A method and system for monitoring the operating status of intelligent equipment in enterprise production

Abstract

The present invention relates to the technical field of production monitoring, and specifically discloses a method and system for monitoring the operation status of enterprise production intelligent equipment, including: dividing the product production process into multiple stages, obtaining the number of defective products in each stage within the monitoring period, calculating the stage deviation ratio and the stage defective rate, and further calculating the equipment status value; obtaining the equipment status values in different monitoring periods, calculating the status abnormality ratio, drawing the cycle-status abnormality ratio change curve and calculating the linear reference value, and comparing it with the linear reference threshold to determine the type of curve change. If the curve is non-linearly changing, obtaining the equipment maintenance deviation ratio, drawing the cycle-equipment status value and cycle-maintenance deviation ratio change curves, calculating the correlation degree and comparing it with the threshold to decide whether to repair the equipment. The present invention helps to timely master the operation status of the equipment and improve production efficiency and product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of production monitoring, and particularly to a method and system for monitoring the operating status of intelligent production equipment in enterprises. Background Art

[0002] In modern enterprise production, the wide application of intelligent production equipment has greatly improved production efficiency and product quality, but the monitoring and management of equipment operating status also face many challenges.

[0003] In the prior art, the monitoring technology has insufficient ability to predict and analyze equipment failures. Usually, maintenance is carried out only after obvious equipment failures occur, lacking foresight. This way of after-the-fact maintenance will not only affect the production progress, resulting in delayed product delivery, but also may cause a large number of defective products due to sudden equipment failures, increasing production costs and reducing the economic benefits of enterprises. Moreover, during the maintenance process, due to the lack of effective analysis of the historical operation data of the equipment, it is often difficult for maintenance personnel to quickly and accurately locate the cause of the failure, affecting production efficiency.

[0004] By obtaining the number of defective products in multiple stages of the production process, calculating the equipment status value Zt, the abnormal stage ratio, the deviation mean ratio, and the status abnormal ratio, and drawing the cycle-status abnormal ratio change curve, deeply exploring the change trend of the equipment operating status can comprehensively and accurately evaluate the operating status of the equipment in each production stage. This method of comprehensive multi-index analysis can more timely detect abnormal situations in equipment operation, early warning of potential problems, avoid sudden occurrence of equipment failures, thus ensuring the continuity of production and reducing the defective rate. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for monitoring the operating status of intelligent production equipment in enterprises to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method and system for monitoring the operating status of intelligent production equipment in enterprises, including:

[0008] Obtain the production process of the products manufactured by the intelligent production equipment, divide the production process into multiple stages to obtain production stages, and obtain the number of defective products in each production stage;

[0009] Based on the number of defective products in each stage, obtain the target range of defective products in each stage, calculate the stage deviation ratio Pc, the stage defective rate Cp, and calculate the equipment status value Zt. If the equipment status value Zt < the equipment status threshold, generate a status analysis signal;

[0010] Mark the production stage that generates the status analysis signal as the production abnormal stage, calculate the abnormal stage ratio, calculate the deviation mean ratio of the equipment status value Zt and the equipment status threshold, calculate the ratio of the deviation mean ratio to the abnormal stage ratio to obtain the status abnormal ratio, obtain the status abnormal ratios of different monitoring periods, plot the change curve of the period-status abnormal ratio, calculate the linear reference value Ck through the change curve, and compare it with the linear reference threshold. If the change curve is non-linear, generate a trend analysis signal;

[0011] Based on the trend analysis signal, calculate the maintenance deviation ratio of the production equipment in the production abnormal stage, obtain the equipment status value Zt and the maintenance deviation ratio within different monitoring periods, plot the corresponding change curves in the same coordinate system, obtain the cycle time when the curve convex peaks coincide, calculate the coincidence time ratio Sj and the average number of coincidence times Jz, and calculate the correlation degree Gl. Compare the correlation degree Gl with the correlation degree threshold. If the correlation degree GI exceeds the threshold, it is necessary to stop production and repair the production intelligent equipment.

[0012] As a further solution of the present invention: The obtaining method of the equipment status value Zt is:

[0013] Based on the stage deviation ratio Pc and the stage defective rate Cp, calculate the equipment status value Zt;

[0014] Through the formula: , calculate the equipment status value Zt, where a1 and a2 are preset proportional coefficients.

[0015] As a further solution of the present invention: The obtaining method of the stage deviation ratio Pc is:

[0016] Based on the number of defective products in each production stage, obtain the defective product target range of each stage;

[0017] Subtract the number of defective products in each production stage from the two end values of the defective product target range of each stage and take the absolute value. Mark the minimum value obtained as the stage defective product difference;

[0018] Ratio the stage defective product difference to the length of the defective product target range to obtain the stage deviation ratio, and mark the stage deviation ratio as Pc;

[0019] The obtaining method of the stage defective rate Cp is:

[0020] Obtain the total number of products manufactured in each production stage within the monitoring period, ratio the number of defective products to the total number of products to obtain the stage defective rate, and mark the stage defective rate as Cp.

[0021] As a further solution of the present invention: The obtaining method of the linear reference value Ck is:

[0022] Calculate the linear reference value Ck of the change curve of the period-state anomaly ratio based on the linear threshold ratio Xb and the linear variance Xf;

[0023] Through the formula: , the linear reference value Ck is calculated, where ln(b1*Xb + b2*Cf + 1.112) is the logarithmic function with base e, and b1, b2 are preset proportional coefficients.

[0024] As a further solution of the present invention: The acquisition method of the linear variance Xf is:

[0025] Put the linear parameter differences of all sub-curve segments as elements into a data group, calculate the variance of the elements in the data group to obtain the linear variance, and mark the linear variance as Xf;

[0026] The acquisition method of the linear threshold ratio Xb is:

[0027] Obtain the linear parameter differences of all sub-curve segments, sum and average the linear parameter differences of all sub-curve segments to obtain the linear difference mean value;

[0028] Perform a difference operation on the linear difference mean value and the linear difference threshold to obtain the linear threshold difference, perform a ratio operation on the linear threshold difference and the linear difference threshold to obtain the linear threshold ratio, and mark the linear threshold ratio as Xb.

[0029] As a further solution of the present invention: The acquisition method of the linear stagger is:

[0030] Obtain the state anomaly ratios of different monitoring periods, and draw the change curve of the period-state anomaly ratio in a two-dimensional rectangular coordinate system;

[0031] Connect the two endpoints of the change curve of the period-state anomaly ratio to obtain a linear reference line, and divide the change curve into multiple curve segments to obtain sub-curve segments;

[0032] Obtain the state anomaly ratios of the sub-curve segments, sum and average the state anomaly ratios of the sub-curve segments to obtain the curve segment anomaly mean value;

[0033] Draw a straight line parallel to the Y-axis with the curve segment anomaly mean value, and obtain the state anomaly ratio corresponding to the intersection point of the straight line and the linear reference line;

[0034] Perform a difference and absolute value operation on the curve segment anomaly mean value and the state anomaly ratio to obtain the linear parameter difference.

[0035] As a further solution of the present invention: The acquisition method of the state anomaly ratio is;

[0036] Mark the production stage that generates the status analysis signal as the production abnormal stage, obtain the number of production abnormal stages, sum up the numbers of all production abnormal stages to obtain the total number of abnormal stages;

[0037] Obtain the number of all production stages, and perform a ratio process on the total number of abnormal stages and the number of all production stages to obtain the abnormal stage ratio;

[0038] Take the difference between the device status value Zt and the device status threshold and take the absolute value to obtain the status numerical difference;

[0039] Perform a ratio process on the status numerical difference and the device status threshold to obtain the status deviation ratio;

[0040] Obtain the status deviation ratios of all production abnormal stages, and perform a sum and average process on the status deviation ratios to obtain the average deviation ratio;

[0041] Perform a ratio process on the average deviation ratio and the abnormal stage ratio to obtain the status abnormality ratio.

[0042] As a further solution of the present invention: The acquisition method of the correlation degree GI is as follows:

[0043] Based on the coincidence time ratio Sj and the average number of coincidence times Jz, calculate the correlation degree Gl;

[0044] Through the formula: , calculate to obtain the correlation degree GI.

[0045] As a further solution of the present invention: The acquisition methods of the coincidence time ratio Sj and the average number of coincidence times Jz are as follows:

[0046] Obtain the number of device maintenance times in the production abnormal stage, take the difference between the number of device maintenance times and the target number of maintenance times to obtain the maintenance times difference;

[0047] Perform a ratio process on the maintenance times difference and the target number of maintenance times to obtain the maintenance deviation ratio;

[0048] It should be noted that the maintenance deviation ratio reflects the deviation degree between the actual maintenance situation of the device in the production abnormal stage and the expected maintenance target;

[0049] Obtain the device status value Zt and the maintenance deviation ratio of each production abnormal stage in different monitoring periods, and draw the cycle-device status value Zt change curve and the cycle-maintenance deviation ratio change curve in the same two-dimensional rectangular coordinate system;

[0050] Obtain the cycle time when the cycle-device status value Zt change curve and the cycle-maintenance deviation ratio change curve have convex peak coincidences to obtain the coincidence duration;

[0051] Obtain the overlapping duration of all monitoring cycles to get the total overlapping time. Process the ratio of the total overlapping time to the duration of all monitoring cycles to obtain the overlapping time ratio, and mark the overlapping time ratio as Sj.

[0052] Obtain the number of times of overlapping duration. Sum up and take the average of the number of times of overlapping duration of all monitoring cycles to obtain the average number of overlapping times, and mark the average number of overlapping times as Jz.

[0053] An intelligent operation state monitoring system for enterprise production equipment includes:

[0054] Parameter acquisition module: Obtain the production process of the products manufactured by the production intelligent equipment, divide the production process into multiple stages to obtain production stages, and obtain the number of defective products in each production stage.

[0055] State analysis module: Based on the number of defective products in each stage, obtain the target range of defective products in each stage, calculate the stage deviation ratio Pc and the stage defective product rate Cp, and calculate the equipment state value Zt. If the equipment state value Zt < the equipment state threshold, generate a state analysis signal.

[0056] Trend judgment module: Based on the state analysis signal, mark the production stage where the state analysis signal is generated as the production abnormal stage, calculate the abnormal stage ratio, calculate the deviation mean ratio by calculating the equipment state value Zt and the equipment state threshold, calculate the state abnormal ratio by calculating the deviation mean ratio and the abnormal stage ratio, obtain the state abnormal ratio of different monitoring cycles, draw the change curve of the cycle - state abnormal ratio, calculate the linear reference value Ck through the change curve, and compare it with the linear reference threshold. If the change curve is non-linear, generate a trend analysis signal.

[0057] Correlation analysis module: Based on the trend analysis signal, calculate the maintenance deviation ratio of the production equipment in the production abnormal stage, obtain the equipment state value Zt and the maintenance deviation ratio in the production abnormal stage within different monitoring cycles, draw the corresponding change curves in the same coordinate system, obtain the cycle time when the curve peaks coincide, calculate the overlapping time ratio Sj and the average number of overlapping times Jz, and calculate the correlation degree Gl. Compare the correlation degree Gl with the correlation degree threshold. If the correlation degree GI exceeds the threshold, it is necessary to stop production and repair the production intelligent equipment.

[0058] The beneficial effects of the present invention:

[0059] (1) By dividing the production process into multiple stages and comprehensively considering multiple key indicators such as the number of defective products, the stage deviation ratio Pc, the stage defective rate Cp, and the equipment status value Zt in each stage, the comprehensive and accurate monitoring of the operation status of intelligent production equipment is achieved. This multi-dimensional analysis method can timely detect subtle anomalies in equipment operation and early warn potential problems before equipment failures occur. If a certain key component of the equipment just starts to show wear and has not caused a serious failure, the changes in the stage deviation ratio Pc and the stage defective rate Cp can be used to detect it in time, giving the enterprise enough time to arrange equipment maintenance and avoid production interruption caused by sudden equipment shutdown.

[0060] (2) In the production abnormal stage, by obtaining the equipment maintenance deviation ratio and conducting correlation analysis with the equipment status value Zt, calculating the coincidence time Sj, the average number of coincidence times Jz, and the correlation degree Gl, it provides a scientific basis for equipment maintenance decision-making. When the correlation degree GI exceeds the threshold, it can accurately locate the close relationship between equipment failures and maintenance conditions, prompting the enterprise to stop the production process in time for targeted maintenance and avoiding the waste of time and resources caused by blind maintenance. Brief Description of the Drawings

[0061] The present invention will be further described below with reference to the accompanying drawings.

[0062] Figure 1 is a flowchart of a method for monitoring the operation status of intelligent production equipment of an enterprise according to the present invention;

[0063] Figure 2 is a module diagram of a system for monitoring the operation status of intelligent production equipment of an enterprise in the present invention. Detailed Embodiments

[0064] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0065] Embodiment 1, please refer to Figure 1 As shown, the present invention is a method for monitoring the operation status of intelligent production equipment of an enterprise, including:

[0066] Step 1: Obtain the production process of the products manufactured by the intelligent production equipment, divide the production process into multiple stages to obtain production stages, and obtain the number of defective products in each production stage;

[0067] Obtain the production process of the products manufactured by the intelligent production equipment of the enterprise, and divide the production process into multiple stages to obtain production stages;

[0068] Using an infrared sensor and a counting sensor, obtain the number of unqualified products in each production stage within the monitoring period to obtain the number of defective products.

[0069] In some embodiments, use an infrared sensor to obtain a product image and compare it with a target image to classify the products into qualified products and unqualified products.

[0070] Step 2: Based on the number of defective products in each stage, obtain the defective product target range for each stage, calculate the stage deviation ratio Pc and the stage defective rate Cp, and calculate the equipment status value Zt. If the equipment status value Zt < the equipment status threshold, generate a status analysis signal.

[0071] Based on the number of defective products in each production stage, obtain the defective product target range for each stage.

[0072] Subtract the number of defective products in each production stage from the two endpoint values of the defective product target range for each stage and take the absolute value. Mark the minimum value obtained as the stage defective product difference.

[0073] Divide the stage defective product difference by the length of the defective product target range to obtain the stage deviation ratio, and mark the stage deviation ratio as Pc.

[0074] Obtain the total number of products manufactured in each production stage within the monitoring period. Divide the number of defective products by the total number of products to obtain the stage defective rate, and mark the stage defective rate as Cp.

[0075] Based on the stage deviation ratio Pc and the stage defective rate Cp, calculate the equipment status value Zt.

[0076] Through the formula: , calculate the equipment status value Zt, where a1 and a2 are preset proportionality coefficients.

[0077] Compare the equipment status value Zt with the equipment status threshold.

[0078] If the equipment status value Zt ≥ the equipment status threshold, it indicates that within the current monitoring period, the equipment status value Zt of the production intelligent equipment is within the target expectation. Since the operating state of the equipment may change at any time, it is still necessary to continuously monitor the change of the production deviation value Cp in each production stage.

[0079] If the equipment status value Zt < the equipment status threshold, it indicates that the equipment status value Zt of the current production stage is lower than expected. Generate a status analysis signal to further analyze the production process.

[0080] It should be noted that when the device status value Zt is lower than the expected production stage and the stage defective rate Cp or the stage deviation ratio Pc of the device is relatively high, it indicates that potential problems may occur in the operating status of the device, resulting in the device status value Zt being lower than expected;

[0081] The technical solution of this embodiment is as follows: Obtain the production process of the products manufactured by the production intelligent device, divide the production process into multiple stages to obtain the production stages, obtain the number of defective products in each production stage, based on the number of defective products in each stage, obtain the target range of defective products in each stage, calculate the stage deviation ratio Pc and the stage defective rate Cp, and calculate the device status value Zt. If the device status value Zt < the device status threshold, generate a status analysis signal.

[0082] Embodiment 2, based on Embodiment 1, a method for monitoring the operating status of an enterprise production intelligent device further includes:

[0083] Step 3: Based on the status analysis signal, mark the production stage that generates the status analysis signal as the production abnormal stage, calculate the abnormal stage ratio, calculate the deviation mean ratio by calculating the device status value Zt and the device status threshold, calculate the deviation mean ratio and the abnormal stage ratio to obtain the status abnormal ratio, obtain the status abnormal ratios of different monitoring periods, draw the change curve of the period - status abnormal ratio, calculate the linear reference value Ck through the change curve, and divide the change curve into linear change and non - linear change by comparing with the linear reference threshold. For the non - linear change curve, generate a trend analysis signal;

[0084] Mark the production stage that generates the status analysis signal as the production abnormal stage, obtain the number of production abnormal stages, and perform a summation process on the number of all production abnormal stages to obtain the total abnormal stage;

[0085] Obtain the number of all production stages, and perform a ratio process on the total abnormal stage and the number of all production stages to obtain the abnormal stage ratio;

[0086] Take the absolute value of the difference between the device status value Zt and the device status threshold to obtain the status numerical difference;

[0087] Perform a ratio process on the status numerical difference and the device status threshold to obtain the status deviation ratio;

[0088] Obtain the status deviation ratios of all production abnormal stages, and perform a summation mean process on the status deviation ratios to obtain the deviation mean ratio;

[0089] Perform a ratio process on the deviation mean ratio and the abnormal stage ratio to obtain the status abnormal ratio;

[0090] Obtain the status anomaly ratios for different monitoring periods. Using the X-axis within the monitoring period and the status anomaly ratio as the Y-axis, plot the change curve of the period-status anomaly ratio in a two-dimensional rectangular coordinate system;

[0091] Connect the two endpoints of the change curve of the period-status anomaly ratio to obtain a linear reference line, and divide the change curve into multiple curve segments to obtain sub-curve segments;

[0092] Obtain the status anomaly ratios of the sub-curve segments, perform a sum and mean processing on the status anomaly ratios of the sub-curve segments to obtain the curve segment anomaly mean;

[0093] Draw a straight line parallel to the Y-axis using the curve segment anomaly mean, and obtain the status anomaly ratio corresponding to the intersection point of the straight line and the linear reference line;

[0094] Take the absolute value of the difference between the curve segment anomaly mean and the status anomaly ratio to obtain the linear parameter difference;

[0095] Obtain the linear parameter differences of all sub-curve segments, perform a sum and mean processing on the linear parameter differences of all sub-curve segments to obtain the linear difference mean;

[0096] Perform a difference processing on the linear difference mean and the linear difference threshold to obtain the linear threshold difference, perform a ratio processing on the linear threshold difference and the linear difference threshold to obtain the linear threshold ratio, and label the linear threshold ratio as Xb;

[0097] It should be noted that the linear difference threshold is set by professionals in this field based on experience;

[0098] Put the linear parameter differences of all sub-curve segments as elements into a data group, calculate the variance of the elements in the data group to obtain the linear variance, and label the linear variance as Xf;

[0099] Based on the linear threshold ratio Xb and the linear variance Xf, calculate the linear reference value Ck of the change curve of the period-status anomaly ratio;

[0100] Through the formula: , calculate to obtain the linear reference value Ck, where ln(b1*Xb + b2*Cf + 1.112) is the natural logarithm function with base e, and b1, b2 are preset proportionality coefficients;

[0101] Compare the linear reference value Ck with the linear reference threshold;

[0102] If the linear reference value Ck ≥ the linear reference threshold, use the least squares method to fit the period-status anomaly ratio to obtain a fitting straight line, and calculate the slope of the fitting straight line;

[0103] If the slope of the fitting line is greater than 0, it indicates that the curve of the cycle - state anomaly ratio change is linearly increasing, and the production process needs to be stopped for maintenance and repair of the intelligent production equipment;

[0104] If the linear reference value Ck < the linear reference threshold, it indicates that the curve of the cycle - state anomaly ratio change is non - linear, and a trend analysis signal is generated;

[0105] It should be noted that when the slope of the fitting line is greater than 0, as the monitoring cycle increases, the state anomaly ratio gradually increases in a linear trend, indicating that the operating state of the intelligent production equipment is gradually deteriorating. The production process needs to be stopped for maintenance of the intelligent production equipment. For the non - linear trend curve of the cycle - state anomaly ratio change, a trend analysis signal is generated for further analysis of the intelligent production equipment;

[0106] Step 4: Based on the trend analysis signal, calculate the maintenance deviation ratio of the production equipment during the production anomaly stage, obtain the equipment state value Zt and the maintenance deviation ratio during the production anomaly stage for different monitoring cycles, draw the corresponding change curves in the same coordinate system, obtain the cycle time when the convex peaks of the curves coincide, calculate the coincidence time ratio Sj, the average number of coincidence times Jz, and calculate the correlation degree Gl. Compare the correlation degree Gl with the correlation degree threshold. If the correlation degree GI exceeds the threshold, the production needs to be stopped and the intelligent production equipment needs to be repaired;

[0107] Obtain the number of equipment maintenance times during the production anomaly stage, subtract the number of equipment maintenance times from the target number of maintenance times to get the difference in maintenance times;

[0108] Divide the difference in maintenance times by the target number of maintenance times to get the maintenance deviation ratio;

[0109] It should be noted that the maintenance deviation ratio reflects the deviation degree between the actual maintenance situation of the equipment during the production anomaly stage and the expected maintenance target;

[0110] Obtain the equipment state value Zt and the maintenance deviation ratio for each production anomaly stage during different monitoring cycles, and draw the cycle - equipment state value Zt change curve and the cycle - maintenance deviation ratio change curve in the same two - dimensional rectangular coordinate system;

[0111] Obtain the cycle time when the convex peaks of the cycle - equipment state value Zt change curve and the cycle - maintenance deviation ratio change curve coincide to get the coincidence duration;

[0112] Obtain the total coincidence duration of all monitoring cycles to get the total coincidence time, divide the total coincidence time by the duration of all monitoring cycles to get the coincidence time ratio, and mark the coincidence time ratio as Sj;

[0113] Obtain the number of overlapping durations, sum up the number of overlapping durations for all monitoring periods and take the average to obtain the average number of overlaps, and mark the average number of overlaps as Jz;

[0114] Based on the overlap time ratio Sj and the average number of overlaps Jz, calculate the correlation degree Gl;

[0115] Through the formula: , calculate the correlation degree GI;

[0116] Compare the correlation degree GI with the correlation threshold;

[0117] If the correlation degree GI in the current production abnormal stage exceeds the correlation threshold, it indicates that the equipment state value Zt in the production abnormal stage of the production intelligent equipment has a relatively large correlation degree with the maintenance deviation ratio, and it is necessary to stop the production process currently and perform maintenance on the production intelligent equipment;

[0118] If the correlation degree GI in the current production abnormal stage is within the correlation threshold, it is still necessary to continuously monitor the change of the correlation degree GI;

[0119] Example 3, as Figure 2 shown, an operation status monitoring system for enterprise production intelligent equipment further includes:

[0120] Parameter acquisition module: Obtain the production process of the products manufactured by the production intelligent equipment, divide the production process into multiple stages to obtain production stages, and obtain the number of defective products in each production stage;

[0121] Status analysis module: Based on the number of defective products in each stage, obtain the target range of defective products in each stage, calculate the stage deviation ratio Pc, the stage defective product rate Cp, and calculate the equipment state value Zt. If the equipment state value Zt < the equipment state threshold, generate a status analysis signal;

[0122] Trend judgment module: Based on the status analysis signal, mark the production stage that generates the status analysis signal as the production abnormal stage, calculate the abnormal stage ratio, calculate the deviation average ratio by calculating the equipment state value Zt and the equipment state threshold, calculate the status abnormal ratio by calculating the deviation average ratio and the abnormal stage ratio, obtain the status abnormal ratio of different monitoring periods, draw the change curve of the cycle - status abnormal ratio, calculate the linear reference value Ck through the change curve, and compare it with the linear reference threshold. If the change curve is non - linear, generate a trend analysis signal;

[0123] Association analysis module: Based on the trend analysis signal, calculate the maintenance deviation ratio of production equipment during the production anomaly stage, obtain the equipment status value Zt and the maintenance deviation ratio during the production anomaly stage within different monitoring cycles, draw the corresponding change curves in the same coordinate system, obtain the cycle time when the convex peaks of the curves coincide, calculate the coincidence time ratio Sj and the average number of coincidences Jz, and calculate the correlation degree Gl. Compare the correlation degree Gl with the correlation degree threshold. If the correlation degree GI exceeds the threshold, it is necessary to stop production and repair the production intelligent equipment.

[0124] The above has described an embodiment of the present invention in detail, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made in accordance with the scope of the application of the present invention should still fall within the scope covered by the present invention.

Claims

1. A method for monitoring the operating status of intelligent equipment in an enterprise, characterized in that: include: Obtain the production process of products manufactured by intelligent production equipment, divide the production process into multiple stages, obtain the production stages, and obtain the number of defective products in each production stage; Based on the number of defective products in each stage, the defective target range of each stage is obtained, the stage deviation ratio Pc and the stage defective rate Cp are calculated, and the equipment state value Zt is calculated. If the equipment state value Zt is less than the equipment state threshold, a state analysis signal is generated; The device status value Zt is obtained as follows: Calculate the equipment status value Zt based on the stage deviation ratio Pc and the stage defective rate Cp; By formula: , calculate the device state value Zt, where a1 and a2 are preset proportional coefficients; The production stage that generates the state analysis signal is marked as the production abnormality stage, and the abnormal stage ratio is calculated. The deviation mean ratio of the equipment state value Zt and the equipment state threshold is calculated, and the deviation mean ratio is calculated with the abnormal stage ratio to obtain the state abnormality ratio. The state abnormality ratio of different monitoring periods is obtained, and the change curve of the cycle-state abnormality ratio is drawn. The linear reference value Ck is calculated through the change curve. If the linear reference value Ck is less than the linear reference threshold, the change curve is a nonlinear change, and a trend analysis signal is generated; The linear reference value Ck is obtained as follows: Based on the linear threshold ratio Xb and the linear variance Xf, a linear reference value Ck of the change curve of the cycle-state abnormality ratio is calculated; By formula: , calculate the linear reference value Ck, where b1 and b2 are preset proportional coefficients; Based on the trend analysis signal, calculate the maintenance deviation ratio of production equipment in the abnormal production stage, obtain the equipment status value Zt and maintenance deviation ratio in different monitoring cycles, draw the corresponding change curve in the same coordinate system, obtain the cycle time of the curve peak overlap, calculate the overlap time ratio Sj, the average number of overlaps Jz, and calculate the correlation Gl. Compare the correlation Gl with the correlation threshold. If the correlation GI exceeds the threshold, it is necessary to stop production and overhaul the production intelligent equipment; The method for obtaining the correlation index GI is as follows: Based on the overlap time ratio Sj and the average overlap times Jz, the correlation degree Gl is calculated; By formula: , calculate the association index GI.

2. The method for monitoring the operation status of enterprise production intelligent equipment according to claim 1, characterized in that: The stage deviation ratio Pc is obtained as follows: Based on the number of defective products at each production stage, obtain the target range of defective products at each stage; Subtract the number of defective products in each production stage from the two endpoints of the defective product target range in each stage and take the absolute value, and mark the minimum value obtained as the stage defective product difference; The stage defective difference is processed by ratio with the length of the defective target range to obtain the stage deviation ratio, which is marked as Pc; The method for obtaining the defective rate Cp in the above stage is: Obtain the total number of products manufactured in each production stage during the monitoring period, and calculate the ratio of the number of defective products to the total number of products to obtain the stage defective rate, which is marked as Cp.

3. The method for monitoring the operation status of enterprise production intelligent equipment according to claim 1, characterized in that: The linear variance Xf is obtained as follows: Put the linear parameter differences of all sub-curve segments into the data set as elements, calculate the variance of the elements in the data set, obtain the linear variance, and mark the linear variance as Xf; The linear threshold ratio Xb is obtained as follows: Obtain the linear parameter differences of all sub-curve segments, sum and average the linear parameter differences of all sub-curve segments, and obtain the linear difference mean; The linear difference mean is processed with the linear difference threshold to obtain the linear threshold difference, and the linear threshold difference is processed with the linear difference threshold to obtain the linear threshold ratio, which is marked as Xb.

4. The method for monitoring the operation status of enterprise production intelligent equipment according to claim 3, characterized in that: The linear parameter difference is obtained as follows: Obtain the state anomaly ratios of different monitoring periods, and draw a change curve of the period-state anomaly ratio in a two-dimensional rectangular coordinate system; Connect the two end points of the change curve of the cycle-state anomaly ratio to obtain a linear reference line, and divide the change curve into multiple curve segments to obtain sub-curve segments; Obtain the state anomaly ratio of the sub-curve segment, perform summation and mean processing on the state anomaly ratio of the sub-curve segment, and obtain the curve segment anomaly mean; Draw a straight line parallel to the Y axis with the curve anomaly mean, and obtain the state anomaly ratio corresponding to the intersection of the straight line and the linear reference line; The difference between the segment anomaly mean and the state anomaly ratio is taken and the absolute value is taken to obtain the linear parameter difference.

5. The method for monitoring the operation status of intelligent production equipment in an enterprise according to claim 4, characterized in that: The state abnormality ratio is obtained in the following manner: Marking the production stage that generates the status analysis signal as the production abnormality stage, obtaining the number of the production abnormality stages, and summing up the numbers of all the production abnormality stages to obtain the total number of abnormal stages; The number of all production stages is obtained, and the ratio of the sum of abnormal stages to the number of all production stages is processed to obtain the abnormal stage ratio; The device state value Zt is subtracted from the device state threshold and the absolute value is taken to obtain the state value difference; The state value difference is processed by ratio with the device state threshold to obtain the state deviation ratio; Obtain the state deviation ratios of all abnormal production stages, perform summation and mean processing on the state deviation ratios, and obtain the deviation mean ratio; The deviation mean ratio and the abnormal stage ratio are processed as ratios to obtain the state abnormality ratio.

6. The method for monitoring the operation status of intelligent production equipment in an enterprise according to claim 1, characterized in that: The acquisition method of the overlap time ratio Sj and the overlap times mean value Jz is as follows: Obtain the equipment maintenance times during the abnormal production stage, perform subtraction processing on the equipment maintenance times and the maintenance target times, and obtain the maintenance times difference; The maintenance deviation ratio is obtained by ratioing the maintenance frequency difference with the maintenance target frequency. Obtain the equipment status value Zt and maintenance deviation ratio of each production abnormality stage in different monitoring cycles, and draw the cycle-equipment status value Zt change curve and cycle-maintenance deviation ratio change curve in the same two-dimensional rectangular coordinate system; Obtain the cycle-equipment status value Zt change curve, the cycle-maintenance deviation ratio change curve, the cycle time when the peaks overlap, and obtain the overlap duration; Obtain the overlap duration of all monitoring cycles to obtain the total overlap time, perform ratio processing on the total overlap time and the duration of all monitoring cycles to obtain the overlap time ratio, and mark the overlap time ratio as Sj; The number of overlap durations is obtained, and the number of overlap durations of all monitoring cycles is summed and averaged to obtain the average number of overlap times, which is marked as Jz.

7. A system for monitoring the operation status of intelligent production equipment in an enterprise, used to implement the method for monitoring the operation status of intelligent production equipment in an enterprise according to any one of claims 1 to 6, characterized in that: Includes the following modules: Parameter acquisition module: obtains the production process of products manufactured by intelligent production equipment, divides the production process into multiple stages, obtains the production stages, and obtains the number of defective products in each production stage; State analysis module: based on the number of defective products in each stage, obtain the defective target range of each stage, calculate the stage deviation ratio Pc, stage defective rate Cp, and calculate the equipment state value Zt. If the equipment state value Zt is less than the equipment state threshold, generate a state analysis signal; Trend judgment module: Based on the state analysis signal, the production stage that generates the state analysis signal is marked as the production abnormality stage, and the abnormal stage ratio is calculated. The equipment state value Zt and the equipment state threshold are calculated to obtain the deviation mean ratio. The deviation mean ratio is calculated with the abnormal stage ratio to obtain the state abnormality ratio, and the state abnormality ratio of different monitoring periods is obtained. The change curve of the cycle-state abnormality ratio is drawn, and the linear reference value Ck is calculated through the change curve. If the linear reference value Ck is less than the linear reference threshold, the curve is nonlinear, and a trend analysis signal is generated; Correlation analysis module: Based on the trend analysis signal, calculate the maintenance deviation ratio of production equipment in the abnormal production stage, obtain the equipment status value Zt and maintenance deviation ratio in the abnormal production stage in different monitoring cycles, draw the corresponding change curve in the same coordinate system, obtain the cycle time of the curve peak overlap, calculate the overlap time ratio Sj, the average number of overlaps Jz, and calculate the correlation Gl. Compare the correlation Gl with the correlation threshold. If the correlation GI exceeds the threshold, it is necessary to stop production and repair the intelligent production equipment.

Images