Enterprise safety production monitoring system and method based on power utilization monitoring terminal

Abstract

The invention discloses an enterprise safety production monitoring system and method based on a power utilization monitoring terminal, and belongs to the field of enterprise power utilization monitoring. The invention discloses an enterprise safety production monitoring method based on a power utilization monitoring terminal. The method comprises the following steps: S1, collecting power data for enterprise production; s2, according to the type of the enterprise, performing alarm identification on the power data of the enterprise by adopting different alarm models; s3, obtaining the alarm frequency, the rectification standard-reaching rate and the power utilization stability of the enterprise, and calculating the safety index of the enterprise in combination with the alarm identification result; and S4, according to the safety index of the enterprise, the type of the enterprise and the alarm identification result, adjusting the supervision means of the enterprise, and improving the safety production level. The enterprise alarm types are divided into types such as production-halted enterprise bright-stop and dark-start, production-halted enterprise rework and the like, so that the characteristics in the power data can be extracted in a targeted manner, and the accuracy of alarm identification is improved.

Description

Technical Field

[0001] The present invention relates to the field of enterprise electricity consumption monitoring, and more specifically, to an enterprise production safety monitoring system and method based on an electricity consumption monitoring terminal. Background Art

[0002] In order to further strengthen the safety production supervision of high-risk enterprises, it is necessary to conduct big data analysis on the monitoring data of smart terminals, learn the current operation rules of the enterprise production lines, and complete the real-time current monitoring and alarm function of smart terminals, so as to achieve real-time and accurate supervision of the main production lines and key areas of high-risk enterprises.

[0003] After searching, a patent document with the existing publication number CN118396223A provides a method for intelligent analysis and monitoring of abnormal electricity consumption of an enterprise. The method collects and analyzes the historical electricity consumption data of the enterprise, and issues an alarm when the electricity consumption of the enterprise fluctuates abnormally.

[0004] The above patent collects the power data of the enterprise production and uses similarity analysis to determine whether the fluctuation of the enterprise power consumption is abnormal, and issues an early warning based on the judgment result; this analysis method cannot effectively extract the features contained in the enterprise power data, resulting in a single alarm category and an inability to effectively analyze the types of abnormal business operations of the enterprise. In view of this, we propose an enterprise production safety monitoring system and method based on power consumption monitoring terminals. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] The purpose of the present invention is to provide an enterprise production safety monitoring system and method based on an electricity consumption monitoring terminal to solve the problems raised in the above background technology.

[0007] 2. Technical solution

[0008] The present invention is achieved through the following technical solutions:

[0009] An enterprise production safety monitoring system and method based on an electricity consumption monitoring terminal comprises the following steps:

[0010] S1. Collect the electricity data used in enterprise production;

[0011] S2. According to the type of enterprise, different alarm models are used to identify the alarm of the enterprise's power data;

[0012] S3. Obtain the alarm frequency, rectification compliance rate, and power consumption stability of the enterprise, and calculate the enterprise's safety index based on the alarm identification results;

[0013] S4. Adjust the supervision measures on the enterprise according to its safety indicators, enterprise type and alarm identification results to improve the level of production safety.

[0014] As an optional solution of the technical solution of this application document, the power data includes current data, power data and timestamp.

[0015] As an optional solution to the technical solution of this application document, the results of the alarm identification include: a suspended enterprise that stops production in public but starts production in secret, a suspended enterprise that stops production and resumes work, an enterprise's emergency production shutdown, an enterprise's hot work, abnormal changes in the enterprise's fire-fighting equipment, an enterprise's automatic shutdown, and an enterprise's long-term shutdown.

[0016] As an optional solution of the technical solution of this application document, in S2, the alarm model is a neural network model, and its output layer adopts a softmax function. The training method of the alarm model includes:

[0017] A1. Collect electricity data of enterprises of the same type;

[0018] A2. Segment the power data according to the set time interval;

[0019] A3. Alarm the divided power data;

[0020] A4. Use the power data after alarm marking to train the alarm model.

[0021] As an optional solution to the technical solution of this application document, the types of enterprises include: hazardous chemical enterprises, mining enterprises, metallurgical enterprises and general industrial and commercial enterprises.

[0022] As an optional solution of the technical solution of this application document, in S3, the safety index of the enterprise is calculated using the following formula:

[0023]

[0024] x1 = number of alarms / number of days in the observation period;

[0025] x2 = number of rectifications that meet the standards / total number of rectifications;

[0026] x3=1-standard deviation of power consumption fluctuation / average power consumption;

[0027] Among them, S is the safety index of the enterprise, is the weight vector, is the recognition result of the alarm recognition model, x1 is the alarm frequency, x2 is the rectification compliance rate, x3 is the power consumption stability, and w1 to w3 are weight coefficients.

[0028] As an optional solution of the technical solution of this application document, S4 specifically includes:

[0029] The safety threshold is determined according to the type of enterprise; if the safety index of the enterprise is lower than the safety threshold, an alarm will be issued to the enterprise; for enterprises of hazardous chemical enterprises, mining enterprises, and metallurgical enterprises, the monitoring intensity will be increased.

[0030] An enterprise safety production monitoring system based on an electricity consumption monitoring terminal comprises:

[0031] The data collection module is configured to: collect the enterprise production power data;

[0032] The data storage module is configured to store the enterprise's power data, alarm data, and rectification data;

[0033] The alarm identification module is configured to: identify the alarm identification result of the enterprise according to the power data of the enterprise;

[0034] The safety index calculation module is configured to: calculate the safety index of the enterprise according to the alarm identification result, power data, alarm data, and rectification data;

[0035] The alarm push module is configured to send alarm reports to management personnel and related enterprises based on the enterprise's security indicators and alarm identification results.

[0036] As an optional solution of the technical solution of this application document, it also includes a display module, which is configured to: display the enterprise's power data, alarm data, and rectification data.

[0037] 3. Beneficial effects

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. This application can effectively identify abnormal behaviors of enterprises and increase the accuracy of alarm identification by classifying enterprises and adopting different alarm identification models according to the types of enterprises.

[0040] 2. This application can extract features from power data in a targeted manner and increase the accuracy of alarm identification by dividing enterprise alarm types into types such as suspended production enterprises that openly stop but secretly start, suspended production enterprises that stop and resume work, enterprise emergency production shutdown, enterprise hot work, enterprise fire equipment changes, enterprise automatic shutdown, and enterprise long-term shutdown.

[0041] 3. This application conducts a comprehensive evaluation of the enterprise by taking into account the type of enterprise, alarm frequency, rectification compliance rate, and power consumption stability. It can comprehensively consider the operation of the enterprise and avoid wrong judgments made by a single evaluation rule, which will affect the normal operation of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1The present invention is a logic block diagram of an enterprise production safety monitoring method based on an electricity consumption monitoring terminal. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0044] Embodiment 1:

[0045] See also Figure 1 ,A method for monitoring safety of an enterprise based on an electricity consumption monitoring terminal comprises the following steps:

[0046] S1. Collect the electricity data used in enterprise production;

[0047] S2. According to the type of enterprise, different alarm models are used to identify the alarm of the enterprise's power data;

[0048] S3. Obtain the alarm frequency, rectification compliance rate, and power consumption stability of the enterprise, and calculate the enterprise's safety index based on the alarm identification results;

[0049] S4. Adjust the supervision measures on the enterprise according to its safety indicators, enterprise type and alarm identification results to improve the level of production safety.

[0050] In S1, power data includes current data, power data and timestamp. Through the connection between smart meters and the primary equipment of enterprises, accurate supervision of the production operations of the main production lines and key areas of high-risk enterprises can be achieved through real-time current and current changes.

[0051] In S2, the types of enterprises can be divided into hazardous chemical enterprises, mining enterprises, metallurgical enterprises and general industrial and commercial enterprises.

[0052] Due to the differences in enterprise types, the power data characteristics of different types of enterprises are different, and different alarm recognition models are needed for alarm recognition. The alarm recognition model uses a neural network model, and its output layer uses a softmax function; the training methods of the alarm model include:

[0053] A1. Collect electricity data of enterprises of the same type;

[0054] A2. Segment the power data according to the set time interval;

[0055] A3. Alarm the divided power data;

[0056] A4. Use the power data after alarm marking to train the alarm model.

[0057] In A3, the results of alarm identification include: the suspension of production of a suspended enterprise with an open shutdown and a concealed operation, the suspension and resumption of production of a suspended enterprise, the emergency production shutdown of an enterprise, the hot work of an enterprise, the abnormal change of fire-fighting equipment of an enterprise, the automatic suspension of production of an enterprise, and the long-term suspension of production of an enterprise. The segmented power data is marked according to the type of the alarm identification result; for example, [1,0,0,0,0,0,0] is used to indicate that a suspended enterprise is openly shut down and secretly operated, and [0,1,0,0,0,0,0] is used to indicate that a suspended enterprise is suspended and resumed.

[0058] A4 also includes sampling and normalization of power data. By preprocessing the power data, the training efficiency of the alarm model is increased.

[0059] In S3, the need for an alarm is determined by comprehensively considering the operation of the enterprise; the enterprise's safety index can be calculated using the following formula:

[0060]

[0061] x1 = number of alarms / number of days in the observation period;

[0062] x2 = number of rectifications that meet the standards / total number of rectifications;

[0063] x3=1-standard deviation of power consumption fluctuation / average power consumption;

[0064] Among them, S is the safety index of the enterprise, is the weight vector. The value of the weight vector varies according to the type of enterprise. is the recognition result of the alarm recognition model, x1 is the alarm frequency, x2 is the rectification compliance rate, x3 is the power consumption stability, w1 to w3 are weight coefficients, and the values ​​of the weight coefficients vary depending on the type of enterprise.

[0065] In S4, hazardous chemical enterprises, mining enterprises, and metallurgical enterprises are high-risk enterprises. These enterprises have great potential for safety accidents. The production operation areas and the start and stop of enterprises are strictly managed by the emergency department. Illegal production alarms need to be discovered and reminded in real time. Therefore, if the safety indicators of such enterprises are lower than the safety threshold, the enterprises will be warned and the monitoring efforts will be increased.

[0066] Compared with high-risk enterprises, general industrial and commercial enterprises have the characteristics of large number of enterprises, huge supervision volume, production conditions are easily affected by order conditions, and relatively small potential safety accident hazards. For general industrial and commercial enterprises, alarms are only statistically queried, and real-time reminders and disposal push are not required.

[0067] Embodiment 2:

[0068] The present invention provides an enterprise safety production monitoring system based on an electricity consumption monitoring terminal, comprising:

[0069] The data collection module is configured to: collect the enterprise production power data;

[0070] The data storage module is configured to store the enterprise's power data, alarm data, and rectification data;

[0071] The alarm identification module is configured to: identify the alarm identification result of the enterprise according to the power data of the enterprise;

[0072] The safety index calculation module is configured to: calculate the safety index of the enterprise according to the alarm identification result, power data, alarm data, and rectification data;

[0073] The alarm push module is configured to send alarm reports to management personnel and related enterprises based on the enterprise's security indicators and alarm identification results.

[0074] The display module is configured to display the enterprise's power data, alarm data, and rectification data.

[0075] The data acquisition module mainly includes smart meters, which are used to collect power data, and then the power data is cleaned, converted, loaded, and desensitized to form result data, which is then uploaded to the data storage module.

[0076] During the data communication process, checksum technology should be used to ensure the integrity of the data during the communication process. Before the communicating parties establish a connection, the application system should use cryptographic technology to perform session initialization verification and encrypt sensitive information fields during the communication process.

[0077] The data storage module should be able to prevent SQL injection intrusion, strengthen system application function authorization, strengthen system identity authentication, strengthen the verification of system input and output data, strictly control configuration management, strengthen the control of session creation and lifetime, and strengthen system exception and audit log functions.

[0078] The alarm identification module obtains necessary enterprise power data, alarm data, and rectification data by accessing the data storage module, and uses different alarm identification models to identify alarms for different types of enterprises. The safety indicator calculation module then processes the alarm identification results and scores the enterprises based on their types, alarm data, and rectification data. The alarm push module alerts the enterprises based on their scoring results.

Claims

1. A method for monitoring enterprise production safety based on an electricity consumption monitoring terminal, characterized in that: The following steps are involved: S1. Collect the electricity data used in enterprise production; S2. According to the type of enterprise, different alarm models are used to identify the alarm of the enterprise's power data; S3. Obtain the alarm frequency, rectification compliance rate, and power consumption stability of the enterprise, and calculate the enterprise's safety index based on the alarm identification results; S4. Adjust the supervision measures on the enterprise according to its safety indicators, enterprise type and alarm identification results to improve the level of production safety.

2. According to claim 1, a method for monitoring production safety of an enterprise based on an electricity consumption monitoring terminal is characterized in that: The power data includes current data, power data and a timestamp.

3. The enterprise safety production monitoring method based on the power consumption monitoring terminal according to claim 1 is characterized in that: The results of the alarm identification include: a suspended enterprise that is openly shut down but secretly running, a suspended enterprise that is shutting down and resuming production, an enterprise's emergency production shutdown, an enterprise's hot work, an enterprise's fire-fighting device changes, an enterprise's automatic shutdown, and an enterprise's long-term shutdown.

4. The enterprise production safety monitoring method based on the power consumption monitoring terminal according to claim 1 is characterized in that: In S2, the alarm model is a neural network model, whose output layer adopts a softmax function, and the training method of the alarm model includes: A1. Collect electricity data of enterprises of the same type; A2. Segment the power data according to the set time interval; A3. Alarm the divided power data; A4. Use the power data after alarm marking to train the alarm model.

5. The enterprise production safety monitoring method based on the power consumption monitoring terminal according to claim 1 is characterized in that: The types of enterprises mentioned include: hazardous chemical enterprises, mining enterprises, metallurgical enterprises and general industrial and commercial enterprises.

6. The enterprise production safety monitoring method based on the power consumption monitoring terminal according to claim 1 is characterized in that: In S3, the enterprise's security index is calculated using the following formula: x1 = number of alarms / number of days in the observation period; x2 = number of rectifications that meet the standards / total number of rectifications; x3=1-standard deviation of power consumption fluctuation / average power consumption; Among them, S is the safety index of the enterprise, is the weight vector, is the recognition result of the alarm recognition model, x1 is the alarm frequency, x2 is the rectification compliance rate, x3 is the power consumption stability, and w1 to w3 are weight coefficients.

7. The enterprise safety production monitoring method based on the power consumption monitoring terminal according to claim 1 is characterized by: The S4 specifically includes: The safety threshold is determined according to the type of enterprise; if the safety index of the enterprise is lower than the safety threshold, an alarm will be issued to the enterprise; for enterprises of hazardous chemical enterprises, mining enterprises, and metallurgical enterprises, the monitoring intensity will be increased.

8. An enterprise production safety monitoring system based on an electricity consumption monitoring terminal, using an enterprise production safety monitoring method based on an electricity consumption monitoring terminal as claimed in any one of claims 1 to 7, characterized in that: include: The data collection module is configured to: collect the enterprise production power data; The data storage module is configured to store the enterprise's power data, alarm data, and rectification data; The alarm identification module is configured to: identify the alarm identification result of the enterprise according to the power data of the enterprise; The safety index calculation module is configured to: calculate the safety index of the enterprise according to the alarm identification result, power data, alarm data, and rectification data; The alarm push module is configured to send alarm reports to management personnel and related enterprises based on the enterprise's security indicators and alarm identification results.

9. The enterprise production safety monitoring system based on the power consumption monitoring terminal according to claim 8 is characterized in that: It also includes a display module configured to display the enterprise's power data, alarm data, and rectification data.

Images