Electrical working environment abnormity monitoring and automatic alarm system based on Internet of Things

Abstract

The invention relates to the technical field of electrical safety monitoring, in particular to an electrical operation environment abnormity monitoring and automatic alarm system based on the Internet of Things, which comprises an environment data acquisition module, a fault identification and analysis module, a priority ranking module and an alarm triggering module, wherein the environment data acquisition module is used for acquiring environment data in real time; the fault identification and analysis module is used for identifying abnormal conditions in the working environment of the electrical equipment and automatically judging whether a fault exists or not; the priority ranking module is used for distributing a priority for each fault; the alarm triggering module is used for automatically triggering alarm measures according to the fault priorities output by the priority ranking module; according to the invention, by combining the Internet of Things technology, the machine learning algorithm and the intelligent alarm mechanism, real-time monitoring, accurate fault identification and priority ranking of the electrical working environment are realized, the accuracy and response speed of fault early warning are improved, and the equipment safety is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical safety monitoring, and in particular to an electrical operating environment abnormality monitoring and automatic alarm system based on the Internet of Things. Background Art

[0002] With the widespread application of electrical equipment in industry, energy, transportation and other fields, the safety and stability of the electrical working environment have become particularly important. In the electrical working environment, environmental factors such as temperature and humidity changes, current fluctuations, voltage anomalies and changes in the concentration of harmful gases will affect the operation of electrical equipment and even cause major safety hazards such as equipment failure and fire. Therefore, real-time monitoring of various parameters of the electrical working environment, timely detection of anomalies and taking effective alarm measures have become important means to ensure the safe operation of equipment and reduce accidents.

[0003] The existing electrical operating environment abnormality monitoring system has the following problems: on the one hand, traditional monitoring systems mostly rely on manual inspections, which make it difficult to detect potential environmental changes and equipment abnormalities in a timely manner; on the other hand, existing alarm systems usually rely solely on simple threshold settings and lack in-depth analysis of abnormal situations, resulting in low alarm accuracy and prone to false alarms or missed alarms; in addition, although the existing system can collect environmental data and perform simple processing, it lacks intelligent support in terms of in-depth analysis and real-time response of data, and cannot automatically adjust the response strategy according to the severity and location of the fault. These problems have led to the failure to effectively prevent and control safety hazards in the operating environment of electrical equipment. There is an urgent need for an electrical operating environment abnormality monitoring and automatic alarm system based on the Internet of Things to solve the above problems. Summary of the invention

[0004] Based on the above objectives, the present invention provides an electrical working environment abnormality monitoring and automatic alarm system based on the Internet of Things.

[0005] An electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things includes an environmental data acquisition module, a fault identification and analysis module, a priority sorting module and an alarm triggering module; wherein:

[0006] Environmental data acquisition module: used to deploy sensors in the electrical operation environment to collect environmental data in real time, including temperature, humidity, current, voltage and gas concentration;

[0007] Fault identification and analysis module: used to extract features and perform pattern recognition on the collected environmental data, and combined with the pre-trained support vector machine model, identify abnormal conditions in the operating environment of electrical equipment in real time and automatically determine whether there is a fault;

[0008] Priority sorting module: used to assign a priority to each fault based on the fault information output by the fault identification and analysis module. Priority sorting is based on the type, severity and location of the fault.

[0009] Alarm trigger module: used to automatically trigger alarm measures according to the fault priority output by the priority sorting module, including sound and light alarm, SMS notification, email reminder or App push, to ensure that relevant personnel receive fault information in time.

[0010] Optionally, the environmental data acquisition module includes a sensor deployment unit, a data acquisition unit and a data preprocessing unit; wherein:

[0011] Sensor deployment unit: used to deploy multiple sensors in the electrical operation environment, the sensors including temperature and humidity sensors, current sensors, voltage sensors and gas concentration sensors;

[0012] Data acquisition unit: used to collect environmental data in real time through deployed sensors, the environmental data including temperature, humidity, current, voltage and gas concentration; and transmit the collected data to the data preprocessing unit through the Internet of Things communication protocol, the Internet of Things communication protocol including Wi-Fi, LoRa and NB-IoT;

[0013] Data preprocessing unit: used to perform preliminary processing on the collected environmental data, including noise removal, filtering, outlier removal and data interpolation and completion.

[0014] Optionally, the fault identification and analysis module includes a data processing unit, a feature extraction unit, a pattern recognition unit and a fault judgment unit; wherein:

[0015] Data processing unit: used to receive data from the environmental data acquisition module and standardize or normalize the environmental data to ensure that the data belongs to the same dimension;

[0016] Feature extraction unit: used to extract relevant features from the processed environmental data, including current fluctuation amplitude, voltage abnormal amplitude, and temperature and humidity change rate, and transform the time domain, frequency domain, and statistical features into numerical data for model training through feature engineering technology to form feature vectors;

[0017] Pattern recognition unit: Uses the pre-trained support vector machine model to perform real-time pattern recognition on the extracted feature vectors to identify abnormal conditions in the operating environment of electrical equipment, including current fluctuations, voltage anomalies, and sudden changes in temperature and humidity;

[0018] Fault judgment unit: used to automatically judge whether there is a fault according to the abnormal situation output by the pattern recognition unit and the preset fault judgment rules.

[0019] Optionally, the feature extraction unit includes:

[0020] Current fluctuation amplitude extraction: Calculate the current fluctuation amplitude based on the collected current data. The current fluctuation amplitude is defined as the difference between the maximum value and the minimum value of the collected current signal.

[0021] Voltage abnormal amplitude extraction: Calculate the voltage abnormal amplitude based on the collected voltage data. The voltage abnormal amplitude is the ratio of the standard deviation of the voltage signal to the mean value.

[0022] Temperature and humidity change rate extraction: Calculate the temperature and humidity change rate based on the collected temperature and humidity data. The change rate is the change amplitude of temperature or humidity per unit time.

[0023] Time domain feature extraction: By performing time domain analysis on the collected environmental data, the time domain features of mean, variance, kurtosis and skewness are extracted;

[0024] Frequency domain feature extraction: The collected time series data is converted into frequency domain data through Fourier transform, so as to extract frequency domain features, including spectrum density and main frequency;

[0025] Statistical feature extraction: Extract statistical features based on the collected environmental data, including maximum value, minimum value, average value, standard deviation and variance;

[0026] Feature vector formation: After standardization or normalization, the above time domain, frequency domain and statistical features are combined into a high-dimensional feature vector; the feature vector form is: F = [F1, F2, ..., F n ]; where F1, F2, …, F n are the extracted eigenvalues, and F is the final eigenvector.

[0027] Optionally, the pattern recognition unit includes:

[0028] Feature vector input: The feature vector output from the feature extraction unit is input into the pre-trained support vector machine model, wherein the feature vector includes the current fluctuation amplitude, the voltage abnormal amplitude, and the temperature and humidity change rate;

[0029] Support vector machine model classification: The feature vector is input into the support vector machine model for classification; the support vector machine model establishes a decision boundary by learning the existing labeled data to distinguish the normal state from the abnormal state; the expression of the decision function is: Among them, x i represents the i-th sample in the training set, y i is the category label of the sample, N1 is the total number of samples, α i is the Lagrange multiplier of the support vector, K(x i, x) is the kernel function, b is the bias term, and f(x) is the classification decision function;

[0030] Abnormal situation identification: By calculating the decision function value f(x), the support vector machine model classifies the input feature vector in real time; when the value of f(x) exceeds the preset threshold, it is judged as an abnormal situation; the formula is: Among them, θ is the preset threshold.

[0031] Optionally, the fault judgment unit includes:

[0032] Abnormal situation input: Receives abnormal situation information identified in real time from the pattern recognition unit, including current fluctuation, voltage anomaly, and temperature and humidity mutation. The abnormal situation is transmitted through an abnormal identifier in the form of:

[0033] e=[e current ,e voltage ,e temperature ,e humidity ], where e is the abnormal situation vector, e current、 e voltage、 e temperature and e humidity Identifiers representing current fluctuation, voltage anomaly, temperature anomaly, and humidity anomaly, respectively, with values ​​of 1 or 0, where 1 represents an abnormality and 0 represents a normal state;

[0034] Fault judgment rule setting: Fault judgment is performed based on preset rules and combined with identifiers of various abnormal situations; specific rules include:

[0035] Rule 1, when the current fluctuates e current =1 and voltage abnormality e voltage =1, it is judged as an electrical fault;

[0036] Rule 2: When the temperature is abnormal temperature =1 and humidity is abnormal e humidity =1, it is judged as an environmental fault;

[0037] Rule 3: When current fluctuation and temperature anomaly occur simultaneously, that is, e current =1 and e temperature =1, it is judged as equipment overload fault;

[0038] Fault judgment logic: Based on the preset rules, the input abnormal situation vector e is matched with rules and fault judgment is performed. The expression is:

[0039]

[0040] Among them, F fault Indicates the fault judgment result. If the fault condition is met, F fault=1, indicating a fault; otherwise, F fault =0, indicating no fault.

[0041] Optionally, the priority sorting module includes a fault type assessment unit, a fault severity assessment unit, a fault location identification unit and a priority decision unit; wherein:

[0042] Fault type assessment unit: used to identify the fault type according to the fault information output by the fault identification and analysis module, including electrical fault, environmental fault and equipment overload fault; and assign different basic priorities according to different fault types;

[0043] If the fault type is an electrical fault, the basic priority is set to high priority;

[0044] If the fault type is an environmental fault, the basic priority is set to medium priority;

[0045] If the fault type is equipment overload fault, the basic priority is set to low priority;

[0046] Fault severity evaluation unit: used to evaluate the severity of the fault according to the data values ​​in the fault information, the data values ​​include current value, voltage value, temperature value and humidity value, the severity evaluation is judged according to the set threshold value, the higher the severity of the fault, the higher the priority assigned;

[0047] Fault location identification unit: used to obtain the specific location of the fault, and identify the importance of the fault location in combination with the layout of the electrical working environment and the equipment operating status. If the fault occurs in high-voltage equipment or a dangerous area, the priority of the fault is increased; on the contrary, if the fault occurs in an auxiliary device or a safe area, the priority of the fault is reduced;

[0048] Priority decision unit: used to assign a final priority to each fault event based on the output information of the fault type assessment unit, the fault severity assessment unit and the fault location identification unit in combination with the set priority decision rules.

[0049] Optionally, the fault severity assessment unit includes:

[0050] Severity calculation: By comparing each data value with the corresponding threshold, the severity value S of the fault is calculated. fault ;

[0051] Severity output: Through the above calculation, the severity value S of the fault is obtained fault If S fault Reaching the preset severity threshold S threshold , then the fault is considered a high-severity fault and needs to be handled with priority.

[0052] Optionally, the priority decision unit specifically includes:

[0053] Input data: receiving fault information from the fault type assessment unit, the fault severity assessment unit and the fault location identification unit, the specific information including the fault type basic priority, the fault severity value and the fault location;

[0054] Priority decision rule: The basic priority of the fault type, the severity value of the fault and the fault location are weighted and combined to calculate the final priority F of each fault event. fi1al ;

[0055] Final priority output: According to the calculated F final , each fault event is assigned a final priority, if F final If the high priority threshold is reached, the fault is considered to be the most urgent fault with a high priority. final If it is in the medium range, the priority is medium, otherwise it is low;

[0056] Priority adjustment: When a fault occurs, the priority decision unit will dynamically adjust the priority of each fault event based on real-time changing environmental data and fault information to ensure that the most serious and urgent faults are handled first.

[0057] Optionally, the alarm triggering module includes a fault priority input unit and an alarm strategy selection unit; wherein:

[0058] Fault priority input unit: used to receive the fault priority information output by the priority sorting module, the information includes the final priority of each fault event, indicating the urgency of the fault and the priority of processing;

[0059] Alarm strategy selection unit: used to select corresponding alarm measures according to the received fault priority information and in combination with the preset alarm strategy, wherein the alarm strategy rule makes decisions based on the fault priority;

[0060] Strategy 1: For high-priority faults, comprehensive alarm measures are triggered, including audible and visual alarms, SMS notifications, email reminders, and App push notifications;

[0061] Strategy 2: For medium-priority faults, an audible and visual alarm and SMS notification are triggered, but no immediate processing is required;

[0062] Strategy 3: For low-priority faults, trigger SMS notifications or email reminders so that relevant personnel can view them during normal operations.

[0063] Beneficial effects of the present invention:

[0064] The present invention can monitor various abnormal conditions in the electrical operation environment in real time and discover potential safety hazards in a timely manner through comprehensive environmental data collection, accurate fault identification and analysis, and intelligent priority sorting and alarm triggering mechanisms. Compared with traditional monitoring systems, this solution can efficiently identify environmental changes such as current fluctuations, voltage anomalies, and temperature and humidity changes, and automatically perform intelligent analysis and alarms based on the type, severity, and location of the fault, effectively improving the accuracy and response speed of fault warnings and reducing reliance on human intervention.

[0065] The present invention, by introducing real-time data transmission and machine learning algorithms based on the Internet of Things, has highly intelligent capabilities in fault identification and alarm response. The system can automatically adjust the alarm priority according to real-time data and preset rules to ensure that emergency faults can be handled in a timely manner. For minor faults, they can be recorded and tracked through low-priority notification measures. This priority-based intelligent alarm mechanism effectively reduces the impact of faults on electrical equipment, thereby extending the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of an abnormal monitoring and automatic alarm system for an electrical working environment according to an embodiment of the present invention;

[0068] Figure 2 Schematic diagram of a fault identification and analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0070] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0071] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0072] like Figure 1-Figure 2 As shown, an electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things includes an environmental data acquisition module, a fault identification and analysis module, a priority sorting module and an alarm triggering module; wherein:

[0073] Environmental data acquisition module: used to deploy sensors in the electrical operation environment to collect environmental data in real time, including temperature, humidity, current, voltage and gas concentration;

[0074] Fault identification and analysis module: used to extract features and perform pattern recognition on the collected environmental data, and combined with the pre-trained support vector machine (SVM) model, identify abnormal conditions in the operating environment of electrical equipment in real time and automatically determine whether there is a fault;

[0075] Priority sorting module: used to assign a priority to each fault based on the fault information output by the fault identification and analysis module. Priority sorting is based on the type, severity and location of the fault to ensure that the most urgent fault events are handled first;

[0076] Alarm trigger module: used to automatically trigger alarm measures according to the fault priority output by the priority sorting module, including sound and light alarm, SMS notification, email reminder or App push, to ensure that relevant personnel receive fault information in time.

[0077] The environmental data acquisition module includes a sensor deployment unit, a data acquisition unit and a data preprocessing unit; wherein:

[0078] Sensor deployment unit: used to deploy multiple sensors in the electrical operation environment, including temperature and humidity sensors, current sensors, voltage sensors, and gas concentration sensors; the sensor layout is reasonably planned according to the working environment, operating conditions, and monitoring requirements of the electrical equipment to ensure accurate and comprehensive acquisition of key parameter data in the electrical operation environment;

[0079] Data acquisition unit: used to collect environmental data in real time through deployed sensors, including temperature, humidity, current, voltage and gas concentration; and transmit the collected data to the data preprocessing unit through the Internet of Things communication protocol, including Wi-Fi, LoRa and NB-IoT;

[0080] Data preprocessing unit: used to perform preliminary processing on the collected environmental data, including noise removal, filtering, outlier elimination and data interpolation and completion, to ensure that the environmental data finally collected is accurate, reliable, and suitable for subsequent data analysis and fault identification; through the collaborative work of the above units, the environmental data acquisition module can collect key environmental data in the electrical operation environment in real time, and transmit it to the system's fault identification and analysis module, providing accurate data support for subsequent fault monitoring and alarm.

[0081] The fault identification and analysis module includes a data processing unit, a feature extraction unit, a pattern recognition unit and a fault judgment unit; wherein:

[0082] Data processing unit: used to receive data from the environmental data acquisition module and standardize or normalize the environmental data to ensure that the data belongs to the same dimension and provide consistent input for subsequent feature extraction and pattern recognition;

[0083] Feature extraction unit: used to extract relevant features from the processed environmental data, including current fluctuation amplitude, voltage abnormal amplitude, and temperature and humidity change rate, and transform the time domain, frequency domain, and statistical features into numerical data for model training through feature engineering technology to form feature vectors;

[0084] Pattern recognition unit: Uses the pre-trained support vector machine model to perform real-time pattern recognition on the extracted feature vectors to identify abnormal conditions in the operating environment of electrical equipment, including current fluctuations, voltage anomalies, and sudden changes in temperature and humidity;

[0085] Fault judgment unit: used to automatically judge whether there is a fault according to the abnormal situation output by the pattern recognition unit and the preset fault judgment rules; through the collaborative work of the above units, the fault identification and analysis module can monitor the abnormal situation in the operating environment of the electrical equipment in real time, automatically identify and judge whether there is a potential fault, and provide accurate information for subsequent fault handling and alarm.

[0086] The feature extraction unit includes:

[0087] Current fluctuation amplitude extraction: Calculate the current fluctuation amplitude based on the collected current data. The current fluctuation amplitude is defined as the difference between the maximum and minimum values ​​of the collected current signal. The formula is: C peak =I max -I min , where C peak Indicates the current fluctuation amplitude, I max Indicates the maximum value of the current signal, I min Indicates the minimum value of the current signal;

[0088] Voltage abnormal amplitude extraction: Calculate the voltage abnormal amplitude based on the collected voltage data. The voltage abnormal amplitude is the ratio of the standard deviation of the voltage signal to the mean value, reflecting the discrete degree of voltage fluctuation. The formula is: Among them, V abnorm Indicates the voltage abnormality amplitude, σ V is the standard deviation of the voltage signal, μ V is the mean value of the voltage signal;

[0089] Temperature and humidity change rate extraction: Calculate the temperature and humidity change rate based on the collected temperature and humidity data. The change rate is the change range of temperature or humidity per unit time. The formula is: Among them, T rate is the temperature change rate, ΔT is the temperature change amplitude, and Δt is the unit time interval; H rate is the humidity change rate, ΔH is the humidity change amplitude, and Δt is the unit time interval;

[0090] Time domain feature extraction: By performing time domain analysis on the collected environmental data (such as current, voltage, temperature, humidity, etc.), the time domain features of mean, variance, kurtosis and skewness are extracted. The formula is as follows:

[0091] Among them, x i represents the i-th data point in the data sequence, μ x is the mean, σ x is the standard deviation, N is the number of data points;

[0092] Frequency domain feature extraction: The collected time series data is converted into frequency domain data through Fourier transform, so as to extract frequency domain features, including spectrum density and main frequency; the Fourier transform formula is: Among them, X(f) is the frequency domain data, f is the frequency, x n is the time domain data, N is the number of data points;

[0093] Statistical feature extraction: Based on the collected environmental data, statistical features are extracted, including maximum, minimum, average, standard deviation and variance, to further quantify the volatility and stability of environmental parameters;

[0094] Feature vector formation: After standardization or normalization, the above time domain, frequency domain and statistical features are combined into a high-dimensional feature vector as the input data for subsequent pattern recognition; the feature vector form is: F = [F1, F2, ..., F n ]; where F1, F2, …, F n are the various eigenvalues ​​extracted, and F is the final feature vector formed; through the above steps, the feature extraction unit can extract features related to abnormal electrical working environment from the processed environmental data, and use feature engineering technology to convert them into numerical data that can be used for subsequent machine learning model training to form a feature vector.

[0095] The pattern recognition unit includes:

[0096] Feature vector input: The feature vector output from the feature extraction unit is input into the pre-trained support vector machine model. The feature vector includes the current fluctuation amplitude, voltage abnormal amplitude, and temperature and humidity change rate. The format is: x = [C peak , V abnorm , T rate , H rate , μ x , σ x , Kurt(x), Skew(x), ...], where x represents a feature vector, which contains various environmental data features;

[0097] Support vector machine model classification: The feature vector is input into the support vector machine model for classification; the support vector machine model establishes a decision boundary by learning the existing labeled data to distinguish the normal state from the abnormal state; the expression of the decision function is: Among them, x i represents the i-th sample in the training set, y i is the category label of the sample (normal or abnormal), N1 is the total number of samples, α i is the Lagrange multiplier of the support vector, K(x i , x) is the kernel function, b is the bias term, and f(x) is the classification decision function;

[0098] Abnormal situation identification: By calculating the decision function value f(x), the support vector machine model classifies the input feature vector in real time; when the value of f(x) exceeds the preset threshold, it is judged as an abnormal situation; the formula is: Among them, θ is a preset threshold; through the above steps, the pattern recognition unit can perform pattern recognition on the data in the electrical operation environment in real time based on the pre-trained support vector machine model, and effectively identify abnormal conditions such as current fluctuations, voltage anomalies, and sudden changes in temperature and humidity.

[0099] The fault judgment unit includes:

[0100] Abnormal situation input: Receives real-time abnormal situation information from the pattern recognition unit, including current fluctuations, voltage anomalies, and temperature and humidity mutations. Abnormal situations are transmitted through abnormal identifiers in the form of:

[0101] e=[e current ,e voltage ,e temperature ,e humidity ], where e is the abnormal situation vector, e current、 e voltage、 e temperature and e humidity Identifiers representing current fluctuation, voltage anomaly, temperature anomaly, and humidity anomaly, respectively, with values ​​of 1 or 0, where 1 represents an abnormality and 0 represents a normal state;

[0102] Fault judgment rule setting: Fault judgment is performed based on preset rules and combined with identifiers of various abnormal situations; specific rules include:

[0103] Rule 1, when the current fluctuates e current =1 and voltage abnormality e voltage =1, it is judged as an electrical fault;

[0104] Rule 2: When the temperature is abnormal temperature =1 and humidity is abnormal e humidity =1, it is judged as an environmental fault;

[0105] Rule 3: When current fluctuation and temperature anomaly occur simultaneously, that is, e current =1 and e temperature =1, it is judged as equipment overload fault;

[0106] Fault judgment logic: Based on the preset rules, the input abnormal situation vector e is matched with rules and fault judgment is performed. The expression is:

[0107]

[0108] Among them, F fault Indicates the fault judgment result. If the fault condition is met, F fault =1, indicating a fault; otherwise, F fault=0, indicating no fault; through the above steps, the fault judgment unit can automatically determine whether the abnormal situation in the electrical working environment constitutes a fault. If a fault exists, the result is passed to the alarm trigger module so as to trigger the alarm measures in time to ensure the safety of the operation.

[0109] The priority sorting module includes a fault type assessment unit, a fault severity assessment unit, a fault location identification unit and a priority decision unit; wherein:

[0110] Fault type assessment unit: used to identify the fault type according to the fault information output by the fault identification and analysis module, including electrical fault, environmental fault and equipment overload fault; and assign different basic priorities according to different fault types;

[0111] If the fault type is an electrical fault (such as current fluctuation, voltage anomaly, etc.), the unit is assigned a higher basic priority because electrical faults directly affect equipment operation and may even cause electrical fires or electrical accidents. The basic priority is set to a high priority;

[0112] If the fault type is an environmental fault (such as abnormal temperature and humidity, excessive gas concentration, etc.), the unit is assigned a medium basic priority. Although environmental faults may affect the long-term stability and performance of the equipment, the threat to personnel safety is relatively small, and the basic priority is set to medium priority;

[0113] If the fault type is an equipment overload fault (such as current overload, overtemperature, etc.), the unit is assigned a lower basic priority because the equipment overload fault is usually a non-emergency fault of the equipment. Although it may cause damage to the equipment, it does not immediately threaten the safety of personnel. The basic priority is set to a low priority;

[0114] Fault severity assessment unit: used to assess the severity of the fault according to the data values ​​in the fault information. The data values ​​include current value, voltage value, temperature value and humidity value. The severity assessment is judged according to the set threshold value. The higher the severity of the fault, the higher the priority assigned.

[0115] Fault location identification unit: used to obtain the specific location of the fault, and identify the importance of the fault location in combination with the layout of the electrical working environment and the equipment operating status; the fault location plays a key role in the priority sorting. If the fault occurs in high-voltage equipment or a dangerous area, the priority of the fault is increased; on the contrary, if the fault occurs in auxiliary equipment or a safe area, the priority of the fault will be reduced;

[0116] Priority decision unit: It is used to assign a final priority to each fault event based on the output information of the fault type assessment unit, the fault severity assessment unit and the fault location identification unit, combined with the set priority decision rules, to ensure that the most urgent and most serious faults can be handled first.

[0117] The fault severity assessment unit includes:

[0118] Severity calculation: By comparing each data value with the corresponding threshold, the severity value S of the fault is calculated. fault , which is calculated by weighted summation, and the formula is:

[0119] S fault =w1·sign(ΔI-T1)+w V ·sign(ΔV-T V )+w T ·sign(ΔT-T T )+w H ·sign(ΔH-T H ), where: S fault is the severity value of the fault, sign(x) is the sign function, if x>0, it returns 1, if x≤0, it returns 0, indicating whether it exceeds the threshold; w I ,w V ,w T ,w H are the weight coefficients of current, voltage, temperature and humidity, which are adjusted according to their contribution to the fault severity; ΔI, ΔV, ΔT, ΔH are the deviation values ​​of current, voltage, temperature and humidity, respectively; T1, T V , T T and T H They are the deviation thresholds for current, voltage, temperature and humidity respectively;

[0120] Severity output: Through the above calculation, the severity value S of the fault is obtained fault If S fault Reaching the preset severity threshold S threshold , then the fault is regarded as a high-severity fault and needs to be handled with priority; through the above steps, the fault severity assessment unit can accurately assess the severity of the fault according to the input fault information and the preset threshold, providing a basis for subsequent priority sorting.

[0121] The priority decision unit specifically includes:

[0122] Input data: receiving fault information from the fault type assessment unit, the fault severity assessment unit and the fault location identification unit, the specific information including the fault type basic priority, the fault severity value and the fault location;

[0123] Priority decision rule: The basic priority of the fault type, the severity value of the fault and the fault location are weighted and combined to calculate the final priority P of each fault event. final , the specific formula is: final =w type ·P type +w severity ·S fault +w location ·P location ; Among them, P final is the final priority; w type is the weight coefficient of the fault type, indicating the influence of the fault type on the final priority; w severity is the weight coefficient of fault severity, indicating the influence of fault severity on the final priority; w location is the weight coefficient of the fault location, indicating the influence of the fault location on the final priority; P type S is the basic priority of the fault type; fault Score the severity of the fault; P location is the fault location;

[0124] Final priority output: According to the calculated P final , each fault event is assigned a final priority, if P final If the high priority threshold is reached, the fault is considered to be the most urgent fault with a high priority. final If it is in the medium range, the priority is medium, otherwise it is low;

[0125] Priority adjustment: When a fault occurs, the priority decision unit will dynamically adjust the priority of each fault event based on real-time changing environmental data and fault information to ensure that the most serious and urgent faults are handled first. This decision-making process uses appropriate weight settings and rules to enable the system to intelligently prioritize faults based on different fault types, severity, and locations to ensure that emergency faults are handled in a timely manner.

[0126] The alarm trigger module includes a fault priority input unit and an alarm strategy selection unit; wherein:

[0127] Fault priority input unit: used to receive the fault priority information output by the priority sorting module, which includes the final priority of each fault event, indicating the urgency of the fault and the priority of handling;

[0128] Alarm strategy selection unit: used to select corresponding alarm measures according to the received fault priority information and the preset alarm strategy. The alarm strategy rules make decisions based on the fault priority.

[0129] Strategy 1: For high-priority faults, comprehensive alarm measures are triggered, including sound and light alarms, SMS notifications, email reminders, and App push notifications, to ensure that relevant personnel can handle emergency faults in a timely manner;

[0130] Strategy 2: For medium-priority faults, trigger audible and visual alarms and SMS notifications to ensure that relevant personnel can respond to the fault in a short time, but they do not need to be handled immediately;

[0131] Strategy 3: For low-priority faults, SMS notifications or email reminders are triggered so that relevant personnel can view them during normal operations. Through the collaborative work of the above units, the alarm trigger module can automatically select and execute appropriate alarm measures according to the priority of the fault when a fault occurs, ensuring that relevant personnel can respond in a timely manner according to the urgency of the fault.

[0132] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0133] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things, characterized in that: It includes an environmental data acquisition module, a fault identification and analysis module, a priority sorting module, and an alarm triggering module; among which: Environmental data acquisition module: used to deploy sensors in the electrical operation environment to collect environmental data in real time, including temperature, humidity, current, voltage and gas concentration; Fault identification and analysis module: used to extract features and perform pattern recognition on the collected environmental data, and combined with the pre-trained support vector machine model, identify abnormal conditions in the operating environment of electrical equipment in real time and automatically determine whether there is a fault; Priority sorting module: used to assign a priority to each fault based on the fault information output by the fault identification and analysis module. Priority sorting is based on the type, severity and location of the fault. Alarm trigger module: used to automatically trigger alarm measures according to the fault priority output by the priority sorting module, including sound and light alarm, SMS notification, email reminder or App push, to ensure that relevant personnel receive fault information in time.

2. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 1 is characterized in that: The environmental data acquisition module includes a sensor deployment unit, a data acquisition unit and a data preprocessing unit; wherein: Sensor deployment unit: used to deploy multiple sensors in the electrical working environment, the sensors including temperature and humidity sensors, current sensors, voltage sensors and gas concentration sensors; Data acquisition unit: used to collect environmental data in real time through deployed sensors, the environmental data including temperature, humidity, current, voltage and gas concentration; and transmit the collected data to the data preprocessing unit through the Internet of Things communication protocol, the Internet of Things communication protocol including Wi-Fi, LoRa and NB-IoT; Data preprocessing unit: used to perform preliminary processing on the collected environmental data, including noise removal, filtering, outlier removal and data interpolation and completion.

3. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 1 is characterized in that: The fault identification and analysis module includes a data processing unit, a feature extraction unit, a pattern recognition unit and a fault judgment unit; wherein: Data processing unit: used to receive data from the environmental data acquisition module and standardize or normalize the environmental data to ensure that the data belongs to the same dimension; Feature extraction unit: used to extract relevant features from the processed environmental data, including current fluctuation amplitude, voltage abnormal amplitude, and temperature and humidity change rate, and transform the time domain, frequency domain, and statistical features into numerical data for model training through feature engineering technology to form feature vectors; Pattern recognition unit: Uses the pre-trained support vector machine model to perform real-time pattern recognition on the extracted feature vectors to identify abnormal conditions in the operating environment of electrical equipment, including current fluctuations, voltage anomalies, and sudden changes in temperature and humidity; Fault judgment unit: used to automatically judge whether there is a fault according to the abnormal situation output by the pattern recognition unit and the preset fault judgment rules.

4. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 3 is characterized in that: The feature extraction unit comprises: Current fluctuation amplitude extraction: Calculate the current fluctuation amplitude based on the collected current data. The current fluctuation amplitude is defined as the difference between the maximum value and the minimum value of the collected current signal. Voltage abnormal amplitude extraction: Calculate the voltage abnormal amplitude based on the collected voltage data. The voltage abnormal amplitude is the ratio of the standard deviation of the voltage signal to the mean value. Temperature and humidity change rate extraction: Calculate the temperature and humidity change rate based on the collected temperature and humidity data. The change rate is the change amplitude of temperature or humidity per unit time. Time domain feature extraction: By performing time domain analysis on the collected environmental data, the time domain features of mean, variance, kurtosis and skewness are extracted; Frequency domain feature extraction: The collected time series data is converted into frequency domain data through Fourier transform, so as to extract frequency domain features, including spectrum density and main frequency; Statistical feature extraction: Extract statistical features based on the collected environmental data, including maximum value, minimum value, average value, standard deviation and variance; Feature vector formation: The above time domain, frequency domain and statistical features are standardized or normalized and then merged into a high-dimensional feature vector; the feature vector form is: F = [F1, F2, ..., F n ]; where F1, Fx, ..., F n are the extracted eigenvalues, and F is the final eigenvector.

5. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 4 is characterized in that: The pattern recognition unit comprises: Feature vector input: The feature vector output from the feature extraction unit is input into the pre-trained support vector machine model, wherein the feature vector includes the current fluctuation amplitude, the voltage abnormal amplitude, and the temperature and humidity change rate; Support vector machine model classification: The feature vector is input into the support vector machine model for classification; the support vector machine model establishes a decision boundary by learning the existing labeled data to distinguish the normal state from the abnormal state; the expression of the decision function is: Among them, x i represents the i-th sample in the training set, y i is the category label of the sample, N1 is the total number of samples, α i is the Lagrange multiplier of the support vector, K(x i , x) is the kernel function, b is the bias term, and f(x) is the classification decision function; Abnormal situation identification: By calculating the decision function value f(x), the support vector machine model classifies the input feature vector in real time; when the value of f(x) exceeds the preset threshold, it is judged as an abnormal situation; the formula is: f(x)≥θ→abnormal situation, where θ is the preset threshold.

6. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 5 is characterized in that: The fault judgment unit comprises: Abnormal situation input: Receives abnormal situation information identified in real time from the pattern recognition unit, including current fluctuation, voltage anomaly, and temperature and humidity mutation. The abnormal situation is transmitted through an abnormal identifier in the form of: e=[e current , e voltage , e temperature , e humidity ], where e is the abnormal situation vector, e current 、e voltage 、e temperature and e humidity Identifiers representing current fluctuation, voltage anomaly, temperature anomaly, and humidity anomaly, respectively, with values ​​of 1 or 0, where 1 represents an abnormality and 0 represents a normal state; Fault judgment rule setting: Fault judgment is performed based on preset rules and combined with identifiers of various abnormal situations; specific rules include: Rule 1, when the current fluctuates e current =1 and voltage abnormality e voltage =1, it is judged as an electrical fault; Rule 2: When the temperature is abnormal temperature =1 and humidity is abnormal e humidity =1, it is judged as an environmental fault; Rule 3: When current fluctuation and temperature anomaly occur simultaneously, that is, e current =1 and e temDerature =1, it is judged as equipment overload fault; Fault judgment logic: Based on the preset rules, the input abnormal situation vector e is matched with rules and fault judgment is performed. The expression is: Among them, F fault Indicates the fault judgment result. If the fault condition is met, F fault =1, indicating a fault; otherwise, F fault =0, indicating no fault.

7. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 1 is characterized in that: The priority sorting module includes a fault type assessment unit, a fault severity assessment unit, a fault location identification unit and a priority decision unit; wherein: Fault type assessment unit: used to identify the fault type according to the fault information output by the fault identification and analysis module, including electrical fault, environmental fault and equipment overload fault; and assign different basic priorities according to different fault types; If the fault type is an electrical fault, the basic priority is set to high priority; If the fault type is an environmental fault, the basic priority is set to medium priority; If the fault type is equipment overload fault, the basic priority is set to low priority; Fault severity evaluation unit: used to evaluate the severity of the fault according to the data values ​​in the fault information, the data values ​​include current value, voltage value, temperature value and humidity value, the severity evaluation is judged according to the set threshold value, the higher the severity of the fault, the higher the priority assigned; Fault location identification unit: used to obtain the specific location of the fault, and identify the importance of the fault location in combination with the layout of the electrical working environment and the equipment operating status. If the fault occurs in high-voltage equipment or a dangerous area, the priority of the fault is increased; on the contrary, if the fault occurs in an auxiliary device or a safe area, the priority of the fault is reduced; Priority decision unit: used to assign a final priority to each fault event based on the output information of the fault type assessment unit, the fault severity assessment unit and the fault location identification unit in combination with the set priority decision rules.

8. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 7 is characterized in that: The fault severity assessment unit comprises: Severity calculation: By comparing each data value with the corresponding threshold, the severity value S of the fault is calculated. fault ; Severity output: Through the above calculation, the severity value S of the fault is obtained fault If S fault Reaching the preset severity threshold S threshold , then the fault is considered a high-severity fault and needs to be handled with priority.

9. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 8 is characterized in that: The priority decision unit specifically includes: Input data: receiving fault information from the fault type assessment unit, the fault severity assessment unit and the fault location identification unit, the specific information including the fault type basic priority, the fault severity value and the fault location; Priority decision rule: The basic priority of the fault type, the severity value of the fault and the fault location are weighted and combined to calculate the final priority P of each fault event. final ; Final priority output: According to the calculated P final , each fault event is assigned a final priority, if P final If the high priority threshold is reached, the fault is considered to be the most urgent fault with a high priority. final If it is in the medium range, the priority is medium, otherwise it is low; Priority adjustment: When a fault occurs, the priority decision unit will dynamically adjust the priority of each fault event based on real-time changing environmental data and fault information to ensure that the most serious and urgent faults are handled first.

10. The electrical operation environment abnormality monitoring and automatic alarm system based on the Internet of Things according to claim 1 is characterized in that: The alarm trigger module includes a fault priority input unit and an alarm strategy selection unit; wherein: Fault priority input unit: used to receive the fault priority information output by the priority sorting module, the information includes the final priority of each fault event, indicating the urgency of the fault and the priority of processing; Alarm strategy selection unit: used to select corresponding alarm measures according to the received fault priority information and in combination with the preset alarm strategy, wherein the alarm strategy rule makes decisions based on the fault priority; Strategy 1: For high-priority faults, comprehensive alarm measures are triggered, including audible and visual alarms, SMS notifications, email reminders, and App push notifications; Strategy 2: For medium-priority faults, an audible and visual alarm and SMS notification are triggered, but no immediate processing is required; Strategy 3: For low-priority faults, trigger SMS notifications or email reminders so that relevant personnel can view them during normal operations.

Images