Intelligent switch circuit control system

Abstract

The invention provides an intelligent switching circuit control system, which relates to the technical field of circuit control, and comprises a switching circuit control unit used for controlling the switching operation of at least one circuit according to a preset control strategy and adjusting the working parameters of the circuit according to the running state of the circuit, and a fault prediction module connected with the switching circuit control unit. According to the intelligent switch circuit control system, more accurate fault prediction is realized by introducing the dynamic fault probability model, and the prediction accuracy is gradually adjusted according to the error weight of historical data. As time goes on, the system can more depend on latest real-time data, the prediction sensitivity and response speed are improved, and the probability of false alarm and missing alarm is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit control, and in particular to an intelligent switch circuit control system. Background Art

[0002] Currently, switching circuit control systems are widely used in various automation control fields, including industrial automation, home appliance control, and power dispatching. Common switching control technologies include mechanical relay control systems and solid-state switch control systems. Relay control systems typically switch circuits through mechanical contacts and are suitable for many low-power, high-load applications, offering high reliability and stability. Solid-state switch control systems, on the other hand, use semiconductor switching elements, offering faster response times and longer lifespans, and are widely used in high-frequency, low-power applications. These control systems can effectively switch circuits on and off and provide certain automated control functions to ensure proper operation.

[0003] While existing switching circuit control systems have achieved widespread application across a wide range of sectors, they still suffer from numerous key deficiencies. These systems often lack the ability to diagnose and monitor faults in real time, hindering the timely detection and implementation of measures for potential issues, impacting overall system safety and reliability. Therefore, existing technologies urgently need to be improved to meet the increasingly complex and diverse demands of industrial applications. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides an intelligent switching circuit control system. The technical problem to be solved by this invention is: how to improve system energy efficiency and reduce energy consumption by real-time monitoring of circuit load and environmental changes, combining dynamic fault prediction and adaptive control strategies, while accurately predicting circuit faults.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent switch circuit control system, comprising:

[0006] A switching circuit control unit, configured to control the switching operation of at least one circuit according to a preset control strategy;

[0007] a fault prediction module, connected to the switch circuit control unit and based on historical data and real-time sensor data;

[0008] Adaptive control module, used to automatically adjust the control strategy according to real-time circuit load, environmental changes and working conditions;

[0009] A fault alarm module, which triggers an alarm signal to notify the user or management system when the fault prediction module detects a fault risk;

[0010] The remote monitoring interface allows users to remotely view circuit status, operating parameters and fault information through external devices.

[0011] Preferably, the switch circuit control unit includes a switch control module, a working parameter adjustment module and a control strategy interface.

[0012] Preferably, the fault prediction module includes a data acquisition unit, a data preprocessing unit, a machine learning algorithm unit, a prediction analysis unit and a fault warning generation unit. The data preprocessing unit includes a signal filter, an outlier remover and a standardization module. The machine learning algorithm unit generates a circuit fault prediction model based on an unsupervised learning model and evaluates the probability of occurrence of circuit faults in real time. The prediction analysis unit calculates the probability of each type of circuit fault in combination with the output of the machine learning algorithm unit.

[0013] Preferably, the adaptive control module includes a load monitoring unit, an environment perception unit, an adaptive adjustment unit, an optimization algorithm unit and an energy management unit.

[0014] Preferably, the fault alarm module includes an alarm triggering unit, an alarm mode selecting unit, a fault handling suggestion unit and a handling execution unit.

[0015] Preferably, the adaptive control module reflects the nonlinear regulation of the circuit power output when the load changes by introducing an exponential decay relationship between the load and the ambient temperature. When the load increases, the system adjusts the power output according to the load change while avoiding overload. The formula for the exponential decay relationship between the load and the ambient temperature is:

[0016]

[0017] in:

[0018] P a is the power output of the optimized circuit;

[0019] P b is the basic power;

[0020] L r For real-time load;

[0021] L max is the maximum load;

[0022] T e is the real-time ambient temperature;

[0023] T min and T max are the minimum and maximum ambient temperatures, respectively;

[0024] λ1 is the load adjustment coefficient, which is used to adjust the impact of the load on the circuit power;

[0025] γ is the influence coefficient of temperature change, which controls the influence of temperature on power regulation.

[0026] Preferably, the fault prediction module adopts the following dynamic fault probability model formula:

[0027]

[0028] in:

[0029] P f (t) is the predicted probability of failure at time t;

[0030] I(t) is the real-time current value at time t, I max is the maximum current of the circuit;

[0031] V(t) is the real-time voltage value at time t, V max is the maximum voltage of the circuit;

[0032] T(t) is the ambient temperature at time t, T min and T max are the minimum and maximum ambient temperatures, respectively;

[0033] a, b, and c are the weight coefficients of the fault model, reflecting the contribution of current, voltage, and temperature to the fault probability;

[0034] α, β, and γ are their respective influence indices, which are used to control the nonlinear contribution of each factor to the failure probability;

[0035] δ is the time decay coefficient, which is used to reflect the impact of historical data;

[0036] W k is the prediction error weight at the kth moment. As time goes by, the weight gradually increases, increasing the dependence on the latest data.

[0037] Preferably, the alarm mode selection unit includes visual alarm, sound alarm and network-based SMS push notification, and the processing execution unit performs automated operations according to the alarm information and fault handling suggestions.

[0038] The present invention provides an intelligent switch circuit control system. It has the following beneficial effects:

[0039] This intelligent switching circuit control system achieves more accurate fault predictions by incorporating a dynamic fault probability model. It gradually adjusts the accuracy of predictions based on the error weights of historical data. Over time, the system becomes more reliant on the latest real-time data, improving prediction sensitivity and response speed, and effectively reducing the probability of false positives and missed negatives.

[0040] By incorporating an exponential decay relationship between load and ambient temperature, this approach dynamically adjusts the circuit's power output, avoiding the over-regulation and instability that can occur in traditional circuit control systems under load fluctuations and environmental changes. This nonlinear regulation method responds in real time to changes in load and ambient temperature, ensuring optimal circuit operation, thereby improving system efficiency and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of a structure for realizing the invention;

[0042] Figure 2 The present invention is a schematic diagram of the structure of a fault prediction module. DETAILED DESCRIPTION

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0044] Example 1

[0045] like Figure 1-2 As shown, an embodiment of the present invention provides an intelligent switching circuit control system, including a switching circuit control unit for controlling the switching operation of at least one circuit according to a preset control strategy and adjusting the circuit operating parameters based on the circuit's operating status. The switching circuit control unit includes a switch control module, an operating parameter adjustment module, and a control strategy interface. In a home automation system, the switch control module controls a home lighting circuit. Assume that the control signal sets a maximum current of 10A, a voltage of 220V, and a maximum load of 200W for the lighting circuit. When the system detects that the circuit load is approaching the maximum, the switch control module shuts down the circuit via a solid-state relay to prevent overload. When the load falls below 80% of the maximum, the system re-enables the circuit via a relay. For example, when the system detects a load of 160W (less than 80% of the maximum load), the switch control module re-enables the circuit. The operating parameter adjustment module primarily adjusts the circuit's voltage, current, and frequency to ensure efficient operation according to actual requirements. Dynamic adjustment is performed through real-time data feedback, and parameter optimization is performed using a PID control algorithm (proportional-integral-derivative control).

[0046] Assume that in a power system, the voltage and current are set to 220V and 8A. The operating parameter adjustment module in the system monitors the current value of the current circuit in real time. Suppose that during a real-time monitoring, the current value is 6A, which is lower than the set standard current value.

[0047] Based on the PID algorithm, the control system calculates the adjustment increment to optimize the current output. When the control system calculates the current difference ΔI = 2A, the system will compensate for the current difference by adjusting the voltage or frequency to ensure stable circuit operation.

[0048] The fault prediction module is connected to the switching circuit control unit. Based on historical data and real-time sensor data, it predicts possible circuit faults, analyzes the circuit status in real time, and generates fault warning information. The fault prediction module includes a data acquisition unit, a data preprocessing unit, a machine learning algorithm unit, a prediction analysis unit, and a fault warning generation unit. The data preprocessing unit includes a signal filter, an outlier remover, and a standardization module. It performs noise filtering, anomaly detection, and standardization on the collected data to ensure high quality and consistency of the data. The machine learning algorithm unit generates a circuit fault prediction model based on an unsupervised learning model and evaluates the probability of circuit faults in real time. The prediction analysis unit calculates the probability of each type of circuit fault based on the output of the machine learning algorithm unit and determines whether to trigger a fault warning through threshold judgment. The fault prediction module adopts a dynamic fault probability model. Traditional fault prediction often uses a static model, which only considers data such as current or temperature at a certain moment, but ignores the dynamic changes in the weights of various factors. The dynamic fault probability model dynamically adjusts the influence weights of various parameters according to the historical behavior of the circuit, load changes, and environmental conditions.

[0049] The formula is as follows:

[0050]

[0051] in:

[0052] P f (t) is the predicted probability of failure at time t.

[0053] I(t) is the real-time current value at time t, I max is the maximum current of the circuit.

[0054] V(t) is the real-time voltage value at time t, V max is the maximum voltage of the circuit.

[0055] T(t) is the ambient temperature at time t, T min and T max are the minimum and maximum ambient temperatures, respectively.

[0056] a, b, and c are the weight coefficients of the fault model, reflecting the contribution of current, voltage, and temperature to the fault probability.

[0057] α, β, and γ are their respective influence indices, which are used to control the nonlinear contribution of each factor to the failure probability.

[0058] δ is the time attenuation coefficient, which is used to reflect the impact of historical data.

[0059] W k is the prediction error weight at moment k. Over time, the weight gradually increases, increasing reliance on the latest data. By introducing the historical prediction error weight Wk and the dynamic attenuation coefficient δ, the influence of various parameters can be adjusted based on the circuit's performance over different time periods. Over long-term use, the model can better adapt to the actual nonlinear relationships in the circuit: the relationship between current, voltage, and temperature and the probability of fault occurrence is modeled using a power function, which allows the fault prediction model to better handle nonlinear changes.

[0060] The adaptive control module is used to automatically adjust the control strategy based on real-time circuit load, environmental changes, and operating conditions to optimize the circuit's operating state, improve system energy efficiency, and reduce energy consumption. The adaptive control module includes a load monitoring unit, an environmental perception unit, an adaptive adjustment unit, an optimization algorithm unit, and an energy management unit. The adaptive control module reflects the nonlinear regulation of the circuit's power output when the load changes by introducing an exponential decay relationship between the load and the ambient temperature. When the load increases, the system will adjust the power output according to the load change while avoiding overload. The formula for the exponential decay relationship between the load and the ambient temperature is:

[0061]

[0062] in:

[0063] P a is the power output of the optimized circuit.

[0064] P b As the basic power.

[0065] L r For real-time load.

[0066] L max is the maximum load.

[0067] T e The real-time ambient temperature.

[0068] T min and T max are the minimum and maximum ambient temperatures, respectively.

[0069] λ1 is the load adjustment coefficient, which is used to adjust the impact of the load on the circuit power.

[0070] γ is the influence coefficient of temperature change, which controls the influence of temperature on power regulation.

[0071] The relationship between ambient temperature and power regulation uses a nonlinear power function, reflecting the nonlinear effect of high temperature environment on circuit performance.

[0072] The fault alarm module triggers an alarm signal when the fault prediction module detects a fault risk, notifying the user or management system. The fault alarm module includes an alarm trigger unit, an alarm mode selection unit, a fault handling suggestion unit, and a processing execution unit. The alarm mode selection unit includes visual alarms (such as LED flashing, display screen warnings), audible alarms (such as buzzers), and network-based SMS push notifications. The processing execution unit performs automated operations based on the alarm information and fault handling suggestions, such as switching to a backup circuit, shutting down a circuit, and adjusting circuit parameters, to prevent the fault from escalating and improve system stability.

[0073] The remote monitoring interface allows users to remotely view circuit status, operating parameters and fault information through external devices.

[0074] Example 2

[0075] Specific implementation of the fault prediction module

[0076] 1. Data acquisition unit:

[0077] The data acquisition unit is responsible for acquiring various operating parameters in the circuit (such as current, voltage, temperature, etc.) in real time and transmitting these data to the subsequent processing unit.

[0078] Implementation steps:

[0079] In an industrial circuit application, assume that the system uses sensors to collect data such as current, voltage, and ambient temperature. The system collects data once per second, with the current data (in amperes) ranging from 0A to 10A, the voltage data (in volts) ranging from 0V to 240V, and the temperature data (in degrees Celsius) ranging from 10°C to 50°C.

[0080] In one acquisition process, assuming that the current value is 6.5A, the voltage value is 220V, and the temperature value is 35°C, the real-time acquired data is transmitted to the data pre-processing unit for subsequent processing.

[0081] 2. Data preprocessing unit:

[0082] The data preprocessing unit is responsible for processing the collected raw data to ensure that the data quality meets the requirements of the fault prediction model. This unit includes a signal filter, an outlier remover, and a normalization module.

[0083] Implementation steps:

[0084] Signal filter: Kalman filtering technology is used to remove high-frequency noise from current and voltage data. For example, when collecting data, the current value is 6.5A. After Kalman filtering, the current value is smoothed to 6.45A.

[0085] Outlier rejecter: Detects and rejects sensor data that is clearly abnormal. For example, if the temperature data suddenly changes to 100°C, this value is clearly an abnormal data and will be rejected.

[0086] Normalization: This module normalizes current, voltage, and temperature data. For example, a current of 6.5A is converted to 0.65 after normalization (based on a maximum current of 10A). All data is uniformly converted to the range of [0, 1] for subsequent analysis.

[0087] 3. Machine Learning Algorithm Unit:

[0088] The machine learning algorithm unit generates a circuit fault prediction model based on an unsupervised learning model. This module trains the model using historical and real-time data and evaluates the circuit's fault probability in real time based on the training results.

[0089] Implementation steps:

[0090] Assume that the current, voltage, and temperature data from historical data have been normalized. For example, the historical data set contains current (normalized to a range of 0.1 to 1.0), voltage (normalized to a range of 0.05 to 1.0), and temperature (normalized to a range of 0.1 to 1.0).

[0091] Using the K-means clustering algorithm, the historical data is divided into three clusters, each representing a state with a certain probability of failure. Assuming the center of the first cluster (representing the normal state) is 0.5 for current, 0.7 for voltage, and 0.6 for temperature, any current, voltage, or temperature data that deviates from this state is likely to be predicted as a failure state.

[0092] When real-time data such as 6.5A, 220V, and 35°C is fed into the model, the machine learning algorithm unit evaluates the current state and maps it to the corresponding cluster, predicting whether the data belongs to a normal or faulty state.

[0093] 4. Prediction and Analysis Unit:

[0094] The prediction and analysis unit calculates the probability of circuit failure based on the output of the machine learning algorithm unit and determines whether to trigger an early warning.

[0095] Implementation steps:

[0096] Assuming the real-time current is 6.5A, the voltage is 220V, and the temperature is 35°C, through the output of the machine learning algorithm, the current current value is within the standardized range of 0.65, and the voltage and temperature also conform to the predicted pattern.

[0097] According to the calculation of the prediction analysis unit, the probability of failure corresponding to the combined value of current, voltage and temperature is 0.12, which is lower than the set threshold (for example, 0.5), so the alarm is not triggered temporarily.

[0098] If the predicted probability exceeds a threshold, the unit will trigger a fault warning signal, indicating that the circuit is at risk of failure.

[0099] 5. Fault warning generation unit:

[0100] The fault warning generation unit is responsible for generating fault warning signals and sending warning information to users or management systems. The warning content includes the fault type, possible location, and recommended treatment measures.

[0101] Implementation steps:

[0102] If the failure probability output by the prediction analysis unit is 0.55, which exceeds the set threshold of 0.5, the warning generation unit will generate a warning signal with the following content:

[0103] Fault type: current overload.

[0104] Occurrence location: Lighting circuit A1.

[0105] Action: Immediately shut down the circuit and check the load.

[0106] This warning will be sent to the operator or maintenance personnel via SMS to ensure timely response.

[0107] Specific implementation of the dynamic failure probability model:

[0108] Dynamic weight adjustment: The dynamic fault probability model of the fault prediction module dynamically adjusts the weights of these factors based on the changes in current, voltage, and temperature. Assume that the historical fault data and real-time data are:

[0109] The normalized value of the current I(t) is 0.65, and the maximum current is 10A.

[0110] The normalized value of the voltage V(t) is 0.9, and the maximum voltage is 240V.

[0111] The normalized value of temperature T(t) is 0.7, and the temperature range is 10°C to 50°C.

[0112] Dynamically adjust weights: Assuming the dynamic attenuation coefficient δ = 0.01, the prediction error weight W kAs time goes by, it gradually increases. Based on the above data, the system dynamically calculates and adjusts the parameters:

[0113]

[0114] The weights of current, voltage, and temperature are 0.6, 0.3, and 0.1, respectively, reflecting the contribution of these parameters to the failure probability.

[0115] Through historical data and time decay, W k Increasing it gradually allows the system to focus more on recent real-time data rather than relying too much on historical data.

[0116] At the current time t, the probability of circuit failure is 0.664, which indicates that the circuit has a high failure risk at this moment and the system needs to take corresponding measures (such as issuing an early warning).

[0117] Example 3

[0118] Specific implementation of the adaptive control module

[0119] 1. Load monitoring unit:

[0120] The load monitoring unit is responsible for real-time monitoring of the load conditions in the circuit to ensure that the system can dynamically adjust the working state of the circuit according to the changes in the load to avoid circuit overload or unstable operation.

[0121] Implementation steps:

[0122] Assume that in an industrial control system, the maximum load of a circuit is 5000W. The system uses sensors to measure the circuit's load power in real time. For example, suppose the current real-time load is 3500W, which is 70% of the maximum load and lower than 80%.

[0123] The load monitoring unit will periodically transmit this data to the adaptive regulation unit for subsequent regulation.

[0124] 2. Environmental perception unit:

[0125] The environmental sensing unit monitors the temperature of the circuit's environment in real time, ensuring that the circuit can operate efficiently and safely under different temperature conditions. The system adjusts the circuit's operating mode in response to changes in ambient temperature.

[0126] Implementation steps:

[0127] Assume that the circuit operates in a factory environment with an ambient temperature range from 10°C (winter) to 45°C (summer). The current ambient temperature is 30°C.

[0128] The environmental perception unit monitors the real-time data of 30°C through the temperature sensor and transmits this data to the adaptive adjustment module.

[0129] 3. Adaptive adjustment unit:

[0130] The adaptive regulation unit automatically adjusts circuit parameters such as current, voltage or frequency according to real-time load and environmental changes, optimizes circuit power output, and ensures that the system can operate stably under different working conditions.

[0131] Implementation steps:

[0132] Based on real-time load data (3500W) and ambient temperature (30°C), the system adjusts the circuit power output by introducing an exponential decay relationship between load and ambient temperature.

[0133] Assume that the system base power is 5000W, the maximum load is 5000W, the current load is 3500W, the current ambient temperature is 30°C, the minimum temperature is 10°C, and the maximum temperature is 45°C. Based on this data, the system will use the following formula to calculate the optimized circuit power output:

[0134]

[0135] in:

[0136] P a is the power output of the optimized circuit.

[0137] P b It is the basic power (5000W).

[0138] L r is the real-time load (3500W).

[0139] L max is the maximum load (5000W).

[0140] T env is the real-time ambient temperature (30°C).

[0141] T min and T max are the minimum and maximum ambient temperatures (10°C and 45°C), respectively.

[0142] λ is the load adjustment coefficient (0.05).

[0143] α is the influence coefficient of temperature change (1.2).

[0144] Implementation steps:

[0145] First calculate the exponential decay part of the load effect:

[0146]

[0147] Then calculate the power function part of the temperature effect:

[0148]

[0149] Substitute the formula to calculate the optimized circuit power output:

[0150] P a =5000W·(1-0.05·0.496·0.334)≈5000W·(1-0.0083)≈4995.85W

[0151] After adjustment, the system will optimize the power output to 4995.85W to achieve optimal power distribution.

[0152] 4. Optimization algorithm unit:

[0153] The optimization algorithm unit uses a real-time optimization algorithm based on load and environmental impact data to determine the optimal control parameters for the circuit. This algorithm dynamically adjusts the circuit's operating state, improving energy efficiency and reducing unnecessary energy loss.

[0154] Implementation steps:

[0155] Based on the load data (3500W) and ambient temperature data (30℃), the optimization algorithm unit evaluates the energy efficiency of the current system and adjusts the circuit's operating mode according to the set goals (such as maximum energy efficiency or minimum energy consumption).

[0156] For example, when the load is low and the temperature is moderate, the system chooses to reduce the current to save energy, while in a high load or high temperature environment, the system chooses to increase the current appropriately to ensure stable operation of the circuit.

[0157] 5. Energy Management Unit:

[0158] The energy management unit achieves energy-saving operation by regulating the power output of the circuit and generates energy consumption reports based on real-time data.

[0159] Implementation steps:

[0160] Assume that the energy efficiency target set by the system is to save 10% of energy consumption each year. The energy management unit monitors the total energy consumption of the circuit in real time and adjusts the circuit's operating mode based on the optimized power output.

[0161] For example, when the load is 3500W and the temperature is 30℃, the system achieves energy saving by adjusting the power output to 4995.85W, which is optimized compared to the original 5000W.

[0162] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent switch circuit control system, characterized in that: include: A switching circuit control unit, configured to control the switching operation of at least one circuit according to a preset control strategy; a fault prediction module, connected to the switch circuit control unit and based on historical data and real-time sensor data; Adaptive control module, used to automatically adjust the control strategy according to real-time circuit load, environmental changes and working conditions; Fault alarm module; The remote monitoring interface allows users to remotely view circuit status, operating parameters and fault information through external devices.

2. The intelligent switch circuit control system according to claim 1, characterized in that: The switch circuit control unit includes a switch control module, a working parameter adjustment module and a control strategy interface.

3. The intelligent switch circuit control system according to claim 1, characterized in that: The fault prediction module includes a data acquisition unit, a data preprocessing unit, a machine learning algorithm unit, a prediction analysis unit and a fault warning generation unit. The data preprocessing unit includes a signal filter, an outlier remover and a normalization module. The machine learning algorithm unit generates a circuit fault prediction model based on an unsupervised learning model. The prediction analysis unit calculates the probability of each type of circuit fault based on the output of the machine learning algorithm unit.

4. The intelligent switch circuit control system according to claim 1, characterized in that: The adaptive control module includes a load monitoring unit, an environment perception unit, an adaptive adjustment unit, an optimization algorithm unit and an energy management unit.

5. The intelligent switch circuit control system according to claim 1, characterized in that: The fault alarm module includes an alarm triggering unit, an alarm mode selecting unit, a fault handling suggestion unit and a handling execution unit.

6. The intelligent switch circuit control system according to claim 4, characterized in that: The adaptive control module reflects the nonlinear regulation of the power output of the circuit when the load changes by introducing an exponential decay relationship between the load and the ambient temperature. The formula for the exponential decay relationship between the load and the ambient temperature is: in: P a is the power output of the optimized circuit; P b is the basic power; L r For real-time load; L max is the maximum load; T e is the real-time ambient temperature; T min and T max are the minimum and maximum ambient temperatures, respectively; λ1 is the load adjustment coefficient, which is used to adjust the impact of the load on the circuit power; γ is the influence coefficient of temperature change, which controls the influence of temperature on power regulation.

7. The intelligent switch circuit control system according to claim 3, characterized in that: The fault prediction module adopts the dynamic fault probability model formula as follows: in: P f (t) is the predicted probability of failure at time t; I(t) is the real-time current value at time t, I max is the maximum current of the circuit; V(t) is the real-time voltage value at time t, V max is the maximum voltage of the circuit; T(t) is the ambient temperature at time t, T min and T max are the minimum and maximum ambient temperatures, respectively; a, b, and c are the weight coefficients of the fault model, reflecting the contribution of current, voltage, and temperature to the fault probability; α, β, and γ are their respective influence indices, which are used to control the nonlinear contribution of each factor to the failure probability; δ is the time decay coefficient, which is used to reflect the impact of historical data; W k is the prediction error weight at the kth moment.

8. The intelligent switch circuit control system according to claim 5, characterized in that: The alarm mode selection unit includes visual alarm, sound alarm and network-based SMS push notification, and the processing execution unit performs automated operations based on the alarm information and fault handling suggestions.

Images