Real-time monitoring alarm method and device, electronic equipment and storage medium

Through real-time monitoring and alarm methods, the reward value and window length adjustment technology are used to solve the problem of false alarms and omissions in multi-dimensional indicator monitoring in complex industrial processes, and the monitoring accuracy and stability of industrial processes are improved.

CN119002323AActive Publication Date: 2024-11-22TSINGHUA UNIVERSITY
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202310559953.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-17
Publication Date
2024-11-22
Estimated Expiration
2043-05-17

AI Technical Summary

Technical Problem

The existing industrial process monitoring methods rely on manual judgment and cannot meet the monitoring needs of multi-dimensional indicators in complex production processes, and are prone to false alarms and missed alarms.

Method used

Through real-time monitoring and alarm methods, the monitoring feature value is obtained according to the preset time period, the target feature value and reference feature value are determined, the window length and action is adjusted according to the reward value, the alarm and normal reward are accumulated, the alarm status is determined, and the instantaneous feature value changes are avoided. A false alarm is generated.

Benefits of technology

Improve the accuracy of monitoring alarms, avoid false alarms and missed alarms, and enhance the stability and safety of industrial processes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002323A_ABST
    Figure CN119002323A_ABST
Patent Text Reader

Abstract

The invention relates to a real-time monitoring alarm method and device, electronic equipment and a storage medium. Monitoring characteristic values monitored in the production process are acquired for multiple times according to a preset time period to serve as target characteristic values; and determining an initial window length of the target feature value and determining a monitoring feature value obtained in the window length before the target feature value as a reference feature value. And determining a reference action corresponding to the target feature value according to the reward value corresponding to each reference feature value. And adjusting the window length according to a reference action corresponding to the target feature value to update the reference feature value. And determining an accumulated alarm reward and an accumulated normal reward according to the reward value corresponding to the updated reference feature value so as to determine an alarm state corresponding to the target feature value. According to the method, the alarm state of the next period is determined according to the characteristic value of the determined alarm state in a manner of setting the reward value. According to the mode, a plurality of monitoring characteristic values of one stage are considered when the alarm state is determined, and false alarm caused by instantaneous characteristic value change is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of secure computing, and in particular to a real-time monitoring alarm method, device, electronic device and storage medium. Background Art

[0002] With the improvement of production requirements and the advancement of technology, process industries represented by steel, metallurgy, energy, and chemical industry are gradually developing towards large-scale and high complexity. Ensuring the stable and normal operation of complex industrial processes is of great significance for reducing production costs, improving production efficiency and benefits. Obtaining various process variable (indicator) data reflecting the production status through various sensing means and judging whether the production status is normal through analysis of these data is an important guarantee for the stable production of industrial processes. In actual production, traditional process monitoring methods mainly rely on manual threshold judgment of a few key indicators. However, with the increase in the complexity of the production process, the dimensions of monitoring indicators are also increasing. Simply relying on manual work can no longer meet the monitoring requirements. At present, some methods of automatic alarm monitoring based on alarm strategies have been produced, but they mainly compare the real-time value of the monitoring statistic with the control limit through online calculation. When the control limit is exceeded, an alarm is issued, which is prone to false alarms and missed alarms. Summary of the invention

[0003] In view of this, the present disclosure proposes a real-time monitoring alarm method, device, electronic device and storage medium, aiming to accurately monitor the safety of the production process.

[0004] According to a first aspect of the present disclosure, a real-time monitoring alarm method is provided, the method comprising:

[0005] Acquire the monitoring characteristic value monitored during the production process multiple times according to a preset time period, and determine the currently acquired monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is acquired;

[0006] Determine the initial window length of the target characteristic value, and use the monitoring characteristic value obtained within the window length before the target characteristic value as a reference characteristic value;

[0007] Determine a reference action corresponding to the target feature value according to a reward value corresponding to each reference feature value, wherein the reward value is determined according to a reference action corresponding to the reference feature value, and the reference action includes an alarm action and a normal action;

[0008] Adjusting the window length according to the reference action corresponding to the target feature value, and updating the corresponding reference feature value according to the adjusted window length;

[0009] The cumulative alarm reward and the cumulative normal reward are determined according to the reward value corresponding to the reference characteristic value after update, and the alarm state corresponding to the target characteristic value is determined according to the cumulative alarm reward and the cumulative normal reward, and the alarm state includes alarm and normal.

[0010] In a possible implementation manner, determining the initial window length of the target feature value includes:

[0011] The window length adjusted based on the reference action corresponding to the previous target feature value is determined as the initial window length of the current target feature value.

[0012] In a possible implementation, determining the reference action corresponding to the target feature value according to the reward value corresponding to each reference feature value includes:

[0013] Determine the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target characteristic value according to the reward value corresponding to each reference characteristic value;

[0014] In response to the alarm confidence upper limit value being greater than the normal confidence upper limit value, determining the reference action corresponding to the target feature value as an alarm action;

[0015] In response to the normal confidence upper limit value being greater than the alarm confidence upper limit value, it is determined that the reference action corresponding to the target feature value is a normal action.

[0016] In a possible implementation, determining the warning confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value according to the reward value corresponding to each reference feature value includes:

[0017] Counting the warning reward value and the normal reward value included in the reward value corresponding to each reference feature value;

[0018] The alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value are determined respectively according to each of the alarm reward values ​​and each of the normal reward values.

[0019] In a possible implementation, determining the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value according to each of the alarm reward values ​​and each of the normal reward values ​​respectively includes:

[0020] Determining an alarm estimation value according to each of the alarm reward values ​​and the position of the corresponding reference feature value, and a preset forgetting factor;

[0021] Determine a normal estimation value according to each of the normal reward values ​​and the position of the corresponding reference feature value, and the forgetting factor;

[0022] Determine an alarm metric value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics, wherein the dynamic probability is determined according to the window length corresponding to the target feature value;

[0023] Determine a normal measurement value according to the forgetting factor, the dynamic probability and the normal reward value quantity obtained by statistics;

[0024] Calculate the product of the alarm metric value and a preset control coefficient, and the sum of the product and the alarm estimation value as the alarm confidence upper limit value;

[0025] The product of the normal measurement value and the preset control coefficient is calculated, and the sum of the product and the normal estimated value is used as the normal confidence upper limit value.

[0026] In a possible implementation, determining the alarm estimation value according to each of the alarm reward values ​​and the position of the corresponding reference feature value, and a preset forgetting factor, includes:

[0027] By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a1) is the number of alarm reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the alarm estimation value, r a1 is the alarm reward value corresponding to the reference feature value.

[0028] In a possible implementation, determining a normal estimation value according to each of the normal reward values ​​and the corresponding reference feature value position, and the forgetting factor, includes:

[0029] By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a2) is the number of normal reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the normal estimated value, r a2 is the normal reward value corresponding to the reference feature value.

[0030] In a possible implementation, determining the alarm metric value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics includes:

[0031] By formula The alarm metric value is calculated, where p is a dynamic probability value.

[0032] In a possible implementation, determining a normal measurement value according to the forgetting factor, the dynamic probability and the normal reward value quantity obtained by statistics includes:

[0033] By formula The normality metric is calculated, where p is a dynamic probability value.

[0034] In a possible implementation manner, adjusting the window length according to a reference action corresponding to the target feature value includes:

[0035] In response to the reference action corresponding to the target feature value being the same as the reference action corresponding to the previous target feature value, determining to extend the window length by 1;

[0036] In response to the reference action corresponding to the target feature value being different from the reference action corresponding to a previous target feature value, the window length is scaled according to a preset scaling parameter.

[0037] In a possible implementation manner, scaling the window length according to a preset scaling parameter includes:

[0038] Calculating the product of the window length and the scaling parameter, and rounding the product to obtain a candidate length;

[0039] In response to the candidate length being greater than a preset shortest length, determining the candidate length to be an adjusted window length;

[0040] In response to the candidate length being smaller than the shortest length, determining the shortest length as the adjusted window length.

[0041] In a possible implementation, the method further includes:

[0042] A corresponding reward value is calculated according to the target feature value and the reference action.

[0043] In a possible implementation, the calculating a corresponding reward value according to the target feature value and the reference action includes:

[0044] In response to the reference action being an alarm action, the formula 1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value, where Stat is the target feature value and Stat_UCL is the preset feature value threshold.

[0045] In a possible implementation, the calculating a corresponding reward value according to the target feature value and the reference action further includes:

[0046] In response to the reference action being a normal action, the formula 1-1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value.

[0047] According to a second aspect of the present disclosure, a real-time monitoring alarm device is provided, the device comprising:

[0048] A target characteristic value determination module is used to obtain the monitoring characteristic values ​​monitored during the production process multiple times according to a preset time period, and determine the currently obtained monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is obtained;

[0049] A reference eigenvalue determination module, used to determine the initial window length of the target eigenvalue, and use the monitoring eigenvalue obtained within the window length before the target eigenvalue as the reference eigenvalue;

[0050] An action determination module, used to determine a reference action corresponding to the target feature value according to a reward value corresponding to each reference feature value, wherein the reward value is determined according to a reference action corresponding to the reference feature value, and the reference action includes an alarm action and a normal action;

[0051] A window adjustment module, used to adjust the window length according to the reference action corresponding to the target feature value, and update the corresponding reference feature value according to the adjusted window length;

[0052] The monitoring alarm module is used to determine the cumulative alarm reward and the cumulative normal reward according to the reward value corresponding to the reference characteristic value after update, and determine the alarm state corresponding to the target characteristic value according to the cumulative alarm reward and the cumulative normal reward, and the alarm state includes alarm and normal.

[0053] In a possible implementation manner, the reference feature value determination module is further used to:

[0054] The window length adjusted based on the reference action corresponding to the previous target feature value is determined as the initial window length of the current target feature value.

[0055] In a possible implementation, the action determination module is further configured to:

[0056] Determine the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target characteristic value according to the reward value corresponding to each reference characteristic value;

[0057] In response to the alarm confidence upper limit value being greater than the normal confidence upper limit value, determining the reference action corresponding to the target feature value as an alarm action;

[0058] In response to the normal confidence upper limit value being greater than the alarm confidence upper limit value, it is determined that the reference action corresponding to the target feature value is a normal action.

[0059] In a possible implementation, the action determination module is further configured to:

[0060] Counting the warning reward value and the normal reward value included in the reward value corresponding to each reference feature value;

[0061] The alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value are determined respectively according to each of the alarm reward values ​​and each of the normal reward values.

[0062] In a possible implementation, the action determination module is further configured to:

[0063] Determining an alarm estimation value according to each of the alarm reward values ​​and the position of the corresponding reference feature value, and a preset forgetting factor;

[0064] Determine a normal estimation value according to each of the normal reward values ​​and the position of the corresponding reference feature value, and the forgetting factor;

[0065] Determine an alarm metric value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics, wherein the dynamic probability is determined according to the window length corresponding to the target feature value;

[0066] Determine a normal measurement value according to the forgetting factor, the dynamic probability and the normal reward value quantity obtained by statistics;

[0067] Calculate the product of the alarm metric value and a preset control coefficient, and the sum of the product and the alarm estimation value as the alarm confidence upper limit value;

[0068] The product of the normal measurement value and the preset control coefficient is calculated, and the sum of the product and the normal estimated value is used as the normal confidence upper limit value.

[0069] In a possible implementation, the action determination module is further configured to:

[0070] By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a1) is the number of alarm reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the alarm estimation value, r a1 is the alarm reward value corresponding to the reference feature value.

[0071] In a possible implementation, the action determination module is further configured to:

[0072] By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a2) is the number of normal reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the normal estimated value, r a2 is the normal reward value corresponding to the reference feature value.

[0073] In a possible implementation, the action determination module is further configured to:

[0074] By formula The alarm metric value is calculated, where p is a dynamic probability value.

[0075] In a possible implementation, the action determination module is further configured to:

[0076] By formula The normality metric is calculated, where p is a dynamic probability value.

[0077] In a possible implementation, the window adjustment module is further used to:

[0078] In response to the reference action corresponding to the target feature value being the same as the reference action corresponding to the previous target feature value, determining to extend the window length by 1;

[0079] In response to the reference action corresponding to the target feature value being different from the reference action corresponding to a previous target feature value, the window length is scaled according to a preset scaling parameter.

[0080] In a possible implementation, the window adjustment module is further used to:

[0081] Calculating the product of the window length and the scaling parameter, and rounding the product to obtain a candidate length;

[0082] In response to the candidate length being greater than a preset shortest length, determining the candidate length to be an adjusted window length;

[0083] In response to the candidate length being smaller than the shortest length, determining the shortest length as the adjusted window length.

[0084] In a possible implementation manner, the device further includes:

[0085] A reward value calculation module is used to calculate the corresponding reward value according to the target feature value and the reference action.

[0086] In a possible implementation, the reward value calculation module is further used to:

[0087] In response to the reference action being an alarm action, the formula 1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value, where Stat is the target feature value and Stat_UCL is the preset feature value threshold.

[0088] In a possible implementation, the reward value calculation module is further used to:

[0089] In response to the reference action being a normal action, the formula 1-1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value.

[0090] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0091] According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0092] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0093] In an embodiment of the present disclosure, the monitoring characteristic values ​​monitored during the production process are obtained multiple times according to a preset time period as target characteristic values, the initial window length of the target characteristic value is determined, and the monitoring characteristic values ​​obtained within the window length before the target characteristic value are determined as reference characteristic values. The reference action corresponding to the target characteristic value is determined according to the reward value corresponding to each reference characteristic value. The window length is adjusted according to the reference action corresponding to the target characteristic value to update the reference characteristic value. The cumulative alarm reward and the cumulative normal reward are determined according to the reward value corresponding to the updated reference characteristic value to determine the alarm state corresponding to the target characteristic value. The present disclosure determines the alarm state of the next cycle according to the characteristic value that has determined the alarm state by setting the reward value. This method considers multiple monitoring characteristic values ​​of a stage when determining the alarm state to avoid false alarms due to instantaneous characteristic value changes.

[0094] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0096] Figure 1 A flowchart of a real-time monitoring alarm method according to an embodiment of the present disclosure is shown;

[0097] Figure 2 A schematic diagram showing a target characteristic value and a reference characteristic value according to an embodiment of the present disclosure;

[0098] Figure 3 A schematic diagram of a real-time monitoring alarm device according to an embodiment of the present disclosure;

[0099] Figure 4 A schematic diagram showing an electronic device according to an embodiment of the present disclosure;

[0100] Figure 5 A schematic diagram showing another electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0101] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0102] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0103] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0104] The real-time monitoring alarm method of the embodiment of the present disclosure can be executed by an electronic device such as a terminal device or a server. Among them, the terminal device can be any fixed or mobile terminal such as a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server can be a single server or a server cluster composed of multiple servers. Any electronic device can implement the real-time monitoring alarm method of the embodiment of the present disclosure by a processor calling a computer-readable instruction stored in a memory.

[0105] Figure 1 FIG. 1 is a flow chart showing a real-time monitoring alarm method according to an embodiment of the present disclosure. Figure 1 As shown, the real-time monitoring alarm method of the embodiment of the present disclosure may include the following steps S10-S50.

[0106] Step S10: acquiring the monitoring characteristic values ​​monitored during the production process multiple times according to a preset time period, and determining the currently acquired monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is acquired.

[0107] In a possible implementation, the real-time monitoring and alarm method of the disclosed embodiment can be applied to real-time monitoring of industrial production processes in any field such as steel, metallurgy, energy, and chemical industry, so as to timely alarm when equipment failure, component failure, or illegal operation occurs in the production process, prompting the staff to deal with emergencies in the production process to avoid danger. Among them, the electronic device can obtain the monitoring characteristic value characterizing the production status obtained by monitoring during the production process for multiple times in a preset time period, and determine whether an alarm is required each time the monitoring characteristic value is obtained according to the preset alarm strategy. The monitoring characteristic value can be sensor data obtained by sensor detection during the production process, or a value characterizing whether the state of the production process is normal obtained by calculating and processing the sensor data obtained by multiple sensors.

[0108] Optionally, the electronic device obtains the monitoring characteristic value multiple times according to a preset time period, and determines the current monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is obtained. For example, when the monitoring characteristic value obtained by the electronic device in a certain period is T1, T1 is determined to be the target characteristic value. When the electronic device re-acquires the monitoring characteristic value as T2 in the next period, T1 obtained in the previous period is no longer used as the target characteristic value, and T2 is updated to the new target characteristic value.

[0109] Step S20: determine the initial window length of the target feature value, and use the monitoring feature value obtained within the window length before the target feature value as a reference feature value.

[0110] In a possible implementation, the electronic device may adjust the initial window length when determining the initial window length corresponding to the current target characteristic value and determining the alarm state at the time of obtaining the current target characteristic value. Wherein, when the current target characteristic value is the monitoring characteristic value obtained for the first time, the window length corresponding to the target characteristic value may be 0. When the current target characteristic value is not the monitoring characteristic value obtained for the first time, the window length corresponding to the current target characteristic value may inherit the adjusted window length of the previous target characteristic value.

[0111] Optionally, after determining the initial window length corresponding to the current target feature value, the electronic device obtains multiple monitoring feature values ​​obtained before the current target feature value according to the window length as reference feature values ​​corresponding to the current target feature value. Exemplarily, when the window length corresponding to the current target feature value is 3, the electronic device sequentially obtains three monitoring feature values ​​before the current target feature value as corresponding reference feature values.

[0112] Figure 2 A schematic diagram showing a target characteristic value and a reference characteristic value according to an embodiment of the present disclosure is shown. Figure 2 As shown, the monitoring feature value obtained at the current time k is T k In the case of k When the initial window length corresponding to the current target feature value is 3, the electronic device can sequentially determine the three monitoring feature values ​​T that are acquired adjacent to the current target feature value. k-1 , T k-2 and T k-3 is the corresponding reference eigenvalue.

[0113] Step S30: Determine a reference action corresponding to the target feature value according to the reward value corresponding to each reference feature value.

[0114] In a possible implementation, each reference characteristic value has a corresponding reward value, which is used to characterize the influence of the state of the reference characteristic value selecting alarm or no alarm at the corresponding moment on the current moment. After determining multiple reference characteristic values ​​corresponding to the current target characteristic value, the electronic device determines the reward value corresponding to the reference characteristic value to determine the reference action of the target characteristic value according to the reward values ​​of the multiple reference characteristic values. Among them, the reference action includes an alarm action and a normal action, the alarm action represents that an alarm may be needed at the corresponding moment, and the normal action represents that an alarm may not be needed at the corresponding moment. The reward value corresponding to each reference characteristic value can be determined based on the reference action corresponding to the alarm state of the reference characteristic value at the corresponding moment.

[0115] Optionally, the process of the electronic device determining the reference action of the target feature value according to the reward value corresponding to each reference feature value may include: determining the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value according to the reward value corresponding to each reference feature value. In response to the alarm confidence upper limit value being greater than the normal confidence upper limit value, the reference action corresponding to the target feature value is determined to be an alarm action. In response to the normal confidence upper limit value being greater than the alarm confidence upper limit value, the reference action corresponding to the target feature value is determined to be a normal action. Among them, the alarm confidence upper limit is used to characterize the probability that the reference action corresponding to the current target feature value is an alarm action, and the normal confidence upper limit is used to characterize the probability that the reference action corresponding to the current target feature value is a non-alarm action. That is, the electronic device can determine that the reference action corresponding to the target feature value is an alarm when the probability of alarm is large, and determine that the reference action corresponding to the target feature value is a non-alarm when the probability of non-alarm is large. The reference action is only used as a reference for alarm or non-alarm at the current moment to generate a reward value for determining the alarm state at the next moment, and is not directly used to determine the final alarm state.

[0116] Furthermore, the reward value corresponding to each reference characteristic value may be an alarm reward value or a normal reward value, the alarm reward value being a reward value calculated when the reference action corresponding to the reference characteristic value is an alarm action, and the normal reward value being a reward value calculated when the reference action corresponding to the reference characteristic value is a normal action. The electronic device may calculate the alarm confidence upper limit value and the normal confidence upper limit value by counting the alarm reward value and the normal reward value in the reward value of the reference characteristic value corresponding to the current target characteristic value. That is, the electronic device may first count the alarm reward value and the normal reward value included in the reward value corresponding to each reference characteristic value, and then determine the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target characteristic value according to each alarm reward value and each normal reward value.

[0117] In a possible implementation, both the alarm confidence upper limit value and the normal confidence upper limit value can be determined by corresponding estimated values, measurement values ​​and preset control coefficients. Among them, the estimated value is used to characterize the possibility that the reference action of the target feature value is the corresponding action, the measurement value is used to characterize the uncertainty that the reference action of the target feature value is the corresponding action, and the control coefficient is a preset value used as the weight of the measurement value.

[0118] Exemplarily, the electronic device can determine the alarm estimation value according to the position of each alarm reward value and the corresponding reference characteristic value, and the preset forgetting factor, and determine the alarm measurement value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics. Then calculate the product of the alarm measurement value and the preset control coefficient, and the sum of the alarm estimation value as the alarm confidence upper limit value. Among them, the position of the reference characteristic value corresponding to each alarm reward value is a numerical value representing its acquisition order, that is, the reference characteristic value is the monitoring characteristic value acquired by the electronic device for the nth time. For example, when the corresponding reference characteristic value is the monitoring characteristic value acquired by the electronic device for the i-th time, the position of the reference characteristic value is determined to be i. The preset forgetting factor is a value between 0 and 1, which is used to reduce the influence of the reference characteristic value far from the target characteristic value on the calculation result. The dynamic probability is determined according to the window length corresponding to the target characteristic value, and the smaller the window length is, for example, it can be the reciprocal of the window length.

[0119] Among them, the alarm estimation value can be obtained by the formula Calculated, the alarm metric value can be obtained through the formula Calculated. λ is the forgetting factor, N K (a1) is the number of alarm reward values ​​obtained by statistics, that is, the number of reference feature values ​​corresponding to the alarm reward value. i is the position of the reference feature value corresponding to the alarm estimation value, r a1 is the alarm reward value corresponding to the reference feature value, and p is the dynamic probability value. Indicates that the alarm metric value is Indicates that when the control coefficient is represented by c, the calculated alarm confidence upper limit value can be

[0120] Furthermore, the method for determining the normal confidence upper limit is similar to the method for determining the alarm confidence upper limit. That is, the electronic device can determine the normal estimation value according to the position of each normal reward value and the corresponding reference characteristic value, and the forgetting factor. The normal measurement value is determined according to the forgetting factor, the dynamic probability and the number of normal reward values ​​obtained by statistics, and the product of the normal measurement value and the preset control coefficient is calculated, and the sum of the normal estimation value is used as the normal confidence upper limit. Among them, the statistically obtained normal reward value is the number of reference characteristic values ​​corresponding to the normal reward value.

[0121] Among them, the normal estimate can be obtained by the formula Calculated, the normal measurement value can be obtained by the formula Calculated. λ is the forgetting factor, N K (a2) is the number of normal reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the normal estimated value, r a2 is the normal reward value corresponding to the reference feature value, and p is the dynamic probability value. Indicates that normal measurement values ​​are passed Indicates that when the control coefficient is represented by c, the calculated normal confidence upper limit value can be

[0122] Optionally, after calculating the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target characteristic value, the electronic device determines the reference action corresponding to the target characteristic value by comparing the values. That is, when the alarm confidence upper limit value is greater than the normal confidence upper limit value, the reference action of the target characteristic value is determined to be the alarm action, and when the normal confidence upper limit value is greater than the alarm confidence upper limit value, the reference action of the target characteristic value is determined to be the normal action.

[0123] In a possible implementation, after determining the reference action corresponding to the target feature value, the electronic device can also calculate the corresponding reward value according to the target feature value and the reference action, so as to determine the reference action corresponding to the next monitoring feature value obtained. In the case where the reference action is an alarm action, the electronic device can calculate the reward value according to the formula 1 / (1+e Stat -Stat_UCL ) to calculate the reward value corresponding to the target feature value. When the reference action is a normal action, the electronic device can calculate the reward value corresponding to the target feature value by the formula 1-1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value. Stat is the target feature value, and Stat_UCL is the preset feature value threshold. Optionally, the reward value corresponding to each reference feature value can also be determined in the same way.

[0124] Step S40: adjusting the window length according to the reference action corresponding to the target feature value, and updating the corresponding reference feature value according to the adjusted window length.

[0125] In a possible implementation, after the electronic device determines the reference action corresponding to the target feature value, the current window length is adjusted according to a preset adjustment rule and the reference action, and the reference feature value corresponding to the target feature value is updated after the window length is adjusted. For example, when the current target feature value is T k , corresponding to the initial window length of 3, the three reference eigenvalues ​​determined by the electronic device in sequence are T k-1 , T k-2 and T k-3 When the window length is adjusted to 2, the reference eigenvalue corresponding to the target eigenvalue is updated to T k-1 and T k-2 When the window length is adjusted to 4, the reference eigenvalue corresponding to the target eigenvalue is updated to T k-1 , T k-2 、T k-3 and T k-4 .

[0126] Optionally, the electronic device can adjust the window length according to the change of the reference action corresponding to the target feature value and the adjacent feature value. That is, the electronic device can compare the reference action of the current target feature value to see whether it is the same as the reference action corresponding to the previous target feature value, and the previous target feature value is the monitoring feature value obtained in the previous cycle of the current target feature value. When the reference action corresponding to the target feature value is the same as the reference action corresponding to the previous target feature value, it is determined to extend the window length by 1. When the reference action corresponding to the target feature value is different from the reference action corresponding to the previous target feature value, the window length is scaled according to a preset scaling parameter. That is, when the current reference action is a normal action and the reference action corresponding to the previous target feature value is also a normal action, or when the current reference action is an alarm action and the reference action corresponding to the previous target feature value is also an alarm action, the electronic device extends the window length by 1. When the current reference action is an alarm action and the reference action corresponding to the previous target feature value is a normal action, or when the current reference action is a normal action and the reference action corresponding to the previous target feature value is an alarm action, the electronic device scales the window length according to a preset scaling parameter. The scaling parameter can be a preset value between 0 and 1.

[0127] Furthermore, the electronic device may scale the window length by the scaling parameter by rounding the product of the window length and the scaling parameter to obtain a candidate length, and then determine the adjusted window length according to the size of the candidate length. Wherein, when the candidate length is greater than a preset minimum length, the candidate length is determined to be the adjusted window length. When the candidate length is less than the minimum length, the shortest length is determined to be the adjusted window length.

[0128] Step S50: Determine the cumulative alarm reward and the cumulative normal reward according to the reward value corresponding to the reference characteristic value after update, and determine the alarm state corresponding to the target characteristic value according to the cumulative alarm reward and the cumulative normal reward.

[0129] In one possible implementation, after determining the updated reference characteristic value, the electronic device calculates the cumulative alarm reward and the cumulative normal reward by using the reward value corresponding to the updated reference characteristic value. The cumulative alarm reward is the sum of the alarm reward values ​​in the reward value corresponding to the updated reference characteristic value, and the cumulative normal reward is the sum of the normal reward values ​​in the reward value corresponding to the updated reference characteristic value. After the electronic device determines the cumulative alarm reward and the cumulative normal reward, the alarm state corresponding to the target characteristic value can be determined based on the cumulative alarm reward and the cumulative normal reward. The alarm state can include alarm and normal, which is used to determine whether an alarm is needed at the current moment. The determination method can be to compare the size of the cumulative alarm reward and the cumulative normal reward, and determine the alarm state as alarm when the cumulative alarm reward is larger, and determine the alarm state as normal when the cumulative normal reward is larger.

[0130] Furthermore, when the electronic device determines the alarm state corresponding to the target characteristic value, it selects to alarm or not to alarm according to the alarm state. Alternatively, the electronic device may calculate the corresponding alarm state before acquiring the target characteristic value, and directly alarm if the alarm state is alarm, and continue to acquire the target characteristic value if the alarm state is normal.

[0131] Based on the above technical features, the embodiment of the present disclosure can determine the alarm state of the next cycle according to multiple monitoring characteristic values ​​that have already determined the alarm state by setting a reward value, that is, considering multiple monitoring characteristic values ​​within a time interval for alarming, avoiding false alarms or missed alarms caused by changes in instantaneous characteristic values. At the same time, the embodiment of the present disclosure determines the alarm state by dynamically obtaining the reward value corresponding to the monitoring characteristic value that has a greater impact on the alarm state of the next cycle by setting a dynamic time window, thereby improving the accuracy of the alarm state and reducing the amount of calculation due to the screening of the monitoring characteristic values.

[0132] Figure 3 A schematic diagram of a real-time monitoring alarm device according to an embodiment of the present disclosure. Figure 3As shown, the real-time monitoring alarm device of the embodiment of the present disclosure may include:

[0133] A target characteristic value determination module 30 is used to obtain the monitoring characteristic values ​​monitored during the production process multiple times according to a preset time period, and determine the currently obtained monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is obtained;

[0134] A reference eigenvalue determination module 31 is used to determine the initial window length of the target eigenvalue and use the monitoring eigenvalue obtained within the window length before the target eigenvalue as a reference eigenvalue;

[0135] An action determination module 32, configured to determine a reference action corresponding to the target feature value according to a reward value corresponding to each reference feature value, wherein the reward value is determined according to a reference action corresponding to the reference feature value, and the reference action includes an alarm action and a normal action;

[0136] A window adjustment module 33, configured to adjust the window length according to the reference action corresponding to the target feature value, and update the corresponding reference feature value according to the adjusted window length;

[0137] The monitoring alarm module 34 is used to determine the cumulative alarm reward and the cumulative normal reward according to the reward value corresponding to the reference characteristic value after update, and determine the alarm state corresponding to the target characteristic value according to the cumulative alarm reward and the cumulative normal reward, and the alarm state includes alarm and normal.

[0138] In a possible implementation, the reference feature value determination module 34 is further configured to:

[0139] The window length adjusted based on the reference action corresponding to the previous target feature value is determined as the initial window length of the current target feature value.

[0140] In a possible implementation, the action determination module 32 is further configured to:

[0141] Determine the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target characteristic value according to the reward value corresponding to each reference characteristic value;

[0142] In response to the alarm confidence upper limit value being greater than the normal confidence upper limit value, determining the reference action corresponding to the target feature value as an alarm action;

[0143] In response to the normal confidence upper limit value being greater than the alarm confidence upper limit value, it is determined that the reference action corresponding to the target feature value is a normal action.

[0144] In a possible implementation, the action determination module 32 is further configured to:

[0145] Counting the warning reward value and the normal reward value included in the reward value corresponding to each reference feature value;

[0146] The alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value are determined respectively according to each of the alarm reward values ​​and each of the normal reward values.

[0147] In a possible implementation, the action determination module 32 is further configured to:

[0148] Determining an alarm estimation value according to each of the alarm reward values ​​and the position of the corresponding reference feature value, and a preset forgetting factor;

[0149] Determine a normal estimation value according to each of the normal reward values ​​and the position of the corresponding reference feature value, and the forgetting factor;

[0150] Determine an alarm metric value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics, wherein the dynamic probability is determined according to the window length corresponding to the target feature value;

[0151] Determine a normal measurement value according to the forgetting factor, the dynamic probability and the normal reward value quantity obtained by statistics;

[0152] Calculate the product of the alarm metric value and a preset control coefficient, and the sum of the product and the alarm estimation value as the alarm confidence upper limit value;

[0153] The product of the normal measurement value and the preset control coefficient is calculated, and the sum of the product and the normal estimated value is used as the normal confidence upper limit value.

[0154] In a possible implementation, the action determination module 32 is further configured to:

[0155] By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a1) is the number of alarm reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the alarm estimation value, r a1 is the alarm reward value corresponding to the reference feature value.

[0156] In a possible implementation, the action determination module 32 is further configured to:

[0157] By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a2) is the number of normal reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the normal estimated value, r a2 is the normal reward value corresponding to the reference feature value.

[0158] In a possible implementation, the action determination module 32 is further configured to:

[0159] By formula The alarm metric value is calculated, where p is a dynamic probability value.

[0160] In a possible implementation, the action determination module 32 is further configured to:

[0161] By formula The normality metric is calculated, where p is a dynamic probability value.

[0162] In a possible implementation, the window adjustment module 33 is further configured to:

[0163] In response to the reference action corresponding to the target feature value being the same as the reference action corresponding to the previous target feature value, determining to extend the window length by 1;

[0164] In response to the reference action corresponding to the target feature value being different from the reference action corresponding to a previous target feature value, the window length is scaled according to a preset scaling parameter.

[0165] In a possible implementation, the window adjustment module 33 is further configured to:

[0166] Calculating the product of the window length and the scaling parameter, and rounding the product to obtain a candidate length;

[0167] In response to the candidate length being greater than a preset shortest length, determining the candidate length to be an adjusted window length;

[0168] In response to the candidate length being smaller than the shortest length, determining the shortest length as the adjusted window length.

[0169] In a possible implementation manner, the device further includes:

[0170] A reward value calculation module is used to calculate the corresponding reward value according to the target feature value and the reference action.

[0171] In a possible implementation, the reward value calculation module is further used to:

[0172] In response to the reference action being an alarm action, the formula 1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value, where Stat is the target feature value and Stat_UCL is the preset feature value threshold.

[0173] In a possible implementation, the reward value calculation module is further used to:

[0174] In response to the reference action being a normal action, the formula 1-1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value.

[0175] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0176] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0177] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0178] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0179] Figure 4 A schematic diagram of an electronic device 800 according to an embodiment of the present disclosure is shown. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0180] Reference Figure 4 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0181] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0182] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0183] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0184] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0185] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0186] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0187] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of the components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0188] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0189] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0190] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above method.

[0191] Figure 5 1 is a schematic diagram showing another electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Figure 5 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0192] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0193] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0194] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0195] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0196] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0197] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0198] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0199] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0200] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0201] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0202] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A real-time monitoring and alarm method, characterized in that: The method comprises: Acquire the monitoring characteristic value monitored during the production process multiple times according to a preset time period, and determine the currently acquired monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is acquired; Determine the initial window length of the target characteristic value, and use the monitoring characteristic value obtained within the window length before the target characteristic value as a reference characteristic value; Determine a reference action corresponding to the target feature value according to a reward value corresponding to each reference feature value, wherein the reward value is determined according to a reference action corresponding to the reference feature value, and the reference action includes an alarm action and a normal action; Adjusting the window length according to the reference action corresponding to the target feature value, and updating the corresponding reference feature value according to the adjusted window length; The cumulative alarm reward and the cumulative normal reward are determined according to the reward value corresponding to the reference characteristic value after update, and the alarm state corresponding to the target characteristic value is determined according to the cumulative alarm reward and the cumulative normal reward, and the alarm state includes alarm and normal.

2. The method according to claim 1, characterized in that The determining of the initial window length of the target feature value comprises: The window length adjusted based on the reference action corresponding to the previous target feature value is determined as the initial window length of the current target feature value.

3. The method according to claim 1 or 2, characterized in that: The step of determining the reference action corresponding to the target feature value according to the reward value corresponding to each reference feature value includes: Determine the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target characteristic value according to the reward value corresponding to each reference characteristic value; In response to the alarm confidence upper limit value being greater than the normal confidence upper limit value, determining the reference action corresponding to the target feature value as an alarm action; In response to the normal confidence upper limit value being greater than the alarm confidence upper limit value, it is determined that the reference action corresponding to the target feature value is a normal action.

4. The method according to claim 3, characterized in that The step of determining the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value according to the reward value corresponding to each reference feature value includes: Counting the warning reward value and the normal reward value included in the reward value corresponding to each reference feature value; The alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value are determined respectively according to each of the alarm reward values ​​and each of the normal reward values.

5. The method according to claim 4, characterized in that The step of respectively determining the alarm confidence upper limit value and the normal confidence upper limit value corresponding to the target feature value according to each of the alarm reward values ​​and each of the normal reward values ​​comprises: Determining an alarm estimation value according to each of the alarm reward values ​​and the position of the corresponding reference feature value, and a preset forgetting factor; Determine a normal estimation value according to each of the normal reward values ​​and the position of the corresponding reference feature value, and the forgetting factor; Determine an alarm metric value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics, wherein the dynamic probability is determined according to the window length corresponding to the target feature value; Determine a normal measurement value according to the forgetting factor, the dynamic probability and the normal reward value quantity obtained by statistics; Calculate the product of the alarm metric value and a preset control coefficient, and the sum of the product and the alarm estimation value as the alarm confidence upper limit value; The product of the normal measurement value and the preset control coefficient is calculated, and the sum of the product and the normal estimated value is used as the normal confidence upper limit value.

6. The method according to claim 5, characterized in that The step of determining the alarm estimation value according to each of the alarm reward values ​​and the position of the corresponding reference feature value, and a preset forgetting factor, comprises: By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a1) is the number of alarm reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the alarm estimation value, r a1 is the alarm reward value corresponding to the reference feature value.

7. The method according to claim 5 or 6, characterized in that: The determining of the normal estimation value according to each of the normal reward values ​​and the corresponding reference feature value position, and the forgetting factor, comprises: By formula Calculate the alarm estimate, where λ is the forgetting factor, N K (a2) is the number of normal reward values ​​obtained by statistics, i is the position of the reference feature value corresponding to the normal estimated value, r a2 is the normal reward value corresponding to the reference feature value.

8. The method according to claim 6 or 7, characterized in that: The step of determining the alarm metric value according to the forgetting factor, the dynamic probability and the number of alarm reward values ​​obtained by statistics includes: By formula The alarm metric value is calculated, where p is a dynamic probability value.

9. The method according to claim 7 or 8, characterized in that: The determining of the normal measurement value according to the forgetting factor, the dynamic probability and the normal reward value quantity obtained by statistics includes: By formula The normality metric is calculated, where p is a dynamic probability value.

10. The method according to any one of claims 1 to 9, characterized in that: The adjusting the window length according to the reference action corresponding to the target feature value includes: In response to the reference action corresponding to the target feature value being the same as the reference action corresponding to the previous target feature value, determining to extend the window length by 1; In response to the reference action corresponding to the target feature value being different from the reference action corresponding to a previous target feature value, the window length is scaled according to a preset scaling parameter.

11. The method according to claim 10, characterized in that The step of scaling the window length according to a preset scaling parameter includes: Calculating the product of the window length and the scaling parameter, and rounding the product to obtain a candidate length; In response to the candidate length being greater than a preset shortest length, determining the candidate length to be an adjusted window length; In response to the candidate length being smaller than the shortest length, determining the shortest length as the adjusted window length.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: A corresponding reward value is calculated according to the target feature value and the reference action.

13. The method according to claim 12, characterized in that The calculating a corresponding reward value according to the target feature value and the reference action includes: In response to the reference action being an alarm action, the formula 1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value, where Stat is the target feature value and Stat_UCL is the preset feature value threshold.

14. The method according to claim 13, characterized in that The calculating of the corresponding reward value according to the target feature value and the reference action also includes: In response to the reference action being a normal action, the formula 1-1 / (1+e Stat-Stat_UCL ) calculates the reward value corresponding to the target feature value.

15. A real-time monitoring alarm device, characterized in that: The device comprises: A target characteristic value determination module is used to obtain the monitoring characteristic values ​​monitored during the production process multiple times according to a preset time period, and determine the currently obtained monitoring characteristic value as the target characteristic value each time the monitoring characteristic value is obtained; A reference eigenvalue determination module, used to determine the initial window length of the target eigenvalue, and use the monitoring eigenvalue obtained within the window length before the target eigenvalue as the reference eigenvalue; An action determination module, used to determine a reference action corresponding to the target feature value according to a reward value corresponding to each reference feature value, wherein the reward value is determined according to a reference action corresponding to the reference feature value, and the reference action includes an alarm action and a normal action; A window adjustment module, used to adjust the window length according to the reference action corresponding to the target feature value, and update the corresponding reference feature value according to the adjusted window length; The monitoring alarm module is used to determine the cumulative alarm reward and the cumulative normal reward according to the reward value corresponding to the reference characteristic value after update, and determine the alarm state corresponding to the target characteristic value according to the cumulative alarm reward and the cumulative normal reward, and the alarm state includes alarm and normal.

16. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 14 when executing the instructions stored in the memory.

17. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 14 is implemented.

Citation Information

Patent Citations

  • Monitoring method and system for production line equipment

    CN101694580A

  • Depth weighted double-Q learning-based large-scale monitoring method and monitoring robot

    CN107292392A

  • Driver working state monitoring system and driver working state monitoring method

    CN107845238A

  • Fault alarm parameter adjustment method and device, electronic equipment and storage medium

    CN112131081A

  • Dynamic alarm threshold determination method

    CN114446033A