on the conveyor belt is uniform. Its value ranges from 0 to 1. The closer the value is to 1, the more uniform the pressure distribution, the more stable the load state of the conveyor belt, and the greater the fault tolerance. The acquisition logic is to divide the conveyor belt equally from the midpoint to obtain a front half and a back half of the conveyor belt of the same length. The corresponding pressure sum is collected by gravity sensors and recorded as the front half pressure and the back half pressure. The pressure distribution uniformity is calculated by the absolute difference between the front half pressure and the back half pressure and the average pressure.

[0066] Specifically, the formula for calculating the uniformity of pressure distribution is expressed as follows:

[0067] ;

[0068] In the formula, For pressure distribution uniformity, This is the absolute difference between the pressure in the first half and the pressure in the second half. The average pressure of the conveyor belt, To prevent small positive numbers from being divided by zero;

[0069] It should be noted that this indicator normalizes the pressure difference to the overall pressure level, eliminating the influence of absolute pressure magnitude and accurately reflecting the relative uniformity of pressure distribution; the closer the pressures of the two parts are, the better. When it approaches zero, the uniformity A value close to 1 indicates a very uniform pressure distribution; conversely, when the pressure difference between two parts is large, the uniformity is low. A decrease indicates uneven load on the conveyor belt, which may pose a risk of localized overload.

[0070] It is understandable that, theoretically, when the pressure difference is extremely large, Substituting into the formula, we find that the pressure distribution uniformity approaches 0;

[0071] When pressure difference Exceed (For example, in the case of measurement error), the pressure distribution uniformity will be negative, which means that the sensor data is abnormal and the personnel in this experiment need to check and calibrate the sensor equipment.

[0072] Furthermore, when the pressure difference approaches 0, the pressure distribution uniformity approaches 1, indicating that the pressure is completely uniform.

[0073] The motor power impact index is a quantitative indicator used to reflect the relationship between the load condition of the conveyor belt drive system and the fault tolerance of the conveyor belt. Its acquisition logic is to install current and voltage sensors at the conveyor belt drive motor, monitor the input current and voltage of the motor in real time, and calculate the actual output power of the motor by multiplying it with the power factor of the motor. After the actual output power of the motor is obtained, the reciprocal conversion is performed as the motor power impact index.

[0074] Specifically, the formula for converting the actual output power of the motor into its reciprocal is as follows:

[0075] ;

[0076] In the formula, For indicators affecting motor power, This refers to the actual output power of the motor. To prevent extremely small positive numbers from being divided by zero;

[0077] It should be noted that the actual output power of the motor is usually inversely proportional to the current operating load of the conveyor belt. The higher the motor power, the heavier the load on the conveyor belt, and the lower the fault tolerance. Specifically, in material sensing start-up, the conveyor belt only starts when the conveying equipment is detected, and the motor power needs to be dynamically adjusted according to the weight and volume of the conveying equipment to ensure that the conveyor belt maintains a constant speed when the load changes. When the number of conveying equipment increases, the load on the conveyor belt increases, and the drive motor needs to output more power to overcome the additional resistance and friction and maintain normal operation. Therefore, the increase in motor power directly reflects the increase in the driving force on the conveyor belt, that is, the conveyor belt is subjected to greater tension and friction, thereby reducing the fault tolerance of the conveyor belt.

[0078] It is understandable that the motor power impact index is obtained by converting the actual output power of the motor inversely. The higher the power, the lower the index, indicating that the driving force load on the conveyor belt is larger and the fault tolerance is smaller. Conversely, the lower the power, the higher the index, the lighter the pressure on the conveyor belt and the higher the fault tolerance.

[0079] It should be noted that the locations of the current and voltage sensors installed at the conveyor belt drive motor were determined by the researchers based on the motor wiring structure and national electrical safety standards. The specific number and type of sensors are not limited and will not be elaborated here.

[0080] The motor power influence index is standardized so that the motor power influence index and the conveyor belt pressure distribution uniformity are kept under the same dimension, that is, the values ​​of the motor power influence index and the conveyor belt pressure distribution uniformity are kept between 0 and 1.

[0081] It should be noted that the standardization methods include, but are not limited to, standard linear transformation based on interval scaling, statistical Z-Score standardization method, or normalization method based on nonlinear mapping function. The application methods of standardization will not be elaborated here.

[0082] Furthermore, standardization is a routine operation in data preprocessing. Those skilled in the art can choose appropriate methods based on the characteristics of the dataset. In this example, the purpose of standardization (unifying units) has been clearly defined and will not affect the implementation.

[0083] The standardized motor power influence index and the conveyor belt pressure distribution uniformity are added together to calculate the fault tolerance of the conveyor belt.

[0084] The continuous runtime of the conveyor belt is obtained by calling the runtime timer.

[0085] Among them, the running time timer is an electronic timing device used to record the cumulative running time of the equipment in real time. It can accurately count the running time of the conveyor belt by collecting the start and stop signals of the drive motor of the conveyor belt or the status signals of the control system. The specific device selection is not limited and is common knowledge to those skilled in the art, so it will not be described in detail here.

[0086] The duration of continuous runtime is standardized so that the duration of continuous runtime and the fault tolerance are on the same dimension, that is, the numerical expression is between 0 and 1.

[0087] The fault tolerance coefficient of the conveyor belt is calculated by substituting the standardized continuous running time and the fault tolerance amount into the logistic regression formula. The specific formula is expressed as follows:

[0088] ;

[0089] In the formula, L is the result of logistic regression calculation, i.e., the fault tolerance coefficient of the conveyor belt, e is the natural base, and y is the linear combination term of the logistic regression model, specifically set as follows:

[0090] ;

[0091] In the formula, For bias terms, To accommodate fault tolerance, This refers to the continuous runtime after standardization. as well as These are the regression coefficients for fault tolerance and the standardized duration of operation, respectively.

[0092] Specifically, model training is a well-known machine learning technique. The manual has already given the variable definitions, fault tolerance, duration of operation, and fault tolerance coefficient. Technical personnel can train the model themselves based on publicly available data, so it will not be elaborated here.

[0093] It should be noted that a larger tolerance means a larger fault tolerance coefficient for the conveyor belt, allowing it to withstand greater loads and wear. Conversely, a longer continuous operating time indicates that the conveyor belt has experienced prolonged fatigue and wear, resulting in a smaller fault tolerance coefficient, decreased structure and performance, and reduced load-bearing capacity.

[0094] In step S4, the load-bearing key value of the conveyor belt is corrected according to the fault tolerance coefficient of the conveyor belt. The specific correction process is as follows:

[0095] The tolerance coefficient and the tolerance adjustment value are summed, and then multiplied by the tolerance key value to obtain the tolerance threshold. The specific formula is expressed as follows:

[0096] ;

[0097] In the formula, To withstand the threshold, To accommodate key values, For fault tolerance coefficient, To withstand the adjustment value;

[0098] The tolerance adjustment value was preset by the researchers based on historical operating data and historical alarm information, and will not be elaborated here.

[0099] Compare the total pressure key value of the conveying equipment on the current conveyor belt with the withstand threshold;

[0100] If the total pressure key value of the conveying equipment on the current conveyor belt exceeds the threshold, an alarm message will be generated and sent to the user terminal.

[0101] If the total pressure key value of the conveying equipment on the current conveyor belt is lower than the threshold, no alarm information will be generated, and the conveyor belt will continue to operate.

[0102] It should be noted that the alarm information is based on real-time early warning signals of abnormal conveyor belt operation status, and includes phrases such as "conveyor belt load pressure exceeds limit", "increased wear risk" or "potential equipment failure". This alarm information is sent to the user's monitoring system or mobile terminal through the Internet of Things communication module, prompting operators to take corresponding maintenance measures or stop the machine for inspection to ensure the safe and stable operation of the conveyor belt and related equipment.

[0103] Example 2: A factory equipment fault early warning system based on the Internet of Things, such as... Figure 2As shown, it includes a key value setting module, a key value comparison module, a wear monitoring module, and an evaluation alarm module, with electrical signal connections between the modules;

[0104] The functions of each module are as follows:

[0105] The key value setting module is used to call the transmission information of the conveyor belt and set the bearing key value according to the transmission information of the conveyor belt. It collects the equipment quality of each conveyor and detects the equipment data and sends it to the key value comparison module. It sends the bearing key value of the conveyor belt to the key value comparison module and the evaluation alarm module respectively.

[0106] After receiving the equipment quality and equipment data, the key value comparison module calculates the pressure key value of each conveyor, integrates the pressure key values ​​to generate the total pressure key value of the conveyor on the current conveyor belt and sends it to the evaluation and alarm module. The total pressure key value is compared with the conveyor belt's bearing key value. Based on the judgment result, it selects whether to set the wear monitoring signal and send it to the wear monitoring module.

[0107] When the wear monitoring module receives the wear detection signal, it collects the attribute data of the conveyor belt and calculates the fault tolerance of the conveyor belt. It calls the continuous running time of the conveyor belt and calculates the fault tolerance coefficient in combination with the fault tolerance to correct the fault tolerance key value of the conveyor belt and generate the fault tolerance threshold. The fault tolerance threshold is then sent to the evaluation and alarm module.

[0108] The evaluation and alarm module receives the total pressure key value of the conveying equipment on the current conveyor belt and the conveyor belt's bearing threshold, compares them, and selects whether to send alarm information to the user terminal based on the comparison result.

[0109] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0110] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0111] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and inventive constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0114] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for early warning of factory equipment faults based on the Internet of Things, characterized in that, Includes the following steps: Step S1: Call the conveyor belt transmission information, set the bearing key value according to the conveyor belt transmission information, obtain the equipment quality of each conveyor device, detect the equipment data of each conveyor device on the conveyor belt and calculate the quality fault tolerance ratio; In step S1, the conveyor belt's transmission information is the average pressure it bears over multiple historical time periods; The average bearing pressure in each historical time period is merged into a bearing pressure dataset. Multiple average bearing pressures are randomly selected from the bearing pressure database as pressure benchmarks. The pressure benchmark corresponding to the median value in each pressure benchmark is selected as the bearing pressure key value of the conveyor belt. The equipment data is the overlapping area of ​​the contact surface between the conveying equipment and the conveyor belt. When calculating the quality tolerance ratio, the maximum overlapping area of ​​the conveying equipment on the conveyor belt is selected as the calibration area, and the ratio of the overlapping area of ​​each conveying equipment to the calibration area is calculated as the quality tolerance ratio of each conveying equipment. Step S2: Calculate the pressure key value of the conveyor based on the overall equipment quality and the quality tolerance ratio, count the total pressure key value of the conveyor on the current conveyor belt and compare it with the bearing key value of the conveyor belt, and determine whether to enter the wear monitoring mechanism based on the comparison result. In step S2, the pressure key value of the transmission device is calculated by combining the equipment quality and quality tolerance ratio of each transmission device. The total pressure key value is obtained by summing the pressure key values ​​of each conveying device on the current conveyor belt. Step S3: When entering the wear monitoring mechanism, collect the attribute data of the conveyor belt and calculate the fault tolerance of the conveyor belt. Call the continuous running time of the conveyor belt and calculate the fault tolerance coefficient of the conveyor belt in combination with the fault tolerance. In step S3, when the wear monitoring mechanism is activated, the attribute data of the conveyor belt is collected. The attribute data of the conveyor belt includes the uniformity of the conveyor belt pressure distribution and the motor power influence index. The conveyor belt is divided equally from the midpoint to obtain a front half and a back half of the same length. The total pressure of each half is collected by gravity sensors and recorded as the pressure of the front half and the pressure of the back half. The pressure distribution uniformity is calculated by the absolute difference between the pressure of the front half and the pressure of the back half and the average pressure. By installing current and voltage sensors at the conveyor belt drive motor, the input current and voltage of the motor are monitored in real time. The motor's power factor is then multiplied to calculate the actual output power of the motor. After reciprocal conversion, the power output power is used as an indicator of the motor's power influence. Standardize the indicators affecting motor power; The standardized motor power influence index and the conveyor belt pressure distribution uniformity are added together to calculate the fault tolerance of the conveyor belt. The continuous runtime of the conveyor belt is obtained by calling the runtime timer. The duration of continuous operation will be standardized. The fault tolerance coefficient of the conveyor belt is calculated by substituting the standardized continuous running time and the fault tolerance amount into the logistic regression formula. Step S4: Correct the conveyor belt's tolerance key value according to the conveyor belt's fault tolerance coefficient and generate a tolerance threshold. Compare the total pressure key value of the conveying equipment on the current conveyor belt with the tolerance threshold, and determine whether to send an alarm message to the user terminal based on the comparison result.

2. The method for early warning of factory equipment faults based on the Internet of Things according to claim 1, characterized in that: In step S2, the formula for calculating the pressure key value of the conveying device is as follows: Where m is the equipment mass of the transmission device, z is the mass tolerance ratio of the corresponding transmission device, c is the correction parameter, and Y is the pressure key value of the corresponding transmission device.

3. The method for early warning of factory equipment faults based on the Internet of Things according to claim 2, characterized in that: In step S2, if the total pressure key value of all conveying devices on the current conveyor belt exceeds the conveyor belt's bearing key value, it is determined that the pressure of the conveying devices on the current conveyor belt is high, and the wear monitoring mechanism is activated; otherwise, the conveyor belt continues to operate.

4. The method for early warning of factory equipment faults based on the Internet of Things according to claim 1, characterized in that: In step S3, the formula for calculating the pressure distribution uniformity is expressed as follows: ； In the formula, For pressure distribution uniformity, This represents the absolute difference between the pressure in the first half and the pressure in the second half. The average pressure of the conveyor belt, To prevent small positive numbers from being divided by zero; The formula for converting the actual output power of the motor to its reciprocal is as follows: ； In the formula, For indicators affecting motor power, This refers to the actual output power of the motor. To prevent extremely small positive numbers from being divided by zero.

5. The method for early warning of factory equipment faults based on the Internet of Things according to claim 1, characterized in that: In step S3, the specific formula for calculating the fault tolerance coefficient of the conveyor belt is expressed as follows: ； In the formula, L is the result of logistic regression calculation, i.e., the fault tolerance coefficient of the conveyor belt, e is the natural base, and y is the linear combination term of the logistic regression model, specifically set as follows: ； In the formula, For bias terms, To accommodate fault tolerance, This refers to the continuous runtime after standardization. as well as These are the regression coefficients for the fault tolerance and the standardized duration of operation, respectively.

6. The method for early warning of factory equipment faults based on the Internet of Things according to claim 5, characterized in that: In step S4, the load-bearing key value of the conveyor belt is corrected according to the fault tolerance coefficient of the conveyor belt. The specific correction process is as follows: The tolerance coefficient and the tolerance adjustment value are summed and then multiplied with the tolerance key value to obtain the tolerance threshold. Compare the total pressure key value of the conveying equipment on the current conveyor belt with the withstand threshold; If the total pressure key value of the conveying equipment on the current conveyor belt exceeds the threshold, an alarm message will be generated and sent to the user terminal. If the total pressure key value of the conveying equipment on the current conveyor belt is lower than the withstand threshold, no alarm information will be generated, and the conveyor belt will continue to operate.

7. A factory equipment fault early warning system based on the Internet of Things (IoT), comprising the factory equipment fault early warning method based on the IoT as described in any one of claims 1-6, characterized in that, It includes a key value setting module, a key value comparison module, a wear monitoring module, and an evaluation and alarm module; The key value setting module is used to call the transmission information of the conveyor belt and set the bearing key value according to the transmission information of the conveyor belt. It collects the equipment quality of each conveyor and detects the equipment data and sends it to the key value comparison module. It sends the bearing key value of the conveyor belt to the key value comparison module and the evaluation alarm module respectively. After receiving the equipment quality and equipment data, the key value comparison module calculates the pressure key value of each conveyor, integrates the pressure key values ​​to generate the total pressure key value of the conveyor on the current conveyor belt and sends it to the evaluation and alarm module. The total pressure key value is compared with the conveyor belt's bearing key value. Based on the judgment result, it selects whether to set the wear monitoring signal and send it to the wear monitoring module. When the wear monitoring module receives the wear detection signal, it collects the attribute data of the conveyor belt and calculates the fault tolerance of the conveyor belt. It calls the continuous running time of the conveyor belt and calculates the fault tolerance coefficient in combination with the fault tolerance to correct the fault tolerance key value of the conveyor belt and generate the fault tolerance threshold. The fault tolerance threshold is then sent to the evaluation and alarm module. The evaluation and alarm module receives the total pressure key value of the conveying equipment on the current conveyor belt and the conveyor belt's bearing threshold, compares them, and selects whether to send alarm information to the user terminal based on the comparison result.

Images