Method for setting operating threshold of multi-state device, monitoring method, monitoring system

Abstract

The present application relates to the technical field of device monitoring, in particular to a multi-state device running threshold setting method, a monitoring method, a monitoring system, the method comprising the steps of: S3, finding a target threshold; according to the target threshold, executing step S4 or S5; S4, executing a first verification process; if the verification is passed, the device is set as a running threshold according to the original threshold; S5, setting the obtained target threshold as a running threshold; the device has multiple working states; the obtained target threshold has a corresponding relationship with each working state of the device; a preset running threshold selection range; when executing S4, the target threshold in the running threshold selection range is selected to execute the first verification process; when executing S5, the target threshold in the running threshold selection range is selected as a running threshold; through the application of the device running threshold setting method, the set running threshold has the characteristics of high reliability, and the monitoring and verification accuracy of the monitoring system on the production state of the device is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment monitoring, and in particular to an operation threshold setting method and a monitoring method and a monitoring system for multi-state equipment. Background Art

[0002] Currently, the thresholds for determining whether a pollutant-discharging unit's production line is in production are primarily based on the power consumption of the equipment provided by the unit. If the power is greater than or equal to the set threshold, the unit is considered active; otherwise, it is considered inactive. In practice, these thresholds are often based on the nameplates of the equipment, but actual usage often differs, impacting regulatory oversight.

[0003] Secondly, on-site operating conditions are complex, and sewage discharge unit equipment may be in multiple operating states. For some equipment in standby or insulation mode, turning it on is not considered production, making it difficult to determine whether the sewage discharge unit is actually producing pollutants. Furthermore, with increasing use, sewage discharge unit equipment will show a certain degree of aging after long-term operation, and energy consumption and power will increase, making it difficult to ensure the continued availability of thresholds.

[0004] At present, whether the thresholds provided by pollutant discharge units are in line with the actual situation on site is mainly verified manually during the project operation. This has high requirements on the professional level, data sensitivity and business of technical personnel. However, when there are a large number of pollutant discharge units and a lot of equipment, manual verification negligence is difficult to avoid.

[0005] The main difficulties encountered in determining the production status threshold are:

[0006] (1) The collection of thresholds requires a certain level of cooperation from pollutant-discharging units. Once a pollutant-discharging unit has the idea of ​​evading monitoring and falsely reports the power threshold, resulting in the pollutant-discharging unit being in pollutant production but the online monitoring is inconsistent with the on-site situation, etc., it will affect the environmental protection department's control over the pollutant-discharging unit.

[0007] (2) On-site production conditions are complex, and the turning on of production equipment does not necessarily mean that it is in a pollution-producing state. The thresholds collected in the early stage are more of the thresholds of the equipment turning on state. It is necessary to find a threshold for scientifically evaluating the pollution-producing state of production equipment.

[0008] (3) There are certain requirements for the professional level of the technical personnel who conduct threshold review. They need to have professional knowledge, high data sensitivity, and be familiar with the business. Therefore, a lot of energy and material resources need to be invested in professional and business training in the early stage.

[0009] (4) When the sample size is small, manual review thresholds may be effective in a short period of time. However, with the full coverage of online monitoring and the increase in the number of pollutant-discharging units, a large amount of manpower and time costs will be required for secondary verification. However, manual verification is not foolproof. Once omissions or negligence occur, it will affect the regulatory authorities' judgment on the status of the pollutant-discharging units.

[0010] (5) As time goes by, production equipment ages, energy consumption and power increase, and the continuous availability of thresholds is difficult to guarantee. If the historical experience values ​​obtained deviate from the current actual situation, this will also affect subsequent supervision and increase labor costs. Summary of the Invention

[0011] In view of the current status of full-process monitoring of sewage discharge equipment, it is necessary to provide a complete method for setting equipment operating thresholds, find the dividing line between the equipment's production status operating data and non-production status operating data, and then clarify its scientific and reasonable operating thresholds, and accurately verify them, so that the equipment's operating threshold settings are accurate.

[0012] To this end, the purpose of the present invention is to provide a method for setting the operating threshold of an equipment, and at the same time provide a monitoring method and a monitoring system to meet the application requirements of the monitoring system for status supervision of working equipment, especially sewage treatment equipment.

[0013] A method for setting an operating threshold value for a multi-state device comprises the following steps: S1, obtaining operating data of the device; S2, clustering the operating data using a classification algorithm; S3, finding a target threshold value using a circular binary search method; and then executing step S4 or S5 according to the obtained target threshold value; wherein: S4, executing a first verification process for performing a reliability verification of an original threshold value of the device using the obtained target threshold value; if the verification passes, setting the device to the original threshold value as the operating threshold value; S5, setting the operating threshold value of the device using the obtained target threshold value.

[0014] When the number of target thresholds obtained is not less than two:

[0015] First, the device has multiple working states; in step S3, the target threshold obtained corresponds to each working state of the device; the operating threshold selection range is preset based on the operating data obtained from the target working state, and when step S4 is executed, the target threshold obtained in the operating threshold selection range is selected to perform the first verification process for the reliability verification of the original threshold of the device; when step S5 is executed, the target threshold obtained in the operating threshold selection range is selected as the operating threshold setting of the device.

[0016] For equipment applications with multiple working states, this solution is based on the correspondence between the obtained target threshold and the various working states of the equipment in terms of quantity and value selection range, and the reasonable operating range of the operating data in each working state is used as the selection range of the operating threshold. This can ensure the rationality and reliability of the applied target threshold when executing step S4 or S5.

[0017] Secondly, the device has multiple working states, and the device has corresponding multiple original thresholds corresponding to each working state; in step S3, the obtained target threshold is obtained to have a corresponding relationship with the original threshold of the working state of the device; when executing step S4, one or more obtained target thresholds are verified for reliability with the corresponding one or more original thresholds of each working state using the first verification process; when executing step S5, the obtained one or more target thresholds replace the corresponding one or more original thresholds of each working state as the operating threshold setting of the device.

[0018] According to the setting of the operating threshold in the equipment, the equipment can be associated with the corresponding monitoring system; when the equipment is in the corresponding working state and generates specific operating data, the corresponding operating threshold setting can effectively enable the monitoring system to confirm the current working state of the equipment, thereby effectively performing monitoring applications for the specific working state of the equipment.

[0019] Furthermore, in step S1 , data cleaning is performed on the acquired operation data.

[0020] Furthermore, in step S4, if the verification of the first verification process fails, a second verification process is executed to perform reliability verification on the obtained target threshold; if the verification of the second verification process passes, the obtained target threshold is set as the operating threshold of the equipment; if the verification of the second verification process fails, the equipment is marked.

[0021] Furthermore, in step S5, a second verification process for verifying the reliability of the obtained target threshold is executed; if the verification passes, the obtained target threshold is set as the operating threshold of the device.

[0022] Furthermore, the first verification process includes: verifying the first deviation rate of the obtained target threshold and the original threshold of the device; when the obtained first deviation rate is less than the first preset deviation value, it is determined that the verification is passed; the setting range of the first preset deviation value is 8% to 12%.

[0023] Furthermore, the first verification process includes: statistically comparing the analysis and judgment results of the operating data generated by the obtained target threshold with the analysis and judgment results of the operating data generated by the original threshold of the equipment to obtain a third deviation rate; when the obtained third deviation rate is less than the third preset deviation value, it is determined that the verification has passed; the setting range of the third preset deviation value is 8% to 12%.

[0024] Furthermore, the second verification process includes: verifying the second deviation rate of the obtained target threshold and the real-time operating data of the equipment. When the obtained second deviation rate is less than the second preset deviation value, it is determined that the verification has passed; the setting range of the second preset deviation value is 8% to 12%.

[0025] Furthermore, the second verification process includes: obtaining real-time operating data of the device within a unit time period under a fixed working state of the device, and counting the proportion of data whose real-time operating data of the device within the unit time period is greater than the obtained target threshold relative to the real-time operating data of the device within the unit time period; when the proportion is greater than the verification ratio value, it is determined that the verification has passed; the setting range of the verification ratio value is 85% to 95%.

[0026] Furthermore, the operation data includes historical operation power data or historical operation current data or real-time operation power data or real-time operation current data of the device.

[0027] Furthermore, in steps S2 to S3, the target threshold value is obtained as follows: S2-1, cluster the obtained operating data, and record the number of cluster centers as k; S2-2, determine the situation of k; when k=2, execute the following steps: S2-2-1, record i=1, and the cluster center is A i and A i+1 ; Then execute S2-3; S2-3, with A i and A i+1 As the boundary, we get the set D i ; S3-1, use the bisection method to sort the set D i Perform equal width division. The specific operation is to take A i and A i+1 The mean (A i +A i+1 ) / 2 for D i Perform equal-width segmentation to obtain two sets, the set intervals are [A i , (A i +A i+1 ) / 2), [(A i +A i+1 ) / 2,A i+1 ]; compare the size of the two sets of data, and get the set with smaller data volume D mi ; S3-2, judge Dmi Is the amount of data less than D i The preset data ratio of the data volume; when D mi The amount of data is less than D i When the data volume reaches the preset data ratio, execute S3-3; when D mi The amount of data is not less than D i When the data volume is the preset data ratio, output D mi , let D i =D m i, then return to execute S3-1; S3-3, calculate D mi The average of the maximum and minimum values ​​in the set a i , the obtained a i is the target threshold.

[0028] Furthermore, in step S2-2, when k is greater than 2, the following steps are executed: S2-2-2, initializing i=1; S2-2-3, selecting the i-th and i+1-th cluster centers A i and A i+1 ; Then execute S2-3; After step S3-3 is executed, when k is greater than 2, execute step S6; Step S6, determine whether i+1 is less than k; when i+1 is less than k, set i=i+1, and then return to execute step S2-2-3; when i+1 is not less than k, obtain the target threshold.

[0029] Furthermore, when k is greater than 2, the number of target thresholds obtained is not less than two; a screening criterion is preset, and the target thresholds obtained are screened according to the screening criterion, and the screened target thresholds are used as the basis for executing step S4 or S5.

[0030] Furthermore, the preset data ratio is set in a range of 8% to 12%.

[0031] If a device fails the corresponding verification process in the above process, unless otherwise specified, it is usually marked in actual application and then re-calibrated and verified one by one in the subsequent process. This re-calibration and verification process can be handled by experienced engineering personnel or through other system programs.

[0032] A device monitoring method, wherein the device applies the above-described method for setting an operating threshold to the device, and monitors the device using a monitoring system; the monitoring system compares the obtained operating data with the device's operating threshold and makes an analysis and judgment operation; when the monitored device's operating data is not less than the set operating threshold, the analysis and judgment result is that the working state is on; when the monitored device's operating data is less than the set operating threshold, the analysis and judgment result is that the working state is off.

[0033] An equipment monitoring system includes several devices and monitoring devices, and the monitoring devices are communicatively connected to each of the devices; the monitoring system uses the monitoring method described above to monitor the equipment; when the operating data of the equipment obtained by monitoring is not less than the operating threshold of the production working state set by it, the judgment result is that the production working state is turned on and the equipment is in the production state; when the operating data of the equipment obtained by monitoring is less than the operating threshold of the production working state set by it, the judgment result is that the production working state is turned off and the equipment is in the non-production state.

[0034] The beneficial effects of the present invention are:

[0035] 1. By applying the operation threshold setting method of the equipment, the set operation threshold can be made highly reliable, so that the monitored equipment has the reliability of being monitored, ensuring that the monitoring system accurately monitors and verifies the production status of the equipment. There is no need for monitoring and auditing personnel to regularly and quantitatively manually confirm and check a large number of devices one by one, effectively saving manpower and material resources.

[0036] 2. By setting different verification processes for multi-level applications, the reliability of the target threshold and the original threshold as the operating threshold of the equipment can be effectively ensured, avoiding the deviation of the operating threshold setting of the equipment.

[0037] 3. The application of this operating threshold setting method can enable the monitoring system to effectively distinguish and identify the working status of different equipment in different processes and industries during the monitoring process, and make targeted monitoring and analysis operations based on this, which helps regulators to accurately control the working status of the regulated equipment; in particular, it can solve the problem of difficulty in confirming the pollution production of pollutant discharge units in the existing pollution supervision field. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Real-time power trend chart for paint spraying equipment in the auto repair industry;

[0039] Figure 2 Real-time power scatter plot for painting equipment;

[0040] Figure 3 Violin plot of clustering results for paint spraying equipment power data;

[0041] Figure 4 Violin plots for thresholding power data for paint spraying equipment;

[0042] Figure 5 Result diagram of power data threshold division for painting equipment;

[0043] Figure 6 This is a flow chart of a method for obtaining a target threshold value according to embodiment 1 of the present invention;

[0044] Figure 7 This is a verification flow chart of the first verification process of Example 2 of the present invention;

[0045] Figure 8 This is a verification flow chart of the second verification process of Example 3 of the present invention;

[0046] Figure 9 This is a verification flow chart of the second verification process of Example 4 of the present invention;

[0047] Figure 10 This is a verification flow chart of the first verification process of Example 5 of the present invention;

[0048] Figure 11 This is a real-time power status trend chart of the device when the original threshold is not appropriate;

[0049] Figure 12 This is a schematic diagram of the power situation of the injection molding equipment in different working states;

[0050] Figure 13 This is a flowchart of a method for obtaining multi-target thresholds according to embodiment 6 of the present invention;

[0051] Figure 14 Violin plot of clustering results for injection molding equipment power data;

[0052] Figure 15 Violin plot for injection molding equipment power data threshold division;

[0053] Figure 16 This is the result diagram of the power data threshold division of the injection molding equipment;

[0054] Figure 17 This is a clustered violin plot of current data of the injection molding equipment according to Example 7 of the present invention;

[0055] Figure 18 This is a violin plot of the injection molding equipment current data threshold division according to Example 7 of the present invention. DETAILED DESCRIPTION

[0056] In order to make the technical solutions, objectives and advantages of the present invention more clearly understood, the present invention is further explained below with reference to the accompanying drawings and embodiments.

[0057] Example 1:

[0058] The present invention provides an equipment monitoring system, which includes several devices and a monitoring device. The monitoring device is communicatively connected to each of the devices, so that the monitoring device can acquire data and monitor and analyze each device. A device monitoring method is applied in the monitoring system, which sets an operating threshold for the device and compares the operating data obtained from the monitoring with the operating threshold, so that the monitoring system can analyze and operate the working status of the device.

[0059] In this device monitoring method, the device's operating threshold is first set, and then the device with the set operating threshold is monitored. The monitoring system compares the obtained operating data with the device's operating threshold and makes a judgment operation. When the monitored device operating data is not less than the set operating threshold, the judgment result is that the working state is turned on; when the monitored device operating data is less than the set operating threshold, the judgment result is that the working state is turned off.

[0060] Specifically, the equipment monitoring system is a monitoring system for sewage discharge equipment, which is used to monitor whether the sewage discharge equipment is actually in a pollution-producing state; when the operating data of the sewage discharge equipment obtained by monitoring is not less than the operating threshold of the pollution-producing working state, it is judged that the pollution-producing working state is turned on, that is, the sewage discharge equipment is in a pollution-producing production state; when the operating data of the equipment obtained by monitoring is less than the operating threshold of the pollution-producing working state, it is judged that the pollution-producing working state is closed, and its sewage discharge equipment is in a non-production state.

[0061] Taking the power operation data of production equipment in the production line of a pollution-discharging unit as an example to determine whether it is in a pollution-producing working state, the present invention provides a method for obtaining a target threshold value, which can be used to obtain the power target threshold value of the production equipment.

[0062] The specific application settings of the target threshold value are as follows:

[0063] Step 1: Acquisition and cleaning of equipment operation data.

[0064] The equipment power operation data and the corresponding working status data of the power operation data are obtained, and a data set for production equipment monitoring is formed with a cycle time. The cycle data sampling frequency is 5 minutes. After the power operation data recorded in 5 minutes is input into the system, the system will automatically eliminate abnormal values ​​and perform data cleaning processing, such as eliminating records of negative power values.

[0065] Step 2: Automatic clustering by classification algorithm.

[0066] The power distribution of pollutant-discharging unit production equipment during operation and non-operation will have characteristics: for example, during operation, the power value will fluctuate within a certain range. Therefore, based on the data distribution, the data can be divided into intervals.

[0067] like Figures 1 to 3 As shown in the figure, for example, paint spraying equipment in the auto repair industry typically has a power threshold of 0.2 kW. Once the real-time power is no less than 0.2 kW, the corresponding switch is considered on. The data shows that the power distribution is mostly near (0, 0.5) and (3, 5).

[0068] In the figure, the status switch value 1 indicates that the device is turned on, and 0 indicates that it is not turned on.

[0069] From a practical perspective, the unit's power consumption during non-production periods fluctuates around 0.4 kW due to the influence of other lighting equipment. This can lead to misjudgment of the status during non-production periods. In fact, during normal production, the power consumption of this equipment fluctuates between (3, 5). Therefore, we need to find a value between (0.4, 3) as the boundary between production and non-production periods.

[0070] In the classification algorithm, by finding high-density areas separated by low-density areas in the data set, the separated high-density areas are treated as an independent category. Suppose there are many points around point x, recorded as x1, x2...x j , we calculate the movement of point x to each point x around it j The sum of the required offsets is averaged to obtain the average offset. In addition to the magnitude, this offset also includes the direction of the surrounding density. Next, point x is moved in the direction of the average offset, using this as a new starting point. This iteration continues until a certain condition is met.

[0071] The general process is as follows:

[0072] 1) Randomly select a point in the data set as the starting center point S;

[0073] 2) With S as the center and radius r, find all data points that appear in the area, consider these points to belong to the same cluster C, and record the number of times the data point appears in the cluster plus 1;

[0074] 3) Taking S as the center point, calculate the vector from S to each element in the data set and add them together to get the vector s;

[0075] 4) S = S + s, that is, S moves along the direction s, and the moving distance is ||s||;

[0076] 5) Repeat steps 2), 3), and 4 until s is very small. Remember S at this point. At this point, all points encountered in this iterative process should be classified into cluster C.

[0077] 6) If the distance between the center of the current cluster C and the center of the existing cluster C2 is less than the set threshold (the set threshold is determined by the dataset and is the 50% quantile of the set of distances between any pair of samples in the dataset) at the time of convergence, then C2 is merged with C, and the number of data point occurrences is also merged accordingly. Otherwise, C is used as the new cluster;

[0078] 7) Repeat steps 1) to 5) until all points are marked as visited;

[0079] 8) Classification: According to each class, the access frequency of each point, take the access frequency of the largest class as the class to which the current point set belongs.

[0080] As Figure 3 shown, based on the application of paint spraying equipment in the automotive repair industry, it can be seen that the results of the pollution unit have two categories, and the first and second cluster centers are 0.05 and 3.94, respectively.

[0081] Step 3: Find the appropriate power target threshold by binary search.

[0082] As Figures 4 to 5 shown, based on the cluster center results obtained in the previous step, take the two cluster centers A1 and A2 as boundary conditions, and propose all data in this interval as data set D. Use binary search to divide D into two equal-width data sets D1 and D2. Take the preset data proportion value as 8% to 12%, preferably 10%. Compare D1 and D2, and take the smaller one as D m . If the data volume of D m is less than (D1+D2)*10%, take the average of the maximum and minimum values of this data as the target threshold. If the data volume of D m is greater than (D1+D2)*10%, further divide D m by binary search until a data set D m with a data volume less than (D1+D2)*10% is found, and take the average of the maximum and minimum values of this data as the power target threshold.

[0083] Use binary search to divide the power data between the two cluster centers obtained by the classification algorithm of the paint spraying equipment in the automotive repair industry into two equal-width parts, and select the one with the smallest data volume as D m . At this time, the data volume of the smallest data volume is less than 10% of the total data volume of D1 and D2. Based on D m , find the average of the maximum and minimum values a, and output the average value a as the power target threshold of the equipment, which is 2.23KW. Obviously, the numerical value of the obtained power target threshold 2.23KW can better divide the production and non-production situations than the original power threshold 0.2KW of the original equipment.

[0084] The flow of the steps of the above-mentioned target threshold finding method of the equipment is as follows:

[0085] S1, obtain the running data of the equipment;

[0086] S2, cluster the running data by a classification algorithm;

[0087] S3, find the target threshold by binary search.

[0088] According to the obtained target threshold, as a preferred target threshold application method, the target threshold can be selected as the operating threshold setting of the device.

[0089] The calculated power target threshold of 2.23 kW replaces the original 0.2 kW threshold and sets the power threshold for the equipment's actual production operation. This means that only when the paint spraying equipment's real-time power is at least 2.23 kW will its corresponding switch be considered on. This allows the monitoring system to accurately and effectively monitor the equipment's actual production operation.

[0090] The target threshold value calculation method mentioned above can be applied to derive the power target threshold value of the device based on the actual operation data of the device and from the actual production environment of the device; the corresponding target threshold value obtained can be more accurate than the original factory threshold value. The application of the target threshold value calculation method mentioned above can refer to the process as follows: Figure 6 shown.

[0091] A method for setting an operating threshold of an equipment according to the present invention can choose to replace the original threshold of the equipment with the obtained target threshold to directly serve as the operating threshold setting of the equipment; based on the adjustment setting of the operating threshold, it can meet the monitoring system's need for accurate analysis and judgment of the equipment's working status monitoring.

[0092] In the acquisition and calculation of the operating data of the above-mentioned equipment, the real-time operating power data of the equipment in real time or the historical operating power data of the equipment in the past can be selected for application according to actual needs.

[0093] Specifically, the specific process of obtaining the above power target threshold is as follows:

[0094] S2-1. Cluster the obtained operating data and record the number of cluster centers as k;

[0095] S2-2, judging the situation of k; in the case of a single working state, there will be two cluster centers;

[0096] When k=2, execute step: S2-2-1, let i=1, and the cluster center is A i and A i+1 ; Then execute S2-3;

[0097] S2-3, with A i and A i+1 As the boundary, we get the set D i ;

[0098] S3-1, use the bisection method to sort the set D i To divide, the specific operation is to take A i and A i+1The mean (A i +A i+1 ) / 2 for D i Perform equal-width segmentation to obtain two sets, the set intervals are [A i , (A i +A i+1 ) / 2), [(A i +A i+1 ) / 2,A i+1 ]; compare the size of the two sets of data, and get the set with smaller data size D mi ;

[0099] S3-2, Judgement D mi Whether the data volume is less than a preset data ratio of the data volume Di, wherein the setting range of the preset data ratio is 8% to 12%;

[0100] When D mi The amount of data is less than D i When the data volume reaches the preset data ratio, execute S3-3;

[0101] When D mi The amount of data is not less than D i When the data volume is the preset data ratio, output D mi , let D i =D mi , then return to execute S3-1;

[0102] S3-3. Calculate D mi The average of the maximum and minimum values ​​in the set a i , the obtained a i is the target threshold.

[0103] Example 2:

[0104] Based on the application of the target threshold value obtaining method of the above embodiment 1, another preferred application mode of this solution is: based on the premise that the target threshold value obtained by the algorithm is reliable, the reliability of the original threshold value of the device is verified by using the obtained target threshold value in the first verification process, so as to clarify whether the original threshold value of the device is reliable. Figure 7 shown.

[0105] As we've seen above, the operating threshold of production equipment isn't actually a fixed value, but rather fluctuates within a range. Therefore, finding a value within this range allows us to effectively distinguish between on-off states. Assuming the original threshold is within the operating threshold range, the target threshold derived from the algorithm is also within this operating threshold range. In this case, the deviation between the state determined using the original threshold and the target threshold will be minimal. However, if the original threshold is outside this range, the state determined using the target threshold will deviate from the state determined using the original threshold. Therefore, if the difference between the target threshold and the device's original threshold is within a reasonable range, the device's original threshold can be considered reliable. This is the fundamental design principle of this solution.

[0106] When it is confirmed that the original threshold value of the device is reliable, the original threshold value of the device will continue to be used as the operating threshold value setting of the device, thereby ensuring the accurate application of the monitoring work and reducing the operation process.

[0107] The first verification process may optionally include: verifying a first deviation rate between the target threshold and the device's original threshold, and determining that the verification has passed when the first deviation rate is less than a first preset deviation value. The first preset deviation value is in the range of 8-12%, and is preferably set to 10%.

[0108] For example, in the case of the paint spraying equipment in the auto repair industry, if the original threshold value of the equipment is 2 kW, then when the first preset deviation is 12%, the theoretical target threshold value range, which fluctuates 12% above and below the original threshold value, is between 1.76 kW and 2.24 kW. Therefore, if the target threshold value is 2.23 kW, the original threshold setting can be considered reliable. This allows the paint spraying equipment to continue using 2 kW as its operating threshold, and the monitoring device can continuously monitor its production status at 2 kW.

[0109] The setting steps of the above-mentioned first verification process are as follows:

[0110] S4-1. Compare the obtained target threshold with the original threshold of the device to calculate a first deviation rate;

[0111] S4-2, determining whether the first deviation rate is less than a first preset deviation value;

[0112] When the first deviation rate is less than the first preset deviation value, the verification of the first verification process passes.

[0113] To this end, a method for setting the operating threshold of an equipment according to the present invention can optionally execute a first verification process for reliability verification of the original threshold of the equipment using the obtained target threshold; if the verification passes, the equipment continues to use the original threshold as its own operating threshold setting, thereby meeting the monitoring system's requirements for accurate analysis and judgment of the equipment's working status monitoring.

[0114] Example 3:

[0115] In order to avoid large deviations in the target threshold value obtained due to other circumstances (such as data packet loss during operation data acquisition), the reliability of the target threshold value can be verified by the second verification process. Only when the target threshold value passes the verification can the target threshold value be used as the operating threshold value setting of the device or as the reliability verification benchmark setting of the original threshold value of the device. For the application of the verification process of the second verification process, please refer to Figure 8 shown.

[0116] The second verification process may optionally include verifying a second deviation rate between the target threshold and the real-time operating data of the device, and determining that the verification has passed when the second deviation rate is less than a second preset deviation value. The second preset deviation value is in the range of 8-12%, and is preferably set to 10%.

[0117] Specifically, continuing to take the application of the paint spraying equipment in the above-mentioned auto repair industry as an example: the real-time operation data can be selected as the average power data within the periodic sampling time (5 minutes) of the equipment in the target working state.

[0118] For example: if the target threshold value is required to be obtained under the pollution-producing working state, the operating data of the equipment within the periodic time period is collected under the clear pollution-producing working state (confirmed by manual confirmation or comprehensive analysis), and the data average is obtained; for example, in the above-mentioned paint spraying equipment, when the real-time operating data of the average value obtained under the pollution-producing working state is 2.5KW, the second preset deviation value is set to 12%, and the target threshold value currently obtained is 2.23KW. The second deviation rate between the obtained target threshold value and the real-time operating data of the equipment is less than the second preset deviation value, so it is determined that the verification has passed.

[0119] Under the application premise of the above-mentioned embodiment 2, if the verification result is not passed when executing the first verification process, then there may be a possibility that the target threshold is obtained incorrectly or the original threshold and the obtained target threshold have a large deviation (the target threshold is reasonable). Therefore, a second verification process is subsequently executed to verify the reliability of the obtained target threshold; if the second verification process passes the verification, it is determined that the original threshold and the obtained target threshold have a large deviation; the target threshold is reasonable, and the obtained target threshold can be used as the operating threshold setting of the device. If the second verification process fails to pass the verification, there is a possibility that the target threshold is obtained incorrectly, and the device needs to be marked for subsequent inspection.

[0120] Example 4:

[0121] Based on the application of the above embodiment 3, this embodiment further describes the preferred configuration of embodiment 3.

[0122] The second verification process in the above embodiment 3 can be changed to: in a fixed working state of the device, obtain the real-time operation data of the device in a unit time period, and count the proportion of the real-time operation data of the device in the unit time period that is greater than the obtained target threshold value relative to the real-time operation data of the device in the unit time period. When the proportion is greater than the verification ratio value, it can be considered that the setting of the target threshold is reliable and the verification is determined to be passed. For the application of the verification process of the second verification process, refer to Figure 9 shown.

[0123] For example:

[0124] After confirming that the equipment is in a stable on-working state (such as production state), the real-time power operation data of the equipment in the on-working state is compared with the target threshold in a 24-hour period. If more than 90% of the power operation data monitored within 24 hours exceeds the target threshold, it can be considered that the verification has passed and the obtained target threshold is reliable.

[0125] Example 5:

[0126] Based on the application of the above embodiments, this embodiment further describes the preferred configuration.

[0127] In the application of the above embodiment, the corresponding verification can be performed only based on the data generated by the device itself; however, in the application of the solution of this embodiment, it is further necessary to combine it with a simulated analysis and judgment action setting to make the corresponding verification process more accurate and reliable throughout the entire life cycle.

[0128] The first verification process for verifying the reliability of the device's original threshold using the obtained target threshold is as follows: simulating the evaluation results generated by the target threshold on the operating data and the evaluation results generated by the device's original threshold on the operating data, statistically comparing the evaluation results generated by the obtained target threshold on the operating data with the evaluation results generated by the device's original threshold on the operating data, and obtaining a third deviation rate; when the obtained third deviation rate is less than a third preset deviation value, the verification is determined to have passed. The third preset deviation value is in the range of 8-12%, and is preferably set to 10%.

[0129] Then in the actual application process, after obtaining the target threshold, the analysis and judgment results made in the process of generating the corresponding operating data are correspondingly counted according to the calculation conditions of the selected operating data (or historical operating data or real-time operating data). For the working status that we need to judge (such as the pollution-producing working status of the paint spraying equipment in the auto repair industry mentioned above), determine the situation in which the pollution-producing working status is turned on after the corresponding target threshold is set in the data sampling period (5 minutes) and the situation in which the pollution-producing working status is turned on after the original threshold is set, and perform simulated statistics. When the deviation rate between the number of analysis and judgment results obtained based on the target threshold setting and the number of analysis and judgment results obtained based on the original threshold setting is less than the third preset deviation value, it is determined that the verification is passed, and the reliability of the original threshold is clarified. For the application of the verification process of the first verification process, refer to the following. Figure 10 shown.

[0130] For example, using the target threshold as the operating threshold, the monitoring system determines the device's on / off status at each monitoring time point and then compares the results with the original preset value. If there are 100 preset time points, and the original preset value determines that all points are on, but the target threshold is used as the operating threshold, only 70 points are on, with an error rate of 30%. This exceeds the preset deviation of 10%, and the original threshold is considered unreliable. The first verification process fails, and a second verification process is required, or the device is marked and further confirmation is performed manually.

[0131] As a real application case:

[0132] Based on environmental monitoring data from pollutant-discharging units, totaling approximately 17.5 million data points across 978 production lines, the aforementioned algorithm was used to model and learn the power operating thresholds for these devices. This model was then verified against the devices' original thresholds. 719 of these data points, or approximately 73.6%, showed deviations within 10%, indicating that the current status of most production line equipment was reasonable. 259 of these data points had deviations greater than 10%, indicating that the reliability verification of the original thresholds in the first verification process had failed.

[0133] If the first verification process fails, the target threshold reliability can be verified using the second verification process, or directly rechecked through the monitoring system or manually. The review revealed that 203 of the 259 production lines, representing approximately 20.8% of the total, had the same power value, but could be detected as different states at different times. In these cases, it can be considered that the data generated by the equipment has quality issues, not the accuracy of the target threshold calculated by this solution.

[0134] In addition, 33 production lines experienced significant power fluctuations, with the identified target threshold not being 0 or even being larger, and the actual status being consistently judged as off. This accounted for approximately 3.4% of the total. This indicated that there was a problem with the original threshold settings for the equipment. In this case, the originally preset operating threshold settings for the equipment needed to be changed based on the resulting power target threshold.

[0135] like Figure 11 As shown, after 8:00 AM, the device's power fluctuated significantly, but its status remained off. The original threshold settings for the device on site were unreasonable, possibly set too high, resulting in an inaccurate identification of the device's true status. Overall, this method can verify the existing status and determine whether the original threshold settings for the current sewage unit's equipment are reasonable. The overall misjudgment rate is 2.4%, which is relatively low and reliable.

[0136] type Number of records Proportion Pass verification 719 73.6％ There are problems with data quality 203 20.7％ The operating threshold set on site (original threshold) is unreasonable 33 3.3％ The operating threshold (target threshold) obtained by the algorithm is inappropriate 23 2.4％ total 978 100％

[0137] Example 6:

[0138] In the above embodiment, the operating conditions of paint spraying equipment in the auto repair industry are used as an example to illustrate the calculation of target power thresholds for equipment operating in a single production mode (pollution-generating mode). In this embodiment, the calculation of target power thresholds for equipment operating in multiple modes is further described.

[0139] like Figure 12 As shown, in the injection molding industry, for example, the film blowing process involves heating. In addition to the shutdown state, the production equipment has two distinct operating states: heating and production. While the film blowing process generates a certain amount of power output, since it doesn't actually produce any waste gas, it doesn't generate any. Therefore, from an environmental monitoring perspective, it's crucial to accurately identify the production status of the film blowing equipment for monitoring.

[0140] However, in actual applications, the original threshold of the film blowing process equipment is generally set low (or only set to greater than 1KW). In the preheating state, it may cause the monitoring system to generate a monitoring linkage alarm, which does not meet the actual monitoring requirements.

[0141] Therefore, in view of the above application situation, the algorithm for obtaining the target threshold is further supplemented in this embodiment:

[0142] In the case of two working states, the obtained operating data will have three cluster centers. Therefore, in step S2-2, when k is greater than 2, the following steps are executed: S2-2-2, initializing i=1; S2-2-3, selecting the i-th and i+1-th cluster centers A. i and A i+1 ; Then execute S2-3;

[0143] After step S3-3 is executed, when k is greater than 2, step S6 is executed to determine whether i+1 is less than k;

[0144] When i+1 is less than k, output i=i+1 to step S2-2-3, and repeat the above operation steps sequentially to obtain multiple target thresholds a i , until i+1 is not less than k;

[0145] When i+1 is not less than k, all target thresholds are obtained; at this time, the number of target thresholds obtained is greater than or equal to 2.

[0146] In this embodiment, in the case of three cluster centers generated based on two different working states, two target thresholds will be generated.

[0147] At the above target thresholds a i In the process of obtaining, in response to different verification requirements, different first verification processes or second verification processes in the above embodiments can be selected respectively to perform combined setting applications.

[0148] The process setting of the multi-target threshold value method is as follows: Figure 13 shown.

[0149] like Figures 14 to 16 As shown in the figure, by applying the algorithm for obtaining the target threshold of the equipment, it can be found that the power of the injection molding production equipment will fluctuate in three intervals, corresponding to the shutdown concentration interval, the preheating concentration interval, and the production concentration interval. At this time, there are two target thresholds obtained, which are 1.6KW and 31.2KW respectively. The obtained target threshold is not unique, and the obtained target threshold has a corresponding relationship with each working state of the equipment in terms of quantity and value selection range.

[0150] A screening standard is preset, and the target threshold value obtained is screened according to the screening standard, and the target threshold value obtained by screening is used as the execution basis for monitoring the working status of the equipment.

[0151] First, according to actual experience, the equipment preheating state is a lower power output state, and the equipment pollution producing state is a higher power output state, and the power running data in the application of the two working states will have a significant difference; therefore, the screening standard is to divide and match the running threshold values of different working states by identifying the target threshold value with a significant difference in numerical value through big data or artificial intelligence.

[0152] Therefore, according to the screening standard, the lower power output state value 1.6KW is selected as the running threshold value of the equipment preheating state, and the higher power output state value 31.15KW is selected as the running threshold value of the equipment pollution producing state. Based on 31.15KW as the actual pollution producing state power running threshold value of the equipment, the above-mentioned first verification process and the running threshold value setting application after verification are executed, or the obtained target threshold value is used as the running threshold value setting application of the equipment, and the subsequent actual monitoring situation obtained by the monitoring system will be more in line with the actual needs.

[0153] On the other hand, the screening standard can also set the selection range of the running threshold value according to the obtained running data.

[0154] For example, in the application of a film blowing process equipment, through artificial confirmation or comprehensive analysis and confirmation of other analysis system programs, it can be known that there is a reasonable range of running data of different working states of the equipment (such as the reasonable range of preheating state power output data, and the reasonable range of equipment pollution producing state power output data, which can be set as a 10% range of the upper and lower floating of the corresponding working state running data mean); therefore, on this basis, the running threshold value of the equipment preheating state is selected in the lower range of the above-mentioned preheating state power output data, and the running threshold value of the equipment pollution producing state is selected in the lower range of the pollution producing state power output data. According to the monitoring target we need, which is the equipment pollution producing state, among the multiple target threshold values obtained by the above-mentioned algorithm, the target threshold value within the reasonable range of the above-mentioned equipment pollution producing state power output data is selected as the running threshold value setting of the equipment pollution producing state.

[0155] In different environment applications, for the simultaneous monitoring of multiple working states, the equipment will have multiple original threshold values of corresponding working states, and the equipment will obtain target threshold values through the setting method, which will have a one-to-one correspondence with the original threshold values of the working states in terms of quantity and numerical value setting range.

[0156] Therefore, among the multiple target threshold values obtained by the above-mentioned algorithm, each obtained target threshold value will have a matching relationship with the power output data reasonable range of each working state.

[0157] Accordingly, during the operation threshold setting process, you can choose to execute the first verification process for the reliability verification of the original thresholds for different working states of the equipment and / or execute the second verification process for the reliability verification of each target threshold, and set the operation thresholds for each working state of the equipment for each target threshold that meets the verification pass conditions, or continue to set the original thresholds under each working state after verification as the operation threshold of the equipment, so that the obtained target thresholds can be effectively matched with the corresponding working state conditions. In the application of the monitoring system, the monitoring device can be set with different monitoring alarm measures for different operating threshold standard conditions, which can meet the monitoring system's needs for separate monitoring of multiple working states of the equipment.

[0158] Example 7:

[0159] In the description of each of the above embodiments, it is pointed out that there are devices in the operation threshold setting and monitoring application of power operation data. In this embodiment, the operation setting and monitoring application of the corresponding current operation data are further described. Figures 17 and 18 As shown, by applying the algorithm for determining the target threshold for the equipment, acquiring the corresponding historical current data of the paint spraying equipment and performing the algorithmic calculation, it can be concluded that when the production equipment is generating pollution during the concentrated production period, its current operating threshold is set to the obtained current target threshold of 54.61A to classify pollution production, which is more consistent with actual conditions. During the algorithmic calculation process of this embodiment, the selected operating data includes historical operating current data or real-time operating current data of the equipment.

[0160] Example 8:

[0161] Based on the application of the algorithm for obtaining the target threshold in the above-mentioned embodiment, those skilled in the art can understand that in similar application fields, such as monitoring whether there is any use of illegal electrical appliances in school dormitories, the equipment monitoring system of the present invention will also be able to accurately monitor and analyze the usage status of the corresponding illegal electrical equipment, and meet the needs of other equipment monitoring applications besides the sewage monitoring field.

[0162] The above description is only a preferred embodiment of the present invention. Those skilled in the art can still modify the embodiment without departing from the implementation principle of the present invention, and the corresponding modifications should also be considered as the scope of protection of the present invention.

Claims

1. A method for setting an operating threshold value of a multi-state device, characterized in that: The following steps are involved: S1. Obtain the operating data of the equipment; S2, clustering the operation data through classification algorithm; S3, find the target threshold through circular bisection; According to the obtained target threshold, step S4 or S5 is then executed; S4, executing a first verification process for reliability verification of the original threshold value of the device using the obtained target threshold value; If the verification passes, the device is set to the original threshold as the operating threshold; if the verification of the first verification process fails, a second verification process is performed to verify the reliability of the obtained target threshold; If the second verification process passes, the obtained target threshold is set as the operating threshold of the device; If the second verification process fails, the device is marked; The first verification process includes: statistically comparing the analysis results of the operating data generated by the obtained target threshold with the analysis results of the operating data generated by the original set threshold of the device to obtain a third deviation rate; when the obtained third deviation rate is less than a third preset deviation value, determining that the verification has passed; The second verification process includes: verifying a second deviation rate between the obtained target threshold and the real-time operating data of the device, and determining that the verification has passed when the obtained second deviation rate is less than a second preset deviation value; S5. Using the obtained target threshold as the operating threshold setting for the device; The device has multiple working states; in step S3, the target threshold value obtained corresponds to each working state of the device; and the operating threshold selection range is preset based on the operating data obtained from the target working state; When step S4 is executed, a first verification process is performed to verify the reliability of the device's original threshold by selecting the target threshold within the operating threshold selection range; When executing step S5, the obtained target threshold value within the operating threshold selection range is selected as the operating threshold setting of the device.

2. The method for setting the operating threshold according to claim 1, wherein: In step S5, a second verification process for verifying the reliability of the obtained target threshold is performed; If the verification is passed, the target threshold is set as the operating threshold of the device.

3. The method for setting the operating threshold according to claim 1 or 2, wherein: The first verification process includes: verifying the first deviation rate of the obtained target threshold and the original threshold of the device. When the obtained first deviation rate is less than the first preset deviation value, it is determined that the verification has passed; the setting range of the first preset deviation value is 8% to 12%.

4. The method for setting an operating threshold according to claim 1 or 2, wherein: The setting range of the third preset deviation value is 8% to 12%.

5. The method for setting the operating threshold according to claim 1 or 2, wherein: The setting range of the second preset deviation value is 8% to 12%.

6. The method for setting an operating threshold according to claim 1 or 2, wherein: The second verification process includes: obtaining the real-time operation data of the device within a unit time period under a fixed working state of the device, and counting the proportion of the real-time operation data of the device within the unit time period that is greater than the obtained target threshold value relative to the real-time operation data of the device within the unit time period. When the proportion is greater than the verification ratio value, it is determined that the verification has passed; the setting range of the verification ratio value is 85% to 95%.

7. The method for setting the operating threshold according to claim 1, wherein: The operation data includes historical operation power data or historical operation current data or real-time operation power data or real-time operation current data of the device.

8. A monitoring method, characterized in that: The operating threshold setting method according to any one of claims 1 to 7 is applied to the device to set the operating threshold of the device, and the device is monitored by a monitoring system; the monitoring system compares the obtained operating data with the operating threshold of the device and makes an analysis and judgment operation; when the operating data of the device obtained by monitoring is not less than the set operating threshold, the judgment result is that the working state is on; when the operating data of the device obtained by monitoring is less than the set operating threshold, the judgment result is that the working state is off.

9. Monitoring system, characterized in that, The system comprises a plurality of devices and a monitoring device, wherein the monitoring device is communicatively connected with each of the devices; the monitoring system monitors the devices using the monitoring method as described in claim 8; when the operating data of the device obtained by monitoring is not less than the operating threshold of the production working state set therein, the judgment result is that the production working state is turned on and the device is in the production state; when the operating data of the device obtained by monitoring is less than the operating threshold of the production working state set therein, the judgment result is that the production working state is turned off and the device is in the non-production state.

Images