Fault identification method for branching system alarm controller

Abstract

The invention discloses a fault identification method for a branching system alarm controller, and relates to the technical field of fire safety, and the method comprises the steps: collecting a working current value and a working voltage value of each alarm loop in the branching system alarm controller, converting the working current value and the working voltage value into digital signals, obtaining current data and voltage data, and transmitting the current data and the voltage data to the branching system alarm controller; judging the working state of each alarm loop by adopting a preset threshold value method; establishing a fault feature vector matrix, inputting the fault feature vector matrix into a pre-trained fault diagnosis model, and outputting a fault type judgment result; and according to the fault type judgment result, calling a corresponding processing scheme from a pre-established fault processing database to complete fault identification. According to the invention, the whole process intelligence from fault detection, diagnosis to processing is realized, the operation reliability of the branching system alarm controller is improved, the maintenance cost is reduced, and the method has important practical significance for improving the overall performance of a fire safety system.

Description

Technical Field

[0001] The invention relates to the technical field of fire safety, in particular to a fault identification method for a split-line alarm controller. Background Art

[0002] With the continuous improvement of social security needs, the automatic fire alarm system plays an increasingly important role in building fire safety. As the core component of the automatic fire alarm system, the split-line alarm controller connects various fire detectors and other fire-fighting equipment through multiple alarm circuits to monitor the fire status in the building in real time. In recent years, with the expansion of building scale and the improvement of intelligence, the technical requirements of the split-line alarm controller in terms of system integration, data processing and fault diagnosis have also been increasing. The traditional split-line alarm controller mainly adopts a fault detection method based on current and voltage threshold judgment, and identifies basic fault types such as short circuit and open circuit in the circuit by setting a fixed judgment threshold. However, this simple threshold judgment method is difficult to accurately identify complex faults caused by the superposition of multiple factors, and it is easy to make misjudgments when the external environment interference is large, affecting the reliability and stability of the system.

[0003] The existing fault diagnosis technology for the split-line alarm controller has the following shortcomings: first, the traditional fault diagnosis method mainly relies on manual experience for fault analysis and processing, with low diagnostic efficiency and difficulty in ensuring accuracy; second, the existing automated fault diagnosis system generally adopts a single threshold judgment method, which cannot effectively identify and classify complex fault types, especially when multiple circuits fail at the same time, it is difficult to accurately locate the source of the fault and give corresponding treatment plans; third, there is a lack of intelligent fault feature extraction and analysis methods, and it is impossible to fully utilize the large amount of historical data generated during the system operation to optimize the fault diagnosis strategy; finally, there is a lack of an effective correlation mechanism between the fault diagnosis results of the existing system and the fault handling plan, resulting in slow fault response and poor handling effect.

[0004] In response to the above problems, the present invention proposes a fault identification method for a line-based alarm controller based on deep learning, which can effectively improve the accuracy and automation level of fault diagnosis. Summary of the invention

[0005] In view of the problems in the existing fault diagnosis technology of the split-line alarm controller, such as low fault identification accuracy, low diagnosis efficiency and inability to handle complex fault conditions, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to provide a fault identification method based on deep learning to achieve rapid and accurate identification, classification and intelligent recommendation of treatment solutions for the faults of the split-line alarm controller, so as to improve the automation level and accuracy of fault diagnosis.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In the first aspect, an embodiment of the present invention provides a fault identification method for a split-line alarm controller, which includes collecting the working current value and the working voltage value of each alarm circuit in the split-line alarm controller, converting the working current value and the working voltage value into digital signals to obtain current data and voltage data; based on the current data and voltage data, using a preset threshold method to judge the working state of each alarm circuit, wherein the preset threshold includes an upper current threshold, a lower current threshold, an upper voltage threshold and a lower voltage threshold; according to the working state, establishing a fault feature vector matrix, wherein the fault feature vector matrix includes current abnormality flag bits and voltage abnormality flag bits of each alarm circuit; inputting the fault feature vector matrix into a pre-trained fault diagnosis model, the fault diagnosis model analyzes the fault feature vector matrix through a deep learning algorithm, and outputs a fault type judgment result; according to the fault type judgment result, retrieving the corresponding processing plan from a pre-established fault processing database to complete fault identification.

[0009] As a preferred solution of the fault identification method of the line-split alarm controller of the present invention, wherein: the fault diagnosis model performs forward calculation on the data segment, the output layer calculates the probability distribution of various fault types through the softmax function, and takes the category with the highest probability as the fault type judgment result of this data segment; the judgment results of more than p consecutive data segments are voted and counted to obtain the final fault type judgment result, and the probability values ​​of various fault types are recorded as the credibility indicators of the fault judgment.

[0010] As a preferred solution of the fault identification method of the split-line alarm controller of the present invention, the method for obtaining the data segments is as follows: the fault feature vector matrix is ​​normalized and the data is mapped to the interval [0,1] using the min-max method; the normalized data is divided into data segments of length 10 according to the time series, the overlap rate between each data segment is set, and the data are input into the fault diagnosis model in sequence through a sliding window method.

[0011] As a preferred solution of the fault identification method of the line-split alarm controller of the present invention, the construction process of the fault characteristic vector matrix includes the following steps: a fault characteristic vector matrix is ​​established using an N×M two-dimensional array structure, wherein N is the total number of alarm circuits and M is the number of characteristic bits of each alarm circuit; in the fault characteristic vector matrix, each row of data corresponds to the characteristic data of an alarm circuit, and the first bit of each row of data is a current overload flag bit, which is set to 1 when the alarm circuit is in a current overload state, otherwise it is set to 0; the second bit is a current disconnect flag bit, which is set to 1 when the alarm circuit is in a current disconnect state, otherwise it is set to 0; the third bit is a voltage overvoltage flag bit, which is set to 1 when the alarm circuit is in a voltage overvoltage state, otherwise it is set to 0; the fourth bit is a voltage undervoltage flag bit, which is set to 1 when the alarm circuit is in a voltage undervoltage state, otherwise it is set to 0.

[0012] As a preferred solution of the fault identification method of the split-line alarm controller of the present invention, it also includes: performing statistical analysis on the flag bits in the fault feature vector matrix, and calculating the setting frequency of each flag bit of each alarm loop in a continuous sampling period. The specific formula is as follows:

[0013]

[0014] w i =e -λ(t-i)

[0015] Where F(t) is the frequency of the flag bit at the current sampling point t, n is the sampling window length, b i is the flag value of the i-th sampling point in the window, w i is the time weight coefficient of the i-th sampling point in the window, λ is the time attenuation factor, t is the current sampling point, and i is the sampling point in the window.

[0016] When the setting frequency of a certain flag bit exceeds 80% of the preset bit frequency, the fault type corresponding to this flag bit is determined to be a steady-state fault; when the setting frequency of a certain flag bit is between 20% and 80% of the preset bit frequency, the fault type corresponding to this flag bit is determined to be a fluctuating fault; when the setting frequency of a certain flag bit is less than 20% of the preset bit frequency, the fault type corresponding to this flag bit is determined to be a transient fault; the determination results of steady-state faults, fluctuating faults and transient faults and timestamp information are stored in the fault record database, and the fault feature vector matrix is ​​updated in real time, and the timestamp information when updated is recorded.

[0017] As a preferred solution of the fault identification method of the line-type alarm controller of the present invention, before establishing the fault feature vector matrix, the working state of each alarm circuit shall be judged by adopting the preset threshold method; the method for judging the working state of each alarm circuit is to perform data smoothing processing on the current data and voltage data, and eliminate data jitter by the sliding average method to obtain the smoothed current average value and voltage average value; the current average value and the voltage average value are judged with the corresponding thresholds respectively, when the current average value is greater than the current upper limit threshold or less than the current lower limit threshold, the alarm circuit is marked as a current abnormal state; when the voltage average value is greater than the voltage upper limit threshold or less than the voltage lower limit threshold, the alarm circuit is marked as a voltage abnormal state, and the duration of the current average value and the voltage average value exceeding the corresponding threshold is recorded at the same time; if the duration of the exceeding time is greater than the preset time, the corresponding abnormal state is marked as a continuous fault; if the duration of the exceeding time is less than or equal to the preset time, the corresponding abnormal state is marked as a transient fault; for the alarm circuit of the continuous fault, the percentage of the current average value and the voltage average value deviating from the corresponding threshold is calculated, and this percentage is stored in the fault feature database as a fault degree parameter.

[0018] As a preferred scheme of the fault identification method of the split-line alarm controller of the present invention, wherein: the preset threshold method is used to judge the working state of each alarm circuit based on the current data and voltage data; the method for obtaining the current data and voltage data is to convert the working current value and the working voltage value into digital signals through an analog-to-digital conversion circuit; the analog-to-digital conversion circuit includes a signal conditioning circuit, a sampling and holding circuit and an analog-to-digital conversion chip; the signal conditioning circuit is used to amplify and filter the working current value and the working voltage value; the sampling and holding circuit is used to sample and hold the analog signal processed by the signal conditioning circuit; the analog-to-digital conversion chip converts the analog signal output by the sampling and holding circuit into a digital signal to obtain current data and voltage data; the current data and voltage data are respectively stored in the first data cache area and the second data cache area.

[0019] In a second aspect, an embodiment of the present invention provides a fault identification system for a split-line alarm controller, which includes: an acquisition module, used to acquire the working current value and the working voltage value of each alarm circuit in the split-line alarm controller, and convert the working current value and the working voltage value into digital signals to obtain current data and voltage data; a judgment module, based on the current data and voltage data, using a preset threshold method to judge the working state of each alarm circuit, wherein the preset threshold includes an upper current threshold, a lower current threshold, an upper voltage threshold and a lower voltage threshold; a construction module, used to establish a fault feature vector matrix according to the working state, wherein the fault feature vector matrix contains the current abnormality flag bit and the voltage abnormality flag bit of each alarm circuit; a fault diagnosis module, used to input the fault feature vector matrix into a pre-trained fault diagnosis model, the fault diagnosis model analyzes the fault feature vector matrix through a deep learning algorithm, and outputs a fault type judgment result; a retrieval module, used to retrieve the corresponding processing plan from a pre-established fault processing database according to the fault type judgment result to complete fault identification.

[0020] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned fault identification method for the split-line alarm controller.

[0021] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned fault identification method for the split-line alarm controller is implemented.

[0022] The beneficial effects of the present invention are as follows: the present invention collects and digitally processes the current and voltage data of the alarm circuit, combines multi-dimensional threshold prediction and feature vector matrix construction, and provides high-quality structured input for fault diagnosis; uses deep learning algorithms to perform intelligent analysis of fault characteristics, which can identify complex fault modes and significantly improve the accuracy of fault diagnosis; and achieves intelligent matching of fault handling solutions through a pre-established fault handling database, thereby accelerating the fault response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0024] Figure 1 The present invention is a flow chart of a fault identification method for a split-line alarm controller.

[0025] Figure 2 The present invention is a schematic diagram of a split-line alarm controller and a fault identification method for the split-line alarm controller. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0028] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0029] Example 1

[0030] Reference Figure 1-2 , which is the first embodiment of the present invention, provides a fault identification method for a split-line alarm controller, comprising:

[0031] S1: Collect the working current value and working voltage value of each alarm circuit in the split-line alarm controller, convert the working current value and working voltage value into digital signals, and obtain current data and voltage data.

[0032] Specifically, the working current value is collected through the sampling resistor set in each alarm circuit; the working voltage value is collected through the voltage divider circuit; the sampling resistor is connected in series in the alarm circuit; the voltage divider circuit is connected in parallel in the alarm circuit; the digital signal conversion method is to convert the working current value and the working voltage value into digital signals through a high-precision analog-to-digital conversion circuit.

[0033] It should be noted that the split-line alarm controller includes a power module, a main controller module, a communication module, a loop interface module, an operation module, a display module and an alarm output module.

[0034] Furthermore, the sampling frequency of the analog-to-digital conversion circuit is 10kHz and the resolution is 12 bits, wherein the analog-to-digital conversion circuit includes a signal conditioning circuit, a sampling and holding circuit and an analog-to-digital conversion chip, the signal conditioning circuit is used to amplify and filter the working current value and the working voltage value, the sampling and holding circuit is used to sample and hold the signal processed by the signal conditioning circuit, and the analog-to-digital conversion chip converts the analog signal output by the sampling and holding circuit into a digital signal to obtain current data and voltage data; the sampling time of the current data and the voltage data is 1 minute, the sampling interval is 100 microseconds, and the current data and the voltage data are respectively stored in the first data cache area and the second data cache area.

[0035] Furthermore, in the signal conditioning circuit, the working current value is obtained by obtaining a voltage drop through a sampling resistor, the resistance of the sampling resistor is 0.1 ohm, the accuracy is 0.1%, and the temperature coefficient is less than 25ppm / ℃. The working voltage value is obtained by obtaining a sampling voltage through a 100:1 high-precision resistor voltage divider network, and the overall accuracy of the voltage divider network is better than 0.05%; the voltage drop and the sampling voltage are respectively amplified by an operational amplifier, the gain of the operational amplifier is 10 times, the bandwidth is 1MHz, and at the same time, it is filtered through a second-order Butterworth low-pass filter, and the cut-off frequency of the low-pass filter is 5kHz; in the sample-and-hold circuit In the analog-to-digital conversion chip, the conditioned signal is sampled through a sampling and holding circuit. The sampling time of the sampling and holding circuit is 1 microsecond, and the holding time is 9 microseconds, forming a sampling period of 10 microseconds. The output signal of the sampling and holding circuit is sent to a 12-bit successive approximation analog-to-digital converter. The reference voltage of the analog-to-digital converter is 2.5V, and the conversion time is 8 microseconds. The analog-to-digital converter quantizes the analog signal into a digital range value of 0-4095. The converted digital signal is transmitted to the microprocessor through the SPI bus. The microprocessor performs linear correction on the digital signal to obtain corrected current data and voltage data.

[0036] S2: Based on the current data and voltage data, a preset threshold method is used to determine the working status of each alarm circuit.

[0037] Specifically, the upper current threshold is set to 150% of the rated working current of the alarm circuit; the lower current threshold is set to 50% of the rated working current of the alarm circuit; the upper voltage threshold is set to 120% of the rated working voltage of the alarm circuit; and the lower voltage threshold is set to 80% of the rated working voltage of the alarm circuit.

[0038] Furthermore, the method for judging the working status of each alarm circuit is to perform data smoothing on the current data and voltage data, and eliminate data jitter by a sliding average method to obtain smoothed current average values ​​and voltage average values; the current average values ​​and voltage average values ​​are judged against corresponding thresholds respectively; for alarm circuits with persistent faults, the percentage of deviation of the current average values ​​and the voltage average values ​​from the corresponding threshold values ​​is calculated, and this percentage is stored as a fault degree parameter in a fault feature database.

[0039] Furthermore, when the current average value is greater than the current upper threshold or less than the current lower threshold, the alarm circuit is marked as a current abnormal state; when the voltage average value is greater than the voltage upper threshold or less than the voltage lower threshold, the alarm circuit is marked as a voltage abnormal state, and the duration of the current average value and the voltage average value exceeding the corresponding threshold is recorded; if the duration of the excess time is greater than the preset time, the corresponding abnormal state is marked as a continuous fault; if the duration of the excess time is less than or equal to the preset time, the corresponding abnormal state is marked as a transient fault.

[0040] S3: Establishing a fault characteristic vector matrix according to the working state, wherein the fault characteristic vector matrix includes current abnormality flag bits and voltage abnormality flag bits of each alarm circuit.

[0041] Specifically, the construction process of the fault feature vector matrix includes the following steps: using an N×M two-dimensional array structure to establish a fault feature vector matrix, where N is the total number of alarm loops and M is the number of feature bits of each alarm loop; performing statistical analysis on the flag bits in the fault feature vector matrix, and calculating the setting frequency of each flag bit of each alarm loop in a continuous sampling period. The specific formula is as follows:

[0042]

[0043] w i =e -λ(t-i)

[0044] Where F(t) is the frequency of the flag bit at the current sampling point t, n is the sampling window length, b i is the flag value of the i-th sampling point in the window, w i is the time weight coefficient of the i-th sampling point in the window, λ is the time attenuation factor, t is the current sampling point, and i is the sampling point in the window.

[0045] Furthermore, when the setting frequency of a certain flag bit exceeds 80% of the preset bit frequency, the fault type corresponding to this flag bit is determined as a steady-state fault; when the setting frequency of a certain flag bit is between 20% and 80% of the preset bit frequency, the fault type corresponding to this flag bit is determined as a fluctuating fault; when the setting frequency of a certain flag bit is less than 20% of the preset bit frequency, the fault type corresponding to this flag bit is determined as a transient fault.

[0046] Furthermore, the determination results and timestamp information of steady-state faults, fluctuation faults and transient faults are stored in a fault record database, and the fault feature vector matrix is ​​updated in real time, recording the timestamp information when updated.

[0047] Specifically, in the fault characteristic vector matrix, each row of data corresponds to the characteristic data of an alarm circuit. The first bit of each row of data is the current overload flag, which is set to 1 when the alarm circuit is in a current overload state, otherwise it is set to 0; the second bit is the current open circuit flag, which is set to 1 when the alarm circuit is in a current open circuit state, otherwise it is set to 0; the third bit is the voltage overvoltage flag, which is set to 1 when the alarm circuit is in a voltage overvoltage state, otherwise it is set to 0; the fourth bit is the voltage undervoltage flag, which is set to 1 when the alarm circuit is in a voltage undervoltage state, otherwise it is set to 0.

[0048] S4: Input the fault feature vector matrix into a pre-trained fault diagnosis model. The fault diagnosis model analyzes the fault feature vector matrix through a deep learning algorithm and outputs a fault type judgment result.

[0049] Specifically, the fault diagnosis model adopts a five-layer neural network structure, including an input layer, a hidden layer and an output layer; the number of nodes in the input layer matches the characteristic data of the fault feature vector matrix and is fixed to 4×N nodes, where N is the total number of alarm loops; the hidden layer contains a number of neurons, where the neurons use the ReLU activation function and the residual connection structure is used between neurons to avoid gradient disappearance; the output layer contains 8 nodes, corresponding to 8 working states: short circuit fault, open circuit fault, insulation aging, poor contact, load abnormality, power supply fault, communication fault and normal operation;

[0050] Furthermore, the fault diagnosis model was trained with 50,000 sets of labeled historical fault data during the training phase, and the Adam optimizer was used for parameter optimization. The initial value of the learning rate was set to 0.001, and the learning rate was reduced by 50% every 1,000 training rounds. The batch size was set to 64, and a random inactivation strategy with a dropout rate of 0.3 was used during the training process to prevent overfitting.

[0051] Furthermore, the fault diagnosis model performs forward calculations on the data segments, and the output layer calculates the probability distribution of various fault types through the softmax function, and takes the category with the highest probability as the fault type judgment result of this data segment; the judgment results of more than p consecutive data segments are voted and counted to obtain the final fault type judgment result, and the probability values ​​of various fault types are recorded as credibility indicators of fault judgment.

[0052] Specifically, the method for obtaining the data segments is to normalize the fault feature vector matrix and use the min-max method to map the data to the [0,1] interval; divide the normalized data into data segments of length 10 according to the time series, set the overlap rate between each data segment, and input them into the fault diagnosis model in sequence through a sliding window method.

[0053] S5: According to the fault type judgment result, a corresponding processing solution is retrieved from a pre-established fault processing database, and the fault location and fault type are displayed on the controller display screen.

[0054] Specifically, the fault processing database adopts a relational database structure, which includes three main data tables: fault type table, processing plan table and fault record table; the fault type table stores fault code, fault type name, fault level and fault description; the processing plan table stores processing steps, required tools, precautions and estimated repair time; the fault record table stores fault occurrence time, fault duration, fault location and processing results;

[0055] Furthermore, after obtaining the fault type judgment result, the system retrieves the corresponding record in the fault type table according to the fault type code to obtain the fault level information; when the fault level is an emergency level, the system automatically starts the sound and light alarm, and sends a text message reminder to the preset maintenance personnel's mobile phone; the system retrieves the corresponding processing plan from the processing plan table, organizes the processing plan content according to the preset format, and sends it to the controller display screen.

[0056] Furthermore, the present embodiment also provides a fault identification system for a split-line alarm controller, including: an acquisition module, used to acquire the working current value and the working voltage value of each alarm circuit in the split-line alarm controller, and convert the working current value and the working voltage value into digital signals to obtain current data and voltage data; a judgment module, based on the current data and voltage data, using a preset threshold method to judge the working state of each alarm circuit, wherein the preset threshold includes an upper current threshold, a lower current threshold, an upper voltage threshold and a lower voltage threshold; a construction module, used to establish a fault feature vector matrix according to the working state, wherein the fault feature vector matrix contains the current abnormality flag bit and the voltage abnormality flag bit of each alarm circuit; a fault diagnosis module, used to input the fault feature vector matrix into a pre-trained fault diagnosis model, and the fault diagnosis model analyzes the fault feature vector matrix through a deep learning algorithm and outputs a fault type judgment result; a retrieval module, used to retrieve the corresponding processing plan from a pre-established fault processing database according to the fault type judgment result to complete fault identification.

[0057] This embodiment also provides a computer device, which is suitable for the fault identification method of the divided-line alarm controller, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the fault identification method of the divided-line alarm controller proposed in the above embodiment.

[0058] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0059] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the fault identification method for the split-line alarm controller proposed in the above embodiment is implemented.

[0060] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0061] Example 2

[0062] Referring to Table 1, which is the second embodiment of the present invention, this embodiment provides a fault identification method for a split-line alarm controller. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0063] Specifically, the fire automatic alarm system of a large commercial complex was selected as the test object. The complex has 12 fire zones, each zone is equipped with a split-line alarm controller, each controller is connected to 8 alarm loops, and the number of fire detectors configured on each loop ranges from 20 to 35. The test process uses a split-line alarm controller model FCP-9000, which has a 16-bit high-precision analog-to-digital converter and a sampling frequency of 1kHz. The experimental test lasted for 30 days, during which the system response data under various fault conditions were simulated and recorded.

[0064] Furthermore, in the data acquisition stage, high-precision current probes and voltage probes are used to collect the working current and voltage signals of each alarm circuit respectively. The measurement range of the current probe is 0-500mA with an accuracy of ±0.1%; the measurement range of the voltage probe is 0-30V with an accuracy of ±0.05%. The collected analog signal is amplified and filtered by the signal conditioning circuit, and then converted into a digital signal by a 16-bit ADC, and the sampling rate is set to 1kHz. The warning threshold parameters set by the system are: current upper limit threshold 500mA, current lower limit threshold 5mA, voltage upper limit threshold 28V, and voltage lower limit threshold 20V.

[0065] Furthermore, after normalizing the collected data, the sliding window method is used to divide the data into data segments of length 10, and the overlap rate of adjacent data segments is set to 50%. The fault feature vector matrix adopts a 96×4 two-dimensional array structure (12 controllers×8 loops=96 rows, 4 feature bits=4 columns). The deep learning model adopts a 5-layer fully connected neural network structure, uses the Adam optimizer, the learning rate is set to 0.001, the batch size is 64, and the number of training rounds is 100. The fault type is determined by the voting statistics method of 5 consecutive data segments, and the confidence threshold is set to 0.85.

[0066] Specifically, as shown in Table 1, according to the analysis of the table data, during the 30-day continuous monitoring process, the test results for 6 typical fire partitions showed that the system has excellent performance. In terms of the number of detectors configured, the number of detectors in each fire partition is distributed between 156 and 182, of which the FD-A04 partition has the most, reaching 182, and the FD-A03 partition has the least, at 156. This distribution difference is mainly the result of reasonable configuration based on the spatial characteristics and fire protection needs of each area. In terms of fault identification performance, the system shows extremely high accuracy, and the fault identification accuracy of the 6 partitions is maintained at more than 98.8%. Among them, the FD-A04 partition performs the best, with an accuracy of 99.3%, which is mainly due to the use of high-precision data acquisition equipment and the optimization of deep learning algorithms.

[0067] Table 1 Test data table

[0068]

[0069] Furthermore, from the perspective of system response performance, the fault response time of each partition is controlled within the range of 355-365ms, which is significantly better than the second-level response speed of the traditional system. Among them, the FD-A03 partition achieved the fastest response time of 355ms due to the relatively small number of detectors. In terms of system reliability, the availability indicators of all partitions remained above 99.92%, which fully demonstrated the stability of the system. It is particularly noteworthy that the false alarm rate of the system is controlled at a low level, with a minimum of 0.14% (FD-A04 partition) and a maximum of 0.19% (FD-B01 partition). This low false alarm rate feature is of great significance for reducing system operation and maintenance costs and improving alarm credibility.

[0070] Furthermore, through statistical analysis of the frequency of faults, it was found that during the 30-day test period, the number of faults recorded in each partition was between 36 and 45 times, with an average of about 1.3 fault warnings per partition per day. Among them, the FD-A03 partition recorded the most faults, reaching 45 times, while the FD-B01 partition recorded the least, at 36 times. This fault distribution pattern is consistent with the actual operation of large commercial complexes, indicating that the system can effectively identify and record various types of fault conditions. From the above data, it can be seen that the system has shown good performance indicators in terms of fault identification accuracy, response timeliness and operational reliability, which fully meets the actual application needs and has significant application promotion value.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A fault identification method for a split-line alarm controller, characterized in that: include, Collecting the working current value and working voltage value of each alarm circuit in the split-line alarm controller, converting the working current value and working voltage value into digital signals to obtain current data and voltage data; Based on the current data and voltage data, a preset threshold method is used to judge the working state of each alarm circuit, wherein the preset thresholds include an upper current threshold, a lower current threshold, an upper voltage threshold, and a lower voltage threshold; According to the working state, a fault characteristic vector matrix is ​​established, wherein the fault characteristic vector matrix includes current abnormality flag bits and voltage abnormality flag bits of each alarm circuit; The fault feature vector matrix is ​​input into a pre-trained fault diagnosis model, and the fault diagnosis model analyzes the fault feature vector matrix through a deep learning algorithm and outputs a fault type judgment result; According to the fault type judgment result, the corresponding processing solution is retrieved from a pre-established fault processing database to complete the fault identification.

2. The fault identification method of the split-line alarm controller according to claim 1, characterized in that: The fault diagnosis model performs forward calculation on the data segment, and the output layer calculates the probability distribution of various fault types through the softmax function, and takes the category with the highest probability as the fault type judgment result of this data segment; The judgment results of more than p consecutive data segments are voted and counted to obtain the final fault type judgment result, and the probability values ​​of various fault types are recorded as the credibility indicators of fault judgment.

3. The fault identification method of the split-line alarm controller according to claim 2, characterized in that: The method for obtaining the data fragment is: After normalizing the fault feature vector matrix, the min-max method is used to map the data to the [0,1] interval; The normalized data is divided into data segments of length 10 according to the time series, the overlap rate between each data segment is set, and the data are input into the fault diagnosis model in sequence through the sliding window method.

4. The fault identification method of the split-line alarm controller as claimed in claim 3, characterized in that: The construction process of the fault feature vector matrix includes the following steps: The fault feature vector matrix is ​​established using an N×M two-dimensional array structure, where N is the total number of alarm loops and M is the number of feature bits for each alarm loop; In the fault characteristic vector matrix, each row of data corresponds to the characteristic data of an alarm circuit. The first bit of each row of data is the current overload flag bit, which is set to 1 when the alarm circuit is in a current overload state, otherwise it is set to 0; the second bit is the current open circuit flag bit, which is set to 1 when the alarm circuit is in a current open circuit state, otherwise it is set to 0; the third bit is the voltage overvoltage flag bit, which is set to 1 when the alarm circuit is in a voltage overvoltage state, otherwise it is set to 0; the fourth bit is the voltage undervoltage flag bit, which is set to 1 when the alarm circuit is in a voltage undervoltage state, otherwise it is set to 0.

5. The fault identification method of the split-line alarm controller according to claim 4, characterized in that: Also includes, Perform statistical analysis on the flag bits in the fault feature vector matrix and calculate the setting frequency of each flag bit in each alarm loop within a continuous sampling period. The specific formula is as follows: w i =e -λ ( t-i) Among them, F(t) is the frequency of the flag position at the current sampling point t, n is the sampling window length, b i is the flag value of the i-th sampling point in the window, w i is the time weight coefficient of the i-th sampling point in the window, λ is the time attenuation factor, t is the current sampling point, and i is the sampling point in the window; When the setting frequency of a certain flag bit exceeds 80% of the preset bit frequency, the fault type corresponding to this flag bit is determined as a steady-state fault; when the setting frequency of a certain flag bit is between 20% and 80% of the preset bit frequency, the fault type corresponding to this flag bit is determined as a fluctuation fault; when the setting frequency of a certain flag bit is less than 20% of the preset bit frequency, the fault type corresponding to this flag bit is determined as a transient fault; The determination results and timestamp information of steady-state faults, fluctuation faults and transient faults are stored in the fault record database, and the fault feature vector matrix is ​​updated in real time, recording the timestamp information when updated.

6. The fault identification method of the split-line alarm controller according to claim 5, characterized in that: Before establishing the fault feature vector matrix, the working state of each alarm circuit must be determined by using a preset threshold method; the method for determining the working state of each alarm circuit is: Performing data smoothing on the current data and the voltage data, and eliminating data jitter by a sliding average method, to obtain smoothed current average values ​​and voltage average values; The current average value and the voltage average value are judged against the corresponding thresholds respectively. When the current average value is greater than the current upper threshold or less than the current lower threshold, the alarm circuit is marked as a current abnormal state. When the voltage average value is greater than the voltage upper threshold or less than the voltage lower threshold, the alarm circuit is marked as voltage abnormal state, and the duration of the current average value and the voltage average value exceeding the corresponding threshold is recorded; If the duration of the exceeding time is longer than the preset time, the corresponding abnormal state is marked as a persistent fault; if the duration of the exceeding time is less than or equal to the preset time, the corresponding abnormal state is marked as a transient fault; For the alarm circuit of a persistent fault, the percentage of the average current and average voltage deviation from the corresponding threshold is calculated, and this percentage is stored in the fault feature database as a fault degree parameter.

7. The fault identification method of the split-line alarm controller according to claim 6, characterized in that: The preset threshold method is used to judge the working state of each alarm circuit based on the current data and voltage data; the method for obtaining the current data and voltage data is: The working current value and the working voltage value are converted into digital signals through an analog-to-digital conversion circuit; the analog-to-digital conversion circuit includes a signal conditioning circuit, a sampling and holding circuit and an analog-to-digital conversion chip; the signal conditioning circuit is used to amplify and filter the working current value and the working voltage value; the sampling and holding circuit is used to sample and hold the analog signal processed by the signal conditioning circuit; the analog-to-digital conversion chip converts the analog signal output by the sampling and holding circuit into a digital signal to obtain current data and voltage data; the current data and voltage data are respectively stored in a first data buffer area and a second data buffer area.

8. A fault identification system for a split-line alarm controller, based on a fault identification method for a split-line alarm controller according to any one of claims 1 to 7, characterized in that: include, The acquisition module is used to acquire the working current value and the working voltage value of each alarm circuit in the split-line alarm controller, convert the working current value and the working voltage value into digital signals, and obtain current data and voltage data; A judgment module, based on the current data and the voltage data, uses a preset threshold method to judge the working state of each alarm circuit, wherein the preset thresholds include a current upper limit threshold, a current lower limit threshold, a voltage upper limit threshold, and a voltage lower limit threshold; A construction module, used to establish a fault characteristic vector matrix according to the working state, wherein the fault characteristic vector matrix includes a current abnormality flag bit and a voltage abnormality flag bit of each alarm circuit; A fault diagnosis module, used for inputting the fault feature vector matrix into a pre-trained fault diagnosis model, wherein the fault diagnosis model analyzes the fault feature vector matrix through a deep learning algorithm and outputs a fault type judgment result; The retrieval module is used to retrieve the corresponding processing solution from a pre-established fault processing database according to the fault type judgment result to complete fault identification.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the fault identification method of the split-line alarm controller of any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fault identification method of the split-line alarm controller of any one of claims 1 to 7 are implemented.

Images