An intelligent power distribution network fault early warning system and method based on an internet of things

Abstract

The application relates to the technical field of power distribution network fault early warning systems and methods, in particular to an intelligent power distribution network fault early warning system and method based on the Internet of Things, which comprises a sensing unit, a data processing unit, a data analysis unit, a fault early warning unit, a monitoring management unit and a personnel inspection subsystem unit; the sensing unit is used for installing current sensors, voltage sensors, temperature sensors and humidity sensors at transformer, switch cabinet and line key node positions of a power distribution network; the current sensors are used for monitoring the current size in the line in real time; the voltage sensors are used for monitoring voltage values; and the temperature sensors are used for monitoring the operating temperature of equipment; the system analyzes and judges the fault from multiple angles, reduces the misjudgment and missed judgment, more accurately judges whether there is a fault hidden danger, performs real-time evaluation on the operating state of the equipment through the Internet of Things monitoring, appropriately reduces the frequency of manual inspection, saves the labor cost, and improves the resource utilization efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network fault early warning systems and methods, in particular to an intelligent power distribution network fault early warning system and method based on the Internet of Things. BACKGROUND

[0002] With the rapid development and intelligent transformation of the power industry, the stability and safety of the power distribution network become particularly important. Traditional power distribution network monitoring and fault handling methods have been difficult to meet the needs of modern power systems, and power distribution network fault detection methods often rely solely on manual inspection or post-analysis, resulting in problems such as delayed warning and low accuracy.

[0003] For example, the patent with the publication number CN114977519A discloses a power Internet of Things network management system and method, which relates to the technical field of power management systems. To solve the problem that existing network management systems cannot effectively utilize network resources, and the faults and potential problems encountered in the network greatly reduce the service quality of the network, resulting in the computer network being unable to run normally and stably for a long time. A power Internet of Things network management system and method, including a power management system and a network management system; the power management system includes an electric energy telemetry subsystem, a power distribution monitoring subsystem, and a load management subsystem; the network management system includes a device fault management subsystem and an optimized operation subsystem; the network resources are planned, configured, monitored, analyzed, and controlled through the device fault management subsystem, so that the network resources are effectively utilized.

[0004] However, the system is not convenient for the intelligent combination of the system and manual operation, which reduces the analysis and judgment of power distribution network faults from multiple angles and reduces the convenience of use. SUMMARY

[0005] To solve the above technical problems, the present application provides an intelligent power distribution network fault early warning system and method based on the Internet of Things, which analyzes and judges faults from multiple angles, reduces misjudgment and omission, more accurately judges whether there is a hidden danger, and real-time evaluates the running state of the equipment through Internet of Things monitoring, appropriately reduces the frequency of manual inspection, saves labor cost, and improves resource utilization efficiency.

[0006] The intelligent power distribution network fault early warning system based on the Internet of Things comprises a sensing unit, a data processing unit, a data analysis unit, a fault early warning unit, a monitoring management unit, and a personnel inspection subsystem unit.

[0007] The perception unit is used to install current sensors, voltage sensors, temperature sensors and humidity sensors at transformer, switch cabinet and line key node positions of the power distribution network, to monitor the current size in the line in real time through the current sensor, to monitor the voltage value through the voltage sensor, to monitor the operating temperature of the equipment through the temperature sensor, and to monitor the humidity through the humidity sensor; different sensors collect the operating parameters of the power distribution network according to a sampling frequency of once per second respectively;

[0008] The data processing unit is used to preprocess the data collected by the sensors, filter, amplify and analog-digital convert the collected data information; by removing noise interference in the collection process, then amplifying the weak sensor signal to a set range for processing, and then converting the analog signal to a digital signal, so as to facilitate data transmission and analysis;

[0009] The data analysis unit analyzes the preprocessed data using a data analysis algorithm, and classifies and predicts the fault type by using a support vector machine learning algorithm; by cleaning the data, removing duplicate data, then extracting features and analyzing the cleaned data, constructing a normal operating state model, then comparing the collected data model with the normal state model to calculate the deviation value, when the operating parameters of the power distribution network exceed the normal range or an abnormal trend occurs, a fault information is sent;

[0010] The fault warning unit sends alarm information to maintenance personnel and a monitoring platform according to the fault information sent by the data analysis unit, informs the location of the fault point, the temperature of the fault equipment and the possible fault type; according to the severity and type of the fault, different warning methods are set, for slight faults, alarm information is displayed on the monitoring platform, for serious faults, in addition to displaying on the monitoring platform, an emergency message is sent to the operation and maintenance personnel, and a sound and light alarm of the on-site equipment is triggered;

[0011] The monitoring management unit is used to provide a visual monitoring interface for maintenance personnel, to view the operating state of the power distribution network in real time on the interface, and the maintenance personnel manage the sensors and intelligent devices in the power distribution network through the monitoring management unit; the monitoring management unit displays the voltage, current, temperature and humidity parameters of each node of the power distribution network, and displays the fault information, so as to facilitate real-time monitoring of each node and facilitate the maintenance personnel to quickly reach the fault point position;

[0012] The artificial inspection subsystem unit is used to formulate an artificial inspection plan according to the scale of the power distribution network, the type of equipment, the importance and the inspection route, and to adjust the artificial inspection plan according to the evaluation result of the system on the equipment operation state; for important power distribution network segments, at least one comprehensive inspection is performed every week, and for ordinary power distribution network segments, one comprehensive inspection is performed every month; when the inspection route is formulated, the distribution of the equipment is considered to determine the inspection time, route and key inspection content, as shown below:

[0013] 1. Artificial inspection plan formulation

[0014] The formulation function of the artificial inspection plan Pplan:

[0015] Pplan=f(Pscale,S,I,R)

[0016] Wherein Pscale represents the scale of the power distribution network;

[0017] 2. Adjustment of the plan according to the equipment operation state

[0018] The adjusted artificial inspection plan Padjusted:

[0019] Padjusted=g(Pplan,E)

[0020] 3. Inspection frequency regulation

[0021] For important power distribution network segments (I=I1):

[0022] At least one comprehensive inspection is performed every week, and the inspection frequency is set as N1, then N1≥1 / week

[0023] For ordinary power distribution network segments (I=I2):

[0024] One comprehensive inspection is performed every month, and the inspection frequency is set as N2, then N2=1 / month

[0025] 4. Inspection route

[0026] The inspection route determination function is set as h, the key inspection content is C, and the inspection time is T:

[0027] R=h(Sdistribution,Pscale)

[0028] C=k(S,I)

[0029] T=m(S,I,Pscale)

[0030] Wherein, the functions f, g, h, k, m represent different logical relations; the Internet of Things monitoring can obtain a large amount of equipment operation data in real time, the artificial inspection can visually check and empirically judge the equipment, the two are combined to analyze and judge the fault from multiple angles, reduce the misjudgment and missed judgment, more accurately judge whether there is a fault hidden danger, through the Internet of Things monitoring to evaluate the running state of the equipment in real time, for the equipment in good running state, appropriately reduce the frequency of artificial inspection, thereby saving the labor cost, at the same time, the artificial inspection checks the weak link of the Internet of Things monitoring, improves the resource utilization efficiency.

[0031] Preferably, the personnel inspection subsystem unit further comprises an expert fault diagnosis unit, a training unit and an inspection equipment management unit;

[0032] The expert fault diagnosis unit utilizes the professional power field knowledge of the expert personnel to construct an expert system platform to realize the rapid positioning and preliminary diagnosis of the equipment fault, and utilizes the professional power field knowledge of the expert personnel to formulate the power distribution network maintenance training content;

[0033] The training unit is used to train the inspection personnel in the aspects of power equipment knowledge, safety operation procedures and fault identification skills by using the formulated power distribution network maintenance training content; the inspection personnel master the internal structure of the transformer, know how to check the oil level and oil temperature parameters of the transformer, understand the working principle, structural composition and common fault types of different equipment, ensure that the inspection personnel can comply with the safety regulations in the inspection process, correctly wear insulation protective articles, and maintain a safe distance when working near the high-voltage equipment, improve the ability of the inspection personnel to identify faults by displaying real-time cases of the appearance, sound, smell and other characteristics of the equipment in different fault states, enable the inspection personnel to quickly judge whether the equipment exists faults;

[0034] The inspection equipment management unit is used to equip the inspection personnel with necessary inspection tools and equipment to improve the inspection efficiency and ensure the operation safety of the inspection personnel;

[0035] The inspection cooperation unit is used to collect the information of the equipment name, position, fault phenomenon and preliminary judgment fault factor recorded by the inspection personnel in the inspection process, then send the information to the monitoring management unit, the maintenance personnel of the monitoring management unit compare and integrate the information results of the artificial inspection and the data of the Internet of Things monitoring, when both show that a certain equipment exists faults or fault risks, or one side finds abnormalities and the data of the other side can provide further explanation or verification, thereby more accurately judge the fault cause and take effective maintenance measures, for the problems that cannot be solved, report to the expert fault diagnosis unit, further eliminate the faults through the research of the expert personnel.

[0036] Preferably, the personnel inspection subsystem unit further comprises a feedback optimization unit and an inspection assistance unit;

[0037] The feedback optimization unit is used to collect the equipment operation in the artificial inspection process and feed back the inspection information to the monitoring management unit, so that the actual operation state of the equipment is intuitively understood through the artificial inspection. When the inspection personnel find that the equipment has potential safety hazards, the inspection personnel feed back the information. Then, the monitoring management unit re-evaluates the risk level of the equipment in the area with potential safety hazards according to the on-site feedback information, and adjusts and optimizes the subsequent inspection plan.

[0038] The inspection assistance unit is used to assist the on-site inspection of the inspection personnel by using system data. Before the artificial inspection starts, the inspection personnel accesses the Internet of Things data in the intelligent power distribution network fault early warning system through a mobile terminal, so as to view the recent voltage and current fluctuation curves of the equipment, understand the historical fault records of the equipment, and check the equipment or parameters that may have problems in a targeted manner, thereby improving the inspection efficiency.

[0039] Preferably, the inspection equipment management unit further comprises a device monitoring unit;

[0040] The device monitoring unit is used to collect and record the data results sent by the inspection equipment. During the artificial inspection process, the inspection personnel uses various tools to detect the equipment, and records and uploads the detection results of the tools to the sensing unit. When the sensor of the sensing unit cannot accurately obtain the data of a certain local area due to installation position or its own precision problem, the data of the area is accurately measured through artificial inspection, so that the artificial inspection data supplements the deficiencies of the Internet of Things monitoring, and the judgment of the system on the running state of the equipment is more comprehensive and accurate.

[0041] Preferably, it further comprises a network transmission unit;

[0042] The network transmission unit packages the data collected by the sensing unit according to the pre-defined data transmission protocol, and then transmits the packaged data to the data processing unit by using the Internet of Things communication. In the data transmission process, encryption technology is used to improve the security of the data.

[0043] Preferably, it further comprises a data storage unit;

[0044] A large database is established to store the massive data collected. The database combines the relational database and the non-relational database. The relational database is used to store the basic information of the equipment, the historical fault records and other structured data. The non-relational database is used to store the real-time running data collected by the sensor and other unstructured data.

[0045] Preferably, the personnel inspection subsystem unit further comprises a sharing unit and a scheduling unit;

[0046] The sharing unit is used to create a network sharing platform, and the data analysis unit, expert personnel and inspection personnel publish the latest fault types, fault phenomena and fault solving methods on the platform, so that the fault information is exchanged and shared on the platform, and the knowledge update and skill improvement of personnel are promoted;

[0047] The scheduling unit is used to reasonably allocate the inspection positions of personnel, when the data analysis unit detects that the equipment in a certain area appears abnormal condition, through the position, working state of the current inspection personnel and the importance of the area, therefore, the suitable inspection personnel are quickly allocated to go, and through the probability of equipment fault occurrence in different time periods, the number of allocated inspection personnel near important equipment is increased in the power consumption peak period.

[0048] Preferably, it further comprises a maintenance suggestion unit;

[0049] The maintenance suggestion unit is used for regular health assessment of power equipment in the power distribution network, analyzes and processes the data collected by the sensor, assesses the operation health state and service life of the equipment and proposes maintenance suggestions, and improves the safety of equipment operation.

[0050] A smart power distribution network fault early warning method based on Internet of Things, comprising the following steps:

[0051] S1, install current sensors, voltage sensors, temperature sensors and humidity sensors at the transformer, switch cabinet and line key node positions of the power distribution network, use the current sensor to monitor the current size in the line in real time, use the voltage sensor to monitor the voltage value, use the temperature sensor to monitor the operation temperature of the equipment, and use the humidity sensor to monitor the humidity, different sensors collect the operation parameters of the power distribution network according to a sampling frequency of once per second;

[0052] S2, use a data analysis algorithm to analyze the preprocessed data, and use a support vector machine learning algorithm to classify and predict the fault type; by cleaning the data, removing duplicate data, then extracting features and analyzing the cleaned data, a normal operation state model is constructed, then the collected data model and the normal state model are compared to calculate the deviation value, when it is found that the operation parameters of the power distribution network are out of the normal range or appear abnormal trend, a fault information is issued;

[0053] S3, according to the issued fault information to maintenance personnel and regulatory platform issued alarm information, tell its fault point location, temperature and possible fault type of the fault equipment, according to the severity and type of fault, set different early warning mode, for minor faults, through the display alarm information on the monitoring platform, for serious fault, in addition to the display on the monitoring platform, also to the operation and maintenance personnel send emergency message notification, and trigger the scene device sound and light alarm;

[0054] S4, by real-time viewing of the interface on the running state of the power distribution network, and the maintenance personnel through the monitoring management unit to manage the sensors and intelligent devices in the power distribution network, the monitoring management unit through the display of the voltage, current, temperature and humidity parameters of each node of the power distribution network, at the same time through the display of the fault information, so as to facilitate the real-time monitoring of each node, and facilitate the maintenance personnel to quickly reach the fault point position;

[0055] S5, according to the scale, equipment type, importance and inspection route of the power distribution network to formulate artificial inspection plan, at the same time according to the evaluation result of the system to the equipment running state, cooperate to adjust the artificial inspection plan; for important power distribution network section, at least once a week comprehensive inspection, for ordinary power distribution network section, formulate once a month comprehensive inspection, when formulating the inspection route, through considering the distribution of equipment, so as to determine the time, route and key inspection content of the inspection.

[0056] Preferably, in S5, the expert system platform is constructed to realize the rapid positioning and preliminary diagnosis of equipment failure, at the same time, the professional power field knowledge of expert personnel is utilized to formulate the power distribution network maintenance and operation training content, the inspection personnel are trained in the aspects of power equipment knowledge, safety operation procedures, fault identification skills, so that the inspection personnel master the internal structure of the transformer, know how to check the oil level and oil temperature parameters of the transformer, so that the inspection personnel understand the working principle, structure composition and common fault type of different equipment, ensure that the inspection personnel can abide by the safety regulations in the inspection process, correctly wear insulation protective articles, keep a safe distance when operating near high-voltage equipment, through the real-time cases of showing the appearance, sound, smell and other characteristics of the equipment under different fault states, improve the ability of the inspection personnel to identify faults, so that the inspection personnel can quickly judge whether the equipment has faults.

[0057] Compared with existing technologies, the beneficial effects of this invention are as follows: IoT monitoring can acquire a large amount of equipment operation data in real time, while manual inspection can perform intuitive checks and experience-based judgments on the equipment. By combining the two, faults can be analyzed and judged from multiple perspectives, reducing misjudgments and omissions, and more accurately determining whether there are potential faults. IoT monitoring can evaluate the operating status of equipment in real time. For equipment in good operating condition, the frequency of manual inspections can be appropriately reduced, thereby saving labor costs. At the same time, manual inspections can focus on checking the weak points of IoT monitoring, thereby improving resource utilization efficiency. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of the system structure of the present invention;

[0059] Figure 2 This is a partial isometric structural diagram showing the connection between the sensing unit and the data processing unit, etc.

[0060] Figure 3 This is a partial isometric structural diagram showing the connection between the monitoring and management unit and the personnel inspection subsystem unit, etc.

[0061] Figure 4 This is a partial isometric structural diagram showing the connection between the expert fault diagnosis unit and the training unit, etc.

[0062] Figure 5 This is a schematic diagram of the sensor unit. Detailed Implementation

[0063] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0064] Example 1

[0065] like Figures 1 to 5 As shown, the present invention provides an intelligent power distribution network fault early warning system based on the Internet of Things; it includes a sensing unit, a data processing unit, a data analysis unit, a fault early warning unit, a monitoring and management unit, and a personnel inspection subsystem unit;

[0066] The sensing unit is used to install current sensors, voltage sensors, temperature sensors, and humidity sensors at key nodes of transformers, switchgear, and lines in the power distribution network. The current sensor is used to monitor the current in the line in real time, the voltage sensor is used to monitor the voltage value, the temperature sensor is used to monitor the operating temperature of the equipment, and the humidity sensor is used to monitor the humidity. The different sensors collect the operating parameters of the power distribution network at a sampling frequency of once per second.

[0067] The data processing unit is used for pre-processing the data collected by the sensor, filtering, amplifying and analog-to-digital converting the collected data information; by removing noise interference in the collection process, then amplifying the weak sensor signal to a set range for processing, and then converting the analog signal to a digital signal, thereby facilitating data transmission and analysis;

[0068] The data analysis unit analyzes the pre-processed data using a data analysis algorithm, and classifies and predicts the fault type by using a support vector machine learning algorithm; by cleaning the data, removing duplicate data, then extracting features and analyzing the cleaned data, a normal operation state model is constructed, then the collected data model is compared with the normal state model to calculate the deviation value, when the power distribution network operation parameters exceed the normal range or abnormal trend is found, the fault information is issued;

[0069] The fault warning unit sends alarm information to maintenance personnel and monitoring platform according to the fault information issued by the data analysis unit, and informs the location of the fault point, the temperature of the fault equipment and the possible fault type; according to the severity and type of the fault, different warning methods are set, for slight faults, alarm information is displayed on the monitoring platform, for serious faults, in addition to displaying on the monitoring platform, an emergency message is sent to the operation and maintenance personnel, and the sound and light alarm of the on-site equipment is triggered;

[0070] The monitoring management unit is used to provide a visual monitoring interface for maintenance personnel, through which the running state of the power distribution network can be viewed in real time, and the maintenance personnel can manage the sensors and intelligent devices in the power distribution network through the monitoring management unit; the monitoring management unit displays the voltage, current, temperature and humidity parameters of each node in the power distribution network, and displays the fault information, thereby facilitating real-time monitoring of each node and enabling the maintenance personnel to quickly reach the fault point;

[0071] The artificial inspection subsystem unit is used to develop an artificial inspection plan according to the scale, equipment type, importance and inspection route of the power distribution network, and to adjust the artificial inspection plan according to the evaluation results of the system on the equipment running state; for important power distribution network sections, at least one comprehensive inspection is performed every week, and for ordinary power distribution network sections, one comprehensive inspection is performed every month; when developing the inspection route, the distribution of the equipment is considered to determine the inspection time, route and key inspection content, as follows:

[0072] 1. Artificial inspection plan development

[0073] The development function of the artificial inspection plan Pplan is as follows:

[0074] Pplan=f(Pscale,S,I,R)

[0075] wherein Pscale represents the scale of the power distribution network;

[0076] 2. Adjusting the plan according to the equipment running state

[0077] The adjusted manual inspection plan Padjusted:

[0078] Padjusted=g(Pplan,E)

[0079] 3. Inspection frequency regulation

[0080] For important power distribution network segments (I=I1):

[0081] At least one comprehensive inspection is carried out every week, and the number of inspections is N1, then N1≥1 / week

[0082] For ordinary power distribution network segments (I=I2):

[0083] One comprehensive inspection is carried out every month, and the number of inspections is N2, then N2=1 / month

[0084] 4. Inspection route

[0085] Let the inspection route determination function be h, the key check content be C, and the inspection time be T:

[0086] R=h(Sdistribution,Pscale)

[0087] C=k(S,I)

[0088] T=m(S,I,Pscale)

[0089] wherein the functions f, g, h, k, and m represent different logical relationships;

[0090] The personnel inspection subsystem unit also includes an expert fault diagnosis unit, a training unit, and an inspection equipment management unit;

[0091] The expert fault diagnosis unit utilizes the professional power field knowledge of expert personnel to construct an expert system platform, realizes rapid positioning and preliminary diagnosis of equipment faults, and at the same time utilizes the professional power field knowledge of expert personnel to formulate power distribution network maintenance and operation training content;

[0092] The training unit is configured to train the patrol personnel in the power equipment knowledge, the safe operation procedures, and the fault identification skills by using the formulated power distribution network operation and maintenance training content; the patrol personnel are enabled to master the internal structure of the transformer, to know how to check the oil level and the oil temperature parameters of the transformer, to understand the working principles, the structural compositions, and the common fault types of different equipment, to ensure that the patrol personnel can comply with the safety regulations, correctly wear the insulation protective articles, and keep a safe distance when working near the high-voltage equipment, to improve the ability of the patrol personnel to identify the faults by displaying the real-time cases of the features such as the appearance, the sound, and the smell of the equipment in different fault states, and to enable the patrol personnel to quickly judge whether the equipment has faults;

[0093] The patrol equipment management unit is configured to provide the patrol personnel with the necessary patrol tools and equipment, to improve the patrol efficiency, and to ensure the safety of the patrol personnel;

[0094] The patrol cooperation unit is configured to collect the information such as the device name, the location, the fault phenomenon, and the preliminary fault factor judgment recorded by the patrol personnel during the patrol, and then to send the information to the monitoring management unit; the maintenance personnel of the monitoring management unit are enabled to more accurately judge the fault causes and to take effective maintenance measures by comparing and integrating the information results of the manual patrol with the data of the Internet of Things, when both of them show that a device has a fault or a fault risk, or one side finds an abnormality and the data of the other side can provide further explanation or verification; for the problems that cannot be solved, the problems are reported to the expert fault diagnosis unit, and the problems are further excluded after the expert personnel research.

[0095] The personnel patrol subsystem unit further includes a feedback optimization unit and a patrol auxiliary unit;

[0096] The feedback optimization unit is configured to collect the device operation conditions during the manual patrol, and to feed back the patrol information to the monitoring management unit; the actual operation states of the devices are intuitively understood by the manual patrol; when the patrol personnel find that the devices have potential safety hazards, the patrol personnel feed back the information; then the monitoring management unit re-evaluates the risk levels of the devices in the areas with potential safety hazards according to the feedback information, and adjusts and optimizes the subsequent patrol plan;

[0097] The patrol auxiliary unit is configured to assist the on-site patrol of the patrol personnel by using the system data; before the manual patrol starts, the patrol personnel access the Internet of Things data in the intelligent power distribution network fault early warning system through the mobile terminal, to view the recent voltage and current fluctuation curves of the devices, to understand the historical fault records of the devices, to perform the focused inspection on the devices or parameters that are likely to have problems, and to improve the patrol efficiency.

[0098] The patrol equipment management unit further includes a device monitoring unit;

[0099] The device monitoring unit is used for collecting and recording the data results sent by the inspection device. In the manual inspection process, the inspection personnel use various tools to detect the equipment, and the detection results of the tools are recorded and uploaded to the sensing unit. When the sensor of the sensing unit cannot accurately obtain the data of a certain local area due to installation position or its own precision problem, the data of the area is accurately measured by manual inspection, so that the manual inspection data supplements the deficiencies of the Internet of Things monitoring, and the judgment of the system on the running state of the equipment is more comprehensive and accurate.

[0100] The network transmission unit is also included.

[0101] The network transmission unit packages the data collected by the sensing unit according to the predefined data transmission protocol, and then transmits the packaged data to the data processing unit using Internet of Things communication. In the data transmission process, encryption technology is used to improve the security of the data.

[0102] The data storage unit is also included.

[0103] A large database is established to store the massive data collected. The database combines relational databases and non-relational databases. The relational database is used to store structured data such as basic information of the equipment and historical fault records, and the non-relational database is used to store unstructured data such as real-time running data collected by the sensor.

[0104] The personnel inspection subsystem unit also includes a sharing unit and a scheduling unit.

[0105] The sharing unit is used to create a network sharing platform. The data analysis unit, expert personnel and inspection personnel publish the latest fault types, fault phenomena and fault solving methods on the platform, so that the fault information is exchanged and shared on the platform, promoting the knowledge update and skill improvement of personnel.

[0106] The scheduling unit is used to reasonably allocate the inspection positions of personnel. When the data analysis unit detects that the equipment in a certain area is abnormal, it quickly allocates appropriate inspection personnel to go there according to the current position, working state of the inspection personnel and the importance of the area. At the same time, according to the probability of equipment failure in different time periods, the number of inspection personnel allocated near important equipment is increased during the peak electricity consumption period.

[0107] The maintenance suggestion unit is also included.

[0108] The maintenance suggestion unit is used for regular health assessment of power equipment in the power distribution network. By analyzing and processing the data collected by the sensor, the running health status and service life of the equipment are evaluated and maintenance suggestions are proposed to improve the safety of equipment operation.

[0109] In the embodiment, the Internet of Things monitoring can obtain a large amount of device operation data in real time, the artificial inspection can visually check and empirically judge the device, the combination of the two can analyze and judge the fault from multiple angles, reduce misjudgment and missed judgment, more accurately judge whether there is a fault hidden danger, real-time evaluate the running state of the device through the Internet of Things monitoring, appropriately reduce the frequency of artificial inspection for the device in good running state, thereby saving labor cost, and the artificial inspection can improve resource utilization efficiency by focusing on checking the weak link of the Internet of Things monitoring.

[0110] Embodiment 2

[0111] On the basis of embodiment 1, the intelligent power distribution network fault early warning method based on the Internet of Things comprises the following steps:

[0112] S1, install current sensors, voltage sensors, temperature sensors and humidity sensors at the transformer, switch cabinet and line key node positions of the power distribution network, use the current sensors to monitor the current size in the line in real time, use the voltage sensors to monitor the voltage value, use the temperature sensors to monitor the operation temperature of the device, and use the humidity sensors to monitor the humidity, and different sensors collect the operation parameters of the power distribution network according to a sampling frequency of one per second;

[0113] S2, analyze the preprocessed data by using a data analysis algorithm, and classify and predict the fault type by using a support vector machine learning algorithm; clean the data, remove duplicate data, then extract features and analyze the cleaned data, construct a normal operation state model, then compare the collected data model with the normal state model to calculate a deviation value, and when it is found that the operation parameters of the power distribution network are out of the normal range or an abnormal trend occurs, issue a fault information;

[0114] S3, according to the issued fault information, issue an alarm information to the maintenance personnel and the supervision platform, inform the location of the fault point, the temperature of the fault device and the possible fault type, set different early warning modes according to the severity and type of the fault, for a slight fault, display the alarm information on the monitoring platform, and for a serious fault, in addition to displaying on the monitoring platform, also send an emergency message to the operation and maintenance personnel and trigger the sound and light alarm of the on-site device;

[0115] S4, real-time view the running state of the power distribution network on the interface, and the maintenance personnel manage the sensors and intelligent devices in the power distribution network through a monitoring management unit, the monitoring management unit displays the voltage, current, temperature and humidity parameters of each node in the power distribution network, and displays the fault information, thereby facilitating real-time monitoring of each node and facilitating the maintenance personnel to quickly reach the fault point position.

[0116] S5, according to the scale of power distribution network, equipment type, importance and inspection route, make artificial inspection plan, at the same time, according to the evaluation result of system to equipment operation state, cooperate with adjustment artificial inspection plan, for important power distribution network section, at least once a week comprehensive inspection, for ordinary power distribution network section, make a comprehensive inspection once a month, when making inspection route, through considering the distribution of equipment, thereby determine the time, route and key inspection content of inspection;

[0117] In S5, the expert system platform is constructed, the rapid positioning and preliminary diagnosis of equipment failure are realized, the professional power field knowledge of expert personnel is utilized, the power distribution network maintenance training content is made, the power equipment knowledge, safety operation procedure, fault identification skill training of inspection personnel is carried out, the inspection personnel master the internal structure of transformer, know how to check the oil level, oil temperature parameter of transformer, the inspection personnel understand the working principle, structure composition and common fault type of different equipment, ensure that the inspection personnel can abide by the safety regulations in the inspection process, correctly wear insulation protective articles, keep a safe distance when operating near high-voltage equipment, through the real-time case of showing the appearance, sound, smell and other characteristics of equipment in different fault states, the ability of identifying fault of inspection personnel is improved, the inspection personnel can quickly judge whether the equipment exists fault.

[0118] The main functions realized by the present application are that: the Internet of Things monitoring can obtain a large amount of equipment operation data in real time, the artificial inspection can visually check and empirically judge the equipment, through combining the two, the fault is analyzed and judged from multiple angles, the misjudgment and missed judgment are reduced, and the existence of hidden danger is more accurately judged;

[0119] The operation state of the equipment is evaluated in real time through the Internet of Things monitoring, for the equipment with good operation state, the frequency of artificial inspection is appropriately reduced, so that the labor cost is saved, at the same time, the artificial inspection focuses on checking the weak link of the Internet of Things monitoring, and the resource utilization efficiency is improved.

[0120] The above only describes the preferred embodiments of the present application, it should be pointed out that, for ordinary skilled in the art, without departing from the technical principles of the present application, a number of improvements and modifications can be made, these improvements and modifications should also be regarded as the protection scope of the present application.

Claims

1. An Internet of Things based intelligent power distribution network fault warning system, characterized in that, The system comprises a sensing unit, a data processing unit, a data analysis unit, a fault early warning unit, a monitoring management unit and a personnel inspection subsystem unit. The sensing unit is used for installing current sensors, voltage sensors, temperature sensors and humidity sensors at transformer, switch cabinet and line key node positions of the power distribution network, for monitoring the current size in the line in real time through the current sensor, for monitoring the voltage value through the voltage sensor, for monitoring the operating temperature of the equipment through the temperature sensor, and for monitoring the humidity through the humidity sensor. The data processing unit is used for pre-processing the data collected by the sensors, filtering, amplifying and analog-digital converting the collected data information. The data analysis unit analyzes the pre-processed data by using a data analysis algorithm, and classifies and predicts the fault type by using a support vector machine learning algorithm. The fault early warning unit sends alarm information to the maintenance personnel and the supervision platform according to the fault information sent by the data analysis unit, and informs the location of the fault point, the temperature of the fault equipment and the possible fault type. The monitoring management unit is used for providing a visual monitoring interface for the maintenance personnel, for allowing the maintenance personnel to view the operating state of the power distribution network in real time on the interface, and for allowing the maintenance personnel to manage the sensors and intelligent devices in the power distribution network through the monitoring management unit. The personnel inspection subsystem unit is used for formulating an artificial inspection plan according to the scale, equipment type, importance and inspection route of the power distribution network, for adjusting the artificial inspection plan according to the evaluation result of the system on the equipment operating state, for performing at least one comprehensive inspection per week on important power distribution network sections, for formulating one comprehensive inspection per month on ordinary power distribution network sections, and for determining the inspection time, route and key inspection content by considering the distribution of the equipment when formulating the inspection route. The personnel inspection subsystem unit further comprises a feedback optimization unit and an inspection assistance unit. The feedback optimization unit is used for collecting the equipment operating state in the artificial inspection process, for feeding back the inspection information to the monitoring management unit, for allowing the maintenance personnel to intuitively understand the actual operating state of the equipment, for allowing the maintenance personnel to feed back the information when the maintenance personnel finds potential safety hazards of the equipment, for allowing the monitoring management unit to re-evaluate the risk level of the equipment in the area with potential safety hazards according to the feedback information, and for allowing the monitoring management unit to adjust and optimize the subsequent inspection plan. The inspection assistance unit is used for assisting the on-site inspection of the maintenance personnel by using system data, for allowing the maintenance personnel to access the Internet of Things data in the intelligent power distribution network fault early warning system through a mobile terminal before the artificial inspection starts, for allowing the maintenance personnel to view the recent voltage and current fluctuation curves of the equipment, for allowing the maintenance personnel to understand the historical fault records of the equipment, for allowing the maintenance personnel to perform targeted key inspection on the equipment or parameters that may have problems, and for improving the inspection efficiency.

2. The smart power distribution network fault warning system based on Internet of Things of claim 1, wherein, The personnel inspection subsystem unit further comprises an expert fault diagnosis unit, a training unit and an inspection equipment management unit. The expert fault diagnosis unit constructs an expert system platform by using the professional electric power field knowledge of the expert personnel, realizes the rapid positioning and preliminary diagnosis of the equipment fault, and formulates the power distribution network maintenance and operation training content by using the professional electric power field knowledge of the expert personnel. The training unit is used for training the patrol personnel in the aspects of power equipment knowledge, safe operation procedures and fault identification skills by using the formulated power distribution network operation and maintenance training content; The patrol personnel can master the internal structure of the transformer, know how to check the oil level and oil temperature parameters of the transformer, understand the working principle, structural composition and common fault types of different equipment, ensure that the patrol personnel can comply with the safety regulations, correctly wear insulation protective articles and maintain a safe distance when working near the high-voltage equipment, improve the ability of the patrol personnel to identify faults by displaying real-time cases of the appearance, sound and smell characteristics of the equipment in different fault states, and enable the patrol personnel to quickly judge whether the equipment has faults; The patrol equipment management unit is used for providing the patrol personnel with necessary patrol tools and equipment, improving the patrol efficiency and ensuring the safety of the patrol personnel; The patrol coordination unit is used for collecting the information of the equipment name, position, fault phenomenon and preliminary fault factor judgment recorded by the patrol personnel during the patrol process, and then sending the information to the monitoring management unit, so that the maintenance personnel of the monitoring management unit can compare and integrate the information of the artificial patrol with the data of the Internet of Things monitoring, when both of them show that a certain equipment has faults or fault risks, or one side finds an abnormality and the data of the other side can provide further explanation or verification, so as to more accurately judge the fault cause and take effective maintenance measures, and for the problems that cannot be solved, report to the expert fault diagnosis unit, and further exclude the faults after the discussion of the expert personnel.

3. The smart power distribution network fault warning system based on Internet of Things of claim 2, wherein, The patrol equipment management unit further comprises a device monitoring unit; The device monitoring unit is used for collecting and recording the data results sent by the patrol equipment, in the process of artificial patrol, the patrol personnel use various tools to detect the equipment, and record and upload the detection results of the tools to the sensing unit, when the sensors of the sensing unit cannot accurately obtain the data of a certain local part of the equipment due to installation position or self-precision problem, the data of the area is accurately measured by artificial patrol, so that the artificial patrol data supplements the deficiencies of the Internet of Things monitoring, and the judgment of the system on the running state of the equipment is more comprehensive and accurate.

4. The smart power distribution network fault warning system based on the Internet of Things of claim 1, wherein, Further comprising a network transmission unit; The network transmission unit packs the data collected by the sensing unit according to the predefined data transmission protocol, and then transmits the packaged data to the data processing unit by using the Internet of Things communication, and in the data transmission process, the security of the data is improved by using encryption technology.

5. The smart power distribution network fault warning system based on Internet of Things as claimed in claim 1 wherein, Further comprising a data storage unit; A large database is established to store the massive collected data, the database combines the relational database and the non-relational database, the relational database is used to store the basic information and historical fault record structured data of the equipment, and the non-relational database is used to store the real-time running data non-structured data collected by the sensors.

6. The smart power distribution network fault warning system based on Internet of Things as claimed in claim 1 wherein, The personnel patrol subsystem unit further comprises a sharing unit and a scheduling unit; The sharing unit is used to create a network sharing platform, and the data analysis unit, expert personnel and inspection personnel exchange and share the fault information on the platform by publishing the latest fault types, fault phenomena and fault solving methods on the platform, so as to promote the knowledge update and skill improvement of personnel; The scheduling unit is used to reasonably distribute the inspection positions of personnel, when the data analysis unit detects that the equipment in a certain area appears abnormal condition, the appropriate inspection personnel are quickly distributed to go to the area according to the current position, working state of the inspection personnel and the importance of the area, and the number of distributed inspection personnel near the important equipment is increased in the peak power consumption period according to the probability of equipment fault occurrence in different time periods.

7. The smart power distribution network fault warning system based on Internet of Things as claimed in claim 1 wherein, The maintenance suggestion unit is also included; The maintenance suggestion unit is used for regular health assessment of power equipment in the power distribution network, analyzes and processes the data collected by the sensors, so as to assess the running health state and service life of the equipment and propose maintenance suggestions, and improve the safety of equipment operation.

8. A smart power distribution network fault early warning method based on Internet of Things, characterized in that, The following steps are included: S1, current sensors, voltage sensors, temperature sensors and humidity sensors are installed at the transformer, switch cabinet and line key node positions of the power distribution network, the current sensors are used to monitor the current size in the line in real time, the voltage sensors are used to monitor the voltage value, the temperature sensors are used to monitor the running temperature of the equipment, and the humidity sensors are used to monitor the humidity, different sensors collect the running parameters of the power distribution network according to a sampling frequency of one per second; S2, the preprocessed data are analyzed by using a data analysis algorithm, and the support vector machine learning algorithm is used to classify and predict the fault types; The data are cleaned and repeated data are removed, then the features of the cleaned data are extracted and analyzed, the normal running state model is constructed, then the collected data model is compared with the normal state model to calculate the deviation value, when it is found that the running parameters of the power distribution network exceed the normal range or appear abnormal trend, the fault information is sent; S3, according to the fault information, alarm information is sent to the maintenance personnel and the supervision platform to inform the position of the fault point, the temperature of the fault equipment and the possible fault type, different warning modes are set according to the severity and type of the fault, for slight fault, the alarm information is displayed on the monitoring platform, for serious fault, in addition to the display on the monitoring platform, an emergency message is also sent to the operation and maintenance personnel, and the sound and light alarm of the on-site equipment is triggered; S4, the running state of the power distribution network is viewed in real time on the interface, and the maintenance personnel manage the sensors and intelligent equipment in the power distribution network through the monitoring management unit, the monitoring management unit displays the voltage, current, temperature and humidity parameters of each node of the power distribution network, and displays the fault information, so as to facilitate real-time monitoring of each node and facilitate the maintenance personnel to quickly reach the fault point position; S5, according to the scale of power distribution network, equipment type, importance and inspection route to make artificial inspection plan, at the same time according to the evaluation result of system to equipment operation state, cooperate adjustment artificial inspection plan, for important power distribution network section, at least once a week comprehensive inspection, for ordinary power distribution network section, make a comprehensive inspection once a month, in the formulation of inspection route, through the consideration of equipment distribution situation, thereby determine the inspection time, route and key check content; In S5, the expert system platform is constructed, the rapid positioning and preliminary diagnosis of equipment failure are realized, the professional power field knowledge of expert personnel is utilized, the power distribution network maintenance training content is formulated, the power equipment knowledge, safety operation procedure, fault identification skill of the inspection personnel are trained, the inspection personnel master the internal structure of transformer, know how to check the oil level and oil temperature parameters of transformer, the inspection personnel understand the working principle, structure composition and common fault type of different equipment, ensure that the inspection personnel can abide by the safety regulations in the inspection process, correctly wear insulation protective articles, keep a safe distance when working near high voltage equipment, through the real-time case of showing the appearance, sound, smell characteristics of equipment under different fault states, improve the ability of the inspection personnel to identify faults, let the inspection personnel can quickly judge whether the equipment exists fault.

Images