A gas meter production line monitoring system based on intelligent data analysis

Abstract

The present invention relates to the field of data monitoring and analysis technology, and in particular to a gas meter production line monitoring system based on data intelligent analysis, comprising an equipment detection unit, an equipment early warning unit, an equipment maintenance unit, an equipment operation analysis unit, a production efficiency evaluation unit and a monitoring and analysis unit; the present invention calculates the fault weighted number F of the equipment by the equipment early warning unit to determine whether there is a fault, the equipment maintenance unit evaluates whether the equipment needs maintenance, the equipment early warning unit can generate a fault signal, and the equipment maintenance unit can generate a maintenance signal, and when the fault signal and the maintenance signal are generated, the operation and maintenance personnel can perform maintenance in time; the present invention monitors equipment operation data, predicts the equipment failure probability Q and the equipment maintenance parameter Di, and then evaluates the equipment operation efficiency parameter, determines whether it matches the production plan, ensures the orderly progress of production, and performs maintenance in advance according to the equipment situation.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring and analysis, and in particular to a gas meter production line monitoring system based on data intelligent analysis. Background Art

[0002] Currently, the production of gas meters relies heavily on automated generation and a high degree of data integration. Furthermore, the stable operation of equipment on the gas meter production line is closely related to whether production can be completed as planned. Therefore, timely maintenance and early warning are required for gas meter production line equipment to minimize unexpected equipment failures. Gas meter production line equipment should be maintained and troubleshooted in a timely manner. Manual inspections of equipment consume manpower and are unable to assess whether maintenance is necessary. Therefore, data analysis can provide more accurate support for managers' decision-making.

[0003] Gas meter production lines generate a large amount of production data. Analyzing this data has many benefits, such as promptly identifying and resolving production bottlenecks, thereby improving overall production efficiency; monitoring various parameters during the production process to improve production efficiency and ensure the completion of production plans; and identifying potential risks, helping companies continuously improve their production processes. However, the excessive dispersion of production data has brought many inconveniences to gas meter production line monitoring, making it difficult to provide early warnings for equipment maintenance and equipment failures, and unable to assess the impact of equipment maintenance and equipment failures on overall production efficiency and production plans. Consequently, management lacks an effective evaluation strategy to improve production levels. Therefore, a solution is proposed to address the above technical deficiencies. Summary of the Invention

[0004] The purpose of the present invention is to provide a gas meter production line monitoring system based on data intelligent analysis to solve the technical defects mentioned above. The present invention calculates the fault weighted number F of the equipment through the equipment early warning unit to determine whether there is a fault. The equipment maintenance unit evaluates whether the equipment needs maintenance. The equipment early warning unit can generate a fault signal, and the equipment maintenance unit can generate a maintenance signal. When the fault signal and maintenance signal are generated, the operation and maintenance personnel can perform maintenance in time; the present invention monitors the equipment operation data, predicts the equipment failure probability Q and the equipment maintenance parameter Di, and then evaluates the equipment operation efficiency parameter, determines whether it matches the production plan, ensures the orderly progress of production, and performs maintenance in advance according to the equipment situation.

[0005] The object of the present invention can be achieved by the following technical solutions: A gas meter production line monitoring system based on data intelligent analysis, comprising an equipment detection unit, an equipment early warning unit, an equipment maintenance unit, an equipment operation analysis unit, a production efficiency evaluation unit and a monitoring and analysis unit;

[0006] The equipment detection unit is used to collect equipment operation data and send the equipment operation data to the equipment early warning unit, equipment maintenance unit, and monitoring and analysis unit respectively; the equipment operation data includes equipment temperature Ti, equipment vibration frequency Vi, equipment operation current Ii, and speed Ri.

[0007] The equipment early warning unit is used to count the number of equipment failures P and predict the probability of equipment failure Q, and send the number of equipment failures P to the equipment operation analysis unit and the predicted probability of equipment failure Q to the equipment maintenance unit.

[0008] The equipment early warning unit receives the equipment operation data and evaluates the equipment operation data through the abnormal data evaluation model to obtain the abnormal data type; the equipment failure weight F is calculated and compared with the set threshold to obtain the number of equipment failures P; ,in is the weight parameter of the device temperature Ti, and Tn is the normalized value of the device temperature Ti; is the weight parameter of the device vibration frequency Vi, and Vn is the normalized value of the device vibration frequency Vi; is the weight parameter of the equipment operating current Ii, and In is the normalized value of the equipment operating current Ii; is the weight parameter of the speed Ri, and Rn is the normalized value of the speed Ri.

[0009] If F is less than the threshold value P1min or greater than the threshold value P1max, it is marked as a fault, and the equipment early warning unit generates a fault signal to notify the operation and maintenance personnel to perform maintenance in time; the equipment early warning unit adds one to the equipment failure count P and records it; if F is less than P2min and greater than or equal to P1min or F is greater than P2max and less than or equal to P1max, it is marked as a warning; if F is greater than or equal to P2min and less than or equal to P2max, it is marked as normal; when the equipment is marked as a warning, the logistic regression model is used to calculate the predicted equipment failure probability Q.

[0010] in, ,in is the model intercept value, , , , They are characteristic parameters of equipment temperature, equipment vibration frequency, equipment operating current, and speed.

[0011] Furthermore, the training steps of the abnormal data evaluation model include:

[0012] S1. Data marking: Mark the received device temperature Ti, device vibration frequency Vi, device operating current Ii, and speed Ri data, and divide them into normal values ​​and abnormal values. The abnormal values ​​are divided into abnormal data types according to the device operating data. The abnormal data types are temperature abnormality, vibration abnormality, current abnormality, and speed abnormality.

[0013] S2. Data preprocessing: remove missing values ​​and obviously erroneous data, and then standardize the remaining data to obtain a data set;

[0014] S3, training model: divide the data set into 80% training set and 20% test set, and use the training set data to train the SVM model;

[0015] S4. Output abnormal data type: Use the SVM model to predict the abnormal data type that the collected equipment temperature Ti, equipment vibration frequency Vi, equipment operating current Ii, and speed Ri data meet.

[0016] After the equipment early warning unit determines the abnormal data type, it starts the incremental weight θ of the equipment operation data corresponding to the abnormal data type. The weight parameter of the equipment operation data corresponding to the abnormal data type is added with the incremental weight θ. That is, if the SVM model predicts that it is a temperature anomaly, the weight parameter of the equipment temperature Ti is An incremental weight θ needs to be added as the new weight parameter for the device temperature Ti in the fault weighted number F. The weight parameters for other abnormal data types are similar. If multiple abnormal data types appear, the weight parameters of the corresponding device operation data are added with the incremental weight θ, and then the fault weighted number F is calculated.

[0017] The equipment maintenance unit is used to evaluate the equipment maintenance parameter Di and calculate the maintenance time Wi. The equipment maintenance unit sends the equipment maintenance parameter Di and maintenance time Wi to the equipment operation analysis unit. When the maintenance parameter Di is greater than or equal to the threshold Dx, the equipment maintenance unit generates a maintenance signal to notify the operation and maintenance personnel to perform maintenance in a timely manner.

[0018] When the equipment maintenance unit receives the predicted equipment failure probability Q, the equipment maintenance unit calculates the equipment maintenance parameter Di, , where RUL represents the ratio of the remaining operating time of the equipment to the theoretical operating time of the equipment. The remaining operating time is the theoretical operating time of the equipment minus the operating time of the equipment. C represents the critical parameters of the equipment. MC represents the estimated cost of equipment maintenance. ZC represents the equipment maintenance budget. It is a cost parameter; when a maintenance signal and a fault signal are generated, the operation and maintenance personnel shall promptly perform maintenance and record the maintenance time Wi in the equipment maintenance unit.

[0019] The equipment operation analysis unit is used to calculate the equipment operation efficiency parameter EREP. When EREP is less than a threshold, an equipment operation alarm report is generated. The equipment operation analysis unit sends the equipment operation efficiency parameter EREP to the production efficiency evaluation unit and the monitoring analysis unit. The equipment operation efficiency parameter EREP includes its calculation formula and various parameters and data in the formula.

[0020] Calculate the equipment operating efficiency parameter EREP, , where Ui represents the planned production time, Wi represents the maintenance time, PS represents the theoretical output, PL represents the actual output; w1 and w2 represent the adjustment coefficients.

[0021] The production efficiency evaluation unit is used to calculate the overall equipment efficiency (OEE) and send it to the monitoring and analysis unit. The overall equipment efficiency (OEE) is calculated as follows: OEE = RERP * H, where H represents the product qualification rate and H is the ratio of qualified product output to actual output.

[0022] The monitoring and analysis unit receives and stores all data from the equipment detection unit, equipment early warning unit, equipment maintenance unit, equipment operation analysis unit, and production efficiency evaluation unit; the monitoring and analysis unit receives real-time equipment operation data collected by the equipment detection unit and stores it as historical data; the monitoring and analysis unit uses support vector machine (SVM) to train an abnormal data evaluation model based on historical data, and then sends the trained abnormal data evaluation model to the equipment early warning unit; the monitoring and analysis unit compares the comprehensive equipment efficiency (OEE) with the production plan, and dynamically monitors the equipment status and production progress, and produces a gas meter production line monitoring and analysis report for management decision-making.

[0023] The beneficial effects of the present invention are as follows:

[0024] (1) The present invention collects equipment operation data during the production process and evaluates the equipment operation status by constructing a prediction model. It can evaluate the equipment failure probability and equipment maintenance parameters, and evaluate whether the equipment needs maintenance through the equipment early warning unit and equipment maintenance unit, and generate maintenance signals and fault signals. Operation and maintenance personnel can perform maintenance in a timely manner to avoid frequent equipment failures or accelerated equipment damage due to untimely maintenance, which in turn affects the normal progress of production activities;

[0025] (2) The present invention monitors equipment operation data, evaluates production efficiency based on equipment operation conditions, and provides decision support for scientific planning by management. The present invention predicts equipment failure probability Q and equipment maintenance parameters Di, and then evaluates equipment operation efficiency parameters to determine whether they match the production plan, thereby ensuring orderly production and performing maintenance in advance based on equipment conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention will be further described below with reference to the accompanying drawings;

[0027] Figure 1 It is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0029] Example 1:

[0030] The present invention is a gas meter production line monitoring system based on data intelligent analysis, which includes an equipment detection unit, an equipment early warning unit, an equipment maintenance unit, an equipment operation analysis unit, a production efficiency evaluation unit and a monitoring and analysis unit;

[0031] The equipment detection unit is used to collect equipment operation data and send the equipment operation data to the equipment early warning unit, equipment maintenance unit, and monitoring and analysis unit respectively; the equipment operation data includes equipment temperature Ti, equipment vibration frequency Vi, equipment operation current Ii, and speed Ri;

[0032] The equipment early warning unit is used to count the number of equipment failures P and predict the probability of equipment failure Q, and send the number of equipment failures P to the equipment operation analysis unit and the predicted probability of equipment failure Q to the equipment maintenance unit;

[0033] The equipment early warning unit receives the equipment operation data and evaluates the equipment operation data through the abnormal data evaluation model to obtain the abnormal data type; the equipment failure weight F is calculated and compared with the set threshold to obtain the number of equipment failures P; ,in is the weight parameter of the device temperature Ti, and Tn is the normalized value of the device temperature Ti; is the weight parameter of the device vibration frequency Vi, and Vn is the normalized value of the device vibration frequency Vi; is the weight parameter of the equipment operating current Ii, and In is the normalized value of the equipment operating current Ii; is the weight parameter of the speed Ri, Rn is the normalized value of the speed Ri; the normalization method used in this embodiment is the Min-max normalization algorithm. Take 1.35, Take 1.5, Take 1.12, Take 2.12; F is greater than 0 and less than 1.

[0034] If F is less than the threshold value P1min or greater than the threshold value P1max, it is marked as a fault, and the equipment early warning unit generates a fault signal to notify the operation and maintenance personnel to perform maintenance in time; the equipment early warning unit adds one to the number of equipment failures P and records it, which is expressed as P=P+1 in the software system for cumulative counting; if F is less than P2min and greater than or equal to P1min or F is greater than P2max and less than or equal to P1max, it is marked as a warning; if F is greater than or equal to P2min and less than or equal to P2max, it is marked as normal; in this embodiment, P1min is 0.18, P1max is 0.81, P2min is 0.32, and P2max is 0.76.

[0035] When a device is marked as a warning, the probability of device failure Q is calculated and predicted using a logistic regression model.

[0036] in, ,in is the model intercept value, , , , They are characteristic parameters of device temperature, device vibration frequency, device operating current, and speed, and their values ​​are greater than 0. In this embodiment, The value is -2. The value is 1.46, The value is 1.37, The value is 1.22, The value is 1.07.

[0037] Furthermore, the training steps of the abnormal data evaluation model include:

[0038] S1. Data marking: Mark the received device temperature Ti, device vibration frequency Vi, device operating current Ii, and speed Ri data, and divide them into normal values ​​and abnormal values. The abnormal values ​​are divided into abnormal data types according to the device operating data. The abnormal data types are temperature abnormality, vibration abnormality, current abnormality, and speed abnormality.

[0039] S2. Data preprocessing: remove missing values ​​and obviously erroneous data, and then standardize the remaining data to obtain a data set. Z-score standardization is used during standardization: convert the data into a distribution with a mean of 0 and a standard deviation of 1, using the formula , x is the original value, is the mean, is the standard deviation;

[0040] S3, training model: divide the data set into 80% training set and 20% test set, and use the training set data to train the SVM model;

[0041] S4. Output abnormal data type: Use the SVM model to predict the abnormal data type that the collected equipment temperature Ti, equipment vibration frequency Vi, equipment operating current Ii, and speed Ri data meet.

[0042] After the equipment early warning unit determines the abnormal data type, it starts the incremental weight θ of the equipment operation data corresponding to the abnormal data type. The weight parameter of the equipment operation data corresponding to the abnormal data type is added with the incremental weight θ. That is, if the SVM model predicts that it is a temperature anomaly, the weight parameter of the equipment temperature Ti is It is necessary to add an incremental weight θ as a new weight parameter for the device temperature Ti in the fault weighted number F. The weight parameters of other abnormal data types are deduced in the same way. If multiple abnormal data types appear, the weight parameters of the corresponding device operation data are added with the incremental weight θ, and then the fault weighted number F is calculated. In this embodiment, θ=0.11 is taken. For example, when the device temperature Ti and the device vibration frequency Vi are evaluated by the SVM model to meet the abnormal data type, corresponding to temperature abnormality and vibration abnormality respectively, then .

[0043] The equipment maintenance unit is used to evaluate the equipment maintenance parameter Di and calculate the maintenance time Wi. The equipment maintenance unit sends the equipment maintenance parameter Di and maintenance time Wi to the equipment operation analysis unit. When the maintenance parameter Di is greater than or equal to the threshold Dx, the equipment maintenance unit generates a maintenance signal to notify the operation and maintenance personnel to perform maintenance in a timely manner.

[0044] When the equipment maintenance unit receives the predicted equipment failure probability Q, the equipment maintenance unit calculates the equipment maintenance parameter Di, , where RUL represents the ratio of the remaining operating time of the equipment to the theoretical operating time of the equipment. The remaining operating time is the theoretical operating time of the equipment minus the operating time of the equipment. C represents the critical parameters of the equipment. MC represents the estimated cost of equipment maintenance. ZC represents the equipment maintenance budget. is a cost parameter; when a maintenance signal and a fault signal are generated, the operation and maintenance personnel shall promptly perform maintenance and record the maintenance time Wi in the equipment maintenance unit; in this embodiment, C takes a value of 3.2, The value is 0.12, and the threshold Dx value is 0.944.

[0045] The equipment operation analysis unit is used to calculate the equipment operation efficiency parameter EREP. When the EREP is less than a threshold, an equipment operation alarm report is generated. In this embodiment, the equipment operation alarm report is generated when the EREP is less than 0.5704. The equipment operation analysis unit sends the equipment operation efficiency parameter EREP to the production efficiency evaluation unit and the monitoring analysis unit.

[0046] Calculate the equipment operating efficiency parameter EREP, , where Ui represents the planned production time, Wi represents the maintenance time, PS represents the theoretical output, and PL represents the actual output; w1 and w2 represent adjustment coefficients. In this embodiment, w1 takes a value of 0.3 and w2 takes a value of 0.2.

[0047] The production efficiency evaluation unit is used to calculate the overall equipment efficiency (OEE) and send it to the monitoring and analysis unit. To calculate the overall equipment efficiency (OEE), OEE = RERP * H, where H represents the product qualification rate and H is the ratio of the qualified product output to the actual output. The qualified product output and actual output are obtained by the production workers after statistics.

[0048] The monitoring and analysis unit receives and stores all data from the equipment detection unit, equipment early warning unit, equipment maintenance unit, equipment operation analysis unit, and production efficiency evaluation unit; the monitoring and analysis unit receives real-time equipment operation data collected by the equipment detection unit and stores it as historical data; the monitoring and analysis unit uses support vector machine (SVM) to train an abnormal data evaluation model based on historical data, and then sends the trained abnormal data evaluation model to the equipment early warning unit; the monitoring and analysis unit compares the comprehensive equipment efficiency (OEE) with the production plan, and dynamically monitors the equipment status and production progress, and produces a gas meter production line monitoring and analysis report for management decision-making.

[0049] The present invention collects equipment operation data during the production process, evaluates the equipment operation status by constructing a prediction model, can evaluate the equipment failure probability and equipment maintenance parameters, and evaluates whether the equipment needs maintenance through the equipment early warning unit and equipment maintenance unit, and generates maintenance signals and fault signals. Operation and maintenance personnel can perform maintenance in a timely manner to avoid frequent equipment failures or accelerated damage to the equipment due to untimely maintenance, which in turn affects the normal progress of production activities.

[0050] Implementation 2:

[0051] The difference between this embodiment and the first embodiment is that:

[0052] When the equipment is marked as faulty, Q=1. At this time, the equipment fails and the equipment early warning unit generates a fault signal to notify the operation and maintenance personnel to perform maintenance in time. The operation and maintenance personnel record the maintenance time Wi and calculate the equipment operation efficiency parameter EREP. Then the production efficiency evaluation unit calculates the overall equipment efficiency (OEE), and the monitoring and analysis unit compares the overall equipment efficiency (OEE) with the production plan. If, after analysis, the equipment failure has a significant impact on the production plan, management needs to adjust the production plan based on the order situation and formulate a response strategy in advance.

[0053] Implementation three:

[0054] The difference between this embodiment and the first embodiment is that:

[0055] When the device is marked as normal, Q=0; at this time the device is operating normally, and the device maintenance unit calculates the device maintenance parameter Di, , calculate the equipment operation efficiency parameter EREP,

[0056] , then under the condition that the estimated cost MC of equipment maintenance is certain, improving maintenance efficiency and reducing maintenance time while complying with maintenance equipment specifications will be conducive to the smooth completion of production plans. Management can adjust equipment maintenance according to order conditions.

[0057] The data transmission between the equipment detection unit, equipment early warning unit, equipment maintenance unit, equipment operation analysis unit, production efficiency evaluation unit, and monitoring analysis unit mentioned in the present invention is carried out through wired or wireless network communication, which belongs to the existing technology and will not be repeated here.

[0058] In summary, the present invention monitors equipment operating data, evaluates production efficiency based on equipment operating conditions, and provides decision support for scientific planning by management. The present invention predicts equipment failure probability Q and equipment maintenance parameters Di, and then evaluates equipment operating efficiency parameters to determine whether they match the production plan, thereby ensuring orderly production and performing maintenance in advance based on equipment conditions.

[0059] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0060] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A gas meter production line monitoring system based on data intelligent analysis, characterized in that: It includes equipment detection unit, equipment early warning unit, equipment maintenance unit, equipment operation analysis unit, production efficiency evaluation unit and monitoring analysis unit; The equipment detection unit is used to collect equipment operation data and send the equipment operation data to the equipment early warning unit, the equipment maintenance unit, and the monitoring and analysis unit respectively; The equipment early warning unit is used to count the number of equipment failures P and predict the probability of equipment failure Q, and send the number of equipment failures P to the equipment operation analysis unit and the predicted probability of equipment failure Q to the equipment maintenance unit; The equipment maintenance unit is used to evaluate the equipment maintenance parameter Di and calculate the maintenance time Wi. The equipment maintenance unit sends the equipment maintenance parameter Di and the maintenance time Wi to the equipment operation analysis unit; when the maintenance parameter Di is greater than or equal to the threshold Dx, the equipment maintenance unit generates a maintenance signal to notify the operation and maintenance personnel to perform maintenance in a timely manner; The equipment operation analysis unit is used to calculate the equipment operation efficiency parameter EREP, and when the EREP is less than a threshold, an equipment operation alarm report is generated; the equipment operation analysis unit sends the equipment operation efficiency parameter EREP to the production efficiency evaluation unit and the monitoring analysis unit; The production efficiency evaluation unit is used to calculate the comprehensive equipment efficiency (OEE) and send the OEE to the monitoring and analysis unit; the comprehensive equipment efficiency (OEE) is calculated as follows: OEE = RERP * H, where H represents the product qualification rate and H is the ratio of the qualified product output to the actual output; The monitoring and analysis unit receives and stores all data from the equipment detection unit, equipment early warning unit, equipment maintenance unit, equipment operation analysis unit, and production efficiency evaluation unit. The monitoring and analysis unit compares the overall equipment efficiency (OEE) with the production plan, dynamically monitors equipment status and production progress, and produces a gas meter production line monitoring and analysis report for management decision-making. The equipment detection unit collects equipment operation data, including equipment temperature Ti, equipment vibration frequency Vi, equipment operation current Ii, and rotation speed Ri; the monitoring and analysis unit receives the real-time equipment operation data collected by the equipment detection unit and stores it as historical data; the monitoring and analysis unit uses a support vector machine (SVM) to train an abnormal data evaluation model based on the historical data, and then sends the trained abnormal data evaluation model to the equipment early warning unit.

2. A gas meter production line monitoring system based on data intelligent analysis according to claim 1, characterized in that: The equipment early warning unit receives equipment operation data and evaluates the equipment operation data through the abnormal data evaluation model to obtain the abnormal data type; the equipment failure weight F is calculated and compared with the set threshold to obtain the number of equipment failures P; ,in is the weight parameter of the device temperature Ti, and Tn is the normalized value of the device temperature Ti; is the weight parameter of the device vibration frequency Vi, and Vn is the normalized value of the device vibration frequency Vi; is the weight parameter of the equipment operating current Ii, and In is the normalized value of the equipment operating current Ii; is the weight parameter of the speed Ri, and Rn is the normalized value of the speed Ri.

3. A gas meter production line monitoring system based on data intelligent analysis according to claim 2, characterized in that: If F is less than the threshold value P1min or greater than the threshold value P1max, it is marked as a fault. The equipment early warning unit generates a fault signal and notifies the operation and maintenance personnel to perform maintenance in time. The equipment early warning unit increases the number of equipment failures P by one and records it. If F is less than P2min and greater than or equal to P1min, or F is greater than P2max and less than or equal to P1max, it is marked as a warning. If F is greater than or equal to P2min and less than or equal to P2max, it is marked as normal; When a device is marked as a warning, the probability of device failure Q is calculated and predicted using a logistic regression model. ,in is the model intercept value, , , , They are characteristic parameters of equipment temperature, equipment vibration frequency, equipment operating current, and speed.

4. A gas meter production line monitoring system based on data intelligent analysis according to claim 3, characterized in that: When the equipment maintenance unit receives the predicted equipment failure probability Q, the equipment maintenance unit calculates the equipment maintenance parameter Di, , where RUL represents the ratio of the remaining operating time of the equipment to the theoretical operating time of the equipment. The remaining operating time is the theoretical operating time of the equipment minus the operating time of the equipment. C represents the critical parameters of the equipment. MC represents the estimated cost of equipment maintenance. ZC represents the equipment maintenance budget. It is a cost parameter; when a maintenance signal and a fault signal are generated, the operation and maintenance personnel shall promptly perform maintenance and record the maintenance time Wi in the equipment maintenance unit.

5. A gas meter production line monitoring system based on data intelligent analysis according to claim 4, characterized in that: Calculate the equipment operating efficiency parameter EREP, , where Ui represents the planned production time, Wi represents the maintenance time, PS represents the theoretical output, PL represents the actual output; w1 and w2 represent the adjustment coefficients.

6. A gas meter production line monitoring system based on data intelligent analysis according to claim 2, characterized in that: The training steps of the abnormal data evaluation model include: S1. Data marking: Mark the received device temperature Ti, device vibration frequency Vi, device operating current Ii, and speed Ri data, and divide them into normal values ​​and abnormal values. The abnormal values ​​are divided into abnormal data types according to the device operating data. The abnormal data types are temperature abnormality, vibration abnormality, current abnormality, and speed abnormality. S2. Data preprocessing: remove missing values ​​and obviously erroneous data, and then standardize the remaining data to obtain a data set; S3, training model: divide the data set into 80% training set and 20% test set, and use the training set data to train the SVM model; S4. Output abnormal data type: Use the SVM model to predict the abnormal data type that the collected equipment temperature Ti, equipment vibration frequency Vi, equipment operating current Ii, and speed Ri data meet.

7. A gas meter production line monitoring system based on data intelligent analysis according to claim 6, characterized in that: After determining the abnormal data type, the equipment early warning unit starts the incremental weight θ of the equipment operation data corresponding to the abnormal data type, and the weight parameter of the equipment operation data corresponding to the abnormal data type is added with the incremental weight θ.

Images